| checkpoints: |
| ckpt_best.pth.tar: |
| checkpoint_name: ckpt_best.pth.tar |
| checkpoint_path: /home/molfetta/combinatorial_reasoning_post_training/models/main5_hf_bot_mode_recovery_50k_20260522/simplified__first_attack/attempt-01_260522_170112/ckpt/ckpt_best.pth.tar |
| saved_at: '2026-05-22T15:15:49.523597+00:00' |
| train_iter: 3650 |
| envstep: 10023 |
| trigger: null |
| latest_scalars: |
| evaluator_iter/episode_count: |
| value: 20 |
| step: 0 |
| walltime: null |
| evaluator_step/episode_count: |
| value: 20 |
| step: 0 |
| walltime: null |
| evaluator_iter/envstep_count: |
| value: 90 |
| step: 0 |
| walltime: null |
| evaluator_step/envstep_count: |
| value: 90 |
| step: 0 |
| walltime: null |
| evaluator_iter/avg_envstep_per_episode: |
| value: 4.5 |
| step: 0 |
| walltime: null |
| evaluator_step/avg_envstep_per_episode: |
| value: 4.5 |
| step: 0 |
| walltime: null |
| evaluator_iter/evaluate_time: |
| value: 2.57061328125 |
| step: 0 |
| walltime: null |
| evaluator_step/evaluate_time: |
| value: 2.57061328125 |
| step: 0 |
| walltime: null |
| evaluator_iter/avg_envstep_per_sec: |
| value: 35.011100524710635 |
| step: 0 |
| walltime: null |
| evaluator_step/avg_envstep_per_sec: |
| value: 35.011100524710635 |
| step: 0 |
| walltime: null |
| evaluator_iter/avg_time_per_episode: |
| value: 7.780244561046808 |
| step: 0 |
| walltime: null |
| evaluator_step/avg_time_per_episode: |
| value: 7.780244561046808 |
| step: 0 |
| walltime: null |
| evaluator_iter/reward_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_step/reward_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/reward_std: |
| value: 0.0 |
| step: 0 |
| walltime: null |
| evaluator_step/reward_std: |
| value: 0.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/reward_max: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_step/reward_max: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/reward_min: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_step/reward_min: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/seat_swap: |
| value: true |
| step: 0 |
| walltime: null |
| evaluator_step/seat_swap: |
| value: true |
| step: 0 |
| walltime: null |
| evaluator_iter/seat1_episode_count: |
| value: 10 |
| step: 0 |
| walltime: null |
| evaluator_step/seat1_episode_count: |
| value: 10 |
| step: 0 |
| walltime: null |
| evaluator_iter/seat2_episode_count: |
| value: 10 |
| step: 0 |
| walltime: null |
| evaluator_step/seat2_episode_count: |
| value: 10 |
| step: 0 |
| walltime: null |
| evaluator_iter/seat1_reward_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_step/seat1_reward_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/seat2_reward_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_step/seat2_reward_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/eval_episode_return_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_step/eval_episode_return_mean: |
| value: -1.0 |
| step: 0 |
| walltime: null |
| evaluator_iter/live_policy_seat_mean: |
| value: 1.5 |
| step: 0 |
| walltime: null |
| evaluator_step/live_policy_seat_mean: |
| value: 1.5 |
| step: 0 |
| walltime: null |
| Buffer/Task_0/num_collected_episodes: |
| value: 4768 |
| step: 3650 |
| walltime: null |
| Buffer/Task_0/num_game_segments: |
| value: 4768 |
| step: 3650 |
| walltime: null |
| Buffer/Task_0/num_transitions: |
| value: 10023 |
| step: 3650 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/game_segment_buffer: |
| value: 16.035552978515625 |
| step: 3650 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/process: |
| value: 2206.61328125 |
| step: 3650 |
| walltime: null |
| learner_iter/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 3600 |
| walltime: null |
| learner_step/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 9955 |
| walltime: null |
| learner_iter/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 3600 |
| walltime: null |
| learner_step/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 9955 |
| walltime: null |
| learner_iter/weighted_total_loss_avg: |
| value: 3.0139227997172964 |
| step: 3600 |
| walltime: null |
| learner_step/weighted_total_loss_avg: |
| value: 3.0139227997172964 |
| step: 9955 |
| walltime: null |
| learner_iter/total_loss_avg: |
| value: 3.0139227997172964 |
| step: 3600 |
| walltime: null |
| learner_step/total_loss_avg: |
| value: 3.0139227997172964 |
| step: 9955 |
| walltime: null |
| learner_iter/policy_loss_avg: |
| value: 3.7389746579256924 |
| step: 3600 |
| walltime: null |
| learner_step/policy_loss_avg: |
| value: 3.7389746579256924 |
| step: 9955 |
| walltime: null |
| learner_iter/policy_entropy_avg: |
| value: 1.9136938470782654 |
| step: 3600 |
| walltime: null |
| learner_step/policy_entropy_avg: |
| value: 1.9136938470782654 |
| step: 9955 |
| walltime: null |
| learner_iter/target_policy_entropy_avg: |
| value: 2.3717358040087153 |
| step: 3600 |
| walltime: null |
| learner_step/target_policy_entropy_avg: |
| value: 2.3717358040087153 |
| step: 9955 |
| walltime: null |
| learner_iter/value_prefix_loss_avg: |
| value: 3.0078010992570356 |
| step: 3600 |
| walltime: null |
| learner_step/value_prefix_loss_avg: |
| value: 3.0078010992570356 |
| step: 9955 |
| walltime: null |
| learner_iter/value_loss_avg: |
| value: 1.6353803656317971 |
| step: 3600 |
| walltime: null |
| learner_step/value_loss_avg: |
| value: 1.6353803656317971 |
| step: 9955 |
| walltime: null |
| learner_iter/consistency_loss_avg: |
| value: -0.41416979703036216 |
| step: 3600 |
| walltime: null |
| learner_step/consistency_loss_avg: |
| value: -0.41416979703036216 |
| step: 9955 |
| walltime: null |
| learner_iter/value_priority_avg: |
| value: 0.5120764618570154 |
| step: 3600 |
| walltime: null |
| learner_step/value_priority_avg: |
| value: 0.5120764618570154 |
| step: 9955 |
| walltime: null |
| learner_iter/target_value_prefix_avg: |
| value: -0.32788826389746234 |
| step: 3600 |
| walltime: null |
| learner_step/target_value_prefix_avg: |
| value: -0.32788826389746234 |
| step: 9955 |
| walltime: null |
| learner_iter/target_value_avg: |
| value: -0.16264205087314954 |
| step: 3600 |
| walltime: null |
| learner_step/target_value_avg: |
| value: -0.16264205087314954 |
| step: 9955 |
| walltime: null |
| learner_iter/predicted_value_prefixs_avg: |
| value: -0.35477335344661365 |
| step: 3600 |
| walltime: null |
| learner_step/predicted_value_prefixs_avg: |
| value: -0.35477335344661365 |
| step: 9955 |
| walltime: null |
| learner_iter/predicted_values_avg: |
| value: -0.16285475411198355 |
| step: 3600 |
| walltime: null |
| learner_step/predicted_values_avg: |
| value: -0.16285475411198355 |
| step: 9955 |
| walltime: null |
| learner_iter/transformed_target_value_prefix_avg: |
| value: -0.13614363900639795 |
| step: 3600 |
| walltime: null |
| learner_step/transformed_target_value_prefix_avg: |
| value: -0.13614363900639795 |
| step: 9955 |
| walltime: null |
| learner_iter/transformed_target_value_avg: |
| value: -0.06753117828206583 |
| step: 3600 |
| walltime: null |
| learner_step/transformed_target_value_avg: |
| value: -0.06753117828206583 |
| step: 9955 |
| walltime: null |
| learner_iter/total_grad_norm_before_clip_avg: |
| value: 0.1326096308502284 |
| step: 3600 |
| walltime: null |
| learner_step/total_grad_norm_before_clip_avg: |
| value: 0.1326096308502284 |
| step: 9955 |
| walltime: null |
| collector_iter/episode_count: |
| value: 128 |
| step: 3600 |
| walltime: null |
| collector_step/episode_count: |
| value: 128 |
| step: 9955 |
| walltime: null |
| collector_iter/envstep_count: |
| value: 270 |
| step: 3600 |
| walltime: null |
| collector_step/envstep_count: |
| value: 270 |
| step: 9955 |
| walltime: null |
| collector_iter/avg_envstep_per_episode: |
| value: 2.109375 |
| step: 3600 |
| walltime: null |
| collector_step/avg_envstep_per_episode: |
| value: 2.109375 |
| step: 9955 |
| walltime: null |
| collector_iter/avg_envstep_per_sec: |
| value: 35.258120969017575 |
| step: 3600 |
| walltime: null |
| collector_step/avg_envstep_per_sec: |
| value: 35.258120969017575 |
| step: 9955 |
| walltime: null |
| collector_iter/avg_episode_per_sec: |
| value: 16.7149610519787 |
| step: 3600 |
| walltime: null |
| collector_step/avg_episode_per_sec: |
| value: 16.7149610519787 |
| step: 9955 |
| walltime: null |
| collector_iter/collect_time: |
| value: 7.657810245680918 |
| step: 3600 |
| walltime: null |
| collector_step/collect_time: |
| value: 7.657810245680918 |
| step: 9955 |
| walltime: null |
| collector_iter/reward_mean: |
| value: -0.46875 |
| step: 3600 |
| walltime: null |
| collector_step/reward_mean: |
| value: -0.46875 |
| step: 9955 |
| walltime: null |
| collector_iter/reward_std: |
| value: 0.8833308765689106 |
| step: 3600 |
| walltime: null |
| collector_step/reward_std: |
| value: 0.8833308765689106 |
| step: 9955 |
| walltime: null |
| collector_iter/reward_max: |
| value: 1.0 |
| step: 3600 |
| walltime: null |
| collector_step/reward_max: |
| value: 1.0 |
| step: 9955 |
| walltime: null |
| collector_iter/reward_min: |
| value: -1.0 |
| step: 3600 |
| walltime: null |
| collector_step/reward_min: |
| value: -1.0 |
| step: 9955 |
| walltime: null |
| collector_iter/total_envstep_count: |
| value: 9955 |
| step: 3600 |
| walltime: null |
| collector_step/total_envstep_count: |
| value: 9955 |
| step: 9955 |
| walltime: null |
| collector_iter/total_episode_count: |
| value: 4736 |
| step: 3600 |
| walltime: null |
| collector_step/total_episode_count: |
| value: 4736 |
| step: 9955 |
| walltime: null |
| collector_iter/total_duration: |
| value: 439.8722621845222 |
| step: 3600 |
| walltime: null |
| collector_step/total_duration: |
| value: 439.8722621845222 |
| step: 9955 |
| walltime: null |
| collector_iter/visit_entropy_mean: |
| value: 1.9511570511956342 |
| step: 3600 |
| walltime: null |
| collector_step/visit_entropy_mean: |
| value: 1.9511570511956342 |
| step: 9955 |
| walltime: null |
| collector_iter/live_seat1_episode_count: |
| value: 32 |
| step: 3600 |
| walltime: null |
| collector_step/live_seat1_episode_count: |
| value: 32 |
| step: 9955 |
| walltime: null |
| collector_iter/live_seat1_reward_mean: |
| value: -0.125 |
| step: 3600 |
| walltime: null |
| collector_step/live_seat1_reward_mean: |
| value: -0.125 |
| step: 9955 |
| walltime: null |
| collector_iter/live_seat2_episode_count: |
| value: 96 |
| step: 3600 |
| walltime: null |
| collector_step/live_seat2_episode_count: |
| value: 96 |
| step: 9955 |
| walltime: null |
| collector_iter/live_seat2_reward_mean: |
| value: -0.5833333333333334 |
| step: 3600 |
| walltime: null |
| collector_step/live_seat2_reward_mean: |
| value: -0.5833333333333334 |
| step: 9955 |
| walltime: null |
| envstep_140000.pth.tar: |
| checkpoint_name: envstep_140000.pth.tar |
| checkpoint_path: /home/molfetta/combinatorial_reasoning_post_training/models/main5_hf_bot_mode_recovery_50k_20260522/simplified__first_attack/attempt-01_260522_170112/ckpt/envstep_140000.pth.tar |
| saved_at: '2026-05-22T19:05:45.370754+00:00' |
| train_iter: 51600 |
| envstep: 140000 |
| trigger: envstep |
| latest_scalars: |
| evaluator_iter/episode_count: |
| value: 20 |
| step: 47950 |
| walltime: null |
| evaluator_step/episode_count: |
| value: 20 |
| step: 130067 |
| walltime: null |
| evaluator_iter/envstep_count: |
| value: 90 |
| step: 47950 |
| walltime: null |
| evaluator_step/envstep_count: |
| value: 90 |
| step: 130067 |
| walltime: null |
| evaluator_iter/avg_envstep_per_episode: |
| value: 4.5 |
| step: 47950 |
| walltime: null |
| evaluator_step/avg_envstep_per_episode: |
| value: 4.5 |
| step: 130067 |
| walltime: null |
| evaluator_iter/evaluate_time: |
| value: 1.1295750732421874 |
| step: 47950 |
| walltime: null |
| evaluator_step/evaluate_time: |
| value: 1.1295750732421874 |
| step: 130067 |
| walltime: null |
| evaluator_iter/avg_envstep_per_sec: |
| value: 79.67597916416086 |
| step: 47950 |
| walltime: null |
| evaluator_step/avg_envstep_per_sec: |
| value: 79.67597916416086 |
| step: 130067 |
| walltime: null |
| evaluator_iter/avg_time_per_episode: |
| value: 17.7057731475913 |
| step: 47950 |
| walltime: null |
| evaluator_step/avg_time_per_episode: |
| value: 17.7057731475913 |
| step: 130067 |
| walltime: null |
| evaluator_iter/reward_mean: |
| value: -1.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/reward_mean: |
| value: -1.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/reward_std: |
| value: 0.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/reward_std: |
| value: 0.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/reward_max: |
| value: -1.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/reward_max: |
| value: -1.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/reward_min: |
| value: -1.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/reward_min: |
| value: -1.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/seat_swap: |
| value: true |
| step: 47950 |
| walltime: null |
| evaluator_step/seat_swap: |
| value: true |
| step: 130067 |
| walltime: null |
| evaluator_iter/seat1_episode_count: |
| value: 10 |
| step: 47950 |
| walltime: null |
| evaluator_step/seat1_episode_count: |
| value: 10 |
| step: 130067 |
| walltime: null |
| evaluator_iter/seat2_episode_count: |
| value: 10 |
| step: 47950 |
| walltime: null |
| evaluator_step/seat2_episode_count: |
| value: 10 |
| step: 130067 |
| walltime: null |
| evaluator_iter/seat1_reward_mean: |
| value: -1.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/seat1_reward_mean: |
| value: -1.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/seat2_reward_mean: |
| value: -1.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/seat2_reward_mean: |
| value: -1.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/eval_episode_return_mean: |
| value: -1.0 |
| step: 47950 |
| walltime: null |
| evaluator_step/eval_episode_return_mean: |
| value: -1.0 |
| step: 130067 |
| walltime: null |
| evaluator_iter/live_policy_seat_mean: |
| value: 1.5 |
| step: 47950 |
| walltime: null |
| evaluator_step/live_policy_seat_mean: |
| value: 1.5 |
| step: 130067 |
| walltime: null |
| Buffer/Task_0/num_collected_episodes: |
| value: 66144 |
| step: 51600 |
| walltime: null |
| Buffer/Task_0/num_game_segments: |
| value: 23590 |
| step: 51600 |
| walltime: null |
| Buffer/Task_0/num_transitions: |
| value: 49999 |
| step: 51600 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/game_segment_buffer: |
| value: 79.51673889160156 |
| step: 51600 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/process: |
| value: 2044.0234375 |
| step: 51600 |
| walltime: null |
| learner_iter/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 51500 |
| walltime: null |
| learner_step/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 139773 |
| walltime: null |
| learner_iter/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 51500 |
| walltime: null |
| learner_step/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 139773 |
| walltime: null |
| learner_iter/weighted_total_loss_avg: |
| value: 3.0222666480324487 |
| step: 51500 |
| walltime: null |
| learner_step/weighted_total_loss_avg: |
| value: 3.0222666480324487 |
| step: 139773 |
| walltime: null |
| learner_iter/total_loss_avg: |
| value: 3.0222666480324487 |
| step: 51500 |
| walltime: null |
| learner_step/total_loss_avg: |
| value: 3.0222666480324487 |
| step: 139773 |
| walltime: null |
| learner_iter/policy_loss_avg: |
| value: 3.733693903142756 |
| step: 51500 |
| walltime: null |
| learner_step/policy_loss_avg: |
| value: 3.733693903142756 |
| step: 139773 |
| walltime: null |
| learner_iter/policy_entropy_avg: |
| value: 1.898308956261837 |
| step: 51500 |
| walltime: null |
| learner_step/policy_entropy_avg: |
| value: 1.898308956261837 |
| step: 139773 |
| walltime: null |
| learner_iter/target_policy_entropy_avg: |
| value: 2.377243229837129 |
| step: 51500 |
| walltime: null |
| learner_step/target_policy_entropy_avg: |
| value: 2.377243229837129 |
| step: 139773 |
| walltime: null |
| learner_iter/value_prefix_loss_avg: |
| value: 3.026756850155917 |
| step: 51500 |
| walltime: null |
| learner_step/value_prefix_loss_avg: |
| value: 3.026756850155917 |
| step: 139773 |
| walltime: null |
| learner_iter/value_loss_avg: |
| value: 1.6892908811569214 |
| step: 51500 |
| walltime: null |
| learner_step/value_loss_avg: |
| value: 1.6892908811569214 |
| step: 139773 |
| walltime: null |
| learner_iter/consistency_loss_avg: |
| value: -0.41605067686601116 |
| step: 51500 |
| walltime: null |
| learner_step/consistency_loss_avg: |
| value: -0.41605067686601116 |
| step: 139773 |
| walltime: null |
| learner_iter/value_priority_avg: |
| value: 0.6531094637784091 |
| step: 51500 |
| walltime: null |
| learner_step/value_priority_avg: |
| value: 0.6531094637784091 |
| step: 139773 |
| walltime: null |
| learner_iter/target_value_prefix_avg: |
| value: -0.2559185705401681 |
| step: 51500 |
| walltime: null |
| learner_step/target_value_prefix_avg: |
| value: -0.2559185705401681 |
| step: 139773 |
| walltime: null |
| learner_iter/target_value_avg: |
| value: -0.12428977746855129 |
| step: 51500 |
| walltime: null |
| learner_step/target_value_avg: |
| value: -0.12428977746855129 |
| step: 139773 |
| walltime: null |
| learner_iter/predicted_value_prefixs_avg: |
| value: -0.27869279140775854 |
| step: 51500 |
| walltime: null |
| learner_step/predicted_value_prefixs_avg: |
| value: -0.27869279140775854 |
| step: 139773 |
| walltime: null |
| learner_iter/predicted_values_avg: |
| value: -0.11516526951031252 |
| step: 51500 |
| walltime: null |
| learner_step/predicted_values_avg: |
| value: -0.11516526951031252 |
| step: 139773 |
| walltime: null |
| learner_iter/transformed_target_value_prefix_avg: |
| value: -0.1062608456069773 |
| step: 51500 |
| walltime: null |
| learner_step/transformed_target_value_prefix_avg: |
| value: -0.1062608456069773 |
| step: 139773 |
| walltime: null |
| learner_iter/transformed_target_value_avg: |
| value: -0.051606794649904426 |
| step: 51500 |
| walltime: null |
| learner_step/transformed_target_value_avg: |
| value: -0.051606794649904426 |
| step: 139773 |
| walltime: null |
| learner_iter/total_grad_norm_before_clip_avg: |
| value: 0.10974988138133829 |
| step: 51500 |
| walltime: null |
| learner_step/total_grad_norm_before_clip_avg: |
| value: 0.10974988138133829 |
| step: 139773 |
| walltime: null |
| collector_iter/episode_count: |
| value: 128 |
| step: 51600 |
| walltime: null |
| collector_step/episode_count: |
| value: 128 |
| step: 140045 |
| walltime: null |
| collector_iter/envstep_count: |
| value: 272 |
| step: 51600 |
| walltime: null |
| collector_step/envstep_count: |
| value: 272 |
| step: 140045 |
| walltime: null |
| collector_iter/avg_envstep_per_episode: |
| value: 2.125 |
| step: 51600 |
| walltime: null |
| collector_step/avg_envstep_per_episode: |
| value: 2.125 |
| step: 140045 |
| walltime: null |
| collector_iter/avg_envstep_per_sec: |
| value: 70.84570636043641 |
| step: 51600 |
| walltime: null |
| collector_step/avg_envstep_per_sec: |
| value: 70.84570636043641 |
| step: 140045 |
| walltime: null |
| collector_iter/avg_episode_per_sec: |
| value: 33.33915593432302 |
| step: 51600 |
| walltime: null |
| collector_step/avg_episode_per_sec: |
| value: 33.33915593432302 |
| step: 140045 |
| walltime: null |
| collector_iter/collect_time: |
| value: 3.8393293535131954 |
| step: 51600 |
| walltime: null |
| collector_step/collect_time: |
| value: 3.8393293535131954 |
| step: 140045 |
| walltime: null |
| collector_iter/reward_mean: |
| value: -0.546875 |
| step: 51600 |
| walltime: null |
| collector_step/reward_mean: |
| value: -0.546875 |
| step: 140045 |
| walltime: null |
| collector_iter/reward_std: |
| value: 0.8372142702886759 |
| step: 51600 |
| walltime: null |
| collector_step/reward_std: |
| value: 0.8372142702886759 |
| step: 140045 |
| walltime: null |
| collector_iter/reward_max: |
| value: 1.0 |
| step: 51600 |
| walltime: null |
| collector_step/reward_max: |
| value: 1.0 |
| step: 140045 |
| walltime: null |
| collector_iter/reward_min: |
| value: -1.0 |
| step: 51600 |
| walltime: null |
| collector_step/reward_min: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| collector_iter/total_envstep_count: |
| value: 140045 |
| step: 51600 |
| walltime: null |
| collector_step/total_envstep_count: |
| value: 140045 |
| step: 140045 |
| walltime: null |
| collector_iter/total_episode_count: |
| value: 66176 |
| step: 51600 |
| walltime: null |
| collector_step/total_episode_count: |
| value: 66176 |
| step: 140045 |
| walltime: null |
| collector_iter/total_duration: |
| value: 5494.625854929663 |
| step: 51600 |
| walltime: null |
| collector_step/total_duration: |
| value: 5494.625854929663 |
| step: 140045 |
| walltime: null |
| collector_iter/visit_entropy_mean: |
| value: 2.0858158426240725 |
| step: 51600 |
| walltime: null |
| collector_step/visit_entropy_mean: |
| value: 2.0858158426240725 |
| step: 140045 |
| walltime: null |
| collector_iter/live_seat1_episode_count: |
| value: 32 |
| step: 51600 |
| walltime: null |
| collector_step/live_seat1_episode_count: |
| value: 32 |
| step: 140045 |
| walltime: null |
| collector_iter/live_seat1_reward_mean: |
| value: 0.0 |
| step: 51600 |
| walltime: null |
| collector_step/live_seat1_reward_mean: |
| value: 0.0 |
| step: 140045 |
| walltime: null |
| collector_iter/live_seat2_episode_count: |
| value: 96 |
| step: 51600 |
| walltime: null |
| collector_step/live_seat2_episode_count: |
| value: 96 |
| step: 140045 |
| walltime: null |
| collector_iter/live_seat2_reward_mean: |
| value: -0.7291666666666666 |
| step: 51600 |
| walltime: null |
| collector_step/live_seat2_reward_mean: |
| value: -0.7291666666666666 |
| step: 140045 |
| walltime: null |
| envstep_150000.pth.tar: |
| checkpoint_name: envstep_150000.pth.tar |
| checkpoint_path: /home/molfetta/combinatorial_reasoning_post_training/models/main5_hf_bot_mode_recovery_50k_20260522/simplified__first_attack/attempt-01_260522_170112/ckpt/envstep_150000.pth.tar |
| saved_at: '2026-05-22T19:23:52.933052+00:00' |
| train_iter: 55275 |
| envstep: 150000 |
| trigger: envstep |
| latest_scalars: |
| evaluator_iter/episode_count: |
| value: 20 |
| step: 51625 |
| walltime: null |
| evaluator_step/episode_count: |
| value: 20 |
| step: 140045 |
| walltime: null |
| evaluator_iter/envstep_count: |
| value: 90 |
| step: 51625 |
| walltime: null |
| evaluator_step/envstep_count: |
| value: 90 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_envstep_per_episode: |
| value: 4.5 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_envstep_per_episode: |
| value: 4.5 |
| step: 140045 |
| walltime: null |
| evaluator_iter/evaluate_time: |
| value: 1.5140567626953125 |
| step: 51625 |
| walltime: null |
| evaluator_step/evaluate_time: |
| value: 1.5140567626953125 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_envstep_per_sec: |
| value: 59.442949708029886 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_envstep_per_sec: |
| value: 59.442949708029886 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_time_per_episode: |
| value: 13.209544379562196 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_time_per_episode: |
| value: 13.209544379562196 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_std: |
| value: 0.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_std: |
| value: 0.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_max: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_max: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_min: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_min: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat_swap: |
| value: true |
| step: 51625 |
| walltime: null |
| evaluator_step/seat_swap: |
| value: true |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat1_episode_count: |
| value: 10 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat1_episode_count: |
| value: 10 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat2_episode_count: |
| value: 10 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat2_episode_count: |
| value: 10 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat1_reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat1_reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat2_reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat2_reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/eval_episode_return_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/eval_episode_return_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/live_policy_seat_mean: |
| value: 1.5 |
| step: 51625 |
| walltime: null |
| evaluator_step/live_policy_seat_mean: |
| value: 1.5 |
| step: 140045 |
| walltime: null |
| Buffer/Task_0/num_collected_episodes: |
| value: 70848 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/num_game_segments: |
| value: 23597 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/num_transitions: |
| value: 49999 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/game_segment_buffer: |
| value: 79.53292083740234 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/process: |
| value: 2047.0234375 |
| step: 55275 |
| walltime: null |
| learner_iter/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 55200 |
| walltime: null |
| learner_step/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 149795 |
| walltime: null |
| learner_iter/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 55200 |
| walltime: null |
| learner_step/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 149795 |
| walltime: null |
| learner_iter/weighted_total_loss_avg: |
| value: 2.993369861082597 |
| step: 55200 |
| walltime: null |
| learner_step/weighted_total_loss_avg: |
| value: 2.993369861082597 |
| step: 149795 |
| walltime: null |
| learner_iter/total_loss_avg: |
| value: 2.993369861082597 |
| step: 55200 |
| walltime: null |
| learner_step/total_loss_avg: |
| value: 2.993369861082597 |
| step: 149795 |
| walltime: null |
| learner_iter/policy_loss_avg: |
| value: 3.7127135450189765 |
| step: 55200 |
| walltime: null |
| learner_step/policy_loss_avg: |
| value: 3.7127135450189765 |
| step: 149795 |
| walltime: null |
| learner_iter/policy_entropy_avg: |
| value: 1.8206564874360056 |
| step: 55200 |
| walltime: null |
| learner_step/policy_entropy_avg: |
| value: 1.8206564874360056 |
| step: 149795 |
| walltime: null |
| learner_iter/target_policy_entropy_avg: |
| value: 2.3736922524192114 |
| step: 55200 |
| walltime: null |
| learner_step/target_policy_entropy_avg: |
| value: 2.3736922524192114 |
| step: 149795 |
| walltime: null |
| learner_iter/value_prefix_loss_avg: |
| value: 3.0188358913768423 |
| step: 55200 |
| walltime: null |
| learner_step/value_prefix_loss_avg: |
| value: 3.0188358913768423 |
| step: 149795 |
| walltime: null |
| learner_iter/value_loss_avg: |
| value: 1.6818079406564885 |
| step: 55200 |
| walltime: null |
| learner_step/value_loss_avg: |
| value: 1.6818079406564885 |
| step: 149795 |
| walltime: null |
| learner_iter/consistency_loss_avg: |
| value: -0.4158631281419234 |
| step: 55200 |
| walltime: null |
| learner_step/consistency_loss_avg: |
| value: -0.4158631281419234 |
| step: 149795 |
| walltime: null |
| learner_iter/value_priority_avg: |
| value: 0.6368463201956316 |
| step: 55200 |
| walltime: null |
| learner_step/value_priority_avg: |
| value: 0.6368463201956316 |
| step: 149795 |
| walltime: null |
| learner_iter/target_value_prefix_avg: |
| value: -0.25568182089112024 |
| step: 55200 |
| walltime: null |
| learner_step/target_value_prefix_avg: |
| value: -0.25568182089112024 |
| step: 149795 |
| walltime: null |
| learner_iter/target_value_avg: |
| value: -0.12352036278356206 |
| step: 55200 |
| walltime: null |
| learner_step/target_value_avg: |
| value: -0.12352036278356206 |
| step: 149795 |
| walltime: null |
| learner_iter/predicted_value_prefixs_avg: |
| value: -0.27838644114407624 |
| step: 55200 |
| walltime: null |
| learner_step/predicted_value_prefixs_avg: |
| value: -0.27838644114407624 |
| step: 149795 |
| walltime: null |
| learner_iter/predicted_values_avg: |
| value: -0.11092928526076404 |
| step: 55200 |
| walltime: null |
| learner_step/predicted_values_avg: |
| value: -0.11092928526076404 |
| step: 149795 |
| walltime: null |
| learner_iter/transformed_target_value_prefix_avg: |
| value: -0.10616254671053453 |
| step: 55200 |
| walltime: null |
| learner_step/transformed_target_value_prefix_avg: |
| value: -0.10616254671053453 |
| step: 149795 |
| walltime: null |
| learner_iter/transformed_target_value_avg: |
| value: -0.05128732526844198 |
| step: 55200 |
| walltime: null |
| learner_step/transformed_target_value_avg: |
| value: -0.05128732526844198 |
| step: 149795 |
| walltime: null |
| learner_iter/total_grad_norm_before_clip_avg: |
| value: 0.11628456616943533 |
| step: 55200 |
| walltime: null |
| learner_step/total_grad_norm_before_clip_avg: |
| value: 0.11628456616943533 |
| step: 149795 |
| walltime: null |
| collector_iter/episode_count: |
| value: 128 |
| step: 55200 |
| walltime: null |
| collector_step/episode_count: |
| value: 128 |
| step: 149795 |
| walltime: null |
| collector_iter/envstep_count: |
| value: 272 |
| step: 55200 |
| walltime: null |
| collector_step/envstep_count: |
| value: 272 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_envstep_per_episode: |
| value: 2.125 |
| step: 55200 |
| walltime: null |
| collector_step/avg_envstep_per_episode: |
| value: 2.125 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_envstep_per_sec: |
| value: 71.82140759220879 |
| step: 55200 |
| walltime: null |
| collector_step/avg_envstep_per_sec: |
| value: 71.82140759220879 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_episode_per_sec: |
| value: 33.798309455157074 |
| step: 55200 |
| walltime: null |
| collector_step/avg_episode_per_sec: |
| value: 33.798309455157074 |
| step: 149795 |
| walltime: null |
| collector_iter/collect_time: |
| value: 3.78717166815186 |
| step: 55200 |
| walltime: null |
| collector_step/collect_time: |
| value: 3.78717166815186 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_mean: |
| value: -0.453125 |
| step: 55200 |
| walltime: null |
| collector_step/reward_mean: |
| value: -0.453125 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_std: |
| value: 0.8914469890997445 |
| step: 55200 |
| walltime: null |
| collector_step/reward_std: |
| value: 0.8914469890997445 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_max: |
| value: 1.0 |
| step: 55200 |
| walltime: null |
| collector_step/reward_max: |
| value: 1.0 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_min: |
| value: -1.0 |
| step: 55200 |
| walltime: null |
| collector_step/reward_min: |
| value: -1.0 |
| step: 149795 |
| walltime: null |
| collector_iter/total_envstep_count: |
| value: 149795 |
| step: 55200 |
| walltime: null |
| collector_step/total_envstep_count: |
| value: 149795 |
| step: 149795 |
| walltime: null |
| collector_iter/total_episode_count: |
| value: 70784 |
| step: 55200 |
| walltime: null |
| collector_step/total_episode_count: |
| value: 70784 |
| step: 149795 |
| walltime: null |
| collector_iter/total_duration: |
| value: 5840.71620646594 |
| step: 55200 |
| walltime: null |
| collector_step/total_duration: |
| value: 5840.71620646594 |
| step: 149795 |
| walltime: null |
| collector_iter/visit_entropy_mean: |
| value: 1.8918631152815573 |
| step: 55200 |
| walltime: null |
| collector_step/visit_entropy_mean: |
| value: 1.8918631152815573 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat1_episode_count: |
| value: 32 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat1_episode_count: |
| value: 32 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat1_reward_mean: |
| value: 0.0 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat1_reward_mean: |
| value: 0.0 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat2_episode_count: |
| value: 96 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat2_episode_count: |
| value: 96 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat2_reward_mean: |
| value: -0.6041666666666666 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat2_reward_mean: |
| value: -0.6041666666666666 |
| step: 149795 |
| walltime: null |
| iteration_55300.pth.tar: |
| checkpoint_name: iteration_55300.pth.tar |
| checkpoint_path: /home/molfetta/combinatorial_reasoning_post_training/models/main5_hf_bot_mode_recovery_50k_20260522/simplified__first_attack/attempt-01_260522_170112/ckpt/iteration_55300.pth.tar |
| saved_at: '2026-05-22T19:23:58.031644+00:00' |
| train_iter: 55300 |
| envstep: 150002 |
| trigger: null |
| latest_scalars: |
| evaluator_iter/episode_count: |
| value: 20 |
| step: 51625 |
| walltime: null |
| evaluator_step/episode_count: |
| value: 20 |
| step: 140045 |
| walltime: null |
| evaluator_iter/envstep_count: |
| value: 90 |
| step: 51625 |
| walltime: null |
| evaluator_step/envstep_count: |
| value: 90 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_envstep_per_episode: |
| value: 4.5 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_envstep_per_episode: |
| value: 4.5 |
| step: 140045 |
| walltime: null |
| evaluator_iter/evaluate_time: |
| value: 1.5140567626953125 |
| step: 51625 |
| walltime: null |
| evaluator_step/evaluate_time: |
| value: 1.5140567626953125 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_envstep_per_sec: |
| value: 59.442949708029886 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_envstep_per_sec: |
| value: 59.442949708029886 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_time_per_episode: |
| value: 13.209544379562196 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_time_per_episode: |
| value: 13.209544379562196 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_std: |
| value: 0.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_std: |
| value: 0.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_max: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_max: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_min: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_min: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat_swap: |
| value: true |
| step: 51625 |
| walltime: null |
| evaluator_step/seat_swap: |
| value: true |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat1_episode_count: |
| value: 10 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat1_episode_count: |
| value: 10 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat2_episode_count: |
| value: 10 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat2_episode_count: |
| value: 10 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat1_reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat1_reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat2_reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat2_reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/eval_episode_return_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/eval_episode_return_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/live_policy_seat_mean: |
| value: 1.5 |
| step: 51625 |
| walltime: null |
| evaluator_step/live_policy_seat_mean: |
| value: 1.5 |
| step: 140045 |
| walltime: null |
| Buffer/Task_0/num_collected_episodes: |
| value: 70848 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/num_game_segments: |
| value: 23597 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/num_transitions: |
| value: 49999 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/game_segment_buffer: |
| value: 79.53292083740234 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/process: |
| value: 2047.0234375 |
| step: 55275 |
| walltime: null |
| learner_iter/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 55200 |
| walltime: null |
| learner_step/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 149795 |
| walltime: null |
| learner_iter/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 55200 |
| walltime: null |
| learner_step/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 149795 |
| walltime: null |
| learner_iter/weighted_total_loss_avg: |
| value: 2.993369861082597 |
| step: 55200 |
| walltime: null |
| learner_step/weighted_total_loss_avg: |
| value: 2.993369861082597 |
| step: 149795 |
| walltime: null |
| learner_iter/total_loss_avg: |
| value: 2.993369861082597 |
| step: 55200 |
| walltime: null |
| learner_step/total_loss_avg: |
| value: 2.993369861082597 |
| step: 149795 |
| walltime: null |
| learner_iter/policy_loss_avg: |
| value: 3.7127135450189765 |
| step: 55200 |
| walltime: null |
| learner_step/policy_loss_avg: |
| value: 3.7127135450189765 |
| step: 149795 |
| walltime: null |
| learner_iter/policy_entropy_avg: |
| value: 1.8206564874360056 |
| step: 55200 |
| walltime: null |
| learner_step/policy_entropy_avg: |
| value: 1.8206564874360056 |
| step: 149795 |
| walltime: null |
| learner_iter/target_policy_entropy_avg: |
| value: 2.3736922524192114 |
| step: 55200 |
| walltime: null |
| learner_step/target_policy_entropy_avg: |
| value: 2.3736922524192114 |
| step: 149795 |
| walltime: null |
| learner_iter/value_prefix_loss_avg: |
| value: 3.0188358913768423 |
| step: 55200 |
| walltime: null |
| learner_step/value_prefix_loss_avg: |
| value: 3.0188358913768423 |
| step: 149795 |
| walltime: null |
| learner_iter/value_loss_avg: |
| value: 1.6818079406564885 |
| step: 55200 |
| walltime: null |
| learner_step/value_loss_avg: |
| value: 1.6818079406564885 |
| step: 149795 |
| walltime: null |
| learner_iter/consistency_loss_avg: |
| value: -0.4158631281419234 |
| step: 55200 |
| walltime: null |
| learner_step/consistency_loss_avg: |
| value: -0.4158631281419234 |
| step: 149795 |
| walltime: null |
| learner_iter/value_priority_avg: |
| value: 0.6368463201956316 |
| step: 55200 |
| walltime: null |
| learner_step/value_priority_avg: |
| value: 0.6368463201956316 |
| step: 149795 |
| walltime: null |
| learner_iter/target_value_prefix_avg: |
| value: -0.25568182089112024 |
| step: 55200 |
| walltime: null |
| learner_step/target_value_prefix_avg: |
| value: -0.25568182089112024 |
| step: 149795 |
| walltime: null |
| learner_iter/target_value_avg: |
| value: -0.12352036278356206 |
| step: 55200 |
| walltime: null |
| learner_step/target_value_avg: |
| value: -0.12352036278356206 |
| step: 149795 |
| walltime: null |
| learner_iter/predicted_value_prefixs_avg: |
| value: -0.27838644114407624 |
| step: 55200 |
| walltime: null |
| learner_step/predicted_value_prefixs_avg: |
| value: -0.27838644114407624 |
| step: 149795 |
| walltime: null |
| learner_iter/predicted_values_avg: |
| value: -0.11092928526076404 |
| step: 55200 |
| walltime: null |
| learner_step/predicted_values_avg: |
| value: -0.11092928526076404 |
| step: 149795 |
| walltime: null |
| learner_iter/transformed_target_value_prefix_avg: |
| value: -0.10616254671053453 |
| step: 55200 |
| walltime: null |
| learner_step/transformed_target_value_prefix_avg: |
| value: -0.10616254671053453 |
| step: 149795 |
| walltime: null |
| learner_iter/transformed_target_value_avg: |
| value: -0.05128732526844198 |
| step: 55200 |
| walltime: null |
| learner_step/transformed_target_value_avg: |
| value: -0.05128732526844198 |
| step: 149795 |
| walltime: null |
| learner_iter/total_grad_norm_before_clip_avg: |
| value: 0.11628456616943533 |
| step: 55200 |
| walltime: null |
| learner_step/total_grad_norm_before_clip_avg: |
| value: 0.11628456616943533 |
| step: 149795 |
| walltime: null |
| collector_iter/episode_count: |
| value: 128 |
| step: 55200 |
| walltime: null |
| collector_step/episode_count: |
| value: 128 |
| step: 149795 |
| walltime: null |
| collector_iter/envstep_count: |
| value: 272 |
| step: 55200 |
| walltime: null |
| collector_step/envstep_count: |
| value: 272 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_envstep_per_episode: |
| value: 2.125 |
| step: 55200 |
| walltime: null |
| collector_step/avg_envstep_per_episode: |
| value: 2.125 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_envstep_per_sec: |
| value: 71.82140759220879 |
| step: 55200 |
| walltime: null |
| collector_step/avg_envstep_per_sec: |
| value: 71.82140759220879 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_episode_per_sec: |
| value: 33.798309455157074 |
| step: 55200 |
| walltime: null |
| collector_step/avg_episode_per_sec: |
| value: 33.798309455157074 |
| step: 149795 |
| walltime: null |
| collector_iter/collect_time: |
| value: 3.78717166815186 |
| step: 55200 |
| walltime: null |
| collector_step/collect_time: |
| value: 3.78717166815186 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_mean: |
| value: -0.453125 |
| step: 55200 |
| walltime: null |
| collector_step/reward_mean: |
| value: -0.453125 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_std: |
| value: 0.8914469890997445 |
| step: 55200 |
| walltime: null |
| collector_step/reward_std: |
| value: 0.8914469890997445 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_max: |
| value: 1.0 |
| step: 55200 |
| walltime: null |
| collector_step/reward_max: |
| value: 1.0 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_min: |
| value: -1.0 |
| step: 55200 |
| walltime: null |
| collector_step/reward_min: |
| value: -1.0 |
| step: 149795 |
| walltime: null |
| collector_iter/total_envstep_count: |
| value: 149795 |
| step: 55200 |
| walltime: null |
| collector_step/total_envstep_count: |
| value: 149795 |
| step: 149795 |
| walltime: null |
| collector_iter/total_episode_count: |
| value: 70784 |
| step: 55200 |
| walltime: null |
| collector_step/total_episode_count: |
| value: 70784 |
| step: 149795 |
| walltime: null |
| collector_iter/total_duration: |
| value: 5840.71620646594 |
| step: 55200 |
| walltime: null |
| collector_step/total_duration: |
| value: 5840.71620646594 |
| step: 149795 |
| walltime: null |
| collector_iter/visit_entropy_mean: |
| value: 1.8918631152815573 |
| step: 55200 |
| walltime: null |
| collector_step/visit_entropy_mean: |
| value: 1.8918631152815573 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat1_episode_count: |
| value: 32 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat1_episode_count: |
| value: 32 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat1_reward_mean: |
| value: 0.0 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat1_reward_mean: |
| value: 0.0 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat2_episode_count: |
| value: 96 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat2_episode_count: |
| value: 96 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat2_reward_mean: |
| value: -0.6041666666666666 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat2_reward_mean: |
| value: -0.6041666666666666 |
| step: 149795 |
| walltime: null |
| ckpt_last.pth.tar: |
| checkpoint_name: ckpt_last.pth.tar |
| checkpoint_path: /home/molfetta/combinatorial_reasoning_post_training/models/main5_hf_bot_mode_recovery_50k_20260522/simplified__first_attack/attempt-01_260522_170112/ckpt/ckpt_last.pth.tar |
| saved_at: '2026-05-22T19:23:59.263977+00:00' |
| train_iter: 55300 |
| envstep: 150002 |
| trigger: null |
| latest_scalars: |
| evaluator_iter/episode_count: |
| value: 20 |
| step: 51625 |
| walltime: null |
| evaluator_step/episode_count: |
| value: 20 |
| step: 140045 |
| walltime: null |
| evaluator_iter/envstep_count: |
| value: 90 |
| step: 51625 |
| walltime: null |
| evaluator_step/envstep_count: |
| value: 90 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_envstep_per_episode: |
| value: 4.5 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_envstep_per_episode: |
| value: 4.5 |
| step: 140045 |
| walltime: null |
| evaluator_iter/evaluate_time: |
| value: 1.5140567626953125 |
| step: 51625 |
| walltime: null |
| evaluator_step/evaluate_time: |
| value: 1.5140567626953125 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_envstep_per_sec: |
| value: 59.442949708029886 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_envstep_per_sec: |
| value: 59.442949708029886 |
| step: 140045 |
| walltime: null |
| evaluator_iter/avg_time_per_episode: |
| value: 13.209544379562196 |
| step: 51625 |
| walltime: null |
| evaluator_step/avg_time_per_episode: |
| value: 13.209544379562196 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_std: |
| value: 0.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_std: |
| value: 0.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_max: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_max: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/reward_min: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/reward_min: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat_swap: |
| value: true |
| step: 51625 |
| walltime: null |
| evaluator_step/seat_swap: |
| value: true |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat1_episode_count: |
| value: 10 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat1_episode_count: |
| value: 10 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat2_episode_count: |
| value: 10 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat2_episode_count: |
| value: 10 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat1_reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat1_reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/seat2_reward_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/seat2_reward_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/eval_episode_return_mean: |
| value: -1.0 |
| step: 51625 |
| walltime: null |
| evaluator_step/eval_episode_return_mean: |
| value: -1.0 |
| step: 140045 |
| walltime: null |
| evaluator_iter/live_policy_seat_mean: |
| value: 1.5 |
| step: 51625 |
| walltime: null |
| evaluator_step/live_policy_seat_mean: |
| value: 1.5 |
| step: 140045 |
| walltime: null |
| Buffer/Task_0/num_collected_episodes: |
| value: 70848 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/num_game_segments: |
| value: 23597 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/num_transitions: |
| value: 49999 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/game_segment_buffer: |
| value: 79.53292083740234 |
| step: 55275 |
| walltime: null |
| Buffer/Task_0/memory_usage_mb/process: |
| value: 2047.0234375 |
| step: 55275 |
| walltime: null |
| learner_iter/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 55200 |
| walltime: null |
| learner_step/collect_mcts_temperature_avg: |
| value: 0.25 |
| step: 149795 |
| walltime: null |
| learner_iter/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 55200 |
| walltime: null |
| learner_step/cur_lr_avg: |
| value: 0.0029999999999999996 |
| step: 149795 |
| walltime: null |
| learner_iter/weighted_total_loss_avg: |
| value: 2.993369861082597 |
| step: 55200 |
| walltime: null |
| learner_step/weighted_total_loss_avg: |
| value: 2.993369861082597 |
| step: 149795 |
| walltime: null |
| learner_iter/total_loss_avg: |
| value: 2.993369861082597 |
| step: 55200 |
| walltime: null |
| learner_step/total_loss_avg: |
| value: 2.993369861082597 |
| step: 149795 |
| walltime: null |
| learner_iter/policy_loss_avg: |
| value: 3.7127135450189765 |
| step: 55200 |
| walltime: null |
| learner_step/policy_loss_avg: |
| value: 3.7127135450189765 |
| step: 149795 |
| walltime: null |
| learner_iter/policy_entropy_avg: |
| value: 1.8206564874360056 |
| step: 55200 |
| walltime: null |
| learner_step/policy_entropy_avg: |
| value: 1.8206564874360056 |
| step: 149795 |
| walltime: null |
| learner_iter/target_policy_entropy_avg: |
| value: 2.3736922524192114 |
| step: 55200 |
| walltime: null |
| learner_step/target_policy_entropy_avg: |
| value: 2.3736922524192114 |
| step: 149795 |
| walltime: null |
| learner_iter/value_prefix_loss_avg: |
| value: 3.0188358913768423 |
| step: 55200 |
| walltime: null |
| learner_step/value_prefix_loss_avg: |
| value: 3.0188358913768423 |
| step: 149795 |
| walltime: null |
| learner_iter/value_loss_avg: |
| value: 1.6818079406564885 |
| step: 55200 |
| walltime: null |
| learner_step/value_loss_avg: |
| value: 1.6818079406564885 |
| step: 149795 |
| walltime: null |
| learner_iter/consistency_loss_avg: |
| value: -0.4158631281419234 |
| step: 55200 |
| walltime: null |
| learner_step/consistency_loss_avg: |
| value: -0.4158631281419234 |
| step: 149795 |
| walltime: null |
| learner_iter/value_priority_avg: |
| value: 0.6368463201956316 |
| step: 55200 |
| walltime: null |
| learner_step/value_priority_avg: |
| value: 0.6368463201956316 |
| step: 149795 |
| walltime: null |
| learner_iter/target_value_prefix_avg: |
| value: -0.25568182089112024 |
| step: 55200 |
| walltime: null |
| learner_step/target_value_prefix_avg: |
| value: -0.25568182089112024 |
| step: 149795 |
| walltime: null |
| learner_iter/target_value_avg: |
| value: -0.12352036278356206 |
| step: 55200 |
| walltime: null |
| learner_step/target_value_avg: |
| value: -0.12352036278356206 |
| step: 149795 |
| walltime: null |
| learner_iter/predicted_value_prefixs_avg: |
| value: -0.27838644114407624 |
| step: 55200 |
| walltime: null |
| learner_step/predicted_value_prefixs_avg: |
| value: -0.27838644114407624 |
| step: 149795 |
| walltime: null |
| learner_iter/predicted_values_avg: |
| value: -0.11092928526076404 |
| step: 55200 |
| walltime: null |
| learner_step/predicted_values_avg: |
| value: -0.11092928526076404 |
| step: 149795 |
| walltime: null |
| learner_iter/transformed_target_value_prefix_avg: |
| value: -0.10616254671053453 |
| step: 55200 |
| walltime: null |
| learner_step/transformed_target_value_prefix_avg: |
| value: -0.10616254671053453 |
| step: 149795 |
| walltime: null |
| learner_iter/transformed_target_value_avg: |
| value: -0.05128732526844198 |
| step: 55200 |
| walltime: null |
| learner_step/transformed_target_value_avg: |
| value: -0.05128732526844198 |
| step: 149795 |
| walltime: null |
| learner_iter/total_grad_norm_before_clip_avg: |
| value: 0.11628456616943533 |
| step: 55200 |
| walltime: null |
| learner_step/total_grad_norm_before_clip_avg: |
| value: 0.11628456616943533 |
| step: 149795 |
| walltime: null |
| collector_iter/episode_count: |
| value: 128 |
| step: 55200 |
| walltime: null |
| collector_step/episode_count: |
| value: 128 |
| step: 149795 |
| walltime: null |
| collector_iter/envstep_count: |
| value: 272 |
| step: 55200 |
| walltime: null |
| collector_step/envstep_count: |
| value: 272 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_envstep_per_episode: |
| value: 2.125 |
| step: 55200 |
| walltime: null |
| collector_step/avg_envstep_per_episode: |
| value: 2.125 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_envstep_per_sec: |
| value: 71.82140759220879 |
| step: 55200 |
| walltime: null |
| collector_step/avg_envstep_per_sec: |
| value: 71.82140759220879 |
| step: 149795 |
| walltime: null |
| collector_iter/avg_episode_per_sec: |
| value: 33.798309455157074 |
| step: 55200 |
| walltime: null |
| collector_step/avg_episode_per_sec: |
| value: 33.798309455157074 |
| step: 149795 |
| walltime: null |
| collector_iter/collect_time: |
| value: 3.78717166815186 |
| step: 55200 |
| walltime: null |
| collector_step/collect_time: |
| value: 3.78717166815186 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_mean: |
| value: -0.453125 |
| step: 55200 |
| walltime: null |
| collector_step/reward_mean: |
| value: -0.453125 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_std: |
| value: 0.8914469890997445 |
| step: 55200 |
| walltime: null |
| collector_step/reward_std: |
| value: 0.8914469890997445 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_max: |
| value: 1.0 |
| step: 55200 |
| walltime: null |
| collector_step/reward_max: |
| value: 1.0 |
| step: 149795 |
| walltime: null |
| collector_iter/reward_min: |
| value: -1.0 |
| step: 55200 |
| walltime: null |
| collector_step/reward_min: |
| value: -1.0 |
| step: 149795 |
| walltime: null |
| collector_iter/total_envstep_count: |
| value: 149795 |
| step: 55200 |
| walltime: null |
| collector_step/total_envstep_count: |
| value: 149795 |
| step: 149795 |
| walltime: null |
| collector_iter/total_episode_count: |
| value: 70784 |
| step: 55200 |
| walltime: null |
| collector_step/total_episode_count: |
| value: 70784 |
| step: 149795 |
| walltime: null |
| collector_iter/total_duration: |
| value: 5840.71620646594 |
| step: 55200 |
| walltime: null |
| collector_step/total_duration: |
| value: 5840.71620646594 |
| step: 149795 |
| walltime: null |
| collector_iter/visit_entropy_mean: |
| value: 1.8918631152815573 |
| step: 55200 |
| walltime: null |
| collector_step/visit_entropy_mean: |
| value: 1.8918631152815573 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat1_episode_count: |
| value: 32 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat1_episode_count: |
| value: 32 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat1_reward_mean: |
| value: 0.0 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat1_reward_mean: |
| value: 0.0 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat2_episode_count: |
| value: 96 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat2_episode_count: |
| value: 96 |
| step: 149795 |
| walltime: null |
| collector_iter/live_seat2_reward_mean: |
| value: -0.6041666666666666 |
| step: 55200 |
| walltime: null |
| collector_step/live_seat2_reward_mean: |
| value: -0.6041666666666666 |
| step: 149795 |
| walltime: null |
| metadata_version: 1 |
|
|
