diff --git a/.gitattributes b/.gitattributes index 06588a503b1e0705854d0c7d4cbe357eda953de3..19637936ef71254dd77a4feb0e6cd8ca73ec8ba9 100644 --- a/.gitattributes +++ b/.gitattributes @@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text completions.jsonl filter=lfs diff=lfs merge=lfs -text +checkpoint-28-merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint-10/adapter_config.json b/checkpoint-10/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-10/adapter_config.json +++ b/checkpoint-10/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-10/trainer_state.json b/checkpoint-10/trainer_state.json index 5a79924b2d245a8abca9496ead30bfe57b2b71eb..d9543360277532e9321b29edfc3279b65f6493cb 100644 --- a/checkpoint-10/trainer_state.json +++ b/checkpoint-10/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 6, "best_metric": 0.012996690347790718, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-6", "epoch": 2.4210526315789473, @@ -7,7 +6,7 @@ "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 } diff --git a/checkpoint-10/training_args.bin b/checkpoint-10/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-10/training_args.bin +++ b/checkpoint-10/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-12/adapter_config.json b/checkpoint-12/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-12/adapter_config.json +++ b/checkpoint-12/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-12/trainer_state.json b/checkpoint-12/trainer_state.json index e881a9a8919b536e9e280ccff4f8b90228fbfebb..63af88b38df0307c22be3faf58351ed68fccbb37 100644 --- a/checkpoint-12/trainer_state.json +++ b/checkpoint-12/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 12, "best_metric": 0.03234308212995529, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-12", "epoch": 2.8421052631578947, @@ -7,7 +6,7 @@ "global_step": 12, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 diff --git a/checkpoint-12/training_args.bin b/checkpoint-12/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-12/training_args.bin +++ b/checkpoint-12/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-14/adapter_config.json b/checkpoint-14/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-14/adapter_config.json +++ b/checkpoint-14/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-14/trainer_state.json b/checkpoint-14/trainer_state.json index 88fbf9becfb5d669da763a3d0ad753433363ad56..0283ff9c783b7aa5ca912544b2dd35fcf23f9a99 100644 --- a/checkpoint-14/trainer_state.json +++ b/checkpoint-14/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 12, "best_metric": 0.03234308212995529, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-12", "epoch": 3.4210526315789473, @@ -7,7 +6,7 @@ "global_step": 14, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 } diff --git a/checkpoint-14/training_args.bin b/checkpoint-14/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-14/training_args.bin +++ b/checkpoint-14/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-16/adapter_config.json b/checkpoint-16/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-16/adapter_config.json +++ b/checkpoint-16/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-16/trainer_state.json b/checkpoint-16/trainer_state.json index 05d1f498967f7d2261705218aabc15ae6b24fdbb..9227c90abf65fb0517b0d1c7eb78e18f0426365e 100644 --- a/checkpoint-16/trainer_state.json +++ b/checkpoint-16/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 12, "best_metric": 0.03234308212995529, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-12", "epoch": 3.8421052631578947, @@ -7,7 +6,7 @@ "global_step": 16, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 } diff --git a/checkpoint-16/training_args.bin b/checkpoint-16/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-16/training_args.bin +++ b/checkpoint-16/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-18/adapter_config.json b/checkpoint-18/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-18/adapter_config.json +++ b/checkpoint-18/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-18/trainer_state.json b/checkpoint-18/trainer_state.json index 68a886310dcb3a5fdd37c6f6e0a752b3deac1847..5e552ea3183048034e8097ff86a4f6d1c899830d 100644 --- a/checkpoint-18/trainer_state.json +++ b/checkpoint-18/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 18, "best_metric": 0.03729328140616417, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-18", "epoch": 4.421052631578947, @@ -7,7 +6,7 @@ "global_step": 18, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 }, @@ -269,7 +268,7 @@ "kl": 0.1787109375, "learning_rate": 9.01061596377522e-05, "loss": -0.04504441097378731, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.027318883687257767, "reward_std": 0.10441224090754986, @@ -283,7 +282,7 @@ "grad_norm": 0.005998397711664438, "learning_rate": 8.83022221559489e-05, "loss": -0.045487549155950546, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 18, "train_speed(iter/s)": 0.000432 }, @@ -298,7 +297,7 @@ "eval_reward_std": 0.10691346973180771, "eval_rewards/CosineReward": 0.03729327768087387, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1041.2277, + "eval_runtime": 1041.231, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 18 diff --git a/checkpoint-18/training_args.bin b/checkpoint-18/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-18/training_args.bin +++ b/checkpoint-18/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-2/adapter_config.json b/checkpoint-2/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-2/adapter_config.json +++ b/checkpoint-2/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-2/trainer_state.json b/checkpoint-2/trainer_state.json index bb52596552917fa1c4d3ad7571620d71c01afb13..abb60dd05407f920c1cb0c23f346741d8e8e4205 100644 --- a/checkpoint-2/trainer_state.json +++ b/checkpoint-2/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.42105263157894735, @@ -7,7 +6,7 @@ "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 } ], "logging_steps": 1, diff --git a/checkpoint-2/training_args.bin b/checkpoint-2/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-2/training_args.bin +++ b/checkpoint-2/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-20/adapter_config.json b/checkpoint-20/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-20/adapter_config.json +++ b/checkpoint-20/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-20/trainer_state.json b/checkpoint-20/trainer_state.json index 917db439a8e53b0f8f659b78dc218b1c69f5106b..939e242f4ac78f4a828aaf48a8eafdabdd7268dd 100644 --- a/checkpoint-20/trainer_state.json +++ b/checkpoint-20/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 18, "best_metric": 0.03729328140616417, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-18", "epoch": 4.842105263157895, @@ -7,7 +6,7 @@ "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 }, @@ -269,7 +268,7 @@ "kl": 0.1787109375, "learning_rate": 9.01061596377522e-05, "loss": -0.04504441097378731, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.027318883687257767, "reward_std": 0.10441224090754986, @@ -283,7 +282,7 @@ "grad_norm": 0.005998397711664438, "learning_rate": 8.83022221559489e-05, "loss": -0.045487549155950546, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 18, "train_speed(iter/s)": 0.000432 }, @@ -298,7 +297,7 @@ "eval_reward_std": 0.10691346973180771, "eval_rewards/CosineReward": 0.03729327768087387, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1041.2277, + "eval_runtime": 1041.231, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 18 @@ -311,7 +310,7 @@ "kl": 0.1820068359375, "learning_rate": 8.636868207865244e-05, "loss": -0.03466903418302536, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.466796875, "reward": 0.04069916973821819, "reward_std": 0.11991005763411522, @@ -327,7 +326,7 @@ "kl": 0.19287109375, "learning_rate": 8.43120818934367e-05, "loss": -0.03502114117145538, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 20, "train_speed(iter/s)": 0.000424 } diff --git a/checkpoint-20/training_args.bin b/checkpoint-20/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-20/training_args.bin +++ b/checkpoint-20/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-22/adapter_config.json b/checkpoint-22/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-22/adapter_config.json +++ b/checkpoint-22/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-22/trainer_state.json b/checkpoint-22/trainer_state.json index 456d04aa7966a1cd12ff9f6c0086d744a460e3c7..f25a50fd2117664a679744f3e1068c255dd295e1 100644 --- a/checkpoint-22/trainer_state.json +++ b/checkpoint-22/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 18, "best_metric": 0.03729328140616417, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-18", "epoch": 5.421052631578947, @@ -7,7 +6,7 @@ "global_step": 22, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 }, @@ -269,7 +268,7 @@ "kl": 0.1787109375, "learning_rate": 9.01061596377522e-05, "loss": -0.04504441097378731, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.027318883687257767, "reward_std": 0.10441224090754986, @@ -283,7 +282,7 @@ "grad_norm": 0.005998397711664438, "learning_rate": 8.83022221559489e-05, "loss": -0.045487549155950546, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 18, "train_speed(iter/s)": 0.000432 }, @@ -298,7 +297,7 @@ "eval_reward_std": 0.10691346973180771, "eval_rewards/CosineReward": 0.03729327768087387, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1041.2277, + "eval_runtime": 1041.231, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 18 @@ -311,7 +310,7 @@ "kl": 0.1820068359375, "learning_rate": 8.636868207865244e-05, "loss": -0.03466903418302536, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.466796875, "reward": 0.04069916973821819, "reward_std": 0.11991005763411522, @@ -327,7 +326,7 @@ "kl": 0.19287109375, "learning_rate": 8.43120818934367e-05, "loss": -0.03502114117145538, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 20, "train_speed(iter/s)": 0.000424 }, @@ -339,14 +338,14 @@ "kl": 0.17626953125, "learning_rate": 8.213938048432697e-05, "loss": -0.008662773296236992, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.04996980866417289, "reward_std": 0.13849420100450516, "rewards/CosineReward": 0.049969930201768875, "rewards/RepetitionPenalty": -1.1864573679076784e-07, "step": 21, - "train_speed(iter/s)": 0.000407 + "train_speed(iter/s)": 0.000408 }, { "clip_ratio": 5.869188044016482e-05, @@ -355,7 +354,7 @@ "kl": 0.178955078125, "learning_rate": 7.985792958513931e-05, "loss": -0.008743642829358578, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 22, "train_speed(iter/s)": 0.000426 } diff --git a/checkpoint-22/training_args.bin b/checkpoint-22/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-22/training_args.bin +++ b/checkpoint-22/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-24/adapter_config.json b/checkpoint-24/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-24/adapter_config.json +++ b/checkpoint-24/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-24/trainer_state.json b/checkpoint-24/trainer_state.json index bb1be19c6a2805c0e9655eb7f7fec3076a704e14..28c98e01019184c604a3825cec4b497fc6482848 100644 --- a/checkpoint-24/trainer_state.json +++ b/checkpoint-24/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 24, "best_metric": 0.04339282959699631, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-24", "epoch": 5.842105263157895, @@ -7,7 +6,7 @@ "global_step": 24, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 }, @@ -269,7 +268,7 @@ "kl": 0.1787109375, "learning_rate": 9.01061596377522e-05, "loss": -0.04504441097378731, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.027318883687257767, "reward_std": 0.10441224090754986, @@ -283,7 +282,7 @@ "grad_norm": 0.005998397711664438, "learning_rate": 8.83022221559489e-05, "loss": -0.045487549155950546, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 18, "train_speed(iter/s)": 0.000432 }, @@ -298,7 +297,7 @@ "eval_reward_std": 0.10691346973180771, "eval_rewards/CosineReward": 0.03729327768087387, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1041.2277, + "eval_runtime": 1041.231, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 18 @@ -311,7 +310,7 @@ "kl": 0.1820068359375, "learning_rate": 8.636868207865244e-05, "loss": -0.03466903418302536, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.466796875, "reward": 0.04069916973821819, "reward_std": 0.11991005763411522, @@ -327,7 +326,7 @@ "kl": 0.19287109375, "learning_rate": 8.43120818934367e-05, "loss": -0.03502114117145538, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 20, "train_speed(iter/s)": 0.000424 }, @@ -339,14 +338,14 @@ "kl": 0.17626953125, "learning_rate": 8.213938048432697e-05, "loss": -0.008662773296236992, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.04996980866417289, "reward_std": 0.13849420100450516, "rewards/CosineReward": 0.049969930201768875, "rewards/RepetitionPenalty": -1.1864573679076784e-07, "step": 21, - "train_speed(iter/s)": 0.000407 + "train_speed(iter/s)": 0.000408 }, { "clip_ratio": 5.869188044016482e-05, @@ -355,7 +354,7 @@ "kl": 0.178955078125, "learning_rate": 7.985792958513931e-05, "loss": -0.008743642829358578, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 22, "train_speed(iter/s)": 0.000426 }, @@ -367,7 +366,7 @@ "kl": 0.1796875, "learning_rate": 7.74754489035403e-05, "loss": -0.03423420712351799, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.583984375, "reward": 0.034468831261619925, "reward_std": 0.11841745302081108, @@ -381,7 +380,7 @@ "grad_norm": 0.014131724834442139, "learning_rate": 7.500000000000001e-05, "loss": -0.03426633030176163, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 24, "train_speed(iter/s)": 0.000427 }, @@ -396,7 +395,7 @@ "eval_reward_std": 0.10456253588199615, "eval_rewards/CosineReward": 0.04339282959699631, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1045.0653, + "eval_runtime": 1045.0632, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 24 diff --git a/checkpoint-24/training_args.bin b/checkpoint-24/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-24/training_args.bin +++ b/checkpoint-24/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-26/adapter_config.json b/checkpoint-26/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-26/adapter_config.json +++ b/checkpoint-26/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-26/trainer_state.json b/checkpoint-26/trainer_state.json index 602a6c1309f1ee6b6bfc89540ccc6ada6b1d2e89..5b072b987db923c7897214c7f630cb7ed87c56ab 100644 --- a/checkpoint-26/trainer_state.json +++ b/checkpoint-26/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 24, "best_metric": 0.04339282959699631, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-24", "epoch": 6.421052631578947, @@ -7,7 +6,7 @@ "global_step": 26, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 }, @@ -269,7 +268,7 @@ "kl": 0.1787109375, "learning_rate": 9.01061596377522e-05, "loss": -0.04504441097378731, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.027318883687257767, "reward_std": 0.10441224090754986, @@ -283,7 +282,7 @@ "grad_norm": 0.005998397711664438, "learning_rate": 8.83022221559489e-05, "loss": -0.045487549155950546, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 18, "train_speed(iter/s)": 0.000432 }, @@ -298,7 +297,7 @@ "eval_reward_std": 0.10691346973180771, "eval_rewards/CosineReward": 0.03729327768087387, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1041.2277, + "eval_runtime": 1041.231, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 18 @@ -311,7 +310,7 @@ "kl": 0.1820068359375, "learning_rate": 8.636868207865244e-05, "loss": -0.03466903418302536, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.466796875, "reward": 0.04069916973821819, "reward_std": 0.11991005763411522, @@ -327,7 +326,7 @@ "kl": 0.19287109375, "learning_rate": 8.43120818934367e-05, "loss": -0.03502114117145538, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 20, "train_speed(iter/s)": 0.000424 }, @@ -339,14 +338,14 @@ "kl": 0.17626953125, "learning_rate": 8.213938048432697e-05, "loss": -0.008662773296236992, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.04996980866417289, "reward_std": 0.13849420100450516, "rewards/CosineReward": 0.049969930201768875, "rewards/RepetitionPenalty": -1.1864573679076784e-07, "step": 21, - "train_speed(iter/s)": 0.000407 + "train_speed(iter/s)": 0.000408 }, { "clip_ratio": 5.869188044016482e-05, @@ -355,7 +354,7 @@ "kl": 0.178955078125, "learning_rate": 7.985792958513931e-05, "loss": -0.008743642829358578, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 22, "train_speed(iter/s)": 0.000426 }, @@ -367,7 +366,7 @@ "kl": 0.1796875, "learning_rate": 7.74754489035403e-05, "loss": -0.03423420712351799, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.583984375, "reward": 0.034468831261619925, "reward_std": 0.11841745302081108, @@ -381,7 +380,7 @@ "grad_norm": 0.014131724834442139, "learning_rate": 7.500000000000001e-05, "loss": -0.03426633030176163, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 24, "train_speed(iter/s)": 0.000427 }, @@ -396,7 +395,7 @@ "eval_reward_std": 0.10456253588199615, "eval_rewards/CosineReward": 0.04339282959699631, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1045.0653, + "eval_runtime": 1045.0632, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 24 @@ -409,7 +408,7 @@ "kl": 0.1800537109375, "learning_rate": 7.243995901002312e-05, "loss": -0.02097315341234207, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.6171875, "reward": 0.03010205877944827, "reward_std": 0.10742511600255966, @@ -425,7 +424,7 @@ "kl": 0.18408203125, "learning_rate": 6.980398830195785e-05, "loss": -0.02103913575410843, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 26, "train_speed(iter/s)": 0.000421 } diff --git a/checkpoint-26/training_args.bin b/checkpoint-26/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-26/training_args.bin +++ b/checkpoint-26/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-28-merged/args.json b/checkpoint-28-merged/args.json new file mode 100644 index 0000000000000000000000000000000000000000..e5fddc18fe4219cc621c4285a0faf4591e553d74 --- /dev/null +++ b/checkpoint-28-merged/args.json @@ -0,0 +1,416 @@ +{ + "model": "/mnt/nvme5n1p1/distill-14b-rl-70", + "model_type": "deepseek_r1_distill", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "num_labels": null, + "rope_scaling": null, + "device_map": null, + "max_memory": {}, + "local_repo_path": null, + "template": "deepseek_r1", + "system": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step. Return final answer within \\\\boxed{}.", + "max_length": 16384, + "truncation_strategy": "left", + "max_pixels": null, + "tools_prompt": "react_en", + "norm_bbox": null, + "response_prefix": null, + "padding_side": "right", + "loss_scale": "last_round", + "sequence_parallel_size": 1, + "use_chat_template": true, + "template_backend": "swift", + "dataset": [ + "stage2_aime.jsonl" + ], + "val_dataset": [], + "split_dataset_ratio": 0.01, + "data_seed": 42, + "dataset_num_proc": 52, + "streaming": false, + "enable_cache": false, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": false, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": 64, + "temperature": 1.0, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.1, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "ckpt_dir": "/mnt/nvme5n1p1/distill-14b-rl-70", + "load_dataset_config": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "seed": 42, + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "use_hf": true, + "hub_token": null, + "custom_register_path": [], + "ignore_args_error": false, + "use_swift_lora": false, + "output_dir": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345", + "overwrite_output_dir": false, + "do_train": false, + "do_eval": false, + "do_predict": false, + "eval_strategy": "steps", + "prediction_loss_only": false, + "per_device_train_batch_size": 4, + "per_device_eval_batch_size": 4, + "per_gpu_train_batch_size": null, + "per_gpu_eval_batch_size": null, + "gradient_accumulation_steps": 4, + "eval_accumulation_steps": null, + "eval_delay": 0, + "torch_empty_cache_steps": null, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "adam_epsilon": 1e-08, + "max_grad_norm": 1.0, + "num_train_epochs": 15.0, + "max_steps": -1, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": null, + "warmup_ratio": 0.1, + "warmup_steps": 0, + "log_level": "passive", + "log_level_replica": "warning", + "log_on_each_node": true, + "logging_dir": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/runs", + "logging_strategy": "steps", + "logging_first_step": true, + "logging_steps": 1, + "logging_nan_inf_filter": true, + "save_strategy": "steps", + "save_steps": 2.0, + "save_total_limit": 100, + "save_safetensors": true, + "save_on_each_node": true, + "save_only_model": false, + "restore_callback_states_from_checkpoint": false, + "no_cuda": false, + "use_cpu": false, + "use_mps_device": false, + "jit_mode_eval": false, + "use_ipex": false, + "bf16": true, + "fp16": false, + "fp16_opt_level": "O1", + "half_precision_backend": "auto", + "bf16_full_eval": false, + "fp16_full_eval": false, + "tf32": null, + "local_rank": 0, + "ddp_backend": null, + "tpu_num_cores": null, + "tpu_metrics_debug": false, + "debug": null, + "dataloader_drop_last": false, + "eval_steps": 6.0, + "dataloader_num_workers": 52, + "dataloader_prefetch_factor": null, + "past_index": -1, + "run_name": null, + "disable_tqdm": null, + "label_names": null, + "load_best_model_at_end": false, + "metric_for_best_model": "reward", + "greater_is_better": true, + "ignore_data_skip": false, + "fsdp": "", + "fsdp_min_num_params": 0, + "fsdp_config": null, + "fsdp_transformer_layer_cls_to_wrap": null, + "accelerator_config": { + "dispatch_batches": false + }, + "deepspeed": { + "fp16": { + "enabled": "auto", + "loss_scale": 0, + "loss_scale_window": 1000, + "initial_scale_power": 16, + "hysteresis": 2, + "min_loss_scale": 1 + }, + "bf16": { + "enabled": "auto" + }, + "zero_optimization": { + "stage": 2, + "offload_optimizer": { + "device": "none", + "pin_memory": true + }, + "allgather_partitions": true, + "allgather_bucket_size": 200000000.0, + "overlap_comm": true, + "reduce_scatter": true, + "reduce_bucket_size": 200000000.0, + "contiguous_gradients": true + }, + "gradient_accumulation_steps": "auto", + "gradient_clipping": "auto", + "steps_per_print": 2000, + "train_batch_size": "auto", + "train_micro_batch_size_per_gpu": "auto", + "wall_clock_breakdown": false + }, + "label_smoothing_factor": 0.0, + "optim": "adamw_torch", + "optim_args": null, + "adafactor": false, + "group_by_length": false, + "length_column_name": "length", + "report_to": [ + "wandb" + ], + "ddp_find_unused_parameters": null, + "ddp_bucket_cap_mb": null, + "ddp_broadcast_buffers": null, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": false, + "skip_memory_metrics": true, + "use_legacy_prediction_loop": false, + "push_to_hub": false, + "resume_from_checkpoint": null, + "hub_model_id": null, + "hub_strategy": "every_save", + "hub_private_repo": null, + "hub_always_push": false, + "gradient_checkpointing": true, + "gradient_checkpointing_kwargs": null, + "include_inputs_for_metrics": false, + "include_for_metrics": [], + "eval_do_concat_batches": true, + "fp16_backend": "auto", + "evaluation_strategy": "steps", + "push_to_hub_model_id": null, + "push_to_hub_organization": null, + "push_to_hub_token": null, + "mp_parameters": "", + "auto_find_batch_size": false, + "full_determinism": false, + "torchdynamo": null, + "ray_scope": "last", + "ddp_timeout": 1800, + "torch_compile": false, + "torch_compile_backend": null, + "torch_compile_mode": null, + "dispatch_batches": null, + "split_batches": null, + "include_tokens_per_second": false, + "include_num_input_tokens_seen": false, + "neftune_noise_alpha": null, + "optim_target_modules": null, + "batch_eval_metrics": false, + "eval_on_start": false, + "use_liger_kernel": false, + "eval_use_gather_object": false, + "average_tokens_across_devices": false, + "sortish_sampler": false, + "predict_with_generate": false, + "generation_max_length": null, + "generation_num_beams": null, + "generation_config": null, + "freeze_parameters": [], + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 32, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "lorap_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "lora_ga_batch_size": 2, + "lora_ga_iters": 2, + "lora_ga_max_length": 1024, + "lora_ga_direction": "ArB2r", + "lora_ga_scale": "stable", + "lora_ga_stable_gamma": 16, + "init_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "acc_steps": 1, + "swanlab_token": null, + "swanlab_project": null, + "swanlab_workspace": null, + "swanlab_exp_name": null, + "swanlab_mode": "cloud", + "add_version": true, + "resume_only_model": false, + "check_model": true, + "create_checkpoint_symlink": false, + "packing": false, + "lazy_tokenize": false, + "loss_type": null, + "optimizer": null, + "metric": null, + "acc_strategy": "token", + "zero_hpz_partition_size": null, + "reward_model": null, + "reward_adapters": [], + "reward_model_type": null, + "reward_model_revision": null, + "num_ppo_epochs": 4, + "whiten_rewards": false, + "kl_coef": 0.05, + "cliprange": 0.2, + "vf_coef": 0.1, + "cliprange_value": 0.2, + "gamma": 1.0, + "lam": 0.95, + "num_mini_batches": 1, + "local_rollout_forward_batch_size": 64, + "num_sample_generations": 10, + "response_length": 512, + "missing_eos_penalty": null, + "num_infer_workers": 8, + "vllm_max_num_seqs": 256, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_enable_prefix_caching": true, + "cosine_min_len_value_wrong": 0.0, + "cosine_max_len_value_wrong": -0.2, + "cosine_min_len_value_correct": 0.8, + "cosine_max_len_value_correct": 0.4, + "cosine_max_len": 12288, + "repetition_n_grams": 40, + "repetition_max_penalty": -0.05, + "use_lmdeploy": false, + "lmdeploy_device": "auto", + "lmdeploy_session_len": null, + "lmdeploy_cache_max_entry_count": 0.8, + "async_generate": false, + "tensor_parallel_size": 1, + "sleep_level": 0, + "move_model_batches": null, + "offload_optimizer": false, + "offload_model": false, + "gc_collect_after_offload": false, + "num_generations": 8, + "max_completion_length": 12288, + "ds3_gather_for_generation": true, + "reward_funcs": [ + "cosine", + "repetition" + ], + "reward_weights": null, + "log_completions": true, + "use_vllm": false, + "vllm_device": [ + "auto" + ], + "vllm_gpu_memory_utilization": 0.9, + "vllm_max_model_len": null, + "num_iterations": 2, + "epsilon": 0.2, + "rlhf_type": "grpo", + "ref_model": null, + "ref_model_type": null, + "ref_model_revision": null, + "beta": 0.04, + "label_smoothing": 0, + "rpo_alpha": 1.0, + "cpo_alpha": 1.0, + "simpo_gamma": 1, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "rank": 0, + "global_world_size": 32, + "local_world_size": 8, + "model_suffix": "distill-14b-rl-70", + "model_info": "ModelInfo(model_type='deepseek_r1_distill', model_dir='/mnt/nvme5n1p1/distill-14b-rl-70', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='deepseek_r1_distill', model_groups=[ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=['transformers>=4.37'], tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='deepseek_r1', get_function=, model_arch='llama', architectures=['Qwen2ForCausalLM', 'LlamaForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=[], tags=[])", + "model_dir": "/mnt/nvme5n1p1/distill-14b-rl-70", + "hub": "", + "training_args": "GRPOConfig(output_dir='/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=4, per_device_eval_batch_size=4, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=15.0, max_steps=-1, lr_scheduler_type=, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/runs', logging_strategy=, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=, save_steps=2, save_total_limit=100, save_safetensors=True, save_on_each_node=True, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=6, dataloader_num_workers=52, dataloader_prefetch_factor=None, past_index=-1, run_name='/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': True, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, max_prompt_length=512, num_generations=8, max_completion_length=12288, ds3_gather_for_generation=True, temperature=1.0, top_p=0.9, top_k=50, min_p=None, repetition_penalty=1.1, cache_implementation=None, use_vllm=False, vllm_server_host='0.0.0.0', vllm_server_port=8000, vllm_server_timeout=120.0, vllm_guided_decoding_regex=None, beta=0.04, num_iterations=2, epsilon=0.2, epsilon_high=None, reward_weights=None, scale_rewards=True, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, log_completions=True, vllm_device=['auto'], vllm_gpu_memory_utilization=0.9, vllm_dtype=None, vllm_max_model_len=None, vllm_enable_prefix_caching=True, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora', optimizer=None, local_repo_path=None, galore_config=None, num_infer_workers=8, vllm_max_num_seqs=256, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, cosine_min_len_value_wrong=0.0, cosine_max_len_value_wrong=-0.2, cosine_min_len_value_correct=0.8, cosine_max_len_value_correct=0.4, cosine_max_len=12288, repetition_n_grams=40, repetition_max_penalty=-0.05, use_lmdeploy=False, lmdeploy_device='auto', lmdeploy_session_len=None, lmdeploy_cache_max_entry_count=0.8, async_generate=False, tensor_parallel_size=1, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, gc_collect_after_offload=False, stop_words=[])" +} \ No newline at end of file diff --git a/checkpoint-28-merged/config.json b/checkpoint-28-merged/config.json new file mode 100644 index 0000000000000000000000000000000000000000..cdc5a80047e548b6f76e47be14daefacc4008243 --- /dev/null +++ b/checkpoint-28-merged/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "/mnt/nvme5n1p1/distill-14b-rl-70", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.49.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/checkpoint-28-merged/generation_config.json b/checkpoint-28-merged/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..01dfe4bd984fc258e2cbd022dd230261e36e4501 --- /dev/null +++ b/checkpoint-28-merged/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.49.0" +} diff --git a/checkpoint-28-merged/model-00001-of-00006.safetensors b/checkpoint-28-merged/model-00001-of-00006.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f68ec9fa35c46d7a8d5911656d7da03932f17624 --- /dev/null +++ b/checkpoint-28-merged/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dad1cc6ad2fcb07c0d28f1fefa020b05bd6f5ad928543fa827063515a82fd36 +size 4986211280 diff --git a/checkpoint-28-merged/model-00002-of-00006.safetensors b/checkpoint-28-merged/model-00002-of-00006.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7b1e69b789d6052f551e71e0d54bd9a99d2b6c7 --- /dev/null +++ b/checkpoint-28-merged/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3373a98462f51330b13f1176c78eab7dfc305789dd096ce8db2fe4c09af0a12 +size 4954847344 diff --git a/checkpoint-28-merged/model-00003-of-00006.safetensors b/checkpoint-28-merged/model-00003-of-00006.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9554d60df5f4d2d31acf0849aeae0807d3d26f4a --- /dev/null +++ b/checkpoint-28-merged/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d38db81bd02623d6f2fbdbc2b4f1326cbc29a33dfa9e74f815e8ce53eda5be0 +size 4954847392 diff --git a/checkpoint-28-merged/model-00004-of-00006.safetensors b/checkpoint-28-merged/model-00004-of-00006.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98605efec2b551fefb038560861b5b7e2449b426 --- /dev/null +++ b/checkpoint-28-merged/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72420ed55ee03b62e4d0048080fc2e77480b59c591ea19af59df846ce40a6085 +size 4954847392 diff --git a/checkpoint-28-merged/model-00005-of-00006.safetensors b/checkpoint-28-merged/model-00005-of-00006.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ba87eca6eee22984092b4d284ec5530f574d378 --- /dev/null +++ b/checkpoint-28-merged/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e7b4b23b74c4b8b7644ebf4d3033cf1b0831e11df821cde515e076716b0b1a +size 4954847392 diff --git a/checkpoint-28-merged/model-00006-of-00006.safetensors b/checkpoint-28-merged/model-00006-of-00006.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53f4efd9babe025e4f126a9eaa5918726658822e --- /dev/null +++ b/checkpoint-28-merged/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f59b1d4bb65717f1d0dca8dfd0a2978bc6a035fe192d352ea7b08f971972996 +size 4734533160 diff --git a/checkpoint-28-merged/model.safetensors.index.json b/checkpoint-28-merged/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..0e9b53532550dfddbf42730aeeb499a3bb7a707f --- /dev/null +++ b/checkpoint-28-merged/model.safetensors.index.json @@ -0,0 +1,586 @@ +{ + "metadata": { + "total_size": 29540067328 + }, + "weight_map": { + "lm_head.weight": "model-00006-of-00006.safetensors", + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} diff --git a/checkpoint-28-merged/special_tokens_map.json b/checkpoint-28-merged/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/checkpoint-28-merged/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-28-merged/tokenizer.json b/checkpoint-28-merged/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/checkpoint-28-merged/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/checkpoint-28-merged/tokenizer_config.json b/checkpoint-28-merged/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..96810ec71ae9f7de6d04f148028be38fa50c3de5 --- /dev/null +++ b/checkpoint-28-merged/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/checkpoint-28/adapter_config.json b/checkpoint-28/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-28/adapter_config.json +++ b/checkpoint-28/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-28/trainer_state.json b/checkpoint-28/trainer_state.json index 1ecbac39b96cd3bf5b99ae1c405479b2290145ec..148e40ed0b36a607a26cd48bcc7a44e47f551f9b 100644 --- a/checkpoint-28/trainer_state.json +++ b/checkpoint-28/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 24, "best_metric": 0.04339282959699631, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-24", "epoch": 6.842105263157895, @@ -7,7 +6,7 @@ "global_step": 28, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 }, @@ -143,7 +142,7 @@ "kl": 0.0963134765625, "learning_rate": 9.924038765061042e-05, "loss": -0.05842069163918495, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.255859375, "reward": 0.03643610421568155, "reward_std": 0.11898956261575222, @@ -159,7 +158,7 @@ "kl": 0.1185302734375, "learning_rate": 9.865224352899119e-05, "loss": -0.06491819024085999, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 10, "train_speed(iter/s)": 0.000436 }, @@ -171,7 +170,7 @@ "kl": 0.1275634765625, "learning_rate": 9.789947561577445e-05, "loss": -0.04600231721997261, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.361328125, "reward": 0.023204635945148766, "reward_std": 0.10593634657561779, @@ -185,7 +184,7 @@ "grad_norm": 0.05781339108943939, "learning_rate": 9.698463103929542e-05, "loss": -0.05069056898355484, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 12, "train_speed(iter/s)": 0.000439 }, @@ -200,7 +199,7 @@ "eval_reward_std": 0.10685288906097412, "eval_rewards/CosineReward": 0.03234308212995529, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1025.9053, + "eval_runtime": 1025.9041, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 12 @@ -213,7 +212,7 @@ "kl": 0.151123046875, "learning_rate": 9.591080534401371e-05, "loss": -0.02191038429737091, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.419921875, "reward": 0.035983758978545666, "reward_std": 0.11553369648754597, @@ -229,7 +228,7 @@ "kl": 0.169189453125, "learning_rate": 9.468163201617062e-05, "loss": -0.022672578692436218, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 14, "train_speed(iter/s)": 0.000427 }, @@ -241,7 +240,7 @@ "kl": 0.166748046875, "learning_rate": 9.330127018922194e-05, "loss": -0.059799157083034515, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.4765625, "reward": 0.03584331553429365, "reward_std": 0.11829411797225475, @@ -257,7 +256,7 @@ "kl": 0.16748046875, "learning_rate": 9.177439057064683e-05, "loss": -0.06071458384394646, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 16, "train_speed(iter/s)": 0.000431 }, @@ -269,7 +268,7 @@ "kl": 0.1787109375, "learning_rate": 9.01061596377522e-05, "loss": -0.04504441097378731, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.027318883687257767, "reward_std": 0.10441224090754986, @@ -283,7 +282,7 @@ "grad_norm": 0.005998397711664438, "learning_rate": 8.83022221559489e-05, "loss": -0.045487549155950546, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 18, "train_speed(iter/s)": 0.000432 }, @@ -298,7 +297,7 @@ "eval_reward_std": 0.10691346973180771, "eval_rewards/CosineReward": 0.03729327768087387, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1041.2277, + "eval_runtime": 1041.231, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 18 @@ -311,7 +310,7 @@ "kl": 0.1820068359375, "learning_rate": 8.636868207865244e-05, "loss": -0.03466903418302536, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.466796875, "reward": 0.04069916973821819, "reward_std": 0.11991005763411522, @@ -327,7 +326,7 @@ "kl": 0.19287109375, "learning_rate": 8.43120818934367e-05, "loss": -0.03502114117145538, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 20, "train_speed(iter/s)": 0.000424 }, @@ -339,14 +338,14 @@ "kl": 0.17626953125, "learning_rate": 8.213938048432697e-05, "loss": -0.008662773296236992, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.5625, "reward": 0.04996980866417289, "reward_std": 0.13849420100450516, "rewards/CosineReward": 0.049969930201768875, "rewards/RepetitionPenalty": -1.1864573679076784e-07, "step": 21, - "train_speed(iter/s)": 0.000407 + "train_speed(iter/s)": 0.000408 }, { "clip_ratio": 5.869188044016482e-05, @@ -355,7 +354,7 @@ "kl": 0.178955078125, "learning_rate": 7.985792958513931e-05, "loss": -0.008743642829358578, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 22, "train_speed(iter/s)": 0.000426 }, @@ -367,7 +366,7 @@ "kl": 0.1796875, "learning_rate": 7.74754489035403e-05, "loss": -0.03423420712351799, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.583984375, "reward": 0.034468831261619925, "reward_std": 0.11841745302081108, @@ -381,7 +380,7 @@ "grad_norm": 0.014131724834442139, "learning_rate": 7.500000000000001e-05, "loss": -0.03426633030176163, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 24, "train_speed(iter/s)": 0.000427 }, @@ -396,7 +395,7 @@ "eval_reward_std": 0.10456253588199615, "eval_rewards/CosineReward": 0.04339282959699631, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1045.0653, + "eval_runtime": 1045.0632, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 24 @@ -409,7 +408,7 @@ "kl": 0.1800537109375, "learning_rate": 7.243995901002312e-05, "loss": -0.02097315341234207, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.6171875, "reward": 0.03010205877944827, "reward_std": 0.10742511600255966, @@ -425,7 +424,7 @@ "kl": 0.18408203125, "learning_rate": 6.980398830195785e-05, "loss": -0.02103913575410843, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 26, "train_speed(iter/s)": 0.000421 }, @@ -437,7 +436,7 @@ "kl": 0.174560546875, "learning_rate": 6.710100716628344e-05, "loss": -0.03593946248292923, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.513671875, "reward": 0.04752760287374258, "reward_std": 0.14935147762298584, @@ -453,7 +452,7 @@ "kl": 0.182373046875, "learning_rate": 6.434016163555452e-05, "loss": -0.03595500811934471, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 28, "train_speed(iter/s)": 0.000422 } diff --git a/checkpoint-28/training_args.bin b/checkpoint-28/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-28/training_args.bin +++ b/checkpoint-28/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-4/adapter_config.json b/checkpoint-4/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-4/adapter_config.json +++ b/checkpoint-4/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-4/trainer_state.json b/checkpoint-4/trainer_state.json index b9e6e0a1939e20ff64b2c526958f9071d2092ce6..f595f5961ff8df694c28b2d941589615801e0294 100644 --- a/checkpoint-4/trainer_state.json +++ b/checkpoint-4/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8421052631578947, @@ -7,7 +6,7 @@ "global_step": 4, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 } diff --git a/checkpoint-4/training_args.bin b/checkpoint-4/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-4/training_args.bin +++ b/checkpoint-4/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-6/adapter_config.json b/checkpoint-6/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-6/adapter_config.json +++ b/checkpoint-6/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-6/trainer_state.json b/checkpoint-6/trainer_state.json index 788be4857b9899abbfb479f3a84793787ed74e90..3667b41328b83c70faf4e00796621b5ccfe72baf 100644 --- a/checkpoint-6/trainer_state.json +++ b/checkpoint-6/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 6, "best_metric": 0.012996690347790718, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-6", "epoch": 1.4210526315789473, @@ -7,7 +6,7 @@ "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 diff --git a/checkpoint-6/training_args.bin b/checkpoint-6/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-6/training_args.bin +++ b/checkpoint-6/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/checkpoint-8/adapter_config.json b/checkpoint-8/adapter_config.json index ff0f4cc95c39fe3def3378592de89aa4d14e7c68..3f8d06e83be137d4af154849ed1686625c42e280 100644 --- a/checkpoint-8/adapter_config.json +++ b/checkpoint-8/adapter_config.json @@ -23,13 +23,13 @@ "rank_pattern": {}, "revision": null, "target_modules": [ - "o_proj", - "gate_proj", "v_proj", + "gate_proj", "k_proj", + "o_proj", "up_proj", - "down_proj", - "q_proj" + "q_proj", + "down_proj" ], "task_type": "CAUSAL_LM", "use_dora": false, diff --git a/checkpoint-8/trainer_state.json b/checkpoint-8/trainer_state.json index ff8b0e6b148baae81697b538a5071347d6601c0c..1878466a3ed5546ada8088e46201029d0f48bef5 100644 --- a/checkpoint-8/trainer_state.json +++ b/checkpoint-8/trainer_state.json @@ -1,5 +1,4 @@ { - "best_global_step": 6, "best_metric": 0.012996690347790718, "best_model_checkpoint": "/mnt/nvme5n1p1/trained_grpo_distill_14b_rl_70_s3/v3-20250330-200345/checkpoint-6", "epoch": 1.8421052631578947, @@ -7,7 +6,7 @@ "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, - "is_world_process_zero": false, + "is_world_process_zero": true, "log_history": [ { "clip_ratio": 0.0, @@ -17,14 +16,14 @@ "kl": 0.0, "learning_rate": 1.6666666666666667e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.11328125, "reward": -0.002658387296833098, "reward_std": 0.06134121119976044, "rewards/CosineReward": -0.0026579967816360295, "rewards/RepetitionPenalty": -3.8975886695880035e-07, "step": 1, - "train_speed(iter/s)": 0.000241 + "train_speed(iter/s)": 0.000242 }, { "clip_ratio": 0.0, @@ -33,9 +32,9 @@ "kl": 0.0, "learning_rate": 3.3333333333333335e-05, "loss": -0.11016345024108887, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 2, - "train_speed(iter/s)": 0.000466 + "train_speed(iter/s)": 0.000467 }, { "clip_ratio": 1.3441811461234465e-05, @@ -45,7 +44,7 @@ "kl": 9.50181856751442e-07, "learning_rate": 5e-05, "loss": -0.06604708731174469, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.13671875, "reward": 0.0006296975770965219, "reward_std": 0.07172460854053497, @@ -61,7 +60,7 @@ "kl": 1.1101365089416504e-05, "learning_rate": 6.666666666666667e-05, "loss": -0.06727766245603561, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 4, "train_speed(iter/s)": 0.000458 }, @@ -73,7 +72,7 @@ "kl": 0.00017762184143066406, "learning_rate": 8.333333333333334e-05, "loss": -0.09315311908721924, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.119140625, "reward": -0.005135859013535082, "reward_std": 0.07994875870645046, @@ -87,7 +86,7 @@ "grad_norm": 0.18263348937034607, "learning_rate": 0.0001, "loss": -0.1041698157787323, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 6, "train_speed(iter/s)": 0.000459 }, @@ -102,7 +101,7 @@ "eval_reward_std": 0.08769983053207397, "eval_rewards/CosineReward": 0.012996694073081017, "eval_rewards/RepetitionPenalty": 0.0, - "eval_runtime": 1030.1122, + "eval_runtime": 1030.1127, "eval_samples_per_second": 0.001, "eval_steps_per_second": 0.001, "step": 6 @@ -115,7 +114,7 @@ "kl": 0.017406463623046875, "learning_rate": 9.991540791356342e-05, "loss": -0.051375165581703186, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "response_clip_ratio": 0.1484375, "reward": 0.004909618757665157, "reward_std": 0.08167182095348835, @@ -131,7 +130,7 @@ "kl": 0.089599609375, "learning_rate": 9.966191788709716e-05, "loss": -0.05105742812156677, - "memory(GiB)": 186.69, + "memory(GiB)": 182.91, "step": 8, "train_speed(iter/s)": 0.000433 } diff --git a/checkpoint-8/training_args.bin b/checkpoint-8/training_args.bin index f36a7dd9bdc6cb2a2d931801db92f6b3a1142a0b..a5c75ad76398d7f403ccc1a74c463d2dab6465ca 100644 --- a/checkpoint-8/training_args.bin +++ b/checkpoint-8/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e699c24e86e1a1f412d6f8c2d25c0baf53692e08baa670377bbc8abc7e07257 +oid sha256:1207fcb9d91c7deb13a80104f3ca89016b4cff3ef13ebd136ee6320d5a9888bb size 9809 diff --git a/completions.jsonl b/completions.jsonl index 815711e07f8986297ea755fa4b4086e2c7899166..97b3e9dc3878a77a5dff83d2f2c280879a247d35 100644 --- a/completions.jsonl +++ b/completions.jsonl @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c930dbbe3610edb7858dea080de882f3feb1f2036ff7d1d075f6228d26e17d2f -size 256188958 +oid sha256:d0cac5ba83180c1a0721b5e0604d154eda7f5a1aee67b1ced24357e9e6c7e175 +size 272303397 diff --git a/logging.jsonl b/logging.jsonl index 8596b3a1eac494e48aaaf7458044daf9aa8716d1..f5c2129421a0917ea55a5da41e0ceefbdcb02c82 100644 --- a/logging.jsonl +++ b/logging.jsonl @@ -30,3 +30,5 @@ {"loss": -0.02103914, "grad_norm": 0.00989576, "learning_rate": 6.98e-05, "memory(GiB)": 182.91, "train_speed(iter/s)": 0.000421, "kl": 0.18408203, "clip_ratio": 4.822e-05, "epoch": 6.42105263, "global_step/max_steps": "26/60", "percentage": "43.33%", "elapsed_time": "17h 8m 51s", "remaining_time": "22h 25m 25s"} {"loss": -0.03593946, "grad_norm": 0.00436775, "learning_rate": 6.71e-05, "memory(GiB)": 182.91, "train_speed(iter/s)": 0.000408, "completion_length": 10197.09960938, "response_clip_ratio": 0.51367188, "rewards/CosineReward": 0.0475284, "rewards/RepetitionPenalty": -7.9e-07, "reward": 0.0475276, "reward_std": 0.14935148, "kl": 0.17456055, "clip_ratio": 5.443e-05, "epoch": 6.63157895, "global_step/max_steps": "27/60", "percentage": "45.00%", "elapsed_time": "18h 22m 20s", "remaining_time": "22h 27m 18s"} {"loss": -0.03595501, "grad_norm": 0.00527766, "learning_rate": 6.434e-05, "memory(GiB)": 182.91, "train_speed(iter/s)": 0.000422, "kl": 0.18237305, "clip_ratio": 5.954e-05, "epoch": 6.84210526, "global_step/max_steps": "28/60", "percentage": "46.67%", "elapsed_time": "18h 25m 42s", "remaining_time": "21h 3m 40s"} +{"loss": -0.03189056, "grad_norm": 0.0168444, "learning_rate": 6.153e-05, "memory(GiB)": 182.91, "train_speed(iter/s)": 0.00041, "completion_length": 10427.296875, "response_clip_ratio": 0.54101562, "rewards/CosineReward": 0.04964366, "rewards/RepetitionPenalty": -7.5e-07, "reward": 0.04964291, "reward_std": 0.13294973, "kl": 0.18701172, "clip_ratio": 5.28e-05, "epoch": 7.21052632, "global_step/max_steps": "29/60", "percentage": "48.33%", "elapsed_time": "19h 37m 59s", "remaining_time": "20h 59m 14s"} +{"loss": -0.03209799, "grad_norm": 0.01443596, "learning_rate": 5.868e-05, "memory(GiB)": 182.91, "train_speed(iter/s)": 0.000423, "epoch": 7.42105263, "global_step/max_steps": "30/60", "percentage": "50.00%", "elapsed_time": "19h 40m 53s", "remaining_time": "19h 40m 53s"}