| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8648648648648649, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 174.78125, | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 58.83098220825195, | |
| "kl": 0.0, | |
| "learning_rate": 4.965903258506806e-07, | |
| "loss": 0.0, | |
| "reward": 0.0901489004609175, | |
| "reward_std": 0.05298215994844213, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.0901489004609175, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "completion_length": 190.0625, | |
| "epoch": 0.17297297297297298, | |
| "grad_norm": 23.854074478149414, | |
| "kl": 0.005669997570294072, | |
| "learning_rate": 4.698684378016222e-07, | |
| "loss": 0.0, | |
| "reward": 0.05685851280577481, | |
| "reward_std": 0.0630133812665008, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.08088976284489036, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": -0.024031249806284904, | |
| "step": 4 | |
| }, | |
| { | |
| "completion_length": 148.5625, | |
| "epoch": 0.2594594594594595, | |
| "grad_norm": 6.543165683746338, | |
| "kl": 0.0016538046838832088, | |
| "learning_rate": 4.193203929064353e-07, | |
| "loss": 0.0, | |
| "reward": 0.11900349933421239, | |
| "reward_std": 0.05877241454436444, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.11600349884247407, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.003000000026077032, | |
| "step": 6 | |
| }, | |
| { | |
| "completion_length": 168.40625, | |
| "epoch": 0.34594594594594597, | |
| "grad_norm": 15.460132598876953, | |
| "kl": 0.013466783606418176, | |
| "learning_rate": 3.5042385616324236e-07, | |
| "loss": 0.0, | |
| "reward": 0.07271899108309299, | |
| "reward_std": 0.220687849301612, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0625, | |
| "rewards/question_recreation_reward_func": 0.08075023861601949, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": -0.07053124718368053, | |
| "step": 8 | |
| }, | |
| { | |
| "completion_length": 190.03125, | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 7.88490629196167, | |
| "kl": 0.002504798882000614, | |
| "learning_rate": 2.706448363680831e-07, | |
| "loss": 0.0, | |
| "reward": 0.07228551083244383, | |
| "reward_std": 0.02558132015474257, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.07228551083244383, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 171.03125, | |
| "epoch": 0.518918918918919, | |
| "grad_norm": 4.811025619506836, | |
| "kl": 0.005568824522924842, | |
| "learning_rate": 1.886286282148002e-07, | |
| "loss": 0.0, | |
| "reward": 0.08030106464866549, | |
| "reward_std": 0.05834139112266712, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.0745510651031509, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.005750000011175871, | |
| "step": 12 | |
| }, | |
| { | |
| "completion_length": 183.03125, | |
| "epoch": 0.6054054054054054, | |
| "grad_norm": 6.628332614898682, | |
| "kl": 0.0027780618984252214, | |
| "learning_rate": 1.1326296046939333e-07, | |
| "loss": 0.0, | |
| "reward": 0.10023158206604421, | |
| "reward_std": 0.14612931123519957, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0625, | |
| "rewards/question_recreation_reward_func": 0.07216907886322588, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": -0.03443750087171793, | |
| "step": 14 | |
| }, | |
| { | |
| "completion_length": 141.21875, | |
| "epoch": 0.6918918918918919, | |
| "grad_norm": 9.415384292602539, | |
| "kl": 0.008354716750545776, | |
| "learning_rate": 5.271487265090163e-08, | |
| "loss": 0.0, | |
| "reward": 0.10022578242933378, | |
| "reward_std": 0.04349068288865965, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.10022578242933378, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "completion_length": 148.125, | |
| "epoch": 0.7783783783783784, | |
| "grad_norm": 6.7181806564331055, | |
| "kl": 0.00582859033238492, | |
| "learning_rate": 1.3545689574841341e-08, | |
| "loss": 0.0, | |
| "reward": 0.11030971497530118, | |
| "reward_std": 0.05407405199366622, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.10496596392476931, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.0053437501192092896, | |
| "step": 18 | |
| }, | |
| { | |
| "completion_length": 192.84375, | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 9.095197677612305, | |
| "kl": 0.027044922050663445, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "reward": 0.08710044820327312, | |
| "reward_std": 0.026370055467396014, | |
| "rewards/concensus_correctness_reward_func": 0.0, | |
| "rewards/consensus_reward_func": 0.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.08710044820327312, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "step": 20, | |
| "total_flos": 0.0, | |
| "train_loss": 7.2930481564981164e-06, | |
| "train_runtime": 9761.5917, | |
| "train_samples_per_second": 0.033, | |
| "train_steps_per_second": 0.002 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |