| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 599.9989124298096, | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.4140438437461853, | |
| "kl": 0.00025391876697540284, | |
| "learning_rate": 2.981532510892707e-06, | |
| "loss": 0.0, | |
| "reward": 0.36986608924344183, | |
| "reward_std": 0.3811873120255768, | |
| "rewards/accuracy_reward": 0.36986608924344183, | |
| "rewards/format_reward": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 606.8819444656372, | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.06738726049661636, | |
| "kl": 0.0030163049697875975, | |
| "learning_rate": 2.6657189421854562e-06, | |
| "loss": 0.0001, | |
| "reward": 0.5493303807452321, | |
| "reward_std": 0.338475276529789, | |
| "rewards/accuracy_reward": 0.5493303807452321, | |
| "rewards/format_reward": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "completion_length": 594.3245794296265, | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.050410859286785126, | |
| "kl": 0.004825687408447266, | |
| "learning_rate": 2.03755192431795e-06, | |
| "loss": 0.0002, | |
| "reward": 0.6329241359606386, | |
| "reward_std": 0.25738380146212875, | |
| "rewards/accuracy_reward": 0.6329241359606386, | |
| "rewards/format_reward": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "completion_length": 602.447682762146, | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.04725565016269684, | |
| "kl": 0.004597854614257812, | |
| "learning_rate": 1.2653483024396534e-06, | |
| "loss": 0.0002, | |
| "reward": 0.6353794910013676, | |
| "reward_std": 0.24207868478260935, | |
| "rewards/accuracy_reward": 0.6353794910013676, | |
| "rewards/format_reward": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "completion_length": 604.7845136642457, | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.050348229706287384, | |
| "kl": 0.004749441146850586, | |
| "learning_rate": 5.560194134252441e-07, | |
| "loss": 0.0002, | |
| "reward": 0.6332589566707612, | |
| "reward_std": 0.24845922645181417, | |
| "rewards/accuracy_reward": 0.6332589566707612, | |
| "rewards/format_reward": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "completion_length": 604.7117460250854, | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.05302207171916962, | |
| "kl": 0.004680252075195313, | |
| "learning_rate": 9.962936025419756e-08, | |
| "loss": 0.0002, | |
| "reward": 0.6436384223401547, | |
| "reward_std": 0.23067113785073162, | |
| "rewards/accuracy_reward": 0.6436384223401547, | |
| "rewards/format_reward": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "completion_length": 598.5010340554373, | |
| "epoch": 1.0, | |
| "kl": 0.0044345855712890625, | |
| "reward": 0.6657632046512195, | |
| "reward_std": 0.23220190632023982, | |
| "rewards/accuracy_reward": 0.6657632046512195, | |
| "rewards/format_reward": 0.0, | |
| "step": 67, | |
| "total_flos": 0.0, | |
| "train_loss": 0.00015022740371389758, | |
| "train_runtime": 9418.0568, | |
| "train_samples_per_second": 0.796, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 67, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |