| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.7032967032967034, |
| "eval_steps": 500, |
| "global_step": 2, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "clip_ratio": 0.0, |
| "completion_length": 941.2790508270264, |
| "epoch": 0.3516483516483517, |
| "grad_norm": 44.65404147324384, |
| "kl": 0.0, |
| "learning_rate": 3e-06, |
| "loss": -0.0005, |
| "reward": 0.4029018059372902, |
| "reward_std": 0.4375760415568948, |
| "rewards/accuracy_reward": 0.041294644703157246, |
| "rewards/format_reward": 0.36160715855658054, |
| "step": 1 |
| }, |
| { |
| "clip_ratio": 0.0, |
| "completion_length": 940.2625408172607, |
| "epoch": 0.7032967032967034, |
| "kl": 0.0, |
| "reward": 0.4040178759023547, |
| "reward_std": 0.4349004360847175, |
| "rewards/accuracy_reward": 0.03236607287544757, |
| "rewards/format_reward": 0.3716518059372902, |
| "step": 2, |
| "total_flos": 0.0, |
| "train_loss": -0.0002648798189381907, |
| "train_runtime": 2998.6741, |
| "train_samples_per_second": 0.21, |
| "train_steps_per_second": 0.001 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 2, |
| "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": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
