| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.07142857142857142, |
| "eval_steps": 500, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "clip_ratio/high_max": 0.0, |
| "clip_ratio/high_mean": 0.0, |
| "clip_ratio/low_mean": 0.0, |
| "clip_ratio/low_min": 0.0, |
| "clip_ratio/region_mean": 0.0, |
| "completions/clipped_ratio": 0.0, |
| "completions/max_length": 16.1, |
| "completions/max_terminated_length": 16.1, |
| "completions/mean_length": 15.43125, |
| "completions/mean_terminated_length": 15.43125, |
| "completions/min_length": 12.8, |
| "completions/min_terminated_length": 12.8, |
| "entropy": 0.11648641154170036, |
| "epoch": 0.02857142857142857, |
| "frac_reward_zero_std": 0.0, |
| "grad_norm": 3.766094207763672, |
| "learning_rate": 1.955e-06, |
| "loss": -0.03027614951133728, |
| "num_tokens": 117861.0, |
| "reward": 0.42463125213980674, |
| "reward_std": 0.4041272960603237, |
| "rewards/<lambda>/mean": 0.42463125213980674, |
| "rewards/<lambda>/std": 0.4041273109614849, |
| "step": 10, |
| "step_time": 8.86154415559722 |
| }, |
| { |
| "clip_ratio/high_max": 0.0, |
| "clip_ratio/high_mean": 0.0, |
| "clip_ratio/low_mean": 0.0, |
| "clip_ratio/low_min": 0.0, |
| "clip_ratio/region_mean": 0.0, |
| "completions/clipped_ratio": 0.0, |
| "completions/max_length": 39.1, |
| "completions/max_terminated_length": 39.1, |
| "completions/mean_length": 15.76875, |
| "completions/mean_terminated_length": 15.76875, |
| "completions/min_length": 12.0, |
| "completions/min_terminated_length": 12.0, |
| "entropy": 0.14287759065628053, |
| "epoch": 0.05714285714285714, |
| "frac_reward_zero_std": 0.3, |
| "grad_norm": 4.652894020080566, |
| "learning_rate": 1.905e-06, |
| "loss": -0.007219273597002029, |
| "num_tokens": 211120.0, |
| "reward": 0.16723437011241912, |
| "reward_std": 0.23346474170684814, |
| "rewards/<lambda>/mean": 0.16723437011241912, |
| "rewards/<lambda>/std": 0.233464752137661, |
| "step": 20, |
| "step_time": 8.861151697207243 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 400, |
| "num_input_tokens_seen": 264439, |
| "num_train_epochs": 2, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
