| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 18, |
| "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": 0.7625, |
| "completions/max_length": 512.0, |
| "completions/max_terminated_length": 265.2, |
| "completions/mean_length": 439.1875, |
| "completions/mean_terminated_length": 209.825, |
| "completions/min_length": 142.5, |
| "completions/min_terminated_length": 142.5, |
| "entropy": 3.4775290532037615, |
| "epoch": 1.6666666666666665, |
| "frac_reward_zero_std": 0.3, |
| "grad_norm": 0.02465509995818138, |
| "learning_rate": 2.9877258050403214e-06, |
| "loss": -0.05790620446205139, |
| "num_tokens": 111519.0, |
| "reward": 0.02350000003352761, |
| "reward_std": 0.036062358692288396, |
| "rewards/combined_reward/mean": 0.02350000003352761, |
| "rewards/combined_reward/std": 0.036062359996140006, |
| "step": 10, |
| "step_time": 11.173231775499994 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 18, |
| "num_input_tokens_seen": 201560, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "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": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
