| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.024691358024691357, |
| "eval_steps": 1, |
| "global_step": 1, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.024691358024691357, |
| "grad_norm": 0.0, |
| "learning_rate": 0.0, |
| "loss": 0.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.024691358024691357, |
| "eval_clip_ratio/high_max": 0.0, |
| "eval_clip_ratio/high_mean": 0.0, |
| "eval_clip_ratio/low_mean": 0.0, |
| "eval_clip_ratio/low_min": 0.0, |
| "eval_clip_ratio/region_mean": 0.0, |
| "eval_completions/clipped_ratio": 0.425, |
| "eval_completions/max_length": 205.0, |
| "eval_completions/max_terminated_length": 138.6, |
| "eval_completions/mean_length": 139.95, |
| "eval_completions/mean_terminated_length": 78.71333465576171, |
| "eval_completions/min_length": 26.8, |
| "eval_completions/min_terminated_length": 26.8, |
| "eval_kl": 0.0, |
| "eval_loss": -0.020106248557567596, |
| "eval_num_tokens": 10430.0, |
| "eval_reward": 0.38962903022766116, |
| "eval_reward_std": 0.4499048709869385, |
| "eval_rewards/reward_func_keyword/mean": 0.1, |
| "eval_rewards/reward_func_keyword/std": 0.10690449476242066, |
| "eval_runtime": 63.1375, |
| "eval_samples_per_second": 0.143, |
| "eval_steps_per_second": 0.032, |
| "step": 1 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1, |
| "num_input_tokens_seen": 10430, |
| "num_train_epochs": 1, |
| "save_steps": 61, |
| "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": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
