| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0, |
| "eval_steps": 100, |
| "global_step": 0, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "completion_length": 367.53125, |
| "epoch": 0, |
| "kl": 0.0, |
| "reward": 0.6822916666666666, |
| "reward_std": 0.45769532521565753, |
| "rewards/accuracy_reward": 0.16666666666666666, |
| "rewards/format_reward": 0.515625, |
| "step": 0, |
| "total_flos": 0.0, |
| "train_loss": 18.18843185901642, |
| "train_runtime": 28.7694, |
| "train_samples_per_second": 3.441, |
| "train_steps_per_second": 0.035 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1, |
| "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": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
