| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 7.964256417199609e-05, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "completion_length": 815.3625, |
| "epoch": 7.964256417199609e-05, |
| "grad_norm": 0.1777159869670868, |
| "kl": 0.0006033990764990449, |
| "learning_rate": 6.25e-07, |
| "loss": 0.0, |
| "reward": 1.2572406262159348, |
| "reward_std": 0.3052074507810175, |
| "rewards/api_reward_func_with_db": 1.2572406262159348, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 800, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "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": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
