| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.988988988988989, |
| "eval_steps": 500, |
| "global_step": 747, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.23750114440918, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 1.031, |
| "mean_token_accuracy": 0.7876539057618505, |
| "num_tokens": 498006.0, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 747, |
| "num_input_tokens_seen": 0, |
| "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": 3.180604511391744e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
