| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0018601767167880949, |
| "eval_steps": 3, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006200589055960316, |
| "grad_norm": 0.39027148485183716, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.1401, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0012401178111920632, |
| "grad_norm": 0.1772935390472412, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.9133, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "grad_norm": 0.192855104804039, |
| "learning_rate": 1.2e-05, |
| "loss": 0.8036, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "eval_loss": 0.993510365486145, |
| "eval_runtime": 46.5106, |
| "eval_samples_per_second": 2.15, |
| "eval_steps_per_second": 2.15, |
| "step": 3 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6959134812119040.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
