| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.64, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.24305464327335358, |
| "learning_rate": 0.00018, |
| "loss": 0.4307, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0533333333333332, |
| "grad_norm": 0.12696263194084167, |
| "learning_rate": 0.00016170212765957446, |
| "loss": 0.2921, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5866666666666667, |
| "grad_norm": 0.18280404806137085, |
| "learning_rate": 0.00011914893617021277, |
| "loss": 0.2568, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.1066666666666665, |
| "grad_norm": 0.17879144847393036, |
| "learning_rate": 7.659574468085106e-05, |
| "loss": 0.2264, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.64, |
| "grad_norm": 0.2087363600730896, |
| "learning_rate": 3.4042553191489365e-05, |
| "loss": 0.1876, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 57, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.920483063935795e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
