| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 57, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 2.2211966514587402, |
| "learning_rate": 0.00016, |
| "loss": 3.5560543060302736, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0526315789473684, |
| "grad_norm": 3.2205631732940674, |
| "learning_rate": 0.00016595744680851065, |
| "loss": 2.059675407409668, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5789473684210527, |
| "grad_norm": 1.3119773864746094, |
| "learning_rate": 0.00012340425531914893, |
| "loss": 1.0977931022644043, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.1052631578947367, |
| "grad_norm": 0.918510377407074, |
| "learning_rate": 8.085106382978723e-05, |
| "loss": 0.9471480369567871, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "grad_norm": 1.5682775974273682, |
| "learning_rate": 3.829787234042553e-05, |
| "loss": 0.9258415222167968, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 57, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1426762871341056.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
