| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.6870229007633588, |
| "eval_steps": 500, |
| "global_step": 1547, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5452562704471101, |
| "grad_norm": 1.3763982057571411, |
| "learning_rate": 2e-05, |
| "loss": 2.0251, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0905125408942202, |
| "grad_norm": 1.0297070741653442, |
| "learning_rate": 1.555752998667259e-05, |
| "loss": 1.7868, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6357688113413305, |
| "grad_norm": 1.0274933576583862, |
| "learning_rate": 1.1115059973345181e-05, |
| "loss": 1.6506, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2751, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 91, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1482652064035635e+17, |
| "train_batch_size": 80, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
