| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 129, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.6120649576187134, |
| "eval_runtime": 0.2712, |
| "eval_samples_per_second": 221.262, |
| "eval_steps_per_second": 29.502, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.5919190645217896, |
| "eval_runtime": 0.2649, |
| "eval_samples_per_second": 226.467, |
| "eval_steps_per_second": 30.196, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.5281654596328735, |
| "eval_runtime": 0.2658, |
| "eval_samples_per_second": 225.736, |
| "eval_steps_per_second": 30.098, |
| "step": 129 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 129, |
| "total_flos": 135123975475200.0, |
| "train_loss": 1.5138977997062741, |
| "train_runtime": 44.0368, |
| "train_samples_per_second": 23.162, |
| "train_steps_per_second": 2.929 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 129, |
| "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": 135123975475200.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
