| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.4992, |
| "eval_steps": 500, |
| "global_step": 29, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.512, |
| "grad_norm": 1.274778209174256, |
| "learning_rate": 3.992896479256966e-06, |
| "loss": 0.8918, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0384, |
| "grad_norm": 1.8080712699620192, |
| "learning_rate": 1.2500000000000007e-06, |
| "loss": 0.9036, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.4992, |
| "step": 29, |
| "total_flos": 16540476899328.0, |
| "train_loss": 0.8755639997021906, |
| "train_runtime": 1939.0102, |
| "train_samples_per_second": 7.736, |
| "train_steps_per_second": 0.015 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 29, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 488, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 16540476899328.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
