| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 250.0, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 100.0, |
| "grad_norm": 0.17752039432525635, |
| "learning_rate": 3.604e-05, |
| "loss": 0.1262, |
| "step": 200 |
| }, |
| { |
| "epoch": 200.0, |
| "grad_norm": 0.3985879421234131, |
| "learning_rate": 1.2079999999999998e-05, |
| "loss": 0.062, |
| "step": 400 |
| }, |
| { |
| "epoch": 250.0, |
| "step": 500, |
| "total_flos": 2.903671701504e+17, |
| "train_loss": 0.08589911651611327, |
| "train_runtime": 1399.8181, |
| "train_samples_per_second": 2.858, |
| "train_steps_per_second": 0.357 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 250, |
| "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": 2.903671701504e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
