| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1608, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.8656716417910446, | |
| "grad_norm": 11.32163143157959, | |
| "learning_rate": 1.722636815920398e-05, | |
| "loss": 0.5103, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.7313432835820897, | |
| "grad_norm": 6.54978609085083, | |
| "learning_rate": 9.45273631840796e-06, | |
| "loss": 0.2075, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.597014925373134, | |
| "grad_norm": 0.33858296275138855, | |
| "learning_rate": 1.6791044776119404e-06, | |
| "loss": 0.1026, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1608, | |
| "total_flos": 3444607255477248.0, | |
| "train_loss": 0.2595453208951808, | |
| "train_runtime": 282.1547, | |
| "train_samples_per_second": 181.836, | |
| "train_steps_per_second": 5.699 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1608, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 3444607255477248.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |