|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.016216216216216217, |
|
"eval_steps": 3, |
|
"global_step": 3, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.005405405405405406, |
|
"grad_norm": 0.2000586837530136, |
|
"learning_rate": 2e-05, |
|
"loss": 2.3204, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.005405405405405406, |
|
"eval_loss": 2.2008719444274902, |
|
"eval_runtime": 9.7979, |
|
"eval_samples_per_second": 7.961, |
|
"eval_steps_per_second": 3.98, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.010810810810810811, |
|
"grad_norm": 0.17591507732868195, |
|
"learning_rate": 4e-05, |
|
"loss": 2.6394, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.016216216216216217, |
|
"grad_norm": 0.19049879908561707, |
|
"learning_rate": 6e-05, |
|
"loss": 2.2241, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.016216216216216217, |
|
"eval_loss": 2.1992404460906982, |
|
"eval_runtime": 9.8906, |
|
"eval_samples_per_second": 7.886, |
|
"eval_steps_per_second": 3.943, |
|
"step": 3 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2034520706514944.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|