|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9821782178217822, |
|
"eval_steps": 500, |
|
"global_step": 31, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.31683168316831684, |
|
"grad_norm": 0.9787688851356506, |
|
"learning_rate": 0.00019853538358476932, |
|
"loss": 0.3544, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.6336633663366337, |
|
"grad_norm": 0.8510770201683044, |
|
"learning_rate": 0.0001736741137876405, |
|
"loss": 0.1631, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.9504950495049505, |
|
"grad_norm": 0.7796549201011658, |
|
"learning_rate": 0.00012542183341934872, |
|
"loss": 0.1302, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 62, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5623717032960000.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|