|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.2091898428053205, |
|
"eval_steps": 500, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.0931076178960096e-05, |
|
"loss": 2.1458, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.1862152357920194e-05, |
|
"loss": 1.7773, |
|
"step": 1000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1654, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 2350690947786240.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|