|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.2631578947368425, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 5.2631578947368425, |
|
"grad_norm": 5.739169120788574, |
|
"learning_rate": 3.6842105263157895e-05, |
|
"loss": 4.1507, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1900, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 20, |
|
"save_steps": 500, |
|
"total_flos": 519971143680000.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|