|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 1735, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.58, |
|
"grad_norm": 0.4044622778892517, |
|
"learning_rate": 1.9059379461269266e-05, |
|
"loss": 0.6635, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 1735, |
|
"total_flos": 1.7240557614936883e+17, |
|
"train_loss": 0.6516804719864463, |
|
"train_runtime": 13798.3901, |
|
"train_samples_per_second": 0.503, |
|
"train_steps_per_second": 0.126 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 1735, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 1000, |
|
"total_flos": 1.7240557614936883e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|