|
{ |
|
"best_metric": 1.7718570232391357, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 0.36429872495446264, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0002, |
|
"loss": 2.1831, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_loss": 2.0129995346069336, |
|
"eval_runtime": 143.7126, |
|
"eval_samples_per_second": 43.657, |
|
"eval_steps_per_second": 5.462, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002, |
|
"loss": 1.9629, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"eval_loss": 1.9196887016296387, |
|
"eval_runtime": 143.7285, |
|
"eval_samples_per_second": 43.652, |
|
"eval_steps_per_second": 5.462, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0002, |
|
"loss": 1.8881, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_loss": 1.8589884042739868, |
|
"eval_runtime": 143.706, |
|
"eval_samples_per_second": 43.659, |
|
"eval_steps_per_second": 5.463, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002, |
|
"loss": 1.8368, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_loss": 1.813078761100769, |
|
"eval_runtime": 143.7443, |
|
"eval_samples_per_second": 43.647, |
|
"eval_steps_per_second": 5.461, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0002, |
|
"loss": 1.7849, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_loss": 1.7718570232391357, |
|
"eval_runtime": 143.7117, |
|
"eval_samples_per_second": 43.657, |
|
"eval_steps_per_second": 5.462, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 4116, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 2.9834861985890304e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|