|
{ |
|
"best_metric": 0.9058380414312618, |
|
"best_model_checkpoint": "./resultsv2xl/output/checkpoint-294528", |
|
"epoch": 3.0, |
|
"global_step": 294528, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 4.2562126159447515e-06, |
|
"loss": 0.527, |
|
"step": 98176 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.8983559831017458, |
|
"eval_loss": 0.4922527074813843, |
|
"eval_runtime": 231.3267, |
|
"eval_samples_per_second": 84.932, |
|
"eval_steps_per_second": 21.234, |
|
"step": 98176 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.1293307712312536e-06, |
|
"loss": 0.3335, |
|
"step": 196352 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9027332417162925, |
|
"eval_loss": 0.5514769554138184, |
|
"eval_runtime": 231.2763, |
|
"eval_samples_per_second": 84.95, |
|
"eval_steps_per_second": 21.239, |
|
"step": 196352 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 2.4705984338428644e-09, |
|
"loss": 0.1729, |
|
"step": 294528 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9058380414312618, |
|
"eval_loss": 0.65480637550354, |
|
"eval_runtime": 230.3593, |
|
"eval_samples_per_second": 85.289, |
|
"eval_steps_per_second": 21.323, |
|
"step": 294528 |
|
} |
|
], |
|
"max_steps": 294528, |
|
"num_train_epochs": 3, |
|
"total_flos": 2.8162430874533802e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|