|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.2822757111597376, |
|
"global_step": 1500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9880602583834709, |
|
"eval_f1": 0.5721476510067114, |
|
"eval_loss": 0.04454098641872406, |
|
"eval_precision": 0.6495238095238095, |
|
"eval_recall": 0.5112443778110944, |
|
"eval_runtime": 28.2935, |
|
"eval_samples_per_second": 40.327, |
|
"eval_steps_per_second": 4.065, |
|
"step": 457 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.7811816192560176e-05, |
|
"loss": 0.1035, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9889464110815727, |
|
"eval_f1": 0.6278166278166278, |
|
"eval_loss": 0.03989504650235176, |
|
"eval_precision": 0.6516129032258065, |
|
"eval_recall": 0.6056971514242878, |
|
"eval_runtime": 28.1601, |
|
"eval_samples_per_second": 40.518, |
|
"eval_steps_per_second": 4.084, |
|
"step": 914 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 1.562363238512035e-05, |
|
"loss": 0.0338, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9899258430110536, |
|
"eval_f1": 0.657707509881423, |
|
"eval_loss": 0.03925063833594322, |
|
"eval_precision": 0.6956521739130435, |
|
"eval_recall": 0.623688155922039, |
|
"eval_runtime": 28.3748, |
|
"eval_samples_per_second": 40.212, |
|
"eval_steps_per_second": 4.053, |
|
"step": 1371 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 1.3435448577680525e-05, |
|
"loss": 0.023, |
|
"step": 1500 |
|
} |
|
], |
|
"max_steps": 4570, |
|
"num_train_epochs": 10, |
|
"total_flos": 3912926914649088.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|