|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 19641, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.3333333333333333e-05, |
|
"loss": 0.337, |
|
"step": 6547 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9013362621270364, |
|
"eval_loss": 0.24480287730693817, |
|
"eval_runtime": 55.721, |
|
"eval_samples_per_second": 98.042, |
|
"eval_steps_per_second": 12.258, |
|
"step": 6547 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 6.666666666666667e-06, |
|
"loss": 0.1971, |
|
"step": 13094 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.914332784184514, |
|
"eval_loss": 0.28385764360427856, |
|
"eval_runtime": 55.6845, |
|
"eval_samples_per_second": 98.106, |
|
"eval_steps_per_second": 12.266, |
|
"step": 13094 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.1175, |
|
"step": 19641 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9099395936298736, |
|
"eval_loss": 0.39857929944992065, |
|
"eval_runtime": 55.8016, |
|
"eval_samples_per_second": 97.9, |
|
"eval_steps_per_second": 12.24, |
|
"step": 19641 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 19641, |
|
"total_flos": 8.267712381471744e+16, |
|
"train_loss": 0.0, |
|
"train_runtime": 0.061, |
|
"train_samples_per_second": 5155073.833, |
|
"train_steps_per_second": 322219.799 |
|
} |
|
], |
|
"max_steps": 19641, |
|
"num_train_epochs": 3, |
|
"total_flos": 8.267712381471744e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|