|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9971671388101983, |
|
"global_step": 88, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1.936949724999762e-05, |
|
"loss": 1.1665, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.7557495743542586e-05, |
|
"loss": 1.1156, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.479248986720057e-05, |
|
"loss": 1.0721, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.1423148382732854e-05, |
|
"loss": 1.0383, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 7.874347104470234e-06, |
|
"loss": 1.0421, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.593591825444028e-06, |
|
"loss": 1.0273, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.994587590756397e-06, |
|
"loss": 1.004, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.0507026385502747e-07, |
|
"loss": 0.9901, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 88, |
|
"total_flos": 1.29608516683776e+16, |
|
"train_loss": 1.053490692918951, |
|
"train_runtime": 628.5043, |
|
"train_samples_per_second": 2.247, |
|
"train_steps_per_second": 0.14 |
|
} |
|
], |
|
"max_steps": 88, |
|
"num_train_epochs": 1, |
|
"total_flos": 1.29608516683776e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|