|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 25.0, |
|
"global_step": 4600, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 4.456521739130435e-05, |
|
"loss": 2.6463, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 3.91304347826087e-05, |
|
"loss": 1.5589, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 8.15, |
|
"learning_rate": 3.369565217391305e-05, |
|
"loss": 1.107, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 10.87, |
|
"learning_rate": 2.826086956521739e-05, |
|
"loss": 0.8178, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 13.59, |
|
"learning_rate": 2.282608695652174e-05, |
|
"loss": 0.6328, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 16.3, |
|
"learning_rate": 1.739130434782609e-05, |
|
"loss": 0.515, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 19.02, |
|
"learning_rate": 1.1956521739130435e-05, |
|
"loss": 0.4357, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 21.74, |
|
"learning_rate": 6.521739130434783e-06, |
|
"loss": 0.3796, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 24.46, |
|
"learning_rate": 1.0869565217391306e-06, |
|
"loss": 0.3478, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"step": 4600, |
|
"total_flos": 3511389310156800.0, |
|
"train_runtime": 1074.2277, |
|
"train_samples_per_second": 4.282 |
|
} |
|
], |
|
"max_steps": 4600, |
|
"num_train_epochs": 25, |
|
"total_flos": 3511389310156800.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|