|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.994762204064529, |
|
"global_step": 2980, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.716955017301038e-05, |
|
"loss": 0.0453, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 1.3709342560553634e-05, |
|
"loss": 0.0162, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 1.0249134948096886e-05, |
|
"loss": 0.0098, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 6.7889273356401385e-06, |
|
"loss": 0.0058, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 3.328719723183391e-06, |
|
"loss": 0.0026, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"step": 2980, |
|
"total_flos": 75597515587584.0, |
|
"train_loss": 0.013506236312373373, |
|
"train_runtime": 73478.2942, |
|
"train_samples_per_second": 2.598, |
|
"train_steps_per_second": 0.041 |
|
} |
|
], |
|
"max_steps": 2980, |
|
"num_train_epochs": 5, |
|
"total_flos": 75597515587584.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|