|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 3465, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.278499278499279e-05, |
|
"loss": 3.3442, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 3.556998556998557e-05, |
|
"loss": 0.7984, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 2.8354978354978357e-05, |
|
"loss": 0.4652, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 2.113997113997114e-05, |
|
"loss": 0.3644, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 1.3924963924963927e-05, |
|
"loss": 0.2928, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 6.709956709956711e-06, |
|
"loss": 0.2326, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 3465, |
|
"total_flos": 2.3687033473990656e+17, |
|
"train_loss": 0.8221148734484917, |
|
"train_runtime": 8159.3229, |
|
"train_samples_per_second": 217.574, |
|
"train_steps_per_second": 0.425 |
|
} |
|
], |
|
"max_steps": 3465, |
|
"num_train_epochs": 3, |
|
"total_flos": 2.3687033473990656e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|