|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.9973568281938325, |
|
"global_step": 3545, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 8.85980221058755e-06, |
|
"loss": 0.7246, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 7.405468295520653e-06, |
|
"loss": 0.5968, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 5.9511343804537524e-06, |
|
"loss": 0.5052, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 4.496800465386853e-06, |
|
"loss": 0.3611, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 3.0424665503199537e-06, |
|
"loss": 0.2573, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 1.5881326352530543e-06, |
|
"loss": 0.1943, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"learning_rate": 1.3379872018615477e-07, |
|
"loss": 0.1354, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"step": 3545, |
|
"total_flos": 897107395346432.0, |
|
"train_loss": 0.3929895871785195, |
|
"train_runtime": 101143.6052, |
|
"train_samples_per_second": 8.977, |
|
"train_steps_per_second": 0.035 |
|
} |
|
], |
|
"max_steps": 3545, |
|
"num_train_epochs": 5, |
|
"total_flos": 897107395346432.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|