|
{ |
|
"best_metric": 0.926829268292683, |
|
"best_model_checkpoint": "my_awesome_product_model/checkpoint-97", |
|
"epoch": 1.9897435897435898, |
|
"eval_steps": 500, |
|
"global_step": 97, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.697, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.8062015503875976e-05, |
|
"loss": 0.6543, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.418604651162791e-05, |
|
"loss": 0.5675, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 4.0310077519379843e-05, |
|
"loss": 0.4375, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"eval_accuracy": 0.8690629011553274, |
|
"eval_loss": 0.32008689641952515, |
|
"eval_runtime": 47.4344, |
|
"eval_samples_per_second": 16.423, |
|
"eval_steps_per_second": 1.033, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 3.6434108527131784e-05, |
|
"loss": 0.3455, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 3.2558139534883724e-05, |
|
"loss": 0.2934, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 2.868217054263566e-05, |
|
"loss": 0.2365, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 2.48062015503876e-05, |
|
"loss": 0.2391, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 2.0930232558139536e-05, |
|
"loss": 0.2112, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"eval_accuracy": 0.926829268292683, |
|
"eval_loss": 0.20997567474842072, |
|
"eval_runtime": 50.4357, |
|
"eval_samples_per_second": 15.445, |
|
"eval_steps_per_second": 0.972, |
|
"step": 97 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 144, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 4.824651273404498e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|