|
{ |
|
"best_metric": 0.472806497515492, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-536", |
|
"epoch": 4.0, |
|
"eval_steps": 500, |
|
"global_step": 536, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.5072507858276367, |
|
"eval_matthews_correlation": 0.38056906932003487, |
|
"eval_runtime": 0.734, |
|
"eval_samples_per_second": 1420.999, |
|
"eval_steps_per_second": 89.919, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.4880638122558594, |
|
"eval_matthews_correlation": 0.43856921453382075, |
|
"eval_runtime": 0.8211, |
|
"eval_samples_per_second": 1270.18, |
|
"eval_steps_per_second": 80.376, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.5360028743743896, |
|
"eval_matthews_correlation": 0.4660612127514574, |
|
"eval_runtime": 0.7407, |
|
"eval_samples_per_second": 1408.186, |
|
"eval_steps_per_second": 89.109, |
|
"step": 402 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"grad_norm": 5.651569366455078, |
|
"learning_rate": 1.3142891344821386e-06, |
|
"loss": 0.3939, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.5550961494445801, |
|
"eval_matthews_correlation": 0.472806497515492, |
|
"eval_runtime": 0.8383, |
|
"eval_samples_per_second": 1244.245, |
|
"eval_steps_per_second": 78.735, |
|
"step": 536 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 536, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 500, |
|
"total_flos": 208996816074072.0, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 1.9568304891178507e-05, |
|
"num_train_epochs": 4, |
|
"per_device_train_batch_size": 64, |
|
"seed": 13 |
|
} |
|
} |
|
|