|
{ |
|
"best_metric": 0.8082191780821918, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-1/checkpoint-585", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 1170, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.85, |
|
"grad_norm": 22.795198440551758, |
|
"learning_rate": 1.1916922083973807e-05, |
|
"loss": 0.6472, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.8082191780821918, |
|
"eval_loss": 0.4663033187389374, |
|
"eval_runtime": 3.5845, |
|
"eval_samples_per_second": 162.924, |
|
"eval_steps_per_second": 10.322, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"grad_norm": 13.945089340209961, |
|
"learning_rate": 3.0236966481724594e-06, |
|
"loss": 0.3781, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7876712328767124, |
|
"eval_loss": 0.5014212727546692, |
|
"eval_runtime": 3.5817, |
|
"eval_samples_per_second": 163.05, |
|
"eval_steps_per_second": 10.33, |
|
"step": 1170 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1170, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 651429105385590.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 2.081014751977516e-05, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 8, |
|
"seed": 35 |
|
} |
|
} |
|
|