{ | |
"best_metric": 0.0, | |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-54", | |
"epoch": 2.0, | |
"eval_steps": 500, | |
"global_step": 108, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"eval_loss": 0.6466443538665771, | |
"eval_matthews_correlation": 0.0, | |
"eval_runtime": 1.6423, | |
"eval_samples_per_second": 635.096, | |
"eval_steps_per_second": 40.188, | |
"step": 54 | |
}, | |
{ | |
"epoch": 2.0, | |
"eval_loss": 0.6164788603782654, | |
"eval_matthews_correlation": 0.0, | |
"eval_runtime": 0.7883, | |
"eval_samples_per_second": 1323.176, | |
"eval_steps_per_second": 83.729, | |
"step": 108 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 216, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 4, | |
"save_steps": 500, | |
"total_flos": 0, | |
"train_batch_size": 16, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 2.8782674356609197e-06, | |
"num_train_epochs": 4, | |
"per_device_train_batch_size": 16, | |
"seed": 16 | |
} | |
} | |