{ | |
"best_metric": 0.0, | |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-535", | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 535, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.93, | |
"grad_norm": 4.029795169830322, | |
"learning_rate": 1.7163903856453514e-06, | |
"loss": 0.6033, | |
"step": 500 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 0.5766915082931519, | |
"eval_matthews_correlation": 0.0, | |
"eval_runtime": 0.7097, | |
"eval_samples_per_second": 1469.555, | |
"eval_steps_per_second": 92.992, | |
"step": 535 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 2140, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 4, | |
"save_steps": 500, | |
"total_flos": 42729015278976.0, | |
"train_batch_size": 16, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 2.2396801373664952e-06, | |
"num_train_epochs": 4, | |
"per_device_train_batch_size": 16, | |
"seed": 33 | |
} | |
} | |