{ | |
"best_metric": 0.5171232876712328, | |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-3/checkpoint-585", | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 585, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.85, | |
"grad_norm": 2.2346689701080322, | |
"learning_rate": 1.7036613585538902e-07, | |
"loss": 1.0151, | |
"step": 500 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_accuracy": 0.5171232876712328, | |
"eval_loss": 0.9680984616279602, | |
"eval_runtime": 3.5917, | |
"eval_samples_per_second": 162.596, | |
"eval_steps_per_second": 10.301, | |
"step": 585 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 585, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 1, | |
"save_steps": 500, | |
"total_flos": 325999802520000.0, | |
"train_batch_size": 8, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 1.1725198761812067e-06, | |
"num_train_epochs": 1, | |
"per_device_train_batch_size": 8, | |
"seed": 16 | |
} | |
} | |