{ | |
"best_metric": -0.02929206145132745, | |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-14", | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 14, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"eval_loss": 0.6642347574234009, | |
"eval_matthews_correlation": -0.02929206145132745, | |
"eval_runtime": 0.7449, | |
"eval_samples_per_second": 1400.248, | |
"eval_steps_per_second": 88.606, | |
"step": 14 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 56, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 4, | |
"save_steps": 500, | |
"total_flos": 0, | |
"train_batch_size": 64, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 3.972386455212293e-06, | |
"num_train_epochs": 4, | |
"per_device_train_batch_size": 64, | |
"seed": 30 | |
} | |
} | |