{ | |
"best_metric": 0.8084862385321101, | |
"best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-1/checkpoint-842", | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 842, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.59, | |
"grad_norm": 7.641239166259766, | |
"learning_rate": 1.4914273614162126e-05, | |
"loss": 0.5407, | |
"step": 500 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_accuracy": 0.8084862385321101, | |
"eval_loss": 0.4513384699821472, | |
"eval_runtime": 0.9147, | |
"eval_samples_per_second": 953.342, | |
"eval_steps_per_second": 60.131, | |
"step": 842 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 4210, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 5, | |
"save_steps": 500, | |
"total_flos": 17905031453568.0, | |
"train_batch_size": 8, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 1.6924283535208234e-05, | |
"num_train_epochs": 5, | |
"per_device_train_batch_size": 8, | |
"seed": 25 | |
} | |
} | |