{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.26490066225165565, | |
"global_step": 20, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.13, | |
"learning_rate": 0.00045, | |
"loss": 10.7126, | |
"step": 10 | |
}, | |
{ | |
"epoch": 0.26, | |
"learning_rate": 0.0007469387755102041, | |
"loss": 5.3922, | |
"step": 20 | |
}, | |
{ | |
"epoch": 0.26, | |
"eval_loss": 3.5064597129821777, | |
"eval_runtime": 4.8648, | |
"eval_samples_per_second": 20.145, | |
"eval_steps_per_second": 0.822, | |
"eval_wer": 1.0, | |
"step": 20 | |
} | |
], | |
"max_steps": 750, | |
"num_train_epochs": 10, | |
"total_flos": 4.155165485184e+17, | |
"trial_name": null, | |
"trial_params": null | |
} | |