{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.17006802721088435, | |
"global_step": 100, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.09, | |
"learning_rate": 2.88e-05, | |
"loss": 14.7169, | |
"step": 50 | |
}, | |
{ | |
"epoch": 0.17, | |
"learning_rate": 5.82e-05, | |
"loss": 10.7288, | |
"step": 100 | |
}, | |
{ | |
"epoch": 0.17, | |
"eval_cer": 0.9860753301809881, | |
"eval_loss": 5.656092166900635, | |
"eval_runtime": 23.0792, | |
"eval_samples_per_second": 25.478, | |
"eval_steps_per_second": 3.206, | |
"step": 100 | |
} | |
], | |
"max_steps": 14700, | |
"num_train_epochs": 25, | |
"total_flos": 9.857428641096192e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |