{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.07393715341959335, | |
"global_step": 1000, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.07, | |
"learning_rate": 4.876771410967345e-05, | |
"loss": 3.2409, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 0.07, | |
"eval_cer": 0.823943661971831, | |
"eval_loss": 2.182781934738159, | |
"eval_runtime": 178.6256, | |
"eval_samples_per_second": 0.28, | |
"eval_steps_per_second": 0.28, | |
"step": 1000 | |
} | |
], | |
"max_steps": 40575, | |
"num_train_epochs": 3, | |
"total_flos": 1.19624687419392e+17, | |
"trial_name": null, | |
"trial_params": null | |
} | |