{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.3574620196604111, | |
"eval_steps": 200, | |
"global_step": 200, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.18, | |
"learning_rate": 2.0000000000000003e-06, | |
"loss": 2.9598, | |
"step": 100 | |
}, | |
{ | |
"epoch": 0.36, | |
"learning_rate": 4.000000000000001e-06, | |
"loss": 2.3436, | |
"step": 200 | |
}, | |
{ | |
"epoch": 0.36, | |
"eval_loss": 1.8791261911392212, | |
"eval_runtime": 1327.8534, | |
"eval_samples_per_second": 0.753, | |
"eval_steps_per_second": 0.047, | |
"eval_wer": 0.8870904221802143, | |
"step": 200 | |
} | |
], | |
"logging_steps": 100, | |
"max_steps": 5000, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 9, | |
"save_steps": 200, | |
"total_flos": 7.458451881984e+18, | |
"train_batch_size": 32, | |
"trial_name": null, | |
"trial_params": null | |
} | |