|
{ |
|
"best_metric": 295.114006514658, |
|
"best_model_checkpoint": "./temp/checkpoint-50", |
|
"epoch": 3.1904761904761907, |
|
"eval_steps": 10, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.6349206349206349, |
|
"eval_cer": 186.56571539506893, |
|
"eval_loss": 9.826007843017578, |
|
"eval_runtime": 21.7924, |
|
"eval_samples_per_second": 2.294, |
|
"eval_steps_per_second": 0.184, |
|
"eval_wer": 332.2475570032573, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.3174603174603174, |
|
"eval_cer": 186.54630168899243, |
|
"eval_loss": 8.942676544189453, |
|
"eval_runtime": 20.9166, |
|
"eval_samples_per_second": 2.39, |
|
"eval_steps_per_second": 0.191, |
|
"eval_wer": 332.5732899022801, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.9523809523809523, |
|
"eval_cer": 179.30498932246167, |
|
"eval_loss": 7.41646671295166, |
|
"eval_runtime": 23.189, |
|
"eval_samples_per_second": 2.156, |
|
"eval_steps_per_second": 0.172, |
|
"eval_wer": 329.64169381107496, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 2.571428571428571, |
|
"eval_cer": 173.6167734420501, |
|
"eval_loss": 4.776045322418213, |
|
"eval_runtime": 23.185, |
|
"eval_samples_per_second": 2.157, |
|
"eval_steps_per_second": 0.173, |
|
"eval_wer": 313.51791530944627, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 3.1904761904761907, |
|
"grad_norm": 63047348.0, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 6.244, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 3.1904761904761907, |
|
"eval_cer": 173.05377596583187, |
|
"eval_loss": 1.3689286708831787, |
|
"eval_runtime": 20.2703, |
|
"eval_samples_per_second": 2.467, |
|
"eval_steps_per_second": 0.197, |
|
"eval_wer": 295.114006514658, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 50, |
|
"max_steps": 75, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 7.759872589824e+16, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|