|
{ |
|
"best_metric": 1.4880632162094116, |
|
"best_model_checkpoint": "./zhko_mbartLarge_19p_run1/checkpoint-5000", |
|
"epoch": 1.7946877243359656, |
|
"eval_steps": 5000, |
|
"global_step": 5000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 2.4329, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 1.9318, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 5e-05, |
|
"loss": 1.8063, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.9379498634897e-05, |
|
"loss": 1.7429, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.875899726979399e-05, |
|
"loss": 1.6586, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 4.8138495904690995e-05, |
|
"loss": 1.5945, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.751799453958799e-05, |
|
"loss": 1.4888, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.689749317448498e-05, |
|
"loss": 1.3603, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 4.627699180938198e-05, |
|
"loss": 1.2398, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 4.5656490444278984e-05, |
|
"loss": 1.1911, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"eval_bleu": 9.7977, |
|
"eval_gen_len": 14.6128, |
|
"eval_loss": 1.4880632162094116, |
|
"eval_runtime": 656.7417, |
|
"eval_samples_per_second": 16.966, |
|
"eval_steps_per_second": 1.061, |
|
"step": 5000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 41790, |
|
"num_train_epochs": 15, |
|
"save_steps": 5000, |
|
"total_flos": 3.4674076286976e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|