|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.998780983340106, |
|
"eval_steps": 500, |
|
"global_step": 1845, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8126777732629012, |
|
"grad_norm": 4.601981163024902, |
|
"learning_rate": 1.4579945799457996e-05, |
|
"loss": 1.622, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.6253555465258025, |
|
"grad_norm": 5.0305256843566895, |
|
"learning_rate": 9.15989159891599e-06, |
|
"loss": 0.5213, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.438033319788704, |
|
"grad_norm": 5.705188751220703, |
|
"learning_rate": 3.7398373983739838e-06, |
|
"loss": 0.3908, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.998780983340106, |
|
"step": 1845, |
|
"total_flos": 2.2098181644877824e+16, |
|
"train_loss": 0.7544660283944148, |
|
"train_runtime": 3792.0333, |
|
"train_samples_per_second": 7.786, |
|
"train_steps_per_second": 0.487 |
|
}, |
|
{ |
|
"epoch": 2.998780983340106, |
|
"step": 1845, |
|
"total_flos": 2.2098181644877824e+16, |
|
"train_loss": 0.0, |
|
"train_runtime": 0.008, |
|
"train_samples_per_second": 274597.397, |
|
"train_steps_per_second": 17185.687 |
|
}, |
|
{ |
|
"epoch": 2.998780983340106, |
|
"step": 1845, |
|
"total_flos": 2.2098181644877824e+16, |
|
"train_loss": 0.0, |
|
"train_runtime": 0.0081, |
|
"train_samples_per_second": 288442.033, |
|
"train_steps_per_second": 17841.775 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 144, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.2098181644877824e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|