|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 15.0, |
|
"eval_steps": 500, |
|
"global_step": 4785, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.567398119122257, |
|
"grad_norm": 1.1618669033050537, |
|
"learning_rate": 4.4775339602925815e-05, |
|
"loss": 3.4578, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.134796238244514, |
|
"grad_norm": 1.134594440460205, |
|
"learning_rate": 3.955067920585162e-05, |
|
"loss": 2.7316, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.702194357366771, |
|
"grad_norm": 1.16652250289917, |
|
"learning_rate": 3.4326018808777435e-05, |
|
"loss": 2.4393, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 6.269592476489028, |
|
"grad_norm": 1.1664645671844482, |
|
"learning_rate": 2.9101358411703238e-05, |
|
"loss": 2.2559, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 7.836990595611285, |
|
"grad_norm": 1.1747838258743286, |
|
"learning_rate": 2.387669801462905e-05, |
|
"loss": 2.127, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 9.404388714733543, |
|
"grad_norm": 1.2233911752700806, |
|
"learning_rate": 1.865203761755486e-05, |
|
"loss": 2.0242, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 10.971786833855798, |
|
"grad_norm": 1.149554967880249, |
|
"learning_rate": 1.3427377220480669e-05, |
|
"loss": 1.9585, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 12.539184952978056, |
|
"grad_norm": 1.1873332262039185, |
|
"learning_rate": 8.202716823406478e-06, |
|
"loss": 1.9004, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 14.106583072100314, |
|
"grad_norm": 1.1350129842758179, |
|
"learning_rate": 2.9780564263322885e-06, |
|
"loss": 1.8692, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"step": 4785, |
|
"total_flos": 1.500338847744e+16, |
|
"train_loss": 2.280068150184496, |
|
"train_runtime": 1782.6608, |
|
"train_samples_per_second": 21.474, |
|
"train_steps_per_second": 2.684 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 4785, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 15, |
|
"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": 1.500338847744e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|