|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.9952, |
|
"eval_steps": 500, |
|
"global_step": 468, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.192, |
|
"grad_norm": 3.0231683208947624, |
|
"learning_rate": 4.94947663010567e-06, |
|
"loss": 1.4404, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.384, |
|
"grad_norm": 1.9054820241083907, |
|
"learning_rate": 4.799948609147061e-06, |
|
"loss": 1.2087, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.576, |
|
"grad_norm": 1.5720300499627058, |
|
"learning_rate": 4.5574596647341414e-06, |
|
"loss": 1.1543, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.768, |
|
"grad_norm": 1.4078091983626713, |
|
"learning_rate": 4.231810883773999e-06, |
|
"loss": 1.1191, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"grad_norm": 1.1931272863597788, |
|
"learning_rate": 3.836164565319503e-06, |
|
"loss": 1.1091, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.152, |
|
"grad_norm": 1.323916079265958, |
|
"learning_rate": 3.386512217606339e-06, |
|
"loss": 1.0086, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.3439999999999999, |
|
"grad_norm": 1.2835553371871835, |
|
"learning_rate": 2.9010282021444008e-06, |
|
"loss": 0.984, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.536, |
|
"grad_norm": 1.1833493404233775, |
|
"learning_rate": 2.399335149726463e-06, |
|
"loss": 0.9717, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.728, |
|
"grad_norm": 1.2611459723983318, |
|
"learning_rate": 1.9017108392811065e-06, |
|
"loss": 0.9689, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"grad_norm": 1.2047500689546384, |
|
"learning_rate": 1.4282685964923643e-06, |
|
"loss": 0.9723, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.112, |
|
"grad_norm": 1.3228375142177193, |
|
"learning_rate": 9.981443394050525e-07, |
|
"loss": 0.9206, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.304, |
|
"grad_norm": 1.1736318918555897, |
|
"learning_rate": 6.28723129572247e-07, |
|
"loss": 0.8778, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.496, |
|
"grad_norm": 1.1911302845348413, |
|
"learning_rate": 3.3493649053890325e-07, |
|
"loss": 0.8836, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.6879999999999997, |
|
"grad_norm": 1.2242781042058175, |
|
"learning_rate": 1.286588951321363e-07, |
|
"loss": 0.8826, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"grad_norm": 1.2168136494769461, |
|
"learning_rate": 1.822781475486507e-08, |
|
"loss": 0.8867, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.9952, |
|
"step": 468, |
|
"total_flos": 102451939377152.0, |
|
"train_loss": 1.0187332528269188, |
|
"train_runtime": 2055.4609, |
|
"train_samples_per_second": 29.191, |
|
"train_steps_per_second": 0.228 |
|
} |
|
], |
|
"logging_steps": 30, |
|
"max_steps": 468, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 102451939377152.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|