|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 3.017467248908297, |
|
"eval_steps": 25, |
|
"global_step": 43, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06986899563318777, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.06986899563318777, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.4338, |
|
"eval_samples_per_second": 34.873, |
|
"eval_steps_per_second": 9.067, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.13973799126637554, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.2096069868995633, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.986796105326832e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.2794759825327511, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.947261907011569e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.34934497816593885, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.881629407450006e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.4192139737991266, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.790283764247188e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.4890829694323144, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.673761029959427e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.5589519650655022, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.53274500632475e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.62882096069869, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.368063231442406e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.6986899563318777, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.18068212345023e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.7685589519650655, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.971701309198744e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.8384279475982532, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.742347171203542e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.9082969432314411, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.493965650745043e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.9781659388646288, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.228014349349872e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 1.0524017467248907, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.946053975005496e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.1222707423580787, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.649739183305184e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.1921397379912664, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.34080886727103e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 1.262008733624454, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.021075952838262e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 1.3318777292576418, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.692416759884978e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 1.4017467248908297, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.356759991241008e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.4716157205240175, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.016075414292803e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 1.5414847161572052, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.6723623016051596e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 1.611353711790393, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.3276376983948415e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 1.6812227074235808, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.9839245857071994e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.7510917030567685, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.643240008758992e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.7510917030567685, |
|
"eval_loss": NaN, |
|
"eval_runtime": 0.7318, |
|
"eval_samples_per_second": 68.323, |
|
"eval_steps_per_second": 17.764, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.8209606986899565, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.307583240115024e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.890829694323144, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.9789240471617385e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.960698689956332, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.659191132728971e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 2.034934497816594, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.350260816694816e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 2.1048034934497815, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.0539460249945056e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 2.1746724890829694, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7719856506501306e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 2.2445414847161573, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.5060343492549566e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 2.314410480349345, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.257652828796459e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 2.3842794759825328, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.0282986908012567e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 2.4541484716157207, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.819317876549771e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 2.524017467248908, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.631936768557596e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 2.593886462882096, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4672549936752506e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 2.6637554585152836, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3262389700405744e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 2.7336244541484715, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2097162357528127e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 2.8034934497816595, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1183705925499948e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.8733624454148474, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0527380929884324e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 2.943231441048035, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.013203894673168e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 3.017467248908297, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 43, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 1, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 9.112012643421389e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|