|
{ |
|
"best_metric": 0.49511729307051994, |
|
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-14300", |
|
"epoch": 6.0, |
|
"eval_steps": 500, |
|
"global_step": 21450, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.9813519813519816e-05, |
|
"loss": 0.4207, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.962703962703963e-05, |
|
"loss": 0.3879, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.944055944055944e-05, |
|
"loss": 0.3832, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 1.9254079254079257e-05, |
|
"loss": 0.3796, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.906759906759907e-05, |
|
"loss": 0.3764, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.888111888111888e-05, |
|
"loss": 0.3732, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.8694638694638696e-05, |
|
"loss": 0.3715, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_akurasi": 0.304635761589404, |
|
"eval_f1": 0.41270686365854736, |
|
"eval_loss": 0.36894935369491577, |
|
"eval_roc_auc": 0.6308684676414661, |
|
"eval_runtime": 132.2279, |
|
"eval_samples_per_second": 115.339, |
|
"eval_steps_per_second": 7.215, |
|
"step": 3575 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.850815850815851e-05, |
|
"loss": 0.3592, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.8321678321678323e-05, |
|
"loss": 0.3515, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.8135198135198137e-05, |
|
"loss": 0.3529, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 1.794871794871795e-05, |
|
"loss": 0.3497, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 1.7762237762237765e-05, |
|
"loss": 0.3489, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 1.7575757575757576e-05, |
|
"loss": 0.3511, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.738927738927739e-05, |
|
"loss": 0.3494, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_akurasi": 0.36633663366336633, |
|
"eval_f1": 0.4571545380212592, |
|
"eval_loss": 0.36878135800361633, |
|
"eval_roc_auc": 0.653645662579503, |
|
"eval_runtime": 132.2013, |
|
"eval_samples_per_second": 115.362, |
|
"eval_steps_per_second": 7.216, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 1.7202797202797203e-05, |
|
"loss": 0.327, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 1.7016317016317017e-05, |
|
"loss": 0.3207, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 1.682983682983683e-05, |
|
"loss": 0.3178, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 1.6643356643356645e-05, |
|
"loss": 0.3141, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 1.645687645687646e-05, |
|
"loss": 0.3183, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 1.6270396270396273e-05, |
|
"loss": 0.3226, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 1.6083916083916083e-05, |
|
"loss": 0.322, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_akurasi": 0.4225296701855616, |
|
"eval_f1": 0.4886535552193646, |
|
"eval_loss": 0.3799174726009369, |
|
"eval_roc_auc": 0.6730296374008262, |
|
"eval_runtime": 132.2733, |
|
"eval_samples_per_second": 115.299, |
|
"eval_steps_per_second": 7.212, |
|
"step": 10725 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 1.5897435897435897e-05, |
|
"loss": 0.2957, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 1.5710955710955715e-05, |
|
"loss": 0.2751, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 1.5524475524475525e-05, |
|
"loss": 0.2724, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 1.533799533799534e-05, |
|
"loss": 0.2827, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 1.5151515151515153e-05, |
|
"loss": 0.2846, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 1.4965034965034965e-05, |
|
"loss": 0.2826, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 1.4778554778554779e-05, |
|
"loss": 0.2863, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_akurasi": 0.448101763818766, |
|
"eval_f1": 0.49511729307051994, |
|
"eval_loss": 0.412160724401474, |
|
"eval_roc_auc": 0.6790866172709985, |
|
"eval_runtime": 132.2949, |
|
"eval_samples_per_second": 115.28, |
|
"eval_steps_per_second": 7.211, |
|
"step": 14300 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 1.4592074592074595e-05, |
|
"loss": 0.2652, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 1.4405594405594407e-05, |
|
"loss": 0.2333, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 1.421911421911422e-05, |
|
"loss": 0.2457, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 1.4032634032634035e-05, |
|
"loss": 0.244, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 1.3846153846153847e-05, |
|
"loss": 0.2438, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 4.76, |
|
"learning_rate": 1.365967365967366e-05, |
|
"loss": 0.2448, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 1.3473193473193473e-05, |
|
"loss": 0.2484, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_akurasi": 0.45597010032129043, |
|
"eval_f1": 0.48838265609168097, |
|
"eval_loss": 0.4510646164417267, |
|
"eval_roc_auc": 0.6768326667103797, |
|
"eval_runtime": 132.311, |
|
"eval_samples_per_second": 115.266, |
|
"eval_steps_per_second": 7.21, |
|
"step": 17875 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 1.3286713286713288e-05, |
|
"loss": 0.2364, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 5.17, |
|
"learning_rate": 1.3100233100233102e-05, |
|
"loss": 0.2016, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 5.31, |
|
"learning_rate": 1.2913752913752915e-05, |
|
"loss": 0.2034, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 5.45, |
|
"learning_rate": 1.2727272727272728e-05, |
|
"loss": 0.2131, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 5.59, |
|
"learning_rate": 1.254079254079254e-05, |
|
"loss": 0.2076, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 5.73, |
|
"learning_rate": 1.2354312354312355e-05, |
|
"loss": 0.2032, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 5.87, |
|
"learning_rate": 1.216783216783217e-05, |
|
"loss": 0.2134, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_akurasi": 0.462986033702708, |
|
"eval_f1": 0.4940430572005852, |
|
"eval_loss": 0.4969989061355591, |
|
"eval_roc_auc": 0.680316044849518, |
|
"eval_runtime": 132.3664, |
|
"eval_samples_per_second": 115.218, |
|
"eval_steps_per_second": 7.207, |
|
"step": 21450 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 53625, |
|
"num_train_epochs": 15, |
|
"save_steps": 500, |
|
"total_flos": 4.514475841140326e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|