|
{ |
|
"best_metric": 1.0, |
|
"best_model_checkpoint": "distilbert-base-uncased_finetuned_text_2_disease/checkpoint-334", |
|
"epoch": 3.0, |
|
"global_step": 501, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.9600798403193614e-05, |
|
"loss": 0.3519, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.920159680638723e-05, |
|
"loss": 0.3228, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.8802395209580838e-05, |
|
"loss": 0.3043, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.8403193612774454e-05, |
|
"loss": 0.232, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.8003992015968066e-05, |
|
"loss": 0.2346, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.7604790419161678e-05, |
|
"loss": 0.2027, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.720558882235529e-05, |
|
"loss": 0.1758, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.6806387225548902e-05, |
|
"loss": 0.1465, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 1.6407185628742518e-05, |
|
"loss": 0.1593, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.600798403193613e-05, |
|
"loss": 0.1201, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.5608782435129742e-05, |
|
"loss": 0.1107, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1.5209580838323354e-05, |
|
"loss": 0.1138, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1.4810379241516968e-05, |
|
"loss": 0.0947, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.4411177644710582e-05, |
|
"loss": 0.0911, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.4011976047904192e-05, |
|
"loss": 0.0613, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.3612774451097806e-05, |
|
"loss": 0.0585, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9984984984984985, |
|
"eval_f1": 0.9984973421631103, |
|
"eval_loss": 0.03541606292128563, |
|
"eval_precision": 0.9985541096652208, |
|
"eval_recall": 0.9984984984984985, |
|
"eval_runtime": 3.7271, |
|
"eval_samples_per_second": 178.69, |
|
"eval_steps_per_second": 5.634, |
|
"step": 167 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 1.3213572854291418e-05, |
|
"loss": 0.0779, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 1.2814371257485032e-05, |
|
"loss": 0.0501, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.2415169660678643e-05, |
|
"loss": 0.0756, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.2015968063872256e-05, |
|
"loss": 0.0417, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 1.161676646706587e-05, |
|
"loss": 0.0505, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 1.1217564870259482e-05, |
|
"loss": 0.0609, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.0818363273453095e-05, |
|
"loss": 0.0764, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.0419161676646707e-05, |
|
"loss": 0.0677, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 1.001996007984032e-05, |
|
"loss": 0.0617, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 9.620758483033933e-06, |
|
"loss": 0.0365, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 9.221556886227547e-06, |
|
"loss": 0.0315, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 8.822355289421159e-06, |
|
"loss": 0.0297, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 8.42315369261477e-06, |
|
"loss": 0.0505, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 8.023952095808385e-06, |
|
"loss": 0.0275, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 7.624750499001997e-06, |
|
"loss": 0.0366, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 7.225548902195609e-06, |
|
"loss": 0.0269, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 6.826347305389223e-06, |
|
"loss": 0.0457, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.01563212461769581, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 4.0223, |
|
"eval_samples_per_second": 165.575, |
|
"eval_steps_per_second": 5.221, |
|
"step": 334 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 6.427145708582835e-06, |
|
"loss": 0.0284, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 6.027944111776448e-06, |
|
"loss": 0.0241, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 5.62874251497006e-06, |
|
"loss": 0.0424, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 5.229540918163674e-06, |
|
"loss": 0.0444, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 4.830339321357286e-06, |
|
"loss": 0.0222, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 4.431137724550898e-06, |
|
"loss": 0.0248, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 4.031936127744511e-06, |
|
"loss": 0.0344, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 3.6327345309381242e-06, |
|
"loss": 0.0214, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 3.2335329341317368e-06, |
|
"loss": 0.0216, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 2.8343313373253494e-06, |
|
"loss": 0.0512, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 2.4351297405189623e-06, |
|
"loss": 0.0437, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 2.035928143712575e-06, |
|
"loss": 0.0439, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 1.6367265469061877e-06, |
|
"loss": 0.0212, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 1.2375249500998005e-06, |
|
"loss": 0.0203, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 8.383233532934132e-07, |
|
"loss": 0.0483, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 4.39121756487026e-07, |
|
"loss": 0.0594, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 3.992015968063872e-08, |
|
"loss": 0.0207, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.012468785047531128, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 4.1959, |
|
"eval_samples_per_second": 158.726, |
|
"eval_steps_per_second": 5.005, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 501, |
|
"total_flos": 2118227382190080.0, |
|
"train_loss": 0.08387424607952673, |
|
"train_runtime": 368.9515, |
|
"train_samples_per_second": 43.323, |
|
"train_steps_per_second": 1.358 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9981231231231231, |
|
"eval_f1": 0.9981237024802164, |
|
"eval_loss": 0.02615901082754135, |
|
"eval_precision": 0.9981332041882663, |
|
"eval_recall": 0.9981231231231231, |
|
"eval_runtime": 31.1804, |
|
"eval_samples_per_second": 170.877, |
|
"eval_steps_per_second": 5.356, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9981231231231231, |
|
"eval_f1": 0.9981237024802164, |
|
"eval_loss": 0.02615901082754135, |
|
"eval_precision": 0.9981332041882663, |
|
"eval_recall": 0.9981231231231231, |
|
"eval_runtime": 31.2125, |
|
"eval_samples_per_second": 170.701, |
|
"eval_steps_per_second": 5.35, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9981231231231231, |
|
"eval_f1": 0.9981237024802164, |
|
"eval_loss": 0.02615901082754135, |
|
"eval_precision": 0.9981332041882663, |
|
"eval_recall": 0.9981231231231231, |
|
"eval_runtime": 33.039, |
|
"eval_samples_per_second": 161.264, |
|
"eval_steps_per_second": 5.055, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9981231231231231, |
|
"eval_f1": 0.9981237024802164, |
|
"eval_loss": 0.02615901082754135, |
|
"eval_precision": 0.9981332041882663, |
|
"eval_recall": 0.9981231231231231, |
|
"eval_runtime": 33.3791, |
|
"eval_samples_per_second": 159.621, |
|
"eval_steps_per_second": 5.003, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.01563212461769581, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 4.7878, |
|
"eval_samples_per_second": 139.103, |
|
"eval_steps_per_second": 4.386, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.015602031722664833, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 3.8386, |
|
"eval_samples_per_second": 173.763, |
|
"eval_steps_per_second": 5.471, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.015602031722664833, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 4.2166, |
|
"eval_samples_per_second": 158.186, |
|
"eval_steps_per_second": 4.98, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.01563212461769581, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 4.1534, |
|
"eval_samples_per_second": 160.349, |
|
"eval_steps_per_second": 5.056, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.015602031722664833, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 3.7938, |
|
"eval_samples_per_second": 175.812, |
|
"eval_steps_per_second": 5.535, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9981231231231231, |
|
"eval_f1": 0.9981237024802164, |
|
"eval_loss": 0.02615901082754135, |
|
"eval_precision": 0.9981332041882663, |
|
"eval_recall": 0.9981231231231231, |
|
"eval_runtime": 30.7406, |
|
"eval_samples_per_second": 173.321, |
|
"eval_steps_per_second": 5.433, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.01563212461769581, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 3.7693, |
|
"eval_samples_per_second": 176.692, |
|
"eval_steps_per_second": 5.571, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 1.0, |
|
"eval_f1": 1.0, |
|
"eval_loss": 0.015602031722664833, |
|
"eval_precision": 1.0, |
|
"eval_recall": 1.0, |
|
"eval_runtime": 3.7629, |
|
"eval_samples_per_second": 177.255, |
|
"eval_steps_per_second": 5.581, |
|
"step": 501 |
|
} |
|
], |
|
"max_steps": 501, |
|
"num_train_epochs": 3, |
|
"total_flos": 2118227382190080.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|