| { | |
| "best_metric": 0.9863776360625434, | |
| "best_model_checkpoint": "distilbert-base-uncased_finetuned_text_2_disease_cel/checkpoint-501", | |
| "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": 3.2148, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.920159680638723e-05, | |
| "loss": 3.1884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8802395209580838e-05, | |
| "loss": 3.1211, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.8403193612774454e-05, | |
| "loss": 3.0229, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.8003992015968066e-05, | |
| "loss": 2.86, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.7604790419161678e-05, | |
| "loss": 2.7413, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.720558882235529e-05, | |
| "loss": 2.5771, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6806387225548902e-05, | |
| "loss": 2.4409, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.6407185628742518e-05, | |
| "loss": 2.252, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.600798403193613e-05, | |
| "loss": 2.1139, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.5608782435129742e-05, | |
| "loss": 2.0014, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5209580838323354e-05, | |
| "loss": 1.8311, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.4810379241516968e-05, | |
| "loss": 1.7216, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4411177644710582e-05, | |
| "loss": 1.6513, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.4011976047904192e-05, | |
| "loss": 1.4706, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3612774451097806e-05, | |
| "loss": 1.3868, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8648648648648649, | |
| "eval_f1": 0.8458007872306277, | |
| "eval_loss": 1.1692062616348267, | |
| "eval_precision": 0.8572972892114447, | |
| "eval_recall": 0.8648648648648649, | |
| "eval_runtime": 3.7382, | |
| "eval_samples_per_second": 178.16, | |
| "eval_steps_per_second": 5.618, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.3213572854291418e-05, | |
| "loss": 1.2438, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2814371257485032e-05, | |
| "loss": 1.1916, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.2415169660678643e-05, | |
| "loss": 1.0778, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2015968063872256e-05, | |
| "loss": 1.0055, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.161676646706587e-05, | |
| "loss": 1.0151, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.1217564870259482e-05, | |
| "loss": 0.9616, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.0818363273453095e-05, | |
| "loss": 0.9831, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.0419161676646707e-05, | |
| "loss": 0.866, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.001996007984032e-05, | |
| "loss": 0.8548, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.620758483033933e-06, | |
| "loss": 0.7455, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.221556886227547e-06, | |
| "loss": 0.693, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.822355289421159e-06, | |
| "loss": 0.6751, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.42315369261477e-06, | |
| "loss": 0.6852, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.023952095808385e-06, | |
| "loss": 0.5647, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.624750499001997e-06, | |
| "loss": 0.5876, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 7.225548902195609e-06, | |
| "loss": 0.5605, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.826347305389223e-06, | |
| "loss": 0.5345, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9744744744744744, | |
| "eval_f1": 0.973584165402074, | |
| "eval_loss": 0.42139312624931335, | |
| "eval_precision": 0.976877941401268, | |
| "eval_recall": 0.9744744744744744, | |
| "eval_runtime": 3.9585, | |
| "eval_samples_per_second": 168.247, | |
| "eval_steps_per_second": 5.305, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.427145708582835e-06, | |
| "loss": 0.5248, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.027944111776448e-06, | |
| "loss": 0.4671, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.62874251497006e-06, | |
| "loss": 0.4804, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.229540918163674e-06, | |
| "loss": 0.4354, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.830339321357286e-06, | |
| "loss": 0.4218, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.431137724550898e-06, | |
| "loss": 0.4162, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.031936127744511e-06, | |
| "loss": 0.4194, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.6327345309381242e-06, | |
| "loss": 0.3967, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.2335329341317368e-06, | |
| "loss": 0.3876, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.8343313373253494e-06, | |
| "loss": 0.3711, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.4351297405189623e-06, | |
| "loss": 0.4061, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.035928143712575e-06, | |
| "loss": 0.3654, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.6367265469061877e-06, | |
| "loss": 0.379, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.2375249500998005e-06, | |
| "loss": 0.3622, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 8.383233532934132e-07, | |
| "loss": 0.3553, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.39121756487026e-07, | |
| "loss": 0.3665, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.992015968063872e-08, | |
| "loss": 0.3472, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9864864864864865, | |
| "eval_f1": 0.9863776360625434, | |
| "eval_loss": 0.27318987250328064, | |
| "eval_precision": 0.987865864189957, | |
| "eval_recall": 0.9864864864864865, | |
| "eval_runtime": 3.7863, | |
| "eval_samples_per_second": 175.899, | |
| "eval_steps_per_second": 5.546, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 501, | |
| "total_flos": 2118227382190080.0, | |
| "train_loss": 1.1732605536302882, | |
| "train_runtime": 338.4848, | |
| "train_samples_per_second": 47.222, | |
| "train_steps_per_second": 1.48 | |
| } | |
| ], | |
| "max_steps": 501, | |
| "num_train_epochs": 3, | |
| "total_flos": 2118227382190080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |