| { | |
| "best_metric": 0.6960989202368513, | |
| "best_model_checkpoint": "google-vit-base-patch16-224-face/checkpoint-712", | |
| "epoch": 7.991643454038997, | |
| "global_step": 712, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.9691, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.9687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9727, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.9245, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 0.8955, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8887, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 0.8827, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00011850000000000001, | |
| "loss": 0.8364, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.648380355276907, | |
| "eval_f1": 0.6385482827611145, | |
| "eval_loss": 0.9452694654464722, | |
| "eval_precision": 0.6461904026185493, | |
| "eval_recall": 0.648380355276907, | |
| "eval_runtime": 32.7545, | |
| "eval_samples_per_second": 175.304, | |
| "eval_steps_per_second": 2.748, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.000116625, | |
| "loss": 0.9165, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00011475000000000001, | |
| "loss": 0.765, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.000112875, | |
| "loss": 0.7639, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00011100000000000001, | |
| "loss": 0.7557, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00010912500000000001, | |
| "loss": 0.7494, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00010725, | |
| "loss": 0.7363, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00010537500000000001, | |
| "loss": 0.7147, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00010350000000000001, | |
| "loss": 0.7283, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.000101625, | |
| "loss": 0.7433, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.6778126088470916, | |
| "eval_f1": 0.672969661980768, | |
| "eval_loss": 0.8876001834869385, | |
| "eval_precision": 0.679362397138447, | |
| "eval_recall": 0.6778126088470916, | |
| "eval_runtime": 37.9557, | |
| "eval_samples_per_second": 151.282, | |
| "eval_steps_per_second": 2.371, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.975000000000001e-05, | |
| "loss": 0.7192, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.787500000000001e-05, | |
| "loss": 0.5258, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.5159, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 9.412500000000001e-05, | |
| "loss": 0.5151, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.225e-05, | |
| "loss": 0.5134, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.0375e-05, | |
| "loss": 0.4776, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 8.850000000000001e-05, | |
| "loss": 0.5188, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 8.6625e-05, | |
| "loss": 0.5312, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.475000000000001e-05, | |
| "loss": 0.4732, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.6872169975618252, | |
| "eval_f1": 0.6840932939913709, | |
| "eval_loss": 0.9042980670928955, | |
| "eval_precision": 0.6906579200512205, | |
| "eval_recall": 0.6872169975618252, | |
| "eval_runtime": 32.8137, | |
| "eval_samples_per_second": 174.988, | |
| "eval_steps_per_second": 2.743, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.287500000000001e-05, | |
| "loss": 0.4772, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 8.1e-05, | |
| "loss": 0.299, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.912500000000001e-05, | |
| "loss": 0.2614, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 7.725000000000001e-05, | |
| "loss": 0.2679, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 7.5375e-05, | |
| "loss": 0.2992, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 7.350000000000001e-05, | |
| "loss": 0.2835, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 7.1625e-05, | |
| "loss": 0.2752, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 6.975e-05, | |
| "loss": 0.27, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 6.787500000000001e-05, | |
| "loss": 0.2861, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.6847788227098572, | |
| "eval_f1": 0.6813474424826861, | |
| "eval_loss": 0.9865238666534424, | |
| "eval_precision": 0.6808262458026351, | |
| "eval_recall": 0.6847788227098572, | |
| "eval_runtime": 34.0061, | |
| "eval_samples_per_second": 168.852, | |
| "eval_steps_per_second": 2.647, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.2485, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 6.412500000000001e-05, | |
| "loss": 0.1212, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 6.225000000000001e-05, | |
| "loss": 0.121, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 6.0375000000000004e-05, | |
| "loss": 0.131, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.85e-05, | |
| "loss": 0.1192, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 5.6625e-05, | |
| "loss": 0.1137, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 5.475e-05, | |
| "loss": 0.1334, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 5.2875e-05, | |
| "loss": 0.1285, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 5.1e-05, | |
| "loss": 0.1234, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.6853012887495646, | |
| "eval_f1": 0.6871627462072427, | |
| "eval_loss": 1.1047998666763306, | |
| "eval_precision": 0.6907009316583976, | |
| "eval_recall": 0.6853012887495646, | |
| "eval_runtime": 32.6937, | |
| "eval_samples_per_second": 175.63, | |
| "eval_steps_per_second": 2.753, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 4.9125e-05, | |
| "loss": 0.1018, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 4.7249999999999997e-05, | |
| "loss": 0.053, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.5375e-05, | |
| "loss": 0.0495, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 4.35e-05, | |
| "loss": 0.052, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 4.1625e-05, | |
| "loss": 0.0597, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 3.975e-05, | |
| "loss": 0.0548, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 3.7875e-05, | |
| "loss": 0.0619, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0627, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 3.4125e-05, | |
| "loss": 0.0599, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.6889585510275166, | |
| "eval_f1": 0.6876003709723829, | |
| "eval_loss": 1.2361745834350586, | |
| "eval_precision": 0.6897347831759311, | |
| "eval_recall": 0.6889585510275166, | |
| "eval_runtime": 34.0898, | |
| "eval_samples_per_second": 168.437, | |
| "eval_steps_per_second": 2.64, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 3.225e-05, | |
| "loss": 0.0431, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 3.0375e-05, | |
| "loss": 0.033, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 2.8499999999999998e-05, | |
| "loss": 0.0332, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 2.6625e-05, | |
| "loss": 0.0315, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 2.475e-05, | |
| "loss": 0.0305, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 2.2875e-05, | |
| "loss": 0.0243, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0241, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.9125e-05, | |
| "loss": 0.0206, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.725e-05, | |
| "loss": 0.0289, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.6931382793451759, | |
| "eval_f1": 0.6921150248707686, | |
| "eval_loss": 1.3140767812728882, | |
| "eval_precision": 0.6925717262836596, | |
| "eval_recall": 0.6931382793451759, | |
| "eval_runtime": 33.0395, | |
| "eval_samples_per_second": 173.792, | |
| "eval_steps_per_second": 2.724, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.5374999999999998e-05, | |
| "loss": 0.0185, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 0.0132, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.1625000000000001e-05, | |
| "loss": 0.014, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 9.75e-06, | |
| "loss": 0.0121, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 7.875e-06, | |
| "loss": 0.0203, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0103, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 4.125e-06, | |
| "loss": 0.0178, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.0126, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 3.75e-07, | |
| "loss": 0.0134, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.6960989202368513, | |
| "eval_f1": 0.6957934361657124, | |
| "eval_loss": 1.3257348537445068, | |
| "eval_precision": 0.6966334506335445, | |
| "eval_recall": 0.6960989202368513, | |
| "eval_runtime": 37.8195, | |
| "eval_samples_per_second": 151.827, | |
| "eval_steps_per_second": 2.38, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "step": 712, | |
| "total_flos": 1.4224524590735456e+19, | |
| "train_loss": 0.3359685759269371, | |
| "train_runtime": 2345.2254, | |
| "train_samples_per_second": 78.345, | |
| "train_steps_per_second": 0.304 | |
| } | |
| ], | |
| "max_steps": 712, | |
| "num_train_epochs": 8, | |
| "total_flos": 1.4224524590735456e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |