| { | |
| "best_metric": 0.8974074074074074, | |
| "best_model_checkpoint": "resnet-50-finetuned-combinedSpiders/checkpoint-1348", | |
| "epoch": 3.9940740740740743, | |
| "eval_steps": 500, | |
| "global_step": 1348, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 2.3139, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 2.3199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 2.3141, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 2.3051, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 2.3055, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.2966, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 2.2891, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 2.2871, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.2767, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 2.2604, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 2.254, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 2.2329, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 2.2251, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.979389942291839e-05, | |
| "loss": 2.2012, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.9381698268755155e-05, | |
| "loss": 2.1776, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.896949711459192e-05, | |
| "loss": 2.1594, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.8557295960428687e-05, | |
| "loss": 2.1244, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.814509480626546e-05, | |
| "loss": 2.0911, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.7732893652102225e-05, | |
| "loss": 2.071, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.7320692497939e-05, | |
| "loss": 2.0046, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.6908491343775764e-05, | |
| "loss": 1.9742, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.649629018961254e-05, | |
| "loss": 1.9107, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.60840890354493e-05, | |
| "loss": 1.8838, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.567188788128607e-05, | |
| "loss": 1.8305, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.525968672712284e-05, | |
| "loss": 1.7924, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.484748557295961e-05, | |
| "loss": 1.7411, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.443528441879637e-05, | |
| "loss": 1.6658, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.402308326463314e-05, | |
| "loss": 1.6818, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.361088211046991e-05, | |
| "loss": 1.5883, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.319868095630668e-05, | |
| "loss": 1.5316, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.278647980214345e-05, | |
| "loss": 1.5345, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.2374278647980216e-05, | |
| "loss": 1.4529, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.196207749381699e-05, | |
| "loss": 1.4418, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6692592592592592, | |
| "eval_f1": 0.6056123000612204, | |
| "eval_loss": 1.2732560634613037, | |
| "eval_precision": 0.6781768119793957, | |
| "eval_recall": 0.6388902436275756, | |
| "eval_runtime": 15.6445, | |
| "eval_samples_per_second": 172.584, | |
| "eval_steps_per_second": 10.803, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.1549876339653755e-05, | |
| "loss": 1.4001, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.113767518549052e-05, | |
| "loss": 1.3676, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.072547403132729e-05, | |
| "loss": 1.3273, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.031327287716406e-05, | |
| "loss": 1.3226, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.9901071723000826e-05, | |
| "loss": 1.2902, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.948887056883759e-05, | |
| "loss": 1.2565, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.907666941467436e-05, | |
| "loss": 1.2411, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.866446826051113e-05, | |
| "loss": 1.2337, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.82522671063479e-05, | |
| "loss": 1.1719, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.784006595218467e-05, | |
| "loss": 1.1746, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.7427864798021435e-05, | |
| "loss": 1.1444, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.701566364385821e-05, | |
| "loss": 1.1284, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.6603462489694974e-05, | |
| "loss": 1.09, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3.619126133553174e-05, | |
| "loss": 1.1276, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.577906018136851e-05, | |
| "loss": 1.0837, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.536685902720528e-05, | |
| "loss": 1.0355, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.4954657873042044e-05, | |
| "loss": 0.9847, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 3.454245671887881e-05, | |
| "loss": 1.0393, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.413025556471558e-05, | |
| "loss": 1.008, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 3.371805441055235e-05, | |
| "loss": 0.977, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.330585325638912e-05, | |
| "loss": 0.9954, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.289365210222589e-05, | |
| "loss": 0.9811, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.248145094806266e-05, | |
| "loss": 1.0519, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.2069249793899426e-05, | |
| "loss": 0.9764, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.165704863973619e-05, | |
| "loss": 0.9426, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.124484748557296e-05, | |
| "loss": 0.9598, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.083264633140973e-05, | |
| "loss": 0.9344, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.0420445177246497e-05, | |
| "loss": 0.9049, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.0008244023083266e-05, | |
| "loss": 0.8284, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.9596042868920032e-05, | |
| "loss": 0.9119, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.9183841714756805e-05, | |
| "loss": 0.8489, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.877164056059357e-05, | |
| "loss": 0.8227, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.8359439406430337e-05, | |
| "loss": 0.8788, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.7947238252267106e-05, | |
| "loss": 0.9058, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8525925925925926, | |
| "eval_f1": 0.8410753034302768, | |
| "eval_loss": 0.5913922786712646, | |
| "eval_precision": 0.8467806416477608, | |
| "eval_recall": 0.840061365110396, | |
| "eval_runtime": 14.4146, | |
| "eval_samples_per_second": 187.31, | |
| "eval_steps_per_second": 11.724, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.753503709810388e-05, | |
| "loss": 0.8246, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.7122835943940645e-05, | |
| "loss": 0.8661, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.671063478977741e-05, | |
| "loss": 0.9393, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.6298433635614183e-05, | |
| "loss": 0.8919, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.588623248145095e-05, | |
| "loss": 0.8454, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.547403132728772e-05, | |
| "loss": 0.8213, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.5061830173124485e-05, | |
| "loss": 0.8213, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.4649629018961254e-05, | |
| "loss": 0.7937, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.4237427864798023e-05, | |
| "loss": 0.7901, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.382522671063479e-05, | |
| "loss": 0.8005, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.341302555647156e-05, | |
| "loss": 0.776, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.3000824402308328e-05, | |
| "loss": 0.776, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.2588623248145097e-05, | |
| "loss": 0.7684, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.2176422093981863e-05, | |
| "loss": 0.7854, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.1764220939818633e-05, | |
| "loss": 0.7608, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.13520197856554e-05, | |
| "loss": 0.7563, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.093981863149217e-05, | |
| "loss": 0.7836, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.0527617477328937e-05, | |
| "loss": 0.7936, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.0115416323165706e-05, | |
| "loss": 0.7693, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.9703215169002472e-05, | |
| "loss": 0.8235, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.9291014014839242e-05, | |
| "loss": 0.8423, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.887881286067601e-05, | |
| "loss": 0.6937, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.846661170651278e-05, | |
| "loss": 0.7325, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.805441055234955e-05, | |
| "loss": 0.779, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.7642209398186316e-05, | |
| "loss": 0.7278, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.7230008244023085e-05, | |
| "loss": 0.6911, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.681780708985985e-05, | |
| "loss": 0.7127, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.640560593569662e-05, | |
| "loss": 0.7116, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.599340478153339e-05, | |
| "loss": 0.76, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.558120362737016e-05, | |
| "loss": 0.7644, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.5169002473206925e-05, | |
| "loss": 0.7876, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.4756801319043694e-05, | |
| "loss": 0.6966, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 1.4344600164880462e-05, | |
| "loss": 0.7425, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.3932399010717231e-05, | |
| "loss": 0.743, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8881481481481481, | |
| "eval_f1": 0.8799732123735866, | |
| "eval_loss": 0.4424385130405426, | |
| "eval_precision": 0.8877465438754772, | |
| "eval_recall": 0.8775775457617858, | |
| "eval_runtime": 14.8388, | |
| "eval_samples_per_second": 181.956, | |
| "eval_steps_per_second": 11.389, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.3520197856553999e-05, | |
| "loss": 0.7802, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.3107996702390768e-05, | |
| "loss": 0.7482, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.2695795548227534e-05, | |
| "loss": 0.6815, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.2283594394064305e-05, | |
| "loss": 0.6821, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.1871393239901073e-05, | |
| "loss": 0.6976, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.145919208573784e-05, | |
| "loss": 0.7766, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.104699093157461e-05, | |
| "loss": 0.7489, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.0634789777411378e-05, | |
| "loss": 0.7489, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.0222588623248145e-05, | |
| "loss": 0.6568, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 9.810387469084915e-06, | |
| "loss": 0.7121, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 9.398186314921682e-06, | |
| "loss": 0.7013, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 8.98598516075845e-06, | |
| "loss": 0.667, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 8.573784006595219e-06, | |
| "loss": 0.715, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 8.161582852431987e-06, | |
| "loss": 0.6593, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 7.749381698268756e-06, | |
| "loss": 0.6886, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 7.337180544105524e-06, | |
| "loss": 0.712, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.924979389942292e-06, | |
| "loss": 0.752, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 6.51277823577906e-06, | |
| "loss": 0.6274, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 6.100577081615829e-06, | |
| "loss": 0.698, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 5.688375927452598e-06, | |
| "loss": 0.7475, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.276174773289365e-06, | |
| "loss": 0.7261, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 4.863973619126134e-06, | |
| "loss": 0.6776, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 4.451772464962902e-06, | |
| "loss": 0.6548, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 4.03957131079967e-06, | |
| "loss": 0.6526, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.6273701566364385e-06, | |
| "loss": 0.6432, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 3.215169002473207e-06, | |
| "loss": 0.6769, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2.8029678483099755e-06, | |
| "loss": 0.6966, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 2.390766694146744e-06, | |
| "loss": 0.662, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.978565539983512e-06, | |
| "loss": 0.6816, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.5663643858202803e-06, | |
| "loss": 0.6373, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.1541632316570488e-06, | |
| "loss": 0.6328, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 7.419620774938171e-07, | |
| "loss": 0.6925, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 3.2976092333058533e-07, | |
| "loss": 0.7272, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.8974074074074074, | |
| "eval_f1": 0.8910186753180345, | |
| "eval_loss": 0.3921002447605133, | |
| "eval_precision": 0.8937527021895239, | |
| "eval_recall": 0.8899884876686517, | |
| "eval_runtime": 14.7611, | |
| "eval_samples_per_second": 182.913, | |
| "eval_steps_per_second": 11.449, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "step": 1348, | |
| "total_flos": 1.8332979581807493e+18, | |
| "train_loss": 1.1345372907485736, | |
| "train_runtime": 1112.1938, | |
| "train_samples_per_second": 77.684, | |
| "train_steps_per_second": 1.212 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1348, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 1.8332979581807493e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |