| { | |
| "best_metric": 0.9894837476099426, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-icpr/checkpoint-2554", | |
| "epoch": 99.23664122137404, | |
| "eval_steps": 500, | |
| "global_step": 6500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 1.4616, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 1.4319, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 1.4003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 1.3194, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 1.2456, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 1.1149, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.762906309751434, | |
| "eval_loss": 0.9589953422546387, | |
| "eval_runtime": 10.6478, | |
| "eval_samples_per_second": 98.236, | |
| "eval_steps_per_second": 6.198, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.3846153846153855e-06, | |
| "loss": 0.9474, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.767, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 0.5454, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.3751, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.3008, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 0.281, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2653, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9531548757170172, | |
| "eval_loss": 0.16476869583129883, | |
| "eval_runtime": 10.0714, | |
| "eval_samples_per_second": 103.858, | |
| "eval_steps_per_second": 6.553, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.0769230769230771e-05, | |
| "loss": 0.2232, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 0.2024, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.230769230769231e-05, | |
| "loss": 0.1796, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.3076923076923078e-05, | |
| "loss": 0.2004, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.3846153846153847e-05, | |
| "loss": 0.1493, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.4615384615384617e-05, | |
| "loss": 0.1984, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.97131931166348, | |
| "eval_loss": 0.08937183022499084, | |
| "eval_runtime": 10.7983, | |
| "eval_samples_per_second": 96.867, | |
| "eval_steps_per_second": 6.112, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.1647, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.6153846153846154e-05, | |
| "loss": 0.1539, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.6923076923076924e-05, | |
| "loss": 0.1643, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.7692307692307694e-05, | |
| "loss": 0.1078, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.8461538461538465e-05, | |
| "loss": 0.127, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 0.1269, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1719, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9684512428298279, | |
| "eval_loss": 0.08631974458694458, | |
| "eval_runtime": 9.6084, | |
| "eval_samples_per_second": 108.863, | |
| "eval_steps_per_second": 6.869, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2.0769230769230772e-05, | |
| "loss": 0.1383, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 2.1538461538461542e-05, | |
| "loss": 0.1304, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.230769230769231e-05, | |
| "loss": 0.1392, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.1269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.384615384615385e-05, | |
| "loss": 0.1296, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.461538461538462e-05, | |
| "loss": 0.1537, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9760994263862333, | |
| "eval_loss": 0.08103872090578079, | |
| "eval_runtime": 10.0768, | |
| "eval_samples_per_second": 103.802, | |
| "eval_steps_per_second": 6.55, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.5384615384615383e-05, | |
| "loss": 0.1774, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 2.6153846153846157e-05, | |
| "loss": 0.1191, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.6923076923076923e-05, | |
| "loss": 0.1717, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 2.7692307692307694e-05, | |
| "loss": 0.1622, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 2.846153846153846e-05, | |
| "loss": 0.1145, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 2.9230769230769234e-05, | |
| "loss": 0.0814, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1162, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9770554493307839, | |
| "eval_loss": 0.07851049304008484, | |
| "eval_runtime": 10.7167, | |
| "eval_samples_per_second": 97.605, | |
| "eval_steps_per_second": 6.159, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.0778, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 3.153846153846154e-05, | |
| "loss": 0.0952, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 3.230769230769231e-05, | |
| "loss": 0.1505, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 3.307692307692308e-05, | |
| "loss": 0.1087, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 3.384615384615385e-05, | |
| "loss": 0.1069, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 3.461538461538462e-05, | |
| "loss": 0.1063, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.9722753346080306, | |
| "eval_loss": 0.08351072669029236, | |
| "eval_runtime": 9.7782, | |
| "eval_samples_per_second": 106.973, | |
| "eval_steps_per_second": 6.75, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.538461538461539e-05, | |
| "loss": 0.0976, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 3.615384615384615e-05, | |
| "loss": 0.0788, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 3.692307692307693e-05, | |
| "loss": 0.1104, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 3.769230769230769e-05, | |
| "loss": 0.1054, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.1131, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 3.923076923076923e-05, | |
| "loss": 0.1597, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1392, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9760994263862333, | |
| "eval_loss": 0.06736110895872116, | |
| "eval_runtime": 9.5406, | |
| "eval_samples_per_second": 109.637, | |
| "eval_steps_per_second": 6.918, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.0769230769230773e-05, | |
| "loss": 0.0986, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 4.1538461538461544e-05, | |
| "loss": 0.1179, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 4.230769230769231e-05, | |
| "loss": 0.0881, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.3076923076923084e-05, | |
| "loss": 0.0884, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 4.384615384615385e-05, | |
| "loss": 0.0972, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 4.461538461538462e-05, | |
| "loss": 0.1286, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.9760994263862333, | |
| "eval_loss": 0.07882168889045715, | |
| "eval_runtime": 10.4396, | |
| "eval_samples_per_second": 100.195, | |
| "eval_steps_per_second": 6.322, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.538461538461539e-05, | |
| "loss": 0.1296, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.0937, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 4.692307692307693e-05, | |
| "loss": 0.1032, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 4.76923076923077e-05, | |
| "loss": 0.1336, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 4.846153846153846e-05, | |
| "loss": 0.0927, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 4.923076923076924e-05, | |
| "loss": 0.1015, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1294, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.06581155955791473, | |
| "eval_runtime": 10.4314, | |
| "eval_samples_per_second": 100.274, | |
| "eval_steps_per_second": 6.327, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 4.991452991452992e-05, | |
| "loss": 0.1018, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 4.982905982905983e-05, | |
| "loss": 0.0903, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 4.9743589743589746e-05, | |
| "loss": 0.1085, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 4.965811965811966e-05, | |
| "loss": 0.0893, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 4.9572649572649575e-05, | |
| "loss": 0.1019, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 4.948717948717949e-05, | |
| "loss": 0.0631, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 4.94017094017094e-05, | |
| "loss": 0.0843, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.9732313575525813, | |
| "eval_loss": 0.07347707450389862, | |
| "eval_runtime": 10.5361, | |
| "eval_samples_per_second": 99.278, | |
| "eval_steps_per_second": 6.264, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 4.931623931623932e-05, | |
| "loss": 0.0675, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 4.923076923076924e-05, | |
| "loss": 0.1206, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 4.9145299145299147e-05, | |
| "loss": 0.0543, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.905982905982906e-05, | |
| "loss": 0.0973, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 4.8974358974358975e-05, | |
| "loss": 0.1046, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.074, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9760994263862333, | |
| "eval_loss": 0.06362002342939377, | |
| "eval_runtime": 10.045, | |
| "eval_samples_per_second": 104.131, | |
| "eval_steps_per_second": 6.57, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 4.8803418803418804e-05, | |
| "loss": 0.0947, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 4.871794871794872e-05, | |
| "loss": 0.079, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 4.863247863247863e-05, | |
| "loss": 0.1109, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 4.854700854700855e-05, | |
| "loss": 0.1039, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 4.846153846153846e-05, | |
| "loss": 0.0797, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 4.8376068376068376e-05, | |
| "loss": 0.0743, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 4.829059829059829e-05, | |
| "loss": 0.0734, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.9751434034416826, | |
| "eval_loss": 0.1042996272444725, | |
| "eval_runtime": 9.3639, | |
| "eval_samples_per_second": 111.706, | |
| "eval_steps_per_second": 7.048, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 4.8205128205128205e-05, | |
| "loss": 0.1188, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 4.8119658119658126e-05, | |
| "loss": 0.0659, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 4.803418803418804e-05, | |
| "loss": 0.092, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 4.7948717948717955e-05, | |
| "loss": 0.0565, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 4.786324786324787e-05, | |
| "loss": 0.0603, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.0774, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9722753346080306, | |
| "eval_loss": 0.08982475847005844, | |
| "eval_runtime": 10.6797, | |
| "eval_samples_per_second": 97.943, | |
| "eval_steps_per_second": 6.18, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 4.76923076923077e-05, | |
| "loss": 0.0848, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 4.7606837606837606e-05, | |
| "loss": 0.0684, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 4.752136752136752e-05, | |
| "loss": 0.0563, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 4.7435897435897435e-05, | |
| "loss": 0.0684, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "learning_rate": 4.735042735042735e-05, | |
| "loss": 0.0607, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 4.7264957264957264e-05, | |
| "loss": 0.0853, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 4.717948717948718e-05, | |
| "loss": 0.068, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.07194650918245316, | |
| "eval_runtime": 10.533, | |
| "eval_samples_per_second": 99.307, | |
| "eval_steps_per_second": 6.266, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 4.709401709401709e-05, | |
| "loss": 0.0867, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 4.700854700854701e-05, | |
| "loss": 0.0606, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 4.692307692307693e-05, | |
| "loss": 0.0921, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 4.683760683760684e-05, | |
| "loss": 0.1273, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 4.675213675213676e-05, | |
| "loss": 0.0708, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0821, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9741873804971319, | |
| "eval_loss": 0.09563681483268738, | |
| "eval_runtime": 9.5529, | |
| "eval_samples_per_second": 109.495, | |
| "eval_steps_per_second": 6.909, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 4.6581196581196586e-05, | |
| "loss": 0.1147, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 4.64957264957265e-05, | |
| "loss": 0.1188, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 4.6410256410256415e-05, | |
| "loss": 0.0562, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 4.632478632478633e-05, | |
| "loss": 0.0575, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.6239316239316244e-05, | |
| "loss": 0.0674, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.0855, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 4.6068376068376066e-05, | |
| "loss": 0.0576, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.97131931166348, | |
| "eval_loss": 0.07245714962482452, | |
| "eval_runtime": 9.8421, | |
| "eval_samples_per_second": 106.279, | |
| "eval_steps_per_second": 6.706, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 4.598290598290598e-05, | |
| "loss": 0.089, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 4.5897435897435895e-05, | |
| "loss": 0.0607, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "learning_rate": 4.581196581196581e-05, | |
| "loss": 0.0875, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 17.56, | |
| "learning_rate": 4.572649572649573e-05, | |
| "loss": 0.1147, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 4.5641025641025645e-05, | |
| "loss": 0.0751, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.0652, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9751434034416826, | |
| "eval_loss": 0.09574375301599503, | |
| "eval_runtime": 10.6204, | |
| "eval_samples_per_second": 98.489, | |
| "eval_steps_per_second": 6.214, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 4.5470085470085474e-05, | |
| "loss": 0.0591, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 4.538461538461539e-05, | |
| "loss": 0.0642, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 4.52991452991453e-05, | |
| "loss": 0.0819, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 4.521367521367522e-05, | |
| "loss": 0.0766, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 4.512820512820513e-05, | |
| "loss": 0.0906, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 4.5042735042735046e-05, | |
| "loss": 0.0694, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 4.495726495726496e-05, | |
| "loss": 0.0712, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.08092983067035675, | |
| "eval_runtime": 10.1615, | |
| "eval_samples_per_second": 102.937, | |
| "eval_steps_per_second": 6.495, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 4.4871794871794874e-05, | |
| "loss": 0.056, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 4.478632478632479e-05, | |
| "loss": 0.0751, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 19.39, | |
| "learning_rate": 4.47008547008547e-05, | |
| "loss": 0.0592, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 4.461538461538462e-05, | |
| "loss": 0.0627, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 4.452991452991453e-05, | |
| "loss": 0.0692, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0801, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.435897435897436e-05, | |
| "loss": 0.075, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9674952198852772, | |
| "eval_loss": 0.1283179670572281, | |
| "eval_runtime": 9.22, | |
| "eval_samples_per_second": 113.449, | |
| "eval_steps_per_second": 7.158, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.15, | |
| "learning_rate": 4.4273504273504275e-05, | |
| "loss": 0.0597, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 20.31, | |
| "learning_rate": 4.418803418803419e-05, | |
| "loss": 0.0835, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 20.46, | |
| "learning_rate": 4.4102564102564104e-05, | |
| "loss": 0.0788, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 20.61, | |
| "learning_rate": 4.401709401709402e-05, | |
| "loss": 0.0612, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 4.393162393162393e-05, | |
| "loss": 0.0565, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "learning_rate": 4.384615384615385e-05, | |
| "loss": 0.0988, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.9741873804971319, | |
| "eval_loss": 0.09660971164703369, | |
| "eval_runtime": 10.5136, | |
| "eval_samples_per_second": 99.49, | |
| "eval_steps_per_second": 6.278, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 21.07, | |
| "learning_rate": 4.376068376068376e-05, | |
| "loss": 0.0496, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 21.22, | |
| "learning_rate": 4.3675213675213676e-05, | |
| "loss": 0.0651, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 4.358974358974359e-05, | |
| "loss": 0.0545, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 4.3504273504273505e-05, | |
| "loss": 0.0774, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "learning_rate": 4.341880341880342e-05, | |
| "loss": 0.0632, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 21.83, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.0754, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "learning_rate": 4.324786324786325e-05, | |
| "loss": 0.0538, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9760994263862333, | |
| "eval_loss": 0.11253877729177475, | |
| "eval_runtime": 10.5371, | |
| "eval_samples_per_second": 99.269, | |
| "eval_steps_per_second": 6.264, | |
| "step": 1441 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 4.316239316239317e-05, | |
| "loss": 0.0742, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "learning_rate": 4.3076923076923084e-05, | |
| "loss": 0.0734, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 4.2991452991453e-05, | |
| "loss": 0.0792, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 22.6, | |
| "learning_rate": 4.2905982905982906e-05, | |
| "loss": 0.078, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "learning_rate": 4.282051282051282e-05, | |
| "loss": 0.0802, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 22.9, | |
| "learning_rate": 4.2735042735042735e-05, | |
| "loss": 0.0578, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.06480014324188232, | |
| "eval_runtime": 9.3635, | |
| "eval_samples_per_second": 111.71, | |
| "eval_steps_per_second": 7.049, | |
| "step": 1506 | |
| }, | |
| { | |
| "epoch": 23.05, | |
| "learning_rate": 4.264957264957265e-05, | |
| "loss": 0.0634, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 23.21, | |
| "learning_rate": 4.2564102564102564e-05, | |
| "loss": 0.0717, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 4.247863247863248e-05, | |
| "loss": 0.0661, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 23.51, | |
| "learning_rate": 4.239316239316239e-05, | |
| "loss": 0.0679, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 23.66, | |
| "learning_rate": 4.230769230769231e-05, | |
| "loss": 0.0646, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.0605, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 4.2136752136752136e-05, | |
| "loss": 0.0675, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.09923950582742691, | |
| "eval_runtime": 10.6598, | |
| "eval_samples_per_second": 98.126, | |
| "eval_steps_per_second": 6.192, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 24.12, | |
| "learning_rate": 4.205128205128206e-05, | |
| "loss": 0.0458, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 24.27, | |
| "learning_rate": 4.196581196581197e-05, | |
| "loss": 0.0425, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 24.43, | |
| "learning_rate": 4.1880341880341886e-05, | |
| "loss": 0.0637, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 24.58, | |
| "learning_rate": 4.17948717948718e-05, | |
| "loss": 0.0593, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 4.1709401709401715e-05, | |
| "loss": 0.0567, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 4.162393162393163e-05, | |
| "loss": 0.0611, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.06819227337837219, | |
| "eval_runtime": 10.2586, | |
| "eval_samples_per_second": 101.963, | |
| "eval_steps_per_second": 6.434, | |
| "step": 1637 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 4.1538461538461544e-05, | |
| "loss": 0.0694, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 25.19, | |
| "learning_rate": 4.145299145299146e-05, | |
| "loss": 0.0484, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 25.34, | |
| "learning_rate": 4.1367521367521366e-05, | |
| "loss": 0.0558, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 25.5, | |
| "learning_rate": 4.128205128205128e-05, | |
| "loss": 0.0498, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 25.65, | |
| "learning_rate": 4.1196581196581195e-05, | |
| "loss": 0.0521, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 25.8, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.0939, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 4.1025641025641023e-05, | |
| "loss": 0.0434, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.0718933716416359, | |
| "eval_runtime": 12.7961, | |
| "eval_samples_per_second": 81.744, | |
| "eval_steps_per_second": 5.158, | |
| "step": 1703 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 4.094017094017094e-05, | |
| "loss": 0.0384, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 26.26, | |
| "learning_rate": 4.085470085470086e-05, | |
| "loss": 0.0533, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 26.41, | |
| "learning_rate": 4.0769230769230773e-05, | |
| "loss": 0.0483, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 4.068376068376069e-05, | |
| "loss": 0.0627, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 4.05982905982906e-05, | |
| "loss": 0.071, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "learning_rate": 4.051282051282052e-05, | |
| "loss": 0.0339, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.9780114722753346, | |
| "eval_loss": 0.09302157908678055, | |
| "eval_runtime": 10.3175, | |
| "eval_samples_per_second": 101.381, | |
| "eval_steps_per_second": 6.397, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.042735042735043e-05, | |
| "loss": 0.0597, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 27.18, | |
| "learning_rate": 4.0341880341880346e-05, | |
| "loss": 0.0443, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 4.025641025641026e-05, | |
| "loss": 0.0623, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 27.48, | |
| "learning_rate": 4.0170940170940174e-05, | |
| "loss": 0.0757, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 27.63, | |
| "learning_rate": 4.008547008547009e-05, | |
| "loss": 0.0294, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 27.79, | |
| "learning_rate": 4e-05, | |
| "loss": 0.063, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 27.94, | |
| "learning_rate": 3.991452991452992e-05, | |
| "loss": 0.0346, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.0902632623910904, | |
| "eval_runtime": 9.3456, | |
| "eval_samples_per_second": 111.924, | |
| "eval_steps_per_second": 7.062, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 3.9829059829059825e-05, | |
| "loss": 0.047, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 3.974358974358974e-05, | |
| "loss": 0.0743, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 3.965811965811966e-05, | |
| "loss": 0.0471, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "learning_rate": 3.9572649572649575e-05, | |
| "loss": 0.0453, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 28.7, | |
| "learning_rate": 3.948717948717949e-05, | |
| "loss": 0.0784, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 3.9401709401709404e-05, | |
| "loss": 0.0806, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.09031251072883606, | |
| "eval_runtime": 10.3537, | |
| "eval_samples_per_second": 101.026, | |
| "eval_steps_per_second": 6.375, | |
| "step": 1899 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 3.931623931623932e-05, | |
| "loss": 0.0711, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 29.16, | |
| "learning_rate": 3.923076923076923e-05, | |
| "loss": 0.0381, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 29.31, | |
| "learning_rate": 3.914529914529915e-05, | |
| "loss": 0.0437, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 29.47, | |
| "learning_rate": 3.905982905982906e-05, | |
| "loss": 0.0597, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 29.62, | |
| "learning_rate": 3.8974358974358976e-05, | |
| "loss": 0.0347, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 29.77, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0482, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 29.92, | |
| "learning_rate": 3.8803418803418805e-05, | |
| "loss": 0.0518, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.09824305772781372, | |
| "eval_runtime": 10.4776, | |
| "eval_samples_per_second": 99.832, | |
| "eval_steps_per_second": 6.299, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 30.08, | |
| "learning_rate": 3.871794871794872e-05, | |
| "loss": 0.0362, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 30.23, | |
| "learning_rate": 3.8632478632478634e-05, | |
| "loss": 0.0363, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 30.38, | |
| "learning_rate": 3.854700854700855e-05, | |
| "loss": 0.0474, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 30.53, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.0475, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 3.837606837606838e-05, | |
| "loss": 0.0605, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 30.84, | |
| "learning_rate": 3.82905982905983e-05, | |
| "loss": 0.0635, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 3.8205128205128206e-05, | |
| "loss": 0.0407, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.07017896324396133, | |
| "eval_runtime": 9.0926, | |
| "eval_samples_per_second": 115.038, | |
| "eval_steps_per_second": 7.259, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "learning_rate": 3.811965811965812e-05, | |
| "loss": 0.0449, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 31.3, | |
| "learning_rate": 3.8034188034188035e-05, | |
| "loss": 0.0321, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 31.45, | |
| "learning_rate": 3.794871794871795e-05, | |
| "loss": 0.0595, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "learning_rate": 3.7863247863247864e-05, | |
| "loss": 0.0452, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 31.76, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.0822, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "learning_rate": 3.769230769230769e-05, | |
| "loss": 0.0528, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9760994263862333, | |
| "eval_loss": 0.08967561274766922, | |
| "eval_runtime": 10.4871, | |
| "eval_samples_per_second": 99.741, | |
| "eval_steps_per_second": 6.293, | |
| "step": 2096 | |
| }, | |
| { | |
| "epoch": 32.06, | |
| "learning_rate": 3.760683760683761e-05, | |
| "loss": 0.0808, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 32.21, | |
| "learning_rate": 3.752136752136752e-05, | |
| "loss": 0.0616, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "learning_rate": 3.7435897435897436e-05, | |
| "loss": 0.0581, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 3.735042735042735e-05, | |
| "loss": 0.0522, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "learning_rate": 3.7264957264957265e-05, | |
| "loss": 0.0624, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 32.82, | |
| "learning_rate": 3.717948717948718e-05, | |
| "loss": 0.0542, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 3.70940170940171e-05, | |
| "loss": 0.0774, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.06260856240987778, | |
| "eval_runtime": 10.4508, | |
| "eval_samples_per_second": 100.088, | |
| "eval_steps_per_second": 6.315, | |
| "step": 2161 | |
| }, | |
| { | |
| "epoch": 33.13, | |
| "learning_rate": 3.7008547008547015e-05, | |
| "loss": 0.0516, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 3.692307692307693e-05, | |
| "loss": 0.0368, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "learning_rate": 3.6837606837606844e-05, | |
| "loss": 0.0509, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 33.59, | |
| "learning_rate": 3.675213675213676e-05, | |
| "loss": 0.0784, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 33.74, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.0732, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 3.658119658119658e-05, | |
| "loss": 0.053, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.05762642249464989, | |
| "eval_runtime": 9.1985, | |
| "eval_samples_per_second": 113.714, | |
| "eval_steps_per_second": 7.175, | |
| "step": 2227 | |
| }, | |
| { | |
| "epoch": 34.05, | |
| "learning_rate": 3.6495726495726495e-05, | |
| "loss": 0.0403, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 34.2, | |
| "learning_rate": 3.641025641025641e-05, | |
| "loss": 0.0429, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 34.35, | |
| "learning_rate": 3.6324786324786323e-05, | |
| "loss": 0.0629, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 34.5, | |
| "learning_rate": 3.623931623931624e-05, | |
| "loss": 0.0538, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 34.66, | |
| "learning_rate": 3.615384615384615e-05, | |
| "loss": 0.0995, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 34.81, | |
| "learning_rate": 3.606837606837607e-05, | |
| "loss": 0.0479, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 34.96, | |
| "learning_rate": 3.598290598290598e-05, | |
| "loss": 0.0512, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "eval_accuracy": 0.9847036328871893, | |
| "eval_loss": 0.07072658836841583, | |
| "eval_runtime": 10.4603, | |
| "eval_samples_per_second": 99.997, | |
| "eval_steps_per_second": 6.31, | |
| "step": 2292 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 3.58974358974359e-05, | |
| "loss": 0.0408, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 35.27, | |
| "learning_rate": 3.581196581196582e-05, | |
| "loss": 0.0599, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 35.42, | |
| "learning_rate": 3.572649572649573e-05, | |
| "loss": 0.0467, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "learning_rate": 3.5641025641025646e-05, | |
| "loss": 0.0415, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.0507, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 35.88, | |
| "learning_rate": 3.5470085470085474e-05, | |
| "loss": 0.0388, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.10397801548242569, | |
| "eval_runtime": 9.1827, | |
| "eval_samples_per_second": 113.91, | |
| "eval_steps_per_second": 7.187, | |
| "step": 2358 | |
| }, | |
| { | |
| "epoch": 36.03, | |
| "learning_rate": 3.538461538461539e-05, | |
| "loss": 0.044, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 36.18, | |
| "learning_rate": 3.52991452991453e-05, | |
| "loss": 0.0477, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 36.34, | |
| "learning_rate": 3.521367521367522e-05, | |
| "loss": 0.0627, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 36.49, | |
| "learning_rate": 3.5128205128205125e-05, | |
| "loss": 0.0486, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 36.64, | |
| "learning_rate": 3.504273504273504e-05, | |
| "loss": 0.0513, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 36.79, | |
| "learning_rate": 3.4957264957264954e-05, | |
| "loss": 0.0507, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 36.95, | |
| "learning_rate": 3.487179487179487e-05, | |
| "loss": 0.06, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.08400359004735947, | |
| "eval_runtime": 10.3767, | |
| "eval_samples_per_second": 100.803, | |
| "eval_steps_per_second": 6.36, | |
| "step": 2423 | |
| }, | |
| { | |
| "epoch": 37.1, | |
| "learning_rate": 3.478632478632479e-05, | |
| "loss": 0.0414, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 37.25, | |
| "learning_rate": 3.4700854700854704e-05, | |
| "loss": 0.0514, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 37.4, | |
| "learning_rate": 3.461538461538462e-05, | |
| "loss": 0.0591, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 37.56, | |
| "learning_rate": 3.452991452991453e-05, | |
| "loss": 0.0562, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 37.71, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.0224, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "learning_rate": 3.435897435897436e-05, | |
| "loss": 0.0477, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.98565965583174, | |
| "eval_loss": 0.06589007377624512, | |
| "eval_runtime": 10.3493, | |
| "eval_samples_per_second": 101.07, | |
| "eval_steps_per_second": 6.377, | |
| "step": 2489 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 3.4273504273504276e-05, | |
| "loss": 0.0414, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 38.17, | |
| "learning_rate": 3.418803418803419e-05, | |
| "loss": 0.0531, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 38.32, | |
| "learning_rate": 3.4102564102564105e-05, | |
| "loss": 0.0407, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 38.47, | |
| "learning_rate": 3.401709401709402e-05, | |
| "loss": 0.0605, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 38.63, | |
| "learning_rate": 3.3931623931623934e-05, | |
| "loss": 0.0504, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 38.78, | |
| "learning_rate": 3.384615384615385e-05, | |
| "loss": 0.0273, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 38.93, | |
| "learning_rate": 3.376068376068376e-05, | |
| "loss": 0.0482, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "eval_accuracy": 0.9894837476099426, | |
| "eval_loss": 0.04790885001420975, | |
| "eval_runtime": 9.1599, | |
| "eval_samples_per_second": 114.194, | |
| "eval_steps_per_second": 7.205, | |
| "step": 2554 | |
| }, | |
| { | |
| "epoch": 39.08, | |
| "learning_rate": 3.367521367521368e-05, | |
| "loss": 0.0457, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 39.24, | |
| "learning_rate": 3.358974358974359e-05, | |
| "loss": 0.0483, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 39.39, | |
| "learning_rate": 3.3504273504273506e-05, | |
| "loss": 0.0345, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 39.54, | |
| "learning_rate": 3.341880341880342e-05, | |
| "loss": 0.0418, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 39.69, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0738, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 39.85, | |
| "learning_rate": 3.324786324786325e-05, | |
| "loss": 0.0781, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.3162393162393164e-05, | |
| "loss": 0.0292, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.06987924128770828, | |
| "eval_runtime": 10.3998, | |
| "eval_samples_per_second": 100.579, | |
| "eval_steps_per_second": 6.346, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 40.15, | |
| "learning_rate": 3.307692307692308e-05, | |
| "loss": 0.0377, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 40.31, | |
| "learning_rate": 3.299145299145299e-05, | |
| "loss": 0.0298, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 40.46, | |
| "learning_rate": 3.290598290598291e-05, | |
| "loss": 0.0221, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 40.61, | |
| "learning_rate": 3.282051282051282e-05, | |
| "loss": 0.0246, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 40.76, | |
| "learning_rate": 3.2735042735042736e-05, | |
| "loss": 0.0517, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "learning_rate": 3.264957264957265e-05, | |
| "loss": 0.0386, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.10300048440694809, | |
| "eval_runtime": 10.0411, | |
| "eval_samples_per_second": 104.171, | |
| "eval_steps_per_second": 6.573, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 41.07, | |
| "learning_rate": 3.2564102564102565e-05, | |
| "loss": 0.0775, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 41.22, | |
| "learning_rate": 3.247863247863248e-05, | |
| "loss": 0.0777, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 41.37, | |
| "learning_rate": 3.2393162393162394e-05, | |
| "loss": 0.0516, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 3.230769230769231e-05, | |
| "loss": 0.0373, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 41.68, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.0505, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 41.83, | |
| "learning_rate": 3.2136752136752144e-05, | |
| "loss": 0.0494, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 41.98, | |
| "learning_rate": 3.205128205128206e-05, | |
| "loss": 0.0441, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.08014865964651108, | |
| "eval_runtime": 9.3785, | |
| "eval_samples_per_second": 111.532, | |
| "eval_steps_per_second": 7.037, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 42.14, | |
| "learning_rate": 3.1965811965811966e-05, | |
| "loss": 0.0428, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "learning_rate": 3.188034188034188e-05, | |
| "loss": 0.044, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 42.44, | |
| "learning_rate": 3.1794871794871795e-05, | |
| "loss": 0.0535, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 42.6, | |
| "learning_rate": 3.170940170940171e-05, | |
| "loss": 0.0467, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 42.75, | |
| "learning_rate": 3.162393162393162e-05, | |
| "loss": 0.0393, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 42.9, | |
| "learning_rate": 3.153846153846154e-05, | |
| "loss": 0.0269, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 42.99, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.10365654528141022, | |
| "eval_runtime": 10.553, | |
| "eval_samples_per_second": 99.119, | |
| "eval_steps_per_second": 6.254, | |
| "step": 2816 | |
| }, | |
| { | |
| "epoch": 43.05, | |
| "learning_rate": 3.145299145299145e-05, | |
| "loss": 0.048, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 43.21, | |
| "learning_rate": 3.136752136752137e-05, | |
| "loss": 0.0646, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 43.36, | |
| "learning_rate": 3.128205128205128e-05, | |
| "loss": 0.0448, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 43.51, | |
| "learning_rate": 3.1196581196581195e-05, | |
| "loss": 0.047, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 43.66, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.0191, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 43.82, | |
| "learning_rate": 3.102564102564103e-05, | |
| "loss": 0.0452, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 43.97, | |
| "learning_rate": 3.0940170940170946e-05, | |
| "loss": 0.0385, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.086981400847435, | |
| "eval_runtime": 10.1033, | |
| "eval_samples_per_second": 103.53, | |
| "eval_steps_per_second": 6.533, | |
| "step": 2882 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "learning_rate": 3.085470085470086e-05, | |
| "loss": 0.0587, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 44.27, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.0558, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 44.43, | |
| "learning_rate": 3.068376068376069e-05, | |
| "loss": 0.0461, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 3.05982905982906e-05, | |
| "loss": 0.0416, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 44.73, | |
| "learning_rate": 3.0512820512820518e-05, | |
| "loss": 0.0405, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "learning_rate": 3.0427350427350425e-05, | |
| "loss": 0.0502, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 44.99, | |
| "eval_accuracy": 0.9770554493307839, | |
| "eval_loss": 0.13666602969169617, | |
| "eval_runtime": 9.3328, | |
| "eval_samples_per_second": 112.078, | |
| "eval_steps_per_second": 7.072, | |
| "step": 2947 | |
| }, | |
| { | |
| "epoch": 45.04, | |
| "learning_rate": 3.034188034188034e-05, | |
| "loss": 0.0508, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 45.19, | |
| "learning_rate": 3.0256410256410257e-05, | |
| "loss": 0.0438, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 45.34, | |
| "learning_rate": 3.0170940170940172e-05, | |
| "loss": 0.0156, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 45.5, | |
| "learning_rate": 3.0085470085470086e-05, | |
| "loss": 0.0662, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 45.65, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0606, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 45.8, | |
| "learning_rate": 2.9914529914529915e-05, | |
| "loss": 0.052, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 45.95, | |
| "learning_rate": 2.982905982905983e-05, | |
| "loss": 0.0389, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.9770554493307839, | |
| "eval_loss": 0.10930032283067703, | |
| "eval_runtime": 10.4976, | |
| "eval_samples_per_second": 99.642, | |
| "eval_steps_per_second": 6.287, | |
| "step": 3013 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 2.9743589743589744e-05, | |
| "loss": 0.0499, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 46.26, | |
| "learning_rate": 2.965811965811966e-05, | |
| "loss": 0.0365, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 46.41, | |
| "learning_rate": 2.9572649572649573e-05, | |
| "loss": 0.0411, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 46.56, | |
| "learning_rate": 2.948717948717949e-05, | |
| "loss": 0.0315, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 46.72, | |
| "learning_rate": 2.9401709401709405e-05, | |
| "loss": 0.0598, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 46.87, | |
| "learning_rate": 2.931623931623932e-05, | |
| "loss": 0.0209, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 46.99, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.0954117476940155, | |
| "eval_runtime": 10.251, | |
| "eval_samples_per_second": 102.039, | |
| "eval_steps_per_second": 6.438, | |
| "step": 3078 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.9230769230769234e-05, | |
| "loss": 0.0785, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 47.18, | |
| "learning_rate": 2.914529914529915e-05, | |
| "loss": 0.0432, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 47.33, | |
| "learning_rate": 2.9059829059829063e-05, | |
| "loss": 0.0427, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 47.48, | |
| "learning_rate": 2.8974358974358977e-05, | |
| "loss": 0.0421, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 47.63, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.035, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 47.79, | |
| "learning_rate": 2.8803418803418803e-05, | |
| "loss": 0.0275, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 47.94, | |
| "learning_rate": 2.8717948717948717e-05, | |
| "loss": 0.0327, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.98565965583174, | |
| "eval_loss": 0.08863285183906555, | |
| "eval_runtime": 9.2312, | |
| "eval_samples_per_second": 113.312, | |
| "eval_steps_per_second": 7.15, | |
| "step": 3144 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 2.863247863247863e-05, | |
| "loss": 0.0332, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 48.24, | |
| "learning_rate": 2.8547008547008546e-05, | |
| "loss": 0.0532, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 48.4, | |
| "learning_rate": 2.846153846153846e-05, | |
| "loss": 0.0212, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 48.55, | |
| "learning_rate": 2.8376068376068378e-05, | |
| "loss": 0.0406, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 48.7, | |
| "learning_rate": 2.8290598290598293e-05, | |
| "loss": 0.0594, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 48.85, | |
| "learning_rate": 2.8205128205128207e-05, | |
| "loss": 0.0269, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 48.99, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.0766867846250534, | |
| "eval_runtime": 10.7207, | |
| "eval_samples_per_second": 97.568, | |
| "eval_steps_per_second": 6.156, | |
| "step": 3209 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 2.811965811965812e-05, | |
| "loss": 0.0588, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 49.16, | |
| "learning_rate": 2.8034188034188036e-05, | |
| "loss": 0.0418, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 49.31, | |
| "learning_rate": 2.794871794871795e-05, | |
| "loss": 0.0389, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 49.47, | |
| "learning_rate": 2.7863247863247865e-05, | |
| "loss": 0.0342, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 49.62, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.046, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 49.77, | |
| "learning_rate": 2.7692307692307694e-05, | |
| "loss": 0.0606, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 49.92, | |
| "learning_rate": 2.760683760683761e-05, | |
| "loss": 0.0461, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.98565965583174, | |
| "eval_loss": 0.06614663451910019, | |
| "eval_runtime": 10.6141, | |
| "eval_samples_per_second": 98.548, | |
| "eval_steps_per_second": 6.218, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 50.08, | |
| "learning_rate": 2.7521367521367526e-05, | |
| "loss": 0.0328, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 50.23, | |
| "learning_rate": 2.743589743589744e-05, | |
| "loss": 0.044, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 50.38, | |
| "learning_rate": 2.7350427350427355e-05, | |
| "loss": 0.0752, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 50.53, | |
| "learning_rate": 2.7264957264957262e-05, | |
| "loss": 0.0543, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 50.69, | |
| "learning_rate": 2.717948717948718e-05, | |
| "loss": 0.0331, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 50.84, | |
| "learning_rate": 2.7094017094017094e-05, | |
| "loss": 0.0436, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 50.99, | |
| "learning_rate": 2.700854700854701e-05, | |
| "loss": 0.0226, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 50.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.07688331604003906, | |
| "eval_runtime": 9.3318, | |
| "eval_samples_per_second": 112.09, | |
| "eval_steps_per_second": 7.073, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 51.15, | |
| "learning_rate": 2.6923076923076923e-05, | |
| "loss": 0.0394, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 51.3, | |
| "learning_rate": 2.6837606837606838e-05, | |
| "loss": 0.0444, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 51.45, | |
| "learning_rate": 2.6752136752136752e-05, | |
| "loss": 0.0424, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0507, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 51.76, | |
| "learning_rate": 2.658119658119658e-05, | |
| "loss": 0.033, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 2.64957264957265e-05, | |
| "loss": 0.0304, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.084078848361969, | |
| "eval_runtime": 10.4168, | |
| "eval_samples_per_second": 100.415, | |
| "eval_steps_per_second": 6.336, | |
| "step": 3406 | |
| }, | |
| { | |
| "epoch": 52.06, | |
| "learning_rate": 2.6410256410256413e-05, | |
| "loss": 0.0369, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 52.21, | |
| "learning_rate": 2.6324786324786328e-05, | |
| "loss": 0.0325, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 52.37, | |
| "learning_rate": 2.6239316239316242e-05, | |
| "loss": 0.0374, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 52.52, | |
| "learning_rate": 2.6153846153846157e-05, | |
| "loss": 0.0527, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 52.67, | |
| "learning_rate": 2.606837606837607e-05, | |
| "loss": 0.0321, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 52.82, | |
| "learning_rate": 2.5982905982905985e-05, | |
| "loss": 0.0725, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 52.98, | |
| "learning_rate": 2.58974358974359e-05, | |
| "loss": 0.0326, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 52.99, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.10022158920764923, | |
| "eval_runtime": 10.2475, | |
| "eval_samples_per_second": 102.074, | |
| "eval_steps_per_second": 6.441, | |
| "step": 3471 | |
| }, | |
| { | |
| "epoch": 53.13, | |
| "learning_rate": 2.5811965811965814e-05, | |
| "loss": 0.0557, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 53.28, | |
| "learning_rate": 2.5726495726495725e-05, | |
| "loss": 0.081, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 53.44, | |
| "learning_rate": 2.564102564102564e-05, | |
| "loss": 0.0479, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 53.59, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.0266, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 53.74, | |
| "learning_rate": 2.547008547008547e-05, | |
| "loss": 0.0559, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "learning_rate": 2.5384615384615383e-05, | |
| "loss": 0.0593, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.9847036328871893, | |
| "eval_loss": 0.06341515481472015, | |
| "eval_runtime": 9.7205, | |
| "eval_samples_per_second": 107.608, | |
| "eval_steps_per_second": 6.79, | |
| "step": 3537 | |
| }, | |
| { | |
| "epoch": 54.05, | |
| "learning_rate": 2.52991452991453e-05, | |
| "loss": 0.0338, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 54.2, | |
| "learning_rate": 2.5213675213675215e-05, | |
| "loss": 0.0373, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 54.35, | |
| "learning_rate": 2.512820512820513e-05, | |
| "loss": 0.0439, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 54.5, | |
| "learning_rate": 2.5042735042735044e-05, | |
| "loss": 0.0455, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 54.66, | |
| "learning_rate": 2.495726495726496e-05, | |
| "loss": 0.0393, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 54.81, | |
| "learning_rate": 2.4871794871794873e-05, | |
| "loss": 0.0427, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 54.96, | |
| "learning_rate": 2.4786324786324787e-05, | |
| "loss": 0.0489, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 54.99, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.070249542593956, | |
| "eval_runtime": 10.5454, | |
| "eval_samples_per_second": 99.191, | |
| "eval_steps_per_second": 6.259, | |
| "step": 3602 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 2.47008547008547e-05, | |
| "loss": 0.0264, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 55.27, | |
| "learning_rate": 2.461538461538462e-05, | |
| "loss": 0.0635, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 55.42, | |
| "learning_rate": 2.452991452991453e-05, | |
| "loss": 0.0655, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 55.57, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.0429, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 55.73, | |
| "learning_rate": 2.435897435897436e-05, | |
| "loss": 0.0381, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 55.88, | |
| "learning_rate": 2.4273504273504274e-05, | |
| "loss": 0.0495, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.10598118603229523, | |
| "eval_runtime": 10.001, | |
| "eval_samples_per_second": 104.589, | |
| "eval_steps_per_second": 6.599, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 56.03, | |
| "learning_rate": 2.4188034188034188e-05, | |
| "loss": 0.0579, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 56.18, | |
| "learning_rate": 2.4102564102564103e-05, | |
| "loss": 0.0539, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 56.34, | |
| "learning_rate": 2.401709401709402e-05, | |
| "loss": 0.0331, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 56.49, | |
| "learning_rate": 2.3931623931623935e-05, | |
| "loss": 0.0358, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 56.64, | |
| "learning_rate": 2.384615384615385e-05, | |
| "loss": 0.038, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 56.79, | |
| "learning_rate": 2.376068376068376e-05, | |
| "loss": 0.0515, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 56.95, | |
| "learning_rate": 2.3675213675213675e-05, | |
| "loss": 0.0457, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 56.99, | |
| "eval_accuracy": 0.9866156787762906, | |
| "eval_loss": 0.07145655900239944, | |
| "eval_runtime": 9.7095, | |
| "eval_samples_per_second": 107.729, | |
| "eval_steps_per_second": 6.797, | |
| "step": 3733 | |
| }, | |
| { | |
| "epoch": 57.1, | |
| "learning_rate": 2.358974358974359e-05, | |
| "loss": 0.0409, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 57.25, | |
| "learning_rate": 2.3504273504273504e-05, | |
| "loss": 0.0397, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 57.4, | |
| "learning_rate": 2.341880341880342e-05, | |
| "loss": 0.0365, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 57.56, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0507, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 57.71, | |
| "learning_rate": 2.324786324786325e-05, | |
| "loss": 0.0337, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 57.86, | |
| "learning_rate": 2.3162393162393165e-05, | |
| "loss": 0.0487, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09061739593744278, | |
| "eval_runtime": 10.6263, | |
| "eval_samples_per_second": 98.435, | |
| "eval_steps_per_second": 6.211, | |
| "step": 3799 | |
| }, | |
| { | |
| "epoch": 58.02, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.0427, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 58.17, | |
| "learning_rate": 2.299145299145299e-05, | |
| "loss": 0.0403, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 58.32, | |
| "learning_rate": 2.2905982905982905e-05, | |
| "loss": 0.0229, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 58.47, | |
| "learning_rate": 2.2820512820512822e-05, | |
| "loss": 0.0724, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 58.63, | |
| "learning_rate": 2.2735042735042737e-05, | |
| "loss": 0.0215, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 58.78, | |
| "learning_rate": 2.264957264957265e-05, | |
| "loss": 0.0358, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 58.93, | |
| "learning_rate": 2.2564102564102566e-05, | |
| "loss": 0.0416, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 58.99, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.0973171517252922, | |
| "eval_runtime": 9.7778, | |
| "eval_samples_per_second": 106.977, | |
| "eval_steps_per_second": 6.75, | |
| "step": 3864 | |
| }, | |
| { | |
| "epoch": 59.08, | |
| "learning_rate": 2.247863247863248e-05, | |
| "loss": 0.0285, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 59.24, | |
| "learning_rate": 2.2393162393162394e-05, | |
| "loss": 0.0363, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 59.39, | |
| "learning_rate": 2.230769230769231e-05, | |
| "loss": 0.0434, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 59.54, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0364, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 59.69, | |
| "learning_rate": 2.2136752136752138e-05, | |
| "loss": 0.0308, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 59.85, | |
| "learning_rate": 2.2051282051282052e-05, | |
| "loss": 0.0392, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.1965811965811967e-05, | |
| "loss": 0.0358, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.98565965583174, | |
| "eval_loss": 0.08869770169258118, | |
| "eval_runtime": 9.8493, | |
| "eval_samples_per_second": 106.2, | |
| "eval_steps_per_second": 6.701, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 60.15, | |
| "learning_rate": 2.188034188034188e-05, | |
| "loss": 0.0416, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 60.31, | |
| "learning_rate": 2.1794871794871795e-05, | |
| "loss": 0.0491, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 60.46, | |
| "learning_rate": 2.170940170940171e-05, | |
| "loss": 0.0342, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 60.61, | |
| "learning_rate": 2.1623931623931624e-05, | |
| "loss": 0.0427, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 60.76, | |
| "learning_rate": 2.1538461538461542e-05, | |
| "loss": 0.026, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "learning_rate": 2.1452991452991453e-05, | |
| "loss": 0.0503, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 60.99, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.09588623046875, | |
| "eval_runtime": 10.6142, | |
| "eval_samples_per_second": 98.548, | |
| "eval_steps_per_second": 6.218, | |
| "step": 3995 | |
| }, | |
| { | |
| "epoch": 61.07, | |
| "learning_rate": 2.1367521367521368e-05, | |
| "loss": 0.0453, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 61.22, | |
| "learning_rate": 2.1282051282051282e-05, | |
| "loss": 0.0431, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 61.37, | |
| "learning_rate": 2.1196581196581196e-05, | |
| "loss": 0.0349, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 61.53, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.0243, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 61.68, | |
| "learning_rate": 2.102564102564103e-05, | |
| "loss": 0.0447, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 61.83, | |
| "learning_rate": 2.0940170940170943e-05, | |
| "loss": 0.03, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 61.98, | |
| "learning_rate": 2.0854700854700857e-05, | |
| "loss": 0.0555, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.9780114722753346, | |
| "eval_loss": 0.10571310669183731, | |
| "eval_runtime": 9.8843, | |
| "eval_samples_per_second": 105.825, | |
| "eval_steps_per_second": 6.677, | |
| "step": 4061 | |
| }, | |
| { | |
| "epoch": 62.14, | |
| "learning_rate": 2.0769230769230772e-05, | |
| "loss": 0.0497, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 62.29, | |
| "learning_rate": 2.0683760683760683e-05, | |
| "loss": 0.0216, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 62.44, | |
| "learning_rate": 2.0598290598290597e-05, | |
| "loss": 0.053, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 62.6, | |
| "learning_rate": 2.0512820512820512e-05, | |
| "loss": 0.0525, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 62.75, | |
| "learning_rate": 2.042735042735043e-05, | |
| "loss": 0.0426, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 62.9, | |
| "learning_rate": 2.0341880341880344e-05, | |
| "loss": 0.0288, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.09712828695774078, | |
| "eval_runtime": 10.2313, | |
| "eval_samples_per_second": 102.235, | |
| "eval_steps_per_second": 6.451, | |
| "step": 4126 | |
| }, | |
| { | |
| "epoch": 63.05, | |
| "learning_rate": 2.025641025641026e-05, | |
| "loss": 0.0289, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 63.21, | |
| "learning_rate": 2.0170940170940173e-05, | |
| "loss": 0.0196, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 63.36, | |
| "learning_rate": 2.0085470085470087e-05, | |
| "loss": 0.034, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 63.51, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0398, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 63.66, | |
| "learning_rate": 1.9914529914529913e-05, | |
| "loss": 0.0195, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 63.82, | |
| "learning_rate": 1.982905982905983e-05, | |
| "loss": 0.0401, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "learning_rate": 1.9743589743589745e-05, | |
| "loss": 0.0514, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.9847036328871893, | |
| "eval_loss": 0.0754217728972435, | |
| "eval_runtime": 10.6351, | |
| "eval_samples_per_second": 98.353, | |
| "eval_steps_per_second": 6.206, | |
| "step": 4192 | |
| }, | |
| { | |
| "epoch": 64.12, | |
| "learning_rate": 1.965811965811966e-05, | |
| "loss": 0.0345, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 64.27, | |
| "learning_rate": 1.9572649572649574e-05, | |
| "loss": 0.0399, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 64.43, | |
| "learning_rate": 1.9487179487179488e-05, | |
| "loss": 0.0563, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 64.58, | |
| "learning_rate": 1.9401709401709403e-05, | |
| "loss": 0.0366, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 64.73, | |
| "learning_rate": 1.9316239316239317e-05, | |
| "loss": 0.0268, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 64.89, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 0.0602, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 64.99, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.07885503023862839, | |
| "eval_runtime": 9.6953, | |
| "eval_samples_per_second": 107.888, | |
| "eval_steps_per_second": 6.807, | |
| "step": 4257 | |
| }, | |
| { | |
| "epoch": 65.04, | |
| "learning_rate": 1.914529914529915e-05, | |
| "loss": 0.0301, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 65.19, | |
| "learning_rate": 1.905982905982906e-05, | |
| "loss": 0.0662, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 65.34, | |
| "learning_rate": 1.8974358974358975e-05, | |
| "loss": 0.0315, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 65.5, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0182, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 65.65, | |
| "learning_rate": 1.8803418803418804e-05, | |
| "loss": 0.0177, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 65.8, | |
| "learning_rate": 1.8717948717948718e-05, | |
| "loss": 0.019, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 65.95, | |
| "learning_rate": 1.8632478632478632e-05, | |
| "loss": 0.0209, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.10050670802593231, | |
| "eval_runtime": 10.2235, | |
| "eval_samples_per_second": 102.314, | |
| "eval_steps_per_second": 6.456, | |
| "step": 4323 | |
| }, | |
| { | |
| "epoch": 66.11, | |
| "learning_rate": 1.854700854700855e-05, | |
| "loss": 0.0344, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 66.26, | |
| "learning_rate": 1.8461538461538465e-05, | |
| "loss": 0.0188, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 66.41, | |
| "learning_rate": 1.837606837606838e-05, | |
| "loss": 0.0495, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 66.56, | |
| "learning_rate": 1.829059829059829e-05, | |
| "loss": 0.0359, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 66.72, | |
| "learning_rate": 1.8205128205128204e-05, | |
| "loss": 0.0196, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 66.87, | |
| "learning_rate": 1.811965811965812e-05, | |
| "loss": 0.0366, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 66.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.10703601688146591, | |
| "eval_runtime": 10.6582, | |
| "eval_samples_per_second": 98.14, | |
| "eval_steps_per_second": 6.192, | |
| "step": 4388 | |
| }, | |
| { | |
| "epoch": 67.02, | |
| "learning_rate": 1.8034188034188033e-05, | |
| "loss": 0.0323, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 67.18, | |
| "learning_rate": 1.794871794871795e-05, | |
| "loss": 0.0326, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 67.33, | |
| "learning_rate": 1.7863247863247866e-05, | |
| "loss": 0.0348, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 67.48, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.031, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 67.63, | |
| "learning_rate": 1.7692307692307694e-05, | |
| "loss": 0.0283, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 67.79, | |
| "learning_rate": 1.760683760683761e-05, | |
| "loss": 0.0171, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 67.94, | |
| "learning_rate": 1.752136752136752e-05, | |
| "loss": 0.031, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.1018110066652298, | |
| "eval_runtime": 9.5096, | |
| "eval_samples_per_second": 109.994, | |
| "eval_steps_per_second": 6.94, | |
| "step": 4454 | |
| }, | |
| { | |
| "epoch": 68.09, | |
| "learning_rate": 1.7435897435897434e-05, | |
| "loss": 0.0254, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 68.24, | |
| "learning_rate": 1.7350427350427352e-05, | |
| "loss": 0.0367, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 68.4, | |
| "learning_rate": 1.7264957264957267e-05, | |
| "loss": 0.0227, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 68.55, | |
| "learning_rate": 1.717948717948718e-05, | |
| "loss": 0.0143, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 68.7, | |
| "learning_rate": 1.7094017094017095e-05, | |
| "loss": 0.0288, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 68.85, | |
| "learning_rate": 1.700854700854701e-05, | |
| "loss": 0.043, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 68.99, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.10203871130943298, | |
| "eval_runtime": 10.358, | |
| "eval_samples_per_second": 100.984, | |
| "eval_steps_per_second": 6.372, | |
| "step": 4519 | |
| }, | |
| { | |
| "epoch": 69.01, | |
| "learning_rate": 1.6923076923076924e-05, | |
| "loss": 0.0302, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 69.16, | |
| "learning_rate": 1.683760683760684e-05, | |
| "loss": 0.0235, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 69.31, | |
| "learning_rate": 1.6752136752136753e-05, | |
| "loss": 0.0463, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 69.47, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0232, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 69.62, | |
| "learning_rate": 1.6581196581196582e-05, | |
| "loss": 0.0559, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 69.77, | |
| "learning_rate": 1.6495726495726496e-05, | |
| "loss": 0.039, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 69.92, | |
| "learning_rate": 1.641025641025641e-05, | |
| "loss": 0.0262, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.08955594152212143, | |
| "eval_runtime": 10.4955, | |
| "eval_samples_per_second": 99.662, | |
| "eval_steps_per_second": 6.288, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 70.08, | |
| "learning_rate": 1.6324786324786325e-05, | |
| "loss": 0.0373, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 70.23, | |
| "learning_rate": 1.623931623931624e-05, | |
| "loss": 0.0138, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 70.38, | |
| "learning_rate": 1.6153846153846154e-05, | |
| "loss": 0.0264, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 70.53, | |
| "learning_rate": 1.6068376068376072e-05, | |
| "loss": 0.0185, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 70.69, | |
| "learning_rate": 1.5982905982905983e-05, | |
| "loss": 0.0496, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 70.84, | |
| "learning_rate": 1.5897435897435897e-05, | |
| "loss": 0.0351, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 70.99, | |
| "learning_rate": 1.581196581196581e-05, | |
| "loss": 0.0299, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 70.99, | |
| "eval_accuracy": 0.9837476099426387, | |
| "eval_loss": 0.09126070141792297, | |
| "eval_runtime": 9.1248, | |
| "eval_samples_per_second": 114.633, | |
| "eval_steps_per_second": 7.233, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 71.15, | |
| "learning_rate": 1.5726495726495726e-05, | |
| "loss": 0.0372, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 71.3, | |
| "learning_rate": 1.564102564102564e-05, | |
| "loss": 0.0291, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 71.45, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0301, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "learning_rate": 1.5470085470085473e-05, | |
| "loss": 0.0573, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 71.76, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.0186, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 71.91, | |
| "learning_rate": 1.52991452991453e-05, | |
| "loss": 0.0211, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.98565965583174, | |
| "eval_loss": 0.09574086219072342, | |
| "eval_runtime": 10.4838, | |
| "eval_samples_per_second": 99.773, | |
| "eval_steps_per_second": 6.295, | |
| "step": 4716 | |
| }, | |
| { | |
| "epoch": 72.06, | |
| "learning_rate": 1.5213675213675213e-05, | |
| "loss": 0.0405, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 72.21, | |
| "learning_rate": 1.5128205128205129e-05, | |
| "loss": 0.025, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 72.37, | |
| "learning_rate": 1.5042735042735043e-05, | |
| "loss": 0.0257, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 72.52, | |
| "learning_rate": 1.4957264957264958e-05, | |
| "loss": 0.0293, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 72.67, | |
| "learning_rate": 1.4871794871794872e-05, | |
| "loss": 0.0511, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 72.82, | |
| "learning_rate": 1.4786324786324786e-05, | |
| "loss": 0.0653, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 72.98, | |
| "learning_rate": 1.4700854700854703e-05, | |
| "loss": 0.0351, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 72.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.11798752844333649, | |
| "eval_runtime": 10.3353, | |
| "eval_samples_per_second": 101.207, | |
| "eval_steps_per_second": 6.386, | |
| "step": 4781 | |
| }, | |
| { | |
| "epoch": 73.13, | |
| "learning_rate": 1.4615384615384617e-05, | |
| "loss": 0.0298, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 73.28, | |
| "learning_rate": 1.4529914529914531e-05, | |
| "loss": 0.0382, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 73.44, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.0291, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 73.59, | |
| "learning_rate": 1.4358974358974359e-05, | |
| "loss": 0.0241, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 73.74, | |
| "learning_rate": 1.4273504273504273e-05, | |
| "loss": 0.0217, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "learning_rate": 1.4188034188034189e-05, | |
| "loss": 0.0498, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.10561424493789673, | |
| "eval_runtime": 9.5301, | |
| "eval_samples_per_second": 109.758, | |
| "eval_steps_per_second": 6.925, | |
| "step": 4847 | |
| }, | |
| { | |
| "epoch": 74.05, | |
| "learning_rate": 1.4102564102564104e-05, | |
| "loss": 0.0305, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 74.2, | |
| "learning_rate": 1.4017094017094018e-05, | |
| "loss": 0.0295, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 74.35, | |
| "learning_rate": 1.3931623931623932e-05, | |
| "loss": 0.0415, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 74.5, | |
| "learning_rate": 1.3846153846153847e-05, | |
| "loss": 0.0531, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 74.66, | |
| "learning_rate": 1.3760683760683763e-05, | |
| "loss": 0.0283, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 74.81, | |
| "learning_rate": 1.3675213675213677e-05, | |
| "loss": 0.0293, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 74.96, | |
| "learning_rate": 1.358974358974359e-05, | |
| "loss": 0.0174, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 74.99, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.10319594293832779, | |
| "eval_runtime": 10.5444, | |
| "eval_samples_per_second": 99.2, | |
| "eval_steps_per_second": 6.259, | |
| "step": 4912 | |
| }, | |
| { | |
| "epoch": 75.11, | |
| "learning_rate": 1.3504273504273504e-05, | |
| "loss": 0.0216, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 75.27, | |
| "learning_rate": 1.3418803418803419e-05, | |
| "loss": 0.0304, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 75.42, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0347, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 75.57, | |
| "learning_rate": 1.324786324786325e-05, | |
| "loss": 0.0208, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 75.73, | |
| "learning_rate": 1.3162393162393164e-05, | |
| "loss": 0.0192, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 75.88, | |
| "learning_rate": 1.3076923076923078e-05, | |
| "loss": 0.0368, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.10714620351791382, | |
| "eval_runtime": 10.1776, | |
| "eval_samples_per_second": 102.775, | |
| "eval_steps_per_second": 6.485, | |
| "step": 4978 | |
| }, | |
| { | |
| "epoch": 76.03, | |
| "learning_rate": 1.2991452991452993e-05, | |
| "loss": 0.0549, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 76.18, | |
| "learning_rate": 1.2905982905982907e-05, | |
| "loss": 0.0363, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 76.34, | |
| "learning_rate": 1.282051282051282e-05, | |
| "loss": 0.0377, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 76.49, | |
| "learning_rate": 1.2735042735042734e-05, | |
| "loss": 0.0272, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 76.64, | |
| "learning_rate": 1.264957264957265e-05, | |
| "loss": 0.0384, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 76.79, | |
| "learning_rate": 1.2564102564102565e-05, | |
| "loss": 0.0344, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 76.95, | |
| "learning_rate": 1.247863247863248e-05, | |
| "loss": 0.0367, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 76.99, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.09872549772262573, | |
| "eval_runtime": 10.524, | |
| "eval_samples_per_second": 99.392, | |
| "eval_steps_per_second": 6.271, | |
| "step": 5043 | |
| }, | |
| { | |
| "epoch": 77.1, | |
| "learning_rate": 1.2393162393162394e-05, | |
| "loss": 0.0206, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 77.25, | |
| "learning_rate": 1.230769230769231e-05, | |
| "loss": 0.0368, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 77.4, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0193, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 77.56, | |
| "learning_rate": 1.2136752136752137e-05, | |
| "loss": 0.0427, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 77.71, | |
| "learning_rate": 1.2051282051282051e-05, | |
| "loss": 0.0326, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 77.86, | |
| "learning_rate": 1.1965811965811967e-05, | |
| "loss": 0.027, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.10366753488779068, | |
| "eval_runtime": 10.054, | |
| "eval_samples_per_second": 104.038, | |
| "eval_steps_per_second": 6.565, | |
| "step": 5109 | |
| }, | |
| { | |
| "epoch": 78.02, | |
| "learning_rate": 1.188034188034188e-05, | |
| "loss": 0.0416, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 78.17, | |
| "learning_rate": 1.1794871794871795e-05, | |
| "loss": 0.0193, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 78.32, | |
| "learning_rate": 1.170940170940171e-05, | |
| "loss": 0.0362, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 78.47, | |
| "learning_rate": 1.1623931623931625e-05, | |
| "loss": 0.0348, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 78.63, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 0.0424, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 78.78, | |
| "learning_rate": 1.1452991452991452e-05, | |
| "loss": 0.0275, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 78.93, | |
| "learning_rate": 1.1367521367521368e-05, | |
| "loss": 0.0225, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 78.99, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.11285591125488281, | |
| "eval_runtime": 9.5703, | |
| "eval_samples_per_second": 109.296, | |
| "eval_steps_per_second": 6.896, | |
| "step": 5174 | |
| }, | |
| { | |
| "epoch": 79.08, | |
| "learning_rate": 1.1282051282051283e-05, | |
| "loss": 0.0243, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 79.24, | |
| "learning_rate": 1.1196581196581197e-05, | |
| "loss": 0.0362, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 79.39, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.027, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 79.54, | |
| "learning_rate": 1.1025641025641026e-05, | |
| "loss": 0.0462, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 79.69, | |
| "learning_rate": 1.094017094017094e-05, | |
| "loss": 0.0341, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 79.85, | |
| "learning_rate": 1.0854700854700855e-05, | |
| "loss": 0.0302, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.0769230769230771e-05, | |
| "loss": 0.0241, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.12019278109073639, | |
| "eval_runtime": 10.7086, | |
| "eval_samples_per_second": 97.679, | |
| "eval_steps_per_second": 6.163, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 80.15, | |
| "learning_rate": 1.0683760683760684e-05, | |
| "loss": 0.0322, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 80.31, | |
| "learning_rate": 1.0598290598290598e-05, | |
| "loss": 0.0205, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 80.46, | |
| "learning_rate": 1.0512820512820514e-05, | |
| "loss": 0.0606, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 80.61, | |
| "learning_rate": 1.0427350427350429e-05, | |
| "loss": 0.0468, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 80.76, | |
| "learning_rate": 1.0341880341880341e-05, | |
| "loss": 0.0439, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 80.92, | |
| "learning_rate": 1.0256410256410256e-05, | |
| "loss": 0.026, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 80.99, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.12190443277359009, | |
| "eval_runtime": 9.89, | |
| "eval_samples_per_second": 105.763, | |
| "eval_steps_per_second": 6.673, | |
| "step": 5305 | |
| }, | |
| { | |
| "epoch": 81.07, | |
| "learning_rate": 1.0170940170940172e-05, | |
| "loss": 0.0184, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 81.22, | |
| "learning_rate": 1.0085470085470086e-05, | |
| "loss": 0.0346, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 81.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0346, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 81.53, | |
| "learning_rate": 9.914529914529915e-06, | |
| "loss": 0.0237, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 81.68, | |
| "learning_rate": 9.82905982905983e-06, | |
| "loss": 0.031, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 81.83, | |
| "learning_rate": 9.743589743589744e-06, | |
| "loss": 0.0101, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 81.98, | |
| "learning_rate": 9.658119658119659e-06, | |
| "loss": 0.0223, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.11935597658157349, | |
| "eval_runtime": 9.9357, | |
| "eval_samples_per_second": 105.277, | |
| "eval_steps_per_second": 6.643, | |
| "step": 5371 | |
| }, | |
| { | |
| "epoch": 82.14, | |
| "learning_rate": 9.572649572649575e-06, | |
| "loss": 0.0398, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 82.29, | |
| "learning_rate": 9.487179487179487e-06, | |
| "loss": 0.0337, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 82.44, | |
| "learning_rate": 9.401709401709402e-06, | |
| "loss": 0.046, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 82.6, | |
| "learning_rate": 9.316239316239316e-06, | |
| "loss": 0.0425, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 82.75, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 0.0144, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 82.9, | |
| "learning_rate": 9.145299145299145e-06, | |
| "loss": 0.0454, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 82.99, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.11481741070747375, | |
| "eval_runtime": 10.9253, | |
| "eval_samples_per_second": 95.741, | |
| "eval_steps_per_second": 6.041, | |
| "step": 5436 | |
| }, | |
| { | |
| "epoch": 83.05, | |
| "learning_rate": 9.05982905982906e-06, | |
| "loss": 0.0217, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 83.21, | |
| "learning_rate": 8.974358974358976e-06, | |
| "loss": 0.024, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 83.36, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0312, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 83.51, | |
| "learning_rate": 8.803418803418804e-06, | |
| "loss": 0.0318, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 83.66, | |
| "learning_rate": 8.717948717948717e-06, | |
| "loss": 0.0374, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 83.82, | |
| "learning_rate": 8.632478632478633e-06, | |
| "loss": 0.0118, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 83.97, | |
| "learning_rate": 8.547008547008548e-06, | |
| "loss": 0.019, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.11676544696092606, | |
| "eval_runtime": 9.8983, | |
| "eval_samples_per_second": 105.674, | |
| "eval_steps_per_second": 6.668, | |
| "step": 5502 | |
| }, | |
| { | |
| "epoch": 84.12, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.032, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 84.27, | |
| "learning_rate": 8.376068376068377e-06, | |
| "loss": 0.0268, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 84.43, | |
| "learning_rate": 8.290598290598291e-06, | |
| "loss": 0.0589, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 84.58, | |
| "learning_rate": 8.205128205128205e-06, | |
| "loss": 0.0402, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 84.73, | |
| "learning_rate": 8.11965811965812e-06, | |
| "loss": 0.0301, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 84.89, | |
| "learning_rate": 8.034188034188036e-06, | |
| "loss": 0.0269, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 84.99, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.12455571442842484, | |
| "eval_runtime": 10.278, | |
| "eval_samples_per_second": 101.771, | |
| "eval_steps_per_second": 6.421, | |
| "step": 5567 | |
| }, | |
| { | |
| "epoch": 85.04, | |
| "learning_rate": 7.948717948717949e-06, | |
| "loss": 0.0279, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 85.19, | |
| "learning_rate": 7.863247863247863e-06, | |
| "loss": 0.02, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 85.34, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0235, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 85.5, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.027, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 85.65, | |
| "learning_rate": 7.606837606837606e-06, | |
| "loss": 0.0421, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 85.8, | |
| "learning_rate": 7.521367521367522e-06, | |
| "loss": 0.0178, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 85.95, | |
| "learning_rate": 7.435897435897436e-06, | |
| "loss": 0.0403, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.13009017705917358, | |
| "eval_runtime": 10.5359, | |
| "eval_samples_per_second": 99.279, | |
| "eval_steps_per_second": 6.264, | |
| "step": 5633 | |
| }, | |
| { | |
| "epoch": 86.11, | |
| "learning_rate": 7.350427350427351e-06, | |
| "loss": 0.0359, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 86.26, | |
| "learning_rate": 7.264957264957266e-06, | |
| "loss": 0.0326, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 86.41, | |
| "learning_rate": 7.179487179487179e-06, | |
| "loss": 0.0363, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 86.56, | |
| "learning_rate": 7.0940170940170945e-06, | |
| "loss": 0.0162, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 86.72, | |
| "learning_rate": 7.008547008547009e-06, | |
| "loss": 0.0422, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 86.87, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 0.0294, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 86.99, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.12042093276977539, | |
| "eval_runtime": 9.222, | |
| "eval_samples_per_second": 113.424, | |
| "eval_steps_per_second": 7.157, | |
| "step": 5698 | |
| }, | |
| { | |
| "epoch": 87.02, | |
| "learning_rate": 6.837606837606839e-06, | |
| "loss": 0.038, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 87.18, | |
| "learning_rate": 6.752136752136752e-06, | |
| "loss": 0.0103, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 87.33, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0627, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 87.48, | |
| "learning_rate": 6.581196581196582e-06, | |
| "loss": 0.0244, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 87.63, | |
| "learning_rate": 6.495726495726496e-06, | |
| "loss": 0.0235, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 87.79, | |
| "learning_rate": 6.41025641025641e-06, | |
| "loss": 0.0233, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 87.94, | |
| "learning_rate": 6.324786324786325e-06, | |
| "loss": 0.0501, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.9789674952198852, | |
| "eval_loss": 0.11684638261795044, | |
| "eval_runtime": 10.4843, | |
| "eval_samples_per_second": 99.768, | |
| "eval_steps_per_second": 6.295, | |
| "step": 5764 | |
| }, | |
| { | |
| "epoch": 88.09, | |
| "learning_rate": 6.23931623931624e-06, | |
| "loss": 0.0321, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 88.24, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.0223, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 88.4, | |
| "learning_rate": 6.0683760683760684e-06, | |
| "loss": 0.0497, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 88.55, | |
| "learning_rate": 5.982905982905984e-06, | |
| "loss": 0.0319, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 88.7, | |
| "learning_rate": 5.897435897435897e-06, | |
| "loss": 0.0444, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 88.85, | |
| "learning_rate": 5.8119658119658126e-06, | |
| "loss": 0.0361, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 88.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.11426308006048203, | |
| "eval_runtime": 10.4122, | |
| "eval_samples_per_second": 100.459, | |
| "eval_steps_per_second": 6.339, | |
| "step": 5829 | |
| }, | |
| { | |
| "epoch": 89.01, | |
| "learning_rate": 5.726495726495726e-06, | |
| "loss": 0.0254, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 89.16, | |
| "learning_rate": 5.641025641025641e-06, | |
| "loss": 0.0327, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 89.31, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0289, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 89.47, | |
| "learning_rate": 5.47008547008547e-06, | |
| "loss": 0.0174, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 89.62, | |
| "learning_rate": 5.3846153846153855e-06, | |
| "loss": 0.0278, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 89.77, | |
| "learning_rate": 5.299145299145299e-06, | |
| "loss": 0.031, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 89.92, | |
| "learning_rate": 5.213675213675214e-06, | |
| "loss": 0.0278, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.9799235181644359, | |
| "eval_loss": 0.10286556929349899, | |
| "eval_runtime": 9.3657, | |
| "eval_samples_per_second": 111.684, | |
| "eval_steps_per_second": 7.047, | |
| "step": 5895 | |
| }, | |
| { | |
| "epoch": 90.08, | |
| "learning_rate": 5.128205128205128e-06, | |
| "loss": 0.0184, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 90.23, | |
| "learning_rate": 5.042735042735043e-06, | |
| "loss": 0.0323, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 90.38, | |
| "learning_rate": 4.957264957264958e-06, | |
| "loss": 0.0127, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 90.53, | |
| "learning_rate": 4.871794871794872e-06, | |
| "loss": 0.0258, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 90.69, | |
| "learning_rate": 4.786324786324787e-06, | |
| "loss": 0.0364, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 90.84, | |
| "learning_rate": 4.700854700854701e-06, | |
| "loss": 0.0385, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 90.99, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.0267, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 90.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09912797808647156, | |
| "eval_runtime": 10.4, | |
| "eval_samples_per_second": 100.577, | |
| "eval_steps_per_second": 6.346, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 91.15, | |
| "learning_rate": 4.52991452991453e-06, | |
| "loss": 0.0313, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 91.3, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0327, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 91.45, | |
| "learning_rate": 4.3589743589743586e-06, | |
| "loss": 0.0239, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 91.6, | |
| "learning_rate": 4.273504273504274e-06, | |
| "loss": 0.0314, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 91.76, | |
| "learning_rate": 4.188034188034188e-06, | |
| "loss": 0.0274, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 91.91, | |
| "learning_rate": 4.102564102564103e-06, | |
| "loss": 0.0308, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.982791586998088, | |
| "eval_loss": 0.10278183221817017, | |
| "eval_runtime": 10.2154, | |
| "eval_samples_per_second": 102.395, | |
| "eval_steps_per_second": 6.461, | |
| "step": 6026 | |
| }, | |
| { | |
| "epoch": 92.06, | |
| "learning_rate": 4.017094017094018e-06, | |
| "loss": 0.04, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 92.21, | |
| "learning_rate": 3.9316239316239315e-06, | |
| "loss": 0.0103, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 92.37, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.0456, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 92.52, | |
| "learning_rate": 3.760683760683761e-06, | |
| "loss": 0.0231, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 92.67, | |
| "learning_rate": 3.6752136752136756e-06, | |
| "loss": 0.0334, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 92.82, | |
| "learning_rate": 3.5897435897435896e-06, | |
| "loss": 0.0389, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 92.98, | |
| "learning_rate": 3.5042735042735045e-06, | |
| "loss": 0.0246, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 92.99, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.10309727489948273, | |
| "eval_runtime": 9.5539, | |
| "eval_samples_per_second": 109.484, | |
| "eval_steps_per_second": 6.908, | |
| "step": 6091 | |
| }, | |
| { | |
| "epoch": 93.13, | |
| "learning_rate": 3.4188034188034193e-06, | |
| "loss": 0.0262, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 93.28, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0234, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 93.44, | |
| "learning_rate": 3.247863247863248e-06, | |
| "loss": 0.0211, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 93.59, | |
| "learning_rate": 3.1623931623931626e-06, | |
| "loss": 0.0293, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 93.74, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.0361, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "learning_rate": 2.991452991452992e-06, | |
| "loss": 0.0283, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.10351178050041199, | |
| "eval_runtime": 10.7511, | |
| "eval_samples_per_second": 97.292, | |
| "eval_steps_per_second": 6.139, | |
| "step": 6157 | |
| }, | |
| { | |
| "epoch": 94.05, | |
| "learning_rate": 2.9059829059829063e-06, | |
| "loss": 0.0281, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 94.2, | |
| "learning_rate": 2.8205128205128207e-06, | |
| "loss": 0.0175, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 94.35, | |
| "learning_rate": 2.735042735042735e-06, | |
| "loss": 0.019, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 94.5, | |
| "learning_rate": 2.6495726495726495e-06, | |
| "loss": 0.0248, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 94.66, | |
| "learning_rate": 2.564102564102564e-06, | |
| "loss": 0.0295, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 94.81, | |
| "learning_rate": 2.478632478632479e-06, | |
| "loss": 0.0243, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 94.96, | |
| "learning_rate": 2.3931623931623937e-06, | |
| "loss": 0.0278, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 94.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09991679340600967, | |
| "eval_runtime": 10.1438, | |
| "eval_samples_per_second": 103.117, | |
| "eval_steps_per_second": 6.506, | |
| "step": 6222 | |
| }, | |
| { | |
| "epoch": 95.11, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.0323, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 95.27, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0189, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 95.42, | |
| "learning_rate": 2.136752136752137e-06, | |
| "loss": 0.0194, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 95.57, | |
| "learning_rate": 2.0512820512820513e-06, | |
| "loss": 0.0318, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 95.73, | |
| "learning_rate": 1.9658119658119658e-06, | |
| "loss": 0.0363, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 95.88, | |
| "learning_rate": 1.8803418803418804e-06, | |
| "loss": 0.0221, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.9808795411089866, | |
| "eval_loss": 0.1006636694073677, | |
| "eval_runtime": 10.5083, | |
| "eval_samples_per_second": 99.54, | |
| "eval_steps_per_second": 6.281, | |
| "step": 6288 | |
| }, | |
| { | |
| "epoch": 96.03, | |
| "learning_rate": 1.7948717948717948e-06, | |
| "loss": 0.0297, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 96.18, | |
| "learning_rate": 1.7094017094017097e-06, | |
| "loss": 0.0359, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 96.34, | |
| "learning_rate": 1.623931623931624e-06, | |
| "loss": 0.0131, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 96.49, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.012, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 96.64, | |
| "learning_rate": 1.4529914529914531e-06, | |
| "loss": 0.0279, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 96.79, | |
| "learning_rate": 1.3675213675213676e-06, | |
| "loss": 0.0251, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 96.95, | |
| "learning_rate": 1.282051282051282e-06, | |
| "loss": 0.0197, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 96.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09894201159477234, | |
| "eval_runtime": 10.0809, | |
| "eval_samples_per_second": 103.761, | |
| "eval_steps_per_second": 6.547, | |
| "step": 6353 | |
| }, | |
| { | |
| "epoch": 97.1, | |
| "learning_rate": 1.1965811965811968e-06, | |
| "loss": 0.0481, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 97.25, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.038, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 97.4, | |
| "learning_rate": 1.0256410256410257e-06, | |
| "loss": 0.0476, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 97.56, | |
| "learning_rate": 9.401709401709402e-07, | |
| "loss": 0.023, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 97.71, | |
| "learning_rate": 8.547008547008548e-07, | |
| "loss": 0.0267, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 97.86, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.0435, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09859943389892578, | |
| "eval_runtime": 9.3732, | |
| "eval_samples_per_second": 111.595, | |
| "eval_steps_per_second": 7.041, | |
| "step": 6419 | |
| }, | |
| { | |
| "epoch": 98.02, | |
| "learning_rate": 6.837606837606838e-07, | |
| "loss": 0.0195, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 98.17, | |
| "learning_rate": 5.982905982905984e-07, | |
| "loss": 0.0445, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 98.32, | |
| "learning_rate": 5.128205128205128e-07, | |
| "loss": 0.0338, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 98.47, | |
| "learning_rate": 4.273504273504274e-07, | |
| "loss": 0.0303, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 98.63, | |
| "learning_rate": 3.418803418803419e-07, | |
| "loss": 0.0205, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 98.78, | |
| "learning_rate": 2.564102564102564e-07, | |
| "loss": 0.0288, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 98.93, | |
| "learning_rate": 1.7094017094017095e-07, | |
| "loss": 0.0266, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 98.99, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09866122901439667, | |
| "eval_runtime": 10.6097, | |
| "eval_samples_per_second": 98.589, | |
| "eval_steps_per_second": 6.221, | |
| "step": 6484 | |
| }, | |
| { | |
| "epoch": 99.08, | |
| "learning_rate": 8.547008547008547e-08, | |
| "loss": 0.0251, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 99.24, | |
| "learning_rate": 0.0, | |
| "loss": 0.0334, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 99.24, | |
| "eval_accuracy": 0.9818355640535373, | |
| "eval_loss": 0.09865351021289825, | |
| "eval_runtime": 10.5658, | |
| "eval_samples_per_second": 98.999, | |
| "eval_steps_per_second": 6.247, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 99.24, | |
| "step": 6500, | |
| "total_flos": 1.0320982228805714e+19, | |
| "train_loss": 0.06894740481560047, | |
| "train_runtime": 8315.1084, | |
| "train_samples_per_second": 50.318, | |
| "train_steps_per_second": 0.782 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6500, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 1.0320982228805714e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |