| { | |
| "best_metric": 0.9448669201520913, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-blank_img/checkpoint-222", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 740, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3783783783783788e-06, | |
| "loss": 0.6924, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 0.6582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.0135135135135136e-05, | |
| "loss": 0.5654, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.4386, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.6891891891891892e-05, | |
| "loss": 0.3558, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0270270270270273e-05, | |
| "loss": 0.2918, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.364864864864865e-05, | |
| "loss": 0.3143, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.2339, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.0405405405405407e-05, | |
| "loss": 0.2426, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.3783783783783784e-05, | |
| "loss": 0.2386, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.7162162162162165e-05, | |
| "loss": 0.212, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 0.2642, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.391891891891892e-05, | |
| "loss": 0.2034, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.72972972972973e-05, | |
| "loss": 0.2646, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9391634980988594, | |
| "eval_loss": 0.19738444685935974, | |
| "eval_runtime": 6.6287, | |
| "eval_samples_per_second": 158.704, | |
| "eval_steps_per_second": 4.978, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.9924924924924924e-05, | |
| "loss": 0.2718, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.954954954954955e-05, | |
| "loss": 0.2249, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.9174174174174175e-05, | |
| "loss": 0.2091, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.87987987987988e-05, | |
| "loss": 0.2049, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.8423423423423426e-05, | |
| "loss": 0.2384, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.804804804804805e-05, | |
| "loss": 0.2021, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.767267267267268e-05, | |
| "loss": 0.1791, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.72972972972973e-05, | |
| "loss": 0.2404, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.692192192192192e-05, | |
| "loss": 0.2547, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.654654654654655e-05, | |
| "loss": 0.2253, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.617117117117117e-05, | |
| "loss": 0.2445, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.57957957957958e-05, | |
| "loss": 0.2609, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.5420420420420424e-05, | |
| "loss": 0.2177, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.5045045045045046e-05, | |
| "loss": 0.229, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.4669669669669675e-05, | |
| "loss": 0.2287, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.935361216730038, | |
| "eval_loss": 0.19786785542964935, | |
| "eval_runtime": 7.1255, | |
| "eval_samples_per_second": 147.638, | |
| "eval_steps_per_second": 4.631, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.42942942942943e-05, | |
| "loss": 0.2053, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.391891891891892e-05, | |
| "loss": 0.1898, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 4.354354354354355e-05, | |
| "loss": 0.1946, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.316816816816817e-05, | |
| "loss": 0.2265, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.27927927927928e-05, | |
| "loss": 0.2404, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.241741741741742e-05, | |
| "loss": 0.2073, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 4.204204204204204e-05, | |
| "loss": 0.2608, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.2168, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.1291291291291294e-05, | |
| "loss": 0.2091, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.091591591591592e-05, | |
| "loss": 0.2468, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 0.2181, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.016516516516517e-05, | |
| "loss": 0.1717, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.9789789789789796e-05, | |
| "loss": 0.205, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.941441441441442e-05, | |
| "loss": 0.1944, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.903903903903904e-05, | |
| "loss": 0.198, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9448669201520913, | |
| "eval_loss": 0.17274008691310883, | |
| "eval_runtime": 7.4744, | |
| "eval_samples_per_second": 140.747, | |
| "eval_steps_per_second": 4.415, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.866366366366366e-05, | |
| "loss": 0.2083, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.8288288288288285e-05, | |
| "loss": 0.1868, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.7912912912912914e-05, | |
| "loss": 0.23, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.7537537537537536e-05, | |
| "loss": 0.2083, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.7162162162162165e-05, | |
| "loss": 0.1851, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.678678678678679e-05, | |
| "loss": 0.2355, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.641141141141141e-05, | |
| "loss": 0.2357, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 3.603603603603604e-05, | |
| "loss": 0.1995, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 3.566066066066066e-05, | |
| "loss": 0.205, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 3.528528528528528e-05, | |
| "loss": 0.247, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 3.490990990990991e-05, | |
| "loss": 0.1991, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 3.453453453453453e-05, | |
| "loss": 0.1895, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 3.415915915915916e-05, | |
| "loss": 0.2351, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.3783783783783784e-05, | |
| "loss": 0.2073, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 3.3408408408408406e-05, | |
| "loss": 0.1889, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9429657794676806, | |
| "eval_loss": 0.174727663397789, | |
| "eval_runtime": 7.3243, | |
| "eval_samples_per_second": 143.632, | |
| "eval_steps_per_second": 4.506, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.3033033033033035e-05, | |
| "loss": 0.1688, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.265765765765766e-05, | |
| "loss": 0.1977, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 3.2282282282282286e-05, | |
| "loss": 0.198, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.190690690690691e-05, | |
| "loss": 0.2217, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 3.153153153153153e-05, | |
| "loss": 0.1959, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.115615615615616e-05, | |
| "loss": 0.2229, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.078078078078078e-05, | |
| "loss": 0.1919, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.0405405405405407e-05, | |
| "loss": 0.2318, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 3.0030030030030033e-05, | |
| "loss": 0.214, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.9654654654654658e-05, | |
| "loss": 0.1875, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.927927927927928e-05, | |
| "loss": 0.2289, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.8903903903903906e-05, | |
| "loss": 0.1887, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 2.852852852852853e-05, | |
| "loss": 0.1918, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.8153153153153157e-05, | |
| "loss": 0.1691, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.223, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9448669201520913, | |
| "eval_loss": 0.17105169594287872, | |
| "eval_runtime": 6.7978, | |
| "eval_samples_per_second": 154.755, | |
| "eval_steps_per_second": 4.854, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.7402402402402405e-05, | |
| "loss": 0.1872, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.2184, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 2.6651651651651656e-05, | |
| "loss": 0.2066, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.6276276276276278e-05, | |
| "loss": 0.181, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.5900900900900903e-05, | |
| "loss": 0.1743, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 2.552552552552553e-05, | |
| "loss": 0.188, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 2.5150150150150154e-05, | |
| "loss": 0.2181, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.4774774774774777e-05, | |
| "loss": 0.2173, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 2.43993993993994e-05, | |
| "loss": 0.2207, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2.4024024024024024e-05, | |
| "loss": 0.2025, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.364864864864865e-05, | |
| "loss": 0.1718, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 2.3273273273273275e-05, | |
| "loss": 0.189, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.28978978978979e-05, | |
| "loss": 0.1891, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 2.2522522522522523e-05, | |
| "loss": 0.1771, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.938212927756654, | |
| "eval_loss": 0.16966551542282104, | |
| "eval_runtime": 6.7174, | |
| "eval_samples_per_second": 156.609, | |
| "eval_steps_per_second": 4.913, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.214714714714715e-05, | |
| "loss": 0.212, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 2.1771771771771774e-05, | |
| "loss": 0.193, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 2.13963963963964e-05, | |
| "loss": 0.2115, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 2.102102102102102e-05, | |
| "loss": 0.2092, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 2.0645645645645647e-05, | |
| "loss": 0.1678, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 2.0270270270270273e-05, | |
| "loss": 0.1898, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.9894894894894898e-05, | |
| "loss": 0.1948, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 1.951951951951952e-05, | |
| "loss": 0.2115, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.9144144144144142e-05, | |
| "loss": 0.1735, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.8768768768768768e-05, | |
| "loss": 0.1791, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 1.8393393393393393e-05, | |
| "loss": 0.1728, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.801801801801802e-05, | |
| "loss": 0.1969, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.764264264264264e-05, | |
| "loss": 0.2058, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 1.7267267267267267e-05, | |
| "loss": 0.1762, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.6891891891891892e-05, | |
| "loss": 0.1864, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9391634980988594, | |
| "eval_loss": 0.16719643771648407, | |
| "eval_runtime": 7.3392, | |
| "eval_samples_per_second": 143.339, | |
| "eval_steps_per_second": 4.496, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.6516516516516518e-05, | |
| "loss": 0.2046, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.6141141141141143e-05, | |
| "loss": 0.1794, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.5765765765765765e-05, | |
| "loss": 0.1919, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 1.539039039039039e-05, | |
| "loss": 0.187, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.5015015015015016e-05, | |
| "loss": 0.1637, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.463963963963964e-05, | |
| "loss": 0.1572, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 1.4264264264264266e-05, | |
| "loss": 0.1708, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1963, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.1977, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 1.3138138138138139e-05, | |
| "loss": 0.1751, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 1.2762762762762764e-05, | |
| "loss": 0.1707, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.2387387387387388e-05, | |
| "loss": 0.1561, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.2012012012012012e-05, | |
| "loss": 0.1918, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 1.1636636636636638e-05, | |
| "loss": 0.2219, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.1261261261261261e-05, | |
| "loss": 0.1716, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9429657794676806, | |
| "eval_loss": 0.18012098968029022, | |
| "eval_runtime": 7.5217, | |
| "eval_samples_per_second": 139.861, | |
| "eval_steps_per_second": 4.387, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1.0885885885885887e-05, | |
| "loss": 0.1603, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 1.051051051051051e-05, | |
| "loss": 0.1871, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 1.0135135135135136e-05, | |
| "loss": 0.1972, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 9.75975975975976e-06, | |
| "loss": 0.223, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 9.384384384384384e-06, | |
| "loss": 0.1672, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 0.1529, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 8.633633633633633e-06, | |
| "loss": 0.1701, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 8.258258258258259e-06, | |
| "loss": 0.1925, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.882882882882883e-06, | |
| "loss": 0.1448, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 7.507507507507508e-06, | |
| "loss": 0.181, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 7.132132132132133e-06, | |
| "loss": 0.1984, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 0.203, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 6.381381381381382e-06, | |
| "loss": 0.1554, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 6.006006006006006e-06, | |
| "loss": 0.1743, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 5.630630630630631e-06, | |
| "loss": 0.192, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.94106463878327, | |
| "eval_loss": 0.17536889016628265, | |
| "eval_runtime": 6.7103, | |
| "eval_samples_per_second": 156.774, | |
| "eval_steps_per_second": 4.918, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.255255255255255e-06, | |
| "loss": 0.1613, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 4.87987987987988e-06, | |
| "loss": 0.1746, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 0.1584, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 4.129129129129129e-06, | |
| "loss": 0.1849, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.753753753753754e-06, | |
| "loss": 0.1871, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 3.3783783783783788e-06, | |
| "loss": 0.1302, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 3.003003003003003e-06, | |
| "loss": 0.1586, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 2.6276276276276277e-06, | |
| "loss": 0.2135, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 2.2522522522522524e-06, | |
| "loss": 0.1994, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.876876876876877e-06, | |
| "loss": 0.1693, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 1.5015015015015015e-06, | |
| "loss": 0.2072, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.1261261261261262e-06, | |
| "loss": 0.1806, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.507507507507508e-07, | |
| "loss": 0.1692, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 3.753753753753754e-07, | |
| "loss": 0.1998, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1886, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9420152091254753, | |
| "eval_loss": 0.17660604417324066, | |
| "eval_runtime": 6.7015, | |
| "eval_samples_per_second": 156.979, | |
| "eval_steps_per_second": 4.924, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 740, | |
| "total_flos": 2.3513765580619776e+18, | |
| "train_loss": 0.21299834186966354, | |
| "train_runtime": 1451.9061, | |
| "train_samples_per_second": 65.156, | |
| "train_steps_per_second": 0.51 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 740, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.3513765580619776e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |