| { | |
| "best_metric": 0.8803088803088803, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-310", | |
| "epoch": 49.31506849315068, | |
| "eval_steps": 500, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 2.1952, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5984555984555985, | |
| "eval_loss": 1.5913729667663574, | |
| "eval_runtime": 64.7917, | |
| "eval_samples_per_second": 3.997, | |
| "eval_steps_per_second": 0.139, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.7838, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.3705, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.6872586872586872, | |
| "eval_loss": 1.2163656949996948, | |
| "eval_runtime": 2.7019, | |
| "eval_samples_per_second": 95.857, | |
| "eval_steps_per_second": 3.331, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.2071, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.026, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.7374517374517374, | |
| "eval_loss": 0.9973997473716736, | |
| "eval_runtime": 2.773, | |
| "eval_samples_per_second": 93.401, | |
| "eval_steps_per_second": 3.246, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8747, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.829, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7722007722007722, | |
| "eval_loss": 0.7666593790054321, | |
| "eval_runtime": 2.7043, | |
| "eval_samples_per_second": 95.774, | |
| "eval_steps_per_second": 3.328, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6805, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6513, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8223938223938224, | |
| "eval_loss": 0.6674064993858337, | |
| "eval_runtime": 2.7216, | |
| "eval_samples_per_second": 95.164, | |
| "eval_steps_per_second": 3.307, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.5516, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_accuracy": 0.8378378378378378, | |
| "eval_loss": 0.58104407787323, | |
| "eval_runtime": 2.7003, | |
| "eval_samples_per_second": 95.916, | |
| "eval_steps_per_second": 3.333, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 4.876543209876544e-05, | |
| "loss": 0.5259, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.4978, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.8262548262548263, | |
| "eval_loss": 0.5498219132423401, | |
| "eval_runtime": 2.7634, | |
| "eval_samples_per_second": 93.724, | |
| "eval_steps_per_second": 3.257, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 4.7530864197530866e-05, | |
| "loss": 0.4849, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.4568, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8185328185328186, | |
| "eval_loss": 0.5999107360839844, | |
| "eval_runtime": 2.6558, | |
| "eval_samples_per_second": 97.523, | |
| "eval_steps_per_second": 3.389, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.4352, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.4047, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5210986137390137, | |
| "eval_runtime": 2.6564, | |
| "eval_samples_per_second": 97.5, | |
| "eval_steps_per_second": 3.388, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 4.506172839506173e-05, | |
| "loss": 0.4443, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.3696, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.5201298594474792, | |
| "eval_runtime": 2.969, | |
| "eval_samples_per_second": 87.234, | |
| "eval_steps_per_second": 3.031, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 4.3827160493827164e-05, | |
| "loss": 0.3712, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.3479, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_accuracy": 0.8262548262548263, | |
| "eval_loss": 0.5309751033782959, | |
| "eval_runtime": 2.8895, | |
| "eval_samples_per_second": 89.636, | |
| "eval_steps_per_second": 3.115, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.329, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5438859462738037, | |
| "eval_runtime": 2.8848, | |
| "eval_samples_per_second": 89.781, | |
| "eval_steps_per_second": 3.12, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.3452, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.135802469135803e-05, | |
| "loss": 0.3376, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.505037784576416, | |
| "eval_runtime": 2.6792, | |
| "eval_samples_per_second": 96.671, | |
| "eval_steps_per_second": 3.359, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.3155, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.2804, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "eval_accuracy": 0.8262548262548263, | |
| "eval_loss": 0.5709359645843506, | |
| "eval_runtime": 2.6578, | |
| "eval_samples_per_second": 97.449, | |
| "eval_steps_per_second": 3.386, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 0.292, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.2941, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_accuracy": 0.8146718146718147, | |
| "eval_loss": 0.6376463770866394, | |
| "eval_runtime": 3.1239, | |
| "eval_samples_per_second": 82.91, | |
| "eval_steps_per_second": 2.881, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.254, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 3.7654320987654326e-05, | |
| "loss": 0.3026, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5446977615356445, | |
| "eval_runtime": 2.6837, | |
| "eval_samples_per_second": 96.51, | |
| "eval_steps_per_second": 3.354, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2807, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 3.6419753086419754e-05, | |
| "loss": 0.2578, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8803088803088803, | |
| "eval_loss": 0.5055761933326721, | |
| "eval_runtime": 3.0337, | |
| "eval_samples_per_second": 85.374, | |
| "eval_steps_per_second": 2.967, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.219, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "eval_accuracy": 0.861003861003861, | |
| "eval_loss": 0.5619993209838867, | |
| "eval_runtime": 2.7058, | |
| "eval_samples_per_second": 95.72, | |
| "eval_steps_per_second": 3.326, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.2377, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.2403, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "eval_accuracy": 0.8455598455598455, | |
| "eval_loss": 0.5581746101379395, | |
| "eval_runtime": 2.7021, | |
| "eval_samples_per_second": 95.85, | |
| "eval_steps_per_second": 3.331, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.203, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2258, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5458388328552246, | |
| "eval_runtime": 3.0873, | |
| "eval_samples_per_second": 83.891, | |
| "eval_steps_per_second": 2.915, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 3.271604938271605e-05, | |
| "loss": 0.211, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.2265, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.541065514087677, | |
| "eval_runtime": 2.7072, | |
| "eval_samples_per_second": 95.67, | |
| "eval_steps_per_second": 3.324, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.1848, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.1893, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 21.97, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5476610064506531, | |
| "eval_runtime": 2.9316, | |
| "eval_samples_per_second": 88.348, | |
| "eval_steps_per_second": 3.07, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "learning_rate": 3.0246913580246916e-05, | |
| "loss": 0.1896, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5125249028205872, | |
| "eval_runtime": 2.7238, | |
| "eval_samples_per_second": 95.087, | |
| "eval_steps_per_second": 3.304, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2007, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 23.56, | |
| "learning_rate": 2.9012345679012347e-05, | |
| "loss": 0.1976, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.833976833976834, | |
| "eval_loss": 0.5671693086624146, | |
| "eval_runtime": 3.015, | |
| "eval_samples_per_second": 85.904, | |
| "eval_steps_per_second": 2.985, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 24.11, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.1781, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 24.66, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1725, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8455598455598455, | |
| "eval_loss": 0.5581468343734741, | |
| "eval_runtime": 3.0099, | |
| "eval_samples_per_second": 86.048, | |
| "eval_steps_per_second": 2.99, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.1542, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 2.654320987654321e-05, | |
| "loss": 0.168, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "eval_accuracy": 0.8455598455598455, | |
| "eval_loss": 0.5964789390563965, | |
| "eval_runtime": 2.7357, | |
| "eval_samples_per_second": 94.676, | |
| "eval_steps_per_second": 3.29, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 26.3, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.1806, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 2.5308641975308646e-05, | |
| "loss": 0.1821, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 26.96, | |
| "eval_accuracy": 0.861003861003861, | |
| "eval_loss": 0.5566571950912476, | |
| "eval_runtime": 3.0269, | |
| "eval_samples_per_second": 85.566, | |
| "eval_steps_per_second": 2.973, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.1622, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.1805, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.5998114943504333, | |
| "eval_runtime": 2.7276, | |
| "eval_samples_per_second": 94.954, | |
| "eval_steps_per_second": 3.3, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 28.49, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 0.1616, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.5450794696807861, | |
| "eval_runtime": 2.7182, | |
| "eval_samples_per_second": 95.285, | |
| "eval_steps_per_second": 3.311, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 29.04, | |
| "learning_rate": 2.2839506172839506e-05, | |
| "loss": 0.1757, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 29.59, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1467, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5574297308921814, | |
| "eval_runtime": 2.825, | |
| "eval_samples_per_second": 91.683, | |
| "eval_steps_per_second": 3.186, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.1363, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 30.68, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.1439, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 30.96, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.5706761479377747, | |
| "eval_runtime": 2.7105, | |
| "eval_samples_per_second": 95.556, | |
| "eval_steps_per_second": 3.32, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 31.23, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.1329, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 31.78, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.13, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8378378378378378, | |
| "eval_loss": 0.6018989086151123, | |
| "eval_runtime": 3.1531, | |
| "eval_samples_per_second": 82.14, | |
| "eval_steps_per_second": 2.854, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "learning_rate": 1.91358024691358e-05, | |
| "loss": 0.1193, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 32.88, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1353, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "eval_accuracy": 0.861003861003861, | |
| "eval_loss": 0.5952116847038269, | |
| "eval_runtime": 2.7134, | |
| "eval_samples_per_second": 95.452, | |
| "eval_steps_per_second": 3.317, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 33.42, | |
| "learning_rate": 1.7901234567901236e-05, | |
| "loss": 0.1312, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 33.97, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.1329, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 33.97, | |
| "eval_accuracy": 0.8378378378378378, | |
| "eval_loss": 0.6262175440788269, | |
| "eval_runtime": 2.6635, | |
| "eval_samples_per_second": 97.242, | |
| "eval_steps_per_second": 3.379, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 34.52, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1258, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 34.96, | |
| "eval_accuracy": 0.8455598455598455, | |
| "eval_loss": 0.6313734650611877, | |
| "eval_runtime": 3.0086, | |
| "eval_samples_per_second": 86.087, | |
| "eval_steps_per_second": 2.991, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 35.07, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.1403, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 35.62, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.1408, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5761238932609558, | |
| "eval_runtime": 2.696, | |
| "eval_samples_per_second": 96.069, | |
| "eval_steps_per_second": 3.338, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 36.16, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1398, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "learning_rate": 1.419753086419753e-05, | |
| "loss": 0.1197, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "eval_accuracy": 0.861003861003861, | |
| "eval_loss": 0.5702797174453735, | |
| "eval_runtime": 2.6925, | |
| "eval_samples_per_second": 96.193, | |
| "eval_steps_per_second": 3.343, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 37.26, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.1258, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 37.81, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.1208, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 37.97, | |
| "eval_accuracy": 0.8455598455598455, | |
| "eval_loss": 0.624657392501831, | |
| "eval_runtime": 2.9681, | |
| "eval_samples_per_second": 87.263, | |
| "eval_steps_per_second": 3.032, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 38.36, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.1356, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 38.9, | |
| "learning_rate": 1.1728395061728396e-05, | |
| "loss": 0.1197, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 38.96, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.6025857329368591, | |
| "eval_runtime": 2.7949, | |
| "eval_samples_per_second": 92.669, | |
| "eval_steps_per_second": 3.22, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 39.45, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1045, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.0493827160493827e-05, | |
| "loss": 0.1271, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.5952697396278381, | |
| "eval_runtime": 2.6623, | |
| "eval_samples_per_second": 97.285, | |
| "eval_steps_per_second": 3.381, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.1053, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.6070245504379272, | |
| "eval_runtime": 3.0263, | |
| "eval_samples_per_second": 85.583, | |
| "eval_steps_per_second": 2.974, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 41.1, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1095, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 41.64, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.0846, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 41.97, | |
| "eval_accuracy": 0.861003861003861, | |
| "eval_loss": 0.6094004511833191, | |
| "eval_runtime": 2.6949, | |
| "eval_samples_per_second": 96.107, | |
| "eval_steps_per_second": 3.34, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 42.19, | |
| "learning_rate": 8.02469135802469e-06, | |
| "loss": 0.1012, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 42.74, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1206, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 42.96, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5911765098571777, | |
| "eval_runtime": 2.7122, | |
| "eval_samples_per_second": 95.495, | |
| "eval_steps_per_second": 3.318, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 43.29, | |
| "learning_rate": 6.790123456790123e-06, | |
| "loss": 0.0978, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 43.84, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1225, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.607361376285553, | |
| "eval_runtime": 4.6667, | |
| "eval_samples_per_second": 55.5, | |
| "eval_steps_per_second": 1.929, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 44.38, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.1033, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 44.93, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.1184, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 44.99, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.5943210124969482, | |
| "eval_runtime": 2.7226, | |
| "eval_samples_per_second": 95.13, | |
| "eval_steps_per_second": 3.306, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 45.48, | |
| "learning_rate": 4.3209876543209875e-06, | |
| "loss": 0.1027, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 45.97, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.6083826422691345, | |
| "eval_runtime": 3.0894, | |
| "eval_samples_per_second": 83.836, | |
| "eval_steps_per_second": 2.913, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 46.03, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1305, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 46.58, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.1113, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 46.96, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.6033775210380554, | |
| "eval_runtime": 2.9035, | |
| "eval_samples_per_second": 89.202, | |
| "eval_steps_per_second": 3.1, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 47.12, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.1018, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 47.67, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0945, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8494208494208494, | |
| "eval_loss": 0.610550582408905, | |
| "eval_runtime": 2.6737, | |
| "eval_samples_per_second": 96.869, | |
| "eval_steps_per_second": 3.366, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 48.22, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.0992, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 48.77, | |
| "learning_rate": 6.17283950617284e-07, | |
| "loss": 0.1159, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 48.99, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.6142740845680237, | |
| "eval_runtime": 3.3099, | |
| "eval_samples_per_second": 78.25, | |
| "eval_steps_per_second": 2.719, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 49.32, | |
| "learning_rate": 0.0, | |
| "loss": 0.0963, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 49.32, | |
| "eval_accuracy": 0.8532818532818532, | |
| "eval_loss": 0.6143748760223389, | |
| "eval_runtime": 3.568, | |
| "eval_samples_per_second": 72.59, | |
| "eval_steps_per_second": 2.522, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 49.32, | |
| "step": 900, | |
| "total_flos": 2.8579589371326874e+18, | |
| "train_loss": 0.3051255483759774, | |
| "train_runtime": 3022.9937, | |
| "train_samples_per_second": 38.554, | |
| "train_steps_per_second": 0.298 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 2.8579589371326874e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |