| { | |
| "best_metric": 0.9829629629629629, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1011", | |
| "epoch": 2.9955555555555557, | |
| "eval_steps": 500, | |
| "global_step": 1011, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02962962962962963, | |
| "grad_norm": 6.962750434875488, | |
| "learning_rate": 4.901960784313726e-06, | |
| "loss": 2.2752, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05925925925925926, | |
| "grad_norm": 7.147613048553467, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 2.1844, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 8.060157775878906, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 1.9996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 10.434203147888184, | |
| "learning_rate": 1.9607843137254903e-05, | |
| "loss": 1.692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 14.684704780578613, | |
| "learning_rate": 2.4509803921568626e-05, | |
| "loss": 1.2463, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 15.639288902282715, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.8793, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2074074074074074, | |
| "grad_norm": 14.043598175048828, | |
| "learning_rate": 3.431372549019608e-05, | |
| "loss": 0.6109, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 26.815710067749023, | |
| "learning_rate": 3.9215686274509805e-05, | |
| "loss": 0.5877, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 18.923198699951172, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.4282, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 21.275344848632812, | |
| "learning_rate": 4.901960784313725e-05, | |
| "loss": 0.4887, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32592592592592595, | |
| "grad_norm": 58.36842346191406, | |
| "learning_rate": 4.955995599559956e-05, | |
| "loss": 0.3896, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 18.006397247314453, | |
| "learning_rate": 4.9009900990099014e-05, | |
| "loss": 0.4162, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3851851851851852, | |
| "grad_norm": 13.68799114227295, | |
| "learning_rate": 4.845984598459846e-05, | |
| "loss": 0.3605, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4148148148148148, | |
| "grad_norm": 15.165467262268066, | |
| "learning_rate": 4.790979097909791e-05, | |
| "loss": 0.4391, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 10.881718635559082, | |
| "learning_rate": 4.7359735973597365e-05, | |
| "loss": 0.3706, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 15.909368515014648, | |
| "learning_rate": 4.680968096809682e-05, | |
| "loss": 0.3148, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5037037037037037, | |
| "grad_norm": 25.3117733001709, | |
| "learning_rate": 4.6259625962596256e-05, | |
| "loss": 0.3611, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 10.446706771850586, | |
| "learning_rate": 4.570957095709571e-05, | |
| "loss": 0.345, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.562962962962963, | |
| "grad_norm": 15.340864181518555, | |
| "learning_rate": 4.515951595159516e-05, | |
| "loss": 0.3645, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 21.318401336669922, | |
| "learning_rate": 4.4609460946094614e-05, | |
| "loss": 0.3063, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 13.705307006835938, | |
| "learning_rate": 4.405940594059406e-05, | |
| "loss": 0.2603, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6518518518518519, | |
| "grad_norm": 14.29479694366455, | |
| "learning_rate": 4.350935093509351e-05, | |
| "loss": 0.2617, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6814814814814815, | |
| "grad_norm": 15.511056900024414, | |
| "learning_rate": 4.2959295929592964e-05, | |
| "loss": 0.2583, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 42.817989349365234, | |
| "learning_rate": 4.240924092409242e-05, | |
| "loss": 0.3146, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 11.812172889709473, | |
| "learning_rate": 4.1859185918591856e-05, | |
| "loss": 0.2315, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7703703703703704, | |
| "grad_norm": 11.193636894226074, | |
| "learning_rate": 4.130913091309131e-05, | |
| "loss": 0.329, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 12.144834518432617, | |
| "learning_rate": 4.075907590759076e-05, | |
| "loss": 0.3005, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 10.566153526306152, | |
| "learning_rate": 4.020902090209021e-05, | |
| "loss": 0.2443, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8592592592592593, | |
| "grad_norm": 10.785486221313477, | |
| "learning_rate": 3.965896589658966e-05, | |
| "loss": 0.242, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 14.177382469177246, | |
| "learning_rate": 3.910891089108911e-05, | |
| "loss": 0.2615, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9185185185185185, | |
| "grad_norm": 16.649311065673828, | |
| "learning_rate": 3.8558855885588564e-05, | |
| "loss": 0.257, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 11.974807739257812, | |
| "learning_rate": 3.800880088008801e-05, | |
| "loss": 0.2559, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 9.136080741882324, | |
| "learning_rate": 3.745874587458746e-05, | |
| "loss": 0.2381, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9985185185185185, | |
| "eval_accuracy": 0.9575925925925926, | |
| "eval_loss": 0.1251903772354126, | |
| "eval_runtime": 33.135, | |
| "eval_samples_per_second": 162.97, | |
| "eval_steps_per_second": 10.201, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.0074074074074073, | |
| "grad_norm": 23.605918884277344, | |
| "learning_rate": 3.690869086908691e-05, | |
| "loss": 0.2405, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.037037037037037, | |
| "grad_norm": 9.887730598449707, | |
| "learning_rate": 3.635863586358636e-05, | |
| "loss": 0.2412, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 12.197110176086426, | |
| "learning_rate": 3.580858085808581e-05, | |
| "loss": 0.2298, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0962962962962963, | |
| "grad_norm": 12.699515342712402, | |
| "learning_rate": 3.525852585258526e-05, | |
| "loss": 0.2001, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.125925925925926, | |
| "grad_norm": 13.966781616210938, | |
| "learning_rate": 3.470847084708471e-05, | |
| "loss": 0.2106, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 20.575868606567383, | |
| "learning_rate": 3.415841584158416e-05, | |
| "loss": 0.2002, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 15.80282974243164, | |
| "learning_rate": 3.360836083608361e-05, | |
| "loss": 0.2532, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2148148148148148, | |
| "grad_norm": 18.04647445678711, | |
| "learning_rate": 3.305830583058306e-05, | |
| "loss": 0.2609, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 8.6199312210083, | |
| "learning_rate": 3.250825082508251e-05, | |
| "loss": 0.253, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2740740740740741, | |
| "grad_norm": 7.412827968597412, | |
| "learning_rate": 3.195819581958196e-05, | |
| "loss": 0.213, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 7.904267311096191, | |
| "learning_rate": 3.140814081408141e-05, | |
| "loss": 0.2584, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 18.86865234375, | |
| "learning_rate": 3.0858085808580864e-05, | |
| "loss": 0.227, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.362962962962963, | |
| "grad_norm": 5.769145965576172, | |
| "learning_rate": 3.0308030803080313e-05, | |
| "loss": 0.2016, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.3925925925925926, | |
| "grad_norm": 11.96108341217041, | |
| "learning_rate": 2.9757975797579756e-05, | |
| "loss": 0.1635, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 13.738970756530762, | |
| "learning_rate": 2.9207920792079208e-05, | |
| "loss": 0.1717, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.4518518518518517, | |
| "grad_norm": 11.988739967346191, | |
| "learning_rate": 2.8657865786578657e-05, | |
| "loss": 0.2126, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 11.078845977783203, | |
| "learning_rate": 2.810781078107811e-05, | |
| "loss": 0.2282, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 10.5954008102417, | |
| "learning_rate": 2.755775577557756e-05, | |
| "loss": 0.1351, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 15.503268241882324, | |
| "learning_rate": 2.700770077007701e-05, | |
| "loss": 0.2507, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5703703703703704, | |
| "grad_norm": 15.796453475952148, | |
| "learning_rate": 2.645764576457646e-05, | |
| "loss": 0.185, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 11.540029525756836, | |
| "learning_rate": 2.5907590759075913e-05, | |
| "loss": 0.1605, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6296296296296298, | |
| "grad_norm": 13.062150001525879, | |
| "learning_rate": 2.5357535753575355e-05, | |
| "loss": 0.2464, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 11.136322021484375, | |
| "learning_rate": 2.480748074807481e-05, | |
| "loss": 0.2067, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 8.773016929626465, | |
| "learning_rate": 2.4257425742574257e-05, | |
| "loss": 0.229, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7185185185185186, | |
| "grad_norm": 8.625940322875977, | |
| "learning_rate": 2.370737073707371e-05, | |
| "loss": 0.1535, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.748148148148148, | |
| "grad_norm": 6.024807929992676, | |
| "learning_rate": 2.3157315731573158e-05, | |
| "loss": 0.1205, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 9.04062557220459, | |
| "learning_rate": 2.2607260726072607e-05, | |
| "loss": 0.1724, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8074074074074074, | |
| "grad_norm": 20.10211753845215, | |
| "learning_rate": 2.2057205720572056e-05, | |
| "loss": 0.1504, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.837037037037037, | |
| "grad_norm": 9.104300498962402, | |
| "learning_rate": 2.150715071507151e-05, | |
| "loss": 0.157, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 8.573586463928223, | |
| "learning_rate": 2.0957095709570958e-05, | |
| "loss": 0.2248, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 7.876155853271484, | |
| "learning_rate": 2.0407040704070407e-05, | |
| "loss": 0.1622, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.925925925925926, | |
| "grad_norm": 6.861870288848877, | |
| "learning_rate": 1.9856985698569856e-05, | |
| "loss": 0.1846, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 8.942523956298828, | |
| "learning_rate": 1.930693069306931e-05, | |
| "loss": 0.1585, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9851851851851852, | |
| "grad_norm": 12.770540237426758, | |
| "learning_rate": 1.8756875687568758e-05, | |
| "loss": 0.1729, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9775925925925926, | |
| "eval_loss": 0.06562940031290054, | |
| "eval_runtime": 32.5381, | |
| "eval_samples_per_second": 165.959, | |
| "eval_steps_per_second": 10.388, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 8.93161678314209, | |
| "learning_rate": 1.8206820682068207e-05, | |
| "loss": 0.1736, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 8.148313522338867, | |
| "learning_rate": 1.765676567656766e-05, | |
| "loss": 0.1518, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.074074074074074, | |
| "grad_norm": 9.238503456115723, | |
| "learning_rate": 1.7106710671067108e-05, | |
| "loss": 0.181, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1037037037037036, | |
| "grad_norm": 7.2876081466674805, | |
| "learning_rate": 1.6556655665566557e-05, | |
| "loss": 0.1277, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 14.298846244812012, | |
| "learning_rate": 1.6006600660066006e-05, | |
| "loss": 0.1439, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.162962962962963, | |
| "grad_norm": 19.348224639892578, | |
| "learning_rate": 1.545654565456546e-05, | |
| "loss": 0.202, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.1925925925925926, | |
| "grad_norm": 8.49962043762207, | |
| "learning_rate": 1.4906490649064908e-05, | |
| "loss": 0.1552, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 6.094121932983398, | |
| "learning_rate": 1.4356435643564355e-05, | |
| "loss": 0.177, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 10.521448135375977, | |
| "learning_rate": 1.3806380638063806e-05, | |
| "loss": 0.1667, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.2814814814814817, | |
| "grad_norm": 15.489738464355469, | |
| "learning_rate": 1.3256325632563257e-05, | |
| "loss": 0.1298, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 11.301315307617188, | |
| "learning_rate": 1.2706270627062708e-05, | |
| "loss": 0.1701, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.3407407407407406, | |
| "grad_norm": 8.533815383911133, | |
| "learning_rate": 1.2156215621562157e-05, | |
| "loss": 0.1708, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 13.924063682556152, | |
| "learning_rate": 1.1606160616061606e-05, | |
| "loss": 0.1394, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 2.552699089050293, | |
| "learning_rate": 1.1056105610561057e-05, | |
| "loss": 0.1553, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.4296296296296296, | |
| "grad_norm": 11.489421844482422, | |
| "learning_rate": 1.0506050605060507e-05, | |
| "loss": 0.1479, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4592592592592593, | |
| "grad_norm": 11.2034330368042, | |
| "learning_rate": 9.955995599559956e-06, | |
| "loss": 0.1715, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 6.7186737060546875, | |
| "learning_rate": 9.405940594059407e-06, | |
| "loss": 0.1441, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.5185185185185186, | |
| "grad_norm": 7.652073383331299, | |
| "learning_rate": 8.855885588558856e-06, | |
| "loss": 0.1058, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.5481481481481483, | |
| "grad_norm": 10.549448013305664, | |
| "learning_rate": 8.305830583058307e-06, | |
| "loss": 0.1485, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 7.53530740737915, | |
| "learning_rate": 7.755775577557756e-06, | |
| "loss": 0.1403, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 12.338042259216309, | |
| "learning_rate": 7.205720572057206e-06, | |
| "loss": 0.1746, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.637037037037037, | |
| "grad_norm": 18.06306266784668, | |
| "learning_rate": 6.655665566556656e-06, | |
| "loss": 0.1506, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 8.664934158325195, | |
| "learning_rate": 6.105610561056106e-06, | |
| "loss": 0.1258, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.696296296296296, | |
| "grad_norm": 6.592322826385498, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.1438, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 4.439072608947754, | |
| "learning_rate": 5.005500550055006e-06, | |
| "loss": 0.1049, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 4.729221343994141, | |
| "learning_rate": 4.455445544554456e-06, | |
| "loss": 0.1445, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.785185185185185, | |
| "grad_norm": 6.323641300201416, | |
| "learning_rate": 3.905390539053906e-06, | |
| "loss": 0.1269, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.814814814814815, | |
| "grad_norm": 8.931975364685059, | |
| "learning_rate": 3.3553355335533555e-06, | |
| "loss": 0.1046, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 25.645519256591797, | |
| "learning_rate": 2.8052805280528055e-06, | |
| "loss": 0.166, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.8740740740740742, | |
| "grad_norm": 5.7749128341674805, | |
| "learning_rate": 2.2552255225522554e-06, | |
| "loss": 0.1325, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.9037037037037035, | |
| "grad_norm": 3.4846718311309814, | |
| "learning_rate": 1.7051705170517053e-06, | |
| "loss": 0.1116, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 9.06553840637207, | |
| "learning_rate": 1.155115511551155e-06, | |
| "loss": 0.1218, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 4.044698238372803, | |
| "learning_rate": 6.050605060506051e-07, | |
| "loss": 0.0964, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.9925925925925925, | |
| "grad_norm": 13.73366928100586, | |
| "learning_rate": 5.5005500550055006e-08, | |
| "loss": 0.1188, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9955555555555557, | |
| "eval_accuracy": 0.9829629629629629, | |
| "eval_loss": 0.05130303278565407, | |
| "eval_runtime": 32.1348, | |
| "eval_samples_per_second": 168.042, | |
| "eval_steps_per_second": 10.518, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 2.9955555555555557, | |
| "step": 1011, | |
| "total_flos": 1.608641425498964e+18, | |
| "train_loss": 0.3095316025258054, | |
| "train_runtime": 1092.5533, | |
| "train_samples_per_second": 59.311, | |
| "train_steps_per_second": 0.925 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1011, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.608641425498964e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |