{ "best_metric": 0.9881481481481481, "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-4554", "epoch": 2.999506172839506, "global_step": 4554, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 1.0964912280701754e-06, "loss": 2.3354, "step": 10 }, { "epoch": 0.01, "learning_rate": 2.1929824561403507e-06, "loss": 2.3016, "step": 20 }, { "epoch": 0.02, "learning_rate": 3.2894736842105265e-06, "loss": 2.2538, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.3859649122807014e-06, "loss": 2.2661, "step": 40 }, { "epoch": 0.03, "learning_rate": 5.482456140350877e-06, "loss": 2.154, "step": 50 }, { "epoch": 0.04, "learning_rate": 6.578947368421053e-06, "loss": 2.0706, "step": 60 }, { "epoch": 0.05, "learning_rate": 7.675438596491228e-06, "loss": 1.9964, "step": 70 }, { "epoch": 0.05, "learning_rate": 8.771929824561403e-06, "loss": 1.9312, "step": 80 }, { "epoch": 0.06, "learning_rate": 9.868421052631579e-06, "loss": 1.7427, "step": 90 }, { "epoch": 0.07, "learning_rate": 1.0964912280701754e-05, "loss": 1.6202, "step": 100 }, { "epoch": 0.07, "learning_rate": 1.206140350877193e-05, "loss": 1.3101, "step": 110 }, { "epoch": 0.08, "learning_rate": 1.3157894736842106e-05, "loss": 1.2006, "step": 120 }, { "epoch": 0.09, "learning_rate": 1.425438596491228e-05, "loss": 1.0041, "step": 130 }, { "epoch": 0.09, "learning_rate": 1.5350877192982457e-05, "loss": 0.9363, "step": 140 }, { "epoch": 0.1, "learning_rate": 1.6447368421052635e-05, "loss": 0.8446, "step": 150 }, { "epoch": 0.11, "learning_rate": 1.7543859649122806e-05, "loss": 0.706, "step": 160 }, { "epoch": 0.11, "learning_rate": 1.8640350877192984e-05, "loss": 0.6885, "step": 170 }, { "epoch": 0.12, "learning_rate": 1.9736842105263158e-05, "loss": 0.6005, "step": 180 }, { "epoch": 0.13, "learning_rate": 2.0833333333333336e-05, "loss": 0.5182, "step": 190 }, { "epoch": 0.13, "learning_rate": 2.1929824561403507e-05, "loss": 0.6304, "step": 200 }, { "epoch": 0.14, "learning_rate": 2.3026315789473685e-05, "loss": 0.6107, "step": 210 }, { "epoch": 0.14, "learning_rate": 2.412280701754386e-05, "loss": 0.6052, "step": 220 }, { "epoch": 0.15, "learning_rate": 2.5219298245614037e-05, "loss": 0.5927, "step": 230 }, { "epoch": 0.16, "learning_rate": 2.6315789473684212e-05, "loss": 0.583, "step": 240 }, { "epoch": 0.16, "learning_rate": 2.741228070175439e-05, "loss": 0.6158, "step": 250 }, { "epoch": 0.17, "learning_rate": 2.850877192982456e-05, "loss": 0.3667, "step": 260 }, { "epoch": 0.18, "learning_rate": 2.9605263157894735e-05, "loss": 0.592, "step": 270 }, { "epoch": 0.18, "learning_rate": 3.0701754385964913e-05, "loss": 0.4609, "step": 280 }, { "epoch": 0.19, "learning_rate": 3.179824561403509e-05, "loss": 0.4029, "step": 290 }, { "epoch": 0.2, "learning_rate": 3.289473684210527e-05, "loss": 0.4293, "step": 300 }, { "epoch": 0.2, "learning_rate": 3.3991228070175444e-05, "loss": 0.5068, "step": 310 }, { "epoch": 0.21, "learning_rate": 3.508771929824561e-05, "loss": 0.4074, "step": 320 }, { "epoch": 0.22, "learning_rate": 3.618421052631579e-05, "loss": 0.6593, "step": 330 }, { "epoch": 0.22, "learning_rate": 3.728070175438597e-05, "loss": 0.3653, "step": 340 }, { "epoch": 0.23, "learning_rate": 3.837719298245614e-05, "loss": 0.5295, "step": 350 }, { "epoch": 0.24, "learning_rate": 3.9473684210526316e-05, "loss": 0.5563, "step": 360 }, { "epoch": 0.24, "learning_rate": 4.057017543859649e-05, "loss": 0.4606, "step": 370 }, { "epoch": 0.25, "learning_rate": 4.166666666666667e-05, "loss": 0.3967, "step": 380 }, { "epoch": 0.26, "learning_rate": 4.2763157894736847e-05, "loss": 0.5117, "step": 390 }, { "epoch": 0.26, "learning_rate": 4.3859649122807014e-05, "loss": 0.3037, "step": 400 }, { "epoch": 0.27, "learning_rate": 4.4956140350877196e-05, "loss": 0.4378, "step": 410 }, { "epoch": 0.28, "learning_rate": 4.605263157894737e-05, "loss": 0.5083, "step": 420 }, { "epoch": 0.28, "learning_rate": 4.714912280701755e-05, "loss": 0.4625, "step": 430 }, { "epoch": 0.29, "learning_rate": 4.824561403508772e-05, "loss": 0.444, "step": 440 }, { "epoch": 0.3, "learning_rate": 4.9342105263157894e-05, "loss": 0.4297, "step": 450 }, { "epoch": 0.3, "learning_rate": 4.9951195705222064e-05, "loss": 0.3812, "step": 460 }, { "epoch": 0.31, "learning_rate": 4.9829184968277206e-05, "loss": 0.4137, "step": 470 }, { "epoch": 0.32, "learning_rate": 4.970717423133236e-05, "loss": 0.358, "step": 480 }, { "epoch": 0.32, "learning_rate": 4.958516349438751e-05, "loss": 0.3854, "step": 490 }, { "epoch": 0.33, "learning_rate": 4.946315275744266e-05, "loss": 0.3569, "step": 500 }, { "epoch": 0.34, "learning_rate": 4.934114202049781e-05, "loss": 0.5532, "step": 510 }, { "epoch": 0.34, "learning_rate": 4.9219131283552955e-05, "loss": 0.2395, "step": 520 }, { "epoch": 0.35, "learning_rate": 4.9097120546608104e-05, "loss": 0.3434, "step": 530 }, { "epoch": 0.36, "learning_rate": 4.897510980966325e-05, "loss": 0.5604, "step": 540 }, { "epoch": 0.36, "learning_rate": 4.88530990727184e-05, "loss": 0.4767, "step": 550 }, { "epoch": 0.37, "learning_rate": 4.873108833577355e-05, "loss": 0.5108, "step": 560 }, { "epoch": 0.38, "learning_rate": 4.86090775988287e-05, "loss": 0.4881, "step": 570 }, { "epoch": 0.38, "learning_rate": 4.848706686188385e-05, "loss": 0.3519, "step": 580 }, { "epoch": 0.39, "learning_rate": 4.8365056124938995e-05, "loss": 0.4509, "step": 590 }, { "epoch": 0.4, "learning_rate": 4.824304538799414e-05, "loss": 0.2967, "step": 600 }, { "epoch": 0.4, "learning_rate": 4.81210346510493e-05, "loss": 0.5555, "step": 610 }, { "epoch": 0.41, "learning_rate": 4.799902391410445e-05, "loss": 0.319, "step": 620 }, { "epoch": 0.41, "learning_rate": 4.787701317715959e-05, "loss": 0.37, "step": 630 }, { "epoch": 0.42, "learning_rate": 4.7755002440214744e-05, "loss": 0.4335, "step": 640 }, { "epoch": 0.43, "learning_rate": 4.763299170326989e-05, "loss": 0.2259, "step": 650 }, { "epoch": 0.43, "learning_rate": 4.751098096632504e-05, "loss": 0.2966, "step": 660 }, { "epoch": 0.44, "learning_rate": 4.738897022938019e-05, "loss": 0.4836, "step": 670 }, { "epoch": 0.45, "learning_rate": 4.726695949243534e-05, "loss": 0.505, "step": 680 }, { "epoch": 0.45, "learning_rate": 4.7144948755490486e-05, "loss": 0.3296, "step": 690 }, { "epoch": 0.46, "learning_rate": 4.7022938018545635e-05, "loss": 0.3114, "step": 700 }, { "epoch": 0.47, "learning_rate": 4.690092728160078e-05, "loss": 0.4039, "step": 710 }, { "epoch": 0.47, "learning_rate": 4.677891654465593e-05, "loss": 0.3181, "step": 720 }, { "epoch": 0.48, "learning_rate": 4.665690580771108e-05, "loss": 0.3256, "step": 730 }, { "epoch": 0.49, "learning_rate": 4.6534895070766235e-05, "loss": 0.4063, "step": 740 }, { "epoch": 0.49, "learning_rate": 4.641288433382138e-05, "loss": 0.2393, "step": 750 }, { "epoch": 0.5, "learning_rate": 4.6290873596876525e-05, "loss": 0.3919, "step": 760 }, { "epoch": 0.51, "learning_rate": 4.616886285993168e-05, "loss": 0.3218, "step": 770 }, { "epoch": 0.51, "learning_rate": 4.604685212298683e-05, "loss": 0.3082, "step": 780 }, { "epoch": 0.52, "learning_rate": 4.592484138604197e-05, "loss": 0.3404, "step": 790 }, { "epoch": 0.53, "learning_rate": 4.580283064909712e-05, "loss": 0.2105, "step": 800 }, { "epoch": 0.53, "learning_rate": 4.5680819912152275e-05, "loss": 0.1712, "step": 810 }, { "epoch": 0.54, "learning_rate": 4.555880917520742e-05, "loss": 0.3661, "step": 820 }, { "epoch": 0.55, "learning_rate": 4.5436798438262565e-05, "loss": 0.4927, "step": 830 }, { "epoch": 0.55, "learning_rate": 4.531478770131772e-05, "loss": 0.3264, "step": 840 }, { "epoch": 0.56, "learning_rate": 4.519277696437287e-05, "loss": 0.1937, "step": 850 }, { "epoch": 0.57, "learning_rate": 4.507076622742802e-05, "loss": 0.3127, "step": 860 }, { "epoch": 0.57, "learning_rate": 4.4948755490483165e-05, "loss": 0.3682, "step": 870 }, { "epoch": 0.58, "learning_rate": 4.4826744753538314e-05, "loss": 0.4293, "step": 880 }, { "epoch": 0.59, "learning_rate": 4.470473401659346e-05, "loss": 0.3893, "step": 890 }, { "epoch": 0.59, "learning_rate": 4.458272327964861e-05, "loss": 0.3438, "step": 900 }, { "epoch": 0.6, "learning_rate": 4.446071254270376e-05, "loss": 0.3812, "step": 910 }, { "epoch": 0.61, "learning_rate": 4.433870180575891e-05, "loss": 0.163, "step": 920 }, { "epoch": 0.61, "learning_rate": 4.4216691068814056e-05, "loss": 0.3507, "step": 930 }, { "epoch": 0.62, "learning_rate": 4.409468033186921e-05, "loss": 0.205, "step": 940 }, { "epoch": 0.63, "learning_rate": 4.397266959492435e-05, "loss": 0.4546, "step": 950 }, { "epoch": 0.63, "learning_rate": 4.38506588579795e-05, "loss": 0.2742, "step": 960 }, { "epoch": 0.64, "learning_rate": 4.372864812103466e-05, "loss": 0.41, "step": 970 }, { "epoch": 0.65, "learning_rate": 4.3606637384089805e-05, "loss": 0.1573, "step": 980 }, { "epoch": 0.65, "learning_rate": 4.348462664714495e-05, "loss": 0.2863, "step": 990 }, { "epoch": 0.66, "learning_rate": 4.33626159102001e-05, "loss": 0.3761, "step": 1000 }, { "epoch": 0.67, "learning_rate": 4.324060517325525e-05, "loss": 0.1772, "step": 1010 }, { "epoch": 0.67, "learning_rate": 4.31185944363104e-05, "loss": 0.1806, "step": 1020 }, { "epoch": 0.68, "learning_rate": 4.299658369936555e-05, "loss": 0.1849, "step": 1030 }, { "epoch": 0.68, "learning_rate": 4.2874572962420696e-05, "loss": 0.4006, "step": 1040 }, { "epoch": 0.69, "learning_rate": 4.2752562225475845e-05, "loss": 0.3365, "step": 1050 }, { "epoch": 0.7, "learning_rate": 4.263055148853099e-05, "loss": 0.2371, "step": 1060 }, { "epoch": 0.7, "learning_rate": 4.250854075158614e-05, "loss": 0.2707, "step": 1070 }, { "epoch": 0.71, "learning_rate": 4.238653001464129e-05, "loss": 0.2841, "step": 1080 }, { "epoch": 0.72, "learning_rate": 4.226451927769644e-05, "loss": 0.2384, "step": 1090 }, { "epoch": 0.72, "learning_rate": 4.2142508540751594e-05, "loss": 0.283, "step": 1100 }, { "epoch": 0.73, "learning_rate": 4.2020497803806735e-05, "loss": 0.2722, "step": 1110 }, { "epoch": 0.74, "learning_rate": 4.1898487066861884e-05, "loss": 0.3541, "step": 1120 }, { "epoch": 0.74, "learning_rate": 4.177647632991704e-05, "loss": 0.3857, "step": 1130 }, { "epoch": 0.75, "learning_rate": 4.165446559297219e-05, "loss": 0.3877, "step": 1140 }, { "epoch": 0.76, "learning_rate": 4.153245485602733e-05, "loss": 0.2678, "step": 1150 }, { "epoch": 0.76, "learning_rate": 4.141044411908248e-05, "loss": 0.4025, "step": 1160 }, { "epoch": 0.77, "learning_rate": 4.128843338213763e-05, "loss": 0.2822, "step": 1170 }, { "epoch": 0.78, "learning_rate": 4.116642264519278e-05, "loss": 0.1737, "step": 1180 }, { "epoch": 0.78, "learning_rate": 4.104441190824792e-05, "loss": 0.3764, "step": 1190 }, { "epoch": 0.79, "learning_rate": 4.092240117130308e-05, "loss": 0.2449, "step": 1200 }, { "epoch": 0.8, "learning_rate": 4.080039043435823e-05, "loss": 0.2968, "step": 1210 }, { "epoch": 0.8, "learning_rate": 4.0678379697413375e-05, "loss": 0.3152, "step": 1220 }, { "epoch": 0.81, "learning_rate": 4.0556368960468524e-05, "loss": 0.2674, "step": 1230 }, { "epoch": 0.82, "learning_rate": 4.043435822352367e-05, "loss": 0.2267, "step": 1240 }, { "epoch": 0.82, "learning_rate": 4.031234748657882e-05, "loss": 0.3197, "step": 1250 }, { "epoch": 0.83, "learning_rate": 4.019033674963397e-05, "loss": 0.1525, "step": 1260 }, { "epoch": 0.84, "learning_rate": 4.006832601268912e-05, "loss": 0.3441, "step": 1270 }, { "epoch": 0.84, "learning_rate": 3.9946315275744266e-05, "loss": 0.2637, "step": 1280 }, { "epoch": 0.85, "learning_rate": 3.9824304538799415e-05, "loss": 0.3026, "step": 1290 }, { "epoch": 0.86, "learning_rate": 3.970229380185457e-05, "loss": 0.24, "step": 1300 }, { "epoch": 0.86, "learning_rate": 3.958028306490971e-05, "loss": 0.324, "step": 1310 }, { "epoch": 0.87, "learning_rate": 3.945827232796486e-05, "loss": 0.3333, "step": 1320 }, { "epoch": 0.88, "learning_rate": 3.9336261591020015e-05, "loss": 0.2276, "step": 1330 }, { "epoch": 0.88, "learning_rate": 3.9214250854075164e-05, "loss": 0.3149, "step": 1340 }, { "epoch": 0.89, "learning_rate": 3.9092240117130305e-05, "loss": 0.2824, "step": 1350 }, { "epoch": 0.9, "learning_rate": 3.897022938018546e-05, "loss": 0.2141, "step": 1360 }, { "epoch": 0.9, "learning_rate": 3.884821864324061e-05, "loss": 0.309, "step": 1370 }, { "epoch": 0.91, "learning_rate": 3.872620790629576e-05, "loss": 0.3318, "step": 1380 }, { "epoch": 0.92, "learning_rate": 3.8604197169350906e-05, "loss": 0.3266, "step": 1390 }, { "epoch": 0.92, "learning_rate": 3.8482186432406055e-05, "loss": 0.2694, "step": 1400 }, { "epoch": 0.93, "learning_rate": 3.83601756954612e-05, "loss": 0.4114, "step": 1410 }, { "epoch": 0.93, "learning_rate": 3.823816495851635e-05, "loss": 0.3237, "step": 1420 }, { "epoch": 0.94, "learning_rate": 3.81161542215715e-05, "loss": 0.178, "step": 1430 }, { "epoch": 0.95, "learning_rate": 3.799414348462665e-05, "loss": 0.2378, "step": 1440 }, { "epoch": 0.95, "learning_rate": 3.78721327476818e-05, "loss": 0.2098, "step": 1450 }, { "epoch": 0.96, "learning_rate": 3.775012201073695e-05, "loss": 0.3246, "step": 1460 }, { "epoch": 0.97, "learning_rate": 3.7628111273792094e-05, "loss": 0.2404, "step": 1470 }, { "epoch": 0.97, "learning_rate": 3.750610053684724e-05, "loss": 0.1812, "step": 1480 }, { "epoch": 0.98, "learning_rate": 3.73840897999024e-05, "loss": 0.2259, "step": 1490 }, { "epoch": 0.99, "learning_rate": 3.7262079062957546e-05, "loss": 0.1704, "step": 1500 }, { "epoch": 0.99, "learning_rate": 3.714006832601269e-05, "loss": 0.2241, "step": 1510 }, { "epoch": 1.0, "eval_accuracy": 0.9718518518518519, "eval_loss": 0.08855165541172028, "eval_runtime": 19.125, "eval_samples_per_second": 141.176, "eval_steps_per_second": 35.294, "step": 1518 }, { "epoch": 1.0, "learning_rate": 3.7018057589067836e-05, "loss": 0.2928, "step": 1520 }, { "epoch": 1.01, "learning_rate": 3.689604685212299e-05, "loss": 0.1758, "step": 1530 }, { "epoch": 1.01, "learning_rate": 3.677403611517814e-05, "loss": 0.208, "step": 1540 }, { "epoch": 1.02, "learning_rate": 3.665202537823328e-05, "loss": 0.3002, "step": 1550 }, { "epoch": 1.03, "learning_rate": 3.653001464128844e-05, "loss": 0.2929, "step": 1560 }, { "epoch": 1.03, "learning_rate": 3.6408003904343585e-05, "loss": 0.2811, "step": 1570 }, { "epoch": 1.04, "learning_rate": 3.6285993167398734e-05, "loss": 0.306, "step": 1580 }, { "epoch": 1.05, "learning_rate": 3.616398243045388e-05, "loss": 0.1664, "step": 1590 }, { "epoch": 1.05, "learning_rate": 3.604197169350903e-05, "loss": 0.3777, "step": 1600 }, { "epoch": 1.06, "learning_rate": 3.591996095656418e-05, "loss": 0.1813, "step": 1610 }, { "epoch": 1.07, "learning_rate": 3.579795021961933e-05, "loss": 0.3321, "step": 1620 }, { "epoch": 1.07, "learning_rate": 3.5675939482674476e-05, "loss": 0.174, "step": 1630 }, { "epoch": 1.08, "learning_rate": 3.5553928745729625e-05, "loss": 0.413, "step": 1640 }, { "epoch": 1.09, "learning_rate": 3.543191800878477e-05, "loss": 0.2501, "step": 1650 }, { "epoch": 1.09, "learning_rate": 3.530990727183993e-05, "loss": 0.2178, "step": 1660 }, { "epoch": 1.1, "learning_rate": 3.518789653489507e-05, "loss": 0.315, "step": 1670 }, { "epoch": 1.11, "learning_rate": 3.506588579795022e-05, "loss": 0.1949, "step": 1680 }, { "epoch": 1.11, "learning_rate": 3.4943875061005374e-05, "loss": 0.155, "step": 1690 }, { "epoch": 1.12, "learning_rate": 3.482186432406052e-05, "loss": 0.3164, "step": 1700 }, { "epoch": 1.13, "learning_rate": 3.4699853587115664e-05, "loss": 0.226, "step": 1710 }, { "epoch": 1.13, "learning_rate": 3.457784285017082e-05, "loss": 0.1877, "step": 1720 }, { "epoch": 1.14, "learning_rate": 3.445583211322597e-05, "loss": 0.2876, "step": 1730 }, { "epoch": 1.15, "learning_rate": 3.4333821376281116e-05, "loss": 0.3382, "step": 1740 }, { "epoch": 1.15, "learning_rate": 3.4211810639336265e-05, "loss": 0.2365, "step": 1750 }, { "epoch": 1.16, "learning_rate": 3.408979990239141e-05, "loss": 0.1905, "step": 1760 }, { "epoch": 1.17, "learning_rate": 3.396778916544656e-05, "loss": 0.1819, "step": 1770 }, { "epoch": 1.17, "learning_rate": 3.384577842850171e-05, "loss": 0.1083, "step": 1780 }, { "epoch": 1.18, "learning_rate": 3.372376769155686e-05, "loss": 0.2163, "step": 1790 }, { "epoch": 1.19, "learning_rate": 3.360175695461201e-05, "loss": 0.2147, "step": 1800 }, { "epoch": 1.19, "learning_rate": 3.3479746217667155e-05, "loss": 0.2272, "step": 1810 }, { "epoch": 1.2, "learning_rate": 3.335773548072231e-05, "loss": 0.4225, "step": 1820 }, { "epoch": 1.21, "learning_rate": 3.323572474377745e-05, "loss": 0.1956, "step": 1830 }, { "epoch": 1.21, "learning_rate": 3.31137140068326e-05, "loss": 0.2118, "step": 1840 }, { "epoch": 1.22, "learning_rate": 3.299170326988775e-05, "loss": 0.2271, "step": 1850 }, { "epoch": 1.23, "learning_rate": 3.2869692532942905e-05, "loss": 0.2547, "step": 1860 }, { "epoch": 1.23, "learning_rate": 3.2747681795998046e-05, "loss": 0.3846, "step": 1870 }, { "epoch": 1.24, "learning_rate": 3.2625671059053195e-05, "loss": 0.2101, "step": 1880 }, { "epoch": 1.24, "learning_rate": 3.250366032210835e-05, "loss": 0.1602, "step": 1890 }, { "epoch": 1.25, "learning_rate": 3.23816495851635e-05, "loss": 0.1085, "step": 1900 }, { "epoch": 1.26, "learning_rate": 3.225963884821864e-05, "loss": 0.1934, "step": 1910 }, { "epoch": 1.26, "learning_rate": 3.2137628111273795e-05, "loss": 0.1075, "step": 1920 }, { "epoch": 1.27, "learning_rate": 3.2015617374328944e-05, "loss": 0.4623, "step": 1930 }, { "epoch": 1.28, "learning_rate": 3.189360663738409e-05, "loss": 0.2331, "step": 1940 }, { "epoch": 1.28, "learning_rate": 3.177159590043924e-05, "loss": 0.2424, "step": 1950 }, { "epoch": 1.29, "learning_rate": 3.164958516349439e-05, "loss": 0.314, "step": 1960 }, { "epoch": 1.3, "learning_rate": 3.152757442654954e-05, "loss": 0.1985, "step": 1970 }, { "epoch": 1.3, "learning_rate": 3.1405563689604686e-05, "loss": 0.1887, "step": 1980 }, { "epoch": 1.31, "learning_rate": 3.1283552952659835e-05, "loss": 0.1782, "step": 1990 }, { "epoch": 1.32, "learning_rate": 3.116154221571498e-05, "loss": 0.238, "step": 2000 }, { "epoch": 1.32, "learning_rate": 3.103953147877013e-05, "loss": 0.16, "step": 2010 }, { "epoch": 1.33, "learning_rate": 3.091752074182529e-05, "loss": 0.3491, "step": 2020 }, { "epoch": 1.34, "learning_rate": 3.079551000488043e-05, "loss": 0.3438, "step": 2030 }, { "epoch": 1.34, "learning_rate": 3.067349926793558e-05, "loss": 0.2704, "step": 2040 }, { "epoch": 1.35, "learning_rate": 3.055148853099073e-05, "loss": 0.1693, "step": 2050 }, { "epoch": 1.36, "learning_rate": 3.042947779404588e-05, "loss": 0.2388, "step": 2060 }, { "epoch": 1.36, "learning_rate": 3.0307467057101026e-05, "loss": 0.1829, "step": 2070 }, { "epoch": 1.37, "learning_rate": 3.0185456320156174e-05, "loss": 0.2022, "step": 2080 }, { "epoch": 1.38, "learning_rate": 3.0063445583211326e-05, "loss": 0.1623, "step": 2090 }, { "epoch": 1.38, "learning_rate": 2.9941434846266475e-05, "loss": 0.2162, "step": 2100 }, { "epoch": 1.39, "learning_rate": 2.981942410932162e-05, "loss": 0.2487, "step": 2110 }, { "epoch": 1.4, "learning_rate": 2.969741337237677e-05, "loss": 0.3367, "step": 2120 }, { "epoch": 1.4, "learning_rate": 2.957540263543192e-05, "loss": 0.3359, "step": 2130 }, { "epoch": 1.41, "learning_rate": 2.9453391898487072e-05, "loss": 0.1669, "step": 2140 }, { "epoch": 1.42, "learning_rate": 2.9331381161542214e-05, "loss": 0.1659, "step": 2150 }, { "epoch": 1.42, "learning_rate": 2.9209370424597365e-05, "loss": 0.2319, "step": 2160 }, { "epoch": 1.43, "learning_rate": 2.9087359687652517e-05, "loss": 0.189, "step": 2170 }, { "epoch": 1.44, "learning_rate": 2.8965348950707666e-05, "loss": 0.1465, "step": 2180 }, { "epoch": 1.44, "learning_rate": 2.884333821376281e-05, "loss": 0.2268, "step": 2190 }, { "epoch": 1.45, "learning_rate": 2.872132747681796e-05, "loss": 0.157, "step": 2200 }, { "epoch": 1.46, "learning_rate": 2.859931673987311e-05, "loss": 0.1943, "step": 2210 }, { "epoch": 1.46, "learning_rate": 2.847730600292826e-05, "loss": 0.2083, "step": 2220 }, { "epoch": 1.47, "learning_rate": 2.8355295265983405e-05, "loss": 0.193, "step": 2230 }, { "epoch": 1.48, "learning_rate": 2.8233284529038557e-05, "loss": 0.0976, "step": 2240 }, { "epoch": 1.48, "learning_rate": 2.8111273792093705e-05, "loss": 0.2128, "step": 2250 }, { "epoch": 1.49, "learning_rate": 2.7989263055148857e-05, "loss": 0.2238, "step": 2260 }, { "epoch": 1.5, "learning_rate": 2.7867252318204002e-05, "loss": 0.2234, "step": 2270 }, { "epoch": 1.5, "learning_rate": 2.774524158125915e-05, "loss": 0.238, "step": 2280 }, { "epoch": 1.51, "learning_rate": 2.7623230844314302e-05, "loss": 0.1314, "step": 2290 }, { "epoch": 1.51, "learning_rate": 2.750122010736945e-05, "loss": 0.1609, "step": 2300 }, { "epoch": 1.52, "learning_rate": 2.7379209370424596e-05, "loss": 0.2341, "step": 2310 }, { "epoch": 1.53, "learning_rate": 2.7257198633479748e-05, "loss": 0.2158, "step": 2320 }, { "epoch": 1.53, "learning_rate": 2.7135187896534896e-05, "loss": 0.1087, "step": 2330 }, { "epoch": 1.54, "learning_rate": 2.7013177159590048e-05, "loss": 0.1339, "step": 2340 }, { "epoch": 1.55, "learning_rate": 2.6891166422645193e-05, "loss": 0.2046, "step": 2350 }, { "epoch": 1.55, "learning_rate": 2.676915568570034e-05, "loss": 0.1847, "step": 2360 }, { "epoch": 1.56, "learning_rate": 2.6647144948755493e-05, "loss": 0.3734, "step": 2370 }, { "epoch": 1.57, "learning_rate": 2.6525134211810642e-05, "loss": 0.1368, "step": 2380 }, { "epoch": 1.57, "learning_rate": 2.6403123474865787e-05, "loss": 0.3313, "step": 2390 }, { "epoch": 1.58, "learning_rate": 2.628111273792094e-05, "loss": 0.0891, "step": 2400 }, { "epoch": 1.59, "learning_rate": 2.6159102000976087e-05, "loss": 0.3472, "step": 2410 }, { "epoch": 1.59, "learning_rate": 2.603709126403124e-05, "loss": 0.2252, "step": 2420 }, { "epoch": 1.6, "learning_rate": 2.5915080527086384e-05, "loss": 0.1036, "step": 2430 }, { "epoch": 1.61, "learning_rate": 2.5793069790141533e-05, "loss": 0.1796, "step": 2440 }, { "epoch": 1.61, "learning_rate": 2.5671059053196685e-05, "loss": 0.0714, "step": 2450 }, { "epoch": 1.62, "learning_rate": 2.5549048316251833e-05, "loss": 0.0964, "step": 2460 }, { "epoch": 1.63, "learning_rate": 2.5427037579306978e-05, "loss": 0.2922, "step": 2470 }, { "epoch": 1.63, "learning_rate": 2.530502684236213e-05, "loss": 0.1718, "step": 2480 }, { "epoch": 1.64, "learning_rate": 2.518301610541728e-05, "loss": 0.2722, "step": 2490 }, { "epoch": 1.65, "learning_rate": 2.506100536847243e-05, "loss": 0.1688, "step": 2500 }, { "epoch": 1.65, "learning_rate": 2.4938994631527575e-05, "loss": 0.1201, "step": 2510 }, { "epoch": 1.66, "learning_rate": 2.4816983894582724e-05, "loss": 0.3123, "step": 2520 }, { "epoch": 1.67, "learning_rate": 2.4694973157637872e-05, "loss": 0.1435, "step": 2530 }, { "epoch": 1.67, "learning_rate": 2.457296242069302e-05, "loss": 0.1422, "step": 2540 }, { "epoch": 1.68, "learning_rate": 2.4450951683748173e-05, "loss": 0.1769, "step": 2550 }, { "epoch": 1.69, "learning_rate": 2.4328940946803318e-05, "loss": 0.2226, "step": 2560 }, { "epoch": 1.69, "learning_rate": 2.420693020985847e-05, "loss": 0.1398, "step": 2570 }, { "epoch": 1.7, "learning_rate": 2.4084919472913618e-05, "loss": 0.3306, "step": 2580 }, { "epoch": 1.71, "learning_rate": 2.3962908735968767e-05, "loss": 0.1219, "step": 2590 }, { "epoch": 1.71, "learning_rate": 2.3840897999023915e-05, "loss": 0.1988, "step": 2600 }, { "epoch": 1.72, "learning_rate": 2.3718887262079064e-05, "loss": 0.1459, "step": 2610 }, { "epoch": 1.73, "learning_rate": 2.3596876525134212e-05, "loss": 0.1356, "step": 2620 }, { "epoch": 1.73, "learning_rate": 2.3474865788189364e-05, "loss": 0.1911, "step": 2630 }, { "epoch": 1.74, "learning_rate": 2.335285505124451e-05, "loss": 0.1032, "step": 2640 }, { "epoch": 1.75, "learning_rate": 2.323084431429966e-05, "loss": 0.1663, "step": 2650 }, { "epoch": 1.75, "learning_rate": 2.310883357735481e-05, "loss": 0.2107, "step": 2660 }, { "epoch": 1.76, "learning_rate": 2.2986822840409958e-05, "loss": 0.0851, "step": 2670 }, { "epoch": 1.77, "learning_rate": 2.2864812103465106e-05, "loss": 0.16, "step": 2680 }, { "epoch": 1.77, "learning_rate": 2.2742801366520255e-05, "loss": 0.1259, "step": 2690 }, { "epoch": 1.78, "learning_rate": 2.2620790629575403e-05, "loss": 0.1364, "step": 2700 }, { "epoch": 1.78, "learning_rate": 2.249877989263055e-05, "loss": 0.195, "step": 2710 }, { "epoch": 1.79, "learning_rate": 2.23767691556857e-05, "loss": 0.2133, "step": 2720 }, { "epoch": 1.8, "learning_rate": 2.2254758418740852e-05, "loss": 0.1744, "step": 2730 }, { "epoch": 1.8, "learning_rate": 2.2132747681795997e-05, "loss": 0.2282, "step": 2740 }, { "epoch": 1.81, "learning_rate": 2.201073694485115e-05, "loss": 0.1695, "step": 2750 }, { "epoch": 1.82, "learning_rate": 2.1888726207906297e-05, "loss": 0.1033, "step": 2760 }, { "epoch": 1.82, "learning_rate": 2.1766715470961446e-05, "loss": 0.1914, "step": 2770 }, { "epoch": 1.83, "learning_rate": 2.1644704734016594e-05, "loss": 0.1528, "step": 2780 }, { "epoch": 1.84, "learning_rate": 2.1522693997071743e-05, "loss": 0.2343, "step": 2790 }, { "epoch": 1.84, "learning_rate": 2.140068326012689e-05, "loss": 0.2458, "step": 2800 }, { "epoch": 1.85, "learning_rate": 2.1278672523182043e-05, "loss": 0.2258, "step": 2810 }, { "epoch": 1.86, "learning_rate": 2.1156661786237188e-05, "loss": 0.2613, "step": 2820 }, { "epoch": 1.86, "learning_rate": 2.103465104929234e-05, "loss": 0.2116, "step": 2830 }, { "epoch": 1.87, "learning_rate": 2.0912640312347485e-05, "loss": 0.1899, "step": 2840 }, { "epoch": 1.88, "learning_rate": 2.0790629575402637e-05, "loss": 0.1115, "step": 2850 }, { "epoch": 1.88, "learning_rate": 2.0668618838457785e-05, "loss": 0.2686, "step": 2860 }, { "epoch": 1.89, "learning_rate": 2.0546608101512934e-05, "loss": 0.1193, "step": 2870 }, { "epoch": 1.9, "learning_rate": 2.0424597364568082e-05, "loss": 0.1021, "step": 2880 }, { "epoch": 1.9, "learning_rate": 2.030258662762323e-05, "loss": 0.172, "step": 2890 }, { "epoch": 1.91, "learning_rate": 2.018057589067838e-05, "loss": 0.158, "step": 2900 }, { "epoch": 1.92, "learning_rate": 2.005856515373353e-05, "loss": 0.2134, "step": 2910 }, { "epoch": 1.92, "learning_rate": 1.9936554416788676e-05, "loss": 0.0816, "step": 2920 }, { "epoch": 1.93, "learning_rate": 1.9814543679843828e-05, "loss": 0.196, "step": 2930 }, { "epoch": 1.94, "learning_rate": 1.9692532942898977e-05, "loss": 0.2682, "step": 2940 }, { "epoch": 1.94, "learning_rate": 1.9570522205954125e-05, "loss": 0.218, "step": 2950 }, { "epoch": 1.95, "learning_rate": 1.9448511469009274e-05, "loss": 0.251, "step": 2960 }, { "epoch": 1.96, "learning_rate": 1.9326500732064422e-05, "loss": 0.2833, "step": 2970 }, { "epoch": 1.96, "learning_rate": 1.920448999511957e-05, "loss": 0.1391, "step": 2980 }, { "epoch": 1.97, "learning_rate": 1.9082479258174722e-05, "loss": 0.1959, "step": 2990 }, { "epoch": 1.98, "learning_rate": 1.8960468521229867e-05, "loss": 0.1985, "step": 3000 }, { "epoch": 1.98, "learning_rate": 1.883845778428502e-05, "loss": 0.284, "step": 3010 }, { "epoch": 1.99, "learning_rate": 1.8716447047340164e-05, "loss": 0.1014, "step": 3020 }, { "epoch": 2.0, "learning_rate": 1.8594436310395316e-05, "loss": 0.082, "step": 3030 }, { "epoch": 2.0, "eval_accuracy": 0.9814814814814815, "eval_loss": 0.07054726779460907, "eval_runtime": 18.7083, "eval_samples_per_second": 144.321, "eval_steps_per_second": 36.08, "step": 3036 }, { "epoch": 2.0, "learning_rate": 1.8472425573450465e-05, "loss": 0.1371, "step": 3040 }, { "epoch": 2.01, "learning_rate": 1.8350414836505613e-05, "loss": 0.1256, "step": 3050 }, { "epoch": 2.02, "learning_rate": 1.822840409956076e-05, "loss": 0.1609, "step": 3060 }, { "epoch": 2.02, "learning_rate": 1.810639336261591e-05, "loss": 0.0995, "step": 3070 }, { "epoch": 2.03, "learning_rate": 1.798438262567106e-05, "loss": 0.3005, "step": 3080 }, { "epoch": 2.04, "learning_rate": 1.786237188872621e-05, "loss": 0.0905, "step": 3090 }, { "epoch": 2.04, "learning_rate": 1.7740361151781356e-05, "loss": 0.2747, "step": 3100 }, { "epoch": 2.05, "learning_rate": 1.7618350414836507e-05, "loss": 0.2143, "step": 3110 }, { "epoch": 2.06, "learning_rate": 1.7496339677891656e-05, "loss": 0.147, "step": 3120 }, { "epoch": 2.06, "learning_rate": 1.7374328940946804e-05, "loss": 0.1069, "step": 3130 }, { "epoch": 2.07, "learning_rate": 1.7252318204001953e-05, "loss": 0.0796, "step": 3140 }, { "epoch": 2.08, "learning_rate": 1.71303074670571e-05, "loss": 0.0877, "step": 3150 }, { "epoch": 2.08, "learning_rate": 1.700829673011225e-05, "loss": 0.2032, "step": 3160 }, { "epoch": 2.09, "learning_rate": 1.68862859931674e-05, "loss": 0.1379, "step": 3170 }, { "epoch": 2.09, "learning_rate": 1.6764275256222547e-05, "loss": 0.1742, "step": 3180 }, { "epoch": 2.1, "learning_rate": 1.66422645192777e-05, "loss": 0.0823, "step": 3190 }, { "epoch": 2.11, "learning_rate": 1.6520253782332844e-05, "loss": 0.1625, "step": 3200 }, { "epoch": 2.11, "learning_rate": 1.6398243045387995e-05, "loss": 0.2042, "step": 3210 }, { "epoch": 2.12, "learning_rate": 1.6276232308443144e-05, "loss": 0.1367, "step": 3220 }, { "epoch": 2.13, "learning_rate": 1.6154221571498292e-05, "loss": 0.1764, "step": 3230 }, { "epoch": 2.13, "learning_rate": 1.603221083455344e-05, "loss": 0.1701, "step": 3240 }, { "epoch": 2.14, "learning_rate": 1.591020009760859e-05, "loss": 0.0838, "step": 3250 }, { "epoch": 2.15, "learning_rate": 1.5788189360663738e-05, "loss": 0.1189, "step": 3260 }, { "epoch": 2.15, "learning_rate": 1.566617862371889e-05, "loss": 0.1854, "step": 3270 }, { "epoch": 2.16, "learning_rate": 1.5544167886774035e-05, "loss": 0.24, "step": 3280 }, { "epoch": 2.17, "learning_rate": 1.5422157149829187e-05, "loss": 0.1878, "step": 3290 }, { "epoch": 2.17, "learning_rate": 1.5300146412884335e-05, "loss": 0.1349, "step": 3300 }, { "epoch": 2.18, "learning_rate": 1.5178135675939484e-05, "loss": 0.1088, "step": 3310 }, { "epoch": 2.19, "learning_rate": 1.5056124938994632e-05, "loss": 0.014, "step": 3320 }, { "epoch": 2.19, "learning_rate": 1.4934114202049782e-05, "loss": 0.0921, "step": 3330 }, { "epoch": 2.2, "learning_rate": 1.4812103465104929e-05, "loss": 0.2237, "step": 3340 }, { "epoch": 2.21, "learning_rate": 1.4690092728160079e-05, "loss": 0.266, "step": 3350 }, { "epoch": 2.21, "learning_rate": 1.4568081991215226e-05, "loss": 0.1167, "step": 3360 }, { "epoch": 2.22, "learning_rate": 1.4446071254270376e-05, "loss": 0.2226, "step": 3370 }, { "epoch": 2.23, "learning_rate": 1.4324060517325525e-05, "loss": 0.1691, "step": 3380 }, { "epoch": 2.23, "learning_rate": 1.4202049780380675e-05, "loss": 0.1663, "step": 3390 }, { "epoch": 2.24, "learning_rate": 1.4080039043435821e-05, "loss": 0.2938, "step": 3400 }, { "epoch": 2.25, "learning_rate": 1.3958028306490972e-05, "loss": 0.0817, "step": 3410 }, { "epoch": 2.25, "learning_rate": 1.383601756954612e-05, "loss": 0.0924, "step": 3420 }, { "epoch": 2.26, "learning_rate": 1.371400683260127e-05, "loss": 0.1979, "step": 3430 }, { "epoch": 2.27, "learning_rate": 1.3591996095656417e-05, "loss": 0.1476, "step": 3440 }, { "epoch": 2.27, "learning_rate": 1.3469985358711567e-05, "loss": 0.2025, "step": 3450 }, { "epoch": 2.28, "learning_rate": 1.3347974621766716e-05, "loss": 0.138, "step": 3460 }, { "epoch": 2.29, "learning_rate": 1.3225963884821866e-05, "loss": 0.1118, "step": 3470 }, { "epoch": 2.29, "learning_rate": 1.3103953147877013e-05, "loss": 0.2307, "step": 3480 }, { "epoch": 2.3, "learning_rate": 1.2981942410932163e-05, "loss": 0.1993, "step": 3490 }, { "epoch": 2.31, "learning_rate": 1.2859931673987311e-05, "loss": 0.1583, "step": 3500 }, { "epoch": 2.31, "learning_rate": 1.2737920937042461e-05, "loss": 0.164, "step": 3510 }, { "epoch": 2.32, "learning_rate": 1.2615910200097608e-05, "loss": 0.2269, "step": 3520 }, { "epoch": 2.33, "learning_rate": 1.2493899463152758e-05, "loss": 0.0831, "step": 3530 }, { "epoch": 2.33, "learning_rate": 1.2371888726207907e-05, "loss": 0.1676, "step": 3540 }, { "epoch": 2.34, "learning_rate": 1.2249877989263055e-05, "loss": 0.0981, "step": 3550 }, { "epoch": 2.35, "learning_rate": 1.2127867252318205e-05, "loss": 0.2707, "step": 3560 }, { "epoch": 2.35, "learning_rate": 1.2005856515373354e-05, "loss": 0.0235, "step": 3570 }, { "epoch": 2.36, "learning_rate": 1.1883845778428502e-05, "loss": 0.1038, "step": 3580 }, { "epoch": 2.36, "learning_rate": 1.1761835041483651e-05, "loss": 0.1165, "step": 3590 }, { "epoch": 2.37, "learning_rate": 1.1639824304538801e-05, "loss": 0.2056, "step": 3600 }, { "epoch": 2.38, "learning_rate": 1.151781356759395e-05, "loss": 0.1459, "step": 3610 }, { "epoch": 2.38, "learning_rate": 1.1395802830649098e-05, "loss": 0.16, "step": 3620 }, { "epoch": 2.39, "learning_rate": 1.1273792093704246e-05, "loss": 0.1323, "step": 3630 }, { "epoch": 2.4, "learning_rate": 1.1151781356759395e-05, "loss": 0.0746, "step": 3640 }, { "epoch": 2.4, "learning_rate": 1.1029770619814545e-05, "loss": 0.109, "step": 3650 }, { "epoch": 2.41, "learning_rate": 1.0907759882869694e-05, "loss": 0.1262, "step": 3660 }, { "epoch": 2.42, "learning_rate": 1.0785749145924842e-05, "loss": 0.0642, "step": 3670 }, { "epoch": 2.42, "learning_rate": 1.066373840897999e-05, "loss": 0.0643, "step": 3680 }, { "epoch": 2.43, "learning_rate": 1.054172767203514e-05, "loss": 0.1396, "step": 3690 }, { "epoch": 2.44, "learning_rate": 1.0419716935090289e-05, "loss": 0.1623, "step": 3700 }, { "epoch": 2.44, "learning_rate": 1.0297706198145438e-05, "loss": 0.1065, "step": 3710 }, { "epoch": 2.45, "learning_rate": 1.0175695461200586e-05, "loss": 0.2549, "step": 3720 }, { "epoch": 2.46, "learning_rate": 1.0053684724255735e-05, "loss": 0.2752, "step": 3730 }, { "epoch": 2.46, "learning_rate": 9.931673987310885e-06, "loss": 0.1021, "step": 3740 }, { "epoch": 2.47, "learning_rate": 9.809663250366033e-06, "loss": 0.1233, "step": 3750 }, { "epoch": 2.48, "learning_rate": 9.687652513421182e-06, "loss": 0.1324, "step": 3760 }, { "epoch": 2.48, "learning_rate": 9.56564177647633e-06, "loss": 0.0958, "step": 3770 }, { "epoch": 2.49, "learning_rate": 9.44363103953148e-06, "loss": 0.1788, "step": 3780 }, { "epoch": 2.5, "learning_rate": 9.321620302586629e-06, "loss": 0.0721, "step": 3790 }, { "epoch": 2.5, "learning_rate": 9.199609565641777e-06, "loss": 0.1408, "step": 3800 }, { "epoch": 2.51, "learning_rate": 9.077598828696926e-06, "loss": 0.1038, "step": 3810 }, { "epoch": 2.52, "learning_rate": 8.955588091752074e-06, "loss": 0.1108, "step": 3820 }, { "epoch": 2.52, "learning_rate": 8.833577354807224e-06, "loss": 0.1849, "step": 3830 }, { "epoch": 2.53, "learning_rate": 8.711566617862373e-06, "loss": 0.2029, "step": 3840 }, { "epoch": 2.54, "learning_rate": 8.589555880917521e-06, "loss": 0.0657, "step": 3850 }, { "epoch": 2.54, "learning_rate": 8.46754514397267e-06, "loss": 0.0576, "step": 3860 }, { "epoch": 2.55, "learning_rate": 8.34553440702782e-06, "loss": 0.1392, "step": 3870 }, { "epoch": 2.56, "learning_rate": 8.223523670082968e-06, "loss": 0.2049, "step": 3880 }, { "epoch": 2.56, "learning_rate": 8.101512933138117e-06, "loss": 0.2311, "step": 3890 }, { "epoch": 2.57, "learning_rate": 7.979502196193265e-06, "loss": 0.1042, "step": 3900 }, { "epoch": 2.58, "learning_rate": 7.857491459248414e-06, "loss": 0.1597, "step": 3910 }, { "epoch": 2.58, "learning_rate": 7.735480722303564e-06, "loss": 0.1141, "step": 3920 }, { "epoch": 2.59, "learning_rate": 7.613469985358712e-06, "loss": 0.1527, "step": 3930 }, { "epoch": 2.6, "learning_rate": 7.491459248413861e-06, "loss": 0.1251, "step": 3940 }, { "epoch": 2.6, "learning_rate": 7.36944851146901e-06, "loss": 0.1911, "step": 3950 }, { "epoch": 2.61, "learning_rate": 7.247437774524159e-06, "loss": 0.1502, "step": 3960 }, { "epoch": 2.61, "learning_rate": 7.125427037579307e-06, "loss": 0.1547, "step": 3970 }, { "epoch": 2.62, "learning_rate": 7.0034163006344565e-06, "loss": 0.1413, "step": 3980 }, { "epoch": 2.63, "learning_rate": 6.881405563689605e-06, "loss": 0.1673, "step": 3990 }, { "epoch": 2.63, "learning_rate": 6.759394826744754e-06, "loss": 0.4336, "step": 4000 }, { "epoch": 2.64, "learning_rate": 6.637384089799903e-06, "loss": 0.2296, "step": 4010 }, { "epoch": 2.65, "learning_rate": 6.515373352855052e-06, "loss": 0.1307, "step": 4020 }, { "epoch": 2.65, "learning_rate": 6.3933626159102005e-06, "loss": 0.1758, "step": 4030 }, { "epoch": 2.66, "learning_rate": 6.27135187896535e-06, "loss": 0.1915, "step": 4040 }, { "epoch": 2.67, "learning_rate": 6.149341142020498e-06, "loss": 0.1185, "step": 4050 }, { "epoch": 2.67, "learning_rate": 6.027330405075647e-06, "loss": 0.1209, "step": 4060 }, { "epoch": 2.68, "learning_rate": 5.905319668130796e-06, "loss": 0.1094, "step": 4070 }, { "epoch": 2.69, "learning_rate": 5.7833089311859446e-06, "loss": 0.0834, "step": 4080 }, { "epoch": 2.69, "learning_rate": 5.661298194241094e-06, "loss": 0.1262, "step": 4090 }, { "epoch": 2.7, "learning_rate": 5.539287457296242e-06, "loss": 0.1116, "step": 4100 }, { "epoch": 2.71, "learning_rate": 5.417276720351392e-06, "loss": 0.1289, "step": 4110 }, { "epoch": 2.71, "learning_rate": 5.29526598340654e-06, "loss": 0.1206, "step": 4120 }, { "epoch": 2.72, "learning_rate": 5.173255246461689e-06, "loss": 0.1522, "step": 4130 }, { "epoch": 2.73, "learning_rate": 5.051244509516838e-06, "loss": 0.1731, "step": 4140 }, { "epoch": 2.73, "learning_rate": 4.929233772571986e-06, "loss": 0.1232, "step": 4150 }, { "epoch": 2.74, "learning_rate": 4.807223035627136e-06, "loss": 0.1826, "step": 4160 }, { "epoch": 2.75, "learning_rate": 4.685212298682284e-06, "loss": 0.0827, "step": 4170 }, { "epoch": 2.75, "learning_rate": 4.5632015617374335e-06, "loss": 0.0632, "step": 4180 }, { "epoch": 2.76, "learning_rate": 4.441190824792582e-06, "loss": 0.1184, "step": 4190 }, { "epoch": 2.77, "learning_rate": 4.319180087847731e-06, "loss": 0.1199, "step": 4200 }, { "epoch": 2.77, "learning_rate": 4.19716935090288e-06, "loss": 0.0813, "step": 4210 }, { "epoch": 2.78, "learning_rate": 4.075158613958028e-06, "loss": 0.0658, "step": 4220 }, { "epoch": 2.79, "learning_rate": 3.9531478770131775e-06, "loss": 0.0782, "step": 4230 }, { "epoch": 2.79, "learning_rate": 3.831137140068326e-06, "loss": 0.1828, "step": 4240 }, { "epoch": 2.8, "learning_rate": 3.7091264031234753e-06, "loss": 0.1335, "step": 4250 }, { "epoch": 2.81, "learning_rate": 3.587115666178624e-06, "loss": 0.0839, "step": 4260 }, { "epoch": 2.81, "learning_rate": 3.4651049292337727e-06, "loss": 0.1274, "step": 4270 }, { "epoch": 2.82, "learning_rate": 3.3430941922889216e-06, "loss": 0.0738, "step": 4280 }, { "epoch": 2.83, "learning_rate": 3.2210834553440705e-06, "loss": 0.0583, "step": 4290 }, { "epoch": 2.83, "learning_rate": 3.0990727183992194e-06, "loss": 0.0594, "step": 4300 }, { "epoch": 2.84, "learning_rate": 2.9770619814543683e-06, "loss": 0.1833, "step": 4310 }, { "epoch": 2.85, "learning_rate": 2.855051244509517e-06, "loss": 0.0747, "step": 4320 }, { "epoch": 2.85, "learning_rate": 2.733040507564666e-06, "loss": 0.0931, "step": 4330 }, { "epoch": 2.86, "learning_rate": 2.611029770619815e-06, "loss": 0.1447, "step": 4340 }, { "epoch": 2.87, "learning_rate": 2.4890190336749634e-06, "loss": 0.2114, "step": 4350 }, { "epoch": 2.87, "learning_rate": 2.3670082967301123e-06, "loss": 0.1706, "step": 4360 }, { "epoch": 2.88, "learning_rate": 2.244997559785261e-06, "loss": 0.1236, "step": 4370 }, { "epoch": 2.88, "learning_rate": 2.12298682284041e-06, "loss": 0.0746, "step": 4380 }, { "epoch": 2.89, "learning_rate": 2.000976085895559e-06, "loss": 0.0672, "step": 4390 }, { "epoch": 2.9, "learning_rate": 1.8789653489507079e-06, "loss": 0.0754, "step": 4400 }, { "epoch": 2.9, "learning_rate": 1.7569546120058566e-06, "loss": 0.1822, "step": 4410 }, { "epoch": 2.91, "learning_rate": 1.6349438750610055e-06, "loss": 0.0668, "step": 4420 }, { "epoch": 2.92, "learning_rate": 1.5129331381161544e-06, "loss": 0.1071, "step": 4430 }, { "epoch": 2.92, "learning_rate": 1.3909224011713032e-06, "loss": 0.2719, "step": 4440 }, { "epoch": 2.93, "learning_rate": 1.268911664226452e-06, "loss": 0.0667, "step": 4450 }, { "epoch": 2.94, "learning_rate": 1.1469009272816008e-06, "loss": 0.1908, "step": 4460 }, { "epoch": 2.94, "learning_rate": 1.0248901903367497e-06, "loss": 0.0702, "step": 4470 }, { "epoch": 2.95, "learning_rate": 9.028794533918985e-07, "loss": 0.0646, "step": 4480 }, { "epoch": 2.96, "learning_rate": 7.808687164470474e-07, "loss": 0.059, "step": 4490 }, { "epoch": 2.96, "learning_rate": 6.588579795021963e-07, "loss": 0.1765, "step": 4500 }, { "epoch": 2.97, "learning_rate": 5.368472425573451e-07, "loss": 0.0369, "step": 4510 }, { "epoch": 2.98, "learning_rate": 4.148365056124939e-07, "loss": 0.1873, "step": 4520 }, { "epoch": 2.98, "learning_rate": 2.9282576866764276e-07, "loss": 0.0937, "step": 4530 }, { "epoch": 2.99, "learning_rate": 1.7081503172279163e-07, "loss": 0.0971, "step": 4540 }, { "epoch": 3.0, "learning_rate": 4.880429477794046e-08, "loss": 0.101, "step": 4550 }, { "epoch": 3.0, "eval_accuracy": 0.9881481481481481, "eval_loss": 0.0507892481982708, "eval_runtime": 18.9316, "eval_samples_per_second": 142.619, "eval_steps_per_second": 35.655, "step": 4554 }, { "epoch": 3.0, "step": 4554, "total_flos": 1.812108312032772e+18, "train_loss": 0.28194282464740317, "train_runtime": 1397.0334, "train_samples_per_second": 52.182, "train_steps_per_second": 3.26 } ], "max_steps": 4554, "num_train_epochs": 3, "total_flos": 1.812108312032772e+18, "trial_name": null, "trial_params": null }