{ "best_metric": null, "best_model_checkpoint": null, "epoch": 92.95132541133455, "global_step": 387159, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 9.99999998711498e-05, "loss": 1.4805, "step": 10 }, { "epoch": 0.0, "learning_rate": 9.999999948459917e-05, "loss": 1.4179, "step": 20 }, { "epoch": 0.01, "learning_rate": 9.999999884034814e-05, "loss": 1.3482, "step": 30 }, { "epoch": 0.01, "learning_rate": 9.999999793839668e-05, "loss": 1.2311, "step": 40 }, { "epoch": 0.01, "learning_rate": 9.99999967787448e-05, "loss": 1.1575, "step": 50 }, { "epoch": 0.01, "learning_rate": 9.999999536139255e-05, "loss": 1.1186, "step": 60 }, { "epoch": 0.02, "learning_rate": 9.999999368633989e-05, "loss": 1.1409, "step": 70 }, { "epoch": 0.02, "learning_rate": 9.999999175358685e-05, "loss": 1.0983, "step": 80 }, { "epoch": 0.02, "learning_rate": 9.999998956313344e-05, "loss": 1.1158, "step": 90 }, { "epoch": 0.02, "learning_rate": 9.999998711497966e-05, "loss": 1.0825, "step": 100 }, { "epoch": 0.03, "learning_rate": 9.999998440912552e-05, "loss": 1.1315, "step": 110 }, { "epoch": 0.03, "learning_rate": 9.999998144557106e-05, "loss": 1.1227, "step": 120 }, { "epoch": 0.03, "learning_rate": 9.999997822431626e-05, "loss": 1.0465, "step": 130 }, { "epoch": 0.03, "learning_rate": 9.999997474536116e-05, "loss": 1.0465, "step": 140 }, { "epoch": 0.03, "learning_rate": 9.999997100870578e-05, "loss": 1.0608, "step": 150 }, { "epoch": 0.04, "learning_rate": 9.999996701435012e-05, "loss": 1.1434, "step": 160 }, { "epoch": 0.04, "learning_rate": 9.999996276229422e-05, "loss": 1.0732, "step": 170 }, { "epoch": 0.04, "learning_rate": 9.99999582525381e-05, "loss": 1.0762, "step": 180 }, { "epoch": 0.04, "learning_rate": 9.999995348508176e-05, "loss": 1.1126, "step": 190 }, { "epoch": 0.05, "learning_rate": 9.999994845992525e-05, "loss": 1.0864, "step": 200 }, { "epoch": 0.05, "learning_rate": 9.99999431770686e-05, "loss": 1.0663, "step": 210 }, { "epoch": 0.05, "learning_rate": 9.999993763651181e-05, "loss": 1.0763, "step": 220 }, { "epoch": 0.05, "learning_rate": 9.999993183825492e-05, "loss": 1.0675, "step": 230 }, { "epoch": 0.05, "learning_rate": 9.999992578229798e-05, "loss": 1.1079, "step": 240 }, { "epoch": 0.06, "learning_rate": 9.999991946864098e-05, "loss": 1.0634, "step": 250 }, { "epoch": 0.06, "learning_rate": 9.999991289728399e-05, "loss": 1.1158, "step": 260 }, { "epoch": 0.06, "learning_rate": 9.999990606822704e-05, "loss": 1.0682, "step": 270 }, { "epoch": 0.06, "learning_rate": 9.999989898147015e-05, "loss": 1.0766, "step": 280 }, { "epoch": 0.07, "learning_rate": 9.999989163701336e-05, "loss": 1.0792, "step": 290 }, { "epoch": 0.07, "learning_rate": 9.999988403485671e-05, "loss": 1.1048, "step": 300 }, { "epoch": 0.07, "learning_rate": 9.999987617500024e-05, "loss": 1.0648, "step": 310 }, { "epoch": 0.07, "learning_rate": 9.999986805744399e-05, "loss": 1.0573, "step": 320 }, { "epoch": 0.08, "learning_rate": 9.999985968218802e-05, "loss": 1.0908, "step": 330 }, { "epoch": 0.08, "learning_rate": 9.999985104923232e-05, "loss": 1.0741, "step": 340 }, { "epoch": 0.08, "learning_rate": 9.9999842158577e-05, "loss": 1.0459, "step": 350 }, { "epoch": 0.08, "learning_rate": 9.999983301022207e-05, "loss": 1.0769, "step": 360 }, { "epoch": 0.08, "learning_rate": 9.999982360416758e-05, "loss": 1.0702, "step": 370 }, { "epoch": 0.09, "learning_rate": 9.999981394041357e-05, "loss": 1.0881, "step": 380 }, { "epoch": 0.09, "learning_rate": 9.999980401896011e-05, "loss": 1.0797, "step": 390 }, { "epoch": 0.09, "learning_rate": 9.999979383980725e-05, "loss": 1.0586, "step": 400 }, { "epoch": 0.09, "learning_rate": 9.999978340295502e-05, "loss": 1.1049, "step": 410 }, { "epoch": 0.1, "learning_rate": 9.999977270840349e-05, "loss": 1.1528, "step": 420 }, { "epoch": 0.1, "learning_rate": 9.999976175615272e-05, "loss": 1.1208, "step": 430 }, { "epoch": 0.1, "learning_rate": 9.999975054620276e-05, "loss": 1.0974, "step": 440 }, { "epoch": 0.1, "learning_rate": 9.999973907855366e-05, "loss": 1.1127, "step": 450 }, { "epoch": 0.11, "learning_rate": 9.99997273532055e-05, "loss": 1.1065, "step": 460 }, { "epoch": 0.11, "learning_rate": 9.999971537015832e-05, "loss": 1.1157, "step": 470 }, { "epoch": 0.11, "learning_rate": 9.999970312941219e-05, "loss": 1.0918, "step": 480 }, { "epoch": 0.11, "learning_rate": 9.999969063096717e-05, "loss": 1.075, "step": 490 }, { "epoch": 0.11, "learning_rate": 9.999967787482333e-05, "loss": 1.0315, "step": 500 }, { "epoch": 0.12, "learning_rate": 9.999966486098074e-05, "loss": 1.0367, "step": 510 }, { "epoch": 0.12, "learning_rate": 9.999965158943943e-05, "loss": 1.0363, "step": 520 }, { "epoch": 0.12, "learning_rate": 9.999963806019951e-05, "loss": 1.0333, "step": 530 }, { "epoch": 0.12, "learning_rate": 9.999962427326106e-05, "loss": 1.0603, "step": 540 }, { "epoch": 0.13, "learning_rate": 9.999961022862412e-05, "loss": 1.0286, "step": 550 }, { "epoch": 0.13, "learning_rate": 9.999959592628876e-05, "loss": 1.0373, "step": 560 }, { "epoch": 0.13, "learning_rate": 9.999958136625507e-05, "loss": 1.0572, "step": 570 }, { "epoch": 0.13, "learning_rate": 9.999956654852312e-05, "loss": 1.0629, "step": 580 }, { "epoch": 0.13, "learning_rate": 9.999955147309298e-05, "loss": 1.0988, "step": 590 }, { "epoch": 0.14, "learning_rate": 9.999953613996474e-05, "loss": 1.04, "step": 600 }, { "epoch": 0.14, "learning_rate": 9.999952054913848e-05, "loss": 1.0347, "step": 610 }, { "epoch": 0.14, "learning_rate": 9.999950470061426e-05, "loss": 1.0564, "step": 620 }, { "epoch": 0.14, "learning_rate": 9.999948859439217e-05, "loss": 1.0364, "step": 630 }, { "epoch": 0.15, "learning_rate": 9.999947223047231e-05, "loss": 1.0268, "step": 640 }, { "epoch": 0.15, "learning_rate": 9.999945560885475e-05, "loss": 1.0612, "step": 650 }, { "epoch": 0.15, "learning_rate": 9.999943872953958e-05, "loss": 1.0213, "step": 660 }, { "epoch": 0.15, "learning_rate": 9.999942159252688e-05, "loss": 1.0141, "step": 670 }, { "epoch": 0.16, "learning_rate": 9.999940419781675e-05, "loss": 1.0333, "step": 680 }, { "epoch": 0.16, "learning_rate": 9.999938654540926e-05, "loss": 1.0522, "step": 690 }, { "epoch": 0.16, "learning_rate": 9.999936863530452e-05, "loss": 1.0784, "step": 700 }, { "epoch": 0.16, "learning_rate": 9.999935046750262e-05, "loss": 1.0385, "step": 710 }, { "epoch": 0.16, "learning_rate": 9.999933204200366e-05, "loss": 1.0562, "step": 720 }, { "epoch": 0.17, "learning_rate": 9.999931335880771e-05, "loss": 1.0331, "step": 730 }, { "epoch": 0.17, "learning_rate": 9.99992944179149e-05, "loss": 1.0176, "step": 740 }, { "epoch": 0.17, "learning_rate": 9.999927521932528e-05, "loss": 1.044, "step": 750 }, { "epoch": 0.17, "learning_rate": 9.999925576303899e-05, "loss": 1.0331, "step": 760 }, { "epoch": 0.18, "learning_rate": 9.999923604905612e-05, "loss": 1.0143, "step": 770 }, { "epoch": 0.18, "learning_rate": 9.999921607737676e-05, "loss": 1.0166, "step": 780 }, { "epoch": 0.18, "learning_rate": 9.999919584800104e-05, "loss": 1.0353, "step": 790 }, { "epoch": 0.18, "learning_rate": 9.999917536092901e-05, "loss": 1.0167, "step": 800 }, { "epoch": 0.19, "learning_rate": 9.999915461616085e-05, "loss": 1.0027, "step": 810 }, { "epoch": 0.19, "learning_rate": 9.999913361369663e-05, "loss": 1.0233, "step": 820 }, { "epoch": 0.19, "learning_rate": 9.999911235353644e-05, "loss": 1.0374, "step": 830 }, { "epoch": 0.19, "learning_rate": 9.999909083568042e-05, "loss": 1.0021, "step": 840 }, { "epoch": 0.19, "learning_rate": 9.999906906012866e-05, "loss": 1.0386, "step": 850 }, { "epoch": 0.2, "learning_rate": 9.999904702688128e-05, "loss": 1.0253, "step": 860 }, { "epoch": 0.2, "learning_rate": 9.999902473593838e-05, "loss": 1.0098, "step": 870 }, { "epoch": 0.2, "learning_rate": 9.999900218730012e-05, "loss": 0.9909, "step": 880 }, { "epoch": 0.2, "learning_rate": 9.999897938096656e-05, "loss": 1.0066, "step": 890 }, { "epoch": 0.21, "learning_rate": 9.999895631693786e-05, "loss": 1.0519, "step": 900 }, { "epoch": 0.21, "learning_rate": 9.99989329952141e-05, "loss": 1.0003, "step": 910 }, { "epoch": 0.21, "learning_rate": 9.999890941579544e-05, "loss": 1.0005, "step": 920 }, { "epoch": 0.21, "learning_rate": 9.999888557868196e-05, "loss": 1.0211, "step": 930 }, { "epoch": 0.21, "learning_rate": 9.999886148387383e-05, "loss": 1.0227, "step": 940 }, { "epoch": 0.22, "learning_rate": 9.999883713137114e-05, "loss": 1.0617, "step": 950 }, { "epoch": 0.22, "learning_rate": 9.999881252117403e-05, "loss": 0.9936, "step": 960 }, { "epoch": 0.22, "learning_rate": 9.999878765328262e-05, "loss": 1.0833, "step": 970 }, { "epoch": 0.22, "learning_rate": 9.999876252769703e-05, "loss": 1.0101, "step": 980 }, { "epoch": 0.23, "learning_rate": 9.99987371444174e-05, "loss": 0.9943, "step": 990 }, { "epoch": 0.23, "learning_rate": 9.999871150344389e-05, "loss": 1.0786, "step": 1000 }, { "epoch": 0.23, "learning_rate": 9.999868560477658e-05, "loss": 1.001, "step": 1010 }, { "epoch": 0.23, "learning_rate": 9.999865944841562e-05, "loss": 1.0183, "step": 1020 }, { "epoch": 0.24, "learning_rate": 9.999863303436116e-05, "loss": 0.9937, "step": 1030 }, { "epoch": 0.24, "learning_rate": 9.999860636261333e-05, "loss": 0.9847, "step": 1040 }, { "epoch": 0.24, "learning_rate": 9.999857943317227e-05, "loss": 0.9862, "step": 1050 }, { "epoch": 0.24, "learning_rate": 9.999855224603811e-05, "loss": 0.9801, "step": 1060 }, { "epoch": 0.24, "learning_rate": 9.999852480121099e-05, "loss": 0.9776, "step": 1070 }, { "epoch": 0.25, "learning_rate": 9.999849709869104e-05, "loss": 0.9986, "step": 1080 }, { "epoch": 0.25, "learning_rate": 9.999846913847846e-05, "loss": 0.968, "step": 1090 }, { "epoch": 0.25, "learning_rate": 9.999844092057331e-05, "loss": 0.9556, "step": 1100 }, { "epoch": 0.25, "learning_rate": 9.99984124449758e-05, "loss": 0.964, "step": 1110 }, { "epoch": 0.26, "learning_rate": 9.999838371168604e-05, "loss": 0.99, "step": 1120 }, { "epoch": 0.26, "learning_rate": 9.99983547207042e-05, "loss": 0.9908, "step": 1130 }, { "epoch": 0.26, "learning_rate": 9.999832547203043e-05, "loss": 0.9831, "step": 1140 }, { "epoch": 0.26, "learning_rate": 9.999829596566487e-05, "loss": 0.9935, "step": 1150 }, { "epoch": 0.27, "learning_rate": 9.999826620160766e-05, "loss": 0.9946, "step": 1160 }, { "epoch": 0.27, "learning_rate": 9.999823617985898e-05, "loss": 0.9647, "step": 1170 }, { "epoch": 0.27, "learning_rate": 9.999820590041898e-05, "loss": 0.974, "step": 1180 }, { "epoch": 0.27, "learning_rate": 9.999817536328779e-05, "loss": 0.9306, "step": 1190 }, { "epoch": 0.27, "learning_rate": 9.999814456846558e-05, "loss": 0.9329, "step": 1200 }, { "epoch": 0.28, "learning_rate": 9.999811351595255e-05, "loss": 0.917, "step": 1210 }, { "epoch": 0.28, "learning_rate": 9.99980822057488e-05, "loss": 0.9564, "step": 1220 }, { "epoch": 0.28, "learning_rate": 9.999805063785452e-05, "loss": 0.9444, "step": 1230 }, { "epoch": 0.28, "learning_rate": 9.999801881226988e-05, "loss": 0.9855, "step": 1240 }, { "epoch": 0.29, "learning_rate": 9.999798672899503e-05, "loss": 0.9754, "step": 1250 }, { "epoch": 0.29, "learning_rate": 9.999795438803012e-05, "loss": 0.9394, "step": 1260 }, { "epoch": 0.29, "learning_rate": 9.999792178937535e-05, "loss": 0.9806, "step": 1270 }, { "epoch": 0.29, "learning_rate": 9.999788893303087e-05, "loss": 1.0343, "step": 1280 }, { "epoch": 0.29, "learning_rate": 9.999785581899686e-05, "loss": 0.9337, "step": 1290 }, { "epoch": 0.3, "learning_rate": 9.999782244727346e-05, "loss": 0.9421, "step": 1300 }, { "epoch": 0.3, "learning_rate": 9.999778881786091e-05, "loss": 0.9188, "step": 1310 }, { "epoch": 0.3, "learning_rate": 9.999775493075929e-05, "loss": 0.9877, "step": 1320 }, { "epoch": 0.3, "learning_rate": 9.999772078596885e-05, "loss": 0.9552, "step": 1330 }, { "epoch": 0.31, "learning_rate": 9.999768638348974e-05, "loss": 0.9244, "step": 1340 }, { "epoch": 0.31, "learning_rate": 9.999765172332212e-05, "loss": 0.915, "step": 1350 }, { "epoch": 0.31, "learning_rate": 9.99976168054662e-05, "loss": 0.9299, "step": 1360 }, { "epoch": 0.31, "learning_rate": 9.999758162992215e-05, "loss": 0.9305, "step": 1370 }, { "epoch": 0.32, "learning_rate": 9.999754619669013e-05, "loss": 0.9196, "step": 1380 }, { "epoch": 0.32, "learning_rate": 9.999751050577033e-05, "loss": 0.9141, "step": 1390 }, { "epoch": 0.32, "learning_rate": 9.999747455716297e-05, "loss": 0.9505, "step": 1400 }, { "epoch": 0.32, "learning_rate": 9.999743835086819e-05, "loss": 0.9233, "step": 1410 }, { "epoch": 0.32, "learning_rate": 9.99974018868862e-05, "loss": 0.9254, "step": 1420 }, { "epoch": 0.33, "learning_rate": 9.999736516521718e-05, "loss": 0.9562, "step": 1430 }, { "epoch": 0.33, "learning_rate": 9.999732818586134e-05, "loss": 0.9251, "step": 1440 }, { "epoch": 0.33, "learning_rate": 9.999729094881883e-05, "loss": 0.9711, "step": 1450 }, { "epoch": 0.33, "learning_rate": 9.999725345408988e-05, "loss": 0.9092, "step": 1460 }, { "epoch": 0.34, "learning_rate": 9.999721570167465e-05, "loss": 0.924, "step": 1470 }, { "epoch": 0.34, "learning_rate": 9.999717769157337e-05, "loss": 0.928, "step": 1480 }, { "epoch": 0.34, "learning_rate": 9.999713942378621e-05, "loss": 0.9068, "step": 1490 }, { "epoch": 0.34, "learning_rate": 9.999710089831338e-05, "loss": 0.9256, "step": 1500 }, { "epoch": 0.35, "learning_rate": 9.999706211515507e-05, "loss": 0.8826, "step": 1510 }, { "epoch": 0.35, "learning_rate": 9.999702307431148e-05, "loss": 0.9595, "step": 1520 }, { "epoch": 0.35, "learning_rate": 9.999698377578281e-05, "loss": 0.9066, "step": 1530 }, { "epoch": 0.35, "learning_rate": 9.99969442195693e-05, "loss": 0.9228, "step": 1540 }, { "epoch": 0.35, "learning_rate": 9.999690440567109e-05, "loss": 0.9665, "step": 1550 }, { "epoch": 0.36, "learning_rate": 9.999686433408843e-05, "loss": 0.9263, "step": 1560 }, { "epoch": 0.36, "learning_rate": 9.999682400482151e-05, "loss": 0.9683, "step": 1570 }, { "epoch": 0.36, "learning_rate": 9.999678341787053e-05, "loss": 0.9384, "step": 1580 }, { "epoch": 0.36, "learning_rate": 9.999674257323573e-05, "loss": 0.8933, "step": 1590 }, { "epoch": 0.37, "learning_rate": 9.999670147091729e-05, "loss": 0.9429, "step": 1600 }, { "epoch": 0.37, "learning_rate": 9.999666011091543e-05, "loss": 0.9254, "step": 1610 }, { "epoch": 0.37, "learning_rate": 9.999661849323037e-05, "loss": 0.9443, "step": 1620 }, { "epoch": 0.37, "learning_rate": 9.999657661786233e-05, "loss": 0.9513, "step": 1630 }, { "epoch": 0.37, "learning_rate": 9.99965344848115e-05, "loss": 0.904, "step": 1640 }, { "epoch": 0.38, "learning_rate": 9.999649209407812e-05, "loss": 0.8586, "step": 1650 }, { "epoch": 0.38, "learning_rate": 9.99964494456624e-05, "loss": 0.905, "step": 1660 }, { "epoch": 0.38, "learning_rate": 9.999640653956457e-05, "loss": 0.9028, "step": 1670 }, { "epoch": 0.38, "learning_rate": 9.999636337578483e-05, "loss": 0.9325, "step": 1680 }, { "epoch": 0.39, "learning_rate": 9.999631995432341e-05, "loss": 0.8536, "step": 1690 }, { "epoch": 0.39, "learning_rate": 9.999627627518056e-05, "loss": 0.9031, "step": 1700 }, { "epoch": 0.39, "learning_rate": 9.999623233835648e-05, "loss": 0.9176, "step": 1710 }, { "epoch": 0.39, "learning_rate": 9.999618814385139e-05, "loss": 0.8884, "step": 1720 }, { "epoch": 0.4, "learning_rate": 9.999614369166554e-05, "loss": 0.9658, "step": 1730 }, { "epoch": 0.4, "learning_rate": 9.999609898179914e-05, "loss": 0.948, "step": 1740 }, { "epoch": 0.4, "learning_rate": 9.999605401425243e-05, "loss": 0.8982, "step": 1750 }, { "epoch": 0.4, "learning_rate": 9.999600878902564e-05, "loss": 0.9139, "step": 1760 }, { "epoch": 0.4, "learning_rate": 9.9995963306119e-05, "loss": 0.9163, "step": 1770 }, { "epoch": 0.41, "learning_rate": 9.999591756553274e-05, "loss": 0.899, "step": 1780 }, { "epoch": 0.41, "learning_rate": 9.999587156726712e-05, "loss": 0.9232, "step": 1790 }, { "epoch": 0.41, "learning_rate": 9.999582531132234e-05, "loss": 0.9488, "step": 1800 }, { "epoch": 0.41, "learning_rate": 9.999577879769867e-05, "loss": 0.9263, "step": 1810 }, { "epoch": 0.42, "learning_rate": 9.999573202639635e-05, "loss": 0.9057, "step": 1820 }, { "epoch": 0.42, "learning_rate": 9.999568499741561e-05, "loss": 0.9651, "step": 1830 }, { "epoch": 0.42, "learning_rate": 9.999563771075666e-05, "loss": 0.9794, "step": 1840 }, { "epoch": 0.42, "learning_rate": 9.99955901664198e-05, "loss": 0.9089, "step": 1850 }, { "epoch": 0.43, "learning_rate": 9.999554236440525e-05, "loss": 0.926, "step": 1860 }, { "epoch": 0.43, "learning_rate": 9.999549430471324e-05, "loss": 0.8919, "step": 1870 }, { "epoch": 0.43, "learning_rate": 9.999544598734405e-05, "loss": 0.9036, "step": 1880 }, { "epoch": 0.43, "learning_rate": 9.999539741229792e-05, "loss": 0.9279, "step": 1890 }, { "epoch": 0.43, "learning_rate": 9.999534857957508e-05, "loss": 0.9101, "step": 1900 }, { "epoch": 0.44, "learning_rate": 9.99952994891758e-05, "loss": 0.9368, "step": 1910 }, { "epoch": 0.44, "learning_rate": 9.999525014110033e-05, "loss": 0.9039, "step": 1920 }, { "epoch": 0.44, "learning_rate": 9.999520053534893e-05, "loss": 0.8974, "step": 1930 }, { "epoch": 0.44, "learning_rate": 9.999515067192182e-05, "loss": 0.9099, "step": 1940 }, { "epoch": 0.45, "learning_rate": 9.99951005508193e-05, "loss": 0.9421, "step": 1950 }, { "epoch": 0.45, "learning_rate": 9.999505017204163e-05, "loss": 0.8952, "step": 1960 }, { "epoch": 0.45, "learning_rate": 9.999499953558904e-05, "loss": 0.898, "step": 1970 }, { "epoch": 0.45, "learning_rate": 9.999494864146182e-05, "loss": 0.8342, "step": 1980 }, { "epoch": 0.45, "learning_rate": 9.99948974896602e-05, "loss": 0.947, "step": 1990 }, { "epoch": 0.46, "learning_rate": 9.999484608018446e-05, "loss": 0.9448, "step": 2000 }, { "epoch": 0.46, "learning_rate": 9.999479441303486e-05, "loss": 0.9414, "step": 2010 }, { "epoch": 0.46, "learning_rate": 9.999474248821169e-05, "loss": 0.9656, "step": 2020 }, { "epoch": 0.46, "learning_rate": 9.999469030571518e-05, "loss": 0.8775, "step": 2030 }, { "epoch": 0.47, "learning_rate": 9.999463786554564e-05, "loss": 0.9557, "step": 2040 }, { "epoch": 0.47, "learning_rate": 9.99945851677033e-05, "loss": 0.9158, "step": 2050 }, { "epoch": 0.47, "learning_rate": 9.999453221218847e-05, "loss": 0.9296, "step": 2060 }, { "epoch": 0.47, "learning_rate": 9.999447899900138e-05, "loss": 0.9388, "step": 2070 }, { "epoch": 0.48, "learning_rate": 9.999442552814234e-05, "loss": 0.906, "step": 2080 }, { "epoch": 0.48, "learning_rate": 9.999437179961162e-05, "loss": 0.9136, "step": 2090 }, { "epoch": 0.48, "learning_rate": 9.999431781340947e-05, "loss": 0.8913, "step": 2100 }, { "epoch": 0.48, "learning_rate": 9.999426356953621e-05, "loss": 0.9012, "step": 2110 }, { "epoch": 0.48, "learning_rate": 9.999420906799209e-05, "loss": 0.8775, "step": 2120 }, { "epoch": 0.49, "learning_rate": 9.999415430877739e-05, "loss": 0.9137, "step": 2130 }, { "epoch": 0.49, "learning_rate": 9.99940992918924e-05, "loss": 0.9057, "step": 2140 }, { "epoch": 0.49, "learning_rate": 9.99940440173374e-05, "loss": 0.9077, "step": 2150 }, { "epoch": 0.49, "learning_rate": 9.99939884851127e-05, "loss": 0.9068, "step": 2160 }, { "epoch": 0.5, "learning_rate": 9.999393269521855e-05, "loss": 0.9126, "step": 2170 }, { "epoch": 0.5, "learning_rate": 9.999387664765525e-05, "loss": 0.9153, "step": 2180 }, { "epoch": 0.5, "learning_rate": 9.99938203424231e-05, "loss": 0.8709, "step": 2190 }, { "epoch": 0.5, "learning_rate": 9.999376377952239e-05, "loss": 0.9237, "step": 2200 }, { "epoch": 0.51, "learning_rate": 9.99937069589534e-05, "loss": 0.9036, "step": 2210 }, { "epoch": 0.51, "learning_rate": 9.999364988071642e-05, "loss": 0.8542, "step": 2220 }, { "epoch": 0.51, "learning_rate": 9.999359254481175e-05, "loss": 0.9437, "step": 2230 }, { "epoch": 0.51, "learning_rate": 9.999353495123968e-05, "loss": 0.9223, "step": 2240 }, { "epoch": 0.51, "learning_rate": 9.999347710000053e-05, "loss": 0.9034, "step": 2250 }, { "epoch": 0.52, "learning_rate": 9.999341899109458e-05, "loss": 0.9488, "step": 2260 }, { "epoch": 0.52, "learning_rate": 9.999336062452211e-05, "loss": 0.9015, "step": 2270 }, { "epoch": 0.52, "learning_rate": 9.999330200028347e-05, "loss": 0.9216, "step": 2280 }, { "epoch": 0.52, "learning_rate": 9.99932431183789e-05, "loss": 0.9231, "step": 2290 }, { "epoch": 0.53, "learning_rate": 9.999318397880877e-05, "loss": 0.8536, "step": 2300 }, { "epoch": 0.53, "learning_rate": 9.999312458157333e-05, "loss": 0.9048, "step": 2310 }, { "epoch": 0.53, "learning_rate": 9.999306492667291e-05, "loss": 0.9032, "step": 2320 }, { "epoch": 0.53, "learning_rate": 9.999300501410784e-05, "loss": 0.9249, "step": 2330 }, { "epoch": 0.53, "learning_rate": 9.999294484387838e-05, "loss": 0.9214, "step": 2340 }, { "epoch": 0.54, "learning_rate": 9.999288441598487e-05, "loss": 0.9116, "step": 2350 }, { "epoch": 0.54, "learning_rate": 9.99928237304276e-05, "loss": 0.9405, "step": 2360 }, { "epoch": 0.54, "learning_rate": 9.999276278720693e-05, "loss": 0.9073, "step": 2370 }, { "epoch": 0.54, "learning_rate": 9.999270158632312e-05, "loss": 0.9196, "step": 2380 }, { "epoch": 0.55, "learning_rate": 9.999264012777651e-05, "loss": 0.9104, "step": 2390 }, { "epoch": 0.55, "learning_rate": 9.999257841156742e-05, "loss": 0.9139, "step": 2400 }, { "epoch": 0.55, "learning_rate": 9.999251643769617e-05, "loss": 0.9414, "step": 2410 }, { "epoch": 0.55, "learning_rate": 9.999245420616307e-05, "loss": 0.9327, "step": 2420 }, { "epoch": 0.56, "learning_rate": 9.999239171696843e-05, "loss": 0.9118, "step": 2430 }, { "epoch": 0.56, "learning_rate": 9.999232897011259e-05, "loss": 0.9223, "step": 2440 }, { "epoch": 0.56, "learning_rate": 9.999226596559587e-05, "loss": 0.9018, "step": 2450 }, { "epoch": 0.56, "learning_rate": 9.99922027034186e-05, "loss": 0.8514, "step": 2460 }, { "epoch": 0.56, "learning_rate": 9.99921391835811e-05, "loss": 0.8887, "step": 2470 }, { "epoch": 0.57, "learning_rate": 9.999207540608368e-05, "loss": 0.927, "step": 2480 }, { "epoch": 0.57, "learning_rate": 9.99920113709267e-05, "loss": 0.8757, "step": 2490 }, { "epoch": 0.57, "learning_rate": 9.999194707811049e-05, "loss": 0.9157, "step": 2500 }, { "epoch": 0.57, "learning_rate": 9.999188252763533e-05, "loss": 0.8759, "step": 2510 }, { "epoch": 0.58, "learning_rate": 9.999181771950161e-05, "loss": 0.8801, "step": 2520 }, { "epoch": 0.58, "learning_rate": 9.999175265370966e-05, "loss": 0.9036, "step": 2530 }, { "epoch": 0.58, "learning_rate": 9.999168733025978e-05, "loss": 0.9092, "step": 2540 }, { "epoch": 0.58, "learning_rate": 9.999162174915232e-05, "loss": 0.8954, "step": 2550 }, { "epoch": 0.59, "learning_rate": 9.999155591038764e-05, "loss": 0.943, "step": 2560 }, { "epoch": 0.59, "learning_rate": 9.999148981396604e-05, "loss": 0.8684, "step": 2570 }, { "epoch": 0.59, "learning_rate": 9.99914234598879e-05, "loss": 0.9472, "step": 2580 }, { "epoch": 0.59, "learning_rate": 9.999135684815355e-05, "loss": 0.919, "step": 2590 }, { "epoch": 0.59, "learning_rate": 9.999128997876333e-05, "loss": 0.8902, "step": 2600 }, { "epoch": 0.6, "learning_rate": 9.999122285171756e-05, "loss": 0.885, "step": 2610 }, { "epoch": 0.6, "learning_rate": 9.999115546701663e-05, "loss": 0.9661, "step": 2620 }, { "epoch": 0.6, "learning_rate": 9.999108782466087e-05, "loss": 0.8836, "step": 2630 }, { "epoch": 0.6, "learning_rate": 9.99910199246506e-05, "loss": 0.9266, "step": 2640 }, { "epoch": 0.61, "learning_rate": 9.999095176698622e-05, "loss": 0.975, "step": 2650 }, { "epoch": 0.61, "learning_rate": 9.999088335166807e-05, "loss": 0.8988, "step": 2660 }, { "epoch": 0.61, "learning_rate": 9.999081467869645e-05, "loss": 0.86, "step": 2670 }, { "epoch": 0.61, "learning_rate": 9.999074574807179e-05, "loss": 0.9169, "step": 2680 }, { "epoch": 0.61, "learning_rate": 9.999067655979438e-05, "loss": 0.9233, "step": 2690 }, { "epoch": 0.62, "learning_rate": 9.99906071138646e-05, "loss": 0.9374, "step": 2700 }, { "epoch": 0.62, "learning_rate": 9.999053741028284e-05, "loss": 0.903, "step": 2710 }, { "epoch": 0.62, "learning_rate": 9.999046744904944e-05, "loss": 0.905, "step": 2720 }, { "epoch": 0.62, "learning_rate": 9.999039723016472e-05, "loss": 0.8876, "step": 2730 }, { "epoch": 0.63, "learning_rate": 9.999032675362909e-05, "loss": 0.9123, "step": 2740 }, { "epoch": 0.63, "learning_rate": 9.999025601944289e-05, "loss": 0.9059, "step": 2750 }, { "epoch": 0.63, "learning_rate": 9.999018502760651e-05, "loss": 0.9272, "step": 2760 }, { "epoch": 0.63, "learning_rate": 9.999011377812029e-05, "loss": 0.9099, "step": 2770 }, { "epoch": 0.64, "learning_rate": 9.99900422709846e-05, "loss": 0.9066, "step": 2780 }, { "epoch": 0.64, "learning_rate": 9.998997050619983e-05, "loss": 0.8661, "step": 2790 }, { "epoch": 0.64, "learning_rate": 9.99898984837663e-05, "loss": 0.8913, "step": 2800 }, { "epoch": 0.64, "learning_rate": 9.998982620368444e-05, "loss": 0.897, "step": 2810 }, { "epoch": 0.64, "learning_rate": 9.99897536659546e-05, "loss": 0.9248, "step": 2820 }, { "epoch": 0.65, "learning_rate": 9.998968087057716e-05, "loss": 0.9206, "step": 2830 }, { "epoch": 0.65, "learning_rate": 9.998960781755247e-05, "loss": 0.9235, "step": 2840 }, { "epoch": 0.65, "learning_rate": 9.998953450688093e-05, "loss": 0.9431, "step": 2850 }, { "epoch": 0.65, "learning_rate": 9.99894609385629e-05, "loss": 0.8741, "step": 2860 }, { "epoch": 0.66, "learning_rate": 9.998938711259879e-05, "loss": 0.8884, "step": 2870 }, { "epoch": 0.66, "learning_rate": 9.998931302898895e-05, "loss": 0.9077, "step": 2880 }, { "epoch": 0.66, "learning_rate": 9.998923868773378e-05, "loss": 0.8742, "step": 2890 }, { "epoch": 0.66, "learning_rate": 9.998916408883365e-05, "loss": 0.8534, "step": 2900 }, { "epoch": 0.66, "learning_rate": 9.998908923228894e-05, "loss": 0.8841, "step": 2910 }, { "epoch": 0.67, "learning_rate": 9.998901411810006e-05, "loss": 0.8976, "step": 2920 }, { "epoch": 0.67, "learning_rate": 9.998893874626739e-05, "loss": 0.8897, "step": 2930 }, { "epoch": 0.67, "learning_rate": 9.998886311679129e-05, "loss": 0.8944, "step": 2940 }, { "epoch": 0.67, "learning_rate": 9.998878722967218e-05, "loss": 0.9033, "step": 2950 }, { "epoch": 0.68, "learning_rate": 9.998871108491044e-05, "loss": 0.8688, "step": 2960 }, { "epoch": 0.68, "learning_rate": 9.998863468250648e-05, "loss": 0.9118, "step": 2970 }, { "epoch": 0.68, "learning_rate": 9.998855802246068e-05, "loss": 0.842, "step": 2980 }, { "epoch": 0.68, "learning_rate": 9.998848110477342e-05, "loss": 0.912, "step": 2990 }, { "epoch": 0.69, "learning_rate": 9.99884039294451e-05, "loss": 0.8875, "step": 3000 }, { "epoch": 0.69, "learning_rate": 9.998832649647616e-05, "loss": 0.8913, "step": 3010 }, { "epoch": 0.69, "learning_rate": 9.998824880586695e-05, "loss": 0.8801, "step": 3020 }, { "epoch": 0.69, "learning_rate": 9.998817085761788e-05, "loss": 0.9308, "step": 3030 }, { "epoch": 0.69, "learning_rate": 9.998809265172937e-05, "loss": 0.8984, "step": 3040 }, { "epoch": 0.7, "learning_rate": 9.998801418820181e-05, "loss": 0.9104, "step": 3050 }, { "epoch": 0.7, "learning_rate": 9.99879354670356e-05, "loss": 0.9067, "step": 3060 }, { "epoch": 0.7, "learning_rate": 9.998785648823117e-05, "loss": 0.8939, "step": 3070 }, { "epoch": 0.7, "learning_rate": 9.99877772517889e-05, "loss": 0.8851, "step": 3080 }, { "epoch": 0.71, "learning_rate": 9.99876977577092e-05, "loss": 0.9408, "step": 3090 }, { "epoch": 0.71, "learning_rate": 9.99876180059925e-05, "loss": 0.8919, "step": 3100 }, { "epoch": 0.71, "learning_rate": 9.99875379966392e-05, "loss": 0.8791, "step": 3110 }, { "epoch": 0.71, "learning_rate": 9.99874577296497e-05, "loss": 0.8728, "step": 3120 }, { "epoch": 0.72, "learning_rate": 9.998737720502443e-05, "loss": 0.9315, "step": 3130 }, { "epoch": 0.72, "learning_rate": 9.99872964227638e-05, "loss": 0.8702, "step": 3140 }, { "epoch": 0.72, "learning_rate": 9.998721538286824e-05, "loss": 0.8938, "step": 3150 }, { "epoch": 0.72, "learning_rate": 9.998713408533813e-05, "loss": 0.8678, "step": 3160 }, { "epoch": 0.72, "learning_rate": 9.998705253017393e-05, "loss": 0.8977, "step": 3170 }, { "epoch": 0.73, "learning_rate": 9.998697071737604e-05, "loss": 0.8681, "step": 3180 }, { "epoch": 0.73, "learning_rate": 9.998688864694489e-05, "loss": 0.9145, "step": 3190 }, { "epoch": 0.73, "learning_rate": 9.998680631888089e-05, "loss": 0.8982, "step": 3200 }, { "epoch": 0.73, "learning_rate": 9.998672373318447e-05, "loss": 0.9323, "step": 3210 }, { "epoch": 0.74, "learning_rate": 9.998664088985607e-05, "loss": 0.8398, "step": 3220 }, { "epoch": 0.74, "learning_rate": 9.99865577888961e-05, "loss": 0.919, "step": 3230 }, { "epoch": 0.74, "learning_rate": 9.998647443030498e-05, "loss": 0.9493, "step": 3240 }, { "epoch": 0.74, "learning_rate": 9.998639081408316e-05, "loss": 0.8655, "step": 3250 }, { "epoch": 0.74, "learning_rate": 9.998630694023107e-05, "loss": 0.8851, "step": 3260 }, { "epoch": 0.75, "learning_rate": 9.998622280874914e-05, "loss": 0.9408, "step": 3270 }, { "epoch": 0.75, "learning_rate": 9.99861384196378e-05, "loss": 0.8967, "step": 3280 }, { "epoch": 0.75, "learning_rate": 9.998605377289747e-05, "loss": 0.8948, "step": 3290 }, { "epoch": 0.75, "learning_rate": 9.998596886852862e-05, "loss": 0.9043, "step": 3300 }, { "epoch": 0.76, "learning_rate": 9.998588370653164e-05, "loss": 0.8692, "step": 3310 }, { "epoch": 0.76, "learning_rate": 9.998579828690702e-05, "loss": 0.9388, "step": 3320 }, { "epoch": 0.76, "learning_rate": 9.998571260965518e-05, "loss": 0.8692, "step": 3330 }, { "epoch": 0.76, "learning_rate": 9.998562667477655e-05, "loss": 0.8925, "step": 3340 }, { "epoch": 0.77, "learning_rate": 9.998554048227158e-05, "loss": 0.8646, "step": 3350 }, { "epoch": 0.77, "learning_rate": 9.998545403214073e-05, "loss": 0.8813, "step": 3360 }, { "epoch": 0.77, "learning_rate": 9.998536732438441e-05, "loss": 0.8936, "step": 3370 }, { "epoch": 0.77, "learning_rate": 9.998528035900312e-05, "loss": 0.9199, "step": 3380 }, { "epoch": 0.77, "learning_rate": 9.998519313599725e-05, "loss": 0.969, "step": 3390 }, { "epoch": 0.78, "learning_rate": 9.99851056553673e-05, "loss": 0.909, "step": 3400 }, { "epoch": 0.78, "learning_rate": 9.998501791711367e-05, "loss": 0.8941, "step": 3410 }, { "epoch": 0.78, "learning_rate": 9.998492992123685e-05, "loss": 0.8766, "step": 3420 }, { "epoch": 0.78, "learning_rate": 9.998484166773729e-05, "loss": 0.9126, "step": 3430 }, { "epoch": 0.79, "learning_rate": 9.998475315661544e-05, "loss": 0.8826, "step": 3440 }, { "epoch": 0.79, "learning_rate": 9.998466438787176e-05, "loss": 0.9247, "step": 3450 }, { "epoch": 0.79, "learning_rate": 9.99845753615067e-05, "loss": 0.9223, "step": 3460 }, { "epoch": 0.79, "learning_rate": 9.99844860775207e-05, "loss": 0.8961, "step": 3470 }, { "epoch": 0.8, "learning_rate": 9.998439653591425e-05, "loss": 0.8728, "step": 3480 }, { "epoch": 0.8, "learning_rate": 9.998430673668782e-05, "loss": 0.972, "step": 3490 }, { "epoch": 0.8, "learning_rate": 9.998421667984183e-05, "loss": 0.8998, "step": 3500 }, { "epoch": 0.8, "learning_rate": 9.998412636537679e-05, "loss": 0.8666, "step": 3510 }, { "epoch": 0.8, "learning_rate": 9.998403579329313e-05, "loss": 0.8897, "step": 3520 }, { "epoch": 0.81, "learning_rate": 9.998394496359134e-05, "loss": 0.863, "step": 3530 }, { "epoch": 0.81, "learning_rate": 9.998385387627188e-05, "loss": 0.8904, "step": 3540 }, { "epoch": 0.81, "learning_rate": 9.998376253133522e-05, "loss": 0.8967, "step": 3550 }, { "epoch": 0.81, "learning_rate": 9.998367092878182e-05, "loss": 0.8755, "step": 3560 }, { "epoch": 0.82, "learning_rate": 9.998357906861217e-05, "loss": 0.9406, "step": 3570 }, { "epoch": 0.82, "learning_rate": 9.998348695082673e-05, "loss": 0.8802, "step": 3580 }, { "epoch": 0.82, "learning_rate": 9.998339457542598e-05, "loss": 0.8725, "step": 3590 }, { "epoch": 0.82, "learning_rate": 9.998330194241041e-05, "loss": 0.8742, "step": 3600 }, { "epoch": 0.82, "learning_rate": 9.998320905178047e-05, "loss": 0.8802, "step": 3610 }, { "epoch": 0.83, "learning_rate": 9.998311590353667e-05, "loss": 0.8743, "step": 3620 }, { "epoch": 0.83, "learning_rate": 9.998302249767945e-05, "loss": 0.8448, "step": 3630 }, { "epoch": 0.83, "learning_rate": 9.998292883420933e-05, "loss": 0.8396, "step": 3640 }, { "epoch": 0.83, "learning_rate": 9.998283491312677e-05, "loss": 0.8859, "step": 3650 }, { "epoch": 0.84, "learning_rate": 9.998274073443227e-05, "loss": 0.8699, "step": 3660 }, { "epoch": 0.84, "learning_rate": 9.998264629812631e-05, "loss": 0.8829, "step": 3670 }, { "epoch": 0.84, "learning_rate": 9.998255160420935e-05, "loss": 0.9115, "step": 3680 }, { "epoch": 0.84, "learning_rate": 9.998245665268192e-05, "loss": 0.9004, "step": 3690 }, { "epoch": 0.85, "learning_rate": 9.998236144354449e-05, "loss": 0.883, "step": 3700 }, { "epoch": 0.85, "learning_rate": 9.998226597679755e-05, "loss": 0.8622, "step": 3710 }, { "epoch": 0.85, "learning_rate": 9.998217025244159e-05, "loss": 0.8746, "step": 3720 }, { "epoch": 0.85, "learning_rate": 9.99820742704771e-05, "loss": 0.8608, "step": 3730 }, { "epoch": 0.85, "learning_rate": 9.998197803090459e-05, "loss": 0.875, "step": 3740 }, { "epoch": 0.86, "learning_rate": 9.998188153372455e-05, "loss": 0.9134, "step": 3750 }, { "epoch": 0.86, "learning_rate": 9.998178477893746e-05, "loss": 0.8691, "step": 3760 }, { "epoch": 0.86, "learning_rate": 9.998168776654385e-05, "loss": 0.8933, "step": 3770 }, { "epoch": 0.86, "learning_rate": 9.998159049654419e-05, "loss": 0.8918, "step": 3780 }, { "epoch": 0.87, "learning_rate": 9.9981492968939e-05, "loss": 0.8778, "step": 3790 }, { "epoch": 0.87, "learning_rate": 9.998139518372879e-05, "loss": 0.8395, "step": 3800 }, { "epoch": 0.87, "learning_rate": 9.998129714091404e-05, "loss": 0.8957, "step": 3810 }, { "epoch": 0.87, "learning_rate": 9.998119884049526e-05, "loss": 0.9129, "step": 3820 }, { "epoch": 0.88, "learning_rate": 9.998110028247299e-05, "loss": 0.8748, "step": 3830 }, { "epoch": 0.88, "learning_rate": 9.998100146684768e-05, "loss": 0.8755, "step": 3840 }, { "epoch": 0.88, "learning_rate": 9.998090239361989e-05, "loss": 0.8735, "step": 3850 }, { "epoch": 0.88, "learning_rate": 9.99808030627901e-05, "loss": 0.8683, "step": 3860 }, { "epoch": 0.88, "learning_rate": 9.998070347435884e-05, "loss": 0.8689, "step": 3870 }, { "epoch": 0.89, "learning_rate": 9.99806036283266e-05, "loss": 0.9083, "step": 3880 }, { "epoch": 0.89, "learning_rate": 9.998050352469393e-05, "loss": 0.8497, "step": 3890 }, { "epoch": 0.89, "learning_rate": 9.998040316346133e-05, "loss": 0.8654, "step": 3900 }, { "epoch": 0.89, "learning_rate": 9.998030254462931e-05, "loss": 0.8817, "step": 3910 }, { "epoch": 0.9, "learning_rate": 9.998020166819838e-05, "loss": 0.9353, "step": 3920 }, { "epoch": 0.9, "learning_rate": 9.998010053416909e-05, "loss": 0.9114, "step": 3930 }, { "epoch": 0.9, "learning_rate": 9.997999914254192e-05, "loss": 0.91, "step": 3940 }, { "epoch": 0.9, "learning_rate": 9.997989749331744e-05, "loss": 0.9312, "step": 3950 }, { "epoch": 0.9, "learning_rate": 9.997979558649615e-05, "loss": 0.8445, "step": 3960 }, { "epoch": 0.91, "learning_rate": 9.997969342207857e-05, "loss": 0.9138, "step": 3970 }, { "epoch": 0.91, "learning_rate": 9.997959100006524e-05, "loss": 0.9203, "step": 3980 }, { "epoch": 0.91, "learning_rate": 9.997948832045667e-05, "loss": 0.856, "step": 3990 }, { "epoch": 0.91, "learning_rate": 9.99793853832534e-05, "loss": 0.8805, "step": 4000 }, { "epoch": 0.92, "learning_rate": 9.997928218845596e-05, "loss": 0.8733, "step": 4010 }, { "epoch": 0.92, "learning_rate": 9.997917873606489e-05, "loss": 0.8573, "step": 4020 }, { "epoch": 0.92, "learning_rate": 9.99790750260807e-05, "loss": 0.8679, "step": 4030 }, { "epoch": 0.92, "learning_rate": 9.997897105850395e-05, "loss": 0.8581, "step": 4040 }, { "epoch": 0.93, "learning_rate": 9.997886683333516e-05, "loss": 0.8454, "step": 4050 }, { "epoch": 0.93, "learning_rate": 9.997876235057489e-05, "loss": 0.8849, "step": 4060 }, { "epoch": 0.93, "learning_rate": 9.997865761022364e-05, "loss": 0.8165, "step": 4070 }, { "epoch": 0.93, "learning_rate": 9.997855261228197e-05, "loss": 0.9359, "step": 4080 }, { "epoch": 0.93, "learning_rate": 9.997844735675044e-05, "loss": 0.8847, "step": 4090 }, { "epoch": 0.94, "learning_rate": 9.997834184362956e-05, "loss": 0.8557, "step": 4100 }, { "epoch": 0.94, "learning_rate": 9.997823607291989e-05, "loss": 0.8849, "step": 4110 }, { "epoch": 0.94, "learning_rate": 9.997813004462197e-05, "loss": 0.8974, "step": 4120 }, { "epoch": 0.94, "learning_rate": 9.997802375873636e-05, "loss": 0.8666, "step": 4130 }, { "epoch": 0.95, "learning_rate": 9.997791721526359e-05, "loss": 0.8835, "step": 4140 }, { "epoch": 0.95, "learning_rate": 9.997781041420422e-05, "loss": 0.8879, "step": 4150 }, { "epoch": 0.95, "learning_rate": 9.997770335555881e-05, "loss": 0.8316, "step": 4160 }, { "epoch": 1.0, "learning_rate": 9.997759603932789e-05, "loss": 0.8529, "step": 4170 }, { "epoch": 1.0, "learning_rate": 9.997748846551201e-05, "loss": 0.8793, "step": 4180 }, { "epoch": 1.01, "learning_rate": 9.997738063411175e-05, "loss": 0.8772, "step": 4190 }, { "epoch": 1.01, "learning_rate": 9.997727254512766e-05, "loss": 0.8398, "step": 4200 }, { "epoch": 1.01, "learning_rate": 9.997716419856027e-05, "loss": 0.8608, "step": 4210 }, { "epoch": 1.01, "learning_rate": 9.997705559441017e-05, "loss": 0.8268, "step": 4220 }, { "epoch": 1.02, "learning_rate": 9.99769467326779e-05, "loss": 0.8363, "step": 4230 }, { "epoch": 1.02, "learning_rate": 9.997683761336402e-05, "loss": 0.8447, "step": 4240 }, { "epoch": 1.02, "learning_rate": 9.997672823646913e-05, "loss": 0.8433, "step": 4250 }, { "epoch": 1.02, "learning_rate": 9.997661860199375e-05, "loss": 0.8528, "step": 4260 }, { "epoch": 1.02, "learning_rate": 9.997650870993847e-05, "loss": 0.9161, "step": 4270 }, { "epoch": 1.03, "learning_rate": 9.997639856030383e-05, "loss": 0.8634, "step": 4280 }, { "epoch": 1.03, "learning_rate": 9.997628815309041e-05, "loss": 0.8938, "step": 4290 }, { "epoch": 1.03, "learning_rate": 9.997617748829879e-05, "loss": 0.8944, "step": 4300 }, { "epoch": 1.03, "learning_rate": 9.997606656592955e-05, "loss": 0.894, "step": 4310 }, { "epoch": 1.04, "learning_rate": 9.997595538598323e-05, "loss": 0.9043, "step": 4320 }, { "epoch": 1.04, "learning_rate": 9.997584394846041e-05, "loss": 0.8803, "step": 4330 }, { "epoch": 1.04, "learning_rate": 9.997573225336168e-05, "loss": 0.9056, "step": 4340 }, { "epoch": 1.04, "learning_rate": 9.997562030068761e-05, "loss": 0.9119, "step": 4350 }, { "epoch": 1.05, "learning_rate": 9.997550809043879e-05, "loss": 0.8629, "step": 4360 }, { "epoch": 1.05, "learning_rate": 9.997539562261577e-05, "loss": 0.8621, "step": 4370 }, { "epoch": 1.05, "learning_rate": 9.997528289721914e-05, "loss": 0.8833, "step": 4380 }, { "epoch": 1.05, "learning_rate": 9.997516991424949e-05, "loss": 0.8499, "step": 4390 }, { "epoch": 1.05, "learning_rate": 9.997505667370738e-05, "loss": 0.8356, "step": 4400 }, { "epoch": 1.06, "learning_rate": 9.997494317559343e-05, "loss": 0.8614, "step": 4410 }, { "epoch": 1.06, "learning_rate": 9.99748294199082e-05, "loss": 0.8869, "step": 4420 }, { "epoch": 1.06, "learning_rate": 9.997471540665228e-05, "loss": 0.8998, "step": 4430 }, { "epoch": 1.06, "learning_rate": 9.997460113582626e-05, "loss": 0.8342, "step": 4440 }, { "epoch": 1.07, "learning_rate": 9.997448660743072e-05, "loss": 0.8453, "step": 4450 }, { "epoch": 1.07, "learning_rate": 9.997437182146628e-05, "loss": 0.8443, "step": 4460 }, { "epoch": 1.07, "learning_rate": 9.997425677793349e-05, "loss": 0.8896, "step": 4470 }, { "epoch": 1.07, "learning_rate": 9.997414147683298e-05, "loss": 0.8434, "step": 4480 }, { "epoch": 1.07, "learning_rate": 9.99740259181653e-05, "loss": 0.8775, "step": 4490 }, { "epoch": 1.08, "learning_rate": 9.997391010193109e-05, "loss": 0.8689, "step": 4500 }, { "epoch": 1.08, "learning_rate": 9.997379402813092e-05, "loss": 0.9076, "step": 4510 }, { "epoch": 1.08, "learning_rate": 9.99736776967654e-05, "loss": 0.9018, "step": 4520 }, { "epoch": 1.08, "learning_rate": 9.997356110783515e-05, "loss": 0.8304, "step": 4530 }, { "epoch": 1.09, "learning_rate": 9.997344426134071e-05, "loss": 0.8892, "step": 4540 }, { "epoch": 1.09, "learning_rate": 9.997332715728276e-05, "loss": 0.8328, "step": 4550 }, { "epoch": 1.09, "learning_rate": 9.997320979566185e-05, "loss": 0.8991, "step": 4560 }, { "epoch": 1.09, "learning_rate": 9.99730921764786e-05, "loss": 0.8739, "step": 4570 }, { "epoch": 1.1, "learning_rate": 9.997297429973361e-05, "loss": 0.8612, "step": 4580 }, { "epoch": 1.1, "learning_rate": 9.997285616542749e-05, "loss": 0.8473, "step": 4590 }, { "epoch": 1.1, "learning_rate": 9.997273777356084e-05, "loss": 0.8739, "step": 4600 }, { "epoch": 1.1, "learning_rate": 9.997261912413431e-05, "loss": 0.8453, "step": 4610 }, { "epoch": 1.1, "learning_rate": 9.997250021714846e-05, "loss": 0.8598, "step": 4620 }, { "epoch": 1.11, "learning_rate": 9.997238105260394e-05, "loss": 0.8413, "step": 4630 }, { "epoch": 1.11, "learning_rate": 9.997226163050135e-05, "loss": 0.819, "step": 4640 }, { "epoch": 1.11, "learning_rate": 9.99721419508413e-05, "loss": 0.8763, "step": 4650 }, { "epoch": 1.11, "learning_rate": 9.997202201362441e-05, "loss": 0.8927, "step": 4660 }, { "epoch": 1.12, "learning_rate": 9.997190181885131e-05, "loss": 0.845, "step": 4670 }, { "epoch": 1.12, "learning_rate": 9.997178136652261e-05, "loss": 0.8737, "step": 4680 }, { "epoch": 1.12, "learning_rate": 9.997166065663892e-05, "loss": 0.8556, "step": 4690 }, { "epoch": 1.12, "learning_rate": 9.997153968920088e-05, "loss": 0.8542, "step": 4700 }, { "epoch": 1.12, "learning_rate": 9.997141846420911e-05, "loss": 0.9157, "step": 4710 }, { "epoch": 1.13, "learning_rate": 9.997129698166423e-05, "loss": 0.8151, "step": 4720 }, { "epoch": 1.13, "learning_rate": 9.997117524156687e-05, "loss": 0.852, "step": 4730 }, { "epoch": 1.13, "learning_rate": 9.997105324391764e-05, "loss": 0.8552, "step": 4740 }, { "epoch": 1.13, "learning_rate": 9.997093098871721e-05, "loss": 0.8801, "step": 4750 }, { "epoch": 1.14, "learning_rate": 9.997080847596615e-05, "loss": 0.8719, "step": 4760 }, { "epoch": 1.14, "learning_rate": 9.997068570566516e-05, "loss": 0.8813, "step": 4770 }, { "epoch": 1.14, "learning_rate": 9.997056267781482e-05, "loss": 0.9025, "step": 4780 }, { "epoch": 1.14, "learning_rate": 9.997043939241578e-05, "loss": 0.8683, "step": 4790 }, { "epoch": 1.15, "learning_rate": 9.997031584946868e-05, "loss": 0.8538, "step": 4800 }, { "epoch": 1.15, "learning_rate": 9.997019204897417e-05, "loss": 0.8596, "step": 4810 }, { "epoch": 1.15, "learning_rate": 9.997006799093285e-05, "loss": 0.904, "step": 4820 }, { "epoch": 1.15, "learning_rate": 9.99699436753454e-05, "loss": 0.8962, "step": 4830 }, { "epoch": 1.15, "learning_rate": 9.996981910221244e-05, "loss": 0.897, "step": 4840 }, { "epoch": 1.16, "learning_rate": 9.99696942715346e-05, "loss": 0.8443, "step": 4850 }, { "epoch": 1.16, "learning_rate": 9.996956918331255e-05, "loss": 0.8736, "step": 4860 }, { "epoch": 1.16, "learning_rate": 9.996944383754692e-05, "loss": 0.8568, "step": 4870 }, { "epoch": 1.16, "learning_rate": 9.996931823423836e-05, "loss": 0.8723, "step": 4880 }, { "epoch": 1.17, "learning_rate": 9.996919237338752e-05, "loss": 0.8667, "step": 4890 }, { "epoch": 1.17, "learning_rate": 9.996906625499503e-05, "loss": 0.855, "step": 4900 }, { "epoch": 1.17, "learning_rate": 9.996893987906156e-05, "loss": 0.87, "step": 4910 }, { "epoch": 1.17, "learning_rate": 9.996881324558775e-05, "loss": 0.8699, "step": 4920 }, { "epoch": 1.18, "learning_rate": 9.996868635457428e-05, "loss": 0.9046, "step": 4930 }, { "epoch": 1.18, "learning_rate": 9.996855920602177e-05, "loss": 0.8933, "step": 4940 }, { "epoch": 1.18, "learning_rate": 9.99684317999309e-05, "loss": 0.8471, "step": 4950 }, { "epoch": 1.18, "learning_rate": 9.99683041363023e-05, "loss": 0.8965, "step": 4960 }, { "epoch": 1.18, "learning_rate": 9.996817621513666e-05, "loss": 0.881, "step": 4970 }, { "epoch": 1.19, "learning_rate": 9.99680480364346e-05, "loss": 0.8686, "step": 4980 }, { "epoch": 1.19, "learning_rate": 9.996791960019681e-05, "loss": 0.8534, "step": 4990 }, { "epoch": 1.19, "learning_rate": 9.996779090642396e-05, "loss": 0.8628, "step": 5000 }, { "epoch": 1.19, "learning_rate": 9.996766195511667e-05, "loss": 0.8272, "step": 5010 }, { "epoch": 1.2, "learning_rate": 9.996753274627566e-05, "loss": 0.8764, "step": 5020 }, { "epoch": 1.2, "learning_rate": 9.996740327990155e-05, "loss": 0.8594, "step": 5030 }, { "epoch": 1.2, "learning_rate": 9.996727355599504e-05, "loss": 0.8369, "step": 5040 }, { "epoch": 1.2, "learning_rate": 9.996714357455677e-05, "loss": 0.8673, "step": 5050 }, { "epoch": 1.2, "learning_rate": 9.996701333558744e-05, "loss": 0.8713, "step": 5060 }, { "epoch": 1.21, "learning_rate": 9.996688283908768e-05, "loss": 0.8169, "step": 5070 }, { "epoch": 1.21, "learning_rate": 9.996675208505821e-05, "loss": 0.8553, "step": 5080 }, { "epoch": 1.21, "learning_rate": 9.996662107349967e-05, "loss": 0.9007, "step": 5090 }, { "epoch": 1.21, "learning_rate": 9.996648980441277e-05, "loss": 0.8646, "step": 5100 }, { "epoch": 1.22, "learning_rate": 9.996635827779815e-05, "loss": 0.8295, "step": 5110 }, { "epoch": 1.22, "learning_rate": 9.99662264936565e-05, "loss": 0.8435, "step": 5120 }, { "epoch": 1.22, "learning_rate": 9.99660944519885e-05, "loss": 0.8396, "step": 5130 }, { "epoch": 1.22, "learning_rate": 9.996596215279484e-05, "loss": 0.8373, "step": 5140 }, { "epoch": 1.23, "learning_rate": 9.996582959607617e-05, "loss": 0.8687, "step": 5150 }, { "epoch": 1.23, "learning_rate": 9.996569678183322e-05, "loss": 0.8405, "step": 5160 }, { "epoch": 1.23, "learning_rate": 9.996556371006664e-05, "loss": 0.838, "step": 5170 }, { "epoch": 1.23, "learning_rate": 9.996543038077714e-05, "loss": 0.8701, "step": 5180 }, { "epoch": 1.23, "learning_rate": 9.996529679396538e-05, "loss": 0.9067, "step": 5190 }, { "epoch": 1.24, "learning_rate": 9.996516294963207e-05, "loss": 0.8727, "step": 5200 }, { "epoch": 1.24, "learning_rate": 9.996502884777788e-05, "loss": 0.8565, "step": 5210 }, { "epoch": 1.24, "learning_rate": 9.996489448840353e-05, "loss": 0.8565, "step": 5220 }, { "epoch": 1.24, "learning_rate": 9.996475987150969e-05, "loss": 0.8345, "step": 5230 }, { "epoch": 1.25, "learning_rate": 9.996462499709707e-05, "loss": 0.8633, "step": 5240 }, { "epoch": 1.25, "learning_rate": 9.996448986516633e-05, "loss": 0.8301, "step": 5250 }, { "epoch": 1.25, "learning_rate": 9.996435447571821e-05, "loss": 0.8304, "step": 5260 }, { "epoch": 1.25, "learning_rate": 9.99642188287534e-05, "loss": 0.8633, "step": 5270 }, { "epoch": 1.26, "learning_rate": 9.996408292427257e-05, "loss": 0.8835, "step": 5280 }, { "epoch": 1.26, "learning_rate": 9.996394676227644e-05, "loss": 0.8507, "step": 5290 }, { "epoch": 1.26, "learning_rate": 9.996381034276571e-05, "loss": 0.8603, "step": 5300 }, { "epoch": 1.26, "learning_rate": 9.996367366574109e-05, "loss": 0.825, "step": 5310 }, { "epoch": 1.26, "learning_rate": 9.996353673120328e-05, "loss": 0.8663, "step": 5320 }, { "epoch": 1.27, "learning_rate": 9.996339953915297e-05, "loss": 0.8638, "step": 5330 }, { "epoch": 1.27, "learning_rate": 9.996326208959091e-05, "loss": 0.8106, "step": 5340 }, { "epoch": 1.27, "learning_rate": 9.996312438251776e-05, "loss": 0.8815, "step": 5350 }, { "epoch": 1.27, "learning_rate": 9.996298641793425e-05, "loss": 0.8335, "step": 5360 }, { "epoch": 1.28, "learning_rate": 9.996284819584108e-05, "loss": 0.8596, "step": 5370 }, { "epoch": 1.28, "learning_rate": 9.996270971623899e-05, "loss": 0.9, "step": 5380 }, { "epoch": 1.28, "learning_rate": 9.996257097912867e-05, "loss": 0.8749, "step": 5390 }, { "epoch": 1.28, "learning_rate": 9.996243198451084e-05, "loss": 0.8079, "step": 5400 }, { "epoch": 1.28, "learning_rate": 9.996229273238623e-05, "loss": 0.9641, "step": 5410 }, { "epoch": 1.29, "learning_rate": 9.996215322275553e-05, "loss": 0.8382, "step": 5420 }, { "epoch": 1.29, "learning_rate": 9.996201345561947e-05, "loss": 0.8151, "step": 5430 }, { "epoch": 1.29, "learning_rate": 9.996187343097879e-05, "loss": 0.8418, "step": 5440 }, { "epoch": 1.29, "learning_rate": 9.996173314883419e-05, "loss": 0.8402, "step": 5450 }, { "epoch": 1.3, "learning_rate": 9.99615926091864e-05, "loss": 0.8369, "step": 5460 }, { "epoch": 1.3, "learning_rate": 9.996145181203615e-05, "loss": 0.8293, "step": 5470 }, { "epoch": 1.3, "learning_rate": 9.996131075738415e-05, "loss": 0.8598, "step": 5480 }, { "epoch": 1.3, "learning_rate": 9.996116944523115e-05, "loss": 0.8379, "step": 5490 }, { "epoch": 1.31, "learning_rate": 9.996102787557786e-05, "loss": 0.8879, "step": 5500 }, { "epoch": 1.31, "learning_rate": 9.9960886048425e-05, "loss": 0.8273, "step": 5510 }, { "epoch": 1.31, "learning_rate": 9.996074396377333e-05, "loss": 0.8251, "step": 5520 }, { "epoch": 1.31, "learning_rate": 9.996060162162357e-05, "loss": 0.8585, "step": 5530 }, { "epoch": 1.31, "learning_rate": 9.996045902197645e-05, "loss": 0.8325, "step": 5540 }, { "epoch": 1.32, "learning_rate": 9.99603161648327e-05, "loss": 0.8717, "step": 5550 }, { "epoch": 1.32, "learning_rate": 9.996017305019307e-05, "loss": 0.8221, "step": 5560 }, { "epoch": 1.32, "learning_rate": 9.996002967805828e-05, "loss": 0.8062, "step": 5570 }, { "epoch": 1.32, "learning_rate": 9.99598860484291e-05, "loss": 0.8201, "step": 5580 }, { "epoch": 1.33, "learning_rate": 9.995974216130623e-05, "loss": 0.8579, "step": 5590 }, { "epoch": 1.33, "learning_rate": 9.995959801669043e-05, "loss": 0.8158, "step": 5600 }, { "epoch": 1.33, "learning_rate": 9.995945361458246e-05, "loss": 0.8546, "step": 5610 }, { "epoch": 1.33, "learning_rate": 9.995930895498304e-05, "loss": 0.8513, "step": 5620 }, { "epoch": 1.34, "learning_rate": 9.995916403789293e-05, "loss": 0.8908, "step": 5630 }, { "epoch": 1.34, "learning_rate": 9.995901886331286e-05, "loss": 0.8375, "step": 5640 }, { "epoch": 1.34, "learning_rate": 9.99588734312436e-05, "loss": 0.9373, "step": 5650 }, { "epoch": 1.34, "learning_rate": 9.995872774168589e-05, "loss": 0.8164, "step": 5660 }, { "epoch": 1.34, "learning_rate": 9.995858179464047e-05, "loss": 0.8062, "step": 5670 }, { "epoch": 1.35, "learning_rate": 9.995843559010809e-05, "loss": 0.838, "step": 5680 }, { "epoch": 1.35, "learning_rate": 9.995828912808953e-05, "loss": 0.8229, "step": 5690 }, { "epoch": 1.35, "learning_rate": 9.995814240858554e-05, "loss": 0.8511, "step": 5700 }, { "epoch": 1.35, "learning_rate": 9.995799543159686e-05, "loss": 0.8492, "step": 5710 }, { "epoch": 1.36, "learning_rate": 9.995784819712425e-05, "loss": 0.8433, "step": 5720 }, { "epoch": 1.36, "learning_rate": 9.995770070516848e-05, "loss": 0.8528, "step": 5730 }, { "epoch": 1.36, "learning_rate": 9.995755295573028e-05, "loss": 0.8779, "step": 5740 }, { "epoch": 1.36, "learning_rate": 9.995740494881045e-05, "loss": 0.8931, "step": 5750 }, { "epoch": 1.36, "learning_rate": 9.995725668440974e-05, "loss": 0.9011, "step": 5760 }, { "epoch": 1.37, "learning_rate": 9.995710816252892e-05, "loss": 0.8564, "step": 5770 }, { "epoch": 1.37, "learning_rate": 9.995695938316874e-05, "loss": 0.8382, "step": 5780 }, { "epoch": 1.37, "learning_rate": 9.995681034632997e-05, "loss": 0.8168, "step": 5790 }, { "epoch": 1.37, "learning_rate": 9.995666105201338e-05, "loss": 0.868, "step": 5800 }, { "epoch": 1.38, "learning_rate": 9.995651150021975e-05, "loss": 0.8147, "step": 5810 }, { "epoch": 1.38, "learning_rate": 9.995636169094983e-05, "loss": 0.8629, "step": 5820 }, { "epoch": 1.38, "learning_rate": 9.995621162420441e-05, "loss": 0.8362, "step": 5830 }, { "epoch": 1.38, "learning_rate": 9.995606129998424e-05, "loss": 0.8129, "step": 5840 }, { "epoch": 1.39, "learning_rate": 9.995591071829014e-05, "loss": 0.8452, "step": 5850 }, { "epoch": 1.39, "learning_rate": 9.995575987912286e-05, "loss": 0.8704, "step": 5860 }, { "epoch": 1.39, "learning_rate": 9.995560878248315e-05, "loss": 0.8345, "step": 5870 }, { "epoch": 1.39, "learning_rate": 9.995545742837185e-05, "loss": 0.8555, "step": 5880 }, { "epoch": 1.39, "learning_rate": 9.995530581678967e-05, "loss": 0.8355, "step": 5890 }, { "epoch": 1.4, "learning_rate": 9.995515394773744e-05, "loss": 0.8352, "step": 5900 }, { "epoch": 1.4, "learning_rate": 9.995500182121594e-05, "loss": 0.9199, "step": 5910 }, { "epoch": 1.4, "learning_rate": 9.995484943722593e-05, "loss": 0.8436, "step": 5920 }, { "epoch": 1.4, "learning_rate": 9.99546967957682e-05, "loss": 0.8685, "step": 5930 }, { "epoch": 1.41, "learning_rate": 9.995454389684356e-05, "loss": 0.8197, "step": 5940 }, { "epoch": 1.41, "learning_rate": 9.995439074045278e-05, "loss": 0.8119, "step": 5950 }, { "epoch": 1.41, "learning_rate": 9.995423732659666e-05, "loss": 0.8261, "step": 5960 }, { "epoch": 1.41, "learning_rate": 9.995408365527597e-05, "loss": 0.8633, "step": 5970 }, { "epoch": 1.42, "learning_rate": 9.995392972649152e-05, "loss": 0.8674, "step": 5980 }, { "epoch": 1.42, "learning_rate": 9.99537755402441e-05, "loss": 0.8486, "step": 5990 }, { "epoch": 1.42, "learning_rate": 9.995362109653451e-05, "loss": 0.8405, "step": 6000 }, { "epoch": 1.42, "learning_rate": 9.995346639536354e-05, "loss": 0.8491, "step": 6010 }, { "epoch": 1.42, "learning_rate": 9.995331143673196e-05, "loss": 0.8319, "step": 6020 }, { "epoch": 1.43, "learning_rate": 9.995315622064063e-05, "loss": 0.8543, "step": 6030 }, { "epoch": 1.43, "learning_rate": 9.995300074709028e-05, "loss": 0.8073, "step": 6040 }, { "epoch": 1.43, "learning_rate": 9.995284501608177e-05, "loss": 0.8702, "step": 6050 }, { "epoch": 1.43, "learning_rate": 9.995268902761588e-05, "loss": 0.8228, "step": 6060 }, { "epoch": 1.44, "learning_rate": 9.99525327816934e-05, "loss": 0.8834, "step": 6070 }, { "epoch": 1.44, "learning_rate": 9.995237627831517e-05, "loss": 0.8416, "step": 6080 }, { "epoch": 1.44, "learning_rate": 9.995221951748197e-05, "loss": 0.7824, "step": 6090 }, { "epoch": 1.44, "learning_rate": 9.99520624991946e-05, "loss": 0.8283, "step": 6100 }, { "epoch": 1.44, "learning_rate": 9.995190522345387e-05, "loss": 0.8782, "step": 6110 }, { "epoch": 1.45, "learning_rate": 9.995174769026064e-05, "loss": 0.8211, "step": 6120 }, { "epoch": 1.45, "learning_rate": 9.995158989961567e-05, "loss": 0.8254, "step": 6130 }, { "epoch": 1.45, "learning_rate": 9.995143185151979e-05, "loss": 0.8527, "step": 6140 }, { "epoch": 1.45, "learning_rate": 9.99512735459738e-05, "loss": 0.866, "step": 6150 }, { "epoch": 1.46, "learning_rate": 9.995111498297853e-05, "loss": 0.8657, "step": 6160 }, { "epoch": 1.46, "learning_rate": 9.99509561625348e-05, "loss": 0.8441, "step": 6170 }, { "epoch": 1.46, "learning_rate": 9.995079708464342e-05, "loss": 0.8525, "step": 6180 }, { "epoch": 1.46, "learning_rate": 9.995063774930522e-05, "loss": 0.8183, "step": 6190 }, { "epoch": 1.47, "learning_rate": 9.995047815652101e-05, "loss": 0.8551, "step": 6200 }, { "epoch": 1.47, "learning_rate": 9.995031830629162e-05, "loss": 0.833, "step": 6210 }, { "epoch": 1.47, "learning_rate": 9.995015819861788e-05, "loss": 0.8336, "step": 6220 }, { "epoch": 1.47, "learning_rate": 9.99499978335006e-05, "loss": 0.8792, "step": 6230 }, { "epoch": 1.47, "learning_rate": 9.994983721094062e-05, "loss": 0.8439, "step": 6240 }, { "epoch": 1.48, "learning_rate": 9.994967633093876e-05, "loss": 0.8163, "step": 6250 }, { "epoch": 1.48, "learning_rate": 9.994951519349584e-05, "loss": 0.8704, "step": 6260 }, { "epoch": 1.48, "learning_rate": 9.994935379861272e-05, "loss": 0.872, "step": 6270 }, { "epoch": 1.48, "learning_rate": 9.99491921462902e-05, "loss": 0.8044, "step": 6280 }, { "epoch": 1.49, "learning_rate": 9.994903023652913e-05, "loss": 0.8635, "step": 6290 }, { "epoch": 1.49, "learning_rate": 9.994886806933034e-05, "loss": 0.8404, "step": 6300 }, { "epoch": 1.49, "learning_rate": 9.994870564469467e-05, "loss": 0.8004, "step": 6310 }, { "epoch": 1.49, "learning_rate": 9.994854296262295e-05, "loss": 0.881, "step": 6320 }, { "epoch": 1.5, "learning_rate": 9.994838002311602e-05, "loss": 0.8379, "step": 6330 }, { "epoch": 1.5, "learning_rate": 9.994821682617472e-05, "loss": 0.8492, "step": 6340 }, { "epoch": 1.5, "learning_rate": 9.994805337179989e-05, "loss": 0.8424, "step": 6350 }, { "epoch": 1.5, "learning_rate": 9.994788965999237e-05, "loss": 0.8007, "step": 6360 }, { "epoch": 1.5, "learning_rate": 9.994772569075304e-05, "loss": 0.8345, "step": 6370 }, { "epoch": 1.51, "learning_rate": 9.994756146408269e-05, "loss": 0.8269, "step": 6380 }, { "epoch": 1.51, "learning_rate": 9.994739697998218e-05, "loss": 0.8252, "step": 6390 }, { "epoch": 1.51, "learning_rate": 9.99472322384524e-05, "loss": 0.8601, "step": 6400 }, { "epoch": 1.51, "learning_rate": 9.994706723949415e-05, "loss": 0.8386, "step": 6410 }, { "epoch": 1.52, "learning_rate": 9.99469019831083e-05, "loss": 0.8106, "step": 6420 }, { "epoch": 1.52, "learning_rate": 9.99467364692957e-05, "loss": 0.863, "step": 6430 }, { "epoch": 1.52, "learning_rate": 9.994657069805719e-05, "loss": 0.8441, "step": 6440 }, { "epoch": 1.52, "learning_rate": 9.994640466939367e-05, "loss": 0.8825, "step": 6450 }, { "epoch": 1.52, "learning_rate": 9.994623838330593e-05, "loss": 0.7814, "step": 6460 }, { "epoch": 1.53, "learning_rate": 9.994607183979488e-05, "loss": 0.8413, "step": 6470 }, { "epoch": 1.53, "learning_rate": 9.994590503886134e-05, "loss": 0.8641, "step": 6480 }, { "epoch": 1.53, "learning_rate": 9.994573798050619e-05, "loss": 0.8713, "step": 6490 }, { "epoch": 1.53, "learning_rate": 9.994557066473032e-05, "loss": 0.8799, "step": 6500 }, { "epoch": 1.54, "learning_rate": 9.994540309153452e-05, "loss": 0.8423, "step": 6510 }, { "epoch": 1.54, "learning_rate": 9.994523526091972e-05, "loss": 0.8661, "step": 6520 }, { "epoch": 1.54, "learning_rate": 9.994506717288675e-05, "loss": 0.8835, "step": 6530 }, { "epoch": 1.54, "learning_rate": 9.99448988274365e-05, "loss": 0.8627, "step": 6540 }, { "epoch": 1.55, "learning_rate": 9.994473022456981e-05, "loss": 0.8869, "step": 6550 }, { "epoch": 1.55, "learning_rate": 9.994456136428756e-05, "loss": 0.9099, "step": 6560 }, { "epoch": 1.55, "learning_rate": 9.994439224659063e-05, "loss": 0.8861, "step": 6570 }, { "epoch": 1.55, "learning_rate": 9.994422287147989e-05, "loss": 0.9135, "step": 6580 }, { "epoch": 1.55, "learning_rate": 9.994405323895619e-05, "loss": 0.8516, "step": 6590 }, { "epoch": 1.56, "learning_rate": 9.994388334902045e-05, "loss": 0.8658, "step": 6600 }, { "epoch": 1.56, "learning_rate": 9.994371320167349e-05, "loss": 0.8682, "step": 6610 }, { "epoch": 1.56, "learning_rate": 9.994354279691623e-05, "loss": 0.8505, "step": 6620 }, { "epoch": 1.56, "learning_rate": 9.994337213474953e-05, "loss": 0.9026, "step": 6630 }, { "epoch": 1.57, "learning_rate": 9.994320121517427e-05, "loss": 0.9095, "step": 6640 }, { "epoch": 1.57, "learning_rate": 9.994303003819134e-05, "loss": 0.8346, "step": 6650 }, { "epoch": 1.57, "learning_rate": 9.994285860380161e-05, "loss": 0.8227, "step": 6660 }, { "epoch": 1.57, "learning_rate": 9.994268691200597e-05, "loss": 0.8744, "step": 6670 }, { "epoch": 1.58, "learning_rate": 9.994251496280531e-05, "loss": 0.8257, "step": 6680 }, { "epoch": 1.58, "learning_rate": 9.99423427562005e-05, "loss": 0.8554, "step": 6690 }, { "epoch": 1.58, "learning_rate": 9.994217029219246e-05, "loss": 0.9007, "step": 6700 }, { "epoch": 1.58, "learning_rate": 9.994199757078203e-05, "loss": 0.8623, "step": 6710 }, { "epoch": 1.58, "learning_rate": 9.994182459197013e-05, "loss": 0.843, "step": 6720 }, { "epoch": 1.59, "learning_rate": 9.994165135575766e-05, "loss": 0.9187, "step": 6730 }, { "epoch": 1.59, "learning_rate": 9.99414778621455e-05, "loss": 0.8416, "step": 6740 }, { "epoch": 1.59, "learning_rate": 9.994130411113453e-05, "loss": 0.8925, "step": 6750 }, { "epoch": 1.59, "learning_rate": 9.994113010272568e-05, "loss": 0.8936, "step": 6760 }, { "epoch": 1.6, "learning_rate": 9.994095583691982e-05, "loss": 0.8412, "step": 6770 }, { "epoch": 1.6, "learning_rate": 9.994078131371787e-05, "loss": 0.8301, "step": 6780 }, { "epoch": 1.6, "learning_rate": 9.99406065331207e-05, "loss": 0.8158, "step": 6790 }, { "epoch": 1.6, "learning_rate": 9.994043149512924e-05, "loss": 0.8586, "step": 6800 }, { "epoch": 1.6, "learning_rate": 9.994025619974437e-05, "loss": 0.8374, "step": 6810 }, { "epoch": 1.61, "learning_rate": 9.994008064696699e-05, "loss": 0.8633, "step": 6820 }, { "epoch": 1.61, "learning_rate": 9.993990483679802e-05, "loss": 0.8297, "step": 6830 }, { "epoch": 1.61, "learning_rate": 9.993972876923839e-05, "loss": 0.8541, "step": 6840 }, { "epoch": 1.61, "learning_rate": 9.993955244428897e-05, "loss": 0.899, "step": 6850 }, { "epoch": 1.62, "learning_rate": 9.993937586195066e-05, "loss": 0.8665, "step": 6860 }, { "epoch": 1.62, "learning_rate": 9.99391990222244e-05, "loss": 0.8723, "step": 6870 }, { "epoch": 1.62, "learning_rate": 9.993902192511109e-05, "loss": 0.8488, "step": 6880 }, { "epoch": 1.62, "learning_rate": 9.993884457061164e-05, "loss": 0.8809, "step": 6890 }, { "epoch": 1.63, "learning_rate": 9.993866695872698e-05, "loss": 0.8677, "step": 6900 }, { "epoch": 1.63, "learning_rate": 9.9938489089458e-05, "loss": 0.8921, "step": 6910 }, { "epoch": 1.63, "learning_rate": 9.993831096280564e-05, "loss": 0.8738, "step": 6920 }, { "epoch": 1.63, "learning_rate": 9.99381325787708e-05, "loss": 0.9103, "step": 6930 }, { "epoch": 1.63, "learning_rate": 9.993795393735442e-05, "loss": 0.8499, "step": 6940 }, { "epoch": 1.64, "learning_rate": 9.99377750385574e-05, "loss": 0.8133, "step": 6950 }, { "epoch": 1.64, "learning_rate": 9.993759588238066e-05, "loss": 0.799, "step": 6960 }, { "epoch": 1.64, "learning_rate": 9.993741646882514e-05, "loss": 0.8416, "step": 6970 }, { "epoch": 1.64, "learning_rate": 9.993723679789176e-05, "loss": 0.8647, "step": 6980 }, { "epoch": 1.65, "learning_rate": 9.993705686958145e-05, "loss": 0.8777, "step": 6990 }, { "epoch": 1.65, "learning_rate": 9.993687668389513e-05, "loss": 0.8487, "step": 7000 }, { "epoch": 1.65, "learning_rate": 9.993669624083373e-05, "loss": 0.8095, "step": 7010 }, { "epoch": 1.65, "learning_rate": 9.993651554039817e-05, "loss": 0.8131, "step": 7020 }, { "epoch": 1.66, "learning_rate": 9.99363345825894e-05, "loss": 0.8195, "step": 7030 }, { "epoch": 1.66, "learning_rate": 9.993615336740833e-05, "loss": 0.8902, "step": 7040 }, { "epoch": 1.66, "learning_rate": 9.993597189485593e-05, "loss": 0.8367, "step": 7050 }, { "epoch": 1.66, "learning_rate": 9.99357901649331e-05, "loss": 0.8445, "step": 7060 }, { "epoch": 1.66, "learning_rate": 9.993560817764079e-05, "loss": 0.8409, "step": 7070 }, { "epoch": 1.67, "learning_rate": 9.993542593297994e-05, "loss": 0.8821, "step": 7080 }, { "epoch": 1.67, "learning_rate": 9.993524343095149e-05, "loss": 0.8459, "step": 7090 }, { "epoch": 1.67, "learning_rate": 9.993506067155639e-05, "loss": 0.8714, "step": 7100 }, { "epoch": 1.67, "learning_rate": 9.993487765479554e-05, "loss": 0.8318, "step": 7110 }, { "epoch": 1.68, "learning_rate": 9.993469438066993e-05, "loss": 0.8357, "step": 7120 }, { "epoch": 1.68, "learning_rate": 9.99345108491805e-05, "loss": 0.8213, "step": 7130 }, { "epoch": 1.68, "learning_rate": 9.993432706032817e-05, "loss": 0.7883, "step": 7140 }, { "epoch": 1.68, "learning_rate": 9.993414301411391e-05, "loss": 0.8498, "step": 7150 }, { "epoch": 1.68, "learning_rate": 9.993395871053863e-05, "loss": 0.8654, "step": 7160 }, { "epoch": 1.69, "learning_rate": 9.993377414960334e-05, "loss": 0.8609, "step": 7170 }, { "epoch": 1.69, "learning_rate": 9.993358933130895e-05, "loss": 0.8761, "step": 7180 }, { "epoch": 1.69, "learning_rate": 9.993340425565642e-05, "loss": 0.8441, "step": 7190 }, { "epoch": 1.69, "learning_rate": 9.993321892264671e-05, "loss": 0.8612, "step": 7200 }, { "epoch": 1.7, "learning_rate": 9.993303333228079e-05, "loss": 0.8495, "step": 7210 }, { "epoch": 1.7, "learning_rate": 9.993284748455957e-05, "loss": 0.8214, "step": 7220 }, { "epoch": 1.7, "learning_rate": 9.993266137948405e-05, "loss": 0.8545, "step": 7230 }, { "epoch": 1.7, "learning_rate": 9.993247501705518e-05, "loss": 0.8821, "step": 7240 }, { "epoch": 1.71, "learning_rate": 9.993228839727391e-05, "loss": 0.9051, "step": 7250 }, { "epoch": 1.71, "learning_rate": 9.99321015201412e-05, "loss": 0.8336, "step": 7260 }, { "epoch": 1.71, "learning_rate": 9.993191438565805e-05, "loss": 0.7918, "step": 7270 }, { "epoch": 1.71, "learning_rate": 9.993172699382539e-05, "loss": 0.8008, "step": 7280 }, { "epoch": 1.71, "learning_rate": 9.993153934464417e-05, "loss": 0.8372, "step": 7290 }, { "epoch": 1.72, "learning_rate": 9.993135143811539e-05, "loss": 0.8707, "step": 7300 }, { "epoch": 1.72, "learning_rate": 9.993116327424e-05, "loss": 0.8934, "step": 7310 }, { "epoch": 1.72, "learning_rate": 9.993097485301899e-05, "loss": 0.8666, "step": 7320 }, { "epoch": 1.72, "learning_rate": 9.993078617445331e-05, "loss": 0.825, "step": 7330 }, { "epoch": 1.73, "learning_rate": 9.993059723854393e-05, "loss": 0.8842, "step": 7340 }, { "epoch": 1.73, "learning_rate": 9.993040804529185e-05, "loss": 0.8688, "step": 7350 }, { "epoch": 1.73, "learning_rate": 9.993021859469802e-05, "loss": 0.8094, "step": 7360 }, { "epoch": 1.73, "learning_rate": 9.993002888676344e-05, "loss": 0.8443, "step": 7370 }, { "epoch": 1.74, "learning_rate": 9.992983892148906e-05, "loss": 0.8629, "step": 7380 }, { "epoch": 1.74, "learning_rate": 9.992964869887589e-05, "loss": 0.8597, "step": 7390 }, { "epoch": 1.74, "learning_rate": 9.992945821892488e-05, "loss": 0.8069, "step": 7400 }, { "epoch": 1.74, "learning_rate": 9.992926748163702e-05, "loss": 0.8066, "step": 7410 }, { "epoch": 1.74, "learning_rate": 9.992907648701331e-05, "loss": 0.8318, "step": 7420 }, { "epoch": 1.75, "learning_rate": 9.992888523505472e-05, "loss": 0.8611, "step": 7430 }, { "epoch": 1.75, "learning_rate": 9.992869372576223e-05, "loss": 0.8238, "step": 7440 }, { "epoch": 1.75, "learning_rate": 9.992850195913684e-05, "loss": 0.824, "step": 7450 }, { "epoch": 1.75, "learning_rate": 9.992830993517953e-05, "loss": 0.8311, "step": 7460 }, { "epoch": 1.76, "learning_rate": 9.992811765389129e-05, "loss": 0.8513, "step": 7470 }, { "epoch": 1.76, "learning_rate": 9.992792511527313e-05, "loss": 0.8684, "step": 7480 }, { "epoch": 1.76, "learning_rate": 9.992773231932602e-05, "loss": 0.8227, "step": 7490 }, { "epoch": 1.76, "learning_rate": 9.992753926605096e-05, "loss": 0.8076, "step": 7500 }, { "epoch": 1.76, "learning_rate": 9.992734595544895e-05, "loss": 0.8769, "step": 7510 }, { "epoch": 1.77, "learning_rate": 9.992715238752097e-05, "loss": 0.8517, "step": 7520 }, { "epoch": 1.77, "learning_rate": 9.992695856226803e-05, "loss": 0.8336, "step": 7530 }, { "epoch": 1.77, "learning_rate": 9.992676447969113e-05, "loss": 0.8823, "step": 7540 }, { "epoch": 1.77, "learning_rate": 9.992657013979127e-05, "loss": 0.7855, "step": 7550 }, { "epoch": 1.78, "learning_rate": 9.992637554256946e-05, "loss": 0.8535, "step": 7560 }, { "epoch": 1.78, "learning_rate": 9.992618068802668e-05, "loss": 0.8086, "step": 7570 }, { "epoch": 1.78, "learning_rate": 9.992598557616395e-05, "loss": 0.7969, "step": 7580 }, { "epoch": 1.78, "learning_rate": 9.992579020698229e-05, "loss": 0.8408, "step": 7590 }, { "epoch": 1.79, "learning_rate": 9.992559458048267e-05, "loss": 0.8745, "step": 7600 }, { "epoch": 1.79, "learning_rate": 9.992539869666613e-05, "loss": 0.8731, "step": 7610 }, { "epoch": 1.79, "learning_rate": 9.992520255553366e-05, "loss": 0.8583, "step": 7620 }, { "epoch": 1.79, "learning_rate": 9.992500615708626e-05, "loss": 0.8132, "step": 7630 }, { "epoch": 1.79, "learning_rate": 9.9924809501325e-05, "loss": 0.8762, "step": 7640 }, { "epoch": 1.8, "learning_rate": 9.992461258825084e-05, "loss": 0.8355, "step": 7650 }, { "epoch": 1.8, "learning_rate": 9.99244154178648e-05, "loss": 0.8672, "step": 7660 }, { "epoch": 1.8, "learning_rate": 9.992421799016791e-05, "loss": 0.8237, "step": 7670 }, { "epoch": 1.8, "learning_rate": 9.992402030516117e-05, "loss": 0.8212, "step": 7680 }, { "epoch": 1.81, "learning_rate": 9.992382236284563e-05, "loss": 0.8374, "step": 7690 }, { "epoch": 1.81, "learning_rate": 9.99236241632223e-05, "loss": 0.8216, "step": 7700 }, { "epoch": 1.81, "learning_rate": 9.992342570629217e-05, "loss": 0.856, "step": 7710 }, { "epoch": 1.81, "learning_rate": 9.99232269920563e-05, "loss": 0.8408, "step": 7720 }, { "epoch": 1.82, "learning_rate": 9.99230280205157e-05, "loss": 0.807, "step": 7730 }, { "epoch": 1.82, "learning_rate": 9.99228287916714e-05, "loss": 0.8559, "step": 7740 }, { "epoch": 1.82, "learning_rate": 9.992262930552441e-05, "loss": 0.8676, "step": 7750 }, { "epoch": 1.82, "learning_rate": 9.992242956207578e-05, "loss": 0.8747, "step": 7760 }, { "epoch": 1.82, "learning_rate": 9.992222956132653e-05, "loss": 0.8218, "step": 7770 }, { "epoch": 1.83, "learning_rate": 9.99220293032777e-05, "loss": 0.8092, "step": 7780 }, { "epoch": 1.83, "learning_rate": 9.99218287879303e-05, "loss": 0.8527, "step": 7790 }, { "epoch": 1.83, "learning_rate": 9.992162801528539e-05, "loss": 0.8753, "step": 7800 }, { "epoch": 1.83, "learning_rate": 9.992142698534398e-05, "loss": 0.9131, "step": 7810 }, { "epoch": 1.84, "learning_rate": 9.992122569810713e-05, "loss": 0.8239, "step": 7820 }, { "epoch": 1.84, "learning_rate": 9.992102415357585e-05, "loss": 0.8187, "step": 7830 }, { "epoch": 1.84, "learning_rate": 9.99208223517512e-05, "loss": 0.8043, "step": 7840 }, { "epoch": 1.84, "learning_rate": 9.992062029263422e-05, "loss": 0.8388, "step": 7850 }, { "epoch": 1.84, "learning_rate": 9.992041797622594e-05, "loss": 0.8509, "step": 7860 }, { "epoch": 1.85, "learning_rate": 9.992021540252742e-05, "loss": 0.8077, "step": 7870 }, { "epoch": 1.85, "learning_rate": 9.992001257153968e-05, "loss": 0.8546, "step": 7880 }, { "epoch": 1.85, "learning_rate": 9.991980948326379e-05, "loss": 0.8048, "step": 7890 }, { "epoch": 1.85, "learning_rate": 9.991960613770077e-05, "loss": 0.8851, "step": 7900 }, { "epoch": 1.86, "learning_rate": 9.991940253485169e-05, "loss": 0.8364, "step": 7910 }, { "epoch": 1.86, "learning_rate": 9.991919867471759e-05, "loss": 0.7988, "step": 7920 }, { "epoch": 1.86, "learning_rate": 9.991899455729951e-05, "loss": 0.87, "step": 7930 }, { "epoch": 1.86, "learning_rate": 9.991879018259853e-05, "loss": 0.8671, "step": 7940 }, { "epoch": 1.87, "learning_rate": 9.99185855506157e-05, "loss": 0.8889, "step": 7950 }, { "epoch": 1.87, "learning_rate": 9.991838066135204e-05, "loss": 0.8772, "step": 7960 }, { "epoch": 1.87, "learning_rate": 9.991817551480865e-05, "loss": 0.8391, "step": 7970 }, { "epoch": 1.87, "learning_rate": 9.991797011098655e-05, "loss": 0.8207, "step": 7980 }, { "epoch": 1.87, "learning_rate": 9.991776444988681e-05, "loss": 0.8769, "step": 7990 }, { "epoch": 1.88, "learning_rate": 9.991755853151051e-05, "loss": 0.8217, "step": 8000 }, { "epoch": 1.88, "learning_rate": 9.99173523558587e-05, "loss": 0.8095, "step": 8010 }, { "epoch": 1.88, "learning_rate": 9.991714592293241e-05, "loss": 0.8398, "step": 8020 }, { "epoch": 1.88, "learning_rate": 9.991693923273276e-05, "loss": 0.8367, "step": 8030 }, { "epoch": 1.89, "learning_rate": 9.991673228526079e-05, "loss": 0.8732, "step": 8040 }, { "epoch": 1.89, "learning_rate": 9.991652508051754e-05, "loss": 0.8211, "step": 8050 }, { "epoch": 1.89, "learning_rate": 9.991631761850413e-05, "loss": 0.8554, "step": 8060 }, { "epoch": 1.89, "learning_rate": 9.991610989922158e-05, "loss": 0.8055, "step": 8070 }, { "epoch": 1.9, "learning_rate": 9.9915901922671e-05, "loss": 0.7988, "step": 8080 }, { "epoch": 1.9, "learning_rate": 9.991569368885342e-05, "loss": 0.7611, "step": 8090 }, { "epoch": 1.9, "learning_rate": 9.991548519776996e-05, "loss": 0.7963, "step": 8100 }, { "epoch": 1.9, "learning_rate": 9.991527644942167e-05, "loss": 0.7682, "step": 8110 }, { "epoch": 1.9, "learning_rate": 9.991506744380962e-05, "loss": 0.8425, "step": 8120 }, { "epoch": 1.91, "learning_rate": 9.991485818093489e-05, "loss": 0.8245, "step": 8130 }, { "epoch": 1.91, "learning_rate": 9.991464866079858e-05, "loss": 0.8349, "step": 8140 }, { "epoch": 1.91, "learning_rate": 9.991443888340174e-05, "loss": 0.855, "step": 8150 }, { "epoch": 1.91, "learning_rate": 9.991422884874547e-05, "loss": 0.8408, "step": 8160 }, { "epoch": 1.92, "learning_rate": 9.991401855683084e-05, "loss": 0.8516, "step": 8170 }, { "epoch": 1.92, "learning_rate": 9.991380800765895e-05, "loss": 0.8462, "step": 8180 }, { "epoch": 1.92, "learning_rate": 9.991359720123088e-05, "loss": 0.7962, "step": 8190 }, { "epoch": 1.92, "learning_rate": 9.991338613754771e-05, "loss": 0.8201, "step": 8200 }, { "epoch": 1.92, "learning_rate": 9.991317481661053e-05, "loss": 0.899, "step": 8210 }, { "epoch": 1.93, "learning_rate": 9.991296323842042e-05, "loss": 0.8501, "step": 8220 }, { "epoch": 1.93, "learning_rate": 9.991275140297848e-05, "loss": 0.8534, "step": 8230 }, { "epoch": 1.93, "learning_rate": 9.991253931028582e-05, "loss": 0.8394, "step": 8240 }, { "epoch": 1.93, "learning_rate": 9.99123269603435e-05, "loss": 0.8264, "step": 8250 }, { "epoch": 1.94, "learning_rate": 9.991211435315264e-05, "loss": 0.8001, "step": 8260 }, { "epoch": 1.94, "learning_rate": 9.991190148871432e-05, "loss": 0.825, "step": 8270 }, { "epoch": 1.94, "learning_rate": 9.991168836702964e-05, "loss": 0.8433, "step": 8280 }, { "epoch": 1.94, "learning_rate": 9.99114749880997e-05, "loss": 0.8431, "step": 8290 }, { "epoch": 1.95, "learning_rate": 9.991126135192561e-05, "loss": 0.7773, "step": 8300 }, { "epoch": 1.95, "learning_rate": 9.991104745850845e-05, "loss": 0.7975, "step": 8310 }, { "epoch": 1.95, "learning_rate": 9.991083330784934e-05, "loss": 0.8536, "step": 8320 }, { "epoch": 2.0, "learning_rate": 9.99106188999494e-05, "loss": 0.7918, "step": 8330 }, { "epoch": 2.0, "learning_rate": 9.991040423480969e-05, "loss": 0.7866, "step": 8340 }, { "epoch": 2.01, "learning_rate": 9.991018931243133e-05, "loss": 0.8194, "step": 8350 }, { "epoch": 2.01, "learning_rate": 9.990997413281544e-05, "loss": 0.8157, "step": 8360 }, { "epoch": 2.01, "learning_rate": 9.990975869596315e-05, "loss": 0.8422, "step": 8370 }, { "epoch": 2.01, "learning_rate": 9.990954300187551e-05, "loss": 0.8522, "step": 8380 }, { "epoch": 2.01, "learning_rate": 9.990932705055371e-05, "loss": 0.8533, "step": 8390 }, { "epoch": 2.02, "learning_rate": 9.990911084199878e-05, "loss": 0.778, "step": 8400 }, { "epoch": 2.02, "learning_rate": 9.99088943762119e-05, "loss": 0.8334, "step": 8410 }, { "epoch": 2.02, "learning_rate": 9.990867765319416e-05, "loss": 0.7794, "step": 8420 }, { "epoch": 2.02, "learning_rate": 9.990846067294668e-05, "loss": 0.7745, "step": 8430 }, { "epoch": 2.03, "learning_rate": 9.990824343547056e-05, "loss": 0.784, "step": 8440 }, { "epoch": 2.03, "learning_rate": 9.990802594076696e-05, "loss": 0.7554, "step": 8450 }, { "epoch": 2.03, "learning_rate": 9.990780818883696e-05, "loss": 0.8128, "step": 8460 }, { "epoch": 2.03, "learning_rate": 9.99075901796817e-05, "loss": 0.7823, "step": 8470 }, { "epoch": 2.04, "learning_rate": 9.990737191330231e-05, "loss": 0.8451, "step": 8480 }, { "epoch": 2.04, "learning_rate": 9.990715338969991e-05, "loss": 0.7993, "step": 8490 }, { "epoch": 2.04, "learning_rate": 9.990693460887562e-05, "loss": 0.8095, "step": 8500 }, { "epoch": 2.04, "learning_rate": 9.990671557083056e-05, "loss": 0.8481, "step": 8510 }, { "epoch": 2.04, "learning_rate": 9.990649627556589e-05, "loss": 0.8151, "step": 8520 }, { "epoch": 2.05, "learning_rate": 9.990627672308271e-05, "loss": 0.8567, "step": 8530 }, { "epoch": 2.05, "learning_rate": 9.990605691338217e-05, "loss": 0.838, "step": 8540 }, { "epoch": 2.05, "learning_rate": 9.99058368464654e-05, "loss": 0.8568, "step": 8550 }, { "epoch": 2.05, "learning_rate": 9.990561652233351e-05, "loss": 0.8606, "step": 8560 }, { "epoch": 2.06, "learning_rate": 9.990539594098766e-05, "loss": 0.866, "step": 8570 }, { "epoch": 2.06, "learning_rate": 9.990517510242899e-05, "loss": 0.8318, "step": 8580 }, { "epoch": 2.06, "learning_rate": 9.990495400665864e-05, "loss": 0.8488, "step": 8590 }, { "epoch": 2.06, "learning_rate": 9.990473265367773e-05, "loss": 0.8386, "step": 8600 }, { "epoch": 2.06, "learning_rate": 9.99045110434874e-05, "loss": 0.8058, "step": 8610 }, { "epoch": 2.07, "learning_rate": 9.990428917608882e-05, "loss": 0.8068, "step": 8620 }, { "epoch": 2.07, "learning_rate": 9.99040670514831e-05, "loss": 0.7973, "step": 8630 }, { "epoch": 2.07, "learning_rate": 9.990384466967141e-05, "loss": 0.8022, "step": 8640 }, { "epoch": 2.07, "learning_rate": 9.990362203065488e-05, "loss": 0.8503, "step": 8650 }, { "epoch": 2.08, "learning_rate": 9.990339913443469e-05, "loss": 0.7977, "step": 8660 }, { "epoch": 2.08, "learning_rate": 9.990317598101194e-05, "loss": 0.7698, "step": 8670 }, { "epoch": 2.08, "learning_rate": 9.990295257038781e-05, "loss": 0.8095, "step": 8680 }, { "epoch": 2.08, "learning_rate": 9.990272890256345e-05, "loss": 0.8081, "step": 8690 }, { "epoch": 2.09, "learning_rate": 9.990250497754e-05, "loss": 0.8124, "step": 8700 }, { "epoch": 2.09, "learning_rate": 9.990228079531863e-05, "loss": 0.7831, "step": 8710 }, { "epoch": 2.09, "learning_rate": 9.990205635590049e-05, "loss": 0.8118, "step": 8720 }, { "epoch": 2.09, "learning_rate": 9.990183165928672e-05, "loss": 0.8436, "step": 8730 }, { "epoch": 2.09, "learning_rate": 9.99016067054785e-05, "loss": 0.8225, "step": 8740 }, { "epoch": 2.1, "learning_rate": 9.990138149447699e-05, "loss": 0.8058, "step": 8750 }, { "epoch": 2.1, "learning_rate": 9.990115602628333e-05, "loss": 0.8314, "step": 8760 }, { "epoch": 2.1, "learning_rate": 9.990093030089868e-05, "loss": 0.7735, "step": 8770 }, { "epoch": 2.1, "learning_rate": 9.990070431832426e-05, "loss": 0.8461, "step": 8780 }, { "epoch": 2.11, "learning_rate": 9.990047807856117e-05, "loss": 0.8349, "step": 8790 }, { "epoch": 2.11, "learning_rate": 9.99002515816106e-05, "loss": 0.8255, "step": 8800 }, { "epoch": 2.11, "learning_rate": 9.990002482747371e-05, "loss": 0.8325, "step": 8810 }, { "epoch": 2.11, "learning_rate": 9.989979781615168e-05, "loss": 0.8644, "step": 8820 }, { "epoch": 2.12, "learning_rate": 9.989957054764567e-05, "loss": 0.8037, "step": 8830 }, { "epoch": 2.12, "learning_rate": 9.989934302195687e-05, "loss": 0.8274, "step": 8840 }, { "epoch": 2.12, "learning_rate": 9.989911523908642e-05, "loss": 0.7976, "step": 8850 }, { "epoch": 2.12, "learning_rate": 9.989888719903554e-05, "loss": 0.7879, "step": 8860 }, { "epoch": 2.12, "learning_rate": 9.989865890180535e-05, "loss": 0.8209, "step": 8870 }, { "epoch": 2.13, "learning_rate": 9.989843034739708e-05, "loss": 0.8103, "step": 8880 }, { "epoch": 2.13, "learning_rate": 9.989820153581187e-05, "loss": 0.8393, "step": 8890 }, { "epoch": 2.13, "learning_rate": 9.98979724670509e-05, "loss": 0.8533, "step": 8900 }, { "epoch": 2.13, "learning_rate": 9.989774314111537e-05, "loss": 0.7911, "step": 8910 }, { "epoch": 2.14, "learning_rate": 9.989751355800647e-05, "loss": 0.7602, "step": 8920 }, { "epoch": 2.14, "learning_rate": 9.989728371772535e-05, "loss": 0.8086, "step": 8930 }, { "epoch": 2.14, "learning_rate": 9.989705362027323e-05, "loss": 0.8373, "step": 8940 }, { "epoch": 2.14, "learning_rate": 9.989682326565127e-05, "loss": 0.8066, "step": 8950 }, { "epoch": 2.14, "learning_rate": 9.989659265386066e-05, "loss": 0.7804, "step": 8960 }, { "epoch": 2.15, "learning_rate": 9.989636178490261e-05, "loss": 0.784, "step": 8970 }, { "epoch": 2.15, "learning_rate": 9.989613065877828e-05, "loss": 0.7476, "step": 8980 }, { "epoch": 2.15, "learning_rate": 9.989589927548888e-05, "loss": 0.7952, "step": 8990 }, { "epoch": 2.15, "learning_rate": 9.98956676350356e-05, "loss": 0.7936, "step": 9000 }, { "epoch": 2.16, "learning_rate": 9.989543573741962e-05, "loss": 0.7944, "step": 9010 }, { "epoch": 2.16, "learning_rate": 9.989520358264215e-05, "loss": 0.777, "step": 9020 }, { "epoch": 2.16, "learning_rate": 9.989497117070439e-05, "loss": 0.8719, "step": 9030 }, { "epoch": 2.16, "learning_rate": 9.989473850160753e-05, "loss": 0.817, "step": 9040 }, { "epoch": 2.17, "learning_rate": 9.989450557535279e-05, "loss": 0.7617, "step": 9050 }, { "epoch": 2.17, "learning_rate": 9.989427239194132e-05, "loss": 0.8277, "step": 9060 }, { "epoch": 2.17, "learning_rate": 9.989403895137437e-05, "loss": 0.8295, "step": 9070 }, { "epoch": 2.17, "learning_rate": 9.989380525365313e-05, "loss": 0.7613, "step": 9080 }, { "epoch": 2.17, "learning_rate": 9.989357129877879e-05, "loss": 0.8607, "step": 9090 }, { "epoch": 2.18, "learning_rate": 9.989333708675257e-05, "loss": 0.828, "step": 9100 }, { "epoch": 2.18, "learning_rate": 9.989310261757568e-05, "loss": 0.7419, "step": 9110 }, { "epoch": 2.18, "learning_rate": 9.98928678912493e-05, "loss": 0.8432, "step": 9120 }, { "epoch": 2.18, "learning_rate": 9.989263290777469e-05, "loss": 0.8232, "step": 9130 }, { "epoch": 2.19, "learning_rate": 9.989239766715302e-05, "loss": 0.7625, "step": 9140 }, { "epoch": 2.19, "learning_rate": 9.98921621693855e-05, "loss": 0.7437, "step": 9150 }, { "epoch": 2.19, "learning_rate": 9.989192641447338e-05, "loss": 0.7911, "step": 9160 }, { "epoch": 2.19, "learning_rate": 9.989169040241785e-05, "loss": 0.7804, "step": 9170 }, { "epoch": 2.2, "learning_rate": 9.989145413322013e-05, "loss": 0.8116, "step": 9180 }, { "epoch": 2.2, "learning_rate": 9.989121760688144e-05, "loss": 0.8178, "step": 9190 }, { "epoch": 2.2, "learning_rate": 9.989098082340299e-05, "loss": 0.8331, "step": 9200 }, { "epoch": 2.2, "learning_rate": 9.989074378278602e-05, "loss": 0.8319, "step": 9210 }, { "epoch": 2.2, "learning_rate": 9.989050648503174e-05, "loss": 0.775, "step": 9220 }, { "epoch": 2.21, "learning_rate": 9.989026893014135e-05, "loss": 0.804, "step": 9230 }, { "epoch": 2.21, "learning_rate": 9.989003111811612e-05, "loss": 0.8215, "step": 9240 }, { "epoch": 2.21, "learning_rate": 9.988979304895725e-05, "loss": 0.8026, "step": 9250 }, { "epoch": 2.21, "learning_rate": 9.988955472266596e-05, "loss": 0.7743, "step": 9260 }, { "epoch": 2.22, "learning_rate": 9.988931613924348e-05, "loss": 0.8043, "step": 9270 }, { "epoch": 2.22, "learning_rate": 9.988907729869107e-05, "loss": 0.7669, "step": 9280 }, { "epoch": 2.22, "learning_rate": 9.988883820100993e-05, "loss": 0.8268, "step": 9290 }, { "epoch": 2.22, "learning_rate": 9.98885988462013e-05, "loss": 0.745, "step": 9300 }, { "epoch": 2.22, "learning_rate": 9.98883592342664e-05, "loss": 0.772, "step": 9310 }, { "epoch": 2.23, "learning_rate": 9.98881193652065e-05, "loss": 0.8309, "step": 9320 }, { "epoch": 2.23, "learning_rate": 9.98878792390228e-05, "loss": 0.8106, "step": 9330 }, { "epoch": 2.23, "learning_rate": 9.988763885571657e-05, "loss": 0.7821, "step": 9340 }, { "epoch": 2.23, "learning_rate": 9.988739821528903e-05, "loss": 0.8101, "step": 9350 }, { "epoch": 2.24, "learning_rate": 9.988715731774142e-05, "loss": 0.7935, "step": 9360 }, { "epoch": 2.24, "learning_rate": 9.988691616307497e-05, "loss": 0.7769, "step": 9370 }, { "epoch": 2.24, "learning_rate": 9.988667475129096e-05, "loss": 0.8453, "step": 9380 }, { "epoch": 2.24, "learning_rate": 9.988643308239061e-05, "loss": 0.7801, "step": 9390 }, { "epoch": 2.25, "learning_rate": 9.988619115637514e-05, "loss": 0.7863, "step": 9400 }, { "epoch": 2.25, "learning_rate": 9.988594897324585e-05, "loss": 0.7942, "step": 9410 }, { "epoch": 2.25, "learning_rate": 9.988570653300395e-05, "loss": 0.7944, "step": 9420 }, { "epoch": 2.25, "learning_rate": 9.988546383565071e-05, "loss": 0.7992, "step": 9430 }, { "epoch": 2.25, "learning_rate": 9.988522088118737e-05, "loss": 0.7258, "step": 9440 }, { "epoch": 2.26, "learning_rate": 9.988497766961518e-05, "loss": 0.7919, "step": 9450 }, { "epoch": 2.26, "learning_rate": 9.98847342009354e-05, "loss": 0.7774, "step": 9460 }, { "epoch": 2.26, "learning_rate": 9.988449047514927e-05, "loss": 0.7837, "step": 9470 }, { "epoch": 2.26, "learning_rate": 9.988424649225808e-05, "loss": 0.7732, "step": 9480 }, { "epoch": 2.27, "learning_rate": 9.988400225226307e-05, "loss": 0.7787, "step": 9490 }, { "epoch": 2.27, "learning_rate": 9.988375775516548e-05, "loss": 0.7689, "step": 9500 }, { "epoch": 2.27, "learning_rate": 9.988351300096658e-05, "loss": 0.807, "step": 9510 }, { "epoch": 2.27, "learning_rate": 9.988326798966765e-05, "loss": 0.8021, "step": 9520 }, { "epoch": 2.28, "learning_rate": 9.988302272126993e-05, "loss": 0.7737, "step": 9530 }, { "epoch": 2.28, "learning_rate": 9.98827771957747e-05, "loss": 0.8561, "step": 9540 }, { "epoch": 2.28, "learning_rate": 9.988253141318322e-05, "loss": 0.8347, "step": 9550 }, { "epoch": 2.28, "learning_rate": 9.988228537349676e-05, "loss": 0.767, "step": 9560 }, { "epoch": 2.28, "learning_rate": 9.988203907671658e-05, "loss": 0.7499, "step": 9570 }, { "epoch": 2.29, "learning_rate": 9.988179252284396e-05, "loss": 0.7925, "step": 9580 }, { "epoch": 2.29, "learning_rate": 9.988154571188016e-05, "loss": 0.8117, "step": 9590 }, { "epoch": 2.29, "learning_rate": 9.988129864382645e-05, "loss": 0.8131, "step": 9600 }, { "epoch": 2.29, "learning_rate": 9.98810513186841e-05, "loss": 0.8145, "step": 9610 }, { "epoch": 2.3, "learning_rate": 9.988080373645441e-05, "loss": 0.7443, "step": 9620 }, { "epoch": 2.3, "learning_rate": 9.988055589713865e-05, "loss": 0.7472, "step": 9630 }, { "epoch": 2.3, "learning_rate": 9.988030780073808e-05, "loss": 0.7603, "step": 9640 }, { "epoch": 2.3, "learning_rate": 9.988005944725398e-05, "loss": 0.7909, "step": 9650 }, { "epoch": 2.3, "learning_rate": 9.987981083668764e-05, "loss": 0.7793, "step": 9660 }, { "epoch": 2.31, "learning_rate": 9.987956196904034e-05, "loss": 0.783, "step": 9670 }, { "epoch": 2.31, "learning_rate": 9.987931284431336e-05, "loss": 0.7915, "step": 9680 }, { "epoch": 2.31, "learning_rate": 9.987906346250798e-05, "loss": 0.8527, "step": 9690 }, { "epoch": 2.31, "learning_rate": 9.98788138236255e-05, "loss": 0.794, "step": 9700 }, { "epoch": 2.32, "learning_rate": 9.987856392766719e-05, "loss": 0.8108, "step": 9710 }, { "epoch": 2.32, "learning_rate": 9.987831377463435e-05, "loss": 0.8214, "step": 9720 }, { "epoch": 2.32, "learning_rate": 9.987806336452825e-05, "loss": 0.7757, "step": 9730 }, { "epoch": 2.32, "learning_rate": 9.98778126973502e-05, "loss": 0.74, "step": 9740 }, { "epoch": 2.33, "learning_rate": 9.987756177310149e-05, "loss": 0.7911, "step": 9750 }, { "epoch": 2.33, "learning_rate": 9.987731059178342e-05, "loss": 0.785, "step": 9760 }, { "epoch": 2.33, "learning_rate": 9.987705915339726e-05, "loss": 0.8258, "step": 9770 }, { "epoch": 2.33, "learning_rate": 9.987680745794432e-05, "loss": 0.8084, "step": 9780 }, { "epoch": 2.33, "learning_rate": 9.987655550542591e-05, "loss": 0.7411, "step": 9790 }, { "epoch": 2.34, "learning_rate": 9.98763032958433e-05, "loss": 0.7772, "step": 9800 }, { "epoch": 2.34, "learning_rate": 9.987605082919782e-05, "loss": 0.7711, "step": 9810 }, { "epoch": 2.34, "learning_rate": 9.987579810549074e-05, "loss": 0.7838, "step": 9820 }, { "epoch": 2.34, "learning_rate": 9.987554512472338e-05, "loss": 0.7446, "step": 9830 }, { "epoch": 2.35, "learning_rate": 9.987529188689707e-05, "loss": 0.8119, "step": 9840 }, { "epoch": 2.35, "learning_rate": 9.987503839201308e-05, "loss": 0.8479, "step": 9850 }, { "epoch": 2.35, "learning_rate": 9.987478464007272e-05, "loss": 0.7842, "step": 9860 }, { "epoch": 2.35, "learning_rate": 9.98745306310773e-05, "loss": 0.7419, "step": 9870 }, { "epoch": 2.36, "learning_rate": 9.987427636502812e-05, "loss": 0.7954, "step": 9880 }, { "epoch": 2.36, "learning_rate": 9.987402184192653e-05, "loss": 0.741, "step": 9890 }, { "epoch": 2.36, "learning_rate": 9.98737670617738e-05, "loss": 0.7749, "step": 9900 }, { "epoch": 2.36, "learning_rate": 9.987351202457124e-05, "loss": 0.8019, "step": 9910 }, { "epoch": 2.36, "learning_rate": 9.987325673032021e-05, "loss": 0.7752, "step": 9920 }, { "epoch": 2.37, "learning_rate": 9.987300117902198e-05, "loss": 0.78, "step": 9930 }, { "epoch": 2.37, "learning_rate": 9.98727453706779e-05, "loss": 0.7498, "step": 9940 }, { "epoch": 2.37, "learning_rate": 9.987248930528927e-05, "loss": 0.8006, "step": 9950 }, { "epoch": 2.37, "learning_rate": 9.987223298285742e-05, "loss": 0.7347, "step": 9960 }, { "epoch": 2.38, "learning_rate": 9.987197640338364e-05, "loss": 0.8374, "step": 9970 }, { "epoch": 2.38, "learning_rate": 9.98717195668693e-05, "loss": 0.7841, "step": 9980 }, { "epoch": 2.38, "learning_rate": 9.987146247331569e-05, "loss": 0.8128, "step": 9990 }, { "epoch": 2.38, "learning_rate": 9.987120512272414e-05, "loss": 0.8014, "step": 10000 }, { "epoch": 2.38, "learning_rate": 9.9870947515096e-05, "loss": 0.7909, "step": 10010 }, { "epoch": 2.39, "learning_rate": 9.987068965043256e-05, "loss": 0.8118, "step": 10020 }, { "epoch": 2.39, "learning_rate": 9.987043152873518e-05, "loss": 0.7348, "step": 10030 }, { "epoch": 2.39, "learning_rate": 9.987017315000518e-05, "loss": 0.763, "step": 10040 }, { "epoch": 2.39, "learning_rate": 9.986991451424388e-05, "loss": 0.78, "step": 10050 }, { "epoch": 2.4, "learning_rate": 9.986965562145262e-05, "loss": 0.7718, "step": 10060 }, { "epoch": 2.4, "learning_rate": 9.986939647163276e-05, "loss": 0.7397, "step": 10070 }, { "epoch": 2.4, "learning_rate": 9.98691370647856e-05, "loss": 0.7333, "step": 10080 }, { "epoch": 2.4, "learning_rate": 9.98688774009125e-05, "loss": 0.7809, "step": 10090 }, { "epoch": 2.41, "learning_rate": 9.986861748001478e-05, "loss": 0.8049, "step": 10100 }, { "epoch": 2.41, "learning_rate": 9.98683573020938e-05, "loss": 0.7803, "step": 10110 }, { "epoch": 2.41, "learning_rate": 9.986809686715088e-05, "loss": 0.7781, "step": 10120 }, { "epoch": 2.41, "learning_rate": 9.986783617518737e-05, "loss": 0.804, "step": 10130 }, { "epoch": 2.41, "learning_rate": 9.986757522620463e-05, "loss": 0.8165, "step": 10140 }, { "epoch": 2.42, "learning_rate": 9.986731402020398e-05, "loss": 0.801, "step": 10150 }, { "epoch": 2.42, "learning_rate": 9.986705255718676e-05, "loss": 0.7773, "step": 10160 }, { "epoch": 2.42, "learning_rate": 9.986679083715436e-05, "loss": 0.8377, "step": 10170 }, { "epoch": 2.42, "learning_rate": 9.986652886010807e-05, "loss": 0.7661, "step": 10180 }, { "epoch": 2.43, "learning_rate": 9.98662666260493e-05, "loss": 0.8241, "step": 10190 }, { "epoch": 2.43, "learning_rate": 9.986600413497938e-05, "loss": 0.7662, "step": 10200 }, { "epoch": 2.43, "learning_rate": 9.986574138689966e-05, "loss": 0.7791, "step": 10210 }, { "epoch": 2.43, "learning_rate": 9.986547838181147e-05, "loss": 0.7852, "step": 10220 }, { "epoch": 2.44, "learning_rate": 9.986521511971621e-05, "loss": 0.7374, "step": 10230 }, { "epoch": 2.44, "learning_rate": 9.986495160061519e-05, "loss": 0.765, "step": 10240 }, { "epoch": 2.44, "learning_rate": 9.986468782450982e-05, "loss": 0.7442, "step": 10250 }, { "epoch": 2.44, "learning_rate": 9.986442379140142e-05, "loss": 0.7675, "step": 10260 }, { "epoch": 2.44, "learning_rate": 9.986415950129136e-05, "loss": 0.7915, "step": 10270 }, { "epoch": 2.45, "learning_rate": 9.9863894954181e-05, "loss": 0.7971, "step": 10280 }, { "epoch": 2.45, "learning_rate": 9.986363015007172e-05, "loss": 0.7306, "step": 10290 }, { "epoch": 2.45, "learning_rate": 9.986336508896485e-05, "loss": 0.7823, "step": 10300 }, { "epoch": 2.45, "learning_rate": 9.986309977086181e-05, "loss": 0.7502, "step": 10310 }, { "epoch": 2.46, "learning_rate": 9.986283419576393e-05, "loss": 0.8248, "step": 10320 }, { "epoch": 2.46, "learning_rate": 9.986256836367259e-05, "loss": 0.8006, "step": 10330 }, { "epoch": 2.46, "learning_rate": 9.986230227458912e-05, "loss": 0.7684, "step": 10340 }, { "epoch": 2.46, "learning_rate": 9.986203592851496e-05, "loss": 0.7868, "step": 10350 }, { "epoch": 2.46, "learning_rate": 9.986176932545145e-05, "loss": 0.7606, "step": 10360 }, { "epoch": 2.47, "learning_rate": 9.986150246539996e-05, "loss": 0.7654, "step": 10370 }, { "epoch": 2.47, "learning_rate": 9.986123534836186e-05, "loss": 0.7978, "step": 10380 }, { "epoch": 2.47, "learning_rate": 9.986096797433855e-05, "loss": 0.8286, "step": 10390 }, { "epoch": 2.47, "learning_rate": 9.986070034333139e-05, "loss": 0.7589, "step": 10400 }, { "epoch": 2.48, "learning_rate": 9.986043245534176e-05, "loss": 0.7795, "step": 10410 }, { "epoch": 2.48, "learning_rate": 9.986016431037104e-05, "loss": 0.7922, "step": 10420 }, { "epoch": 2.48, "learning_rate": 9.985989590842062e-05, "loss": 0.748, "step": 10430 }, { "epoch": 2.48, "learning_rate": 9.98596272494919e-05, "loss": 0.7787, "step": 10440 }, { "epoch": 2.49, "learning_rate": 9.985935833358621e-05, "loss": 0.7957, "step": 10450 }, { "epoch": 2.49, "learning_rate": 9.985908916070499e-05, "loss": 0.8252, "step": 10460 }, { "epoch": 2.49, "learning_rate": 9.985881973084961e-05, "loss": 0.7668, "step": 10470 }, { "epoch": 2.49, "learning_rate": 9.985855004402144e-05, "loss": 0.8136, "step": 10480 }, { "epoch": 2.49, "learning_rate": 9.985828010022191e-05, "loss": 0.7525, "step": 10490 }, { "epoch": 2.5, "learning_rate": 9.985800989945237e-05, "loss": 0.735, "step": 10500 }, { "epoch": 2.5, "learning_rate": 9.985773944171424e-05, "loss": 0.7579, "step": 10510 }, { "epoch": 2.5, "learning_rate": 9.98574687270089e-05, "loss": 0.7661, "step": 10520 }, { "epoch": 2.5, "learning_rate": 9.985719775533776e-05, "loss": 0.7937, "step": 10530 }, { "epoch": 2.51, "learning_rate": 9.985692652670218e-05, "loss": 0.8022, "step": 10540 }, { "epoch": 2.51, "learning_rate": 9.98566550411036e-05, "loss": 0.7534, "step": 10550 }, { "epoch": 2.51, "learning_rate": 9.98563832985434e-05, "loss": 0.7192, "step": 10560 }, { "epoch": 2.51, "learning_rate": 9.985611129902299e-05, "loss": 0.7751, "step": 10570 }, { "epoch": 2.52, "learning_rate": 9.985583904254375e-05, "loss": 0.745, "step": 10580 }, { "epoch": 2.52, "learning_rate": 9.985556652910711e-05, "loss": 0.7706, "step": 10590 }, { "epoch": 2.52, "learning_rate": 9.985529375871447e-05, "loss": 0.7505, "step": 10600 }, { "epoch": 2.52, "learning_rate": 9.985502073136722e-05, "loss": 0.7887, "step": 10610 }, { "epoch": 2.52, "learning_rate": 9.985474744706677e-05, "loss": 0.7622, "step": 10620 }, { "epoch": 2.53, "learning_rate": 9.985447390581454e-05, "loss": 0.7865, "step": 10630 }, { "epoch": 2.53, "learning_rate": 9.985420010761195e-05, "loss": 0.7936, "step": 10640 }, { "epoch": 2.53, "learning_rate": 9.985392605246039e-05, "loss": 0.8815, "step": 10650 }, { "epoch": 2.53, "learning_rate": 9.985365174036127e-05, "loss": 0.7824, "step": 10660 }, { "epoch": 2.54, "learning_rate": 9.985337717131602e-05, "loss": 0.8307, "step": 10670 }, { "epoch": 2.54, "learning_rate": 9.985310234532603e-05, "loss": 0.8032, "step": 10680 }, { "epoch": 2.54, "learning_rate": 9.985282726239276e-05, "loss": 0.7947, "step": 10690 }, { "epoch": 2.54, "learning_rate": 9.98525519225176e-05, "loss": 0.7848, "step": 10700 }, { "epoch": 2.54, "learning_rate": 9.985227632570195e-05, "loss": 0.7478, "step": 10710 }, { "epoch": 2.55, "learning_rate": 9.985200047194725e-05, "loss": 0.82, "step": 10720 }, { "epoch": 2.55, "learning_rate": 9.985172436125494e-05, "loss": 0.8488, "step": 10730 }, { "epoch": 2.55, "learning_rate": 9.985144799362642e-05, "loss": 0.7936, "step": 10740 }, { "epoch": 2.55, "learning_rate": 9.985117136906311e-05, "loss": 0.8381, "step": 10750 }, { "epoch": 2.56, "learning_rate": 9.985089448756646e-05, "loss": 0.8461, "step": 10760 }, { "epoch": 2.56, "learning_rate": 9.985061734913788e-05, "loss": 0.8085, "step": 10770 }, { "epoch": 2.56, "learning_rate": 9.985033995377879e-05, "loss": 0.7889, "step": 10780 }, { "epoch": 2.56, "learning_rate": 9.985006230149065e-05, "loss": 0.8226, "step": 10790 }, { "epoch": 2.57, "learning_rate": 9.984978439227486e-05, "loss": 0.8531, "step": 10800 }, { "epoch": 2.57, "learning_rate": 9.984950622613287e-05, "loss": 0.7643, "step": 10810 }, { "epoch": 2.57, "learning_rate": 9.984922780306611e-05, "loss": 0.825, "step": 10820 }, { "epoch": 2.57, "learning_rate": 9.984894912307601e-05, "loss": 0.7973, "step": 10830 }, { "epoch": 2.57, "learning_rate": 9.984867018616401e-05, "loss": 0.8034, "step": 10840 }, { "epoch": 2.58, "learning_rate": 9.984839099233154e-05, "loss": 0.7819, "step": 10850 }, { "epoch": 2.58, "learning_rate": 9.984811154158005e-05, "loss": 0.8045, "step": 10860 }, { "epoch": 2.58, "learning_rate": 9.984783183391098e-05, "loss": 0.7925, "step": 10870 }, { "epoch": 2.58, "learning_rate": 9.984755186932577e-05, "loss": 0.7913, "step": 10880 }, { "epoch": 2.59, "learning_rate": 9.984727164782585e-05, "loss": 0.7943, "step": 10890 }, { "epoch": 2.59, "learning_rate": 9.984699116941269e-05, "loss": 0.7577, "step": 10900 }, { "epoch": 2.59, "learning_rate": 9.98467104340877e-05, "loss": 0.7843, "step": 10910 }, { "epoch": 2.59, "learning_rate": 9.984642944185238e-05, "loss": 0.8399, "step": 10920 }, { "epoch": 2.6, "learning_rate": 9.984614819270812e-05, "loss": 0.7896, "step": 10930 }, { "epoch": 2.6, "learning_rate": 9.98458666866564e-05, "loss": 0.7714, "step": 10940 }, { "epoch": 2.6, "learning_rate": 9.984558492369866e-05, "loss": 0.8316, "step": 10950 }, { "epoch": 2.6, "learning_rate": 9.984530290383638e-05, "loss": 0.8143, "step": 10960 }, { "epoch": 2.6, "learning_rate": 9.984502062707098e-05, "loss": 0.7737, "step": 10970 }, { "epoch": 2.61, "learning_rate": 9.984473809340393e-05, "loss": 0.7793, "step": 10980 }, { "epoch": 2.61, "learning_rate": 9.984445530283668e-05, "loss": 0.7355, "step": 10990 }, { "epoch": 2.61, "learning_rate": 9.98441722553707e-05, "loss": 0.8481, "step": 11000 }, { "epoch": 2.61, "learning_rate": 9.984388895100742e-05, "loss": 0.7785, "step": 11010 }, { "epoch": 2.62, "learning_rate": 9.984360538974833e-05, "loss": 0.8011, "step": 11020 }, { "epoch": 2.62, "learning_rate": 9.984332157159489e-05, "loss": 0.7806, "step": 11030 }, { "epoch": 2.62, "learning_rate": 9.984303749654854e-05, "loss": 0.7659, "step": 11040 }, { "epoch": 2.62, "learning_rate": 9.984275316461075e-05, "loss": 0.7501, "step": 11050 }, { "epoch": 2.62, "learning_rate": 9.984246857578302e-05, "loss": 0.7278, "step": 11060 }, { "epoch": 2.63, "learning_rate": 9.984218373006678e-05, "loss": 0.8028, "step": 11070 }, { "epoch": 2.63, "learning_rate": 9.98418986274635e-05, "loss": 0.8214, "step": 11080 }, { "epoch": 2.63, "learning_rate": 9.984161326797467e-05, "loss": 0.8258, "step": 11090 }, { "epoch": 2.63, "learning_rate": 9.984132765160174e-05, "loss": 0.783, "step": 11100 }, { "epoch": 2.64, "learning_rate": 9.984104177834619e-05, "loss": 0.7336, "step": 11110 }, { "epoch": 2.64, "learning_rate": 9.984075564820951e-05, "loss": 0.8035, "step": 11120 }, { "epoch": 2.64, "learning_rate": 9.984046926119314e-05, "loss": 0.7756, "step": 11130 }, { "epoch": 2.64, "learning_rate": 9.984018261729858e-05, "loss": 0.8083, "step": 11140 }, { "epoch": 2.65, "learning_rate": 9.98398957165273e-05, "loss": 0.7786, "step": 11150 }, { "epoch": 2.65, "learning_rate": 9.98396085588808e-05, "loss": 0.7647, "step": 11160 }, { "epoch": 2.65, "learning_rate": 9.983932114436053e-05, "loss": 0.8005, "step": 11170 }, { "epoch": 2.65, "learning_rate": 9.983903347296797e-05, "loss": 0.7856, "step": 11180 }, { "epoch": 2.65, "learning_rate": 9.983874554470461e-05, "loss": 0.7733, "step": 11190 }, { "epoch": 2.66, "learning_rate": 9.983845735957196e-05, "loss": 0.7358, "step": 11200 }, { "epoch": 2.66, "learning_rate": 9.983816891757147e-05, "loss": 0.7851, "step": 11210 }, { "epoch": 2.66, "learning_rate": 9.983788021870465e-05, "loss": 0.7331, "step": 11220 }, { "epoch": 2.66, "learning_rate": 9.983759126297298e-05, "loss": 0.7901, "step": 11230 }, { "epoch": 2.67, "learning_rate": 9.983730205037794e-05, "loss": 0.7885, "step": 11240 }, { "epoch": 2.67, "learning_rate": 9.983701258092102e-05, "loss": 0.749, "step": 11250 }, { "epoch": 2.67, "learning_rate": 9.983672285460374e-05, "loss": 0.7622, "step": 11260 }, { "epoch": 2.67, "learning_rate": 9.983643287142757e-05, "loss": 0.813, "step": 11270 }, { "epoch": 2.68, "learning_rate": 9.9836142631394e-05, "loss": 0.7655, "step": 11280 }, { "epoch": 2.68, "learning_rate": 9.983585213450454e-05, "loss": 0.7951, "step": 11290 }, { "epoch": 2.68, "learning_rate": 9.983556138076068e-05, "loss": 0.8071, "step": 11300 }, { "epoch": 2.68, "learning_rate": 9.983527037016392e-05, "loss": 0.8048, "step": 11310 }, { "epoch": 2.68, "learning_rate": 9.983497910271575e-05, "loss": 0.8294, "step": 11320 }, { "epoch": 2.69, "learning_rate": 9.98346875784177e-05, "loss": 0.7738, "step": 11330 }, { "epoch": 2.69, "learning_rate": 9.983439579727125e-05, "loss": 0.8218, "step": 11340 }, { "epoch": 2.69, "learning_rate": 9.98341037592779e-05, "loss": 0.7534, "step": 11350 }, { "epoch": 2.69, "learning_rate": 9.983381146443916e-05, "loss": 0.7355, "step": 11360 }, { "epoch": 2.7, "learning_rate": 9.983351891275655e-05, "loss": 0.8142, "step": 11370 }, { "epoch": 2.7, "learning_rate": 9.983322610423156e-05, "loss": 0.786, "step": 11380 }, { "epoch": 2.7, "learning_rate": 9.983293303886571e-05, "loss": 0.7409, "step": 11390 }, { "epoch": 2.7, "learning_rate": 9.98326397166605e-05, "loss": 0.8087, "step": 11400 }, { "epoch": 2.7, "learning_rate": 9.983234613761745e-05, "loss": 0.7515, "step": 11410 }, { "epoch": 2.71, "learning_rate": 9.983205230173808e-05, "loss": 0.7803, "step": 11420 }, { "epoch": 2.71, "learning_rate": 9.983175820902389e-05, "loss": 0.7691, "step": 11430 }, { "epoch": 2.71, "learning_rate": 9.98314638594764e-05, "loss": 0.7859, "step": 11440 }, { "epoch": 2.71, "learning_rate": 9.983116925309712e-05, "loss": 0.7667, "step": 11450 }, { "epoch": 2.72, "learning_rate": 9.98308743898876e-05, "loss": 0.7606, "step": 11460 }, { "epoch": 2.72, "learning_rate": 9.983057926984932e-05, "loss": 0.7909, "step": 11470 }, { "epoch": 2.72, "learning_rate": 9.983028389298383e-05, "loss": 0.7633, "step": 11480 }, { "epoch": 2.72, "learning_rate": 9.982998825929262e-05, "loss": 0.7939, "step": 11490 }, { "epoch": 2.73, "learning_rate": 9.982969236877726e-05, "loss": 0.8178, "step": 11500 }, { "epoch": 2.73, "learning_rate": 9.982939622143923e-05, "loss": 0.7717, "step": 11510 }, { "epoch": 2.73, "learning_rate": 9.982909981728007e-05, "loss": 0.8055, "step": 11520 }, { "epoch": 2.73, "learning_rate": 9.982880315630133e-05, "loss": 0.7294, "step": 11530 }, { "epoch": 2.73, "learning_rate": 9.982850623850452e-05, "loss": 0.7249, "step": 11540 }, { "epoch": 2.74, "learning_rate": 9.982820906389117e-05, "loss": 0.7985, "step": 11550 }, { "epoch": 2.74, "learning_rate": 9.982791163246282e-05, "loss": 0.7376, "step": 11560 }, { "epoch": 2.74, "learning_rate": 9.982761394422097e-05, "loss": 0.762, "step": 11570 }, { "epoch": 2.74, "learning_rate": 9.982731599916721e-05, "loss": 0.7656, "step": 11580 }, { "epoch": 2.75, "learning_rate": 9.982701779730304e-05, "loss": 0.84, "step": 11590 }, { "epoch": 2.75, "learning_rate": 9.982671933862999e-05, "loss": 0.6918, "step": 11600 }, { "epoch": 2.75, "learning_rate": 9.982642062314964e-05, "loss": 0.7624, "step": 11610 }, { "epoch": 2.75, "learning_rate": 9.982612165086347e-05, "loss": 0.732, "step": 11620 }, { "epoch": 2.76, "learning_rate": 9.982582242177307e-05, "loss": 0.775, "step": 11630 }, { "epoch": 2.76, "learning_rate": 9.982552293587997e-05, "loss": 0.7565, "step": 11640 }, { "epoch": 2.76, "learning_rate": 9.98252231931857e-05, "loss": 0.7963, "step": 11650 }, { "epoch": 2.76, "learning_rate": 9.98249231936918e-05, "loss": 0.7158, "step": 11660 }, { "epoch": 2.76, "learning_rate": 9.982462293739985e-05, "loss": 0.7906, "step": 11670 }, { "epoch": 2.77, "learning_rate": 9.982432242431137e-05, "loss": 0.7945, "step": 11680 }, { "epoch": 2.77, "learning_rate": 9.982402165442791e-05, "loss": 0.7376, "step": 11690 }, { "epoch": 2.77, "learning_rate": 9.982372062775104e-05, "loss": 0.7991, "step": 11700 }, { "epoch": 2.77, "learning_rate": 9.982341934428229e-05, "loss": 0.7586, "step": 11710 }, { "epoch": 2.78, "learning_rate": 9.982311780402322e-05, "loss": 0.7469, "step": 11720 }, { "epoch": 2.78, "learning_rate": 9.982281600697539e-05, "loss": 0.7714, "step": 11730 }, { "epoch": 2.78, "learning_rate": 9.982251395314033e-05, "loss": 0.8061, "step": 11740 }, { "epoch": 2.78, "learning_rate": 9.982221164251964e-05, "loss": 0.7985, "step": 11750 }, { "epoch": 2.78, "learning_rate": 9.982190907511483e-05, "loss": 0.811, "step": 11760 }, { "epoch": 2.79, "learning_rate": 9.98216062509275e-05, "loss": 0.7043, "step": 11770 }, { "epoch": 2.79, "learning_rate": 9.98213031699592e-05, "loss": 0.7211, "step": 11780 }, { "epoch": 2.79, "learning_rate": 9.982099983221148e-05, "loss": 0.682, "step": 11790 }, { "epoch": 2.79, "learning_rate": 9.98206962376859e-05, "loss": 0.7432, "step": 11800 }, { "epoch": 2.8, "learning_rate": 9.982039238638405e-05, "loss": 0.7166, "step": 11810 }, { "epoch": 2.8, "learning_rate": 9.982008827830749e-05, "loss": 0.7772, "step": 11820 }, { "epoch": 2.8, "learning_rate": 9.981978391345776e-05, "loss": 0.7906, "step": 11830 }, { "epoch": 2.8, "learning_rate": 9.981947929183646e-05, "loss": 0.7365, "step": 11840 }, { "epoch": 2.81, "learning_rate": 9.981917441344514e-05, "loss": 0.779, "step": 11850 }, { "epoch": 2.81, "learning_rate": 9.981886927828538e-05, "loss": 0.7505, "step": 11860 }, { "epoch": 2.81, "learning_rate": 9.981856388635875e-05, "loss": 0.6944, "step": 11870 }, { "epoch": 2.81, "learning_rate": 9.981825823766682e-05, "loss": 0.7467, "step": 11880 }, { "epoch": 2.81, "learning_rate": 9.981795233221119e-05, "loss": 0.7245, "step": 11890 }, { "epoch": 2.82, "learning_rate": 9.981764616999339e-05, "loss": 0.7623, "step": 11900 }, { "epoch": 2.82, "learning_rate": 9.981733975101504e-05, "loss": 0.7923, "step": 11910 }, { "epoch": 2.82, "learning_rate": 9.98170330752777e-05, "loss": 0.7579, "step": 11920 }, { "epoch": 2.82, "learning_rate": 9.981672614278297e-05, "loss": 0.7901, "step": 11930 }, { "epoch": 2.83, "learning_rate": 9.98164189535324e-05, "loss": 0.7116, "step": 11940 }, { "epoch": 2.83, "learning_rate": 9.98161115075276e-05, "loss": 0.7442, "step": 11950 }, { "epoch": 2.83, "learning_rate": 9.981580380477013e-05, "loss": 0.7589, "step": 11960 }, { "epoch": 2.83, "learning_rate": 9.981549584526161e-05, "loss": 0.7627, "step": 11970 }, { "epoch": 2.84, "learning_rate": 9.98151876290036e-05, "loss": 0.7414, "step": 11980 }, { "epoch": 2.84, "learning_rate": 9.98148791559977e-05, "loss": 0.7691, "step": 11990 }, { "epoch": 2.84, "learning_rate": 9.98145704262455e-05, "loss": 0.7505, "step": 12000 }, { "epoch": 2.84, "learning_rate": 9.981426143974857e-05, "loss": 0.7537, "step": 12010 }, { "epoch": 2.84, "learning_rate": 9.981395219650853e-05, "loss": 0.7294, "step": 12020 }, { "epoch": 2.85, "learning_rate": 9.981364269652697e-05, "loss": 0.7243, "step": 12030 }, { "epoch": 2.85, "learning_rate": 9.981333293980547e-05, "loss": 0.7289, "step": 12040 }, { "epoch": 2.85, "learning_rate": 9.981302292634565e-05, "loss": 0.7585, "step": 12050 }, { "epoch": 2.85, "learning_rate": 9.981271265614907e-05, "loss": 0.7434, "step": 12060 }, { "epoch": 2.86, "learning_rate": 9.981240212921736e-05, "loss": 0.7078, "step": 12070 }, { "epoch": 2.86, "learning_rate": 9.981209134555213e-05, "loss": 0.7112, "step": 12080 }, { "epoch": 2.86, "learning_rate": 9.981178030515495e-05, "loss": 0.7383, "step": 12090 }, { "epoch": 2.86, "learning_rate": 9.981146900802745e-05, "loss": 0.7449, "step": 12100 }, { "epoch": 2.86, "learning_rate": 9.98111574541712e-05, "loss": 0.7749, "step": 12110 }, { "epoch": 2.87, "learning_rate": 9.981084564358785e-05, "loss": 0.7428, "step": 12120 }, { "epoch": 2.87, "learning_rate": 9.981053357627898e-05, "loss": 0.7707, "step": 12130 }, { "epoch": 2.87, "learning_rate": 9.98102212522462e-05, "loss": 0.7038, "step": 12140 }, { "epoch": 2.87, "learning_rate": 9.980990867149111e-05, "loss": 0.7044, "step": 12150 }, { "epoch": 2.88, "learning_rate": 9.980959583401535e-05, "loss": 0.7651, "step": 12160 }, { "epoch": 2.88, "learning_rate": 9.980928273982052e-05, "loss": 0.7777, "step": 12170 }, { "epoch": 2.88, "learning_rate": 9.980896938890822e-05, "loss": 0.7917, "step": 12180 }, { "epoch": 2.88, "learning_rate": 9.980865578128009e-05, "loss": 0.6625, "step": 12190 }, { "epoch": 2.89, "learning_rate": 9.980834191693772e-05, "loss": 0.7346, "step": 12200 }, { "epoch": 2.89, "learning_rate": 9.980802779588275e-05, "loss": 0.7699, "step": 12210 }, { "epoch": 2.89, "learning_rate": 9.980771341811677e-05, "loss": 0.7434, "step": 12220 }, { "epoch": 2.89, "learning_rate": 9.980739878364143e-05, "loss": 0.7299, "step": 12230 }, { "epoch": 2.89, "learning_rate": 9.980708389245834e-05, "loss": 0.7898, "step": 12240 }, { "epoch": 2.9, "learning_rate": 9.980676874456913e-05, "loss": 0.7647, "step": 12250 }, { "epoch": 2.9, "learning_rate": 9.980645333997541e-05, "loss": 0.7319, "step": 12260 }, { "epoch": 2.9, "learning_rate": 9.980613767867881e-05, "loss": 0.7101, "step": 12270 }, { "epoch": 2.9, "learning_rate": 9.980582176068096e-05, "loss": 0.7547, "step": 12280 }, { "epoch": 2.91, "learning_rate": 9.980550558598349e-05, "loss": 0.7196, "step": 12290 }, { "epoch": 2.91, "learning_rate": 9.980518915458803e-05, "loss": 0.7427, "step": 12300 }, { "epoch": 2.91, "learning_rate": 9.98048724664962e-05, "loss": 0.7143, "step": 12310 }, { "epoch": 2.91, "learning_rate": 9.980455552170967e-05, "loss": 0.7405, "step": 12320 }, { "epoch": 2.91, "learning_rate": 9.980423832023003e-05, "loss": 0.7596, "step": 12330 }, { "epoch": 2.92, "learning_rate": 9.980392086205892e-05, "loss": 0.7413, "step": 12340 }, { "epoch": 2.92, "learning_rate": 9.980360314719799e-05, "loss": 0.7082, "step": 12350 }, { "epoch": 2.92, "learning_rate": 9.980328517564886e-05, "loss": 0.7839, "step": 12360 }, { "epoch": 2.92, "learning_rate": 9.98029669474132e-05, "loss": 0.7388, "step": 12370 }, { "epoch": 2.93, "learning_rate": 9.980264846249264e-05, "loss": 0.7017, "step": 12380 }, { "epoch": 2.93, "learning_rate": 9.98023297208888e-05, "loss": 0.7654, "step": 12390 }, { "epoch": 2.93, "learning_rate": 9.980201072260332e-05, "loss": 0.7092, "step": 12400 }, { "epoch": 2.93, "learning_rate": 9.980169146763787e-05, "loss": 0.7741, "step": 12410 }, { "epoch": 2.94, "learning_rate": 9.980137195599411e-05, "loss": 0.7349, "step": 12420 }, { "epoch": 2.94, "learning_rate": 9.980105218767363e-05, "loss": 0.6772, "step": 12430 }, { "epoch": 2.94, "learning_rate": 9.980073216267813e-05, "loss": 0.7142, "step": 12440 }, { "epoch": 2.94, "learning_rate": 9.980041188100924e-05, "loss": 0.7705, "step": 12450 }, { "epoch": 2.94, "learning_rate": 9.980009134266862e-05, "loss": 0.7495, "step": 12460 }, { "epoch": 2.95, "learning_rate": 9.979977054765788e-05, "loss": 0.7157, "step": 12470 }, { "epoch": 2.95, "learning_rate": 9.979944949597873e-05, "loss": 0.6952, "step": 12480 }, { "epoch": 3.0, "learning_rate": 9.97991281876328e-05, "loss": 0.7607, "step": 12490 }, { "epoch": 3.0, "learning_rate": 9.979880662262175e-05, "loss": 0.7171, "step": 12500 }, { "epoch": 3.0, "learning_rate": 9.979848480094723e-05, "loss": 0.7479, "step": 12510 }, { "epoch": 3.01, "learning_rate": 9.97981627226109e-05, "loss": 0.7185, "step": 12520 }, { "epoch": 3.01, "learning_rate": 9.979784038761442e-05, "loss": 0.7311, "step": 12530 }, { "epoch": 3.01, "learning_rate": 9.979751779595945e-05, "loss": 0.7179, "step": 12540 }, { "epoch": 3.01, "learning_rate": 9.979719494764767e-05, "loss": 0.7264, "step": 12550 }, { "epoch": 3.02, "learning_rate": 9.979687184268074e-05, "loss": 0.7522, "step": 12560 }, { "epoch": 3.02, "learning_rate": 9.97965484810603e-05, "loss": 0.7858, "step": 12570 }, { "epoch": 3.02, "learning_rate": 9.979622486278804e-05, "loss": 0.7509, "step": 12580 }, { "epoch": 3.02, "learning_rate": 9.97959009878656e-05, "loss": 0.7267, "step": 12590 }, { "epoch": 3.03, "learning_rate": 9.979557685629471e-05, "loss": 0.7304, "step": 12600 }, { "epoch": 3.03, "learning_rate": 9.979525246807698e-05, "loss": 0.6946, "step": 12610 }, { "epoch": 3.03, "learning_rate": 9.979492782321409e-05, "loss": 0.7323, "step": 12620 }, { "epoch": 3.03, "learning_rate": 9.979460292170773e-05, "loss": 0.6822, "step": 12630 }, { "epoch": 3.03, "learning_rate": 9.979427776355959e-05, "loss": 0.7791, "step": 12640 }, { "epoch": 3.04, "learning_rate": 9.979395234877131e-05, "loss": 0.7316, "step": 12650 }, { "epoch": 3.04, "learning_rate": 9.979362667734458e-05, "loss": 0.7083, "step": 12660 }, { "epoch": 3.04, "learning_rate": 9.979330074928108e-05, "loss": 0.7474, "step": 12670 }, { "epoch": 3.04, "learning_rate": 9.979297456458251e-05, "loss": 0.6979, "step": 12680 }, { "epoch": 3.05, "learning_rate": 9.979264812325053e-05, "loss": 0.7173, "step": 12690 }, { "epoch": 3.05, "learning_rate": 9.97923214252868e-05, "loss": 0.6893, "step": 12700 }, { "epoch": 3.05, "learning_rate": 9.979199447069306e-05, "loss": 0.7516, "step": 12710 }, { "epoch": 3.05, "learning_rate": 9.979166725947095e-05, "loss": 0.723, "step": 12720 }, { "epoch": 3.06, "learning_rate": 9.979133979162216e-05, "loss": 0.6744, "step": 12730 }, { "epoch": 3.06, "learning_rate": 9.979101206714841e-05, "loss": 0.7639, "step": 12740 }, { "epoch": 3.06, "learning_rate": 9.979068408605136e-05, "loss": 0.6558, "step": 12750 }, { "epoch": 3.06, "learning_rate": 9.979035584833271e-05, "loss": 0.7089, "step": 12760 }, { "epoch": 3.06, "learning_rate": 9.979002735399414e-05, "loss": 0.7199, "step": 12770 }, { "epoch": 3.07, "learning_rate": 9.978969860303736e-05, "loss": 0.7933, "step": 12780 }, { "epoch": 3.07, "learning_rate": 9.978936959546406e-05, "loss": 0.7158, "step": 12790 }, { "epoch": 3.07, "learning_rate": 9.978904033127593e-05, "loss": 0.7474, "step": 12800 }, { "epoch": 3.07, "learning_rate": 9.978871081047468e-05, "loss": 0.7327, "step": 12810 }, { "epoch": 3.08, "learning_rate": 9.978838103306197e-05, "loss": 0.6771, "step": 12820 }, { "epoch": 3.08, "learning_rate": 9.978805099903955e-05, "loss": 0.7012, "step": 12830 }, { "epoch": 3.08, "learning_rate": 9.978772070840909e-05, "loss": 0.722, "step": 12840 }, { "epoch": 3.08, "learning_rate": 9.978739016117232e-05, "loss": 0.7598, "step": 12850 }, { "epoch": 3.08, "learning_rate": 9.97870593573309e-05, "loss": 0.7378, "step": 12860 }, { "epoch": 3.09, "learning_rate": 9.978672829688658e-05, "loss": 0.7192, "step": 12870 }, { "epoch": 3.09, "learning_rate": 9.978639697984102e-05, "loss": 0.6987, "step": 12880 }, { "epoch": 3.09, "learning_rate": 9.978606540619599e-05, "loss": 0.6883, "step": 12890 }, { "epoch": 3.09, "learning_rate": 9.978573357595314e-05, "loss": 0.7322, "step": 12900 }, { "epoch": 3.1, "learning_rate": 9.978540148911419e-05, "loss": 0.7098, "step": 12910 }, { "epoch": 3.1, "learning_rate": 9.978506914568089e-05, "loss": 0.726, "step": 12920 }, { "epoch": 3.1, "learning_rate": 9.978473654565492e-05, "loss": 0.6985, "step": 12930 }, { "epoch": 3.1, "learning_rate": 9.978440368903801e-05, "loss": 0.7334, "step": 12940 }, { "epoch": 3.11, "learning_rate": 9.978407057583186e-05, "loss": 0.8073, "step": 12950 }, { "epoch": 3.11, "learning_rate": 9.978373720603818e-05, "loss": 0.7065, "step": 12960 }, { "epoch": 3.11, "learning_rate": 9.978340357965872e-05, "loss": 0.6588, "step": 12970 }, { "epoch": 3.11, "learning_rate": 9.978306969669517e-05, "loss": 0.6734, "step": 12980 }, { "epoch": 3.11, "learning_rate": 9.978273555714928e-05, "loss": 0.7123, "step": 12990 }, { "epoch": 3.12, "learning_rate": 9.978240116102274e-05, "loss": 0.6639, "step": 13000 }, { "epoch": 3.12, "learning_rate": 9.978206650831729e-05, "loss": 0.7005, "step": 13010 }, { "epoch": 3.12, "learning_rate": 9.978173159903466e-05, "loss": 0.6483, "step": 13020 }, { "epoch": 3.12, "learning_rate": 9.978139643317655e-05, "loss": 0.6992, "step": 13030 }, { "epoch": 3.13, "learning_rate": 9.978106101074473e-05, "loss": 0.6877, "step": 13040 }, { "epoch": 3.13, "learning_rate": 9.978072533174089e-05, "loss": 0.7328, "step": 13050 }, { "epoch": 3.13, "learning_rate": 9.978038939616678e-05, "loss": 0.6893, "step": 13060 }, { "epoch": 3.13, "learning_rate": 9.978005320402412e-05, "loss": 0.7092, "step": 13070 }, { "epoch": 3.14, "learning_rate": 9.977971675531467e-05, "loss": 0.7634, "step": 13080 }, { "epoch": 3.14, "learning_rate": 9.977938005004013e-05, "loss": 0.7008, "step": 13090 }, { "epoch": 3.14, "learning_rate": 9.977904308820224e-05, "loss": 0.7051, "step": 13100 }, { "epoch": 3.14, "learning_rate": 9.977870586980277e-05, "loss": 0.7319, "step": 13110 }, { "epoch": 3.14, "learning_rate": 9.977836839484342e-05, "loss": 0.7253, "step": 13120 }, { "epoch": 3.15, "learning_rate": 9.977803066332594e-05, "loss": 0.6596, "step": 13130 }, { "epoch": 3.15, "learning_rate": 9.977769267525208e-05, "loss": 0.729, "step": 13140 }, { "epoch": 3.15, "learning_rate": 9.977735443062357e-05, "loss": 0.7076, "step": 13150 }, { "epoch": 3.15, "learning_rate": 9.977701592944218e-05, "loss": 0.703, "step": 13160 }, { "epoch": 3.16, "learning_rate": 9.97766771717096e-05, "loss": 0.7191, "step": 13170 }, { "epoch": 3.16, "learning_rate": 9.977633815742764e-05, "loss": 0.7382, "step": 13180 }, { "epoch": 3.16, "learning_rate": 9.977599888659799e-05, "loss": 0.7272, "step": 13190 }, { "epoch": 3.16, "learning_rate": 9.977565935922244e-05, "loss": 0.6929, "step": 13200 }, { "epoch": 3.16, "learning_rate": 9.977531957530273e-05, "loss": 0.6727, "step": 13210 }, { "epoch": 3.17, "learning_rate": 9.97749795348406e-05, "loss": 0.7025, "step": 13220 }, { "epoch": 3.17, "learning_rate": 9.97746392378378e-05, "loss": 0.7353, "step": 13230 }, { "epoch": 3.17, "learning_rate": 9.977429868429612e-05, "loss": 0.6964, "step": 13240 }, { "epoch": 3.17, "learning_rate": 9.977395787421728e-05, "loss": 0.7007, "step": 13250 }, { "epoch": 3.18, "learning_rate": 9.977361680760302e-05, "loss": 0.7562, "step": 13260 }, { "epoch": 3.18, "learning_rate": 9.977327548445515e-05, "loss": 0.6756, "step": 13270 }, { "epoch": 3.18, "learning_rate": 9.97729339047754e-05, "loss": 0.6745, "step": 13280 }, { "epoch": 3.18, "learning_rate": 9.977259206856551e-05, "loss": 0.6696, "step": 13290 }, { "epoch": 3.19, "learning_rate": 9.977224997582728e-05, "loss": 0.7374, "step": 13300 }, { "epoch": 3.19, "learning_rate": 9.977190762656247e-05, "loss": 0.7072, "step": 13310 }, { "epoch": 3.19, "learning_rate": 9.977156502077282e-05, "loss": 0.7368, "step": 13320 }, { "epoch": 3.19, "learning_rate": 9.97712221584601e-05, "loss": 0.6758, "step": 13330 }, { "epoch": 3.19, "learning_rate": 9.97708790396261e-05, "loss": 0.7349, "step": 13340 }, { "epoch": 3.2, "learning_rate": 9.977053566427257e-05, "loss": 0.7403, "step": 13350 }, { "epoch": 3.2, "learning_rate": 9.977019203240128e-05, "loss": 0.6445, "step": 13360 }, { "epoch": 3.2, "learning_rate": 9.9769848144014e-05, "loss": 0.7309, "step": 13370 }, { "epoch": 3.2, "learning_rate": 9.976950399911252e-05, "loss": 0.7523, "step": 13380 }, { "epoch": 3.21, "learning_rate": 9.976915959769857e-05, "loss": 0.7933, "step": 13390 }, { "epoch": 3.21, "learning_rate": 9.976881493977399e-05, "loss": 0.6856, "step": 13400 }, { "epoch": 3.21, "learning_rate": 9.97684700253405e-05, "loss": 0.7066, "step": 13410 }, { "epoch": 3.21, "learning_rate": 9.97681248543999e-05, "loss": 0.6368, "step": 13420 }, { "epoch": 3.22, "learning_rate": 9.976777942695399e-05, "loss": 0.6656, "step": 13430 }, { "epoch": 3.22, "learning_rate": 9.976743374300451e-05, "loss": 0.7525, "step": 13440 }, { "epoch": 3.22, "learning_rate": 9.976708780255326e-05, "loss": 0.6686, "step": 13450 }, { "epoch": 3.22, "learning_rate": 9.976674160560204e-05, "loss": 0.6226, "step": 13460 }, { "epoch": 3.22, "learning_rate": 9.97663951521526e-05, "loss": 0.7066, "step": 13470 }, { "epoch": 3.23, "learning_rate": 9.976604844220675e-05, "loss": 0.6938, "step": 13480 }, { "epoch": 3.23, "learning_rate": 9.976570147576627e-05, "loss": 0.6984, "step": 13490 }, { "epoch": 3.23, "learning_rate": 9.976535425283295e-05, "loss": 0.6581, "step": 13500 }, { "epoch": 3.23, "learning_rate": 9.976500677340858e-05, "loss": 0.6986, "step": 13510 }, { "epoch": 3.24, "learning_rate": 9.976465903749495e-05, "loss": 0.6856, "step": 13520 }, { "epoch": 3.24, "learning_rate": 9.976431104509385e-05, "loss": 0.7291, "step": 13530 }, { "epoch": 3.24, "learning_rate": 9.976396279620706e-05, "loss": 0.6824, "step": 13540 }, { "epoch": 3.24, "learning_rate": 9.97636142908364e-05, "loss": 0.7108, "step": 13550 }, { "epoch": 3.24, "learning_rate": 9.976326552898366e-05, "loss": 0.7787, "step": 13560 }, { "epoch": 3.25, "learning_rate": 9.976291651065064e-05, "loss": 0.7255, "step": 13570 }, { "epoch": 3.25, "learning_rate": 9.976256723583912e-05, "loss": 0.6759, "step": 13580 }, { "epoch": 3.25, "learning_rate": 9.976221770455092e-05, "loss": 0.7742, "step": 13590 }, { "epoch": 3.25, "learning_rate": 9.976186791678782e-05, "loss": 0.6968, "step": 13600 }, { "epoch": 3.26, "learning_rate": 9.976151787255165e-05, "loss": 0.6908, "step": 13610 }, { "epoch": 3.26, "learning_rate": 9.97611675718442e-05, "loss": 0.7266, "step": 13620 }, { "epoch": 3.26, "learning_rate": 9.976081701466727e-05, "loss": 0.7393, "step": 13630 }, { "epoch": 3.26, "learning_rate": 9.976046620102269e-05, "loss": 0.6572, "step": 13640 }, { "epoch": 3.27, "learning_rate": 9.976011513091223e-05, "loss": 0.6976, "step": 13650 }, { "epoch": 3.27, "learning_rate": 9.975976380433774e-05, "loss": 0.6742, "step": 13660 }, { "epoch": 3.27, "learning_rate": 9.975941222130099e-05, "loss": 0.7154, "step": 13670 }, { "epoch": 3.27, "learning_rate": 9.975906038180382e-05, "loss": 0.6597, "step": 13680 }, { "epoch": 3.27, "learning_rate": 9.975870828584805e-05, "loss": 0.6961, "step": 13690 }, { "epoch": 3.28, "learning_rate": 9.975835593343548e-05, "loss": 0.6662, "step": 13700 }, { "epoch": 3.28, "learning_rate": 9.97580033245679e-05, "loss": 0.6939, "step": 13710 }, { "epoch": 3.28, "learning_rate": 9.975765045924719e-05, "loss": 0.7529, "step": 13720 }, { "epoch": 3.28, "learning_rate": 9.975729733747512e-05, "loss": 0.6543, "step": 13730 }, { "epoch": 3.29, "learning_rate": 9.975694395925352e-05, "loss": 0.7257, "step": 13740 }, { "epoch": 3.29, "learning_rate": 9.975659032458422e-05, "loss": 0.6613, "step": 13750 }, { "epoch": 3.29, "learning_rate": 9.975623643346903e-05, "loss": 0.6649, "step": 13760 }, { "epoch": 3.29, "learning_rate": 9.97558822859098e-05, "loss": 0.6797, "step": 13770 }, { "epoch": 3.3, "learning_rate": 9.975552788190832e-05, "loss": 0.6592, "step": 13780 }, { "epoch": 3.3, "learning_rate": 9.975517322146644e-05, "loss": 0.6865, "step": 13790 }, { "epoch": 3.3, "learning_rate": 9.975481830458598e-05, "loss": 0.6584, "step": 13800 }, { "epoch": 3.3, "learning_rate": 9.975446313126876e-05, "loss": 0.6951, "step": 13810 }, { "epoch": 3.3, "learning_rate": 9.975410770151663e-05, "loss": 0.6663, "step": 13820 }, { "epoch": 3.31, "learning_rate": 9.975375201533141e-05, "loss": 0.7078, "step": 13830 }, { "epoch": 3.31, "learning_rate": 9.975339607271494e-05, "loss": 0.6745, "step": 13840 }, { "epoch": 3.31, "learning_rate": 9.975303987366906e-05, "loss": 0.6678, "step": 13850 }, { "epoch": 3.31, "learning_rate": 9.975268341819559e-05, "loss": 0.7403, "step": 13860 }, { "epoch": 3.32, "learning_rate": 9.975232670629635e-05, "loss": 0.6699, "step": 13870 }, { "epoch": 3.32, "learning_rate": 9.975196973797323e-05, "loss": 0.6575, "step": 13880 }, { "epoch": 3.32, "learning_rate": 9.975161251322805e-05, "loss": 0.6641, "step": 13890 }, { "epoch": 3.32, "learning_rate": 9.975125503206262e-05, "loss": 0.6974, "step": 13900 }, { "epoch": 3.32, "learning_rate": 9.97508972944788e-05, "loss": 0.6695, "step": 13910 }, { "epoch": 3.33, "learning_rate": 9.975053930047846e-05, "loss": 0.7097, "step": 13920 }, { "epoch": 3.33, "learning_rate": 9.975018105006342e-05, "loss": 0.6847, "step": 13930 }, { "epoch": 3.33, "learning_rate": 9.974982254323553e-05, "loss": 0.6837, "step": 13940 }, { "epoch": 3.33, "learning_rate": 9.974946377999664e-05, "loss": 0.7384, "step": 13950 }, { "epoch": 3.34, "learning_rate": 9.97491047603486e-05, "loss": 0.725, "step": 13960 }, { "epoch": 3.34, "learning_rate": 9.974874548429326e-05, "loss": 0.6259, "step": 13970 }, { "epoch": 3.34, "learning_rate": 9.974838595183245e-05, "loss": 0.7078, "step": 13980 }, { "epoch": 3.34, "learning_rate": 9.974802616296805e-05, "loss": 0.7067, "step": 13990 }, { "epoch": 3.35, "learning_rate": 9.974766611770192e-05, "loss": 0.671, "step": 14000 }, { "epoch": 3.35, "learning_rate": 9.97473058160359e-05, "loss": 0.7345, "step": 14010 }, { "epoch": 3.35, "learning_rate": 9.974694525797185e-05, "loss": 0.692, "step": 14020 }, { "epoch": 3.35, "learning_rate": 9.974658444351162e-05, "loss": 0.72, "step": 14030 }, { "epoch": 3.35, "learning_rate": 9.974622337265709e-05, "loss": 0.6782, "step": 14040 }, { "epoch": 3.36, "learning_rate": 9.97458620454101e-05, "loss": 0.7069, "step": 14050 }, { "epoch": 3.36, "learning_rate": 9.974550046177252e-05, "loss": 0.7079, "step": 14060 }, { "epoch": 3.36, "learning_rate": 9.974513862174622e-05, "loss": 0.6496, "step": 14070 }, { "epoch": 3.36, "learning_rate": 9.974477652533305e-05, "loss": 0.7847, "step": 14080 }, { "epoch": 3.37, "learning_rate": 9.97444141725349e-05, "loss": 0.6599, "step": 14090 }, { "epoch": 3.37, "learning_rate": 9.974405156335363e-05, "loss": 0.6614, "step": 14100 }, { "epoch": 3.37, "learning_rate": 9.974368869779107e-05, "loss": 0.6803, "step": 14110 }, { "epoch": 3.37, "learning_rate": 9.974332557584916e-05, "loss": 0.6686, "step": 14120 }, { "epoch": 3.38, "learning_rate": 9.974296219752971e-05, "loss": 0.6884, "step": 14130 }, { "epoch": 3.38, "learning_rate": 9.974259856283463e-05, "loss": 0.7054, "step": 14140 }, { "epoch": 3.38, "learning_rate": 9.974223467176577e-05, "loss": 0.6307, "step": 14150 }, { "epoch": 3.38, "learning_rate": 9.974187052432502e-05, "loss": 0.677, "step": 14160 }, { "epoch": 3.38, "learning_rate": 9.974150612051425e-05, "loss": 0.6868, "step": 14170 }, { "epoch": 3.39, "learning_rate": 9.974114146033535e-05, "loss": 0.6881, "step": 14180 }, { "epoch": 3.39, "learning_rate": 9.97407765437902e-05, "loss": 0.6822, "step": 14190 }, { "epoch": 3.39, "learning_rate": 9.974041137088066e-05, "loss": 0.6917, "step": 14200 }, { "epoch": 3.39, "learning_rate": 9.974004594160862e-05, "loss": 0.6696, "step": 14210 }, { "epoch": 3.4, "learning_rate": 9.973968025597597e-05, "loss": 0.6701, "step": 14220 }, { "epoch": 3.4, "learning_rate": 9.973931431398459e-05, "loss": 0.6408, "step": 14230 }, { "epoch": 3.4, "learning_rate": 9.973894811563637e-05, "loss": 0.6711, "step": 14240 }, { "epoch": 3.4, "learning_rate": 9.973858166093319e-05, "loss": 0.6599, "step": 14250 }, { "epoch": 3.4, "learning_rate": 9.973821494987696e-05, "loss": 0.6099, "step": 14260 }, { "epoch": 3.41, "learning_rate": 9.973784798246955e-05, "loss": 0.658, "step": 14270 }, { "epoch": 3.41, "learning_rate": 9.973748075871285e-05, "loss": 0.6594, "step": 14280 }, { "epoch": 3.41, "learning_rate": 9.973711327860877e-05, "loss": 0.6524, "step": 14290 }, { "epoch": 3.41, "learning_rate": 9.973674554215917e-05, "loss": 0.6522, "step": 14300 }, { "epoch": 3.42, "learning_rate": 9.973637754936598e-05, "loss": 0.7251, "step": 14310 }, { "epoch": 3.42, "learning_rate": 9.97360093002311e-05, "loss": 0.68, "step": 14320 }, { "epoch": 3.42, "learning_rate": 9.973564079475639e-05, "loss": 0.6404, "step": 14330 }, { "epoch": 3.42, "learning_rate": 9.973527203294377e-05, "loss": 0.6907, "step": 14340 }, { "epoch": 3.43, "learning_rate": 9.973490301479516e-05, "loss": 0.5897, "step": 14350 }, { "epoch": 3.43, "learning_rate": 9.973453374031244e-05, "loss": 0.6929, "step": 14360 }, { "epoch": 3.43, "learning_rate": 9.97341642094975e-05, "loss": 0.7299, "step": 14370 }, { "epoch": 3.43, "learning_rate": 9.973379442235229e-05, "loss": 0.6725, "step": 14380 }, { "epoch": 3.43, "learning_rate": 9.973342437887867e-05, "loss": 0.7267, "step": 14390 }, { "epoch": 3.44, "learning_rate": 9.973305407907855e-05, "loss": 0.6823, "step": 14400 }, { "epoch": 3.44, "learning_rate": 9.973268352295388e-05, "loss": 0.6532, "step": 14410 }, { "epoch": 3.44, "learning_rate": 9.973231271050654e-05, "loss": 0.6097, "step": 14420 }, { "epoch": 3.44, "learning_rate": 9.973194164173843e-05, "loss": 0.6922, "step": 14430 }, { "epoch": 3.45, "learning_rate": 9.97315703166515e-05, "loss": 0.628, "step": 14440 }, { "epoch": 3.45, "learning_rate": 9.973119873524762e-05, "loss": 0.701, "step": 14450 }, { "epoch": 3.45, "learning_rate": 9.973082689752873e-05, "loss": 0.6521, "step": 14460 }, { "epoch": 3.45, "learning_rate": 9.973045480349675e-05, "loss": 0.7169, "step": 14470 }, { "epoch": 3.45, "learning_rate": 9.973008245315358e-05, "loss": 0.6488, "step": 14480 }, { "epoch": 3.46, "learning_rate": 9.972970984650117e-05, "loss": 0.6449, "step": 14490 }, { "epoch": 3.46, "learning_rate": 9.972933698354139e-05, "loss": 0.7097, "step": 14500 }, { "epoch": 3.46, "learning_rate": 9.972896386427621e-05, "loss": 0.6691, "step": 14510 }, { "epoch": 3.46, "learning_rate": 9.972859048870754e-05, "loss": 0.6669, "step": 14520 }, { "epoch": 3.47, "learning_rate": 9.972821685683729e-05, "loss": 0.7083, "step": 14530 }, { "epoch": 3.47, "learning_rate": 9.972784296866739e-05, "loss": 0.7039, "step": 14540 }, { "epoch": 3.47, "learning_rate": 9.972746882419977e-05, "loss": 0.7087, "step": 14550 }, { "epoch": 3.47, "learning_rate": 9.972709442343637e-05, "loss": 0.7008, "step": 14560 }, { "epoch": 3.48, "learning_rate": 9.972671976637911e-05, "loss": 0.6657, "step": 14570 }, { "epoch": 3.48, "learning_rate": 9.972634485302992e-05, "loss": 0.6788, "step": 14580 }, { "epoch": 3.48, "learning_rate": 9.972596968339072e-05, "loss": 0.6469, "step": 14590 }, { "epoch": 3.48, "learning_rate": 9.972559425746347e-05, "loss": 0.6691, "step": 14600 }, { "epoch": 3.48, "learning_rate": 9.972521857525009e-05, "loss": 0.6462, "step": 14610 }, { "epoch": 3.49, "learning_rate": 9.972484263675252e-05, "loss": 0.7304, "step": 14620 }, { "epoch": 3.49, "learning_rate": 9.972446644197269e-05, "loss": 0.712, "step": 14630 }, { "epoch": 3.49, "learning_rate": 9.972408999091254e-05, "loss": 0.6175, "step": 14640 }, { "epoch": 3.49, "learning_rate": 9.972371328357403e-05, "loss": 0.7472, "step": 14650 }, { "epoch": 3.5, "learning_rate": 9.972333631995907e-05, "loss": 0.6403, "step": 14660 }, { "epoch": 3.5, "learning_rate": 9.972295910006963e-05, "loss": 0.7002, "step": 14670 }, { "epoch": 3.5, "learning_rate": 9.972258162390764e-05, "loss": 0.641, "step": 14680 }, { "epoch": 3.5, "learning_rate": 9.972220389147504e-05, "loss": 0.6696, "step": 14690 }, { "epoch": 3.51, "learning_rate": 9.972182590277379e-05, "loss": 0.6955, "step": 14700 }, { "epoch": 3.51, "learning_rate": 9.972144765780585e-05, "loss": 0.7574, "step": 14710 }, { "epoch": 3.51, "learning_rate": 9.972106915657313e-05, "loss": 0.7097, "step": 14720 }, { "epoch": 3.51, "learning_rate": 9.972069039907762e-05, "loss": 0.6302, "step": 14730 }, { "epoch": 3.51, "learning_rate": 9.972031138532126e-05, "loss": 0.6896, "step": 14740 }, { "epoch": 3.52, "learning_rate": 9.971993211530597e-05, "loss": 0.626, "step": 14750 }, { "epoch": 3.52, "learning_rate": 9.971955258903376e-05, "loss": 0.7111, "step": 14760 }, { "epoch": 3.52, "learning_rate": 9.971917280650656e-05, "loss": 0.6262, "step": 14770 }, { "epoch": 3.52, "learning_rate": 9.971879276772631e-05, "loss": 0.6526, "step": 14780 }, { "epoch": 3.53, "learning_rate": 9.971841247269499e-05, "loss": 0.6731, "step": 14790 }, { "epoch": 3.53, "learning_rate": 9.971803192141458e-05, "loss": 0.7068, "step": 14800 }, { "epoch": 3.53, "learning_rate": 9.9717651113887e-05, "loss": 0.703, "step": 14810 }, { "epoch": 3.53, "learning_rate": 9.971727005011424e-05, "loss": 0.6708, "step": 14820 }, { "epoch": 3.53, "learning_rate": 9.971688873009824e-05, "loss": 0.7239, "step": 14830 }, { "epoch": 3.54, "learning_rate": 9.971650715384098e-05, "loss": 0.6881, "step": 14840 }, { "epoch": 3.54, "learning_rate": 9.971612532134444e-05, "loss": 0.73, "step": 14850 }, { "epoch": 3.54, "learning_rate": 9.971574323261056e-05, "loss": 0.6935, "step": 14860 }, { "epoch": 3.54, "learning_rate": 9.971536088764133e-05, "loss": 0.7511, "step": 14870 }, { "epoch": 3.55, "learning_rate": 9.971497828643873e-05, "loss": 0.7438, "step": 14880 }, { "epoch": 3.55, "learning_rate": 9.97145954290047e-05, "loss": 0.7911, "step": 14890 }, { "epoch": 3.55, "learning_rate": 9.971421231534124e-05, "loss": 0.7597, "step": 14900 }, { "epoch": 3.55, "learning_rate": 9.97138289454503e-05, "loss": 0.7655, "step": 14910 }, { "epoch": 3.56, "learning_rate": 9.971344531933388e-05, "loss": 0.7194, "step": 14920 }, { "epoch": 3.56, "learning_rate": 9.971306143699395e-05, "loss": 0.6617, "step": 14930 }, { "epoch": 3.56, "learning_rate": 9.971267729843248e-05, "loss": 0.7194, "step": 14940 }, { "epoch": 3.56, "learning_rate": 9.971229290365144e-05, "loss": 0.7117, "step": 14950 }, { "epoch": 3.56, "learning_rate": 9.971190825265285e-05, "loss": 0.7911, "step": 14960 }, { "epoch": 3.57, "learning_rate": 9.971152334543866e-05, "loss": 0.7748, "step": 14970 }, { "epoch": 3.57, "learning_rate": 9.971113818201087e-05, "loss": 0.7725, "step": 14980 }, { "epoch": 3.57, "learning_rate": 9.971075276237144e-05, "loss": 0.7045, "step": 14990 }, { "epoch": 3.57, "learning_rate": 9.97103670865224e-05, "loss": 0.7092, "step": 15000 }, { "epoch": 3.58, "learning_rate": 9.97099811544657e-05, "loss": 0.7101, "step": 15010 }, { "epoch": 3.58, "learning_rate": 9.970959496620334e-05, "loss": 0.6981, "step": 15020 }, { "epoch": 3.58, "learning_rate": 9.970920852173732e-05, "loss": 0.7311, "step": 15030 }, { "epoch": 3.58, "learning_rate": 9.970882182106963e-05, "loss": 0.7615, "step": 15040 }, { "epoch": 3.59, "learning_rate": 9.970843486420223e-05, "loss": 0.7228, "step": 15050 }, { "epoch": 3.59, "learning_rate": 9.970804765113716e-05, "loss": 0.65, "step": 15060 }, { "epoch": 3.59, "learning_rate": 9.97076601818764e-05, "loss": 0.7553, "step": 15070 }, { "epoch": 3.59, "learning_rate": 9.970727245642192e-05, "loss": 0.672, "step": 15080 }, { "epoch": 3.59, "learning_rate": 9.970688447477577e-05, "loss": 0.8195, "step": 15090 }, { "epoch": 3.6, "learning_rate": 9.970649623693991e-05, "loss": 0.716, "step": 15100 }, { "epoch": 3.6, "learning_rate": 9.970610774291635e-05, "loss": 0.7376, "step": 15110 }, { "epoch": 3.6, "learning_rate": 9.970571899270711e-05, "loss": 0.8146, "step": 15120 }, { "epoch": 3.6, "learning_rate": 9.970532998631416e-05, "loss": 0.736, "step": 15130 }, { "epoch": 3.61, "learning_rate": 9.970494072373953e-05, "loss": 0.7259, "step": 15140 }, { "epoch": 3.61, "learning_rate": 9.970455120498523e-05, "loss": 0.7188, "step": 15150 }, { "epoch": 3.61, "learning_rate": 9.970416143005325e-05, "loss": 0.7193, "step": 15160 }, { "epoch": 3.61, "learning_rate": 9.97037713989456e-05, "loss": 0.6956, "step": 15170 }, { "epoch": 3.61, "learning_rate": 9.970338111166431e-05, "loss": 0.7151, "step": 15180 }, { "epoch": 3.62, "learning_rate": 9.970299056821137e-05, "loss": 0.7109, "step": 15190 }, { "epoch": 3.62, "learning_rate": 9.97025997685888e-05, "loss": 0.6402, "step": 15200 }, { "epoch": 3.62, "learning_rate": 9.970220871279862e-05, "loss": 0.7486, "step": 15210 }, { "epoch": 3.62, "learning_rate": 9.970181740084284e-05, "loss": 0.7228, "step": 15220 }, { "epoch": 3.63, "learning_rate": 9.970142583272347e-05, "loss": 0.7147, "step": 15230 }, { "epoch": 3.63, "learning_rate": 9.970103400844255e-05, "loss": 0.7005, "step": 15240 }, { "epoch": 3.63, "learning_rate": 9.970064192800207e-05, "loss": 0.746, "step": 15250 }, { "epoch": 3.63, "learning_rate": 9.970024959140407e-05, "loss": 0.7475, "step": 15260 }, { "epoch": 3.64, "learning_rate": 9.969985699865057e-05, "loss": 0.6884, "step": 15270 }, { "epoch": 3.64, "learning_rate": 9.96994641497436e-05, "loss": 0.7319, "step": 15280 }, { "epoch": 3.64, "learning_rate": 9.969907104468517e-05, "loss": 0.6817, "step": 15290 }, { "epoch": 3.64, "learning_rate": 9.969867768347732e-05, "loss": 0.7401, "step": 15300 }, { "epoch": 3.64, "learning_rate": 9.969828406612204e-05, "loss": 0.6865, "step": 15310 }, { "epoch": 3.65, "learning_rate": 9.969789019262143e-05, "loss": 0.6679, "step": 15320 }, { "epoch": 3.65, "learning_rate": 9.969749606297744e-05, "loss": 0.7336, "step": 15330 }, { "epoch": 3.65, "learning_rate": 9.969710167719217e-05, "loss": 0.7087, "step": 15340 }, { "epoch": 3.65, "learning_rate": 9.969670703526762e-05, "loss": 0.7084, "step": 15350 }, { "epoch": 3.66, "learning_rate": 9.96963121372058e-05, "loss": 0.6403, "step": 15360 }, { "epoch": 3.66, "learning_rate": 9.96959169830088e-05, "loss": 0.7086, "step": 15370 }, { "epoch": 3.66, "learning_rate": 9.969552157267862e-05, "loss": 0.6901, "step": 15380 }, { "epoch": 3.66, "learning_rate": 9.96951259062173e-05, "loss": 0.7422, "step": 15390 }, { "epoch": 3.67, "learning_rate": 9.96947299836269e-05, "loss": 0.6738, "step": 15400 }, { "epoch": 3.67, "learning_rate": 9.969433380490943e-05, "loss": 0.6919, "step": 15410 }, { "epoch": 3.67, "learning_rate": 9.969393737006695e-05, "loss": 0.6766, "step": 15420 }, { "epoch": 3.67, "learning_rate": 9.96935406791015e-05, "loss": 0.6349, "step": 15430 }, { "epoch": 3.67, "learning_rate": 9.969314373201515e-05, "loss": 0.7321, "step": 15440 }, { "epoch": 3.68, "learning_rate": 9.969274652880989e-05, "loss": 0.6799, "step": 15450 }, { "epoch": 3.68, "learning_rate": 9.969234906948781e-05, "loss": 0.7329, "step": 15460 }, { "epoch": 3.68, "learning_rate": 9.969195135405096e-05, "loss": 0.6873, "step": 15470 }, { "epoch": 3.68, "learning_rate": 9.969155338250137e-05, "loss": 0.7507, "step": 15480 }, { "epoch": 3.69, "learning_rate": 9.969115515484109e-05, "loss": 0.668, "step": 15490 }, { "epoch": 3.69, "learning_rate": 9.96907566710722e-05, "loss": 0.6333, "step": 15500 }, { "epoch": 3.69, "learning_rate": 9.969035793119672e-05, "loss": 0.6895, "step": 15510 }, { "epoch": 3.69, "learning_rate": 9.968995893521672e-05, "loss": 0.705, "step": 15520 }, { "epoch": 3.69, "learning_rate": 9.968955968313424e-05, "loss": 0.6537, "step": 15530 }, { "epoch": 3.7, "learning_rate": 9.968916017495137e-05, "loss": 0.7259, "step": 15540 }, { "epoch": 3.7, "learning_rate": 9.968876041067017e-05, "loss": 0.7462, "step": 15550 }, { "epoch": 3.7, "learning_rate": 9.968836039029267e-05, "loss": 0.6567, "step": 15560 }, { "epoch": 3.7, "learning_rate": 9.968796011382095e-05, "loss": 0.6993, "step": 15570 }, { "epoch": 3.71, "learning_rate": 9.968755958125706e-05, "loss": 0.7449, "step": 15580 }, { "epoch": 3.71, "learning_rate": 9.968715879260306e-05, "loss": 0.6882, "step": 15590 }, { "epoch": 3.71, "learning_rate": 9.968675774786105e-05, "loss": 0.6369, "step": 15600 }, { "epoch": 3.71, "learning_rate": 9.968635644703308e-05, "loss": 0.6887, "step": 15610 }, { "epoch": 3.72, "learning_rate": 9.96859548901212e-05, "loss": 0.7029, "step": 15620 }, { "epoch": 3.72, "learning_rate": 9.968555307712749e-05, "loss": 0.6588, "step": 15630 }, { "epoch": 3.72, "learning_rate": 9.968515100805402e-05, "loss": 0.7048, "step": 15640 }, { "epoch": 3.72, "learning_rate": 9.968474868290288e-05, "loss": 0.6961, "step": 15650 }, { "epoch": 3.72, "learning_rate": 9.968434610167613e-05, "loss": 0.7017, "step": 15660 }, { "epoch": 3.73, "learning_rate": 9.968394326437584e-05, "loss": 0.7017, "step": 15670 }, { "epoch": 3.73, "learning_rate": 9.968354017100409e-05, "loss": 0.6582, "step": 15680 }, { "epoch": 3.73, "learning_rate": 9.968313682156296e-05, "loss": 0.6956, "step": 15690 }, { "epoch": 3.73, "learning_rate": 9.968273321605452e-05, "loss": 0.748, "step": 15700 }, { "epoch": 3.74, "learning_rate": 9.968232935448087e-05, "loss": 0.7167, "step": 15710 }, { "epoch": 3.74, "learning_rate": 9.968192523684407e-05, "loss": 0.7408, "step": 15720 }, { "epoch": 3.74, "learning_rate": 9.968152086314623e-05, "loss": 0.6648, "step": 15730 }, { "epoch": 3.74, "learning_rate": 9.96811162333894e-05, "loss": 0.7263, "step": 15740 }, { "epoch": 3.75, "learning_rate": 9.968071134757569e-05, "loss": 0.6539, "step": 15750 }, { "epoch": 3.75, "learning_rate": 9.968030620570716e-05, "loss": 0.7166, "step": 15760 }, { "epoch": 3.75, "learning_rate": 9.967990080778594e-05, "loss": 0.7045, "step": 15770 }, { "epoch": 3.75, "learning_rate": 9.967949515381409e-05, "loss": 0.7015, "step": 15780 }, { "epoch": 3.75, "learning_rate": 9.96790892437937e-05, "loss": 0.6483, "step": 15790 }, { "epoch": 3.76, "learning_rate": 9.967868307772687e-05, "loss": 0.7218, "step": 15800 }, { "epoch": 3.76, "learning_rate": 9.967827665561568e-05, "loss": 0.7367, "step": 15810 }, { "epoch": 3.76, "learning_rate": 9.967786997746226e-05, "loss": 0.6439, "step": 15820 }, { "epoch": 3.76, "learning_rate": 9.967746304326869e-05, "loss": 0.6705, "step": 15830 }, { "epoch": 3.77, "learning_rate": 9.967705585303704e-05, "loss": 0.5842, "step": 15840 }, { "epoch": 3.77, "learning_rate": 9.967664840676942e-05, "loss": 0.6432, "step": 15850 }, { "epoch": 3.77, "learning_rate": 9.967624070446795e-05, "loss": 0.664, "step": 15860 }, { "epoch": 3.77, "learning_rate": 9.967583274613473e-05, "loss": 0.6719, "step": 15870 }, { "epoch": 3.77, "learning_rate": 9.967542453177183e-05, "loss": 0.6187, "step": 15880 }, { "epoch": 3.78, "learning_rate": 9.96750160613814e-05, "loss": 0.6577, "step": 15890 }, { "epoch": 3.78, "learning_rate": 9.967460733496552e-05, "loss": 0.6419, "step": 15900 }, { "epoch": 3.78, "learning_rate": 9.967419835252629e-05, "loss": 0.656, "step": 15910 }, { "epoch": 3.78, "learning_rate": 9.967378911406582e-05, "loss": 0.6652, "step": 15920 }, { "epoch": 3.79, "learning_rate": 9.967337961958623e-05, "loss": 0.7286, "step": 15930 }, { "epoch": 3.79, "learning_rate": 9.967296986908964e-05, "loss": 0.6662, "step": 15940 }, { "epoch": 3.79, "learning_rate": 9.967255986257814e-05, "loss": 0.7024, "step": 15950 }, { "epoch": 3.79, "learning_rate": 9.967214960005384e-05, "loss": 0.6642, "step": 15960 }, { "epoch": 3.8, "learning_rate": 9.967173908151887e-05, "loss": 0.6718, "step": 15970 }, { "epoch": 3.8, "learning_rate": 9.967132830697536e-05, "loss": 0.6747, "step": 15980 }, { "epoch": 3.8, "learning_rate": 9.967091727642539e-05, "loss": 0.7573, "step": 15990 }, { "epoch": 3.8, "learning_rate": 9.967050598987111e-05, "loss": 0.7476, "step": 16000 }, { "epoch": 3.8, "learning_rate": 9.96700944473146e-05, "loss": 0.6497, "step": 16010 }, { "epoch": 3.81, "learning_rate": 9.966968264875805e-05, "loss": 0.688, "step": 16020 }, { "epoch": 3.81, "learning_rate": 9.96692705942035e-05, "loss": 0.6779, "step": 16030 }, { "epoch": 3.81, "learning_rate": 9.966885828365314e-05, "loss": 0.7382, "step": 16040 }, { "epoch": 3.81, "learning_rate": 9.966844571710906e-05, "loss": 0.6894, "step": 16050 }, { "epoch": 3.82, "learning_rate": 9.96680328945734e-05, "loss": 0.6134, "step": 16060 }, { "epoch": 3.82, "learning_rate": 9.966761981604829e-05, "loss": 0.6987, "step": 16070 }, { "epoch": 3.82, "learning_rate": 9.966720648153584e-05, "loss": 0.6705, "step": 16080 }, { "epoch": 3.82, "learning_rate": 9.966679289103819e-05, "loss": 0.6663, "step": 16090 }, { "epoch": 3.83, "learning_rate": 9.966637904455748e-05, "loss": 0.6939, "step": 16100 }, { "epoch": 3.83, "learning_rate": 9.966596494209583e-05, "loss": 0.6685, "step": 16110 }, { "epoch": 3.83, "learning_rate": 9.966555058365538e-05, "loss": 0.6616, "step": 16120 }, { "epoch": 3.83, "learning_rate": 9.966513596923828e-05, "loss": 0.6804, "step": 16130 }, { "epoch": 3.83, "learning_rate": 9.966472109884666e-05, "loss": 0.7303, "step": 16140 }, { "epoch": 3.84, "learning_rate": 9.966430597248265e-05, "loss": 0.7245, "step": 16150 }, { "epoch": 3.84, "learning_rate": 9.966389059014838e-05, "loss": 0.682, "step": 16160 }, { "epoch": 3.84, "learning_rate": 9.9663474951846e-05, "loss": 0.6233, "step": 16170 }, { "epoch": 3.84, "learning_rate": 9.966305905757767e-05, "loss": 0.7376, "step": 16180 }, { "epoch": 3.85, "learning_rate": 9.96626429073455e-05, "loss": 0.7224, "step": 16190 }, { "epoch": 3.85, "learning_rate": 9.966222650115167e-05, "loss": 0.64, "step": 16200 }, { "epoch": 3.85, "learning_rate": 9.96618098389983e-05, "loss": 0.7058, "step": 16210 }, { "epoch": 3.85, "learning_rate": 9.966139292088754e-05, "loss": 0.6377, "step": 16220 }, { "epoch": 3.85, "learning_rate": 9.966097574682156e-05, "loss": 0.5834, "step": 16230 }, { "epoch": 3.86, "learning_rate": 9.96605583168025e-05, "loss": 0.6915, "step": 16240 }, { "epoch": 3.86, "learning_rate": 9.966014063083249e-05, "loss": 0.6335, "step": 16250 }, { "epoch": 3.86, "learning_rate": 9.965972268891372e-05, "loss": 0.702, "step": 16260 }, { "epoch": 3.86, "learning_rate": 9.96593044910483e-05, "loss": 0.6419, "step": 16270 }, { "epoch": 3.87, "learning_rate": 9.965888603723843e-05, "loss": 0.577, "step": 16280 }, { "epoch": 3.87, "learning_rate": 9.965846732748624e-05, "loss": 0.6591, "step": 16290 }, { "epoch": 3.87, "learning_rate": 9.965804836179389e-05, "loss": 0.6344, "step": 16300 }, { "epoch": 3.87, "learning_rate": 9.965762914016355e-05, "loss": 0.7058, "step": 16310 }, { "epoch": 3.88, "learning_rate": 9.965720966259737e-05, "loss": 0.6443, "step": 16320 }, { "epoch": 3.88, "learning_rate": 9.965678992909751e-05, "loss": 0.6722, "step": 16330 }, { "epoch": 3.88, "learning_rate": 9.965636993966616e-05, "loss": 0.6948, "step": 16340 }, { "epoch": 3.88, "learning_rate": 9.965594969430545e-05, "loss": 0.6137, "step": 16350 }, { "epoch": 3.88, "learning_rate": 9.965552919301755e-05, "loss": 0.6552, "step": 16360 }, { "epoch": 3.89, "learning_rate": 9.965510843580465e-05, "loss": 0.647, "step": 16370 }, { "epoch": 3.89, "learning_rate": 9.965468742266891e-05, "loss": 0.6467, "step": 16380 }, { "epoch": 3.89, "learning_rate": 9.965426615361249e-05, "loss": 0.643, "step": 16390 }, { "epoch": 3.89, "learning_rate": 9.965384462863757e-05, "loss": 0.7017, "step": 16400 }, { "epoch": 3.9, "learning_rate": 9.965342284774632e-05, "loss": 0.6612, "step": 16410 }, { "epoch": 3.9, "learning_rate": 9.965300081094092e-05, "loss": 0.6309, "step": 16420 }, { "epoch": 3.9, "learning_rate": 9.965257851822352e-05, "loss": 0.6965, "step": 16430 }, { "epoch": 3.9, "learning_rate": 9.965215596959633e-05, "loss": 0.6109, "step": 16440 }, { "epoch": 3.91, "learning_rate": 9.965173316506151e-05, "loss": 0.6251, "step": 16450 }, { "epoch": 3.91, "learning_rate": 9.965131010462123e-05, "loss": 0.685, "step": 16460 }, { "epoch": 3.91, "learning_rate": 9.96508867882777e-05, "loss": 0.5557, "step": 16470 }, { "epoch": 3.91, "learning_rate": 9.965046321603309e-05, "loss": 0.6864, "step": 16480 }, { "epoch": 3.91, "learning_rate": 9.965003938788955e-05, "loss": 0.6665, "step": 16490 }, { "epoch": 3.92, "learning_rate": 9.96496153038493e-05, "loss": 0.6281, "step": 16500 }, { "epoch": 3.92, "learning_rate": 9.964919096391454e-05, "loss": 0.5982, "step": 16510 }, { "epoch": 3.92, "learning_rate": 9.964876636808742e-05, "loss": 0.6316, "step": 16520 }, { "epoch": 3.92, "learning_rate": 9.964834151637015e-05, "loss": 0.6657, "step": 16530 }, { "epoch": 3.93, "learning_rate": 9.96479164087649e-05, "loss": 0.6512, "step": 16540 }, { "epoch": 3.93, "learning_rate": 9.964749104527389e-05, "loss": 0.7015, "step": 16550 }, { "epoch": 3.93, "learning_rate": 9.964706542589928e-05, "loss": 0.6416, "step": 16560 }, { "epoch": 3.93, "learning_rate": 9.964663955064328e-05, "loss": 0.6494, "step": 16570 }, { "epoch": 3.93, "learning_rate": 9.96462134195081e-05, "loss": 0.646, "step": 16580 }, { "epoch": 3.94, "learning_rate": 9.964578703249591e-05, "loss": 0.5965, "step": 16590 }, { "epoch": 3.94, "learning_rate": 9.964536038960891e-05, "loss": 0.6598, "step": 16600 }, { "epoch": 3.94, "learning_rate": 9.964493349084933e-05, "loss": 0.6314, "step": 16610 }, { "epoch": 3.94, "learning_rate": 9.964450633621933e-05, "loss": 0.7078, "step": 16620 }, { "epoch": 3.95, "learning_rate": 9.964407892572114e-05, "loss": 0.6855, "step": 16630 }, { "epoch": 3.95, "learning_rate": 9.964365125935696e-05, "loss": 0.7111, "step": 16640 }, { "epoch": 3.95, "learning_rate": 9.964322333712896e-05, "loss": 0.6149, "step": 16650 }, { "epoch": 4.0, "learning_rate": 9.964279515903938e-05, "loss": 0.6531, "step": 16660 }, { "epoch": 4.0, "learning_rate": 9.964236672509043e-05, "loss": 0.6356, "step": 16670 }, { "epoch": 4.01, "learning_rate": 9.96419380352843e-05, "loss": 0.6623, "step": 16680 }, { "epoch": 4.01, "learning_rate": 9.96415090896232e-05, "loss": 0.6419, "step": 16690 }, { "epoch": 4.01, "learning_rate": 9.964107988810937e-05, "loss": 0.6614, "step": 16700 }, { "epoch": 4.01, "learning_rate": 9.964065043074498e-05, "loss": 0.5796, "step": 16710 }, { "epoch": 4.02, "learning_rate": 9.964022071753228e-05, "loss": 0.578, "step": 16720 }, { "epoch": 4.02, "learning_rate": 9.963979074847345e-05, "loss": 0.6573, "step": 16730 }, { "epoch": 4.02, "learning_rate": 9.963936052357073e-05, "loss": 0.6124, "step": 16740 }, { "epoch": 4.02, "learning_rate": 9.963893004282632e-05, "loss": 0.6295, "step": 16750 }, { "epoch": 4.02, "learning_rate": 9.963849930624247e-05, "loss": 0.6038, "step": 16760 }, { "epoch": 4.03, "learning_rate": 9.963806831382137e-05, "loss": 0.6255, "step": 16770 }, { "epoch": 4.03, "learning_rate": 9.963763706556524e-05, "loss": 0.6749, "step": 16780 }, { "epoch": 4.03, "learning_rate": 9.963720556147632e-05, "loss": 0.6077, "step": 16790 }, { "epoch": 4.03, "learning_rate": 9.963677380155683e-05, "loss": 0.6254, "step": 16800 }, { "epoch": 4.04, "learning_rate": 9.9636341785809e-05, "loss": 0.6256, "step": 16810 }, { "epoch": 4.04, "learning_rate": 9.963590951423505e-05, "loss": 0.6107, "step": 16820 }, { "epoch": 4.04, "learning_rate": 9.96354769868372e-05, "loss": 0.6101, "step": 16830 }, { "epoch": 4.04, "learning_rate": 9.963504420361767e-05, "loss": 0.6659, "step": 16840 }, { "epoch": 4.05, "learning_rate": 9.963461116457873e-05, "loss": 0.6451, "step": 16850 }, { "epoch": 4.05, "learning_rate": 9.963417786972259e-05, "loss": 0.6355, "step": 16860 }, { "epoch": 4.05, "learning_rate": 9.963374431905147e-05, "loss": 0.6171, "step": 16870 }, { "epoch": 4.05, "learning_rate": 9.963331051256763e-05, "loss": 0.557, "step": 16880 }, { "epoch": 4.05, "learning_rate": 9.963287645027328e-05, "loss": 0.6193, "step": 16890 }, { "epoch": 4.06, "learning_rate": 9.963244213217069e-05, "loss": 0.6823, "step": 16900 }, { "epoch": 4.06, "learning_rate": 9.963200755826205e-05, "loss": 0.578, "step": 16910 }, { "epoch": 4.06, "learning_rate": 9.963157272854965e-05, "loss": 0.5395, "step": 16920 }, { "epoch": 4.06, "learning_rate": 9.96311376430357e-05, "loss": 0.5659, "step": 16930 }, { "epoch": 4.07, "learning_rate": 9.963070230172245e-05, "loss": 0.6663, "step": 16940 }, { "epoch": 4.07, "learning_rate": 9.963026670461215e-05, "loss": 0.688, "step": 16950 }, { "epoch": 4.07, "learning_rate": 9.962983085170705e-05, "loss": 0.6378, "step": 16960 }, { "epoch": 4.07, "learning_rate": 9.962939474300938e-05, "loss": 0.6029, "step": 16970 }, { "epoch": 4.07, "learning_rate": 9.962895837852137e-05, "loss": 0.6265, "step": 16980 }, { "epoch": 4.08, "learning_rate": 9.962852175824533e-05, "loss": 0.5693, "step": 16990 }, { "epoch": 4.08, "learning_rate": 9.962808488218346e-05, "loss": 0.6767, "step": 17000 }, { "epoch": 4.08, "learning_rate": 9.962764775033801e-05, "loss": 0.6443, "step": 17010 }, { "epoch": 4.08, "learning_rate": 9.962721036271127e-05, "loss": 0.6315, "step": 17020 }, { "epoch": 4.09, "learning_rate": 9.962677271930548e-05, "loss": 0.6324, "step": 17030 }, { "epoch": 4.09, "learning_rate": 9.962633482012286e-05, "loss": 0.5962, "step": 17040 }, { "epoch": 4.09, "learning_rate": 9.962589666516572e-05, "loss": 0.6615, "step": 17050 }, { "epoch": 4.09, "learning_rate": 9.962545825443628e-05, "loss": 0.6645, "step": 17060 }, { "epoch": 4.1, "learning_rate": 9.962501958793682e-05, "loss": 0.6139, "step": 17070 }, { "epoch": 4.1, "learning_rate": 9.96245806656696e-05, "loss": 0.5923, "step": 17080 }, { "epoch": 4.1, "learning_rate": 9.962414148763685e-05, "loss": 0.5579, "step": 17090 }, { "epoch": 4.1, "learning_rate": 9.962370205384089e-05, "loss": 0.6028, "step": 17100 }, { "epoch": 4.1, "learning_rate": 9.962326236428395e-05, "loss": 0.5966, "step": 17110 }, { "epoch": 4.11, "learning_rate": 9.962282241896828e-05, "loss": 0.6134, "step": 17120 }, { "epoch": 4.11, "learning_rate": 9.96223822178962e-05, "loss": 0.5467, "step": 17130 }, { "epoch": 4.11, "learning_rate": 9.962194176106991e-05, "loss": 0.6576, "step": 17140 }, { "epoch": 4.11, "learning_rate": 9.962150104849175e-05, "loss": 0.6469, "step": 17150 }, { "epoch": 4.12, "learning_rate": 9.962106008016395e-05, "loss": 0.5619, "step": 17160 }, { "epoch": 4.12, "learning_rate": 9.962061885608878e-05, "loss": 0.5793, "step": 17170 }, { "epoch": 4.12, "learning_rate": 9.962017737626854e-05, "loss": 0.5786, "step": 17180 }, { "epoch": 4.12, "learning_rate": 9.961973564070548e-05, "loss": 0.5913, "step": 17190 }, { "epoch": 4.13, "learning_rate": 9.96192936494019e-05, "loss": 0.6262, "step": 17200 }, { "epoch": 4.13, "learning_rate": 9.961885140236005e-05, "loss": 0.5921, "step": 17210 }, { "epoch": 4.13, "learning_rate": 9.961840889958222e-05, "loss": 0.6332, "step": 17220 }, { "epoch": 4.13, "learning_rate": 9.961796614107073e-05, "loss": 0.6856, "step": 17230 }, { "epoch": 4.13, "learning_rate": 9.961752312682779e-05, "loss": 0.6096, "step": 17240 }, { "epoch": 4.14, "learning_rate": 9.961707985685574e-05, "loss": 0.5758, "step": 17250 }, { "epoch": 4.14, "learning_rate": 9.961663633115685e-05, "loss": 0.6009, "step": 17260 }, { "epoch": 4.14, "learning_rate": 9.96161925497334e-05, "loss": 0.6407, "step": 17270 }, { "epoch": 4.14, "learning_rate": 9.961574851258767e-05, "loss": 0.6121, "step": 17280 }, { "epoch": 4.15, "learning_rate": 9.961530421972197e-05, "loss": 0.5546, "step": 17290 }, { "epoch": 4.15, "learning_rate": 9.961485967113855e-05, "loss": 0.504, "step": 17300 }, { "epoch": 4.15, "learning_rate": 9.961441486683976e-05, "loss": 0.5488, "step": 17310 }, { "epoch": 4.15, "learning_rate": 9.961396980682784e-05, "loss": 0.5591, "step": 17320 }, { "epoch": 4.15, "learning_rate": 9.961352449110511e-05, "loss": 0.5935, "step": 17330 }, { "epoch": 4.16, "learning_rate": 9.961307891967387e-05, "loss": 0.6202, "step": 17340 }, { "epoch": 4.16, "learning_rate": 9.96126330925364e-05, "loss": 0.653, "step": 17350 }, { "epoch": 4.16, "learning_rate": 9.9612187009695e-05, "loss": 0.5749, "step": 17360 }, { "epoch": 4.16, "learning_rate": 9.961174067115198e-05, "loss": 0.5256, "step": 17370 }, { "epoch": 4.17, "learning_rate": 9.961129407690964e-05, "loss": 0.5703, "step": 17380 }, { "epoch": 4.17, "learning_rate": 9.961084722697026e-05, "loss": 0.6623, "step": 17390 }, { "epoch": 4.17, "learning_rate": 9.961040012133617e-05, "loss": 0.6512, "step": 17400 }, { "epoch": 4.17, "learning_rate": 9.960995276000966e-05, "loss": 0.6408, "step": 17410 }, { "epoch": 4.18, "learning_rate": 9.960950514299303e-05, "loss": 0.6225, "step": 17420 }, { "epoch": 4.18, "learning_rate": 9.96090572702886e-05, "loss": 0.5694, "step": 17430 }, { "epoch": 4.18, "learning_rate": 9.960860914189869e-05, "loss": 0.5682, "step": 17440 }, { "epoch": 4.18, "learning_rate": 9.960816075782558e-05, "loss": 0.6177, "step": 17450 }, { "epoch": 4.18, "learning_rate": 9.960771211807158e-05, "loss": 0.6494, "step": 17460 }, { "epoch": 4.19, "learning_rate": 9.960726322263905e-05, "loss": 0.6171, "step": 17470 }, { "epoch": 4.19, "learning_rate": 9.960681407153025e-05, "loss": 0.5772, "step": 17480 }, { "epoch": 4.19, "learning_rate": 9.960636466474752e-05, "loss": 0.6161, "step": 17490 }, { "epoch": 4.19, "learning_rate": 9.960591500229316e-05, "loss": 0.6044, "step": 17500 }, { "epoch": 4.2, "learning_rate": 9.960546508416952e-05, "loss": 0.6119, "step": 17510 }, { "epoch": 4.2, "learning_rate": 9.960501491037889e-05, "loss": 0.6376, "step": 17520 }, { "epoch": 4.2, "learning_rate": 9.96045644809236e-05, "loss": 0.609, "step": 17530 }, { "epoch": 4.2, "learning_rate": 9.960411379580597e-05, "loss": 0.6257, "step": 17540 }, { "epoch": 4.21, "learning_rate": 9.960366285502831e-05, "loss": 0.5465, "step": 17550 }, { "epoch": 4.21, "learning_rate": 9.960321165859297e-05, "loss": 0.5037, "step": 17560 }, { "epoch": 4.21, "learning_rate": 9.960276020650227e-05, "loss": 0.6006, "step": 17570 }, { "epoch": 4.21, "learning_rate": 9.960230849875851e-05, "loss": 0.6241, "step": 17580 }, { "epoch": 4.21, "learning_rate": 9.960185653536405e-05, "loss": 0.6521, "step": 17590 }, { "epoch": 4.22, "learning_rate": 9.960140431632121e-05, "loss": 0.5959, "step": 17600 }, { "epoch": 4.22, "learning_rate": 9.960095184163231e-05, "loss": 0.6088, "step": 17610 }, { "epoch": 4.22, "learning_rate": 9.960049911129969e-05, "loss": 0.5689, "step": 17620 }, { "epoch": 4.22, "learning_rate": 9.960004612532567e-05, "loss": 0.6844, "step": 17630 }, { "epoch": 4.23, "learning_rate": 9.959959288371262e-05, "loss": 0.5187, "step": 17640 }, { "epoch": 4.23, "learning_rate": 9.959913938646284e-05, "loss": 0.5859, "step": 17650 }, { "epoch": 4.23, "learning_rate": 9.95986856335787e-05, "loss": 0.6273, "step": 17660 }, { "epoch": 4.23, "learning_rate": 9.95982316250625e-05, "loss": 0.6294, "step": 17670 }, { "epoch": 4.23, "learning_rate": 9.95977773609166e-05, "loss": 0.598, "step": 17680 }, { "epoch": 4.24, "learning_rate": 9.959732284114336e-05, "loss": 0.6225, "step": 17690 }, { "epoch": 4.24, "learning_rate": 9.959686806574509e-05, "loss": 0.6338, "step": 17700 }, { "epoch": 4.24, "learning_rate": 9.959641303472414e-05, "loss": 0.6651, "step": 17710 }, { "epoch": 4.24, "learning_rate": 9.959595774808287e-05, "loss": 0.5839, "step": 17720 }, { "epoch": 4.25, "learning_rate": 9.959550220582362e-05, "loss": 0.5442, "step": 17730 }, { "epoch": 4.25, "learning_rate": 9.959504640794873e-05, "loss": 0.5552, "step": 17740 }, { "epoch": 4.25, "learning_rate": 9.959459035446057e-05, "loss": 0.6149, "step": 17750 }, { "epoch": 4.25, "learning_rate": 9.959413404536146e-05, "loss": 0.6257, "step": 17760 }, { "epoch": 4.26, "learning_rate": 9.959367748065378e-05, "loss": 0.5785, "step": 17770 }, { "epoch": 4.26, "learning_rate": 9.959322066033987e-05, "loss": 0.6096, "step": 17780 }, { "epoch": 4.26, "learning_rate": 9.959276358442208e-05, "loss": 0.6442, "step": 17790 }, { "epoch": 4.26, "learning_rate": 9.959230625290279e-05, "loss": 0.5979, "step": 17800 }, { "epoch": 4.26, "learning_rate": 9.959184866578432e-05, "loss": 0.6674, "step": 17810 }, { "epoch": 4.27, "learning_rate": 9.959139082306906e-05, "loss": 0.5982, "step": 17820 }, { "epoch": 4.27, "learning_rate": 9.959093272475934e-05, "loss": 0.5288, "step": 17830 }, { "epoch": 4.27, "learning_rate": 9.959047437085755e-05, "loss": 0.5606, "step": 17840 }, { "epoch": 4.27, "learning_rate": 9.959001576136605e-05, "loss": 0.5984, "step": 17850 }, { "epoch": 4.28, "learning_rate": 9.958955689628718e-05, "loss": 0.5569, "step": 17860 }, { "epoch": 4.28, "learning_rate": 9.958909777562333e-05, "loss": 0.6532, "step": 17870 }, { "epoch": 4.28, "learning_rate": 9.958863839937684e-05, "loss": 0.603, "step": 17880 }, { "epoch": 4.28, "learning_rate": 9.958817876755012e-05, "loss": 0.6127, "step": 17890 }, { "epoch": 4.29, "learning_rate": 9.958771888014548e-05, "loss": 0.5975, "step": 17900 }, { "epoch": 4.29, "learning_rate": 9.958725873716534e-05, "loss": 0.6329, "step": 17910 }, { "epoch": 4.29, "learning_rate": 9.958679833861205e-05, "loss": 0.5696, "step": 17920 }, { "epoch": 4.29, "learning_rate": 9.9586337684488e-05, "loss": 0.5905, "step": 17930 }, { "epoch": 4.29, "learning_rate": 9.958587677479552e-05, "loss": 0.5247, "step": 17940 }, { "epoch": 4.3, "learning_rate": 9.958541560953705e-05, "loss": 0.5657, "step": 17950 }, { "epoch": 4.3, "learning_rate": 9.958495418871491e-05, "loss": 0.5855, "step": 17960 }, { "epoch": 4.3, "learning_rate": 9.958449251233152e-05, "loss": 0.5856, "step": 17970 }, { "epoch": 4.3, "learning_rate": 9.958403058038923e-05, "loss": 0.5786, "step": 17980 }, { "epoch": 4.31, "learning_rate": 9.958356839289042e-05, "loss": 0.6002, "step": 17990 }, { "epoch": 4.31, "learning_rate": 9.958310594983751e-05, "loss": 0.5057, "step": 18000 }, { "epoch": 4.31, "learning_rate": 9.958264325123285e-05, "loss": 0.5471, "step": 18010 }, { "epoch": 4.31, "learning_rate": 9.958218029707882e-05, "loss": 0.5309, "step": 18020 }, { "epoch": 4.31, "learning_rate": 9.958171708737782e-05, "loss": 0.479, "step": 18030 }, { "epoch": 4.32, "learning_rate": 9.958125362213224e-05, "loss": 0.6244, "step": 18040 }, { "epoch": 4.32, "learning_rate": 9.958078990134448e-05, "loss": 0.5246, "step": 18050 }, { "epoch": 4.32, "learning_rate": 9.95803259250169e-05, "loss": 0.5726, "step": 18060 }, { "epoch": 4.32, "learning_rate": 9.95798616931519e-05, "loss": 0.5393, "step": 18070 }, { "epoch": 4.33, "learning_rate": 9.95793972057519e-05, "loss": 0.5883, "step": 18080 }, { "epoch": 4.33, "learning_rate": 9.957893246281924e-05, "loss": 0.5511, "step": 18090 }, { "epoch": 4.33, "learning_rate": 9.957846746435637e-05, "loss": 0.5249, "step": 18100 }, { "epoch": 4.33, "learning_rate": 9.957800221036567e-05, "loss": 0.5772, "step": 18110 }, { "epoch": 4.34, "learning_rate": 9.95775367008495e-05, "loss": 0.5671, "step": 18120 }, { "epoch": 4.34, "learning_rate": 9.957707093581033e-05, "loss": 0.6143, "step": 18130 }, { "epoch": 4.34, "learning_rate": 9.95766049152505e-05, "loss": 0.6123, "step": 18140 }, { "epoch": 4.34, "learning_rate": 9.957613863917243e-05, "loss": 0.5175, "step": 18150 }, { "epoch": 4.34, "learning_rate": 9.957567210757854e-05, "loss": 0.5497, "step": 18160 }, { "epoch": 4.35, "learning_rate": 9.957520532047122e-05, "loss": 0.4641, "step": 18170 }, { "epoch": 4.35, "learning_rate": 9.957473827785287e-05, "loss": 0.6307, "step": 18180 }, { "epoch": 4.35, "learning_rate": 9.957427097972591e-05, "loss": 0.5782, "step": 18190 }, { "epoch": 4.35, "learning_rate": 9.957380342609275e-05, "loss": 0.6296, "step": 18200 }, { "epoch": 4.36, "learning_rate": 9.957333561695578e-05, "loss": 0.5821, "step": 18210 }, { "epoch": 4.36, "learning_rate": 9.957286755231742e-05, "loss": 0.5746, "step": 18220 }, { "epoch": 4.36, "learning_rate": 9.95723992321801e-05, "loss": 0.5732, "step": 18230 }, { "epoch": 4.36, "learning_rate": 9.957193065654623e-05, "loss": 0.6115, "step": 18240 }, { "epoch": 4.37, "learning_rate": 9.957146182541818e-05, "loss": 0.555, "step": 18250 }, { "epoch": 4.37, "learning_rate": 9.957099273879842e-05, "loss": 0.6158, "step": 18260 }, { "epoch": 4.37, "learning_rate": 9.957052339668935e-05, "loss": 0.6073, "step": 18270 }, { "epoch": 4.37, "learning_rate": 9.957005379909339e-05, "loss": 0.6856, "step": 18280 }, { "epoch": 4.37, "learning_rate": 9.956958394601297e-05, "loss": 0.5841, "step": 18290 }, { "epoch": 4.38, "learning_rate": 9.956911383745047e-05, "loss": 0.5705, "step": 18300 }, { "epoch": 4.38, "learning_rate": 9.956864347340838e-05, "loss": 0.5536, "step": 18310 }, { "epoch": 4.38, "learning_rate": 9.956817285388906e-05, "loss": 0.5993, "step": 18320 }, { "epoch": 4.38, "learning_rate": 9.956770197889495e-05, "loss": 0.5363, "step": 18330 }, { "epoch": 4.39, "learning_rate": 9.956723084842851e-05, "loss": 0.5813, "step": 18340 }, { "epoch": 4.39, "learning_rate": 9.956675946249216e-05, "loss": 0.493, "step": 18350 }, { "epoch": 4.39, "learning_rate": 9.95662878210883e-05, "loss": 0.571, "step": 18360 }, { "epoch": 4.39, "learning_rate": 9.956581592421938e-05, "loss": 0.5672, "step": 18370 }, { "epoch": 4.39, "learning_rate": 9.956534377188784e-05, "loss": 0.5662, "step": 18380 }, { "epoch": 4.4, "learning_rate": 9.95648713640961e-05, "loss": 0.5733, "step": 18390 }, { "epoch": 4.4, "learning_rate": 9.95643987008466e-05, "loss": 0.5819, "step": 18400 }, { "epoch": 4.4, "learning_rate": 9.956392578214177e-05, "loss": 0.6519, "step": 18410 }, { "epoch": 4.4, "learning_rate": 9.956345260798406e-05, "loss": 0.5743, "step": 18420 }, { "epoch": 4.41, "learning_rate": 9.956297917837588e-05, "loss": 0.6011, "step": 18430 }, { "epoch": 4.41, "learning_rate": 9.956250549331971e-05, "loss": 0.5656, "step": 18440 }, { "epoch": 4.41, "learning_rate": 9.956203155281796e-05, "loss": 0.5791, "step": 18450 }, { "epoch": 4.41, "learning_rate": 9.956155735687309e-05, "loss": 0.5767, "step": 18460 }, { "epoch": 4.42, "learning_rate": 9.956108290548756e-05, "loss": 0.571, "step": 18470 }, { "epoch": 4.42, "learning_rate": 9.956060819866376e-05, "loss": 0.5513, "step": 18480 }, { "epoch": 4.42, "learning_rate": 9.956013323640418e-05, "loss": 0.5654, "step": 18490 }, { "epoch": 4.42, "learning_rate": 9.955965801871128e-05, "loss": 0.5599, "step": 18500 }, { "epoch": 4.42, "learning_rate": 9.955918254558746e-05, "loss": 0.5791, "step": 18510 }, { "epoch": 4.43, "learning_rate": 9.955870681703522e-05, "loss": 0.4964, "step": 18520 }, { "epoch": 4.43, "learning_rate": 9.9558230833057e-05, "loss": 0.5809, "step": 18530 }, { "epoch": 4.43, "learning_rate": 9.955775459365522e-05, "loss": 0.5982, "step": 18540 }, { "epoch": 4.43, "learning_rate": 9.955727809883237e-05, "loss": 0.5779, "step": 18550 }, { "epoch": 4.44, "learning_rate": 9.955680134859088e-05, "loss": 0.5465, "step": 18560 }, { "epoch": 4.44, "learning_rate": 9.955632434293324e-05, "loss": 0.5338, "step": 18570 }, { "epoch": 4.44, "learning_rate": 9.955584708186188e-05, "loss": 0.4795, "step": 18580 }, { "epoch": 4.44, "learning_rate": 9.955536956537928e-05, "loss": 0.5583, "step": 18590 }, { "epoch": 4.45, "learning_rate": 9.955489179348788e-05, "loss": 0.5772, "step": 18600 }, { "epoch": 4.45, "learning_rate": 9.955441376619016e-05, "loss": 0.5462, "step": 18610 }, { "epoch": 4.45, "learning_rate": 9.955393548348857e-05, "loss": 0.5489, "step": 18620 }, { "epoch": 4.45, "learning_rate": 9.955345694538558e-05, "loss": 0.6088, "step": 18630 }, { "epoch": 4.45, "learning_rate": 9.955297815188367e-05, "loss": 0.505, "step": 18640 }, { "epoch": 4.46, "learning_rate": 9.95524991029853e-05, "loss": 0.5911, "step": 18650 }, { "epoch": 4.46, "learning_rate": 9.955201979869293e-05, "loss": 0.5738, "step": 18660 }, { "epoch": 4.46, "learning_rate": 9.955154023900903e-05, "loss": 0.5761, "step": 18670 }, { "epoch": 4.46, "learning_rate": 9.955106042393607e-05, "loss": 0.5655, "step": 18680 }, { "epoch": 4.47, "learning_rate": 9.955058035347655e-05, "loss": 0.5688, "step": 18690 }, { "epoch": 4.47, "learning_rate": 9.955010002763293e-05, "loss": 0.6257, "step": 18700 }, { "epoch": 4.47, "learning_rate": 9.954961944640765e-05, "loss": 0.6102, "step": 18710 }, { "epoch": 4.47, "learning_rate": 9.954913860980323e-05, "loss": 0.5213, "step": 18720 }, { "epoch": 4.47, "learning_rate": 9.954865751782215e-05, "loss": 0.5952, "step": 18730 }, { "epoch": 4.48, "learning_rate": 9.954817617046686e-05, "loss": 0.6328, "step": 18740 }, { "epoch": 4.48, "learning_rate": 9.954769456773986e-05, "loss": 0.5967, "step": 18750 }, { "epoch": 4.48, "learning_rate": 9.954721270964363e-05, "loss": 0.522, "step": 18760 }, { "epoch": 4.48, "learning_rate": 9.954673059618065e-05, "loss": 0.5421, "step": 18770 }, { "epoch": 4.49, "learning_rate": 9.95462482273534e-05, "loss": 0.6193, "step": 18780 }, { "epoch": 4.49, "learning_rate": 9.954576560316437e-05, "loss": 0.5696, "step": 18790 }, { "epoch": 4.49, "learning_rate": 9.954528272361607e-05, "loss": 0.56, "step": 18800 }, { "epoch": 4.49, "learning_rate": 9.954479958871095e-05, "loss": 0.5501, "step": 18810 }, { "epoch": 4.5, "learning_rate": 9.954431619845153e-05, "loss": 0.5691, "step": 18820 }, { "epoch": 4.5, "learning_rate": 9.954383255284027e-05, "loss": 0.6021, "step": 18830 }, { "epoch": 4.5, "learning_rate": 9.954334865187971e-05, "loss": 0.5704, "step": 18840 }, { "epoch": 4.5, "learning_rate": 9.954286449557231e-05, "loss": 0.5349, "step": 18850 }, { "epoch": 4.5, "learning_rate": 9.954238008392056e-05, "loss": 0.6359, "step": 18860 }, { "epoch": 4.51, "learning_rate": 9.954189541692698e-05, "loss": 0.5989, "step": 18870 }, { "epoch": 4.51, "learning_rate": 9.954141049459406e-05, "loss": 0.5964, "step": 18880 }, { "epoch": 4.51, "learning_rate": 9.954092531692428e-05, "loss": 0.5479, "step": 18890 }, { "epoch": 4.51, "learning_rate": 9.954043988392017e-05, "loss": 0.5029, "step": 18900 }, { "epoch": 4.52, "learning_rate": 9.953995419558422e-05, "loss": 0.5239, "step": 18910 }, { "epoch": 4.52, "learning_rate": 9.953946825191893e-05, "loss": 0.5234, "step": 18920 }, { "epoch": 4.52, "learning_rate": 9.95389820529268e-05, "loss": 0.5314, "step": 18930 }, { "epoch": 4.52, "learning_rate": 9.953849559861035e-05, "loss": 0.5746, "step": 18940 }, { "epoch": 4.53, "learning_rate": 9.953800888897207e-05, "loss": 0.599, "step": 18950 }, { "epoch": 4.53, "learning_rate": 9.953752192401448e-05, "loss": 0.6889, "step": 18960 }, { "epoch": 4.53, "learning_rate": 9.953703470374009e-05, "loss": 0.5762, "step": 18970 }, { "epoch": 4.53, "learning_rate": 9.953654722815143e-05, "loss": 0.6775, "step": 18980 }, { "epoch": 4.53, "learning_rate": 9.953605949725096e-05, "loss": 0.603, "step": 18990 }, { "epoch": 4.54, "learning_rate": 9.953557151104124e-05, "loss": 0.6079, "step": 19000 }, { "epoch": 4.54, "learning_rate": 9.953508326952477e-05, "loss": 0.7052, "step": 19010 }, { "epoch": 4.54, "learning_rate": 9.953459477270406e-05, "loss": 0.6601, "step": 19020 }, { "epoch": 4.54, "learning_rate": 9.953410602058164e-05, "loss": 0.5971, "step": 19030 }, { "epoch": 4.55, "learning_rate": 9.953361701316002e-05, "loss": 0.6336, "step": 19040 }, { "epoch": 4.55, "learning_rate": 9.953312775044172e-05, "loss": 0.6525, "step": 19050 }, { "epoch": 4.55, "learning_rate": 9.953263823242929e-05, "loss": 0.6562, "step": 19060 }, { "epoch": 4.55, "learning_rate": 9.95321484591252e-05, "loss": 0.7074, "step": 19070 }, { "epoch": 4.55, "learning_rate": 9.953165843053201e-05, "loss": 0.6572, "step": 19080 }, { "epoch": 4.56, "learning_rate": 9.953116814665225e-05, "loss": 0.6805, "step": 19090 }, { "epoch": 4.56, "learning_rate": 9.953067760748842e-05, "loss": 0.6438, "step": 19100 }, { "epoch": 4.56, "learning_rate": 9.953018681304307e-05, "loss": 0.6281, "step": 19110 }, { "epoch": 4.56, "learning_rate": 9.952969576331873e-05, "loss": 0.6845, "step": 19120 }, { "epoch": 4.57, "learning_rate": 9.952920445831793e-05, "loss": 0.6584, "step": 19130 }, { "epoch": 4.57, "learning_rate": 9.952871289804317e-05, "loss": 0.6529, "step": 19140 }, { "epoch": 4.57, "learning_rate": 9.952822108249702e-05, "loss": 0.6702, "step": 19150 }, { "epoch": 4.57, "learning_rate": 9.952772901168202e-05, "loss": 0.6268, "step": 19160 }, { "epoch": 4.58, "learning_rate": 9.952723668560068e-05, "loss": 0.6715, "step": 19170 }, { "epoch": 4.58, "learning_rate": 9.952674410425554e-05, "loss": 0.6244, "step": 19180 }, { "epoch": 4.58, "learning_rate": 9.952625126764917e-05, "loss": 0.6424, "step": 19190 }, { "epoch": 4.58, "learning_rate": 9.952575817578407e-05, "loss": 0.6129, "step": 19200 }, { "epoch": 4.58, "learning_rate": 9.952526482866279e-05, "loss": 0.6448, "step": 19210 }, { "epoch": 4.59, "learning_rate": 9.952477122628789e-05, "loss": 0.6218, "step": 19220 }, { "epoch": 4.59, "learning_rate": 9.95242773686619e-05, "loss": 0.6297, "step": 19230 }, { "epoch": 4.59, "learning_rate": 9.952378325578738e-05, "loss": 0.6355, "step": 19240 }, { "epoch": 4.59, "learning_rate": 9.952328888766687e-05, "loss": 0.6723, "step": 19250 }, { "epoch": 4.6, "learning_rate": 9.952279426430291e-05, "loss": 0.6618, "step": 19260 }, { "epoch": 4.6, "learning_rate": 9.952229938569805e-05, "loss": 0.6639, "step": 19270 }, { "epoch": 4.6, "learning_rate": 9.952180425185485e-05, "loss": 0.6518, "step": 19280 }, { "epoch": 4.6, "learning_rate": 9.952130886277585e-05, "loss": 0.7741, "step": 19290 }, { "epoch": 4.61, "learning_rate": 9.952081321846362e-05, "loss": 0.6391, "step": 19300 }, { "epoch": 4.61, "learning_rate": 9.95203173189207e-05, "loss": 0.6683, "step": 19310 }, { "epoch": 4.61, "learning_rate": 9.951982116414965e-05, "loss": 0.6222, "step": 19320 }, { "epoch": 4.61, "learning_rate": 9.951932475415302e-05, "loss": 0.642, "step": 19330 }, { "epoch": 4.61, "learning_rate": 9.95188280889334e-05, "loss": 0.5954, "step": 19340 }, { "epoch": 4.62, "learning_rate": 9.951833116849331e-05, "loss": 0.706, "step": 19350 }, { "epoch": 4.62, "learning_rate": 9.951783399283533e-05, "loss": 0.6044, "step": 19360 }, { "epoch": 4.62, "learning_rate": 9.9517336561962e-05, "loss": 0.6156, "step": 19370 }, { "epoch": 4.62, "learning_rate": 9.951683887587592e-05, "loss": 0.6352, "step": 19380 }, { "epoch": 4.63, "learning_rate": 9.951634093457964e-05, "loss": 0.6006, "step": 19390 }, { "epoch": 4.63, "learning_rate": 9.951584273807573e-05, "loss": 0.5776, "step": 19400 }, { "epoch": 4.63, "learning_rate": 9.951534428636675e-05, "loss": 0.6317, "step": 19410 }, { "epoch": 4.63, "learning_rate": 9.951484557945527e-05, "loss": 0.614, "step": 19420 }, { "epoch": 4.63, "learning_rate": 9.951434661734387e-05, "loss": 0.5836, "step": 19430 }, { "epoch": 4.64, "learning_rate": 9.951384740003509e-05, "loss": 0.6159, "step": 19440 }, { "epoch": 4.64, "learning_rate": 9.951334792753155e-05, "loss": 0.6618, "step": 19450 }, { "epoch": 4.64, "learning_rate": 9.95128481998358e-05, "loss": 0.5951, "step": 19460 }, { "epoch": 4.64, "learning_rate": 9.95123482169504e-05, "loss": 0.5366, "step": 19470 }, { "epoch": 4.65, "learning_rate": 9.951184797887796e-05, "loss": 0.616, "step": 19480 }, { "epoch": 4.65, "learning_rate": 9.951134748562104e-05, "loss": 0.6957, "step": 19490 }, { "epoch": 4.65, "learning_rate": 9.95108467371822e-05, "loss": 0.6092, "step": 19500 }, { "epoch": 4.65, "learning_rate": 9.951034573356405e-05, "loss": 0.6716, "step": 19510 }, { "epoch": 4.66, "learning_rate": 9.950984447476919e-05, "loss": 0.632, "step": 19520 }, { "epoch": 4.66, "learning_rate": 9.950934296080014e-05, "loss": 0.6079, "step": 19530 }, { "epoch": 4.66, "learning_rate": 9.950884119165955e-05, "loss": 0.6482, "step": 19540 }, { "epoch": 4.66, "learning_rate": 9.950833916734998e-05, "loss": 0.6146, "step": 19550 }, { "epoch": 4.66, "learning_rate": 9.950783688787399e-05, "loss": 0.5764, "step": 19560 }, { "epoch": 4.67, "learning_rate": 9.950733435323422e-05, "loss": 0.6703, "step": 19570 }, { "epoch": 4.67, "learning_rate": 9.950683156343323e-05, "loss": 0.684, "step": 19580 }, { "epoch": 4.67, "learning_rate": 9.95063285184736e-05, "loss": 0.6248, "step": 19590 }, { "epoch": 4.67, "learning_rate": 9.950582521835797e-05, "loss": 0.7045, "step": 19600 }, { "epoch": 4.68, "learning_rate": 9.950532166308888e-05, "loss": 0.6729, "step": 19610 }, { "epoch": 4.68, "learning_rate": 9.950481785266896e-05, "loss": 0.6547, "step": 19620 }, { "epoch": 4.68, "learning_rate": 9.950431378710078e-05, "loss": 0.5953, "step": 19630 }, { "epoch": 4.68, "learning_rate": 9.950380946638696e-05, "loss": 0.7199, "step": 19640 }, { "epoch": 4.69, "learning_rate": 9.950330489053009e-05, "loss": 0.6806, "step": 19650 }, { "epoch": 4.69, "learning_rate": 9.950280005953278e-05, "loss": 0.5936, "step": 19660 }, { "epoch": 4.69, "learning_rate": 9.950229497339762e-05, "loss": 0.5891, "step": 19670 }, { "epoch": 4.69, "learning_rate": 9.950178963212722e-05, "loss": 0.6551, "step": 19680 }, { "epoch": 4.69, "learning_rate": 9.950128403572419e-05, "loss": 0.5856, "step": 19690 }, { "epoch": 4.7, "learning_rate": 9.95007781841911e-05, "loss": 0.5508, "step": 19700 }, { "epoch": 4.7, "learning_rate": 9.950027207753061e-05, "loss": 0.6141, "step": 19710 }, { "epoch": 4.7, "learning_rate": 9.94997657157453e-05, "loss": 0.5691, "step": 19720 }, { "epoch": 4.7, "learning_rate": 9.949925909883778e-05, "loss": 0.5494, "step": 19730 }, { "epoch": 4.71, "learning_rate": 9.949875222681067e-05, "loss": 0.6719, "step": 19740 }, { "epoch": 4.71, "learning_rate": 9.949824509966657e-05, "loss": 0.6374, "step": 19750 }, { "epoch": 4.71, "learning_rate": 9.949773771740812e-05, "loss": 0.5816, "step": 19760 }, { "epoch": 4.71, "learning_rate": 9.94972300800379e-05, "loss": 0.656, "step": 19770 }, { "epoch": 4.71, "learning_rate": 9.949672218755855e-05, "loss": 0.548, "step": 19780 }, { "epoch": 4.72, "learning_rate": 9.949621403997267e-05, "loss": 0.6185, "step": 19790 }, { "epoch": 4.72, "learning_rate": 9.94957056372829e-05, "loss": 0.6751, "step": 19800 }, { "epoch": 4.72, "learning_rate": 9.949519697949184e-05, "loss": 0.6015, "step": 19810 }, { "epoch": 4.72, "learning_rate": 9.949468806660211e-05, "loss": 0.5763, "step": 19820 }, { "epoch": 4.73, "learning_rate": 9.949417889861636e-05, "loss": 0.6059, "step": 19830 }, { "epoch": 4.73, "learning_rate": 9.94936694755372e-05, "loss": 0.6102, "step": 19840 }, { "epoch": 4.73, "learning_rate": 9.949315979736724e-05, "loss": 0.6172, "step": 19850 }, { "epoch": 4.73, "learning_rate": 9.949264986410913e-05, "loss": 0.615, "step": 19860 }, { "epoch": 4.74, "learning_rate": 9.949213967576549e-05, "loss": 0.6011, "step": 19870 }, { "epoch": 4.74, "learning_rate": 9.949162923233896e-05, "loss": 0.6173, "step": 19880 }, { "epoch": 4.74, "learning_rate": 9.949111853383214e-05, "loss": 0.6431, "step": 19890 }, { "epoch": 4.74, "learning_rate": 9.949060758024768e-05, "loss": 0.647, "step": 19900 }, { "epoch": 4.74, "learning_rate": 9.949009637158824e-05, "loss": 0.6231, "step": 19910 }, { "epoch": 4.75, "learning_rate": 9.94895849078564e-05, "loss": 0.6295, "step": 19920 }, { "epoch": 4.75, "learning_rate": 9.948907318905484e-05, "loss": 0.6888, "step": 19930 }, { "epoch": 4.75, "learning_rate": 9.948856121518619e-05, "loss": 0.5723, "step": 19940 }, { "epoch": 4.75, "learning_rate": 9.948804898625308e-05, "loss": 0.5943, "step": 19950 }, { "epoch": 4.76, "learning_rate": 9.948753650225814e-05, "loss": 0.5931, "step": 19960 }, { "epoch": 4.76, "learning_rate": 9.948702376320403e-05, "loss": 0.6039, "step": 19970 }, { "epoch": 4.76, "learning_rate": 9.948651076909339e-05, "loss": 0.635, "step": 19980 }, { "epoch": 4.76, "learning_rate": 9.948599751992884e-05, "loss": 0.594, "step": 19990 }, { "epoch": 4.77, "learning_rate": 9.948548401571308e-05, "loss": 0.5449, "step": 20000 }, { "epoch": 4.77, "learning_rate": 9.94849702564487e-05, "loss": 0.636, "step": 20010 }, { "epoch": 4.77, "learning_rate": 9.948445624213836e-05, "loss": 0.6711, "step": 20020 }, { "epoch": 4.77, "learning_rate": 9.948394197278472e-05, "loss": 0.6015, "step": 20030 }, { "epoch": 4.77, "learning_rate": 9.948342744839045e-05, "loss": 0.5578, "step": 20040 }, { "epoch": 4.78, "learning_rate": 9.948291266895817e-05, "loss": 0.5504, "step": 20050 }, { "epoch": 4.78, "learning_rate": 9.948239763449054e-05, "loss": 0.637, "step": 20060 }, { "epoch": 4.78, "learning_rate": 9.948188234499024e-05, "loss": 0.5948, "step": 20070 }, { "epoch": 4.78, "learning_rate": 9.948136680045987e-05, "loss": 0.6269, "step": 20080 }, { "epoch": 4.79, "learning_rate": 9.948085100090214e-05, "loss": 0.5777, "step": 20090 }, { "epoch": 4.79, "learning_rate": 9.948033494631969e-05, "loss": 0.5588, "step": 20100 }, { "epoch": 4.79, "learning_rate": 9.947981863671518e-05, "loss": 0.6347, "step": 20110 }, { "epoch": 4.79, "learning_rate": 9.947930207209129e-05, "loss": 0.5627, "step": 20120 }, { "epoch": 4.79, "learning_rate": 9.947878525245064e-05, "loss": 0.5693, "step": 20130 }, { "epoch": 4.8, "learning_rate": 9.947826817779593e-05, "loss": 0.6021, "step": 20140 }, { "epoch": 4.8, "learning_rate": 9.94777508481298e-05, "loss": 0.5649, "step": 20150 }, { "epoch": 4.8, "learning_rate": 9.947723326345492e-05, "loss": 0.5733, "step": 20160 }, { "epoch": 4.8, "learning_rate": 9.9476715423774e-05, "loss": 0.5858, "step": 20170 }, { "epoch": 4.81, "learning_rate": 9.947619732908965e-05, "loss": 0.5516, "step": 20180 }, { "epoch": 4.81, "learning_rate": 9.947567897940458e-05, "loss": 0.4811, "step": 20190 }, { "epoch": 4.81, "learning_rate": 9.947516037472142e-05, "loss": 0.5415, "step": 20200 }, { "epoch": 4.81, "learning_rate": 9.947464151504289e-05, "loss": 0.626, "step": 20210 }, { "epoch": 4.82, "learning_rate": 9.947412240037163e-05, "loss": 0.6194, "step": 20220 }, { "epoch": 4.82, "learning_rate": 9.947360303071036e-05, "loss": 0.5741, "step": 20230 }, { "epoch": 4.82, "learning_rate": 9.947308340606171e-05, "loss": 0.6631, "step": 20240 }, { "epoch": 4.82, "learning_rate": 9.947256352642837e-05, "loss": 0.6454, "step": 20250 }, { "epoch": 4.82, "learning_rate": 9.947204339181302e-05, "loss": 0.5882, "step": 20260 }, { "epoch": 4.83, "learning_rate": 9.947152300221835e-05, "loss": 0.6115, "step": 20270 }, { "epoch": 4.83, "learning_rate": 9.947100235764705e-05, "loss": 0.6013, "step": 20280 }, { "epoch": 4.83, "learning_rate": 9.947048145810177e-05, "loss": 0.5681, "step": 20290 }, { "epoch": 4.83, "learning_rate": 9.946996030358523e-05, "loss": 0.5321, "step": 20300 }, { "epoch": 4.84, "learning_rate": 9.946943889410009e-05, "loss": 0.6467, "step": 20310 }, { "epoch": 4.84, "learning_rate": 9.946891722964906e-05, "loss": 0.5673, "step": 20320 }, { "epoch": 4.84, "learning_rate": 9.946839531023481e-05, "loss": 0.5637, "step": 20330 }, { "epoch": 4.84, "learning_rate": 9.946787313586003e-05, "loss": 0.558, "step": 20340 }, { "epoch": 4.85, "learning_rate": 9.946735070652743e-05, "loss": 0.5258, "step": 20350 }, { "epoch": 4.85, "learning_rate": 9.946682802223968e-05, "loss": 0.6602, "step": 20360 }, { "epoch": 4.85, "learning_rate": 9.94663050829995e-05, "loss": 0.5634, "step": 20370 }, { "epoch": 4.85, "learning_rate": 9.946578188880957e-05, "loss": 0.5173, "step": 20380 }, { "epoch": 4.85, "learning_rate": 9.946525843967256e-05, "loss": 0.5978, "step": 20390 }, { "epoch": 4.86, "learning_rate": 9.946473473559121e-05, "loss": 0.5881, "step": 20400 }, { "epoch": 4.86, "learning_rate": 9.946421077656822e-05, "loss": 0.676, "step": 20410 }, { "epoch": 4.86, "learning_rate": 9.946368656260625e-05, "loss": 0.5478, "step": 20420 }, { "epoch": 4.86, "learning_rate": 9.946316209370805e-05, "loss": 0.5174, "step": 20430 }, { "epoch": 4.87, "learning_rate": 9.946263736987628e-05, "loss": 0.5015, "step": 20440 }, { "epoch": 4.87, "learning_rate": 9.946211239111367e-05, "loss": 0.6017, "step": 20450 }, { "epoch": 4.87, "learning_rate": 9.946158715742292e-05, "loss": 0.5961, "step": 20460 }, { "epoch": 4.87, "learning_rate": 9.946106166880673e-05, "loss": 0.5573, "step": 20470 }, { "epoch": 4.87, "learning_rate": 9.946053592526783e-05, "loss": 0.6234, "step": 20480 }, { "epoch": 4.88, "learning_rate": 9.94600099268089e-05, "loss": 0.5577, "step": 20490 }, { "epoch": 4.88, "learning_rate": 9.945948367343267e-05, "loss": 0.5601, "step": 20500 }, { "epoch": 4.88, "learning_rate": 9.945895716514185e-05, "loss": 0.6484, "step": 20510 }, { "epoch": 4.88, "learning_rate": 9.945843040193914e-05, "loss": 0.5473, "step": 20520 }, { "epoch": 4.89, "learning_rate": 9.945790338382728e-05, "loss": 0.5639, "step": 20530 }, { "epoch": 4.89, "learning_rate": 9.945737611080897e-05, "loss": 0.5224, "step": 20540 }, { "epoch": 4.89, "learning_rate": 9.945684858288693e-05, "loss": 0.6034, "step": 20550 }, { "epoch": 4.89, "learning_rate": 9.945632080006387e-05, "loss": 0.5493, "step": 20560 }, { "epoch": 4.9, "learning_rate": 9.945579276234254e-05, "loss": 0.5507, "step": 20570 }, { "epoch": 4.9, "learning_rate": 9.945526446972562e-05, "loss": 0.5968, "step": 20580 }, { "epoch": 4.9, "learning_rate": 9.945473592221585e-05, "loss": 0.5595, "step": 20590 }, { "epoch": 4.9, "learning_rate": 9.945420711981597e-05, "loss": 0.5826, "step": 20600 }, { "epoch": 4.9, "learning_rate": 9.94536780625287e-05, "loss": 0.5912, "step": 20610 }, { "epoch": 4.91, "learning_rate": 9.945314875035674e-05, "loss": 0.5647, "step": 20620 }, { "epoch": 4.91, "learning_rate": 9.945261918330285e-05, "loss": 0.5779, "step": 20630 }, { "epoch": 4.91, "learning_rate": 9.945208936136975e-05, "loss": 0.5649, "step": 20640 }, { "epoch": 4.91, "learning_rate": 9.945155928456016e-05, "loss": 0.5421, "step": 20650 }, { "epoch": 4.92, "learning_rate": 9.945102895287683e-05, "loss": 0.5948, "step": 20660 }, { "epoch": 4.92, "learning_rate": 9.945049836632247e-05, "loss": 0.5909, "step": 20670 }, { "epoch": 4.92, "learning_rate": 9.944996752489984e-05, "loss": 0.5639, "step": 20680 }, { "epoch": 4.92, "learning_rate": 9.944943642861166e-05, "loss": 0.5838, "step": 20690 }, { "epoch": 4.93, "learning_rate": 9.944890507746068e-05, "loss": 0.5715, "step": 20700 }, { "epoch": 4.93, "learning_rate": 9.944837347144962e-05, "loss": 0.4623, "step": 20710 }, { "epoch": 4.93, "learning_rate": 9.944784161058123e-05, "loss": 0.5454, "step": 20720 }, { "epoch": 4.93, "learning_rate": 9.944730949485825e-05, "loss": 0.5864, "step": 20730 }, { "epoch": 4.93, "learning_rate": 9.944677712428343e-05, "loss": 0.5815, "step": 20740 }, { "epoch": 4.94, "learning_rate": 9.94462444988595e-05, "loss": 0.5144, "step": 20750 }, { "epoch": 4.94, "learning_rate": 9.944571161858922e-05, "loss": 0.5992, "step": 20760 }, { "epoch": 4.94, "learning_rate": 9.944517848347532e-05, "loss": 0.5934, "step": 20770 }, { "epoch": 4.94, "learning_rate": 9.944464509352056e-05, "loss": 0.4903, "step": 20780 }, { "epoch": 4.95, "learning_rate": 9.94441114487277e-05, "loss": 0.6488, "step": 20790 }, { "epoch": 4.95, "learning_rate": 9.944357754909945e-05, "loss": 0.5524, "step": 20800 }, { "epoch": 4.95, "learning_rate": 9.944304339463861e-05, "loss": 0.5669, "step": 20810 }, { "epoch": 5.0, "learning_rate": 9.944250898534789e-05, "loss": 0.6258, "step": 20820 }, { "epoch": 5.0, "learning_rate": 9.944197432123009e-05, "loss": 0.5476, "step": 20830 }, { "epoch": 5.01, "learning_rate": 9.944143940228792e-05, "loss": 0.5123, "step": 20840 }, { "epoch": 5.01, "learning_rate": 9.944090422852417e-05, "loss": 0.5046, "step": 20850 }, { "epoch": 5.01, "learning_rate": 9.944036879994159e-05, "loss": 0.5189, "step": 20860 }, { "epoch": 5.01, "learning_rate": 9.943983311654292e-05, "loss": 0.5611, "step": 20870 }, { "epoch": 5.01, "learning_rate": 9.943929717833094e-05, "loss": 0.5674, "step": 20880 }, { "epoch": 5.02, "learning_rate": 9.943876098530842e-05, "loss": 0.5269, "step": 20890 }, { "epoch": 5.02, "learning_rate": 9.943822453747811e-05, "loss": 0.4786, "step": 20900 }, { "epoch": 5.02, "learning_rate": 9.943768783484277e-05, "loss": 0.6502, "step": 20910 }, { "epoch": 5.02, "learning_rate": 9.943715087740519e-05, "loss": 0.5397, "step": 20920 }, { "epoch": 5.03, "learning_rate": 9.943661366516811e-05, "loss": 0.5078, "step": 20930 }, { "epoch": 5.03, "learning_rate": 9.943607619813431e-05, "loss": 0.6037, "step": 20940 }, { "epoch": 5.03, "learning_rate": 9.943553847630655e-05, "loss": 0.5384, "step": 20950 }, { "epoch": 5.03, "learning_rate": 9.943500049968764e-05, "loss": 0.5528, "step": 20960 }, { "epoch": 5.04, "learning_rate": 9.94344622682803e-05, "loss": 0.4921, "step": 20970 }, { "epoch": 5.04, "learning_rate": 9.943392378208733e-05, "loss": 0.4871, "step": 20980 }, { "epoch": 5.04, "learning_rate": 9.94333850411115e-05, "loss": 0.5049, "step": 20990 }, { "epoch": 5.04, "learning_rate": 9.94328460453556e-05, "loss": 0.4519, "step": 21000 }, { "epoch": 5.04, "learning_rate": 9.943230679482241e-05, "loss": 0.5698, "step": 21010 }, { "epoch": 5.05, "learning_rate": 9.943176728951467e-05, "loss": 0.4685, "step": 21020 }, { "epoch": 5.05, "learning_rate": 9.943122752943521e-05, "loss": 0.5378, "step": 21030 }, { "epoch": 5.05, "learning_rate": 9.943068751458678e-05, "loss": 0.5492, "step": 21040 }, { "epoch": 5.05, "learning_rate": 9.943014724497217e-05, "loss": 0.486, "step": 21050 }, { "epoch": 5.06, "learning_rate": 9.942960672059419e-05, "loss": 0.5294, "step": 21060 }, { "epoch": 5.06, "learning_rate": 9.942906594145558e-05, "loss": 0.4693, "step": 21070 }, { "epoch": 5.06, "learning_rate": 9.942852490755916e-05, "loss": 0.4847, "step": 21080 }, { "epoch": 5.06, "learning_rate": 9.94279836189077e-05, "loss": 0.4354, "step": 21090 }, { "epoch": 5.07, "learning_rate": 9.9427442075504e-05, "loss": 0.5211, "step": 21100 }, { "epoch": 5.07, "learning_rate": 9.942690027735087e-05, "loss": 0.5113, "step": 21110 }, { "epoch": 5.07, "learning_rate": 9.942635822445107e-05, "loss": 0.5201, "step": 21120 }, { "epoch": 5.07, "learning_rate": 9.94258159168074e-05, "loss": 0.5209, "step": 21130 }, { "epoch": 5.07, "learning_rate": 9.942527335442268e-05, "loss": 0.525, "step": 21140 }, { "epoch": 5.08, "learning_rate": 9.942473053729968e-05, "loss": 0.485, "step": 21150 }, { "epoch": 5.08, "learning_rate": 9.94241874654412e-05, "loss": 0.5517, "step": 21160 }, { "epoch": 5.08, "learning_rate": 9.942364413885003e-05, "loss": 0.5173, "step": 21170 }, { "epoch": 5.08, "learning_rate": 9.942310055752902e-05, "loss": 0.5396, "step": 21180 }, { "epoch": 5.09, "learning_rate": 9.942255672148091e-05, "loss": 0.5732, "step": 21190 }, { "epoch": 5.09, "learning_rate": 9.942201263070854e-05, "loss": 0.4813, "step": 21200 }, { "epoch": 5.09, "learning_rate": 9.94214682852147e-05, "loss": 0.5164, "step": 21210 }, { "epoch": 5.09, "learning_rate": 9.94209236850022e-05, "loss": 0.55, "step": 21220 }, { "epoch": 5.09, "learning_rate": 9.942037883007384e-05, "loss": 0.4624, "step": 21230 }, { "epoch": 5.1, "learning_rate": 9.941983372043246e-05, "loss": 0.5404, "step": 21240 }, { "epoch": 5.1, "learning_rate": 9.941928835608083e-05, "loss": 0.5135, "step": 21250 }, { "epoch": 5.1, "learning_rate": 9.941874273702176e-05, "loss": 0.4956, "step": 21260 }, { "epoch": 5.1, "learning_rate": 9.941819686325808e-05, "loss": 0.4471, "step": 21270 }, { "epoch": 5.11, "learning_rate": 9.941765073479262e-05, "loss": 0.4997, "step": 21280 }, { "epoch": 5.11, "learning_rate": 9.941710435162817e-05, "loss": 0.574, "step": 21290 }, { "epoch": 5.11, "learning_rate": 9.941655771376753e-05, "loss": 0.4832, "step": 21300 }, { "epoch": 5.11, "learning_rate": 9.941601082121355e-05, "loss": 0.4927, "step": 21310 }, { "epoch": 5.12, "learning_rate": 9.941546367396905e-05, "loss": 0.48, "step": 21320 }, { "epoch": 5.12, "learning_rate": 9.941491627203683e-05, "loss": 0.518, "step": 21330 }, { "epoch": 5.12, "learning_rate": 9.94143686154197e-05, "loss": 0.5445, "step": 21340 }, { "epoch": 5.12, "learning_rate": 9.941382070412053e-05, "loss": 0.4585, "step": 21350 }, { "epoch": 5.12, "learning_rate": 9.94132725381421e-05, "loss": 0.5736, "step": 21360 }, { "epoch": 5.13, "learning_rate": 9.941272411748726e-05, "loss": 0.5615, "step": 21370 }, { "epoch": 5.13, "learning_rate": 9.941217544215881e-05, "loss": 0.5386, "step": 21380 }, { "epoch": 5.13, "learning_rate": 9.94116265121596e-05, "loss": 0.5206, "step": 21390 }, { "epoch": 5.13, "learning_rate": 9.941107732749246e-05, "loss": 0.4733, "step": 21400 }, { "epoch": 5.14, "learning_rate": 9.941052788816021e-05, "loss": 0.5506, "step": 21410 }, { "epoch": 5.14, "learning_rate": 9.940997819416569e-05, "loss": 0.5299, "step": 21420 }, { "epoch": 5.14, "learning_rate": 9.940942824551172e-05, "loss": 0.4767, "step": 21430 }, { "epoch": 5.14, "learning_rate": 9.940887804220116e-05, "loss": 0.536, "step": 21440 }, { "epoch": 5.15, "learning_rate": 9.940832758423682e-05, "loss": 0.5069, "step": 21450 }, { "epoch": 5.15, "learning_rate": 9.940777687162155e-05, "loss": 0.5029, "step": 21460 }, { "epoch": 5.15, "learning_rate": 9.940722590435819e-05, "loss": 0.517, "step": 21470 }, { "epoch": 5.15, "learning_rate": 9.940667468244955e-05, "loss": 0.4714, "step": 21480 }, { "epoch": 5.15, "learning_rate": 9.940612320589852e-05, "loss": 0.4643, "step": 21490 }, { "epoch": 5.16, "learning_rate": 9.94055714747079e-05, "loss": 0.5745, "step": 21500 }, { "epoch": 5.16, "learning_rate": 9.940501948888056e-05, "loss": 0.4654, "step": 21510 }, { "epoch": 5.16, "learning_rate": 9.940446724841934e-05, "loss": 0.5507, "step": 21520 }, { "epoch": 5.16, "learning_rate": 9.940391475332709e-05, "loss": 0.507, "step": 21530 }, { "epoch": 5.17, "learning_rate": 9.940336200360665e-05, "loss": 0.477, "step": 21540 }, { "epoch": 5.17, "learning_rate": 9.940280899926086e-05, "loss": 0.5668, "step": 21550 }, { "epoch": 5.17, "learning_rate": 9.940225574029258e-05, "loss": 0.4931, "step": 21560 }, { "epoch": 5.17, "learning_rate": 9.940170222670466e-05, "loss": 0.5655, "step": 21570 }, { "epoch": 5.17, "learning_rate": 9.940114845849995e-05, "loss": 0.4634, "step": 21580 }, { "epoch": 5.18, "learning_rate": 9.940059443568132e-05, "loss": 0.4873, "step": 21590 }, { "epoch": 5.18, "learning_rate": 9.940004015825159e-05, "loss": 0.4487, "step": 21600 }, { "epoch": 5.18, "learning_rate": 9.939948562621367e-05, "loss": 0.4645, "step": 21610 }, { "epoch": 5.18, "learning_rate": 9.939893083957037e-05, "loss": 0.527, "step": 21620 }, { "epoch": 5.19, "learning_rate": 9.939837579832459e-05, "loss": 0.4544, "step": 21630 }, { "epoch": 5.19, "learning_rate": 9.939782050247915e-05, "loss": 0.5038, "step": 21640 }, { "epoch": 5.19, "learning_rate": 9.939726495203691e-05, "loss": 0.4813, "step": 21650 }, { "epoch": 5.19, "learning_rate": 9.939670914700079e-05, "loss": 0.411, "step": 21660 }, { "epoch": 5.2, "learning_rate": 9.93961530873736e-05, "loss": 0.4622, "step": 21670 }, { "epoch": 5.2, "learning_rate": 9.939559677315823e-05, "loss": 0.5645, "step": 21680 }, { "epoch": 5.2, "learning_rate": 9.939504020435754e-05, "loss": 0.5183, "step": 21690 }, { "epoch": 5.2, "learning_rate": 9.939448338097438e-05, "loss": 0.5101, "step": 21700 }, { "epoch": 5.2, "learning_rate": 9.939392630301167e-05, "loss": 0.5283, "step": 21710 }, { "epoch": 5.21, "learning_rate": 9.939336897047225e-05, "loss": 0.5186, "step": 21720 }, { "epoch": 5.21, "learning_rate": 9.939281138335898e-05, "loss": 0.5178, "step": 21730 }, { "epoch": 5.21, "learning_rate": 9.939225354167474e-05, "loss": 0.5117, "step": 21740 }, { "epoch": 5.21, "learning_rate": 9.939169544542242e-05, "loss": 0.5117, "step": 21750 }, { "epoch": 5.22, "learning_rate": 9.93911370946049e-05, "loss": 0.5255, "step": 21760 }, { "epoch": 5.22, "learning_rate": 9.939057848922504e-05, "loss": 0.5357, "step": 21770 }, { "epoch": 5.22, "learning_rate": 9.939001962928571e-05, "loss": 0.4863, "step": 21780 }, { "epoch": 5.22, "learning_rate": 9.938946051478983e-05, "loss": 0.5227, "step": 21790 }, { "epoch": 5.23, "learning_rate": 9.938890114574024e-05, "loss": 0.4618, "step": 21800 }, { "epoch": 5.23, "learning_rate": 9.938834152213985e-05, "loss": 0.5193, "step": 21810 }, { "epoch": 5.23, "learning_rate": 9.938778164399155e-05, "loss": 0.4821, "step": 21820 }, { "epoch": 5.23, "learning_rate": 9.938722151129818e-05, "loss": 0.4793, "step": 21830 }, { "epoch": 5.23, "learning_rate": 9.938666112406267e-05, "loss": 0.5312, "step": 21840 }, { "epoch": 5.24, "learning_rate": 9.93861004822879e-05, "loss": 0.5059, "step": 21850 }, { "epoch": 5.24, "learning_rate": 9.938553958597674e-05, "loss": 0.4311, "step": 21860 }, { "epoch": 5.24, "learning_rate": 9.938497843513212e-05, "loss": 0.4561, "step": 21870 }, { "epoch": 5.24, "learning_rate": 9.938441702975689e-05, "loss": 0.557, "step": 21880 }, { "epoch": 5.25, "learning_rate": 9.938385536985397e-05, "loss": 0.4638, "step": 21890 }, { "epoch": 5.25, "learning_rate": 9.938329345542625e-05, "loss": 0.544, "step": 21900 }, { "epoch": 5.25, "learning_rate": 9.938273128647661e-05, "loss": 0.4738, "step": 21910 }, { "epoch": 5.25, "learning_rate": 9.938216886300797e-05, "loss": 0.4243, "step": 21920 }, { "epoch": 5.25, "learning_rate": 9.938160618502321e-05, "loss": 0.5761, "step": 21930 }, { "epoch": 5.26, "learning_rate": 9.938104325252525e-05, "loss": 0.5731, "step": 21940 }, { "epoch": 5.26, "learning_rate": 9.938048006551698e-05, "loss": 0.4345, "step": 21950 }, { "epoch": 5.26, "learning_rate": 9.93799166240013e-05, "loss": 0.5303, "step": 21960 }, { "epoch": 5.26, "learning_rate": 9.937935292798111e-05, "loss": 0.5159, "step": 21970 }, { "epoch": 5.27, "learning_rate": 9.937878897745933e-05, "loss": 0.4526, "step": 21980 }, { "epoch": 5.27, "learning_rate": 9.937822477243886e-05, "loss": 0.4902, "step": 21990 }, { "epoch": 5.27, "learning_rate": 9.937766031292259e-05, "loss": 0.5129, "step": 22000 }, { "epoch": 5.27, "learning_rate": 9.937709559891348e-05, "loss": 0.5427, "step": 22010 }, { "epoch": 5.28, "learning_rate": 9.937653063041438e-05, "loss": 0.4825, "step": 22020 }, { "epoch": 5.28, "learning_rate": 9.937596540742824e-05, "loss": 0.434, "step": 22030 }, { "epoch": 5.28, "learning_rate": 9.937539992995794e-05, "loss": 0.5238, "step": 22040 }, { "epoch": 5.28, "learning_rate": 9.937483419800644e-05, "loss": 0.4165, "step": 22050 }, { "epoch": 5.28, "learning_rate": 9.937426821157662e-05, "loss": 0.5364, "step": 22060 }, { "epoch": 5.29, "learning_rate": 9.937370197067142e-05, "loss": 0.4388, "step": 22070 }, { "epoch": 5.29, "learning_rate": 9.937313547529374e-05, "loss": 0.5393, "step": 22080 }, { "epoch": 5.29, "learning_rate": 9.937256872544651e-05, "loss": 0.5523, "step": 22090 }, { "epoch": 5.29, "learning_rate": 9.937200172113263e-05, "loss": 0.5341, "step": 22100 }, { "epoch": 5.3, "learning_rate": 9.937143446235506e-05, "loss": 0.5676, "step": 22110 }, { "epoch": 5.3, "learning_rate": 9.937086694911671e-05, "loss": 0.5805, "step": 22120 }, { "epoch": 5.3, "learning_rate": 9.937029918142049e-05, "loss": 0.4783, "step": 22130 }, { "epoch": 5.3, "learning_rate": 9.936973115926934e-05, "loss": 0.5359, "step": 22140 }, { "epoch": 5.31, "learning_rate": 9.936916288266617e-05, "loss": 0.457, "step": 22150 }, { "epoch": 5.31, "learning_rate": 9.936859435161393e-05, "loss": 0.4697, "step": 22160 }, { "epoch": 5.31, "learning_rate": 9.936802556611554e-05, "loss": 0.4965, "step": 22170 }, { "epoch": 5.31, "learning_rate": 9.936745652617395e-05, "loss": 0.5449, "step": 22180 }, { "epoch": 5.31, "learning_rate": 9.936688723179203e-05, "loss": 0.4286, "step": 22190 }, { "epoch": 5.32, "learning_rate": 9.936631768297281e-05, "loss": 0.5387, "step": 22200 }, { "epoch": 5.32, "learning_rate": 9.936574787971915e-05, "loss": 0.4842, "step": 22210 }, { "epoch": 5.32, "learning_rate": 9.936517782203403e-05, "loss": 0.5894, "step": 22220 }, { "epoch": 5.32, "learning_rate": 9.936460750992036e-05, "loss": 0.5534, "step": 22230 }, { "epoch": 5.33, "learning_rate": 9.936403694338109e-05, "loss": 0.4716, "step": 22240 }, { "epoch": 5.33, "learning_rate": 9.936346612241916e-05, "loss": 0.4368, "step": 22250 }, { "epoch": 5.33, "learning_rate": 9.936289504703752e-05, "loss": 0.5089, "step": 22260 }, { "epoch": 5.33, "learning_rate": 9.93623237172391e-05, "loss": 0.4981, "step": 22270 }, { "epoch": 5.33, "learning_rate": 9.936175213302685e-05, "loss": 0.4771, "step": 22280 }, { "epoch": 5.34, "learning_rate": 9.936118029440373e-05, "loss": 0.4926, "step": 22290 }, { "epoch": 5.34, "learning_rate": 9.936060820137266e-05, "loss": 0.4685, "step": 22300 }, { "epoch": 5.34, "learning_rate": 9.936003585393661e-05, "loss": 0.5052, "step": 22310 }, { "epoch": 5.34, "learning_rate": 9.935946325209851e-05, "loss": 0.492, "step": 22320 }, { "epoch": 5.35, "learning_rate": 9.935889039586134e-05, "loss": 0.4965, "step": 22330 }, { "epoch": 5.35, "learning_rate": 9.935831728522802e-05, "loss": 0.516, "step": 22340 }, { "epoch": 5.35, "learning_rate": 9.935774392020154e-05, "loss": 0.4808, "step": 22350 }, { "epoch": 5.35, "learning_rate": 9.935717030078482e-05, "loss": 0.5224, "step": 22360 }, { "epoch": 5.36, "learning_rate": 9.935659642698084e-05, "loss": 0.4481, "step": 22370 }, { "epoch": 5.36, "learning_rate": 9.935602229879255e-05, "loss": 0.467, "step": 22380 }, { "epoch": 5.36, "learning_rate": 9.93554479162229e-05, "loss": 0.5639, "step": 22390 }, { "epoch": 5.36, "learning_rate": 9.935487327927486e-05, "loss": 0.4424, "step": 22400 }, { "epoch": 5.36, "learning_rate": 9.93542983879514e-05, "loss": 0.4963, "step": 22410 }, { "epoch": 5.37, "learning_rate": 9.935372324225547e-05, "loss": 0.5051, "step": 22420 }, { "epoch": 5.37, "learning_rate": 9.935314784219004e-05, "loss": 0.4846, "step": 22430 }, { "epoch": 5.37, "learning_rate": 9.935257218775806e-05, "loss": 0.4086, "step": 22440 }, { "epoch": 5.37, "learning_rate": 9.935199627896252e-05, "loss": 0.3671, "step": 22450 }, { "epoch": 5.38, "learning_rate": 9.935142011580638e-05, "loss": 0.5132, "step": 22460 }, { "epoch": 5.38, "learning_rate": 9.93508436982926e-05, "loss": 0.5109, "step": 22470 }, { "epoch": 5.38, "learning_rate": 9.935026702642417e-05, "loss": 0.5087, "step": 22480 }, { "epoch": 5.38, "learning_rate": 9.934969010020405e-05, "loss": 0.4669, "step": 22490 }, { "epoch": 5.39, "learning_rate": 9.934911291963522e-05, "loss": 0.6017, "step": 22500 }, { "epoch": 5.39, "learning_rate": 9.934853548472062e-05, "loss": 0.4844, "step": 22510 }, { "epoch": 5.39, "learning_rate": 9.934795779546328e-05, "loss": 0.4649, "step": 22520 }, { "epoch": 5.39, "learning_rate": 9.934737985186616e-05, "loss": 0.5144, "step": 22530 }, { "epoch": 5.39, "learning_rate": 9.934680165393222e-05, "loss": 0.4432, "step": 22540 }, { "epoch": 5.4, "learning_rate": 9.934622320166445e-05, "loss": 0.4972, "step": 22550 }, { "epoch": 5.4, "learning_rate": 9.934564449506584e-05, "loss": 0.5096, "step": 22560 }, { "epoch": 5.4, "learning_rate": 9.934506553413936e-05, "loss": 0.4822, "step": 22570 }, { "epoch": 5.4, "learning_rate": 9.9344486318888e-05, "loss": 0.4574, "step": 22580 }, { "epoch": 5.41, "learning_rate": 9.934390684931474e-05, "loss": 0.436, "step": 22590 }, { "epoch": 5.41, "learning_rate": 9.934332712542258e-05, "loss": 0.5081, "step": 22600 }, { "epoch": 5.41, "learning_rate": 9.93427471472145e-05, "loss": 0.4803, "step": 22610 }, { "epoch": 5.41, "learning_rate": 9.934216691469349e-05, "loss": 0.4986, "step": 22620 }, { "epoch": 5.41, "learning_rate": 9.934158642786254e-05, "loss": 0.5085, "step": 22630 }, { "epoch": 5.42, "learning_rate": 9.934100568672465e-05, "loss": 0.4626, "step": 22640 }, { "epoch": 5.42, "learning_rate": 9.934042469128277e-05, "loss": 0.4963, "step": 22650 }, { "epoch": 5.42, "learning_rate": 9.933984344153996e-05, "loss": 0.5228, "step": 22660 }, { "epoch": 5.42, "learning_rate": 9.933926193749918e-05, "loss": 0.5335, "step": 22670 }, { "epoch": 5.43, "learning_rate": 9.933868017916342e-05, "loss": 0.4659, "step": 22680 }, { "epoch": 5.43, "learning_rate": 9.93380981665357e-05, "loss": 0.4362, "step": 22690 }, { "epoch": 5.43, "learning_rate": 9.9337515899619e-05, "loss": 0.4781, "step": 22700 }, { "epoch": 5.43, "learning_rate": 9.933693337841634e-05, "loss": 0.431, "step": 22710 }, { "epoch": 5.44, "learning_rate": 9.933635060293072e-05, "loss": 0.5329, "step": 22720 }, { "epoch": 5.44, "learning_rate": 9.933576757316511e-05, "loss": 0.5049, "step": 22730 }, { "epoch": 5.44, "learning_rate": 9.933518428912256e-05, "loss": 0.4692, "step": 22740 }, { "epoch": 5.44, "learning_rate": 9.933460075080606e-05, "loss": 0.4303, "step": 22750 }, { "epoch": 5.44, "learning_rate": 9.93340169582186e-05, "loss": 0.5044, "step": 22760 }, { "epoch": 5.45, "learning_rate": 9.933343291136322e-05, "loss": 0.5134, "step": 22770 }, { "epoch": 5.45, "learning_rate": 9.933284861024291e-05, "loss": 0.5254, "step": 22780 }, { "epoch": 5.45, "learning_rate": 9.933226405486069e-05, "loss": 0.4501, "step": 22790 }, { "epoch": 5.45, "learning_rate": 9.933167924521956e-05, "loss": 0.4683, "step": 22800 }, { "epoch": 5.46, "learning_rate": 9.933109418132255e-05, "loss": 0.4596, "step": 22810 }, { "epoch": 5.46, "learning_rate": 9.933050886317267e-05, "loss": 0.4947, "step": 22820 }, { "epoch": 5.46, "learning_rate": 9.932992329077293e-05, "loss": 0.5098, "step": 22830 }, { "epoch": 5.46, "learning_rate": 9.932933746412634e-05, "loss": 0.3991, "step": 22840 }, { "epoch": 5.47, "learning_rate": 9.932875138323597e-05, "loss": 0.4782, "step": 22850 }, { "epoch": 5.47, "learning_rate": 9.932816504810476e-05, "loss": 0.4743, "step": 22860 }, { "epoch": 5.47, "learning_rate": 9.932757845873579e-05, "loss": 0.4715, "step": 22870 }, { "epoch": 5.47, "learning_rate": 9.932699161513208e-05, "loss": 0.473, "step": 22880 }, { "epoch": 5.47, "learning_rate": 9.932640451729663e-05, "loss": 0.4607, "step": 22890 }, { "epoch": 5.48, "learning_rate": 9.932581716523248e-05, "loss": 0.5048, "step": 22900 }, { "epoch": 5.48, "learning_rate": 9.932522955894267e-05, "loss": 0.5134, "step": 22910 }, { "epoch": 5.48, "learning_rate": 9.93246416984302e-05, "loss": 0.4144, "step": 22920 }, { "epoch": 5.48, "learning_rate": 9.932405358369812e-05, "loss": 0.4059, "step": 22930 }, { "epoch": 5.49, "learning_rate": 9.932346521474945e-05, "loss": 0.4067, "step": 22940 }, { "epoch": 5.49, "learning_rate": 9.932287659158724e-05, "loss": 0.4768, "step": 22950 }, { "epoch": 5.49, "learning_rate": 9.93222877142145e-05, "loss": 0.4442, "step": 22960 }, { "epoch": 5.49, "learning_rate": 9.932169858263428e-05, "loss": 0.4086, "step": 22970 }, { "epoch": 5.49, "learning_rate": 9.932110919684962e-05, "loss": 0.4179, "step": 22980 }, { "epoch": 5.5, "learning_rate": 9.932051955686355e-05, "loss": 0.5248, "step": 22990 }, { "epoch": 5.5, "learning_rate": 9.931992966267909e-05, "loss": 0.5535, "step": 23000 }, { "epoch": 5.5, "learning_rate": 9.931933951429933e-05, "loss": 0.3732, "step": 23010 }, { "epoch": 5.5, "learning_rate": 9.931874911172727e-05, "loss": 0.4894, "step": 23020 }, { "epoch": 5.51, "learning_rate": 9.931815845496595e-05, "loss": 0.4913, "step": 23030 }, { "epoch": 5.51, "learning_rate": 9.931756754401844e-05, "loss": 0.489, "step": 23040 }, { "epoch": 5.51, "learning_rate": 9.931697637888777e-05, "loss": 0.4467, "step": 23050 }, { "epoch": 5.51, "learning_rate": 9.9316384959577e-05, "loss": 0.528, "step": 23060 }, { "epoch": 5.52, "learning_rate": 9.931579328608918e-05, "loss": 0.5308, "step": 23070 }, { "epoch": 5.52, "learning_rate": 9.931520135842733e-05, "loss": 0.5301, "step": 23080 }, { "epoch": 5.52, "learning_rate": 9.931460917659452e-05, "loss": 0.4799, "step": 23090 }, { "epoch": 5.52, "learning_rate": 9.931401674059382e-05, "loss": 0.5296, "step": 23100 }, { "epoch": 5.52, "learning_rate": 9.931342405042825e-05, "loss": 0.4711, "step": 23110 }, { "epoch": 5.53, "learning_rate": 9.931283110610088e-05, "loss": 0.4947, "step": 23120 }, { "epoch": 5.53, "learning_rate": 9.931223790761477e-05, "loss": 0.4843, "step": 23130 }, { "epoch": 5.53, "learning_rate": 9.931164445497297e-05, "loss": 0.5273, "step": 23140 }, { "epoch": 5.53, "learning_rate": 9.931105074817855e-05, "loss": 0.5668, "step": 23150 }, { "epoch": 5.54, "learning_rate": 9.931045678723457e-05, "loss": 0.6239, "step": 23160 }, { "epoch": 5.54, "learning_rate": 9.930986257214405e-05, "loss": 0.5758, "step": 23170 }, { "epoch": 5.54, "learning_rate": 9.930926810291012e-05, "loss": 0.6368, "step": 23180 }, { "epoch": 5.54, "learning_rate": 9.93086733795358e-05, "loss": 0.6591, "step": 23190 }, { "epoch": 5.55, "learning_rate": 9.930807840202416e-05, "loss": 0.7033, "step": 23200 }, { "epoch": 5.55, "learning_rate": 9.930748317037828e-05, "loss": 0.6746, "step": 23210 }, { "epoch": 5.55, "learning_rate": 9.930688768460121e-05, "loss": 0.5751, "step": 23220 }, { "epoch": 5.55, "learning_rate": 9.930629194469603e-05, "loss": 0.5709, "step": 23230 }, { "epoch": 5.55, "learning_rate": 9.930569595066582e-05, "loss": 0.5835, "step": 23240 }, { "epoch": 5.56, "learning_rate": 9.930509970251363e-05, "loss": 0.6063, "step": 23250 }, { "epoch": 5.56, "learning_rate": 9.930450320024255e-05, "loss": 0.6321, "step": 23260 }, { "epoch": 5.56, "learning_rate": 9.930390644385564e-05, "loss": 0.5355, "step": 23270 }, { "epoch": 5.56, "learning_rate": 9.9303309433356e-05, "loss": 0.5698, "step": 23280 }, { "epoch": 5.57, "learning_rate": 9.930271216874667e-05, "loss": 0.5344, "step": 23290 }, { "epoch": 5.57, "learning_rate": 9.930211465003077e-05, "loss": 0.656, "step": 23300 }, { "epoch": 5.57, "learning_rate": 9.930151687721134e-05, "loss": 0.5714, "step": 23310 }, { "epoch": 5.57, "learning_rate": 9.93009188502915e-05, "loss": 0.5661, "step": 23320 }, { "epoch": 5.57, "learning_rate": 9.930032056927429e-05, "loss": 0.5585, "step": 23330 }, { "epoch": 5.58, "learning_rate": 9.929972203416283e-05, "loss": 0.5783, "step": 23340 }, { "epoch": 5.58, "learning_rate": 9.929912324496019e-05, "loss": 0.6113, "step": 23350 }, { "epoch": 5.58, "learning_rate": 9.929852420166945e-05, "loss": 0.5344, "step": 23360 }, { "epoch": 5.58, "learning_rate": 9.929792490429372e-05, "loss": 0.5373, "step": 23370 }, { "epoch": 5.59, "learning_rate": 9.929732535283606e-05, "loss": 0.5581, "step": 23380 }, { "epoch": 5.59, "learning_rate": 9.929672554729956e-05, "loss": 0.5076, "step": 23390 }, { "epoch": 5.59, "learning_rate": 9.929612548768735e-05, "loss": 0.6043, "step": 23400 }, { "epoch": 5.59, "learning_rate": 9.929552517400249e-05, "loss": 0.5739, "step": 23410 }, { "epoch": 5.6, "learning_rate": 9.929492460624808e-05, "loss": 0.5563, "step": 23420 }, { "epoch": 5.6, "learning_rate": 9.92943237844272e-05, "loss": 0.5323, "step": 23430 }, { "epoch": 5.6, "learning_rate": 9.929372270854298e-05, "loss": 0.6049, "step": 23440 }, { "epoch": 5.6, "learning_rate": 9.92931213785985e-05, "loss": 0.5966, "step": 23450 }, { "epoch": 5.6, "learning_rate": 9.929251979459686e-05, "loss": 0.6005, "step": 23460 }, { "epoch": 5.61, "learning_rate": 9.929191795654117e-05, "loss": 0.5599, "step": 23470 }, { "epoch": 5.61, "learning_rate": 9.92913158644345e-05, "loss": 0.5633, "step": 23480 }, { "epoch": 5.61, "learning_rate": 9.929071351827999e-05, "loss": 0.4915, "step": 23490 }, { "epoch": 5.61, "learning_rate": 9.929011091808073e-05, "loss": 0.5282, "step": 23500 }, { "epoch": 5.62, "learning_rate": 9.928950806383984e-05, "loss": 0.5333, "step": 23510 }, { "epoch": 5.62, "learning_rate": 9.928890495556037e-05, "loss": 0.55, "step": 23520 }, { "epoch": 5.62, "learning_rate": 9.928830159324551e-05, "loss": 0.5838, "step": 23530 }, { "epoch": 5.62, "learning_rate": 9.928769797689832e-05, "loss": 0.5285, "step": 23540 }, { "epoch": 5.62, "learning_rate": 9.928709410652193e-05, "loss": 0.5864, "step": 23550 }, { "epoch": 5.63, "learning_rate": 9.928648998211945e-05, "loss": 0.5639, "step": 23560 }, { "epoch": 5.63, "learning_rate": 9.928588560369397e-05, "loss": 0.5253, "step": 23570 }, { "epoch": 5.63, "learning_rate": 9.928528097124862e-05, "loss": 0.5177, "step": 23580 }, { "epoch": 5.63, "learning_rate": 9.928467608478655e-05, "loss": 0.5408, "step": 23590 }, { "epoch": 5.64, "learning_rate": 9.928407094431083e-05, "loss": 0.6524, "step": 23600 }, { "epoch": 5.64, "learning_rate": 9.92834655498246e-05, "loss": 0.5476, "step": 23610 }, { "epoch": 5.64, "learning_rate": 9.928285990133097e-05, "loss": 0.6166, "step": 23620 }, { "epoch": 5.64, "learning_rate": 9.928225399883306e-05, "loss": 0.5827, "step": 23630 }, { "epoch": 5.65, "learning_rate": 9.928164784233402e-05, "loss": 0.5328, "step": 23640 }, { "epoch": 5.65, "learning_rate": 9.928104143183694e-05, "loss": 0.5484, "step": 23650 }, { "epoch": 5.65, "learning_rate": 9.928043476734497e-05, "loss": 0.5484, "step": 23660 }, { "epoch": 5.65, "learning_rate": 9.927982784886122e-05, "loss": 0.5465, "step": 23670 }, { "epoch": 5.65, "learning_rate": 9.927922067638883e-05, "loss": 0.5548, "step": 23680 }, { "epoch": 5.66, "learning_rate": 9.927861324993093e-05, "loss": 0.5657, "step": 23690 }, { "epoch": 5.66, "learning_rate": 9.927800556949065e-05, "loss": 0.5617, "step": 23700 }, { "epoch": 5.66, "learning_rate": 9.92773976350711e-05, "loss": 0.512, "step": 23710 }, { "epoch": 5.66, "learning_rate": 9.927678944667545e-05, "loss": 0.5272, "step": 23720 }, { "epoch": 5.67, "learning_rate": 9.92761810043068e-05, "loss": 0.5307, "step": 23730 }, { "epoch": 5.67, "learning_rate": 9.927557230796828e-05, "loss": 0.582, "step": 23740 }, { "epoch": 5.67, "learning_rate": 9.927496335766309e-05, "loss": 0.5656, "step": 23750 }, { "epoch": 5.67, "learning_rate": 9.927435415339431e-05, "loss": 0.5077, "step": 23760 }, { "epoch": 5.68, "learning_rate": 9.927374469516511e-05, "loss": 0.5713, "step": 23770 }, { "epoch": 5.68, "learning_rate": 9.92731349829786e-05, "loss": 0.4761, "step": 23780 }, { "epoch": 5.68, "learning_rate": 9.927252501683794e-05, "loss": 0.6064, "step": 23790 }, { "epoch": 5.68, "learning_rate": 9.927191479674628e-05, "loss": 0.5025, "step": 23800 }, { "epoch": 5.68, "learning_rate": 9.927130432270676e-05, "loss": 0.5588, "step": 23810 }, { "epoch": 5.69, "learning_rate": 9.927069359472253e-05, "loss": 0.5692, "step": 23820 }, { "epoch": 5.69, "learning_rate": 9.927008261279672e-05, "loss": 0.5285, "step": 23830 }, { "epoch": 5.69, "learning_rate": 9.92694713769325e-05, "loss": 0.5182, "step": 23840 }, { "epoch": 5.69, "learning_rate": 9.926885988713301e-05, "loss": 0.5313, "step": 23850 }, { "epoch": 5.7, "learning_rate": 9.926824814340141e-05, "loss": 0.6205, "step": 23860 }, { "epoch": 5.7, "learning_rate": 9.926763614574084e-05, "loss": 0.4842, "step": 23870 }, { "epoch": 5.7, "learning_rate": 9.926702389415447e-05, "loss": 0.5266, "step": 23880 }, { "epoch": 5.7, "learning_rate": 9.926641138864545e-05, "loss": 0.6099, "step": 23890 }, { "epoch": 5.7, "learning_rate": 9.926579862921692e-05, "loss": 0.4453, "step": 23900 }, { "epoch": 5.71, "learning_rate": 9.926518561587206e-05, "loss": 0.5173, "step": 23910 }, { "epoch": 5.71, "learning_rate": 9.926457234861401e-05, "loss": 0.5566, "step": 23920 }, { "epoch": 5.71, "learning_rate": 9.926395882744596e-05, "loss": 0.5494, "step": 23930 }, { "epoch": 5.71, "learning_rate": 9.926334505237105e-05, "loss": 0.5804, "step": 23940 }, { "epoch": 5.72, "learning_rate": 9.926273102339245e-05, "loss": 0.5873, "step": 23950 }, { "epoch": 5.72, "learning_rate": 9.92621167405133e-05, "loss": 0.5272, "step": 23960 }, { "epoch": 5.72, "learning_rate": 9.926150220373682e-05, "loss": 0.5214, "step": 23970 }, { "epoch": 5.72, "learning_rate": 9.926088741306613e-05, "loss": 0.5554, "step": 23980 }, { "epoch": 5.73, "learning_rate": 9.926027236850441e-05, "loss": 0.5014, "step": 23990 }, { "epoch": 5.73, "learning_rate": 9.925965707005484e-05, "loss": 0.5179, "step": 24000 }, { "epoch": 5.73, "learning_rate": 9.92590415177206e-05, "loss": 0.4581, "step": 24010 }, { "epoch": 5.73, "learning_rate": 9.925842571150483e-05, "loss": 0.5858, "step": 24020 }, { "epoch": 5.73, "learning_rate": 9.925780965141074e-05, "loss": 0.565, "step": 24030 }, { "epoch": 5.74, "learning_rate": 9.925719333744146e-05, "loss": 0.6012, "step": 24040 }, { "epoch": 5.74, "learning_rate": 9.92565767696002e-05, "loss": 0.4933, "step": 24050 }, { "epoch": 5.74, "learning_rate": 9.925595994789015e-05, "loss": 0.4845, "step": 24060 }, { "epoch": 5.74, "learning_rate": 9.925534287231445e-05, "loss": 0.5007, "step": 24070 }, { "epoch": 5.75, "learning_rate": 9.925472554287633e-05, "loss": 0.4932, "step": 24080 }, { "epoch": 5.75, "learning_rate": 9.925410795957892e-05, "loss": 0.5372, "step": 24090 }, { "epoch": 5.75, "learning_rate": 9.925349012242543e-05, "loss": 0.5748, "step": 24100 }, { "epoch": 5.75, "learning_rate": 9.925287203141904e-05, "loss": 0.5133, "step": 24110 }, { "epoch": 5.76, "learning_rate": 9.925225368656294e-05, "loss": 0.5277, "step": 24120 }, { "epoch": 5.76, "learning_rate": 9.92516350878603e-05, "loss": 0.5562, "step": 24130 }, { "epoch": 5.76, "learning_rate": 9.925101623531434e-05, "loss": 0.4972, "step": 24140 }, { "epoch": 5.76, "learning_rate": 9.925039712892821e-05, "loss": 0.5141, "step": 24150 }, { "epoch": 5.76, "learning_rate": 9.924977776870514e-05, "loss": 0.4793, "step": 24160 }, { "epoch": 5.77, "learning_rate": 9.92491581546483e-05, "loss": 0.5214, "step": 24170 }, { "epoch": 5.77, "learning_rate": 9.924853828676088e-05, "loss": 0.5612, "step": 24180 }, { "epoch": 5.77, "learning_rate": 9.924791816504609e-05, "loss": 0.5481, "step": 24190 }, { "epoch": 5.77, "learning_rate": 9.924729778950712e-05, "loss": 0.4824, "step": 24200 }, { "epoch": 5.78, "learning_rate": 9.924667716014715e-05, "loss": 0.5383, "step": 24210 }, { "epoch": 5.78, "learning_rate": 9.924605627696942e-05, "loss": 0.5218, "step": 24220 }, { "epoch": 5.78, "learning_rate": 9.924543513997707e-05, "loss": 0.5189, "step": 24230 }, { "epoch": 5.78, "learning_rate": 9.924481374917337e-05, "loss": 0.5098, "step": 24240 }, { "epoch": 5.78, "learning_rate": 9.924419210456147e-05, "loss": 0.5213, "step": 24250 }, { "epoch": 5.79, "learning_rate": 9.924357020614459e-05, "loss": 0.5007, "step": 24260 }, { "epoch": 5.79, "learning_rate": 9.924294805392593e-05, "loss": 0.5001, "step": 24270 }, { "epoch": 5.79, "learning_rate": 9.924232564790871e-05, "loss": 0.5085, "step": 24280 }, { "epoch": 5.79, "learning_rate": 9.924170298809616e-05, "loss": 0.4727, "step": 24290 }, { "epoch": 5.8, "learning_rate": 9.924108007449142e-05, "loss": 0.555, "step": 24300 }, { "epoch": 5.8, "learning_rate": 9.924045690709777e-05, "loss": 0.5045, "step": 24310 }, { "epoch": 5.8, "learning_rate": 9.923983348591839e-05, "loss": 0.5539, "step": 24320 }, { "epoch": 5.8, "learning_rate": 9.92392098109565e-05, "loss": 0.5283, "step": 24330 }, { "epoch": 5.81, "learning_rate": 9.923858588221529e-05, "loss": 0.4999, "step": 24340 }, { "epoch": 5.81, "learning_rate": 9.923796169969801e-05, "loss": 0.5016, "step": 24350 }, { "epoch": 5.81, "learning_rate": 9.923733726340786e-05, "loss": 0.4652, "step": 24360 }, { "epoch": 5.81, "learning_rate": 9.923671257334806e-05, "loss": 0.4909, "step": 24370 }, { "epoch": 5.81, "learning_rate": 9.923608762952184e-05, "loss": 0.4541, "step": 24380 }, { "epoch": 5.82, "learning_rate": 9.923546243193241e-05, "loss": 0.5378, "step": 24390 }, { "epoch": 5.82, "learning_rate": 9.9234836980583e-05, "loss": 0.4981, "step": 24400 }, { "epoch": 5.82, "learning_rate": 9.923421127547681e-05, "loss": 0.4518, "step": 24410 }, { "epoch": 5.82, "learning_rate": 9.92335853166171e-05, "loss": 0.4729, "step": 24420 }, { "epoch": 5.83, "learning_rate": 9.923295910400707e-05, "loss": 0.5058, "step": 24430 }, { "epoch": 5.83, "learning_rate": 9.923233263764997e-05, "loss": 0.5227, "step": 24440 }, { "epoch": 5.83, "learning_rate": 9.923170591754901e-05, "loss": 0.4585, "step": 24450 }, { "epoch": 5.83, "learning_rate": 9.923107894370742e-05, "loss": 0.5031, "step": 24460 }, { "epoch": 5.84, "learning_rate": 9.923045171612846e-05, "loss": 0.5308, "step": 24470 }, { "epoch": 5.84, "learning_rate": 9.922982423481532e-05, "loss": 0.4985, "step": 24480 }, { "epoch": 5.84, "learning_rate": 9.922919649977124e-05, "loss": 0.4828, "step": 24490 }, { "epoch": 5.84, "learning_rate": 9.922856851099951e-05, "loss": 0.5143, "step": 24500 }, { "epoch": 5.84, "learning_rate": 9.922794026850331e-05, "loss": 0.5278, "step": 24510 }, { "epoch": 5.85, "learning_rate": 9.922731177228588e-05, "loss": 0.4909, "step": 24520 }, { "epoch": 5.85, "learning_rate": 9.922668302235047e-05, "loss": 0.4677, "step": 24530 }, { "epoch": 5.85, "learning_rate": 9.922605401870035e-05, "loss": 0.5413, "step": 24540 }, { "epoch": 5.85, "learning_rate": 9.922542476133872e-05, "loss": 0.512, "step": 24550 }, { "epoch": 5.86, "learning_rate": 9.922479525026885e-05, "loss": 0.5561, "step": 24560 }, { "epoch": 5.86, "learning_rate": 9.922416548549396e-05, "loss": 0.4763, "step": 24570 }, { "epoch": 5.86, "learning_rate": 9.922353546701732e-05, "loss": 0.5211, "step": 24580 }, { "epoch": 5.86, "learning_rate": 9.922290519484216e-05, "loss": 0.534, "step": 24590 }, { "epoch": 5.86, "learning_rate": 9.922227466897174e-05, "loss": 0.5079, "step": 24600 }, { "epoch": 5.87, "learning_rate": 9.922164388940928e-05, "loss": 0.487, "step": 24610 }, { "epoch": 5.87, "learning_rate": 9.92210128561581e-05, "loss": 0.4685, "step": 24620 }, { "epoch": 5.87, "learning_rate": 9.922038156922137e-05, "loss": 0.5437, "step": 24630 }, { "epoch": 5.87, "learning_rate": 9.92197500286024e-05, "loss": 0.5346, "step": 24640 }, { "epoch": 5.88, "learning_rate": 9.921911823430443e-05, "loss": 0.5726, "step": 24650 }, { "epoch": 5.88, "learning_rate": 9.921848618633072e-05, "loss": 0.4528, "step": 24660 }, { "epoch": 5.88, "learning_rate": 9.92178538846845e-05, "loss": 0.3621, "step": 24670 }, { "epoch": 5.88, "learning_rate": 9.921722132936905e-05, "loss": 0.4808, "step": 24680 }, { "epoch": 5.89, "learning_rate": 9.921658852038765e-05, "loss": 0.4943, "step": 24690 }, { "epoch": 5.89, "learning_rate": 9.921595545774354e-05, "loss": 0.4791, "step": 24700 }, { "epoch": 5.89, "learning_rate": 9.921532214143997e-05, "loss": 0.5452, "step": 24710 }, { "epoch": 5.89, "learning_rate": 9.921468857148022e-05, "loss": 0.5415, "step": 24720 }, { "epoch": 5.89, "learning_rate": 9.921405474786755e-05, "loss": 0.5319, "step": 24730 }, { "epoch": 5.9, "learning_rate": 9.921342067060524e-05, "loss": 0.5138, "step": 24740 }, { "epoch": 5.9, "learning_rate": 9.921278633969655e-05, "loss": 0.4692, "step": 24750 }, { "epoch": 5.9, "learning_rate": 9.921215175514474e-05, "loss": 0.455, "step": 24760 }, { "epoch": 5.9, "learning_rate": 9.92115169169531e-05, "loss": 0.4818, "step": 24770 }, { "epoch": 5.91, "learning_rate": 9.921088182512488e-05, "loss": 0.5634, "step": 24780 }, { "epoch": 5.91, "learning_rate": 9.921024647966337e-05, "loss": 0.4662, "step": 24790 }, { "epoch": 5.91, "learning_rate": 9.920961088057184e-05, "loss": 0.4178, "step": 24800 }, { "epoch": 5.91, "learning_rate": 9.920897502785356e-05, "loss": 0.5128, "step": 24810 }, { "epoch": 5.92, "learning_rate": 9.92083389215118e-05, "loss": 0.4618, "step": 24820 }, { "epoch": 5.92, "learning_rate": 9.920770256154986e-05, "loss": 0.4118, "step": 24830 }, { "epoch": 5.92, "learning_rate": 9.920706594797102e-05, "loss": 0.5261, "step": 24840 }, { "epoch": 5.92, "learning_rate": 9.920642908077853e-05, "loss": 0.4428, "step": 24850 }, { "epoch": 5.92, "learning_rate": 9.92057919599757e-05, "loss": 0.5056, "step": 24860 }, { "epoch": 5.93, "learning_rate": 9.920515458556581e-05, "loss": 0.5274, "step": 24870 }, { "epoch": 5.93, "learning_rate": 9.920451695755215e-05, "loss": 0.3558, "step": 24880 }, { "epoch": 5.93, "learning_rate": 9.920387907593798e-05, "loss": 0.4325, "step": 24890 }, { "epoch": 5.93, "learning_rate": 9.920324094072663e-05, "loss": 0.5099, "step": 24900 }, { "epoch": 5.94, "learning_rate": 9.920260255192135e-05, "loss": 0.4556, "step": 24910 }, { "epoch": 5.94, "learning_rate": 9.920196390952545e-05, "loss": 0.53, "step": 24920 }, { "epoch": 5.94, "learning_rate": 9.92013250135422e-05, "loss": 0.4569, "step": 24930 }, { "epoch": 5.94, "learning_rate": 9.920068586397493e-05, "loss": 0.452, "step": 24940 }, { "epoch": 5.94, "learning_rate": 9.92000464608269e-05, "loss": 0.4884, "step": 24950 }, { "epoch": 5.95, "learning_rate": 9.919940680410144e-05, "loss": 0.5032, "step": 24960 }, { "epoch": 5.95, "learning_rate": 9.919876689380181e-05, "loss": 0.5267, "step": 24970 }, { "epoch": 6.0, "learning_rate": 9.919812672993131e-05, "loss": 0.4102, "step": 24980 }, { "epoch": 6.0, "learning_rate": 9.919748631249328e-05, "loss": 0.4217, "step": 24990 }, { "epoch": 6.01, "learning_rate": 9.919684564149099e-05, "loss": 0.415, "step": 25000 }, { "epoch": 6.01, "learning_rate": 9.919620471692774e-05, "loss": 0.4472, "step": 25010 }, { "epoch": 6.01, "learning_rate": 9.919556353880683e-05, "loss": 0.4687, "step": 25020 }, { "epoch": 6.01, "learning_rate": 9.919492210713159e-05, "loss": 0.4424, "step": 25030 }, { "epoch": 6.01, "learning_rate": 9.91942804219053e-05, "loss": 0.4776, "step": 25040 }, { "epoch": 6.02, "learning_rate": 9.91936384831313e-05, "loss": 0.4398, "step": 25050 }, { "epoch": 6.02, "learning_rate": 9.919299629081285e-05, "loss": 0.4436, "step": 25060 }, { "epoch": 6.02, "learning_rate": 9.91923538449533e-05, "loss": 0.4881, "step": 25070 }, { "epoch": 6.02, "learning_rate": 9.919171114555594e-05, "loss": 0.4603, "step": 25080 }, { "epoch": 6.03, "learning_rate": 9.91910681926241e-05, "loss": 0.4738, "step": 25090 }, { "epoch": 6.03, "learning_rate": 9.919042498616107e-05, "loss": 0.4709, "step": 25100 }, { "epoch": 6.03, "learning_rate": 9.918978152617018e-05, "loss": 0.4566, "step": 25110 }, { "epoch": 6.03, "learning_rate": 9.918913781265475e-05, "loss": 0.5062, "step": 25120 }, { "epoch": 6.03, "learning_rate": 9.918849384561809e-05, "loss": 0.4448, "step": 25130 }, { "epoch": 6.04, "learning_rate": 9.918784962506352e-05, "loss": 0.4405, "step": 25140 }, { "epoch": 6.04, "learning_rate": 9.918720515099436e-05, "loss": 0.452, "step": 25150 }, { "epoch": 6.04, "learning_rate": 9.918656042341394e-05, "loss": 0.4566, "step": 25160 }, { "epoch": 6.04, "learning_rate": 9.918591544232559e-05, "loss": 0.412, "step": 25170 }, { "epoch": 6.05, "learning_rate": 9.918527020773259e-05, "loss": 0.4298, "step": 25180 }, { "epoch": 6.05, "learning_rate": 9.918462471963832e-05, "loss": 0.4013, "step": 25190 }, { "epoch": 6.05, "learning_rate": 9.918397897804607e-05, "loss": 0.4169, "step": 25200 }, { "epoch": 6.05, "learning_rate": 9.918333298295919e-05, "loss": 0.4148, "step": 25210 }, { "epoch": 6.06, "learning_rate": 9.918268673438098e-05, "loss": 0.4755, "step": 25220 }, { "epoch": 6.06, "learning_rate": 9.918204023231481e-05, "loss": 0.4894, "step": 25230 }, { "epoch": 6.06, "learning_rate": 9.9181393476764e-05, "loss": 0.4868, "step": 25240 }, { "epoch": 6.06, "learning_rate": 9.918074646773186e-05, "loss": 0.4044, "step": 25250 }, { "epoch": 6.06, "learning_rate": 9.918009920522175e-05, "loss": 0.4897, "step": 25260 }, { "epoch": 6.07, "learning_rate": 9.9179451689237e-05, "loss": 0.4595, "step": 25270 }, { "epoch": 6.07, "learning_rate": 9.917880391978094e-05, "loss": 0.4162, "step": 25280 }, { "epoch": 6.07, "learning_rate": 9.917815589685691e-05, "loss": 0.4839, "step": 25290 }, { "epoch": 6.07, "learning_rate": 9.917750762046827e-05, "loss": 0.4358, "step": 25300 }, { "epoch": 6.08, "learning_rate": 9.917685909061833e-05, "loss": 0.4592, "step": 25310 }, { "epoch": 6.08, "learning_rate": 9.917621030731045e-05, "loss": 0.4162, "step": 25320 }, { "epoch": 6.08, "learning_rate": 9.917556127054797e-05, "loss": 0.4439, "step": 25330 }, { "epoch": 6.08, "learning_rate": 9.917491198033424e-05, "loss": 0.4631, "step": 25340 }, { "epoch": 6.09, "learning_rate": 9.917426243667261e-05, "loss": 0.4938, "step": 25350 }, { "epoch": 6.09, "learning_rate": 9.91736126395664e-05, "loss": 0.3565, "step": 25360 }, { "epoch": 6.09, "learning_rate": 9.9172962589019e-05, "loss": 0.3983, "step": 25370 }, { "epoch": 6.09, "learning_rate": 9.917231228503372e-05, "loss": 0.4804, "step": 25380 }, { "epoch": 6.09, "learning_rate": 9.917166172761394e-05, "loss": 0.4222, "step": 25390 }, { "epoch": 6.1, "learning_rate": 9.917101091676302e-05, "loss": 0.488, "step": 25400 }, { "epoch": 6.1, "learning_rate": 9.917035985248428e-05, "loss": 0.5111, "step": 25410 }, { "epoch": 6.1, "learning_rate": 9.91697085347811e-05, "loss": 0.41, "step": 25420 }, { "epoch": 6.1, "learning_rate": 9.916905696365684e-05, "loss": 0.4151, "step": 25430 }, { "epoch": 6.11, "learning_rate": 9.916840513911483e-05, "loss": 0.4557, "step": 25440 }, { "epoch": 6.11, "learning_rate": 9.916775306115847e-05, "loss": 0.4149, "step": 25450 }, { "epoch": 6.11, "learning_rate": 9.916710072979108e-05, "loss": 0.4491, "step": 25460 }, { "epoch": 6.11, "learning_rate": 9.916644814501604e-05, "loss": 0.421, "step": 25470 }, { "epoch": 6.11, "learning_rate": 9.916579530683673e-05, "loss": 0.3676, "step": 25480 }, { "epoch": 6.12, "learning_rate": 9.91651422152565e-05, "loss": 0.4443, "step": 25490 }, { "epoch": 6.12, "learning_rate": 9.916448887027872e-05, "loss": 0.4431, "step": 25500 }, { "epoch": 6.12, "learning_rate": 9.916383527190673e-05, "loss": 0.4116, "step": 25510 }, { "epoch": 6.12, "learning_rate": 9.916318142014393e-05, "loss": 0.3874, "step": 25520 }, { "epoch": 6.13, "learning_rate": 9.91625273149937e-05, "loss": 0.4203, "step": 25530 }, { "epoch": 6.13, "learning_rate": 9.916187295645938e-05, "loss": 0.3714, "step": 25540 }, { "epoch": 6.13, "learning_rate": 9.916121834454436e-05, "loss": 0.4411, "step": 25550 }, { "epoch": 6.13, "learning_rate": 9.9160563479252e-05, "loss": 0.4259, "step": 25560 }, { "epoch": 6.14, "learning_rate": 9.91599083605857e-05, "loss": 0.4361, "step": 25570 }, { "epoch": 6.14, "learning_rate": 9.915925298854883e-05, "loss": 0.493, "step": 25580 }, { "epoch": 6.14, "learning_rate": 9.915859736314474e-05, "loss": 0.3695, "step": 25590 }, { "epoch": 6.14, "learning_rate": 9.915794148437683e-05, "loss": 0.4846, "step": 25600 }, { "epoch": 6.14, "learning_rate": 9.915728535224848e-05, "loss": 0.4937, "step": 25610 }, { "epoch": 6.15, "learning_rate": 9.915662896676307e-05, "loss": 0.415, "step": 25620 }, { "epoch": 6.15, "learning_rate": 9.915597232792397e-05, "loss": 0.4015, "step": 25630 }, { "epoch": 6.15, "learning_rate": 9.91553154357346e-05, "loss": 0.4142, "step": 25640 }, { "epoch": 6.15, "learning_rate": 9.915465829019832e-05, "loss": 0.4218, "step": 25650 }, { "epoch": 6.16, "learning_rate": 9.91540008913185e-05, "loss": 0.3964, "step": 25660 }, { "epoch": 6.16, "learning_rate": 9.915334323909858e-05, "loss": 0.4479, "step": 25670 }, { "epoch": 6.16, "learning_rate": 9.91526853335419e-05, "loss": 0.3703, "step": 25680 }, { "epoch": 6.16, "learning_rate": 9.915202717465187e-05, "loss": 0.4358, "step": 25690 }, { "epoch": 6.16, "learning_rate": 9.915136876243189e-05, "loss": 0.4029, "step": 25700 }, { "epoch": 6.17, "learning_rate": 9.915071009688533e-05, "loss": 0.4196, "step": 25710 }, { "epoch": 6.17, "learning_rate": 9.915005117801561e-05, "loss": 0.3974, "step": 25720 }, { "epoch": 6.17, "learning_rate": 9.914939200582611e-05, "loss": 0.4791, "step": 25730 }, { "epoch": 6.17, "learning_rate": 9.914873258032024e-05, "loss": 0.4753, "step": 25740 }, { "epoch": 6.18, "learning_rate": 9.914807290150138e-05, "loss": 0.4329, "step": 25750 }, { "epoch": 6.18, "learning_rate": 9.914741296937295e-05, "loss": 0.3963, "step": 25760 }, { "epoch": 6.18, "learning_rate": 9.914675278393834e-05, "loss": 0.4068, "step": 25770 }, { "epoch": 6.18, "learning_rate": 9.914609234520096e-05, "loss": 0.4975, "step": 25780 }, { "epoch": 6.19, "learning_rate": 9.91454316531642e-05, "loss": 0.3921, "step": 25790 }, { "epoch": 6.19, "learning_rate": 9.914477070783148e-05, "loss": 0.4998, "step": 25800 }, { "epoch": 6.19, "learning_rate": 9.91441095092062e-05, "loss": 0.4786, "step": 25810 }, { "epoch": 6.19, "learning_rate": 9.914344805729177e-05, "loss": 0.448, "step": 25820 }, { "epoch": 6.19, "learning_rate": 9.91427863520916e-05, "loss": 0.4462, "step": 25830 }, { "epoch": 6.2, "learning_rate": 9.914212439360908e-05, "loss": 0.4237, "step": 25840 }, { "epoch": 6.2, "learning_rate": 9.914146218184766e-05, "loss": 0.399, "step": 25850 }, { "epoch": 6.2, "learning_rate": 9.914079971681073e-05, "loss": 0.4151, "step": 25860 }, { "epoch": 6.2, "learning_rate": 9.914013699850171e-05, "loss": 0.4649, "step": 25870 }, { "epoch": 6.21, "learning_rate": 9.913947402692401e-05, "loss": 0.487, "step": 25880 }, { "epoch": 6.21, "learning_rate": 9.913881080208105e-05, "loss": 0.4402, "step": 25890 }, { "epoch": 6.21, "learning_rate": 9.913814732397623e-05, "loss": 0.4422, "step": 25900 }, { "epoch": 6.21, "learning_rate": 9.913748359261303e-05, "loss": 0.3996, "step": 25910 }, { "epoch": 6.22, "learning_rate": 9.913681960799479e-05, "loss": 0.4346, "step": 25920 }, { "epoch": 6.22, "learning_rate": 9.913615537012499e-05, "loss": 0.3886, "step": 25930 }, { "epoch": 6.22, "learning_rate": 9.913549087900703e-05, "loss": 0.4456, "step": 25940 }, { "epoch": 6.22, "learning_rate": 9.913482613464434e-05, "loss": 0.4555, "step": 25950 }, { "epoch": 6.22, "learning_rate": 9.913416113704035e-05, "loss": 0.4062, "step": 25960 }, { "epoch": 6.23, "learning_rate": 9.913349588619847e-05, "loss": 0.4676, "step": 25970 }, { "epoch": 6.23, "learning_rate": 9.913283038212215e-05, "loss": 0.4866, "step": 25980 }, { "epoch": 6.23, "learning_rate": 9.913216462481481e-05, "loss": 0.4127, "step": 25990 }, { "epoch": 6.23, "learning_rate": 9.913149861427988e-05, "loss": 0.45, "step": 26000 }, { "epoch": 6.24, "learning_rate": 9.91308323505208e-05, "loss": 0.4668, "step": 26010 }, { "epoch": 6.24, "learning_rate": 9.9130165833541e-05, "loss": 0.3965, "step": 26020 }, { "epoch": 6.24, "learning_rate": 9.912949906334392e-05, "loss": 0.3998, "step": 26030 }, { "epoch": 6.24, "learning_rate": 9.912883203993297e-05, "loss": 0.4858, "step": 26040 }, { "epoch": 6.24, "learning_rate": 9.912816476331164e-05, "loss": 0.3676, "step": 26050 }, { "epoch": 6.25, "learning_rate": 9.912749723348331e-05, "loss": 0.3971, "step": 26060 }, { "epoch": 6.25, "learning_rate": 9.912682945045146e-05, "loss": 0.4333, "step": 26070 }, { "epoch": 6.25, "learning_rate": 9.912616141421953e-05, "loss": 0.454, "step": 26080 }, { "epoch": 6.25, "learning_rate": 9.912549312479093e-05, "loss": 0.3773, "step": 26090 }, { "epoch": 6.26, "learning_rate": 9.912482458216916e-05, "loss": 0.437, "step": 26100 }, { "epoch": 6.26, "learning_rate": 9.91241557863576e-05, "loss": 0.3698, "step": 26110 }, { "epoch": 6.26, "learning_rate": 9.912348673735975e-05, "loss": 0.4352, "step": 26120 }, { "epoch": 6.26, "learning_rate": 9.912281743517904e-05, "loss": 0.4524, "step": 26130 }, { "epoch": 6.27, "learning_rate": 9.912214787981891e-05, "loss": 0.4528, "step": 26140 }, { "epoch": 6.27, "learning_rate": 9.912147807128283e-05, "loss": 0.4327, "step": 26150 }, { "epoch": 6.27, "learning_rate": 9.912080800957422e-05, "loss": 0.3931, "step": 26160 }, { "epoch": 6.27, "learning_rate": 9.912013769469657e-05, "loss": 0.4804, "step": 26170 }, { "epoch": 6.27, "learning_rate": 9.911946712665331e-05, "loss": 0.4931, "step": 26180 }, { "epoch": 6.28, "learning_rate": 9.911879630544793e-05, "loss": 0.4599, "step": 26190 }, { "epoch": 6.28, "learning_rate": 9.911812523108384e-05, "loss": 0.3562, "step": 26200 }, { "epoch": 6.28, "learning_rate": 9.911745390356452e-05, "loss": 0.4541, "step": 26210 }, { "epoch": 6.28, "learning_rate": 9.911678232289346e-05, "loss": 0.4144, "step": 26220 }, { "epoch": 6.29, "learning_rate": 9.911611048907407e-05, "loss": 0.3856, "step": 26230 }, { "epoch": 6.29, "learning_rate": 9.911543840210984e-05, "loss": 0.386, "step": 26240 }, { "epoch": 6.29, "learning_rate": 9.911476606200422e-05, "loss": 0.4668, "step": 26250 }, { "epoch": 6.29, "learning_rate": 9.91140934687607e-05, "loss": 0.4519, "step": 26260 }, { "epoch": 6.3, "learning_rate": 9.911342062238273e-05, "loss": 0.4234, "step": 26270 }, { "epoch": 6.3, "learning_rate": 9.911274752287378e-05, "loss": 0.4404, "step": 26280 }, { "epoch": 6.3, "learning_rate": 9.911207417023732e-05, "loss": 0.3628, "step": 26290 }, { "epoch": 6.3, "learning_rate": 9.91114005644768e-05, "loss": 0.4033, "step": 26300 }, { "epoch": 6.3, "learning_rate": 9.911072670559574e-05, "loss": 0.4182, "step": 26310 }, { "epoch": 6.31, "learning_rate": 9.911005259359756e-05, "loss": 0.4224, "step": 26320 }, { "epoch": 6.31, "learning_rate": 9.910937822848577e-05, "loss": 0.4771, "step": 26330 }, { "epoch": 6.31, "learning_rate": 9.910870361026383e-05, "loss": 0.3843, "step": 26340 }, { "epoch": 6.31, "learning_rate": 9.910802873893524e-05, "loss": 0.3622, "step": 26350 }, { "epoch": 6.32, "learning_rate": 9.910735361450343e-05, "loss": 0.3014, "step": 26360 }, { "epoch": 6.32, "learning_rate": 9.910667823697192e-05, "loss": 0.4736, "step": 26370 }, { "epoch": 6.32, "learning_rate": 9.910600260634419e-05, "loss": 0.3898, "step": 26380 }, { "epoch": 6.32, "learning_rate": 9.91053267226237e-05, "loss": 0.4215, "step": 26390 }, { "epoch": 6.32, "learning_rate": 9.910465058581395e-05, "loss": 0.4054, "step": 26400 }, { "epoch": 6.33, "learning_rate": 9.910397419591841e-05, "loss": 0.4642, "step": 26410 }, { "epoch": 6.33, "learning_rate": 9.910329755294058e-05, "loss": 0.4029, "step": 26420 }, { "epoch": 6.33, "learning_rate": 9.910262065688396e-05, "loss": 0.4166, "step": 26430 }, { "epoch": 6.33, "learning_rate": 9.910194350775201e-05, "loss": 0.4029, "step": 26440 }, { "epoch": 6.34, "learning_rate": 9.910126610554824e-05, "loss": 0.4423, "step": 26450 }, { "epoch": 6.34, "learning_rate": 9.910058845027613e-05, "loss": 0.4541, "step": 26460 }, { "epoch": 6.34, "learning_rate": 9.909991054193918e-05, "loss": 0.4272, "step": 26470 }, { "epoch": 6.34, "learning_rate": 9.909923238054087e-05, "loss": 0.3265, "step": 26480 }, { "epoch": 6.35, "learning_rate": 9.909855396608472e-05, "loss": 0.4296, "step": 26490 }, { "epoch": 6.35, "learning_rate": 9.909787529857421e-05, "loss": 0.4423, "step": 26500 }, { "epoch": 6.35, "learning_rate": 9.909719637801283e-05, "loss": 0.3732, "step": 26510 }, { "epoch": 6.35, "learning_rate": 9.909651720440409e-05, "loss": 0.3148, "step": 26520 }, { "epoch": 6.35, "learning_rate": 9.90958377777515e-05, "loss": 0.4205, "step": 26530 }, { "epoch": 6.36, "learning_rate": 9.909515809805856e-05, "loss": 0.4165, "step": 26540 }, { "epoch": 6.36, "learning_rate": 9.909447816532874e-05, "loss": 0.4491, "step": 26550 }, { "epoch": 6.36, "learning_rate": 9.909379797956557e-05, "loss": 0.4323, "step": 26560 }, { "epoch": 6.36, "learning_rate": 9.909311754077257e-05, "loss": 0.4208, "step": 26570 }, { "epoch": 6.37, "learning_rate": 9.909243684895324e-05, "loss": 0.3998, "step": 26580 }, { "epoch": 6.37, "learning_rate": 9.909175590411106e-05, "loss": 0.4137, "step": 26590 }, { "epoch": 6.37, "learning_rate": 9.909107470624956e-05, "loss": 0.4229, "step": 26600 }, { "epoch": 6.37, "learning_rate": 9.909039325537226e-05, "loss": 0.3983, "step": 26610 }, { "epoch": 6.38, "learning_rate": 9.908971155148267e-05, "loss": 0.4006, "step": 26620 }, { "epoch": 6.38, "learning_rate": 9.908902959458428e-05, "loss": 0.4039, "step": 26630 }, { "epoch": 6.38, "learning_rate": 9.908834738468063e-05, "loss": 0.4317, "step": 26640 }, { "epoch": 6.38, "learning_rate": 9.908766492177524e-05, "loss": 0.4499, "step": 26650 }, { "epoch": 6.38, "learning_rate": 9.908698220587159e-05, "loss": 0.4018, "step": 26660 }, { "epoch": 6.39, "learning_rate": 9.908629923697323e-05, "loss": 0.3435, "step": 26670 }, { "epoch": 6.39, "learning_rate": 9.908561601508369e-05, "loss": 0.4398, "step": 26680 }, { "epoch": 6.39, "learning_rate": 9.908493254020645e-05, "loss": 0.4469, "step": 26690 }, { "epoch": 6.39, "learning_rate": 9.908424881234508e-05, "loss": 0.4836, "step": 26700 }, { "epoch": 6.4, "learning_rate": 9.908356483150308e-05, "loss": 0.3518, "step": 26710 }, { "epoch": 6.4, "learning_rate": 9.908288059768396e-05, "loss": 0.3583, "step": 26720 }, { "epoch": 6.4, "learning_rate": 9.908219611089126e-05, "loss": 0.3802, "step": 26730 }, { "epoch": 6.4, "learning_rate": 9.908151137112853e-05, "loss": 0.3777, "step": 26740 }, { "epoch": 6.4, "learning_rate": 9.908082637839926e-05, "loss": 0.4328, "step": 26750 }, { "epoch": 6.41, "learning_rate": 9.908014113270702e-05, "loss": 0.3739, "step": 26760 }, { "epoch": 6.41, "learning_rate": 9.907945563405532e-05, "loss": 0.3763, "step": 26770 }, { "epoch": 6.41, "learning_rate": 9.907876988244769e-05, "loss": 0.3869, "step": 26780 }, { "epoch": 6.41, "learning_rate": 9.907808387788766e-05, "loss": 0.3737, "step": 26790 }, { "epoch": 6.42, "learning_rate": 9.907739762037879e-05, "loss": 0.3674, "step": 26800 }, { "epoch": 6.42, "learning_rate": 9.90767111099246e-05, "loss": 0.4186, "step": 26810 }, { "epoch": 6.42, "learning_rate": 9.907602434652863e-05, "loss": 0.3847, "step": 26820 }, { "epoch": 6.42, "learning_rate": 9.907533733019441e-05, "loss": 0.4309, "step": 26830 }, { "epoch": 6.43, "learning_rate": 9.90746500609255e-05, "loss": 0.4699, "step": 26840 }, { "epoch": 6.43, "learning_rate": 9.907396253872543e-05, "loss": 0.4795, "step": 26850 }, { "epoch": 6.43, "learning_rate": 9.907327476359776e-05, "loss": 0.3095, "step": 26860 }, { "epoch": 6.43, "learning_rate": 9.9072586735546e-05, "loss": 0.3924, "step": 26870 }, { "epoch": 6.43, "learning_rate": 9.907189845457375e-05, "loss": 0.387, "step": 26880 }, { "epoch": 6.44, "learning_rate": 9.907120992068449e-05, "loss": 0.4898, "step": 26890 }, { "epoch": 6.44, "learning_rate": 9.907052113388183e-05, "loss": 0.3756, "step": 26900 }, { "epoch": 6.44, "learning_rate": 9.906983209416927e-05, "loss": 0.4174, "step": 26910 }, { "epoch": 6.44, "learning_rate": 9.906914280155039e-05, "loss": 0.3778, "step": 26920 }, { "epoch": 6.45, "learning_rate": 9.906845325602876e-05, "loss": 0.3865, "step": 26930 }, { "epoch": 6.45, "learning_rate": 9.906776345760789e-05, "loss": 0.3471, "step": 26940 }, { "epoch": 6.45, "learning_rate": 9.906707340629137e-05, "loss": 0.4859, "step": 26950 }, { "epoch": 6.45, "learning_rate": 9.906638310208273e-05, "loss": 0.5158, "step": 26960 }, { "epoch": 6.46, "learning_rate": 9.906569254498555e-05, "loss": 0.4286, "step": 26970 }, { "epoch": 6.46, "learning_rate": 9.906500173500339e-05, "loss": 0.3959, "step": 26980 }, { "epoch": 6.46, "learning_rate": 9.906431067213979e-05, "loss": 0.3786, "step": 26990 }, { "epoch": 6.46, "learning_rate": 9.906361935639832e-05, "loss": 0.4136, "step": 27000 }, { "epoch": 6.46, "learning_rate": 9.906292778778255e-05, "loss": 0.4163, "step": 27010 }, { "epoch": 6.47, "learning_rate": 9.906223596629604e-05, "loss": 0.341, "step": 27020 }, { "epoch": 6.47, "learning_rate": 9.906154389194235e-05, "loss": 0.3656, "step": 27030 }, { "epoch": 6.47, "learning_rate": 9.906085156472507e-05, "loss": 0.3818, "step": 27040 }, { "epoch": 6.47, "learning_rate": 9.906015898464773e-05, "loss": 0.3538, "step": 27050 }, { "epoch": 6.48, "learning_rate": 9.905946615171394e-05, "loss": 0.3931, "step": 27060 }, { "epoch": 6.48, "learning_rate": 9.905877306592723e-05, "loss": 0.4445, "step": 27070 }, { "epoch": 6.48, "learning_rate": 9.90580797272912e-05, "loss": 0.4249, "step": 27080 }, { "epoch": 6.48, "learning_rate": 9.905738613580943e-05, "loss": 0.3867, "step": 27090 }, { "epoch": 6.48, "learning_rate": 9.905669229148546e-05, "loss": 0.4188, "step": 27100 }, { "epoch": 6.49, "learning_rate": 9.905599819432291e-05, "loss": 0.3544, "step": 27110 }, { "epoch": 6.49, "learning_rate": 9.905530384432533e-05, "loss": 0.3936, "step": 27120 }, { "epoch": 6.49, "learning_rate": 9.90546092414963e-05, "loss": 0.367, "step": 27130 }, { "epoch": 6.49, "learning_rate": 9.90539143858394e-05, "loss": 0.3288, "step": 27140 }, { "epoch": 6.5, "learning_rate": 9.905321927735822e-05, "loss": 0.3719, "step": 27150 }, { "epoch": 6.5, "learning_rate": 9.905252391605633e-05, "loss": 0.3951, "step": 27160 }, { "epoch": 6.5, "learning_rate": 9.905182830193733e-05, "loss": 0.4017, "step": 27170 }, { "epoch": 6.5, "learning_rate": 9.90511324350048e-05, "loss": 0.3543, "step": 27180 }, { "epoch": 6.51, "learning_rate": 9.905043631526232e-05, "loss": 0.3556, "step": 27190 }, { "epoch": 6.51, "learning_rate": 9.904973994271349e-05, "loss": 0.3496, "step": 27200 }, { "epoch": 6.51, "learning_rate": 9.904904331736187e-05, "loss": 0.423, "step": 27210 }, { "epoch": 6.51, "learning_rate": 9.904834643921108e-05, "loss": 0.3618, "step": 27220 }, { "epoch": 6.51, "learning_rate": 9.904764930826471e-05, "loss": 0.3466, "step": 27230 }, { "epoch": 6.52, "learning_rate": 9.904695192452633e-05, "loss": 0.4451, "step": 27240 }, { "epoch": 6.52, "learning_rate": 9.904625428799957e-05, "loss": 0.4545, "step": 27250 }, { "epoch": 6.52, "learning_rate": 9.904555639868799e-05, "loss": 0.3711, "step": 27260 }, { "epoch": 6.52, "learning_rate": 9.904485825659521e-05, "loss": 0.4576, "step": 27270 }, { "epoch": 6.53, "learning_rate": 9.904415986172482e-05, "loss": 0.4997, "step": 27280 }, { "epoch": 6.53, "learning_rate": 9.904346121408042e-05, "loss": 0.5165, "step": 27290 }, { "epoch": 6.53, "learning_rate": 9.90427623136656e-05, "loss": 0.4907, "step": 27300 }, { "epoch": 6.53, "learning_rate": 9.904206316048398e-05, "loss": 0.486, "step": 27310 }, { "epoch": 6.54, "learning_rate": 9.904136375453916e-05, "loss": 0.5476, "step": 27320 }, { "epoch": 6.54, "learning_rate": 9.904066409583475e-05, "loss": 0.5029, "step": 27330 }, { "epoch": 6.54, "learning_rate": 9.903996418437432e-05, "loss": 0.5497, "step": 27340 }, { "epoch": 6.54, "learning_rate": 9.903926402016153e-05, "loss": 0.5049, "step": 27350 }, { "epoch": 6.54, "learning_rate": 9.903856360319995e-05, "loss": 0.4904, "step": 27360 }, { "epoch": 6.55, "learning_rate": 9.903786293349321e-05, "loss": 0.5313, "step": 27370 }, { "epoch": 6.55, "learning_rate": 9.903716201104491e-05, "loss": 0.5063, "step": 27380 }, { "epoch": 6.55, "learning_rate": 9.903646083585867e-05, "loss": 0.5477, "step": 27390 }, { "epoch": 6.55, "learning_rate": 9.90357594079381e-05, "loss": 0.4693, "step": 27400 }, { "epoch": 6.56, "learning_rate": 9.903505772728683e-05, "loss": 0.4733, "step": 27410 }, { "epoch": 6.56, "learning_rate": 9.903435579390844e-05, "loss": 0.5959, "step": 27420 }, { "epoch": 6.56, "learning_rate": 9.903365360780659e-05, "loss": 0.5532, "step": 27430 }, { "epoch": 6.56, "learning_rate": 9.903295116898485e-05, "loss": 0.5327, "step": 27440 }, { "epoch": 6.56, "learning_rate": 9.90322484774469e-05, "loss": 0.5656, "step": 27450 }, { "epoch": 6.57, "learning_rate": 9.903154553319632e-05, "loss": 0.4882, "step": 27460 }, { "epoch": 6.57, "learning_rate": 9.903084233623674e-05, "loss": 0.5086, "step": 27470 }, { "epoch": 6.57, "learning_rate": 9.90301388865718e-05, "loss": 0.5138, "step": 27480 }, { "epoch": 6.57, "learning_rate": 9.902943518420511e-05, "loss": 0.4515, "step": 27490 }, { "epoch": 6.58, "learning_rate": 9.90287312291403e-05, "loss": 0.5165, "step": 27500 }, { "epoch": 6.58, "learning_rate": 9.902802702138098e-05, "loss": 0.5657, "step": 27510 }, { "epoch": 6.58, "learning_rate": 9.902732256093083e-05, "loss": 0.4915, "step": 27520 }, { "epoch": 6.58, "learning_rate": 9.902661784779343e-05, "loss": 0.5057, "step": 27530 }, { "epoch": 6.59, "learning_rate": 9.902591288197244e-05, "loss": 0.4719, "step": 27540 }, { "epoch": 6.59, "learning_rate": 9.90252076634715e-05, "loss": 0.5251, "step": 27550 }, { "epoch": 6.59, "learning_rate": 9.902450219229421e-05, "loss": 0.5406, "step": 27560 }, { "epoch": 6.59, "learning_rate": 9.902379646844423e-05, "loss": 0.4467, "step": 27570 }, { "epoch": 6.59, "learning_rate": 9.90230904919252e-05, "loss": 0.4804, "step": 27580 }, { "epoch": 6.6, "learning_rate": 9.902238426274073e-05, "loss": 0.4799, "step": 27590 }, { "epoch": 6.6, "learning_rate": 9.90216777808945e-05, "loss": 0.4974, "step": 27600 }, { "epoch": 6.6, "learning_rate": 9.902097104639014e-05, "loss": 0.48, "step": 27610 }, { "epoch": 6.6, "learning_rate": 9.902026405923127e-05, "loss": 0.4844, "step": 27620 }, { "epoch": 6.61, "learning_rate": 9.901955681942155e-05, "loss": 0.5807, "step": 27630 }, { "epoch": 6.61, "learning_rate": 9.901884932696464e-05, "loss": 0.496, "step": 27640 }, { "epoch": 6.61, "learning_rate": 9.901814158186416e-05, "loss": 0.4581, "step": 27650 }, { "epoch": 6.61, "learning_rate": 9.901743358412377e-05, "loss": 0.4837, "step": 27660 }, { "epoch": 6.62, "learning_rate": 9.90167253337471e-05, "loss": 0.4081, "step": 27670 }, { "epoch": 6.62, "learning_rate": 9.901601683073784e-05, "loss": 0.4767, "step": 27680 }, { "epoch": 6.62, "learning_rate": 9.901530807509962e-05, "loss": 0.43, "step": 27690 }, { "epoch": 6.62, "learning_rate": 9.901459906683608e-05, "loss": 0.5262, "step": 27700 }, { "epoch": 6.62, "learning_rate": 9.90138898059509e-05, "loss": 0.4959, "step": 27710 }, { "epoch": 6.63, "learning_rate": 9.901318029244771e-05, "loss": 0.4701, "step": 27720 }, { "epoch": 6.63, "learning_rate": 9.901247052633019e-05, "loss": 0.5165, "step": 27730 }, { "epoch": 6.63, "learning_rate": 9.901176050760198e-05, "loss": 0.5493, "step": 27740 }, { "epoch": 6.63, "learning_rate": 9.901105023626676e-05, "loss": 0.5622, "step": 27750 }, { "epoch": 6.64, "learning_rate": 9.901033971232816e-05, "loss": 0.5913, "step": 27760 }, { "epoch": 6.64, "learning_rate": 9.900962893578987e-05, "loss": 0.4233, "step": 27770 }, { "epoch": 6.64, "learning_rate": 9.900891790665554e-05, "loss": 0.4223, "step": 27780 }, { "epoch": 6.64, "learning_rate": 9.900820662492882e-05, "loss": 0.5317, "step": 27790 }, { "epoch": 6.64, "learning_rate": 9.900749509061341e-05, "loss": 0.574, "step": 27800 }, { "epoch": 6.65, "learning_rate": 9.900678330371296e-05, "loss": 0.4658, "step": 27810 }, { "epoch": 6.65, "learning_rate": 9.900607126423114e-05, "loss": 0.5354, "step": 27820 }, { "epoch": 6.65, "learning_rate": 9.900535897217163e-05, "loss": 0.5307, "step": 27830 }, { "epoch": 6.65, "learning_rate": 9.900464642753806e-05, "loss": 0.597, "step": 27840 }, { "epoch": 6.66, "learning_rate": 9.900393363033415e-05, "loss": 0.4449, "step": 27850 }, { "epoch": 6.66, "learning_rate": 9.900322058056355e-05, "loss": 0.4812, "step": 27860 }, { "epoch": 6.66, "learning_rate": 9.900250727822996e-05, "loss": 0.595, "step": 27870 }, { "epoch": 6.66, "learning_rate": 9.900179372333702e-05, "loss": 0.4698, "step": 27880 }, { "epoch": 6.67, "learning_rate": 9.900107991588844e-05, "loss": 0.4842, "step": 27890 }, { "epoch": 6.67, "learning_rate": 9.900036585588788e-05, "loss": 0.4849, "step": 27900 }, { "epoch": 6.67, "learning_rate": 9.899965154333901e-05, "loss": 0.5406, "step": 27910 }, { "epoch": 6.67, "learning_rate": 9.899893697824554e-05, "loss": 0.448, "step": 27920 }, { "epoch": 6.67, "learning_rate": 9.899822216061115e-05, "loss": 0.343, "step": 27930 }, { "epoch": 6.68, "learning_rate": 9.899750709043949e-05, "loss": 0.4478, "step": 27940 }, { "epoch": 6.68, "learning_rate": 9.899679176773429e-05, "loss": 0.5064, "step": 27950 }, { "epoch": 6.68, "learning_rate": 9.89960761924992e-05, "loss": 0.4747, "step": 27960 }, { "epoch": 6.68, "learning_rate": 9.899536036473794e-05, "loss": 0.5247, "step": 27970 }, { "epoch": 6.69, "learning_rate": 9.899464428445415e-05, "loss": 0.4987, "step": 27980 }, { "epoch": 6.69, "learning_rate": 9.899392795165159e-05, "loss": 0.4608, "step": 27990 }, { "epoch": 6.69, "learning_rate": 9.899321136633389e-05, "loss": 0.4202, "step": 28000 }, { "epoch": 6.69, "learning_rate": 9.899249452850479e-05, "loss": 0.5003, "step": 28010 }, { "epoch": 6.7, "learning_rate": 9.899177743816795e-05, "loss": 0.4755, "step": 28020 }, { "epoch": 6.7, "learning_rate": 9.899106009532709e-05, "loss": 0.4265, "step": 28030 }, { "epoch": 6.7, "learning_rate": 9.899034249998589e-05, "loss": 0.472, "step": 28040 }, { "epoch": 6.7, "learning_rate": 9.898962465214805e-05, "loss": 0.3596, "step": 28050 }, { "epoch": 6.7, "learning_rate": 9.898890655181728e-05, "loss": 0.5211, "step": 28060 }, { "epoch": 6.71, "learning_rate": 9.898818819899727e-05, "loss": 0.5211, "step": 28070 }, { "epoch": 6.71, "learning_rate": 9.898746959369174e-05, "loss": 0.4888, "step": 28080 }, { "epoch": 6.71, "learning_rate": 9.898675073590438e-05, "loss": 0.4398, "step": 28090 }, { "epoch": 6.71, "learning_rate": 9.898603162563889e-05, "loss": 0.4057, "step": 28100 }, { "epoch": 6.72, "learning_rate": 9.8985312262899e-05, "loss": 0.503, "step": 28110 }, { "epoch": 6.72, "learning_rate": 9.898459264768838e-05, "loss": 0.431, "step": 28120 }, { "epoch": 6.72, "learning_rate": 9.898387278001078e-05, "loss": 0.4505, "step": 28130 }, { "epoch": 6.72, "learning_rate": 9.898315265986988e-05, "loss": 0.4523, "step": 28140 }, { "epoch": 6.72, "learning_rate": 9.89824322872694e-05, "loss": 0.4627, "step": 28150 }, { "epoch": 6.73, "learning_rate": 9.898171166221307e-05, "loss": 0.5111, "step": 28160 }, { "epoch": 6.73, "learning_rate": 9.898099078470456e-05, "loss": 0.5126, "step": 28170 }, { "epoch": 6.73, "learning_rate": 9.898026965474763e-05, "loss": 0.4976, "step": 28180 }, { "epoch": 6.73, "learning_rate": 9.897954827234598e-05, "loss": 0.5082, "step": 28190 }, { "epoch": 6.74, "learning_rate": 9.897882663750333e-05, "loss": 0.4618, "step": 28200 }, { "epoch": 6.74, "learning_rate": 9.89781047502234e-05, "loss": 0.3932, "step": 28210 }, { "epoch": 6.74, "learning_rate": 9.897738261050991e-05, "loss": 0.4734, "step": 28220 }, { "epoch": 6.74, "learning_rate": 9.897666021836657e-05, "loss": 0.4092, "step": 28230 }, { "epoch": 6.75, "learning_rate": 9.897593757379712e-05, "loss": 0.5097, "step": 28240 }, { "epoch": 6.75, "learning_rate": 9.897521467680527e-05, "loss": 0.466, "step": 28250 }, { "epoch": 6.75, "learning_rate": 9.897449152739477e-05, "loss": 0.4722, "step": 28260 }, { "epoch": 6.75, "learning_rate": 9.897376812556932e-05, "loss": 0.3694, "step": 28270 }, { "epoch": 6.75, "learning_rate": 9.897304447133267e-05, "loss": 0.4945, "step": 28280 }, { "epoch": 6.76, "learning_rate": 9.897232056468852e-05, "loss": 0.4552, "step": 28290 }, { "epoch": 6.76, "learning_rate": 9.897159640564064e-05, "loss": 0.4352, "step": 28300 }, { "epoch": 6.76, "learning_rate": 9.897087199419274e-05, "loss": 0.4448, "step": 28310 }, { "epoch": 6.76, "learning_rate": 9.897014733034855e-05, "loss": 0.516, "step": 28320 }, { "epoch": 6.77, "learning_rate": 9.896942241411181e-05, "loss": 0.4024, "step": 28330 }, { "epoch": 6.77, "learning_rate": 9.896869724548626e-05, "loss": 0.432, "step": 28340 }, { "epoch": 6.77, "learning_rate": 9.896797182447563e-05, "loss": 0.4932, "step": 28350 }, { "epoch": 6.77, "learning_rate": 9.896724615108368e-05, "loss": 0.4701, "step": 28360 }, { "epoch": 6.78, "learning_rate": 9.896652022531414e-05, "loss": 0.4556, "step": 28370 }, { "epoch": 6.78, "learning_rate": 9.896579404717072e-05, "loss": 0.3823, "step": 28380 }, { "epoch": 6.78, "learning_rate": 9.89650676166572e-05, "loss": 0.4409, "step": 28390 }, { "epoch": 6.78, "learning_rate": 9.896434093377731e-05, "loss": 0.3922, "step": 28400 }, { "epoch": 6.78, "learning_rate": 9.89636139985348e-05, "loss": 0.4516, "step": 28410 }, { "epoch": 6.79, "learning_rate": 9.896288681093341e-05, "loss": 0.4418, "step": 28420 }, { "epoch": 6.79, "learning_rate": 9.89621593709769e-05, "loss": 0.3598, "step": 28430 }, { "epoch": 6.79, "learning_rate": 9.8961431678669e-05, "loss": 0.5086, "step": 28440 }, { "epoch": 6.79, "learning_rate": 9.896070373401347e-05, "loss": 0.4355, "step": 28450 }, { "epoch": 6.8, "learning_rate": 9.895997553701408e-05, "loss": 0.4838, "step": 28460 }, { "epoch": 6.8, "learning_rate": 9.895924708767455e-05, "loss": 0.4647, "step": 28470 }, { "epoch": 6.8, "learning_rate": 9.895851838599866e-05, "loss": 0.4749, "step": 28480 }, { "epoch": 6.8, "learning_rate": 9.895778943199016e-05, "loss": 0.4295, "step": 28490 }, { "epoch": 6.8, "learning_rate": 9.895706022565282e-05, "loss": 0.4432, "step": 28500 }, { "epoch": 6.81, "learning_rate": 9.895633076699034e-05, "loss": 0.4522, "step": 28510 }, { "epoch": 6.81, "learning_rate": 9.895560105600654e-05, "loss": 0.5228, "step": 28520 }, { "epoch": 6.81, "learning_rate": 9.895487109270519e-05, "loss": 0.4733, "step": 28530 }, { "epoch": 6.81, "learning_rate": 9.895414087708998e-05, "loss": 0.4174, "step": 28540 }, { "epoch": 6.82, "learning_rate": 9.895341040916475e-05, "loss": 0.4043, "step": 28550 }, { "epoch": 6.82, "learning_rate": 9.895267968893323e-05, "loss": 0.4817, "step": 28560 }, { "epoch": 6.82, "learning_rate": 9.895194871639918e-05, "loss": 0.3666, "step": 28570 }, { "epoch": 6.82, "learning_rate": 9.895121749156638e-05, "loss": 0.4057, "step": 28580 }, { "epoch": 6.83, "learning_rate": 9.895048601443861e-05, "loss": 0.4641, "step": 28590 }, { "epoch": 6.83, "learning_rate": 9.894975428501961e-05, "loss": 0.5, "step": 28600 }, { "epoch": 6.83, "learning_rate": 9.894902230331317e-05, "loss": 0.4498, "step": 28610 }, { "epoch": 6.83, "learning_rate": 9.894829006932306e-05, "loss": 0.3914, "step": 28620 }, { "epoch": 6.83, "learning_rate": 9.894755758305305e-05, "loss": 0.5098, "step": 28630 }, { "epoch": 6.84, "learning_rate": 9.894682484450693e-05, "loss": 0.3909, "step": 28640 }, { "epoch": 6.84, "learning_rate": 9.894609185368846e-05, "loss": 0.3039, "step": 28650 }, { "epoch": 6.84, "learning_rate": 9.894535861060141e-05, "loss": 0.3866, "step": 28660 }, { "epoch": 6.84, "learning_rate": 9.89446251152496e-05, "loss": 0.3538, "step": 28670 }, { "epoch": 6.85, "learning_rate": 9.894389136763677e-05, "loss": 0.3957, "step": 28680 }, { "epoch": 6.85, "learning_rate": 9.894315736776672e-05, "loss": 0.4253, "step": 28690 }, { "epoch": 6.85, "learning_rate": 9.894242311564322e-05, "loss": 0.4014, "step": 28700 }, { "epoch": 6.85, "learning_rate": 9.894168861127004e-05, "loss": 0.419, "step": 28710 }, { "epoch": 6.86, "learning_rate": 9.894095385465102e-05, "loss": 0.4865, "step": 28720 }, { "epoch": 6.86, "learning_rate": 9.894021884578992e-05, "loss": 0.3831, "step": 28730 }, { "epoch": 6.86, "learning_rate": 9.893948358469049e-05, "loss": 0.4397, "step": 28740 }, { "epoch": 6.86, "learning_rate": 9.893874807135658e-05, "loss": 0.4922, "step": 28750 }, { "epoch": 6.86, "learning_rate": 9.893801230579194e-05, "loss": 0.3632, "step": 28760 }, { "epoch": 6.87, "learning_rate": 9.893727628800038e-05, "loss": 0.4591, "step": 28770 }, { "epoch": 6.87, "learning_rate": 9.89365400179857e-05, "loss": 0.3389, "step": 28780 }, { "epoch": 6.87, "learning_rate": 9.893580349575166e-05, "loss": 0.4546, "step": 28790 }, { "epoch": 6.87, "learning_rate": 9.893506672130211e-05, "loss": 0.4198, "step": 28800 }, { "epoch": 6.88, "learning_rate": 9.893432969464078e-05, "loss": 0.3986, "step": 28810 }, { "epoch": 6.88, "learning_rate": 9.893359241577153e-05, "loss": 0.4162, "step": 28820 }, { "epoch": 6.88, "learning_rate": 9.893285488469813e-05, "loss": 0.5279, "step": 28830 }, { "epoch": 6.88, "learning_rate": 9.893211710142439e-05, "loss": 0.3647, "step": 28840 }, { "epoch": 6.88, "learning_rate": 9.893137906595411e-05, "loss": 0.4403, "step": 28850 }, { "epoch": 6.89, "learning_rate": 9.89306407782911e-05, "loss": 0.4198, "step": 28860 }, { "epoch": 6.89, "learning_rate": 9.892990223843914e-05, "loss": 0.4985, "step": 28870 }, { "epoch": 6.89, "learning_rate": 9.892916344640206e-05, "loss": 0.39, "step": 28880 }, { "epoch": 6.89, "learning_rate": 9.892842440218367e-05, "loss": 0.4774, "step": 28890 }, { "epoch": 6.9, "learning_rate": 9.892768510578777e-05, "loss": 0.4524, "step": 28900 }, { "epoch": 6.9, "learning_rate": 9.892694555721817e-05, "loss": 0.3871, "step": 28910 }, { "epoch": 6.9, "learning_rate": 9.892620575647869e-05, "loss": 0.4071, "step": 28920 }, { "epoch": 6.9, "learning_rate": 9.892546570357312e-05, "loss": 0.4048, "step": 28930 }, { "epoch": 6.91, "learning_rate": 9.89247253985053e-05, "loss": 0.3436, "step": 28940 }, { "epoch": 6.91, "learning_rate": 9.892398484127905e-05, "loss": 0.4251, "step": 28950 }, { "epoch": 6.91, "learning_rate": 9.892324403189817e-05, "loss": 0.3984, "step": 28960 }, { "epoch": 6.91, "learning_rate": 9.892250297036646e-05, "loss": 0.4683, "step": 28970 }, { "epoch": 6.91, "learning_rate": 9.892176165668778e-05, "loss": 0.4807, "step": 28980 }, { "epoch": 6.92, "learning_rate": 9.892102009086593e-05, "loss": 0.4285, "step": 28990 }, { "epoch": 6.92, "learning_rate": 9.892027827290471e-05, "loss": 0.4586, "step": 29000 }, { "epoch": 6.92, "learning_rate": 9.891953620280798e-05, "loss": 0.4383, "step": 29010 }, { "epoch": 6.92, "learning_rate": 9.891879388057956e-05, "loss": 0.3957, "step": 29020 }, { "epoch": 6.93, "learning_rate": 9.891805130622327e-05, "loss": 0.3793, "step": 29030 }, { "epoch": 6.93, "learning_rate": 9.891730847974293e-05, "loss": 0.4277, "step": 29040 }, { "epoch": 6.93, "learning_rate": 9.891656540114238e-05, "loss": 0.3812, "step": 29050 }, { "epoch": 6.93, "learning_rate": 9.891582207042543e-05, "loss": 0.4035, "step": 29060 }, { "epoch": 6.94, "learning_rate": 9.891507848759592e-05, "loss": 0.4064, "step": 29070 }, { "epoch": 6.94, "learning_rate": 9.89143346526577e-05, "loss": 0.4452, "step": 29080 }, { "epoch": 6.94, "learning_rate": 9.891359056561459e-05, "loss": 0.4069, "step": 29090 }, { "epoch": 6.94, "learning_rate": 9.891284622647041e-05, "loss": 0.3821, "step": 29100 }, { "epoch": 6.94, "learning_rate": 9.891210163522903e-05, "loss": 0.3743, "step": 29110 }, { "epoch": 6.95, "learning_rate": 9.891135679189428e-05, "loss": 0.4186, "step": 29120 }, { "epoch": 6.95, "learning_rate": 9.891061169646995e-05, "loss": 0.4332, "step": 29130 }, { "epoch": 6.95, "learning_rate": 9.890986634895995e-05, "loss": 0.4178, "step": 29140 }, { "epoch": 7.0, "learning_rate": 9.890912074936806e-05, "loss": 0.3922, "step": 29150 }, { "epoch": 7.0, "learning_rate": 9.890837489769818e-05, "loss": 0.44, "step": 29160 }, { "epoch": 7.01, "learning_rate": 9.890762879395413e-05, "loss": 0.4403, "step": 29170 }, { "epoch": 7.01, "learning_rate": 9.890688243813974e-05, "loss": 0.3736, "step": 29180 }, { "epoch": 7.01, "learning_rate": 9.890613583025887e-05, "loss": 0.4895, "step": 29190 }, { "epoch": 7.01, "learning_rate": 9.890538897031536e-05, "loss": 0.3711, "step": 29200 }, { "epoch": 7.02, "learning_rate": 9.890464185831307e-05, "loss": 0.3812, "step": 29210 }, { "epoch": 7.02, "learning_rate": 9.890389449425586e-05, "loss": 0.3666, "step": 29220 }, { "epoch": 7.02, "learning_rate": 9.890314687814757e-05, "loss": 0.4366, "step": 29230 }, { "epoch": 7.02, "learning_rate": 9.890239900999204e-05, "loss": 0.5291, "step": 29240 }, { "epoch": 7.02, "learning_rate": 9.890165088979313e-05, "loss": 0.3616, "step": 29250 }, { "epoch": 7.03, "learning_rate": 9.89009025175547e-05, "loss": 0.4272, "step": 29260 }, { "epoch": 7.03, "learning_rate": 9.890015389328064e-05, "loss": 0.4242, "step": 29270 }, { "epoch": 7.03, "learning_rate": 9.889940501697475e-05, "loss": 0.4528, "step": 29280 }, { "epoch": 7.03, "learning_rate": 9.889865588864094e-05, "loss": 0.3682, "step": 29290 }, { "epoch": 7.04, "learning_rate": 9.889790650828303e-05, "loss": 0.3627, "step": 29300 }, { "epoch": 7.04, "learning_rate": 9.889715687590491e-05, "loss": 0.3694, "step": 29310 }, { "epoch": 7.04, "learning_rate": 9.889640699151042e-05, "loss": 0.3753, "step": 29320 }, { "epoch": 7.04, "learning_rate": 9.889565685510345e-05, "loss": 0.3699, "step": 29330 }, { "epoch": 7.05, "learning_rate": 9.889490646668786e-05, "loss": 0.4164, "step": 29340 }, { "epoch": 7.05, "learning_rate": 9.88941558262675e-05, "loss": 0.3842, "step": 29350 }, { "epoch": 7.05, "learning_rate": 9.889340493384628e-05, "loss": 0.4407, "step": 29360 }, { "epoch": 7.05, "learning_rate": 9.889265378942802e-05, "loss": 0.3116, "step": 29370 }, { "epoch": 7.05, "learning_rate": 9.889190239301662e-05, "loss": 0.4528, "step": 29380 }, { "epoch": 7.06, "learning_rate": 9.889115074461594e-05, "loss": 0.3464, "step": 29390 }, { "epoch": 7.06, "learning_rate": 9.889039884422988e-05, "loss": 0.4336, "step": 29400 }, { "epoch": 7.06, "learning_rate": 9.888964669186227e-05, "loss": 0.3709, "step": 29410 }, { "epoch": 7.06, "learning_rate": 9.888889428751702e-05, "loss": 0.3977, "step": 29420 }, { "epoch": 7.07, "learning_rate": 9.888814163119801e-05, "loss": 0.4053, "step": 29430 }, { "epoch": 7.07, "learning_rate": 9.88873887229091e-05, "loss": 0.3804, "step": 29440 }, { "epoch": 7.07, "learning_rate": 9.888663556265418e-05, "loss": 0.4321, "step": 29450 }, { "epoch": 7.07, "learning_rate": 9.888588215043714e-05, "loss": 0.4261, "step": 29460 }, { "epoch": 7.08, "learning_rate": 9.888512848626186e-05, "loss": 0.3971, "step": 29470 }, { "epoch": 7.08, "learning_rate": 9.88843745701322e-05, "loss": 0.3492, "step": 29480 }, { "epoch": 7.08, "learning_rate": 9.888362040205207e-05, "loss": 0.3811, "step": 29490 }, { "epoch": 7.08, "learning_rate": 9.888286598202537e-05, "loss": 0.4262, "step": 29500 }, { "epoch": 7.08, "learning_rate": 9.888211131005595e-05, "loss": 0.4149, "step": 29510 }, { "epoch": 7.09, "learning_rate": 9.888135638614773e-05, "loss": 0.3972, "step": 29520 }, { "epoch": 7.09, "learning_rate": 9.888060121030458e-05, "loss": 0.4624, "step": 29530 }, { "epoch": 7.09, "learning_rate": 9.887984578253041e-05, "loss": 0.3407, "step": 29540 }, { "epoch": 7.09, "learning_rate": 9.88790901028291e-05, "loss": 0.3818, "step": 29550 }, { "epoch": 7.1, "learning_rate": 9.887833417120455e-05, "loss": 0.3978, "step": 29560 }, { "epoch": 7.1, "learning_rate": 9.887757798766067e-05, "loss": 0.3383, "step": 29570 }, { "epoch": 7.1, "learning_rate": 9.887682155220134e-05, "loss": 0.4071, "step": 29580 }, { "epoch": 7.1, "learning_rate": 9.887606486483046e-05, "loss": 0.3696, "step": 29590 }, { "epoch": 7.1, "learning_rate": 9.887530792555192e-05, "loss": 0.3855, "step": 29600 }, { "epoch": 7.11, "learning_rate": 9.887455073436966e-05, "loss": 0.3792, "step": 29610 }, { "epoch": 7.11, "learning_rate": 9.887379329128755e-05, "loss": 0.3681, "step": 29620 }, { "epoch": 7.11, "learning_rate": 9.88730355963095e-05, "loss": 0.4184, "step": 29630 }, { "epoch": 7.11, "learning_rate": 9.887227764943941e-05, "loss": 0.3676, "step": 29640 }, { "epoch": 7.12, "learning_rate": 9.88715194506812e-05, "loss": 0.469, "step": 29650 }, { "epoch": 7.12, "learning_rate": 9.887076100003876e-05, "loss": 0.4012, "step": 29660 }, { "epoch": 7.12, "learning_rate": 9.887000229751601e-05, "loss": 0.3441, "step": 29670 }, { "epoch": 7.12, "learning_rate": 9.886924334311687e-05, "loss": 0.3996, "step": 29680 }, { "epoch": 7.13, "learning_rate": 9.886848413684523e-05, "loss": 0.4306, "step": 29690 }, { "epoch": 7.13, "learning_rate": 9.886772467870502e-05, "loss": 0.4067, "step": 29700 }, { "epoch": 7.13, "learning_rate": 9.886696496870015e-05, "loss": 0.3458, "step": 29710 }, { "epoch": 7.13, "learning_rate": 9.886620500683453e-05, "loss": 0.3, "step": 29720 }, { "epoch": 7.13, "learning_rate": 9.886544479311209e-05, "loss": 0.3518, "step": 29730 }, { "epoch": 7.14, "learning_rate": 9.886468432753673e-05, "loss": 0.3588, "step": 29740 }, { "epoch": 7.14, "learning_rate": 9.886392361011239e-05, "loss": 0.38, "step": 29750 }, { "epoch": 7.14, "learning_rate": 9.886316264084296e-05, "loss": 0.3538, "step": 29760 }, { "epoch": 7.14, "learning_rate": 9.886240141973239e-05, "loss": 0.4164, "step": 29770 }, { "epoch": 7.15, "learning_rate": 9.886163994678458e-05, "loss": 0.3071, "step": 29780 }, { "epoch": 7.15, "learning_rate": 9.88608782220035e-05, "loss": 0.345, "step": 29790 }, { "epoch": 7.15, "learning_rate": 9.886011624539303e-05, "loss": 0.2769, "step": 29800 }, { "epoch": 7.15, "learning_rate": 9.885935401695712e-05, "loss": 0.4213, "step": 29810 }, { "epoch": 7.16, "learning_rate": 9.885859153669968e-05, "loss": 0.3471, "step": 29820 }, { "epoch": 7.16, "learning_rate": 9.885782880462465e-05, "loss": 0.3761, "step": 29830 }, { "epoch": 7.16, "learning_rate": 9.885706582073597e-05, "loss": 0.3591, "step": 29840 }, { "epoch": 7.16, "learning_rate": 9.885630258503757e-05, "loss": 0.3446, "step": 29850 }, { "epoch": 7.16, "learning_rate": 9.885553909753335e-05, "loss": 0.3856, "step": 29860 }, { "epoch": 7.17, "learning_rate": 9.88547753582273e-05, "loss": 0.3737, "step": 29870 }, { "epoch": 7.17, "learning_rate": 9.885401136712332e-05, "loss": 0.3268, "step": 29880 }, { "epoch": 7.17, "learning_rate": 9.885324712422536e-05, "loss": 0.3801, "step": 29890 }, { "epoch": 7.17, "learning_rate": 9.885248262953736e-05, "loss": 0.4252, "step": 29900 }, { "epoch": 7.18, "learning_rate": 9.885171788306325e-05, "loss": 0.3891, "step": 29910 }, { "epoch": 7.18, "learning_rate": 9.885095288480698e-05, "loss": 0.3324, "step": 29920 }, { "epoch": 7.18, "learning_rate": 9.88501876347725e-05, "loss": 0.4355, "step": 29930 }, { "epoch": 7.18, "learning_rate": 9.884942213296372e-05, "loss": 0.2934, "step": 29940 }, { "epoch": 7.18, "learning_rate": 9.884865637938463e-05, "loss": 0.311, "step": 29950 }, { "epoch": 7.19, "learning_rate": 9.884789037403914e-05, "loss": 0.3814, "step": 29960 }, { "epoch": 7.19, "learning_rate": 9.884712411693123e-05, "loss": 0.4097, "step": 29970 }, { "epoch": 7.19, "learning_rate": 9.884635760806483e-05, "loss": 0.3771, "step": 29980 }, { "epoch": 7.19, "learning_rate": 9.88455908474439e-05, "loss": 0.4096, "step": 29990 }, { "epoch": 7.2, "learning_rate": 9.884482383507238e-05, "loss": 0.4241, "step": 30000 }, { "epoch": 7.2, "learning_rate": 9.884405657095422e-05, "loss": 0.383, "step": 30010 }, { "epoch": 7.2, "learning_rate": 9.88432890550934e-05, "loss": 0.3982, "step": 30020 }, { "epoch": 7.2, "learning_rate": 9.884252128749386e-05, "loss": 0.3154, "step": 30030 }, { "epoch": 7.21, "learning_rate": 9.884175326815954e-05, "loss": 0.3341, "step": 30040 }, { "epoch": 7.21, "learning_rate": 9.884098499709444e-05, "loss": 0.4002, "step": 30050 }, { "epoch": 7.21, "learning_rate": 9.884021647430247e-05, "loss": 0.4843, "step": 30060 }, { "epoch": 7.21, "learning_rate": 9.883944769978764e-05, "loss": 0.3053, "step": 30070 }, { "epoch": 7.21, "learning_rate": 9.883867867355387e-05, "loss": 0.3726, "step": 30080 }, { "epoch": 7.22, "learning_rate": 9.883790939560514e-05, "loss": 0.4534, "step": 30090 }, { "epoch": 7.22, "learning_rate": 9.883713986594543e-05, "loss": 0.3777, "step": 30100 }, { "epoch": 7.22, "learning_rate": 9.883637008457869e-05, "loss": 0.3318, "step": 30110 }, { "epoch": 7.22, "learning_rate": 9.883560005150889e-05, "loss": 0.4076, "step": 30120 }, { "epoch": 7.23, "learning_rate": 9.883482976673999e-05, "loss": 0.4052, "step": 30130 }, { "epoch": 7.23, "learning_rate": 9.883405923027598e-05, "loss": 0.4382, "step": 30140 }, { "epoch": 7.23, "learning_rate": 9.883328844212081e-05, "loss": 0.3381, "step": 30150 }, { "epoch": 7.23, "learning_rate": 9.883251740227848e-05, "loss": 0.4206, "step": 30160 }, { "epoch": 7.24, "learning_rate": 9.883174611075294e-05, "loss": 0.3236, "step": 30170 }, { "epoch": 7.24, "learning_rate": 9.883097456754816e-05, "loss": 0.2829, "step": 30180 }, { "epoch": 7.24, "learning_rate": 9.883020277266815e-05, "loss": 0.3579, "step": 30190 }, { "epoch": 7.24, "learning_rate": 9.882943072611684e-05, "loss": 0.4433, "step": 30200 }, { "epoch": 7.24, "learning_rate": 9.882865842789826e-05, "loss": 0.3852, "step": 30210 }, { "epoch": 7.25, "learning_rate": 9.882788587801635e-05, "loss": 0.4025, "step": 30220 }, { "epoch": 7.25, "learning_rate": 9.882711307647513e-05, "loss": 0.4327, "step": 30230 }, { "epoch": 7.25, "learning_rate": 9.882634002327853e-05, "loss": 0.4057, "step": 30240 }, { "epoch": 7.25, "learning_rate": 9.882556671843058e-05, "loss": 0.4017, "step": 30250 }, { "epoch": 7.26, "learning_rate": 9.882479316193526e-05, "loss": 0.3198, "step": 30260 }, { "epoch": 7.26, "learning_rate": 9.882401935379653e-05, "loss": 0.3686, "step": 30270 }, { "epoch": 7.26, "learning_rate": 9.882324529401841e-05, "loss": 0.4279, "step": 30280 }, { "epoch": 7.26, "learning_rate": 9.882247098260487e-05, "loss": 0.4135, "step": 30290 }, { "epoch": 7.26, "learning_rate": 9.882169641955991e-05, "loss": 0.3253, "step": 30300 }, { "epoch": 7.27, "learning_rate": 9.882092160488752e-05, "loss": 0.351, "step": 30310 }, { "epoch": 7.27, "learning_rate": 9.882014653859169e-05, "loss": 0.3922, "step": 30320 }, { "epoch": 7.27, "learning_rate": 9.881937122067642e-05, "loss": 0.3191, "step": 30330 }, { "epoch": 7.27, "learning_rate": 9.88185956511457e-05, "loss": 0.389, "step": 30340 }, { "epoch": 7.28, "learning_rate": 9.881781983000354e-05, "loss": 0.3185, "step": 30350 }, { "epoch": 7.28, "learning_rate": 9.881704375725391e-05, "loss": 0.4088, "step": 30360 }, { "epoch": 7.28, "learning_rate": 9.881626743290083e-05, "loss": 0.376, "step": 30370 }, { "epoch": 7.28, "learning_rate": 9.88154908569483e-05, "loss": 0.4301, "step": 30380 }, { "epoch": 7.29, "learning_rate": 9.881471402940034e-05, "loss": 0.3427, "step": 30390 }, { "epoch": 7.29, "learning_rate": 9.881393695026091e-05, "loss": 0.3339, "step": 30400 }, { "epoch": 7.29, "learning_rate": 9.881315961953405e-05, "loss": 0.3155, "step": 30410 }, { "epoch": 7.29, "learning_rate": 9.881238203722377e-05, "loss": 0.3056, "step": 30420 }, { "epoch": 7.29, "learning_rate": 9.881160420333407e-05, "loss": 0.3427, "step": 30430 }, { "epoch": 7.3, "learning_rate": 9.881082611786893e-05, "loss": 0.3413, "step": 30440 }, { "epoch": 7.3, "learning_rate": 9.881004778083239e-05, "loss": 0.4114, "step": 30450 }, { "epoch": 7.3, "learning_rate": 9.880926919222845e-05, "loss": 0.3246, "step": 30460 }, { "epoch": 7.3, "learning_rate": 9.880849035206115e-05, "loss": 0.3627, "step": 30470 }, { "epoch": 7.31, "learning_rate": 9.880771126033447e-05, "loss": 0.3202, "step": 30480 }, { "epoch": 7.31, "learning_rate": 9.880693191705245e-05, "loss": 0.3755, "step": 30490 }, { "epoch": 7.31, "learning_rate": 9.880615232221908e-05, "loss": 0.3235, "step": 30500 }, { "epoch": 7.31, "learning_rate": 9.88053724758384e-05, "loss": 0.4515, "step": 30510 }, { "epoch": 7.32, "learning_rate": 9.880459237791442e-05, "loss": 0.3438, "step": 30520 }, { "epoch": 7.32, "learning_rate": 9.880381202845118e-05, "loss": 0.3998, "step": 30530 }, { "epoch": 7.32, "learning_rate": 9.880303142745265e-05, "loss": 0.318, "step": 30540 }, { "epoch": 7.32, "learning_rate": 9.88022505749229e-05, "loss": 0.3612, "step": 30550 }, { "epoch": 7.32, "learning_rate": 9.880146947086594e-05, "loss": 0.4464, "step": 30560 }, { "epoch": 7.33, "learning_rate": 9.880068811528582e-05, "loss": 0.3615, "step": 30570 }, { "epoch": 7.33, "learning_rate": 9.879990650818654e-05, "loss": 0.3806, "step": 30580 }, { "epoch": 7.33, "learning_rate": 9.879912464957213e-05, "loss": 0.3222, "step": 30590 }, { "epoch": 7.33, "learning_rate": 9.879834253944662e-05, "loss": 0.3027, "step": 30600 }, { "epoch": 7.34, "learning_rate": 9.879756017781403e-05, "loss": 0.3414, "step": 30610 }, { "epoch": 7.34, "learning_rate": 9.879677756467842e-05, "loss": 0.365, "step": 30620 }, { "epoch": 7.34, "learning_rate": 9.879599470004381e-05, "loss": 0.3921, "step": 30630 }, { "epoch": 7.34, "learning_rate": 9.879521158391425e-05, "loss": 0.3426, "step": 30640 }, { "epoch": 7.34, "learning_rate": 9.879442821629374e-05, "loss": 0.3974, "step": 30650 }, { "epoch": 7.35, "learning_rate": 9.879364459718637e-05, "loss": 0.3897, "step": 30660 }, { "epoch": 7.35, "learning_rate": 9.879286072659612e-05, "loss": 0.331, "step": 30670 }, { "epoch": 7.35, "learning_rate": 9.879207660452706e-05, "loss": 0.3181, "step": 30680 }, { "epoch": 7.35, "learning_rate": 9.879129223098324e-05, "loss": 0.3582, "step": 30690 }, { "epoch": 7.36, "learning_rate": 9.879050760596869e-05, "loss": 0.4342, "step": 30700 }, { "epoch": 7.36, "learning_rate": 9.878972272948743e-05, "loss": 0.3591, "step": 30710 }, { "epoch": 7.36, "learning_rate": 9.878893760154357e-05, "loss": 0.3955, "step": 30720 }, { "epoch": 7.36, "learning_rate": 9.878815222214109e-05, "loss": 0.3382, "step": 30730 }, { "epoch": 7.37, "learning_rate": 9.878736659128408e-05, "loss": 0.4039, "step": 30740 }, { "epoch": 7.37, "learning_rate": 9.878658070897658e-05, "loss": 0.3634, "step": 30750 }, { "epoch": 7.37, "learning_rate": 9.878579457522262e-05, "loss": 0.3656, "step": 30760 }, { "epoch": 7.37, "learning_rate": 9.878500819002628e-05, "loss": 0.3853, "step": 30770 }, { "epoch": 7.37, "learning_rate": 9.878422155339158e-05, "loss": 0.3431, "step": 30780 }, { "epoch": 7.38, "learning_rate": 9.878343466532261e-05, "loss": 0.3635, "step": 30790 }, { "epoch": 7.38, "learning_rate": 9.878264752582341e-05, "loss": 0.3309, "step": 30800 }, { "epoch": 7.38, "learning_rate": 9.878186013489803e-05, "loss": 0.3506, "step": 30810 }, { "epoch": 7.38, "learning_rate": 9.878107249255055e-05, "loss": 0.3683, "step": 30820 }, { "epoch": 7.39, "learning_rate": 9.8780284598785e-05, "loss": 0.2712, "step": 30830 }, { "epoch": 7.39, "learning_rate": 9.877949645360546e-05, "loss": 0.3538, "step": 30840 }, { "epoch": 7.39, "learning_rate": 9.8778708057016e-05, "loss": 0.375, "step": 30850 }, { "epoch": 7.39, "learning_rate": 9.877791940902064e-05, "loss": 0.3713, "step": 30860 }, { "epoch": 7.4, "learning_rate": 9.87771305096235e-05, "loss": 0.3228, "step": 30870 }, { "epoch": 7.4, "learning_rate": 9.877634135882862e-05, "loss": 0.3295, "step": 30880 }, { "epoch": 7.4, "learning_rate": 9.877555195664005e-05, "loss": 0.3656, "step": 30890 }, { "epoch": 7.4, "learning_rate": 9.87747623030619e-05, "loss": 0.3719, "step": 30900 }, { "epoch": 7.4, "learning_rate": 9.87739723980982e-05, "loss": 0.292, "step": 30910 }, { "epoch": 7.41, "learning_rate": 9.877318224175306e-05, "loss": 0.3438, "step": 30920 }, { "epoch": 7.41, "learning_rate": 9.877239183403052e-05, "loss": 0.3532, "step": 30930 }, { "epoch": 7.41, "learning_rate": 9.877160117493467e-05, "loss": 0.4285, "step": 30940 }, { "epoch": 7.41, "learning_rate": 9.877081026446957e-05, "loss": 0.3448, "step": 30950 }, { "epoch": 7.42, "learning_rate": 9.87700191026393e-05, "loss": 0.348, "step": 30960 }, { "epoch": 7.42, "learning_rate": 9.876922768944796e-05, "loss": 0.3059, "step": 30970 }, { "epoch": 7.42, "learning_rate": 9.87684360248996e-05, "loss": 0.3534, "step": 30980 }, { "epoch": 7.42, "learning_rate": 9.876764410899833e-05, "loss": 0.3081, "step": 30990 }, { "epoch": 7.42, "learning_rate": 9.87668519417482e-05, "loss": 0.2913, "step": 31000 }, { "epoch": 7.43, "learning_rate": 9.876605952315332e-05, "loss": 0.341, "step": 31010 }, { "epoch": 7.43, "learning_rate": 9.876526685321774e-05, "loss": 0.311, "step": 31020 }, { "epoch": 7.43, "learning_rate": 9.876447393194559e-05, "loss": 0.3673, "step": 31030 }, { "epoch": 7.43, "learning_rate": 9.876368075934092e-05, "loss": 0.3617, "step": 31040 }, { "epoch": 7.44, "learning_rate": 9.876288733540784e-05, "loss": 0.3957, "step": 31050 }, { "epoch": 7.44, "learning_rate": 9.876209366015042e-05, "loss": 0.2374, "step": 31060 }, { "epoch": 7.44, "learning_rate": 9.876129973357277e-05, "loss": 0.322, "step": 31070 }, { "epoch": 7.44, "learning_rate": 9.876050555567897e-05, "loss": 0.2835, "step": 31080 }, { "epoch": 7.45, "learning_rate": 9.875971112647313e-05, "loss": 0.3793, "step": 31090 }, { "epoch": 7.45, "learning_rate": 9.875891644595931e-05, "loss": 0.3588, "step": 31100 }, { "epoch": 7.45, "learning_rate": 9.875812151414165e-05, "loss": 0.3427, "step": 31110 }, { "epoch": 7.45, "learning_rate": 9.87573263310242e-05, "loss": 0.3481, "step": 31120 }, { "epoch": 7.45, "learning_rate": 9.87565308966111e-05, "loss": 0.3358, "step": 31130 }, { "epoch": 7.46, "learning_rate": 9.875573521090642e-05, "loss": 0.3795, "step": 31140 }, { "epoch": 7.46, "learning_rate": 9.875493927391429e-05, "loss": 0.3872, "step": 31150 }, { "epoch": 7.46, "learning_rate": 9.875414308563878e-05, "loss": 0.3252, "step": 31160 }, { "epoch": 7.46, "learning_rate": 9.875334664608401e-05, "loss": 0.3093, "step": 31170 }, { "epoch": 7.47, "learning_rate": 9.875254995525409e-05, "loss": 0.3387, "step": 31180 }, { "epoch": 7.47, "learning_rate": 9.875175301315311e-05, "loss": 0.3454, "step": 31190 }, { "epoch": 7.47, "learning_rate": 9.87509558197852e-05, "loss": 0.3513, "step": 31200 }, { "epoch": 7.47, "learning_rate": 9.875015837515445e-05, "loss": 0.4009, "step": 31210 }, { "epoch": 7.48, "learning_rate": 9.874936067926499e-05, "loss": 0.3772, "step": 31220 }, { "epoch": 7.48, "learning_rate": 9.87485627321209e-05, "loss": 0.3419, "step": 31230 }, { "epoch": 7.48, "learning_rate": 9.874776453372632e-05, "loss": 0.3627, "step": 31240 }, { "epoch": 7.48, "learning_rate": 9.874696608408535e-05, "loss": 0.2898, "step": 31250 }, { "epoch": 7.48, "learning_rate": 9.87461673832021e-05, "loss": 0.3497, "step": 31260 }, { "epoch": 7.49, "learning_rate": 9.87453684310807e-05, "loss": 0.4135, "step": 31270 }, { "epoch": 7.49, "learning_rate": 9.874456922772529e-05, "loss": 0.3406, "step": 31280 }, { "epoch": 7.49, "learning_rate": 9.874376977313992e-05, "loss": 0.4017, "step": 31290 }, { "epoch": 7.49, "learning_rate": 9.874297006732878e-05, "loss": 0.3454, "step": 31300 }, { "epoch": 7.5, "learning_rate": 9.874217011029596e-05, "loss": 0.3867, "step": 31310 }, { "epoch": 7.5, "learning_rate": 9.87413699020456e-05, "loss": 0.4255, "step": 31320 }, { "epoch": 7.5, "learning_rate": 9.874056944258179e-05, "loss": 0.321, "step": 31330 }, { "epoch": 7.5, "learning_rate": 9.873976873190869e-05, "loss": 0.3575, "step": 31340 }, { "epoch": 7.5, "learning_rate": 9.873896777003042e-05, "loss": 0.323, "step": 31350 }, { "epoch": 7.51, "learning_rate": 9.873816655695108e-05, "loss": 0.3543, "step": 31360 }, { "epoch": 7.51, "learning_rate": 9.873736509267484e-05, "loss": 0.3003, "step": 31370 }, { "epoch": 7.51, "learning_rate": 9.87365633772058e-05, "loss": 0.3417, "step": 31380 }, { "epoch": 7.51, "learning_rate": 9.873576141054812e-05, "loss": 0.2972, "step": 31390 }, { "epoch": 7.52, "learning_rate": 9.873495919270593e-05, "loss": 0.3712, "step": 31400 }, { "epoch": 7.52, "learning_rate": 9.873415672368331e-05, "loss": 0.3538, "step": 31410 }, { "epoch": 7.52, "learning_rate": 9.873335400348446e-05, "loss": 0.3367, "step": 31420 }, { "epoch": 7.52, "learning_rate": 9.873255103211352e-05, "loss": 0.3856, "step": 31430 }, { "epoch": 7.53, "learning_rate": 9.873174780957459e-05, "loss": 0.3683, "step": 31440 }, { "epoch": 7.53, "learning_rate": 9.873094433587181e-05, "loss": 0.4935, "step": 31450 }, { "epoch": 7.53, "learning_rate": 9.873014061100935e-05, "loss": 0.4532, "step": 31460 }, { "epoch": 7.53, "learning_rate": 9.872933663499134e-05, "loss": 0.379, "step": 31470 }, { "epoch": 7.53, "learning_rate": 9.872853240782191e-05, "loss": 0.4032, "step": 31480 }, { "epoch": 7.54, "learning_rate": 9.872772792950523e-05, "loss": 0.3984, "step": 31490 }, { "epoch": 7.54, "learning_rate": 9.872692320004541e-05, "loss": 0.3874, "step": 31500 }, { "epoch": 7.54, "learning_rate": 9.872611821944665e-05, "loss": 0.4807, "step": 31510 }, { "epoch": 7.54, "learning_rate": 9.872531298771303e-05, "loss": 0.4939, "step": 31520 }, { "epoch": 7.55, "learning_rate": 9.872450750484877e-05, "loss": 0.3874, "step": 31530 }, { "epoch": 7.55, "learning_rate": 9.872370177085799e-05, "loss": 0.3824, "step": 31540 }, { "epoch": 7.55, "learning_rate": 9.872289578574484e-05, "loss": 0.5021, "step": 31550 }, { "epoch": 7.55, "learning_rate": 9.872208954951347e-05, "loss": 0.4427, "step": 31560 }, { "epoch": 7.56, "learning_rate": 9.872128306216806e-05, "loss": 0.4164, "step": 31570 }, { "epoch": 7.56, "learning_rate": 9.872047632371274e-05, "loss": 0.4824, "step": 31580 }, { "epoch": 7.56, "learning_rate": 9.871966933415168e-05, "loss": 0.5154, "step": 31590 }, { "epoch": 7.56, "learning_rate": 9.871886209348903e-05, "loss": 0.4315, "step": 31600 }, { "epoch": 7.56, "learning_rate": 9.871805460172895e-05, "loss": 0.4764, "step": 31610 }, { "epoch": 7.57, "learning_rate": 9.871724685887564e-05, "loss": 0.4321, "step": 31620 }, { "epoch": 7.57, "learning_rate": 9.87164388649332e-05, "loss": 0.4993, "step": 31630 }, { "epoch": 7.57, "learning_rate": 9.871563061990586e-05, "loss": 0.4389, "step": 31640 }, { "epoch": 7.57, "learning_rate": 9.871482212379773e-05, "loss": 0.3743, "step": 31650 }, { "epoch": 7.58, "learning_rate": 9.871401337661299e-05, "loss": 0.4591, "step": 31660 }, { "epoch": 7.58, "learning_rate": 9.871320437835583e-05, "loss": 0.4294, "step": 31670 }, { "epoch": 7.58, "learning_rate": 9.87123951290304e-05, "loss": 0.5144, "step": 31680 }, { "epoch": 7.58, "learning_rate": 9.87115856286409e-05, "loss": 0.4206, "step": 31690 }, { "epoch": 7.58, "learning_rate": 9.871077587719147e-05, "loss": 0.4469, "step": 31700 }, { "epoch": 7.59, "learning_rate": 9.870996587468628e-05, "loss": 0.3471, "step": 31710 }, { "epoch": 7.59, "learning_rate": 9.870915562112954e-05, "loss": 0.4685, "step": 31720 }, { "epoch": 7.59, "learning_rate": 9.87083451165254e-05, "loss": 0.4828, "step": 31730 }, { "epoch": 7.59, "learning_rate": 9.870753436087803e-05, "loss": 0.4731, "step": 31740 }, { "epoch": 7.6, "learning_rate": 9.870672335419162e-05, "loss": 0.3674, "step": 31750 }, { "epoch": 7.6, "learning_rate": 9.870591209647037e-05, "loss": 0.4049, "step": 31760 }, { "epoch": 7.6, "learning_rate": 9.870510058771842e-05, "loss": 0.4066, "step": 31770 }, { "epoch": 7.6, "learning_rate": 9.870428882793998e-05, "loss": 0.4388, "step": 31780 }, { "epoch": 7.61, "learning_rate": 9.870347681713925e-05, "loss": 0.4545, "step": 31790 }, { "epoch": 7.61, "learning_rate": 9.870266455532036e-05, "loss": 0.4309, "step": 31800 }, { "epoch": 7.61, "learning_rate": 9.870185204248757e-05, "loss": 0.3083, "step": 31810 }, { "epoch": 7.61, "learning_rate": 9.8701039278645e-05, "loss": 0.3092, "step": 31820 }, { "epoch": 7.61, "learning_rate": 9.870022626379687e-05, "loss": 0.4732, "step": 31830 }, { "epoch": 7.62, "learning_rate": 9.869941299794736e-05, "loss": 0.4475, "step": 31840 }, { "epoch": 7.62, "learning_rate": 9.869859948110067e-05, "loss": 0.3692, "step": 31850 }, { "epoch": 7.62, "learning_rate": 9.869778571326101e-05, "loss": 0.3689, "step": 31860 }, { "epoch": 7.62, "learning_rate": 9.869697169443252e-05, "loss": 0.4169, "step": 31870 }, { "epoch": 7.63, "learning_rate": 9.869615742461946e-05, "loss": 0.4073, "step": 31880 }, { "epoch": 7.63, "learning_rate": 9.8695342903826e-05, "loss": 0.4595, "step": 31890 }, { "epoch": 7.63, "learning_rate": 9.869452813205632e-05, "loss": 0.4312, "step": 31900 }, { "epoch": 7.63, "learning_rate": 9.869371310931464e-05, "loss": 0.408, "step": 31910 }, { "epoch": 7.64, "learning_rate": 9.869289783560516e-05, "loss": 0.4372, "step": 31920 }, { "epoch": 7.64, "learning_rate": 9.869208231093207e-05, "loss": 0.37, "step": 31930 }, { "epoch": 7.64, "learning_rate": 9.869126653529959e-05, "loss": 0.4936, "step": 31940 }, { "epoch": 7.64, "learning_rate": 9.869045050871191e-05, "loss": 0.4615, "step": 31950 }, { "epoch": 7.64, "learning_rate": 9.868963423117324e-05, "loss": 0.3541, "step": 31960 }, { "epoch": 7.65, "learning_rate": 9.868881770268779e-05, "loss": 0.3968, "step": 31970 }, { "epoch": 7.65, "learning_rate": 9.868800092325976e-05, "loss": 0.4388, "step": 31980 }, { "epoch": 7.65, "learning_rate": 9.868718389289337e-05, "loss": 0.3406, "step": 31990 }, { "epoch": 7.65, "learning_rate": 9.868636661159283e-05, "loss": 0.5177, "step": 32000 }, { "epoch": 7.66, "learning_rate": 9.868554907936236e-05, "loss": 0.433, "step": 32010 }, { "epoch": 7.66, "learning_rate": 9.868473129620615e-05, "loss": 0.4419, "step": 32020 }, { "epoch": 7.66, "learning_rate": 9.868391326212843e-05, "loss": 0.4455, "step": 32030 }, { "epoch": 7.66, "learning_rate": 9.868309497713342e-05, "loss": 0.3668, "step": 32040 }, { "epoch": 7.66, "learning_rate": 9.868227644122531e-05, "loss": 0.3721, "step": 32050 }, { "epoch": 7.67, "learning_rate": 9.868145765440836e-05, "loss": 0.488, "step": 32060 }, { "epoch": 7.67, "learning_rate": 9.868063861668676e-05, "loss": 0.331, "step": 32070 }, { "epoch": 7.67, "learning_rate": 9.867981932806477e-05, "loss": 0.4757, "step": 32080 }, { "epoch": 7.67, "learning_rate": 9.867899978854655e-05, "loss": 0.3551, "step": 32090 }, { "epoch": 7.68, "learning_rate": 9.867817999813638e-05, "loss": 0.4065, "step": 32100 }, { "epoch": 7.68, "learning_rate": 9.867735995683844e-05, "loss": 0.4035, "step": 32110 }, { "epoch": 7.68, "learning_rate": 9.8676539664657e-05, "loss": 0.3677, "step": 32120 }, { "epoch": 7.68, "learning_rate": 9.867571912159626e-05, "loss": 0.4792, "step": 32130 }, { "epoch": 7.69, "learning_rate": 9.867489832766045e-05, "loss": 0.4428, "step": 32140 }, { "epoch": 7.69, "learning_rate": 9.867407728285383e-05, "loss": 0.3846, "step": 32150 }, { "epoch": 7.69, "learning_rate": 9.867325598718059e-05, "loss": 0.4273, "step": 32160 }, { "epoch": 7.69, "learning_rate": 9.867243444064498e-05, "loss": 0.4832, "step": 32170 }, { "epoch": 7.69, "learning_rate": 9.867161264325124e-05, "loss": 0.4211, "step": 32180 }, { "epoch": 7.7, "learning_rate": 9.867079059500361e-05, "loss": 0.4154, "step": 32190 }, { "epoch": 7.7, "learning_rate": 9.86699682959063e-05, "loss": 0.361, "step": 32200 }, { "epoch": 7.7, "learning_rate": 9.866914574596358e-05, "loss": 0.3441, "step": 32210 }, { "epoch": 7.7, "learning_rate": 9.86683229451797e-05, "loss": 0.3581, "step": 32220 }, { "epoch": 7.71, "learning_rate": 9.866749989355883e-05, "loss": 0.4227, "step": 32230 }, { "epoch": 7.71, "learning_rate": 9.866667659110529e-05, "loss": 0.3954, "step": 32240 }, { "epoch": 7.71, "learning_rate": 9.866585303782327e-05, "loss": 0.3123, "step": 32250 }, { "epoch": 7.71, "learning_rate": 9.866502923371706e-05, "loss": 0.3481, "step": 32260 }, { "epoch": 7.72, "learning_rate": 9.866420517879087e-05, "loss": 0.4409, "step": 32270 }, { "epoch": 7.72, "learning_rate": 9.866338087304896e-05, "loss": 0.3677, "step": 32280 }, { "epoch": 7.72, "learning_rate": 9.866255631649558e-05, "loss": 0.397, "step": 32290 }, { "epoch": 7.72, "learning_rate": 9.866173150913499e-05, "loss": 0.3752, "step": 32300 }, { "epoch": 7.72, "learning_rate": 9.86609064509714e-05, "loss": 0.4173, "step": 32310 }, { "epoch": 7.73, "learning_rate": 9.866008114200911e-05, "loss": 0.3983, "step": 32320 }, { "epoch": 7.73, "learning_rate": 9.865925558225235e-05, "loss": 0.4235, "step": 32330 }, { "epoch": 7.73, "learning_rate": 9.865842977170538e-05, "loss": 0.3601, "step": 32340 }, { "epoch": 7.73, "learning_rate": 9.865760371037247e-05, "loss": 0.3768, "step": 32350 }, { "epoch": 7.74, "learning_rate": 9.865677739825785e-05, "loss": 0.3332, "step": 32360 }, { "epoch": 7.74, "learning_rate": 9.86559508353658e-05, "loss": 0.3423, "step": 32370 }, { "epoch": 7.74, "learning_rate": 9.865512402170057e-05, "loss": 0.3681, "step": 32380 }, { "epoch": 7.74, "learning_rate": 9.865429695726643e-05, "loss": 0.3796, "step": 32390 }, { "epoch": 7.74, "learning_rate": 9.86534696420676e-05, "loss": 0.323, "step": 32400 }, { "epoch": 7.75, "learning_rate": 9.865264207610843e-05, "loss": 0.4382, "step": 32410 }, { "epoch": 7.75, "learning_rate": 9.865181425939312e-05, "loss": 0.3534, "step": 32420 }, { "epoch": 7.75, "learning_rate": 9.865098619192595e-05, "loss": 0.4378, "step": 32430 }, { "epoch": 7.75, "learning_rate": 9.865015787371117e-05, "loss": 0.3931, "step": 32440 }, { "epoch": 7.76, "learning_rate": 9.86493293047531e-05, "loss": 0.3965, "step": 32450 }, { "epoch": 7.76, "learning_rate": 9.864850048505597e-05, "loss": 0.3891, "step": 32460 }, { "epoch": 7.76, "learning_rate": 9.864767141462406e-05, "loss": 0.3369, "step": 32470 }, { "epoch": 7.76, "learning_rate": 9.864684209346164e-05, "loss": 0.4036, "step": 32480 }, { "epoch": 7.77, "learning_rate": 9.864601252157299e-05, "loss": 0.3157, "step": 32490 }, { "epoch": 7.77, "learning_rate": 9.864518269896239e-05, "loss": 0.4244, "step": 32500 }, { "epoch": 7.77, "learning_rate": 9.864435262563412e-05, "loss": 0.39, "step": 32510 }, { "epoch": 7.77, "learning_rate": 9.864352230159244e-05, "loss": 0.4402, "step": 32520 }, { "epoch": 7.77, "learning_rate": 9.864269172684164e-05, "loss": 0.3519, "step": 32530 }, { "epoch": 7.78, "learning_rate": 9.864186090138601e-05, "loss": 0.3396, "step": 32540 }, { "epoch": 7.78, "learning_rate": 9.86410298252298e-05, "loss": 0.3761, "step": 32550 }, { "epoch": 7.78, "learning_rate": 9.864019849837734e-05, "loss": 0.4145, "step": 32560 }, { "epoch": 7.78, "learning_rate": 9.863936692083287e-05, "loss": 0.3545, "step": 32570 }, { "epoch": 7.79, "learning_rate": 9.863853509260071e-05, "loss": 0.3601, "step": 32580 }, { "epoch": 7.79, "learning_rate": 9.863770301368513e-05, "loss": 0.4043, "step": 32590 }, { "epoch": 7.79, "learning_rate": 9.863687068409043e-05, "loss": 0.3797, "step": 32600 }, { "epoch": 7.79, "learning_rate": 9.863603810382088e-05, "loss": 0.4961, "step": 32610 }, { "epoch": 7.8, "learning_rate": 9.863520527288079e-05, "loss": 0.374, "step": 32620 }, { "epoch": 7.8, "learning_rate": 9.863437219127443e-05, "loss": 0.3738, "step": 32630 }, { "epoch": 7.8, "learning_rate": 9.863353885900612e-05, "loss": 0.318, "step": 32640 }, { "epoch": 7.8, "learning_rate": 9.863270527608015e-05, "loss": 0.4422, "step": 32650 }, { "epoch": 7.8, "learning_rate": 9.863187144250081e-05, "loss": 0.3236, "step": 32660 }, { "epoch": 7.81, "learning_rate": 9.86310373582724e-05, "loss": 0.3985, "step": 32670 }, { "epoch": 7.81, "learning_rate": 9.863020302339921e-05, "loss": 0.3572, "step": 32680 }, { "epoch": 7.81, "learning_rate": 9.862936843788555e-05, "loss": 0.3225, "step": 32690 }, { "epoch": 7.81, "learning_rate": 9.86285336017357e-05, "loss": 0.2853, "step": 32700 }, { "epoch": 7.82, "learning_rate": 9.862769851495401e-05, "loss": 0.4164, "step": 32710 }, { "epoch": 7.82, "learning_rate": 9.862686317754474e-05, "loss": 0.3373, "step": 32720 }, { "epoch": 7.82, "learning_rate": 9.862602758951222e-05, "loss": 0.4223, "step": 32730 }, { "epoch": 7.82, "learning_rate": 9.862519175086074e-05, "loss": 0.3342, "step": 32740 }, { "epoch": 7.82, "learning_rate": 9.862435566159461e-05, "loss": 0.313, "step": 32750 }, { "epoch": 7.83, "learning_rate": 9.862351932171816e-05, "loss": 0.3677, "step": 32760 }, { "epoch": 7.83, "learning_rate": 9.862268273123567e-05, "loss": 0.3789, "step": 32770 }, { "epoch": 7.83, "learning_rate": 9.862184589015148e-05, "loss": 0.3547, "step": 32780 }, { "epoch": 7.83, "learning_rate": 9.862100879846988e-05, "loss": 0.3796, "step": 32790 }, { "epoch": 7.84, "learning_rate": 9.86201714561952e-05, "loss": 0.3551, "step": 32800 }, { "epoch": 7.84, "learning_rate": 9.861933386333174e-05, "loss": 0.339, "step": 32810 }, { "epoch": 7.84, "learning_rate": 9.861849601988383e-05, "loss": 0.3756, "step": 32820 }, { "epoch": 7.84, "learning_rate": 9.86176579258558e-05, "loss": 0.3717, "step": 32830 }, { "epoch": 7.85, "learning_rate": 9.861681958125194e-05, "loss": 0.3611, "step": 32840 }, { "epoch": 7.85, "learning_rate": 9.861598098607658e-05, "loss": 0.3817, "step": 32850 }, { "epoch": 7.85, "learning_rate": 9.861514214033407e-05, "loss": 0.3515, "step": 32860 }, { "epoch": 7.85, "learning_rate": 9.86143030440287e-05, "loss": 0.3425, "step": 32870 }, { "epoch": 7.85, "learning_rate": 9.86134636971648e-05, "loss": 0.3176, "step": 32880 }, { "epoch": 7.86, "learning_rate": 9.861262409974669e-05, "loss": 0.3735, "step": 32890 }, { "epoch": 7.86, "learning_rate": 9.861178425177873e-05, "loss": 0.3465, "step": 32900 }, { "epoch": 7.86, "learning_rate": 9.861094415326523e-05, "loss": 0.3674, "step": 32910 }, { "epoch": 7.86, "learning_rate": 9.861010380421051e-05, "loss": 0.3521, "step": 32920 }, { "epoch": 7.87, "learning_rate": 9.860926320461891e-05, "loss": 0.4332, "step": 32930 }, { "epoch": 7.87, "learning_rate": 9.860842235449475e-05, "loss": 0.3442, "step": 32940 }, { "epoch": 7.87, "learning_rate": 9.86075812538424e-05, "loss": 0.4018, "step": 32950 }, { "epoch": 7.87, "learning_rate": 9.860673990266615e-05, "loss": 0.3604, "step": 32960 }, { "epoch": 7.88, "learning_rate": 9.860589830097036e-05, "loss": 0.3112, "step": 32970 }, { "epoch": 7.88, "learning_rate": 9.860505644875936e-05, "loss": 0.3705, "step": 32980 }, { "epoch": 7.88, "learning_rate": 9.860421434603751e-05, "loss": 0.3266, "step": 32990 }, { "epoch": 7.88, "learning_rate": 9.860337199280912e-05, "loss": 0.3793, "step": 33000 }, { "epoch": 7.88, "learning_rate": 9.860252938907853e-05, "loss": 0.3779, "step": 33010 }, { "epoch": 7.89, "learning_rate": 9.860168653485011e-05, "loss": 0.3424, "step": 33020 }, { "epoch": 7.89, "learning_rate": 9.86008434301282e-05, "loss": 0.3847, "step": 33030 }, { "epoch": 7.89, "learning_rate": 9.860000007491712e-05, "loss": 0.3752, "step": 33040 }, { "epoch": 7.89, "learning_rate": 9.859915646922124e-05, "loss": 0.2857, "step": 33050 }, { "epoch": 7.9, "learning_rate": 9.859831261304491e-05, "loss": 0.3138, "step": 33060 }, { "epoch": 7.9, "learning_rate": 9.859746850639246e-05, "loss": 0.4007, "step": 33070 }, { "epoch": 7.9, "learning_rate": 9.859662414926827e-05, "loss": 0.3098, "step": 33080 }, { "epoch": 7.9, "learning_rate": 9.859577954167665e-05, "loss": 0.3784, "step": 33090 }, { "epoch": 7.9, "learning_rate": 9.8594934683622e-05, "loss": 0.3368, "step": 33100 }, { "epoch": 7.91, "learning_rate": 9.859408957510863e-05, "loss": 0.3448, "step": 33110 }, { "epoch": 7.91, "learning_rate": 9.859324421614092e-05, "loss": 0.3478, "step": 33120 }, { "epoch": 7.91, "learning_rate": 9.859239860672322e-05, "loss": 0.3339, "step": 33130 }, { "epoch": 7.91, "learning_rate": 9.85915527468599e-05, "loss": 0.4707, "step": 33140 }, { "epoch": 7.92, "learning_rate": 9.85907066365553e-05, "loss": 0.3686, "step": 33150 }, { "epoch": 7.92, "learning_rate": 9.85898602758138e-05, "loss": 0.3598, "step": 33160 }, { "epoch": 7.92, "learning_rate": 9.858901366463976e-05, "loss": 0.3246, "step": 33170 }, { "epoch": 7.92, "learning_rate": 9.858816680303753e-05, "loss": 0.3884, "step": 33180 }, { "epoch": 7.93, "learning_rate": 9.85873196910115e-05, "loss": 0.3453, "step": 33190 }, { "epoch": 7.93, "learning_rate": 9.8586472328566e-05, "loss": 0.3168, "step": 33200 }, { "epoch": 7.93, "learning_rate": 9.85856247157054e-05, "loss": 0.3194, "step": 33210 }, { "epoch": 7.93, "learning_rate": 9.85847768524341e-05, "loss": 0.4289, "step": 33220 }, { "epoch": 7.93, "learning_rate": 9.858392873875646e-05, "loss": 0.4298, "step": 33230 }, { "epoch": 7.94, "learning_rate": 9.858308037467685e-05, "loss": 0.361, "step": 33240 }, { "epoch": 7.94, "learning_rate": 9.858223176019961e-05, "loss": 0.3114, "step": 33250 }, { "epoch": 7.94, "learning_rate": 9.858138289532917e-05, "loss": 0.345, "step": 33260 }, { "epoch": 7.94, "learning_rate": 9.858053378006986e-05, "loss": 0.3252, "step": 33270 }, { "epoch": 7.95, "learning_rate": 9.857968441442607e-05, "loss": 0.3796, "step": 33280 }, { "epoch": 7.95, "learning_rate": 9.85788347984022e-05, "loss": 0.3206, "step": 33290 }, { "epoch": 7.95, "learning_rate": 9.85779849320026e-05, "loss": 0.2547, "step": 33300 }, { "epoch": 8.0, "learning_rate": 9.857713481523165e-05, "loss": 0.3515, "step": 33310 }, { "epoch": 8.0, "learning_rate": 9.857628444809375e-05, "loss": 0.2887, "step": 33320 }, { "epoch": 8.01, "learning_rate": 9.857543383059327e-05, "loss": 0.3191, "step": 33330 }, { "epoch": 8.01, "learning_rate": 9.857458296273461e-05, "loss": 0.4409, "step": 33340 }, { "epoch": 8.01, "learning_rate": 9.857373184452212e-05, "loss": 0.2981, "step": 33350 }, { "epoch": 8.01, "learning_rate": 9.857288047596023e-05, "loss": 0.313, "step": 33360 }, { "epoch": 8.02, "learning_rate": 9.85720288570533e-05, "loss": 0.3492, "step": 33370 }, { "epoch": 8.02, "learning_rate": 9.857117698780573e-05, "loss": 0.2865, "step": 33380 }, { "epoch": 8.02, "learning_rate": 9.857032486822191e-05, "loss": 0.402, "step": 33390 }, { "epoch": 8.02, "learning_rate": 9.856947249830624e-05, "loss": 0.3861, "step": 33400 }, { "epoch": 8.02, "learning_rate": 9.856861987806307e-05, "loss": 0.2828, "step": 33410 }, { "epoch": 8.03, "learning_rate": 9.856776700749686e-05, "loss": 0.3148, "step": 33420 }, { "epoch": 8.03, "learning_rate": 9.856691388661195e-05, "loss": 0.4126, "step": 33430 }, { "epoch": 8.03, "learning_rate": 9.856606051541277e-05, "loss": 0.3057, "step": 33440 }, { "epoch": 8.03, "learning_rate": 9.856520689390372e-05, "loss": 0.3542, "step": 33450 }, { "epoch": 8.04, "learning_rate": 9.856435302208917e-05, "loss": 0.3127, "step": 33460 }, { "epoch": 8.04, "learning_rate": 9.856349889997354e-05, "loss": 0.3171, "step": 33470 }, { "epoch": 8.04, "learning_rate": 9.856264452756123e-05, "loss": 0.4164, "step": 33480 }, { "epoch": 8.04, "learning_rate": 9.856178990485665e-05, "loss": 0.411, "step": 33490 }, { "epoch": 8.04, "learning_rate": 9.856093503186421e-05, "loss": 0.3508, "step": 33500 }, { "epoch": 8.05, "learning_rate": 9.856007990858828e-05, "loss": 0.3564, "step": 33510 }, { "epoch": 8.05, "learning_rate": 9.855922453503331e-05, "loss": 0.3472, "step": 33520 }, { "epoch": 8.05, "learning_rate": 9.85583689112037e-05, "loss": 0.362, "step": 33530 }, { "epoch": 8.05, "learning_rate": 9.855751303710383e-05, "loss": 0.3419, "step": 33540 }, { "epoch": 8.06, "learning_rate": 9.855665691273814e-05, "loss": 0.3526, "step": 33550 }, { "epoch": 8.06, "learning_rate": 9.855580053811101e-05, "loss": 0.3392, "step": 33560 }, { "epoch": 8.06, "learning_rate": 9.855494391322692e-05, "loss": 0.3088, "step": 33570 }, { "epoch": 8.06, "learning_rate": 9.855408703809023e-05, "loss": 0.3497, "step": 33580 }, { "epoch": 8.07, "learning_rate": 9.855322991270536e-05, "loss": 0.3328, "step": 33590 }, { "epoch": 8.07, "learning_rate": 9.855237253707674e-05, "loss": 0.2948, "step": 33600 }, { "epoch": 8.07, "learning_rate": 9.855151491120879e-05, "loss": 0.2862, "step": 33610 }, { "epoch": 8.07, "learning_rate": 9.855065703510592e-05, "loss": 0.3363, "step": 33620 }, { "epoch": 8.07, "learning_rate": 9.854979890877256e-05, "loss": 0.3192, "step": 33630 }, { "epoch": 8.08, "learning_rate": 9.854894053221313e-05, "loss": 0.2922, "step": 33640 }, { "epoch": 8.08, "learning_rate": 9.854808190543205e-05, "loss": 0.3148, "step": 33650 }, { "epoch": 8.08, "learning_rate": 9.854722302843376e-05, "loss": 0.3217, "step": 33660 }, { "epoch": 8.08, "learning_rate": 9.854636390122269e-05, "loss": 0.3416, "step": 33670 }, { "epoch": 8.09, "learning_rate": 9.854550452380323e-05, "loss": 0.3232, "step": 33680 }, { "epoch": 8.09, "learning_rate": 9.854464489617984e-05, "loss": 0.2927, "step": 33690 }, { "epoch": 8.09, "learning_rate": 9.854378501835695e-05, "loss": 0.3014, "step": 33700 }, { "epoch": 8.09, "learning_rate": 9.854292489033898e-05, "loss": 0.3178, "step": 33710 }, { "epoch": 8.1, "learning_rate": 9.854206451213037e-05, "loss": 0.3346, "step": 33720 }, { "epoch": 8.1, "learning_rate": 9.854120388373555e-05, "loss": 0.2854, "step": 33730 }, { "epoch": 8.1, "learning_rate": 9.854034300515897e-05, "loss": 0.2672, "step": 33740 }, { "epoch": 8.1, "learning_rate": 9.853948187640504e-05, "loss": 0.3336, "step": 33750 }, { "epoch": 8.1, "learning_rate": 9.853862049747824e-05, "loss": 0.3782, "step": 33760 }, { "epoch": 8.11, "learning_rate": 9.853775886838296e-05, "loss": 0.3259, "step": 33770 }, { "epoch": 8.11, "learning_rate": 9.853689698912369e-05, "loss": 0.2906, "step": 33780 }, { "epoch": 8.11, "learning_rate": 9.853603485970484e-05, "loss": 0.4166, "step": 33790 }, { "epoch": 8.11, "learning_rate": 9.853517248013085e-05, "loss": 0.3471, "step": 33800 }, { "epoch": 8.12, "learning_rate": 9.853430985040617e-05, "loss": 0.2913, "step": 33810 }, { "epoch": 8.12, "learning_rate": 9.853344697053526e-05, "loss": 0.3305, "step": 33820 }, { "epoch": 8.12, "learning_rate": 9.853258384052256e-05, "loss": 0.4118, "step": 33830 }, { "epoch": 8.12, "learning_rate": 9.853172046037251e-05, "loss": 0.342, "step": 33840 }, { "epoch": 8.12, "learning_rate": 9.853085683008958e-05, "loss": 0.3103, "step": 33850 }, { "epoch": 8.13, "learning_rate": 9.85299929496782e-05, "loss": 0.3402, "step": 33860 }, { "epoch": 8.13, "learning_rate": 9.852912881914283e-05, "loss": 0.2882, "step": 33870 }, { "epoch": 8.13, "learning_rate": 9.852826443848793e-05, "loss": 0.3065, "step": 33880 }, { "epoch": 8.13, "learning_rate": 9.852739980771795e-05, "loss": 0.3325, "step": 33890 }, { "epoch": 8.14, "learning_rate": 9.852653492683735e-05, "loss": 0.4073, "step": 33900 }, { "epoch": 8.14, "learning_rate": 9.852566979585056e-05, "loss": 0.3636, "step": 33910 }, { "epoch": 8.14, "learning_rate": 9.852480441476209e-05, "loss": 0.2957, "step": 33920 }, { "epoch": 8.14, "learning_rate": 9.852393878357635e-05, "loss": 0.2847, "step": 33930 }, { "epoch": 8.15, "learning_rate": 9.852307290229782e-05, "loss": 0.3449, "step": 33940 }, { "epoch": 8.15, "learning_rate": 9.8522206770931e-05, "loss": 0.2996, "step": 33950 }, { "epoch": 8.15, "learning_rate": 9.85213403894803e-05, "loss": 0.3787, "step": 33960 }, { "epoch": 8.15, "learning_rate": 9.85204737579502e-05, "loss": 0.3381, "step": 33970 }, { "epoch": 8.15, "learning_rate": 9.851960687634518e-05, "loss": 0.3297, "step": 33980 }, { "epoch": 8.16, "learning_rate": 9.85187397446697e-05, "loss": 0.3016, "step": 33990 }, { "epoch": 8.16, "learning_rate": 9.851787236292824e-05, "loss": 0.3444, "step": 34000 }, { "epoch": 8.16, "learning_rate": 9.851700473112525e-05, "loss": 0.3382, "step": 34010 }, { "epoch": 8.16, "learning_rate": 9.851613684926521e-05, "loss": 0.297, "step": 34020 }, { "epoch": 8.17, "learning_rate": 9.85152687173526e-05, "loss": 0.2775, "step": 34030 }, { "epoch": 8.17, "learning_rate": 9.851440033539187e-05, "loss": 0.352, "step": 34040 }, { "epoch": 8.17, "learning_rate": 9.851353170338755e-05, "loss": 0.3209, "step": 34050 }, { "epoch": 8.17, "learning_rate": 9.851266282134406e-05, "loss": 0.3493, "step": 34060 }, { "epoch": 8.18, "learning_rate": 9.851179368926591e-05, "loss": 0.306, "step": 34070 }, { "epoch": 8.18, "learning_rate": 9.851092430715756e-05, "loss": 0.3094, "step": 34080 }, { "epoch": 8.18, "learning_rate": 9.85100546750235e-05, "loss": 0.2897, "step": 34090 }, { "epoch": 8.18, "learning_rate": 9.850918479286822e-05, "loss": 0.3083, "step": 34100 }, { "epoch": 8.18, "learning_rate": 9.85083146606962e-05, "loss": 0.3017, "step": 34110 }, { "epoch": 8.19, "learning_rate": 9.850744427851191e-05, "loss": 0.3403, "step": 34120 }, { "epoch": 8.19, "learning_rate": 9.850657364631985e-05, "loss": 0.268, "step": 34130 }, { "epoch": 8.19, "learning_rate": 9.850570276412452e-05, "loss": 0.3568, "step": 34140 }, { "epoch": 8.19, "learning_rate": 9.850483163193036e-05, "loss": 0.3002, "step": 34150 }, { "epoch": 8.2, "learning_rate": 9.85039602497419e-05, "loss": 0.2822, "step": 34160 }, { "epoch": 8.2, "learning_rate": 9.850308861756366e-05, "loss": 0.3461, "step": 34170 }, { "epoch": 8.2, "learning_rate": 9.850221673540007e-05, "loss": 0.378, "step": 34180 }, { "epoch": 8.2, "learning_rate": 9.850134460325564e-05, "loss": 0.3261, "step": 34190 }, { "epoch": 8.2, "learning_rate": 9.850047222113488e-05, "loss": 0.2584, "step": 34200 }, { "epoch": 8.21, "learning_rate": 9.84995995890423e-05, "loss": 0.259, "step": 34210 }, { "epoch": 8.21, "learning_rate": 9.849872670698234e-05, "loss": 0.3594, "step": 34220 }, { "epoch": 8.21, "learning_rate": 9.849785357495958e-05, "loss": 0.2648, "step": 34230 }, { "epoch": 8.21, "learning_rate": 9.849698019297845e-05, "loss": 0.3307, "step": 34240 }, { "epoch": 8.22, "learning_rate": 9.849610656104349e-05, "loss": 0.3681, "step": 34250 }, { "epoch": 8.22, "learning_rate": 9.849523267915918e-05, "loss": 0.3745, "step": 34260 }, { "epoch": 8.22, "learning_rate": 9.849435854733005e-05, "loss": 0.3336, "step": 34270 }, { "epoch": 8.22, "learning_rate": 9.849348416556058e-05, "loss": 0.2145, "step": 34280 }, { "epoch": 8.23, "learning_rate": 9.849260953385528e-05, "loss": 0.2779, "step": 34290 }, { "epoch": 8.23, "learning_rate": 9.849173465221869e-05, "loss": 0.3266, "step": 34300 }, { "epoch": 8.23, "learning_rate": 9.849085952065528e-05, "loss": 0.305, "step": 34310 }, { "epoch": 8.23, "learning_rate": 9.848998413916957e-05, "loss": 0.3079, "step": 34320 }, { "epoch": 8.23, "learning_rate": 9.848910850776608e-05, "loss": 0.3588, "step": 34330 }, { "epoch": 8.24, "learning_rate": 9.848823262644932e-05, "loss": 0.2997, "step": 34340 }, { "epoch": 8.24, "learning_rate": 9.84873564952238e-05, "loss": 0.2987, "step": 34350 }, { "epoch": 8.24, "learning_rate": 9.848648011409405e-05, "loss": 0.2773, "step": 34360 }, { "epoch": 8.24, "learning_rate": 9.848560348306458e-05, "loss": 0.2743, "step": 34370 }, { "epoch": 8.25, "learning_rate": 9.848472660213989e-05, "loss": 0.2877, "step": 34380 }, { "epoch": 8.25, "learning_rate": 9.848384947132451e-05, "loss": 0.3409, "step": 34390 }, { "epoch": 8.25, "learning_rate": 9.848297209062299e-05, "loss": 0.341, "step": 34400 }, { "epoch": 8.25, "learning_rate": 9.84820944600398e-05, "loss": 0.2931, "step": 34410 }, { "epoch": 8.26, "learning_rate": 9.848121657957949e-05, "loss": 0.2538, "step": 34420 }, { "epoch": 8.26, "learning_rate": 9.848033844924661e-05, "loss": 0.2891, "step": 34430 }, { "epoch": 8.26, "learning_rate": 9.847946006904564e-05, "loss": 0.2978, "step": 34440 }, { "epoch": 8.26, "learning_rate": 9.847858143898112e-05, "loss": 0.2623, "step": 34450 }, { "epoch": 8.26, "learning_rate": 9.84777025590576e-05, "loss": 0.3473, "step": 34460 }, { "epoch": 8.27, "learning_rate": 9.847682342927959e-05, "loss": 0.2595, "step": 34470 }, { "epoch": 8.27, "learning_rate": 9.847594404965164e-05, "loss": 0.2347, "step": 34480 }, { "epoch": 8.27, "learning_rate": 9.847506442017827e-05, "loss": 0.2556, "step": 34490 }, { "epoch": 8.27, "learning_rate": 9.847418454086399e-05, "loss": 0.2736, "step": 34500 }, { "epoch": 8.28, "learning_rate": 9.847330441171337e-05, "loss": 0.3373, "step": 34510 }, { "epoch": 8.28, "learning_rate": 9.847242403273094e-05, "loss": 0.3347, "step": 34520 }, { "epoch": 8.28, "learning_rate": 9.847154340392121e-05, "loss": 0.2948, "step": 34530 }, { "epoch": 8.28, "learning_rate": 9.847066252528876e-05, "loss": 0.2831, "step": 34540 }, { "epoch": 8.28, "learning_rate": 9.846978139683811e-05, "loss": 0.2947, "step": 34550 }, { "epoch": 8.29, "learning_rate": 9.846890001857381e-05, "loss": 0.2444, "step": 34560 }, { "epoch": 8.29, "learning_rate": 9.846801839050037e-05, "loss": 0.3005, "step": 34570 }, { "epoch": 8.29, "learning_rate": 9.846713651262238e-05, "loss": 0.2601, "step": 34580 }, { "epoch": 8.29, "learning_rate": 9.846625438494435e-05, "loss": 0.347, "step": 34590 }, { "epoch": 8.3, "learning_rate": 9.846537200747083e-05, "loss": 0.2322, "step": 34600 }, { "epoch": 8.3, "learning_rate": 9.84644893802064e-05, "loss": 0.2614, "step": 34610 }, { "epoch": 8.3, "learning_rate": 9.846360650315558e-05, "loss": 0.2889, "step": 34620 }, { "epoch": 8.3, "learning_rate": 9.846272337632292e-05, "loss": 0.3268, "step": 34630 }, { "epoch": 8.31, "learning_rate": 9.846183999971298e-05, "loss": 0.2901, "step": 34640 }, { "epoch": 8.31, "learning_rate": 9.846095637333032e-05, "loss": 0.2721, "step": 34650 }, { "epoch": 8.31, "learning_rate": 9.846007249717947e-05, "loss": 0.2549, "step": 34660 }, { "epoch": 8.31, "learning_rate": 9.845918837126503e-05, "loss": 0.2826, "step": 34670 }, { "epoch": 8.31, "learning_rate": 9.845830399559149e-05, "loss": 0.3155, "step": 34680 }, { "epoch": 8.32, "learning_rate": 9.845741937016346e-05, "loss": 0.2309, "step": 34690 }, { "epoch": 8.32, "learning_rate": 9.84565344949855e-05, "loss": 0.2461, "step": 34700 }, { "epoch": 8.32, "learning_rate": 9.845564937006215e-05, "loss": 0.3428, "step": 34710 }, { "epoch": 8.32, "learning_rate": 9.845476399539797e-05, "loss": 0.3354, "step": 34720 }, { "epoch": 8.33, "learning_rate": 9.845387837099753e-05, "loss": 0.295, "step": 34730 }, { "epoch": 8.33, "learning_rate": 9.845299249686541e-05, "loss": 0.3248, "step": 34740 }, { "epoch": 8.33, "learning_rate": 9.845210637300615e-05, "loss": 0.3589, "step": 34750 }, { "epoch": 8.33, "learning_rate": 9.845121999942434e-05, "loss": 0.2816, "step": 34760 }, { "epoch": 8.34, "learning_rate": 9.845033337612452e-05, "loss": 0.3329, "step": 34770 }, { "epoch": 8.34, "learning_rate": 9.844944650311129e-05, "loss": 0.3144, "step": 34780 }, { "epoch": 8.34, "learning_rate": 9.844855938038922e-05, "loss": 0.3362, "step": 34790 }, { "epoch": 8.34, "learning_rate": 9.844767200796284e-05, "loss": 0.3175, "step": 34800 }, { "epoch": 8.34, "learning_rate": 9.844678438583677e-05, "loss": 0.3145, "step": 34810 }, { "epoch": 8.35, "learning_rate": 9.844589651401557e-05, "loss": 0.3318, "step": 34820 }, { "epoch": 8.35, "learning_rate": 9.844500839250381e-05, "loss": 0.2996, "step": 34830 }, { "epoch": 8.35, "learning_rate": 9.844412002130608e-05, "loss": 0.3552, "step": 34840 }, { "epoch": 8.35, "learning_rate": 9.844323140042693e-05, "loss": 0.3833, "step": 34850 }, { "epoch": 8.36, "learning_rate": 9.844234252987097e-05, "loss": 0.2954, "step": 34860 }, { "epoch": 8.36, "learning_rate": 9.844145340964279e-05, "loss": 0.3933, "step": 34870 }, { "epoch": 8.36, "learning_rate": 9.844056403974693e-05, "loss": 0.2632, "step": 34880 }, { "epoch": 8.36, "learning_rate": 9.8439674420188e-05, "loss": 0.3031, "step": 34890 }, { "epoch": 8.36, "learning_rate": 9.84387845509706e-05, "loss": 0.2751, "step": 34900 }, { "epoch": 8.37, "learning_rate": 9.843789443209929e-05, "loss": 0.2892, "step": 34910 }, { "epoch": 8.37, "learning_rate": 9.843700406357866e-05, "loss": 0.2658, "step": 34920 }, { "epoch": 8.37, "learning_rate": 9.843611344541332e-05, "loss": 0.357, "step": 34930 }, { "epoch": 8.37, "learning_rate": 9.843522257760785e-05, "loss": 0.2984, "step": 34940 }, { "epoch": 8.38, "learning_rate": 9.843433146016682e-05, "loss": 0.2552, "step": 34950 }, { "epoch": 8.38, "learning_rate": 9.843344009309484e-05, "loss": 0.2837, "step": 34960 }, { "epoch": 8.38, "learning_rate": 9.843254847639651e-05, "loss": 0.2792, "step": 34970 }, { "epoch": 8.38, "learning_rate": 9.843165661007643e-05, "loss": 0.2805, "step": 34980 }, { "epoch": 8.39, "learning_rate": 9.843076449413918e-05, "loss": 0.2993, "step": 34990 }, { "epoch": 8.39, "learning_rate": 9.842987212858936e-05, "loss": 0.3263, "step": 35000 }, { "epoch": 8.39, "learning_rate": 9.84289795134316e-05, "loss": 0.3228, "step": 35010 }, { "epoch": 8.39, "learning_rate": 9.842808664867044e-05, "loss": 0.2815, "step": 35020 }, { "epoch": 8.39, "learning_rate": 9.842719353431054e-05, "loss": 0.3, "step": 35030 }, { "epoch": 8.4, "learning_rate": 9.842630017035646e-05, "loss": 0.2831, "step": 35040 }, { "epoch": 8.4, "learning_rate": 9.842540655681285e-05, "loss": 0.2756, "step": 35050 }, { "epoch": 8.4, "learning_rate": 9.842451269368426e-05, "loss": 0.3341, "step": 35060 }, { "epoch": 8.4, "learning_rate": 9.842361858097536e-05, "loss": 0.2911, "step": 35070 }, { "epoch": 8.41, "learning_rate": 9.84227242186907e-05, "loss": 0.245, "step": 35080 }, { "epoch": 8.41, "learning_rate": 9.842182960683491e-05, "loss": 0.3324, "step": 35090 }, { "epoch": 8.41, "learning_rate": 9.842093474541263e-05, "loss": 0.2637, "step": 35100 }, { "epoch": 8.41, "learning_rate": 9.842003963442843e-05, "loss": 0.2578, "step": 35110 }, { "epoch": 8.41, "learning_rate": 9.841914427388694e-05, "loss": 0.2826, "step": 35120 }, { "epoch": 8.42, "learning_rate": 9.84182486637928e-05, "loss": 0.2761, "step": 35130 }, { "epoch": 8.42, "learning_rate": 9.841735280415056e-05, "loss": 0.3162, "step": 35140 }, { "epoch": 8.42, "learning_rate": 9.841645669496491e-05, "loss": 0.2607, "step": 35150 }, { "epoch": 8.42, "learning_rate": 9.841556033624043e-05, "loss": 0.2929, "step": 35160 }, { "epoch": 8.43, "learning_rate": 9.841466372798175e-05, "loss": 0.2103, "step": 35170 }, { "epoch": 8.43, "learning_rate": 9.841376687019348e-05, "loss": 0.2717, "step": 35180 }, { "epoch": 8.43, "learning_rate": 9.841286976288027e-05, "loss": 0.3012, "step": 35190 }, { "epoch": 8.43, "learning_rate": 9.841197240604669e-05, "loss": 0.2121, "step": 35200 }, { "epoch": 8.44, "learning_rate": 9.841107479969742e-05, "loss": 0.2958, "step": 35210 }, { "epoch": 8.44, "learning_rate": 9.841017694383708e-05, "loss": 0.2698, "step": 35220 }, { "epoch": 8.44, "learning_rate": 9.840927883847027e-05, "loss": 0.2719, "step": 35230 }, { "epoch": 8.44, "learning_rate": 9.840838048360163e-05, "loss": 0.248, "step": 35240 }, { "epoch": 8.44, "learning_rate": 9.840748187923578e-05, "loss": 0.2692, "step": 35250 }, { "epoch": 8.45, "learning_rate": 9.84065830253774e-05, "loss": 0.3349, "step": 35260 }, { "epoch": 8.45, "learning_rate": 9.840568392203106e-05, "loss": 0.2371, "step": 35270 }, { "epoch": 8.45, "learning_rate": 9.840478456920141e-05, "loss": 0.3086, "step": 35280 }, { "epoch": 8.45, "learning_rate": 9.840388496689313e-05, "loss": 0.4322, "step": 35290 }, { "epoch": 8.46, "learning_rate": 9.84029851151108e-05, "loss": 0.3096, "step": 35300 }, { "epoch": 8.46, "learning_rate": 9.840208501385908e-05, "loss": 0.2585, "step": 35310 }, { "epoch": 8.46, "learning_rate": 9.840118466314261e-05, "loss": 0.3538, "step": 35320 }, { "epoch": 8.46, "learning_rate": 9.840028406296603e-05, "loss": 0.2992, "step": 35330 }, { "epoch": 8.47, "learning_rate": 9.839938321333398e-05, "loss": 0.2751, "step": 35340 }, { "epoch": 8.47, "learning_rate": 9.839848211425111e-05, "loss": 0.215, "step": 35350 }, { "epoch": 8.47, "learning_rate": 9.839758076572205e-05, "loss": 0.265, "step": 35360 }, { "epoch": 8.47, "learning_rate": 9.839667916775146e-05, "loss": 0.264, "step": 35370 }, { "epoch": 8.47, "learning_rate": 9.839577732034399e-05, "loss": 0.2566, "step": 35380 }, { "epoch": 8.48, "learning_rate": 9.839487522350427e-05, "loss": 0.3138, "step": 35390 }, { "epoch": 8.48, "learning_rate": 9.839397287723695e-05, "loss": 0.3121, "step": 35400 }, { "epoch": 8.48, "learning_rate": 9.83930702815467e-05, "loss": 0.2787, "step": 35410 }, { "epoch": 8.48, "learning_rate": 9.839216743643817e-05, "loss": 0.351, "step": 35420 }, { "epoch": 8.49, "learning_rate": 9.839126434191599e-05, "loss": 0.3719, "step": 35430 }, { "epoch": 8.49, "learning_rate": 9.839036099798483e-05, "loss": 0.2816, "step": 35440 }, { "epoch": 8.49, "learning_rate": 9.838945740464935e-05, "loss": 0.2936, "step": 35450 }, { "epoch": 8.49, "learning_rate": 9.838855356191421e-05, "loss": 0.287, "step": 35460 }, { "epoch": 8.49, "learning_rate": 9.838764946978404e-05, "loss": 0.4083, "step": 35470 }, { "epoch": 8.5, "learning_rate": 9.838674512826354e-05, "loss": 0.346, "step": 35480 }, { "epoch": 8.5, "learning_rate": 9.838584053735733e-05, "loss": 0.2841, "step": 35490 }, { "epoch": 8.5, "learning_rate": 9.838493569707012e-05, "loss": 0.2614, "step": 35500 }, { "epoch": 8.5, "learning_rate": 9.838403060740653e-05, "loss": 0.2686, "step": 35510 }, { "epoch": 8.51, "learning_rate": 9.838312526837123e-05, "loss": 0.3893, "step": 35520 }, { "epoch": 8.51, "learning_rate": 9.838221967996893e-05, "loss": 0.3079, "step": 35530 }, { "epoch": 8.51, "learning_rate": 9.838131384220424e-05, "loss": 0.316, "step": 35540 }, { "epoch": 8.51, "learning_rate": 9.838040775508186e-05, "loss": 0.2551, "step": 35550 }, { "epoch": 8.52, "learning_rate": 9.837950141860645e-05, "loss": 0.2522, "step": 35560 }, { "epoch": 8.52, "learning_rate": 9.837859483278269e-05, "loss": 0.3126, "step": 35570 }, { "epoch": 8.52, "learning_rate": 9.837768799761527e-05, "loss": 0.2689, "step": 35580 }, { "epoch": 8.52, "learning_rate": 9.83767809131088e-05, "loss": 0.2873, "step": 35590 }, { "epoch": 8.52, "learning_rate": 9.837587357926803e-05, "loss": 0.3656, "step": 35600 }, { "epoch": 8.53, "learning_rate": 9.83749659960976e-05, "loss": 0.3028, "step": 35610 }, { "epoch": 8.53, "learning_rate": 9.837405816360217e-05, "loss": 0.3146, "step": 35620 }, { "epoch": 8.53, "learning_rate": 9.837315008178645e-05, "loss": 0.4017, "step": 35630 }, { "epoch": 8.53, "learning_rate": 9.837224175065511e-05, "loss": 0.3528, "step": 35640 }, { "epoch": 8.54, "learning_rate": 9.837133317021284e-05, "loss": 0.405, "step": 35650 }, { "epoch": 8.54, "learning_rate": 9.83704243404643e-05, "loss": 0.3361, "step": 35660 }, { "epoch": 8.54, "learning_rate": 9.83695152614142e-05, "loss": 0.4128, "step": 35670 }, { "epoch": 8.54, "learning_rate": 9.836860593306721e-05, "loss": 0.4572, "step": 35680 }, { "epoch": 8.55, "learning_rate": 9.836769635542802e-05, "loss": 0.3986, "step": 35690 }, { "epoch": 8.55, "learning_rate": 9.836678652850132e-05, "loss": 0.3465, "step": 35700 }, { "epoch": 8.55, "learning_rate": 9.836587645229179e-05, "loss": 0.375, "step": 35710 }, { "epoch": 8.55, "learning_rate": 9.836496612680415e-05, "loss": 0.4159, "step": 35720 }, { "epoch": 8.55, "learning_rate": 9.836405555204305e-05, "loss": 0.3937, "step": 35730 }, { "epoch": 8.56, "learning_rate": 9.83631447280132e-05, "loss": 0.408, "step": 35740 }, { "epoch": 8.56, "learning_rate": 9.836223365471932e-05, "loss": 0.4105, "step": 35750 }, { "epoch": 8.56, "learning_rate": 9.836132233216606e-05, "loss": 0.3662, "step": 35760 }, { "epoch": 8.56, "learning_rate": 9.836041076035815e-05, "loss": 0.4244, "step": 35770 }, { "epoch": 8.57, "learning_rate": 9.835949893930029e-05, "loss": 0.3529, "step": 35780 }, { "epoch": 8.57, "learning_rate": 9.835858686899716e-05, "loss": 0.4935, "step": 35790 }, { "epoch": 8.57, "learning_rate": 9.835767454945347e-05, "loss": 0.408, "step": 35800 }, { "epoch": 8.57, "learning_rate": 9.835676198067392e-05, "loss": 0.3551, "step": 35810 }, { "epoch": 8.57, "learning_rate": 9.83558491626632e-05, "loss": 0.3472, "step": 35820 }, { "epoch": 8.58, "learning_rate": 9.835493609542606e-05, "loss": 0.3847, "step": 35830 }, { "epoch": 8.58, "learning_rate": 9.835402277896715e-05, "loss": 0.4242, "step": 35840 }, { "epoch": 8.58, "learning_rate": 9.835310921329121e-05, "loss": 0.3421, "step": 35850 }, { "epoch": 8.58, "learning_rate": 9.835219539840295e-05, "loss": 0.4002, "step": 35860 }, { "epoch": 8.59, "learning_rate": 9.835128133430705e-05, "loss": 0.4427, "step": 35870 }, { "epoch": 8.59, "learning_rate": 9.835036702100826e-05, "loss": 0.333, "step": 35880 }, { "epoch": 8.59, "learning_rate": 9.834945245851125e-05, "loss": 0.4375, "step": 35890 }, { "epoch": 8.59, "learning_rate": 9.83485376468208e-05, "loss": 0.3621, "step": 35900 }, { "epoch": 8.6, "learning_rate": 9.834762258594154e-05, "loss": 0.3797, "step": 35910 }, { "epoch": 8.6, "learning_rate": 9.834670727587826e-05, "loss": 0.3674, "step": 35920 }, { "epoch": 8.6, "learning_rate": 9.834579171663563e-05, "loss": 0.3906, "step": 35930 }, { "epoch": 8.6, "learning_rate": 9.83448759082184e-05, "loss": 0.4245, "step": 35940 }, { "epoch": 8.6, "learning_rate": 9.834395985063125e-05, "loss": 0.4965, "step": 35950 }, { "epoch": 8.61, "learning_rate": 9.834304354387896e-05, "loss": 0.3625, "step": 35960 }, { "epoch": 8.61, "learning_rate": 9.834212698796619e-05, "loss": 0.3998, "step": 35970 }, { "epoch": 8.61, "learning_rate": 9.83412101828977e-05, "loss": 0.3864, "step": 35980 }, { "epoch": 8.61, "learning_rate": 9.834029312867821e-05, "loss": 0.4196, "step": 35990 }, { "epoch": 8.62, "learning_rate": 9.833937582531245e-05, "loss": 0.3523, "step": 36000 }, { "epoch": 8.62, "learning_rate": 9.833845827280514e-05, "loss": 0.3652, "step": 36010 }, { "epoch": 8.62, "learning_rate": 9.833754047116102e-05, "loss": 0.3411, "step": 36020 }, { "epoch": 8.62, "learning_rate": 9.833662242038482e-05, "loss": 0.3133, "step": 36030 }, { "epoch": 8.63, "learning_rate": 9.833570412048124e-05, "loss": 0.3284, "step": 36040 }, { "epoch": 8.63, "learning_rate": 9.833478557145505e-05, "loss": 0.4008, "step": 36050 }, { "epoch": 8.63, "learning_rate": 9.833386677331097e-05, "loss": 0.3767, "step": 36060 }, { "epoch": 8.63, "learning_rate": 9.833294772605373e-05, "loss": 0.3802, "step": 36070 }, { "epoch": 8.63, "learning_rate": 9.833202842968807e-05, "loss": 0.3378, "step": 36080 }, { "epoch": 8.64, "learning_rate": 9.833110888421874e-05, "loss": 0.3546, "step": 36090 }, { "epoch": 8.64, "learning_rate": 9.833018908965049e-05, "loss": 0.4264, "step": 36100 }, { "epoch": 8.64, "learning_rate": 9.8329269045988e-05, "loss": 0.4144, "step": 36110 }, { "epoch": 8.64, "learning_rate": 9.832834875323609e-05, "loss": 0.3358, "step": 36120 }, { "epoch": 8.65, "learning_rate": 9.832742821139944e-05, "loss": 0.3792, "step": 36130 }, { "epoch": 8.65, "learning_rate": 9.832650742048284e-05, "loss": 0.4001, "step": 36140 }, { "epoch": 8.65, "learning_rate": 9.8325586380491e-05, "loss": 0.3832, "step": 36150 }, { "epoch": 8.65, "learning_rate": 9.83246650914287e-05, "loss": 0.3193, "step": 36160 }, { "epoch": 8.65, "learning_rate": 9.832374355330068e-05, "loss": 0.406, "step": 36170 }, { "epoch": 8.66, "learning_rate": 9.832282176611166e-05, "loss": 0.4109, "step": 36180 }, { "epoch": 8.66, "learning_rate": 9.832189972986641e-05, "loss": 0.338, "step": 36190 }, { "epoch": 8.66, "learning_rate": 9.832097744456971e-05, "loss": 0.3906, "step": 36200 }, { "epoch": 8.66, "learning_rate": 9.832005491022626e-05, "loss": 0.3568, "step": 36210 }, { "epoch": 8.67, "learning_rate": 9.831913212684087e-05, "loss": 0.3858, "step": 36220 }, { "epoch": 8.67, "learning_rate": 9.831820909441824e-05, "loss": 0.3516, "step": 36230 }, { "epoch": 8.67, "learning_rate": 9.831728581296318e-05, "loss": 0.2947, "step": 36240 }, { "epoch": 8.67, "learning_rate": 9.831636228248042e-05, "loss": 0.3485, "step": 36250 }, { "epoch": 8.68, "learning_rate": 9.831543850297472e-05, "loss": 0.3566, "step": 36260 }, { "epoch": 8.68, "learning_rate": 9.831451447445086e-05, "loss": 0.3894, "step": 36270 }, { "epoch": 8.68, "learning_rate": 9.831359019691358e-05, "loss": 0.3425, "step": 36280 }, { "epoch": 8.68, "learning_rate": 9.831266567036763e-05, "loss": 0.3416, "step": 36290 }, { "epoch": 8.68, "learning_rate": 9.831174089481783e-05, "loss": 0.4506, "step": 36300 }, { "epoch": 8.69, "learning_rate": 9.831081587026889e-05, "loss": 0.4024, "step": 36310 }, { "epoch": 8.69, "learning_rate": 9.830989059672562e-05, "loss": 0.3686, "step": 36320 }, { "epoch": 8.69, "learning_rate": 9.830896507419276e-05, "loss": 0.2935, "step": 36330 }, { "epoch": 8.69, "learning_rate": 9.83080393026751e-05, "loss": 0.3195, "step": 36340 }, { "epoch": 8.7, "learning_rate": 9.830711328217739e-05, "loss": 0.3685, "step": 36350 }, { "epoch": 8.7, "learning_rate": 9.830618701270441e-05, "loss": 0.2918, "step": 36360 }, { "epoch": 8.7, "learning_rate": 9.830526049426094e-05, "loss": 0.3769, "step": 36370 }, { "epoch": 8.7, "learning_rate": 9.830433372685178e-05, "loss": 0.3445, "step": 36380 }, { "epoch": 8.71, "learning_rate": 9.830340671048164e-05, "loss": 0.3431, "step": 36390 }, { "epoch": 8.71, "learning_rate": 9.830247944515537e-05, "loss": 0.3616, "step": 36400 }, { "epoch": 8.71, "learning_rate": 9.83015519308777e-05, "loss": 0.3572, "step": 36410 }, { "epoch": 8.71, "learning_rate": 9.830062416765344e-05, "loss": 0.3406, "step": 36420 }, { "epoch": 8.71, "learning_rate": 9.829969615548734e-05, "loss": 0.3325, "step": 36430 }, { "epoch": 8.72, "learning_rate": 9.829876789438421e-05, "loss": 0.3625, "step": 36440 }, { "epoch": 8.72, "learning_rate": 9.829783938434885e-05, "loss": 0.315, "step": 36450 }, { "epoch": 8.72, "learning_rate": 9.829691062538599e-05, "loss": 0.3685, "step": 36460 }, { "epoch": 8.72, "learning_rate": 9.829598161750047e-05, "loss": 0.4624, "step": 36470 }, { "epoch": 8.73, "learning_rate": 9.829505236069704e-05, "loss": 0.3314, "step": 36480 }, { "epoch": 8.73, "learning_rate": 9.829412285498052e-05, "loss": 0.2988, "step": 36490 }, { "epoch": 8.73, "learning_rate": 9.829319310035567e-05, "loss": 0.3895, "step": 36500 }, { "epoch": 8.73, "learning_rate": 9.829226309682732e-05, "loss": 0.3798, "step": 36510 }, { "epoch": 8.73, "learning_rate": 9.829133284440025e-05, "loss": 0.279, "step": 36520 }, { "epoch": 8.74, "learning_rate": 9.829040234307922e-05, "loss": 0.3359, "step": 36530 }, { "epoch": 8.74, "learning_rate": 9.828947159286905e-05, "loss": 0.4283, "step": 36540 }, { "epoch": 8.74, "learning_rate": 9.828854059377457e-05, "loss": 0.418, "step": 36550 }, { "epoch": 8.74, "learning_rate": 9.828760934580052e-05, "loss": 0.304, "step": 36560 }, { "epoch": 8.75, "learning_rate": 9.828667784895173e-05, "loss": 0.398, "step": 36570 }, { "epoch": 8.75, "learning_rate": 9.828574610323303e-05, "loss": 0.2907, "step": 36580 }, { "epoch": 8.75, "learning_rate": 9.828481410864916e-05, "loss": 0.3614, "step": 36590 }, { "epoch": 8.75, "learning_rate": 9.828388186520496e-05, "loss": 0.3916, "step": 36600 }, { "epoch": 8.76, "learning_rate": 9.828294937290523e-05, "loss": 0.4129, "step": 36610 }, { "epoch": 8.76, "learning_rate": 9.828201663175478e-05, "loss": 0.3715, "step": 36620 }, { "epoch": 8.76, "learning_rate": 9.828108364175841e-05, "loss": 0.3534, "step": 36630 }, { "epoch": 8.76, "learning_rate": 9.828015040292094e-05, "loss": 0.302, "step": 36640 }, { "epoch": 8.76, "learning_rate": 9.827921691524716e-05, "loss": 0.3407, "step": 36650 }, { "epoch": 8.77, "learning_rate": 9.82782831787419e-05, "loss": 0.3161, "step": 36660 }, { "epoch": 8.77, "learning_rate": 9.827734919340997e-05, "loss": 0.2681, "step": 36670 }, { "epoch": 8.77, "learning_rate": 9.827641495925616e-05, "loss": 0.2588, "step": 36680 }, { "epoch": 8.77, "learning_rate": 9.827548047628531e-05, "loss": 0.2845, "step": 36690 }, { "epoch": 8.78, "learning_rate": 9.827454574450223e-05, "loss": 0.392, "step": 36700 }, { "epoch": 8.78, "learning_rate": 9.827361076391175e-05, "loss": 0.2468, "step": 36710 }, { "epoch": 8.78, "learning_rate": 9.827267553451866e-05, "loss": 0.3472, "step": 36720 }, { "epoch": 8.78, "learning_rate": 9.82717400563278e-05, "loss": 0.3366, "step": 36730 }, { "epoch": 8.79, "learning_rate": 9.827080432934399e-05, "loss": 0.3412, "step": 36740 }, { "epoch": 8.79, "learning_rate": 9.826986835357206e-05, "loss": 0.254, "step": 36750 }, { "epoch": 8.79, "learning_rate": 9.826893212901682e-05, "loss": 0.3272, "step": 36760 }, { "epoch": 8.79, "learning_rate": 9.82679956556831e-05, "loss": 0.4308, "step": 36770 }, { "epoch": 8.79, "learning_rate": 9.826705893357572e-05, "loss": 0.3393, "step": 36780 }, { "epoch": 8.8, "learning_rate": 9.826612196269953e-05, "loss": 0.3609, "step": 36790 }, { "epoch": 8.8, "learning_rate": 9.826518474305932e-05, "loss": 0.3159, "step": 36800 }, { "epoch": 8.8, "learning_rate": 9.826424727465997e-05, "loss": 0.2741, "step": 36810 }, { "epoch": 8.8, "learning_rate": 9.826330955750627e-05, "loss": 0.3255, "step": 36820 }, { "epoch": 8.81, "learning_rate": 9.826237159160307e-05, "loss": 0.3239, "step": 36830 }, { "epoch": 8.81, "learning_rate": 9.826143337695521e-05, "loss": 0.2601, "step": 36840 }, { "epoch": 8.81, "learning_rate": 9.826049491356752e-05, "loss": 0.3239, "step": 36850 }, { "epoch": 8.81, "learning_rate": 9.825955620144484e-05, "loss": 0.2611, "step": 36860 }, { "epoch": 8.81, "learning_rate": 9.8258617240592e-05, "loss": 0.3324, "step": 36870 }, { "epoch": 8.82, "learning_rate": 9.825767803101384e-05, "loss": 0.3225, "step": 36880 }, { "epoch": 8.82, "learning_rate": 9.82567385727152e-05, "loss": 0.2939, "step": 36890 }, { "epoch": 8.82, "learning_rate": 9.825579886570093e-05, "loss": 0.3493, "step": 36900 }, { "epoch": 8.82, "learning_rate": 9.825485890997587e-05, "loss": 0.288, "step": 36910 }, { "epoch": 8.83, "learning_rate": 9.825391870554486e-05, "loss": 0.2478, "step": 36920 }, { "epoch": 8.83, "learning_rate": 9.825297825241276e-05, "loss": 0.2813, "step": 36930 }, { "epoch": 8.83, "learning_rate": 9.825203755058438e-05, "loss": 0.3764, "step": 36940 }, { "epoch": 8.83, "learning_rate": 9.825109660006464e-05, "loss": 0.3851, "step": 36950 }, { "epoch": 8.84, "learning_rate": 9.825015540085831e-05, "loss": 0.3308, "step": 36960 }, { "epoch": 8.84, "learning_rate": 9.824921395297029e-05, "loss": 0.2717, "step": 36970 }, { "epoch": 8.84, "learning_rate": 9.824827225640541e-05, "loss": 0.3455, "step": 36980 }, { "epoch": 8.84, "learning_rate": 9.824733031116852e-05, "loss": 0.2442, "step": 36990 }, { "epoch": 8.84, "learning_rate": 9.82463881172645e-05, "loss": 0.3664, "step": 37000 }, { "epoch": 8.85, "learning_rate": 9.82454456746982e-05, "loss": 0.2735, "step": 37010 }, { "epoch": 8.85, "learning_rate": 9.824450298347447e-05, "loss": 0.3333, "step": 37020 }, { "epoch": 8.85, "learning_rate": 9.824356004359815e-05, "loss": 0.3493, "step": 37030 }, { "epoch": 8.85, "learning_rate": 9.824261685507414e-05, "loss": 0.3261, "step": 37040 }, { "epoch": 8.86, "learning_rate": 9.824167341790726e-05, "loss": 0.2948, "step": 37050 }, { "epoch": 8.86, "learning_rate": 9.824072973210242e-05, "loss": 0.2895, "step": 37060 }, { "epoch": 8.86, "learning_rate": 9.823978579766442e-05, "loss": 0.2781, "step": 37070 }, { "epoch": 8.86, "learning_rate": 9.823884161459818e-05, "loss": 0.2768, "step": 37080 }, { "epoch": 8.87, "learning_rate": 9.823789718290855e-05, "loss": 0.3922, "step": 37090 }, { "epoch": 8.87, "learning_rate": 9.823695250260039e-05, "loss": 0.2849, "step": 37100 }, { "epoch": 8.87, "learning_rate": 9.823600757367857e-05, "loss": 0.3955, "step": 37110 }, { "epoch": 8.87, "learning_rate": 9.823506239614797e-05, "loss": 0.2551, "step": 37120 }, { "epoch": 8.87, "learning_rate": 9.823411697001346e-05, "loss": 0.3656, "step": 37130 }, { "epoch": 8.88, "learning_rate": 9.823317129527989e-05, "loss": 0.3896, "step": 37140 }, { "epoch": 8.88, "learning_rate": 9.823222537195216e-05, "loss": 0.3715, "step": 37150 }, { "epoch": 8.88, "learning_rate": 9.823127920003514e-05, "loss": 0.3174, "step": 37160 }, { "epoch": 8.88, "learning_rate": 9.82303327795337e-05, "loss": 0.2626, "step": 37170 }, { "epoch": 8.89, "learning_rate": 9.822938611045273e-05, "loss": 0.3474, "step": 37180 }, { "epoch": 8.89, "learning_rate": 9.822843919279709e-05, "loss": 0.3451, "step": 37190 }, { "epoch": 8.89, "learning_rate": 9.822749202657169e-05, "loss": 0.3452, "step": 37200 }, { "epoch": 8.89, "learning_rate": 9.822654461178138e-05, "loss": 0.3058, "step": 37210 }, { "epoch": 8.89, "learning_rate": 9.822559694843105e-05, "loss": 0.3627, "step": 37220 }, { "epoch": 8.9, "learning_rate": 9.82246490365256e-05, "loss": 0.3092, "step": 37230 }, { "epoch": 8.9, "learning_rate": 9.82237008760699e-05, "loss": 0.3755, "step": 37240 }, { "epoch": 8.9, "learning_rate": 9.822275246706885e-05, "loss": 0.2814, "step": 37250 }, { "epoch": 8.9, "learning_rate": 9.822180380952733e-05, "loss": 0.3302, "step": 37260 }, { "epoch": 8.91, "learning_rate": 9.822085490345021e-05, "loss": 0.239, "step": 37270 }, { "epoch": 8.91, "learning_rate": 9.821990574884241e-05, "loss": 0.2997, "step": 37280 }, { "epoch": 8.91, "learning_rate": 9.821895634570883e-05, "loss": 0.3572, "step": 37290 }, { "epoch": 8.91, "learning_rate": 9.821800669405433e-05, "loss": 0.272, "step": 37300 }, { "epoch": 8.92, "learning_rate": 9.821705679388382e-05, "loss": 0.3174, "step": 37310 }, { "epoch": 8.92, "learning_rate": 9.821610664520221e-05, "loss": 0.3048, "step": 37320 }, { "epoch": 8.92, "learning_rate": 9.821515624801437e-05, "loss": 0.2881, "step": 37330 }, { "epoch": 8.92, "learning_rate": 9.821420560232521e-05, "loss": 0.3257, "step": 37340 }, { "epoch": 8.92, "learning_rate": 9.821325470813965e-05, "loss": 0.3414, "step": 37350 }, { "epoch": 8.93, "learning_rate": 9.821230356546256e-05, "loss": 0.2513, "step": 37360 }, { "epoch": 8.93, "learning_rate": 9.821135217429885e-05, "loss": 0.2857, "step": 37370 }, { "epoch": 8.93, "learning_rate": 9.821040053465344e-05, "loss": 0.3996, "step": 37380 }, { "epoch": 8.93, "learning_rate": 9.820944864653122e-05, "loss": 0.2863, "step": 37390 }, { "epoch": 8.94, "learning_rate": 9.820849650993709e-05, "loss": 0.3641, "step": 37400 }, { "epoch": 8.94, "learning_rate": 9.820754412487596e-05, "loss": 0.268, "step": 37410 }, { "epoch": 8.94, "learning_rate": 9.820659149135277e-05, "loss": 0.2691, "step": 37420 }, { "epoch": 8.94, "learning_rate": 9.820563860937237e-05, "loss": 0.3389, "step": 37430 }, { "epoch": 8.95, "learning_rate": 9.820468547893973e-05, "loss": 0.2954, "step": 37440 }, { "epoch": 8.95, "learning_rate": 9.820373210005973e-05, "loss": 0.3379, "step": 37450 }, { "epoch": 8.95, "learning_rate": 9.820277847273729e-05, "loss": 0.229, "step": 37460 }, { "epoch": 9.0, "learning_rate": 9.820182459697733e-05, "loss": 0.3279, "step": 37470 }, { "epoch": 9.0, "learning_rate": 9.820087047278477e-05, "loss": 0.3534, "step": 37480 }, { "epoch": 9.01, "learning_rate": 9.819991610016452e-05, "loss": 0.3201, "step": 37490 }, { "epoch": 9.01, "learning_rate": 9.819896147912148e-05, "loss": 0.279, "step": 37500 }, { "epoch": 9.01, "learning_rate": 9.819800660966062e-05, "loss": 0.2935, "step": 37510 }, { "epoch": 9.01, "learning_rate": 9.819705149178682e-05, "loss": 0.2883, "step": 37520 }, { "epoch": 9.01, "learning_rate": 9.8196096125505e-05, "loss": 0.2818, "step": 37530 }, { "epoch": 9.02, "learning_rate": 9.81951405108201e-05, "loss": 0.3659, "step": 37540 }, { "epoch": 9.02, "learning_rate": 9.819418464773706e-05, "loss": 0.2753, "step": 37550 }, { "epoch": 9.02, "learning_rate": 9.819322853626078e-05, "loss": 0.2788, "step": 37560 }, { "epoch": 9.02, "learning_rate": 9.819227217639619e-05, "loss": 0.315, "step": 37570 }, { "epoch": 9.03, "learning_rate": 9.819131556814824e-05, "loss": 0.2285, "step": 37580 }, { "epoch": 9.03, "learning_rate": 9.819035871152184e-05, "loss": 0.2225, "step": 37590 }, { "epoch": 9.03, "learning_rate": 9.818940160652193e-05, "loss": 0.2563, "step": 37600 }, { "epoch": 9.03, "learning_rate": 9.818844425315343e-05, "loss": 0.2087, "step": 37610 }, { "epoch": 9.03, "learning_rate": 9.81874866514213e-05, "loss": 0.337, "step": 37620 }, { "epoch": 9.04, "learning_rate": 9.818652880133045e-05, "loss": 0.2944, "step": 37630 }, { "epoch": 9.04, "learning_rate": 9.818557070288584e-05, "loss": 0.3396, "step": 37640 }, { "epoch": 9.04, "learning_rate": 9.818461235609238e-05, "loss": 0.2481, "step": 37650 }, { "epoch": 9.04, "learning_rate": 9.818365376095504e-05, "loss": 0.2588, "step": 37660 }, { "epoch": 9.05, "learning_rate": 9.818269491747875e-05, "loss": 0.2504, "step": 37670 }, { "epoch": 9.05, "learning_rate": 9.818173582566844e-05, "loss": 0.2851, "step": 37680 }, { "epoch": 9.05, "learning_rate": 9.818077648552906e-05, "loss": 0.2579, "step": 37690 }, { "epoch": 9.05, "learning_rate": 9.817981689706555e-05, "loss": 0.2963, "step": 37700 }, { "epoch": 9.06, "learning_rate": 9.817885706028286e-05, "loss": 0.2488, "step": 37710 }, { "epoch": 9.06, "learning_rate": 9.817789697518595e-05, "loss": 0.3014, "step": 37720 }, { "epoch": 9.06, "learning_rate": 9.817693664177974e-05, "loss": 0.2926, "step": 37730 }, { "epoch": 9.06, "learning_rate": 9.817597606006921e-05, "loss": 0.2761, "step": 37740 }, { "epoch": 9.06, "learning_rate": 9.81750152300593e-05, "loss": 0.2481, "step": 37750 }, { "epoch": 9.07, "learning_rate": 9.817405415175494e-05, "loss": 0.267, "step": 37760 }, { "epoch": 9.07, "learning_rate": 9.817309282516111e-05, "loss": 0.2378, "step": 37770 }, { "epoch": 9.07, "learning_rate": 9.817213125028276e-05, "loss": 0.2481, "step": 37780 }, { "epoch": 9.07, "learning_rate": 9.817116942712486e-05, "loss": 0.2934, "step": 37790 }, { "epoch": 9.08, "learning_rate": 9.817020735569231e-05, "loss": 0.2632, "step": 37800 }, { "epoch": 9.08, "learning_rate": 9.816924503599014e-05, "loss": 0.3177, "step": 37810 }, { "epoch": 9.08, "learning_rate": 9.816828246802328e-05, "loss": 0.2529, "step": 37820 }, { "epoch": 9.08, "learning_rate": 9.816731965179666e-05, "loss": 0.2313, "step": 37830 }, { "epoch": 9.09, "learning_rate": 9.81663565873153e-05, "loss": 0.2644, "step": 37840 }, { "epoch": 9.09, "learning_rate": 9.816539327458413e-05, "loss": 0.2771, "step": 37850 }, { "epoch": 9.09, "learning_rate": 9.816442971360813e-05, "loss": 0.2634, "step": 37860 }, { "epoch": 9.09, "learning_rate": 9.816346590439223e-05, "loss": 0.2825, "step": 37870 }, { "epoch": 9.09, "learning_rate": 9.816250184694144e-05, "loss": 0.2767, "step": 37880 }, { "epoch": 9.1, "learning_rate": 9.816153754126071e-05, "loss": 0.2943, "step": 37890 }, { "epoch": 9.1, "learning_rate": 9.816057298735501e-05, "loss": 0.2913, "step": 37900 }, { "epoch": 9.1, "learning_rate": 9.815960818522932e-05, "loss": 0.3087, "step": 37910 }, { "epoch": 9.1, "learning_rate": 9.815864313488861e-05, "loss": 0.2663, "step": 37920 }, { "epoch": 9.11, "learning_rate": 9.815767783633784e-05, "loss": 0.213, "step": 37930 }, { "epoch": 9.11, "learning_rate": 9.815671228958201e-05, "loss": 0.3267, "step": 37940 }, { "epoch": 9.11, "learning_rate": 9.815574649462607e-05, "loss": 0.2227, "step": 37950 }, { "epoch": 9.11, "learning_rate": 9.815478045147501e-05, "loss": 0.299, "step": 37960 }, { "epoch": 9.11, "learning_rate": 9.815381416013382e-05, "loss": 0.246, "step": 37970 }, { "epoch": 9.12, "learning_rate": 9.815284762060746e-05, "loss": 0.2326, "step": 37980 }, { "epoch": 9.12, "learning_rate": 9.815188083290092e-05, "loss": 0.292, "step": 37990 }, { "epoch": 9.12, "learning_rate": 9.81509137970192e-05, "loss": 0.2272, "step": 38000 }, { "epoch": 9.12, "learning_rate": 9.814994651296725e-05, "loss": 0.244, "step": 38010 }, { "epoch": 9.13, "learning_rate": 9.814897898075007e-05, "loss": 0.2716, "step": 38020 }, { "epoch": 9.13, "learning_rate": 9.814801120037267e-05, "loss": 0.2974, "step": 38030 }, { "epoch": 9.13, "learning_rate": 9.814704317184e-05, "loss": 0.3199, "step": 38040 }, { "epoch": 9.13, "learning_rate": 9.814607489515707e-05, "loss": 0.3578, "step": 38050 }, { "epoch": 9.14, "learning_rate": 9.814510637032888e-05, "loss": 0.3015, "step": 38060 }, { "epoch": 9.14, "learning_rate": 9.814413759736039e-05, "loss": 0.2204, "step": 38070 }, { "epoch": 9.14, "learning_rate": 9.814316857625663e-05, "loss": 0.2402, "step": 38080 }, { "epoch": 9.14, "learning_rate": 9.814219930702257e-05, "loss": 0.2783, "step": 38090 }, { "epoch": 9.14, "learning_rate": 9.81412297896632e-05, "loss": 0.292, "step": 38100 }, { "epoch": 9.15, "learning_rate": 9.814026002418355e-05, "loss": 0.3716, "step": 38110 }, { "epoch": 9.15, "learning_rate": 9.813929001058859e-05, "loss": 0.2866, "step": 38120 }, { "epoch": 9.15, "learning_rate": 9.813831974888332e-05, "loss": 0.3365, "step": 38130 }, { "epoch": 9.15, "learning_rate": 9.813734923907275e-05, "loss": 0.3143, "step": 38140 }, { "epoch": 9.16, "learning_rate": 9.813637848116188e-05, "loss": 0.2592, "step": 38150 }, { "epoch": 9.16, "learning_rate": 9.813540747515572e-05, "loss": 0.1851, "step": 38160 }, { "epoch": 9.16, "learning_rate": 9.813443622105927e-05, "loss": 0.2751, "step": 38170 }, { "epoch": 9.16, "learning_rate": 9.813346471887752e-05, "loss": 0.3111, "step": 38180 }, { "epoch": 9.17, "learning_rate": 9.813249296861549e-05, "loss": 0.243, "step": 38190 }, { "epoch": 9.17, "learning_rate": 9.81315209702782e-05, "loss": 0.2706, "step": 38200 }, { "epoch": 9.17, "learning_rate": 9.813054872387065e-05, "loss": 0.2488, "step": 38210 }, { "epoch": 9.17, "learning_rate": 9.812957622939784e-05, "loss": 0.2256, "step": 38220 }, { "epoch": 9.17, "learning_rate": 9.812860348686479e-05, "loss": 0.2238, "step": 38230 }, { "epoch": 9.18, "learning_rate": 9.812763049627653e-05, "loss": 0.2114, "step": 38240 }, { "epoch": 9.18, "learning_rate": 9.812665725763805e-05, "loss": 0.2024, "step": 38250 }, { "epoch": 9.18, "learning_rate": 9.812568377095437e-05, "loss": 0.2607, "step": 38260 }, { "epoch": 9.18, "learning_rate": 9.812471003623052e-05, "loss": 0.3087, "step": 38270 }, { "epoch": 9.19, "learning_rate": 9.812373605347152e-05, "loss": 0.3327, "step": 38280 }, { "epoch": 9.19, "learning_rate": 9.812276182268236e-05, "loss": 0.3037, "step": 38290 }, { "epoch": 9.19, "learning_rate": 9.812178734386811e-05, "loss": 0.2645, "step": 38300 }, { "epoch": 9.19, "learning_rate": 9.812081261703375e-05, "loss": 0.262, "step": 38310 }, { "epoch": 9.19, "learning_rate": 9.811983764218433e-05, "loss": 0.3162, "step": 38320 }, { "epoch": 9.2, "learning_rate": 9.811886241932485e-05, "loss": 0.27, "step": 38330 }, { "epoch": 9.2, "learning_rate": 9.811788694846035e-05, "loss": 0.2511, "step": 38340 }, { "epoch": 9.2, "learning_rate": 9.811691122959588e-05, "loss": 0.24, "step": 38350 }, { "epoch": 9.2, "learning_rate": 9.811593526273643e-05, "loss": 0.2553, "step": 38360 }, { "epoch": 9.21, "learning_rate": 9.811495904788706e-05, "loss": 0.2262, "step": 38370 }, { "epoch": 9.21, "learning_rate": 9.811398258505278e-05, "loss": 0.3028, "step": 38380 }, { "epoch": 9.21, "learning_rate": 9.811300587423864e-05, "loss": 0.2363, "step": 38390 }, { "epoch": 9.21, "learning_rate": 9.811202891544965e-05, "loss": 0.311, "step": 38400 }, { "epoch": 9.22, "learning_rate": 9.811105170869087e-05, "loss": 0.2741, "step": 38410 }, { "epoch": 9.22, "learning_rate": 9.811007425396732e-05, "loss": 0.2756, "step": 38420 }, { "epoch": 9.22, "learning_rate": 9.810909655128406e-05, "loss": 0.2505, "step": 38430 }, { "epoch": 9.22, "learning_rate": 9.81081186006461e-05, "loss": 0.3311, "step": 38440 }, { "epoch": 9.22, "learning_rate": 9.810714040205851e-05, "loss": 0.2939, "step": 38450 }, { "epoch": 9.23, "learning_rate": 9.810616195552631e-05, "loss": 0.2833, "step": 38460 }, { "epoch": 9.23, "learning_rate": 9.810518326105454e-05, "loss": 0.3042, "step": 38470 }, { "epoch": 9.23, "learning_rate": 9.810420431864826e-05, "loss": 0.3028, "step": 38480 }, { "epoch": 9.23, "learning_rate": 9.810322512831251e-05, "loss": 0.3335, "step": 38490 }, { "epoch": 9.24, "learning_rate": 9.810224569005233e-05, "loss": 0.2446, "step": 38500 }, { "epoch": 9.24, "learning_rate": 9.810126600387277e-05, "loss": 0.2957, "step": 38510 }, { "epoch": 9.24, "learning_rate": 9.810028606977891e-05, "loss": 0.3487, "step": 38520 }, { "epoch": 9.24, "learning_rate": 9.809930588777575e-05, "loss": 0.2231, "step": 38530 }, { "epoch": 9.25, "learning_rate": 9.809832545786837e-05, "loss": 0.2229, "step": 38540 }, { "epoch": 9.25, "learning_rate": 9.80973447800618e-05, "loss": 0.3313, "step": 38550 }, { "epoch": 9.25, "learning_rate": 9.809636385436114e-05, "loss": 0.2877, "step": 38560 }, { "epoch": 9.25, "learning_rate": 9.80953826807714e-05, "loss": 0.2948, "step": 38570 }, { "epoch": 9.25, "learning_rate": 9.809440125929768e-05, "loss": 0.2708, "step": 38580 }, { "epoch": 9.26, "learning_rate": 9.809341958994501e-05, "loss": 0.2301, "step": 38590 }, { "epoch": 9.26, "learning_rate": 9.809243767271843e-05, "loss": 0.335, "step": 38600 }, { "epoch": 9.26, "learning_rate": 9.809145550762303e-05, "loss": 0.2388, "step": 38610 }, { "epoch": 9.26, "learning_rate": 9.809047309466389e-05, "loss": 0.2587, "step": 38620 }, { "epoch": 9.27, "learning_rate": 9.808949043384602e-05, "loss": 0.3483, "step": 38630 }, { "epoch": 9.27, "learning_rate": 9.808850752517453e-05, "loss": 0.2487, "step": 38640 }, { "epoch": 9.27, "learning_rate": 9.808752436865447e-05, "loss": 0.3014, "step": 38650 }, { "epoch": 9.27, "learning_rate": 9.808654096429091e-05, "loss": 0.2595, "step": 38660 }, { "epoch": 9.27, "learning_rate": 9.80855573120889e-05, "loss": 0.3744, "step": 38670 }, { "epoch": 9.28, "learning_rate": 9.808457341205353e-05, "loss": 0.2544, "step": 38680 }, { "epoch": 9.28, "learning_rate": 9.808358926418988e-05, "loss": 0.22, "step": 38690 }, { "epoch": 9.28, "learning_rate": 9.808260486850301e-05, "loss": 0.2472, "step": 38700 }, { "epoch": 9.28, "learning_rate": 9.808162022499799e-05, "loss": 0.2856, "step": 38710 }, { "epoch": 9.29, "learning_rate": 9.808063533367988e-05, "loss": 0.3341, "step": 38720 }, { "epoch": 9.29, "learning_rate": 9.807965019455379e-05, "loss": 0.3145, "step": 38730 }, { "epoch": 9.29, "learning_rate": 9.807866480762478e-05, "loss": 0.3047, "step": 38740 }, { "epoch": 9.29, "learning_rate": 9.807767917289792e-05, "loss": 0.308, "step": 38750 }, { "epoch": 9.3, "learning_rate": 9.80766932903783e-05, "loss": 0.2538, "step": 38760 }, { "epoch": 9.3, "learning_rate": 9.807570716007102e-05, "loss": 0.2242, "step": 38770 }, { "epoch": 9.3, "learning_rate": 9.807472078198112e-05, "loss": 0.2678, "step": 38780 }, { "epoch": 9.3, "learning_rate": 9.807373415611372e-05, "loss": 0.3278, "step": 38790 }, { "epoch": 9.3, "learning_rate": 9.807274728247389e-05, "loss": 0.2415, "step": 38800 }, { "epoch": 9.31, "learning_rate": 9.807176016106672e-05, "loss": 0.2874, "step": 38810 }, { "epoch": 9.31, "learning_rate": 9.807077279189729e-05, "loss": 0.3099, "step": 38820 }, { "epoch": 9.31, "learning_rate": 9.806978517497071e-05, "loss": 0.2538, "step": 38830 }, { "epoch": 9.31, "learning_rate": 9.806879731029203e-05, "loss": 0.3002, "step": 38840 }, { "epoch": 9.32, "learning_rate": 9.80678091978664e-05, "loss": 0.2642, "step": 38850 }, { "epoch": 9.32, "learning_rate": 9.806682083769884e-05, "loss": 0.2276, "step": 38860 }, { "epoch": 9.32, "learning_rate": 9.806583222979454e-05, "loss": 0.2465, "step": 38870 }, { "epoch": 9.32, "learning_rate": 9.806484337415849e-05, "loss": 0.2881, "step": 38880 }, { "epoch": 9.33, "learning_rate": 9.806385427079585e-05, "loss": 0.2324, "step": 38890 }, { "epoch": 9.33, "learning_rate": 9.806286491971171e-05, "loss": 0.2629, "step": 38900 }, { "epoch": 9.33, "learning_rate": 9.806187532091114e-05, "loss": 0.3055, "step": 38910 }, { "epoch": 9.33, "learning_rate": 9.80608854743993e-05, "loss": 0.2367, "step": 38920 }, { "epoch": 9.33, "learning_rate": 9.805989538018122e-05, "loss": 0.2066, "step": 38930 }, { "epoch": 9.34, "learning_rate": 9.805890503826205e-05, "loss": 0.3196, "step": 38940 }, { "epoch": 9.34, "learning_rate": 9.805791444864688e-05, "loss": 0.2638, "step": 38950 }, { "epoch": 9.34, "learning_rate": 9.805692361134082e-05, "loss": 0.378, "step": 38960 }, { "epoch": 9.34, "learning_rate": 9.805593252634897e-05, "loss": 0.2405, "step": 38970 }, { "epoch": 9.35, "learning_rate": 9.805494119367646e-05, "loss": 0.2751, "step": 38980 }, { "epoch": 9.35, "learning_rate": 9.805394961332837e-05, "loss": 0.257, "step": 38990 }, { "epoch": 9.35, "learning_rate": 9.80529577853098e-05, "loss": 0.2519, "step": 39000 }, { "epoch": 9.35, "learning_rate": 9.805196570962591e-05, "loss": 0.2504, "step": 39010 }, { "epoch": 9.35, "learning_rate": 9.805097338628179e-05, "loss": 0.2316, "step": 39020 }, { "epoch": 9.36, "learning_rate": 9.804998081528254e-05, "loss": 0.2593, "step": 39030 }, { "epoch": 9.36, "learning_rate": 9.804898799663328e-05, "loss": 0.3211, "step": 39040 }, { "epoch": 9.36, "learning_rate": 9.804799493033914e-05, "loss": 0.2695, "step": 39050 }, { "epoch": 9.36, "learning_rate": 9.804700161640524e-05, "loss": 0.2212, "step": 39060 }, { "epoch": 9.37, "learning_rate": 9.80460080548367e-05, "loss": 0.21, "step": 39070 }, { "epoch": 9.37, "learning_rate": 9.80450142456386e-05, "loss": 0.2102, "step": 39080 }, { "epoch": 9.37, "learning_rate": 9.804402018881614e-05, "loss": 0.2911, "step": 39090 }, { "epoch": 9.37, "learning_rate": 9.804302588437437e-05, "loss": 0.2497, "step": 39100 }, { "epoch": 9.38, "learning_rate": 9.804203133231843e-05, "loss": 0.2309, "step": 39110 }, { "epoch": 9.38, "learning_rate": 9.804103653265348e-05, "loss": 0.2684, "step": 39120 }, { "epoch": 9.38, "learning_rate": 9.804004148538464e-05, "loss": 0.1995, "step": 39130 }, { "epoch": 9.38, "learning_rate": 9.8039046190517e-05, "loss": 0.2266, "step": 39140 }, { "epoch": 9.38, "learning_rate": 9.803805064805571e-05, "loss": 0.2077, "step": 39150 }, { "epoch": 9.39, "learning_rate": 9.803705485800591e-05, "loss": 0.2591, "step": 39160 }, { "epoch": 9.39, "learning_rate": 9.803605882037275e-05, "loss": 0.2678, "step": 39170 }, { "epoch": 9.39, "learning_rate": 9.803506253516133e-05, "loss": 0.2675, "step": 39180 }, { "epoch": 9.39, "learning_rate": 9.803406600237679e-05, "loss": 0.3035, "step": 39190 }, { "epoch": 9.4, "learning_rate": 9.803306922202426e-05, "loss": 0.1776, "step": 39200 }, { "epoch": 9.4, "learning_rate": 9.803207219410891e-05, "loss": 0.3022, "step": 39210 }, { "epoch": 9.4, "learning_rate": 9.803107491863585e-05, "loss": 0.2678, "step": 39220 }, { "epoch": 9.4, "learning_rate": 9.803007739561025e-05, "loss": 0.3138, "step": 39230 }, { "epoch": 9.41, "learning_rate": 9.80290796250372e-05, "loss": 0.29, "step": 39240 }, { "epoch": 9.41, "learning_rate": 9.802808160692188e-05, "loss": 0.2529, "step": 39250 }, { "epoch": 9.41, "learning_rate": 9.802708334126943e-05, "loss": 0.2413, "step": 39260 }, { "epoch": 9.41, "learning_rate": 9.8026084828085e-05, "loss": 0.2635, "step": 39270 }, { "epoch": 9.41, "learning_rate": 9.802508606737371e-05, "loss": 0.334, "step": 39280 }, { "epoch": 9.42, "learning_rate": 9.802408705914072e-05, "loss": 0.2392, "step": 39290 }, { "epoch": 9.42, "learning_rate": 9.80230878033912e-05, "loss": 0.2112, "step": 39300 }, { "epoch": 9.42, "learning_rate": 9.802208830013029e-05, "loss": 0.2094, "step": 39310 }, { "epoch": 9.42, "learning_rate": 9.802108854936312e-05, "loss": 0.2229, "step": 39320 }, { "epoch": 9.43, "learning_rate": 9.802008855109486e-05, "loss": 0.2674, "step": 39330 }, { "epoch": 9.43, "learning_rate": 9.801908830533067e-05, "loss": 0.2246, "step": 39340 }, { "epoch": 9.43, "learning_rate": 9.801808781207568e-05, "loss": 0.2117, "step": 39350 }, { "epoch": 9.43, "learning_rate": 9.80170870713351e-05, "loss": 0.2028, "step": 39360 }, { "epoch": 9.43, "learning_rate": 9.801608608311402e-05, "loss": 0.2353, "step": 39370 }, { "epoch": 9.44, "learning_rate": 9.801508484741764e-05, "loss": 0.2821, "step": 39380 }, { "epoch": 9.44, "learning_rate": 9.80140833642511e-05, "loss": 0.2693, "step": 39390 }, { "epoch": 9.44, "learning_rate": 9.80130816336196e-05, "loss": 0.2787, "step": 39400 }, { "epoch": 9.44, "learning_rate": 9.801207965552825e-05, "loss": 0.2641, "step": 39410 }, { "epoch": 9.45, "learning_rate": 9.801107742998226e-05, "loss": 0.1988, "step": 39420 }, { "epoch": 9.45, "learning_rate": 9.801007495698676e-05, "loss": 0.2684, "step": 39430 }, { "epoch": 9.45, "learning_rate": 9.800907223654693e-05, "loss": 0.3055, "step": 39440 }, { "epoch": 9.45, "learning_rate": 9.800806926866796e-05, "loss": 0.2753, "step": 39450 }, { "epoch": 9.46, "learning_rate": 9.800706605335499e-05, "loss": 0.2009, "step": 39460 }, { "epoch": 9.46, "learning_rate": 9.80060625906132e-05, "loss": 0.2849, "step": 39470 }, { "epoch": 9.46, "learning_rate": 9.800505888044777e-05, "loss": 0.2324, "step": 39480 }, { "epoch": 9.46, "learning_rate": 9.800405492286384e-05, "loss": 0.2647, "step": 39490 }, { "epoch": 9.46, "learning_rate": 9.800305071786664e-05, "loss": 0.2567, "step": 39500 }, { "epoch": 9.47, "learning_rate": 9.80020462654613e-05, "loss": 0.2457, "step": 39510 }, { "epoch": 9.47, "learning_rate": 9.8001041565653e-05, "loss": 0.2415, "step": 39520 }, { "epoch": 9.47, "learning_rate": 9.800003661844696e-05, "loss": 0.2551, "step": 39530 }, { "epoch": 9.47, "learning_rate": 9.799903142384831e-05, "loss": 0.2635, "step": 39540 }, { "epoch": 9.48, "learning_rate": 9.799802598186226e-05, "loss": 0.3042, "step": 39550 }, { "epoch": 9.48, "learning_rate": 9.799702029249397e-05, "loss": 0.2331, "step": 39560 }, { "epoch": 9.48, "learning_rate": 9.799601435574865e-05, "loss": 0.2866, "step": 39570 }, { "epoch": 9.48, "learning_rate": 9.799500817163145e-05, "loss": 0.3244, "step": 39580 }, { "epoch": 9.49, "learning_rate": 9.79940017401476e-05, "loss": 0.1978, "step": 39590 }, { "epoch": 9.49, "learning_rate": 9.799299506130226e-05, "loss": 0.2247, "step": 39600 }, { "epoch": 9.49, "learning_rate": 9.799198813510062e-05, "loss": 0.3525, "step": 39610 }, { "epoch": 9.49, "learning_rate": 9.799098096154786e-05, "loss": 0.2352, "step": 39620 }, { "epoch": 9.49, "learning_rate": 9.79899735406492e-05, "loss": 0.2518, "step": 39630 }, { "epoch": 9.5, "learning_rate": 9.798896587240981e-05, "loss": 0.255, "step": 39640 }, { "epoch": 9.5, "learning_rate": 9.798795795683489e-05, "loss": 0.2729, "step": 39650 }, { "epoch": 9.5, "learning_rate": 9.798694979392963e-05, "loss": 0.2015, "step": 39660 }, { "epoch": 9.5, "learning_rate": 9.798594138369923e-05, "loss": 0.2455, "step": 39670 }, { "epoch": 9.51, "learning_rate": 9.798493272614888e-05, "loss": 0.1929, "step": 39680 }, { "epoch": 9.51, "learning_rate": 9.79839238212838e-05, "loss": 0.2807, "step": 39690 }, { "epoch": 9.51, "learning_rate": 9.798291466910916e-05, "loss": 0.2289, "step": 39700 }, { "epoch": 9.51, "learning_rate": 9.798190526963018e-05, "loss": 0.1715, "step": 39710 }, { "epoch": 9.51, "learning_rate": 9.798089562285208e-05, "loss": 0.2243, "step": 39720 }, { "epoch": 9.52, "learning_rate": 9.797988572878003e-05, "loss": 0.2271, "step": 39730 }, { "epoch": 9.52, "learning_rate": 9.797887558741922e-05, "loss": 0.265, "step": 39740 }, { "epoch": 9.52, "learning_rate": 9.797786519877492e-05, "loss": 0.2017, "step": 39750 }, { "epoch": 9.52, "learning_rate": 9.79768545628523e-05, "loss": 0.309, "step": 39760 }, { "epoch": 9.53, "learning_rate": 9.797584367965656e-05, "loss": 0.3312, "step": 39770 }, { "epoch": 9.53, "learning_rate": 9.797483254919292e-05, "loss": 0.2602, "step": 39780 }, { "epoch": 9.53, "learning_rate": 9.797382117146659e-05, "loss": 0.2742, "step": 39790 }, { "epoch": 9.53, "learning_rate": 9.797280954648279e-05, "loss": 0.3508, "step": 39800 }, { "epoch": 9.54, "learning_rate": 9.797179767424674e-05, "loss": 0.3602, "step": 39810 }, { "epoch": 9.54, "learning_rate": 9.797078555476363e-05, "loss": 0.3441, "step": 39820 }, { "epoch": 9.54, "learning_rate": 9.796977318803868e-05, "loss": 0.3734, "step": 39830 }, { "epoch": 9.54, "learning_rate": 9.796876057407713e-05, "loss": 0.3897, "step": 39840 }, { "epoch": 9.54, "learning_rate": 9.79677477128842e-05, "loss": 0.37, "step": 39850 }, { "epoch": 9.55, "learning_rate": 9.796673460446507e-05, "loss": 0.3303, "step": 39860 }, { "epoch": 9.55, "learning_rate": 9.7965721248825e-05, "loss": 0.2979, "step": 39870 }, { "epoch": 9.55, "learning_rate": 9.79647076459692e-05, "loss": 0.3791, "step": 39880 }, { "epoch": 9.55, "learning_rate": 9.796369379590291e-05, "loss": 0.3363, "step": 39890 }, { "epoch": 9.56, "learning_rate": 9.796267969863133e-05, "loss": 0.3342, "step": 39900 }, { "epoch": 9.56, "learning_rate": 9.79616653541597e-05, "loss": 0.3404, "step": 39910 }, { "epoch": 9.56, "learning_rate": 9.796065076249325e-05, "loss": 0.32, "step": 39920 }, { "epoch": 9.56, "learning_rate": 9.79596359236372e-05, "loss": 0.3423, "step": 39930 }, { "epoch": 9.57, "learning_rate": 9.79586208375968e-05, "loss": 0.2859, "step": 39940 }, { "epoch": 9.57, "learning_rate": 9.795760550437724e-05, "loss": 0.3949, "step": 39950 }, { "epoch": 9.57, "learning_rate": 9.79565899239838e-05, "loss": 0.2709, "step": 39960 }, { "epoch": 9.57, "learning_rate": 9.79555740964217e-05, "loss": 0.4219, "step": 39970 }, { "epoch": 9.57, "learning_rate": 9.795455802169614e-05, "loss": 0.3204, "step": 39980 }, { "epoch": 9.58, "learning_rate": 9.795354169981241e-05, "loss": 0.3339, "step": 39990 }, { "epoch": 9.58, "learning_rate": 9.795252513077572e-05, "loss": 0.2929, "step": 40000 }, { "epoch": 9.58, "learning_rate": 9.795150831459132e-05, "loss": 0.347, "step": 40010 }, { "epoch": 9.58, "learning_rate": 9.795049125126444e-05, "loss": 0.2836, "step": 40020 }, { "epoch": 9.59, "learning_rate": 9.794947394080032e-05, "loss": 0.3595, "step": 40030 }, { "epoch": 9.59, "learning_rate": 9.794845638320422e-05, "loss": 0.3068, "step": 40040 }, { "epoch": 9.59, "learning_rate": 9.794743857848138e-05, "loss": 0.3907, "step": 40050 }, { "epoch": 9.59, "learning_rate": 9.794642052663703e-05, "loss": 0.3525, "step": 40060 }, { "epoch": 9.59, "learning_rate": 9.794540222767643e-05, "loss": 0.3966, "step": 40070 }, { "epoch": 9.6, "learning_rate": 9.794438368160483e-05, "loss": 0.364, "step": 40080 }, { "epoch": 9.6, "learning_rate": 9.794336488842748e-05, "loss": 0.3155, "step": 40090 }, { "epoch": 9.6, "learning_rate": 9.794234584814962e-05, "loss": 0.3804, "step": 40100 }, { "epoch": 9.6, "learning_rate": 9.79413265607765e-05, "loss": 0.2971, "step": 40110 }, { "epoch": 9.61, "learning_rate": 9.79403070263134e-05, "loss": 0.2772, "step": 40120 }, { "epoch": 9.61, "learning_rate": 9.793928724476556e-05, "loss": 0.3243, "step": 40130 }, { "epoch": 9.61, "learning_rate": 9.793826721613821e-05, "loss": 0.268, "step": 40140 }, { "epoch": 9.61, "learning_rate": 9.793724694043664e-05, "loss": 0.2885, "step": 40150 }, { "epoch": 9.62, "learning_rate": 9.793622641766612e-05, "loss": 0.3655, "step": 40160 }, { "epoch": 9.62, "learning_rate": 9.793520564783186e-05, "loss": 0.3238, "step": 40170 }, { "epoch": 9.62, "learning_rate": 9.793418463093915e-05, "loss": 0.3488, "step": 40180 }, { "epoch": 9.62, "learning_rate": 9.793316336699326e-05, "loss": 0.399, "step": 40190 }, { "epoch": 9.62, "learning_rate": 9.793214185599945e-05, "loss": 0.3349, "step": 40200 }, { "epoch": 9.63, "learning_rate": 9.793112009796297e-05, "loss": 0.3498, "step": 40210 }, { "epoch": 9.63, "learning_rate": 9.793009809288911e-05, "loss": 0.3321, "step": 40220 }, { "epoch": 9.63, "learning_rate": 9.79290758407831e-05, "loss": 0.3936, "step": 40230 }, { "epoch": 9.63, "learning_rate": 9.792805334165024e-05, "loss": 0.3066, "step": 40240 }, { "epoch": 9.64, "learning_rate": 9.792703059549582e-05, "loss": 0.3274, "step": 40250 }, { "epoch": 9.64, "learning_rate": 9.792600760232507e-05, "loss": 0.2786, "step": 40260 }, { "epoch": 9.64, "learning_rate": 9.792498436214326e-05, "loss": 0.3263, "step": 40270 }, { "epoch": 9.64, "learning_rate": 9.79239608749557e-05, "loss": 0.3737, "step": 40280 }, { "epoch": 9.65, "learning_rate": 9.792293714076763e-05, "loss": 0.3276, "step": 40290 }, { "epoch": 9.65, "learning_rate": 9.792191315958434e-05, "loss": 0.3336, "step": 40300 }, { "epoch": 9.65, "learning_rate": 9.792088893141112e-05, "loss": 0.4095, "step": 40310 }, { "epoch": 9.65, "learning_rate": 9.791986445625323e-05, "loss": 0.3458, "step": 40320 }, { "epoch": 9.65, "learning_rate": 9.791883973411598e-05, "loss": 0.2462, "step": 40330 }, { "epoch": 9.66, "learning_rate": 9.79178147650046e-05, "loss": 0.2149, "step": 40340 }, { "epoch": 9.66, "learning_rate": 9.791678954892441e-05, "loss": 0.3192, "step": 40350 }, { "epoch": 9.66, "learning_rate": 9.791576408588071e-05, "loss": 0.3185, "step": 40360 }, { "epoch": 9.66, "learning_rate": 9.791473837587872e-05, "loss": 0.2933, "step": 40370 }, { "epoch": 9.67, "learning_rate": 9.79137124189238e-05, "loss": 0.2936, "step": 40380 }, { "epoch": 9.67, "learning_rate": 9.791268621502119e-05, "loss": 0.252, "step": 40390 }, { "epoch": 9.67, "learning_rate": 9.79116597641762e-05, "loss": 0.2994, "step": 40400 }, { "epoch": 9.67, "learning_rate": 9.791063306639412e-05, "loss": 0.3204, "step": 40410 }, { "epoch": 9.67, "learning_rate": 9.790960612168023e-05, "loss": 0.2946, "step": 40420 }, { "epoch": 9.68, "learning_rate": 9.790857893003982e-05, "loss": 0.1887, "step": 40430 }, { "epoch": 9.68, "learning_rate": 9.790755149147821e-05, "loss": 0.3652, "step": 40440 }, { "epoch": 9.68, "learning_rate": 9.790652380600067e-05, "loss": 0.2889, "step": 40450 }, { "epoch": 9.68, "learning_rate": 9.790549587361251e-05, "loss": 0.3511, "step": 40460 }, { "epoch": 9.69, "learning_rate": 9.790446769431903e-05, "loss": 0.2846, "step": 40470 }, { "epoch": 9.69, "learning_rate": 9.790343926812551e-05, "loss": 0.3103, "step": 40480 }, { "epoch": 9.69, "learning_rate": 9.790241059503727e-05, "loss": 0.3296, "step": 40490 }, { "epoch": 9.69, "learning_rate": 9.790138167505961e-05, "loss": 0.3434, "step": 40500 }, { "epoch": 9.7, "learning_rate": 9.790035250819782e-05, "loss": 0.2788, "step": 40510 }, { "epoch": 9.7, "learning_rate": 9.789932309445721e-05, "loss": 0.4462, "step": 40520 }, { "epoch": 9.7, "learning_rate": 9.78982934338431e-05, "loss": 0.272, "step": 40530 }, { "epoch": 9.7, "learning_rate": 9.789726352636078e-05, "loss": 0.2665, "step": 40540 }, { "epoch": 9.7, "learning_rate": 9.789623337201557e-05, "loss": 0.3561, "step": 40550 }, { "epoch": 9.71, "learning_rate": 9.789520297081276e-05, "loss": 0.2421, "step": 40560 }, { "epoch": 9.71, "learning_rate": 9.789417232275769e-05, "loss": 0.2506, "step": 40570 }, { "epoch": 9.71, "learning_rate": 9.789314142785564e-05, "loss": 0.2615, "step": 40580 }, { "epoch": 9.71, "learning_rate": 9.789211028611195e-05, "loss": 0.2945, "step": 40590 }, { "epoch": 9.72, "learning_rate": 9.78910788975319e-05, "loss": 0.2753, "step": 40600 }, { "epoch": 9.72, "learning_rate": 9.789004726212085e-05, "loss": 0.2927, "step": 40610 }, { "epoch": 9.72, "learning_rate": 9.78890153798841e-05, "loss": 0.2307, "step": 40620 }, { "epoch": 9.72, "learning_rate": 9.788798325082696e-05, "loss": 0.2936, "step": 40630 }, { "epoch": 9.73, "learning_rate": 9.788695087495475e-05, "loss": 0.3159, "step": 40640 }, { "epoch": 9.73, "learning_rate": 9.78859182522728e-05, "loss": 0.2114, "step": 40650 }, { "epoch": 9.73, "learning_rate": 9.788488538278641e-05, "loss": 0.3907, "step": 40660 }, { "epoch": 9.73, "learning_rate": 9.788385226650094e-05, "loss": 0.2901, "step": 40670 }, { "epoch": 9.73, "learning_rate": 9.78828189034217e-05, "loss": 0.244, "step": 40680 }, { "epoch": 9.74, "learning_rate": 9.7881785293554e-05, "loss": 0.3252, "step": 40690 }, { "epoch": 9.74, "learning_rate": 9.788075143690317e-05, "loss": 0.289, "step": 40700 }, { "epoch": 9.74, "learning_rate": 9.787971733347456e-05, "loss": 0.3557, "step": 40710 }, { "epoch": 9.74, "learning_rate": 9.787868298327348e-05, "loss": 0.3588, "step": 40720 }, { "epoch": 9.75, "learning_rate": 9.787764838630527e-05, "loss": 0.2469, "step": 40730 }, { "epoch": 9.75, "learning_rate": 9.787661354257526e-05, "loss": 0.3028, "step": 40740 }, { "epoch": 9.75, "learning_rate": 9.78755784520888e-05, "loss": 0.2497, "step": 40750 }, { "epoch": 9.75, "learning_rate": 9.787454311485118e-05, "loss": 0.2849, "step": 40760 }, { "epoch": 9.75, "learning_rate": 9.787350753086777e-05, "loss": 0.3334, "step": 40770 }, { "epoch": 9.76, "learning_rate": 9.787247170014391e-05, "loss": 0.3071, "step": 40780 }, { "epoch": 9.76, "learning_rate": 9.787143562268492e-05, "loss": 0.2831, "step": 40790 }, { "epoch": 9.76, "learning_rate": 9.787039929849617e-05, "loss": 0.3392, "step": 40800 }, { "epoch": 9.76, "learning_rate": 9.786936272758298e-05, "loss": 0.3815, "step": 40810 }, { "epoch": 9.77, "learning_rate": 9.786832590995067e-05, "loss": 0.3297, "step": 40820 }, { "epoch": 9.77, "learning_rate": 9.786728884560464e-05, "loss": 0.3346, "step": 40830 }, { "epoch": 9.77, "learning_rate": 9.786625153455017e-05, "loss": 0.3237, "step": 40840 }, { "epoch": 9.77, "learning_rate": 9.786521397679266e-05, "loss": 0.2814, "step": 40850 }, { "epoch": 9.78, "learning_rate": 9.786417617233744e-05, "loss": 0.2643, "step": 40860 }, { "epoch": 9.78, "learning_rate": 9.786313812118985e-05, "loss": 0.3059, "step": 40870 }, { "epoch": 9.78, "learning_rate": 9.786209982335525e-05, "loss": 0.3458, "step": 40880 }, { "epoch": 9.78, "learning_rate": 9.786106127883898e-05, "loss": 0.2862, "step": 40890 }, { "epoch": 9.78, "learning_rate": 9.78600224876464e-05, "loss": 0.1961, "step": 40900 }, { "epoch": 9.79, "learning_rate": 9.785898344978288e-05, "loss": 0.3104, "step": 40910 }, { "epoch": 9.79, "learning_rate": 9.785794416525373e-05, "loss": 0.2857, "step": 40920 }, { "epoch": 9.79, "learning_rate": 9.785690463406436e-05, "loss": 0.3075, "step": 40930 }, { "epoch": 9.79, "learning_rate": 9.785586485622009e-05, "loss": 0.2323, "step": 40940 }, { "epoch": 9.8, "learning_rate": 9.78548248317263e-05, "loss": 0.2822, "step": 40950 }, { "epoch": 9.8, "learning_rate": 9.785378456058836e-05, "loss": 0.2159, "step": 40960 }, { "epoch": 9.8, "learning_rate": 9.785274404281159e-05, "loss": 0.3435, "step": 40970 }, { "epoch": 9.8, "learning_rate": 9.785170327840138e-05, "loss": 0.2255, "step": 40980 }, { "epoch": 9.81, "learning_rate": 9.78506622673631e-05, "loss": 0.3748, "step": 40990 }, { "epoch": 9.81, "learning_rate": 9.78496210097021e-05, "loss": 0.3662, "step": 41000 }, { "epoch": 9.81, "learning_rate": 9.784857950542374e-05, "loss": 0.1943, "step": 41010 }, { "epoch": 9.81, "learning_rate": 9.784753775453342e-05, "loss": 0.2663, "step": 41020 }, { "epoch": 9.81, "learning_rate": 9.784649575703648e-05, "loss": 0.2295, "step": 41030 }, { "epoch": 9.82, "learning_rate": 9.784545351293833e-05, "loss": 0.2789, "step": 41040 }, { "epoch": 9.82, "learning_rate": 9.784441102224427e-05, "loss": 0.3133, "step": 41050 }, { "epoch": 9.82, "learning_rate": 9.784336828495974e-05, "loss": 0.3083, "step": 41060 }, { "epoch": 9.82, "learning_rate": 9.784232530109009e-05, "loss": 0.2515, "step": 41070 }, { "epoch": 9.83, "learning_rate": 9.784128207064069e-05, "loss": 0.2569, "step": 41080 }, { "epoch": 9.83, "learning_rate": 9.784023859361693e-05, "loss": 0.2869, "step": 41090 }, { "epoch": 9.83, "learning_rate": 9.783919487002417e-05, "loss": 0.3029, "step": 41100 }, { "epoch": 9.83, "learning_rate": 9.78381508998678e-05, "loss": 0.3264, "step": 41110 }, { "epoch": 9.83, "learning_rate": 9.78371066831532e-05, "loss": 0.2208, "step": 41120 }, { "epoch": 9.84, "learning_rate": 9.783606221988575e-05, "loss": 0.2297, "step": 41130 }, { "epoch": 9.84, "learning_rate": 9.783501751007084e-05, "loss": 0.2989, "step": 41140 }, { "epoch": 9.84, "learning_rate": 9.783397255371387e-05, "loss": 0.2483, "step": 41150 }, { "epoch": 9.84, "learning_rate": 9.783292735082018e-05, "loss": 0.294, "step": 41160 }, { "epoch": 9.85, "learning_rate": 9.783188190139518e-05, "loss": 0.3561, "step": 41170 }, { "epoch": 9.85, "learning_rate": 9.783083620544429e-05, "loss": 0.2693, "step": 41180 }, { "epoch": 9.85, "learning_rate": 9.782979026297285e-05, "loss": 0.2451, "step": 41190 }, { "epoch": 9.85, "learning_rate": 9.782874407398626e-05, "loss": 0.2981, "step": 41200 }, { "epoch": 9.86, "learning_rate": 9.782769763848993e-05, "loss": 0.2634, "step": 41210 }, { "epoch": 9.86, "learning_rate": 9.782665095648927e-05, "loss": 0.2226, "step": 41220 }, { "epoch": 9.86, "learning_rate": 9.782560402798962e-05, "loss": 0.2999, "step": 41230 }, { "epoch": 9.86, "learning_rate": 9.782455685299643e-05, "loss": 0.3071, "step": 41240 }, { "epoch": 9.86, "learning_rate": 9.782350943151505e-05, "loss": 0.23, "step": 41250 }, { "epoch": 9.87, "learning_rate": 9.782246176355093e-05, "loss": 0.2946, "step": 41260 }, { "epoch": 9.87, "learning_rate": 9.782141384910944e-05, "loss": 0.3696, "step": 41270 }, { "epoch": 9.87, "learning_rate": 9.782036568819596e-05, "loss": 0.3245, "step": 41280 }, { "epoch": 9.87, "learning_rate": 9.781931728081593e-05, "loss": 0.2349, "step": 41290 }, { "epoch": 9.88, "learning_rate": 9.781826862697474e-05, "loss": 0.2862, "step": 41300 }, { "epoch": 9.88, "learning_rate": 9.781721972667779e-05, "loss": 0.2714, "step": 41310 }, { "epoch": 9.88, "learning_rate": 9.781617057993048e-05, "loss": 0.3107, "step": 41320 }, { "epoch": 9.88, "learning_rate": 9.781512118673824e-05, "loss": 0.313, "step": 41330 }, { "epoch": 9.89, "learning_rate": 9.781407154710646e-05, "loss": 0.2858, "step": 41340 }, { "epoch": 9.89, "learning_rate": 9.781302166104056e-05, "loss": 0.2443, "step": 41350 }, { "epoch": 9.89, "learning_rate": 9.781197152854596e-05, "loss": 0.2338, "step": 41360 }, { "epoch": 9.89, "learning_rate": 9.781092114962804e-05, "loss": 0.245, "step": 41370 }, { "epoch": 9.89, "learning_rate": 9.780987052429223e-05, "loss": 0.2184, "step": 41380 }, { "epoch": 9.9, "learning_rate": 9.780881965254395e-05, "loss": 0.2383, "step": 41390 }, { "epoch": 9.9, "learning_rate": 9.780776853438863e-05, "loss": 0.2887, "step": 41400 }, { "epoch": 9.9, "learning_rate": 9.780671716983166e-05, "loss": 0.2905, "step": 41410 }, { "epoch": 9.9, "learning_rate": 9.780566555887847e-05, "loss": 0.2277, "step": 41420 }, { "epoch": 9.91, "learning_rate": 9.780461370153448e-05, "loss": 0.222, "step": 41430 }, { "epoch": 9.91, "learning_rate": 9.780356159780511e-05, "loss": 0.3582, "step": 41440 }, { "epoch": 9.91, "learning_rate": 9.78025092476958e-05, "loss": 0.1803, "step": 41450 }, { "epoch": 9.91, "learning_rate": 9.780145665121194e-05, "loss": 0.2497, "step": 41460 }, { "epoch": 9.91, "learning_rate": 9.780040380835898e-05, "loss": 0.2558, "step": 41470 }, { "epoch": 9.92, "learning_rate": 9.779935071914233e-05, "loss": 0.2482, "step": 41480 }, { "epoch": 9.92, "learning_rate": 9.779829738356743e-05, "loss": 0.2795, "step": 41490 }, { "epoch": 9.92, "learning_rate": 9.779724380163971e-05, "loss": 0.2519, "step": 41500 }, { "epoch": 9.92, "learning_rate": 9.779618997336459e-05, "loss": 0.2133, "step": 41510 }, { "epoch": 9.93, "learning_rate": 9.779513589874752e-05, "loss": 0.1886, "step": 41520 }, { "epoch": 9.93, "learning_rate": 9.779408157779391e-05, "loss": 0.312, "step": 41530 }, { "epoch": 9.93, "learning_rate": 9.77930270105092e-05, "loss": 0.3078, "step": 41540 }, { "epoch": 9.93, "learning_rate": 9.779197219689884e-05, "loss": 0.2152, "step": 41550 }, { "epoch": 9.94, "learning_rate": 9.779091713696827e-05, "loss": 0.3814, "step": 41560 }, { "epoch": 9.94, "learning_rate": 9.778986183072288e-05, "loss": 0.2582, "step": 41570 }, { "epoch": 9.94, "learning_rate": 9.778880627816815e-05, "loss": 0.2165, "step": 41580 }, { "epoch": 9.94, "learning_rate": 9.778775047930952e-05, "loss": 0.3407, "step": 41590 }, { "epoch": 9.94, "learning_rate": 9.778669443415244e-05, "loss": 0.2453, "step": 41600 }, { "epoch": 9.95, "learning_rate": 9.778563814270232e-05, "loss": 0.2453, "step": 41610 }, { "epoch": 9.95, "learning_rate": 9.778458160496463e-05, "loss": 0.2132, "step": 41620 }, { "epoch": 9.95, "learning_rate": 9.77835248209448e-05, "loss": 0.2415, "step": 41630 }, { "epoch": 10.0, "learning_rate": 9.778246779064828e-05, "loss": 0.2511, "step": 41640 }, { "epoch": 10.0, "learning_rate": 9.778141051408052e-05, "loss": 0.2536, "step": 41650 }, { "epoch": 10.01, "learning_rate": 9.778035299124698e-05, "loss": 0.2959, "step": 41660 }, { "epoch": 10.01, "learning_rate": 9.77792952221531e-05, "loss": 0.2743, "step": 41670 }, { "epoch": 10.01, "learning_rate": 9.777823720680434e-05, "loss": 0.2689, "step": 41680 }, { "epoch": 10.01, "learning_rate": 9.777717894520613e-05, "loss": 0.2534, "step": 41690 }, { "epoch": 10.02, "learning_rate": 9.777612043736395e-05, "loss": 0.363, "step": 41700 }, { "epoch": 10.02, "learning_rate": 9.777506168328324e-05, "loss": 0.2833, "step": 41710 }, { "epoch": 10.02, "learning_rate": 9.777400268296948e-05, "loss": 0.3187, "step": 41720 }, { "epoch": 10.02, "learning_rate": 9.777294343642809e-05, "loss": 0.282, "step": 41730 }, { "epoch": 10.03, "learning_rate": 9.777188394366456e-05, "loss": 0.2515, "step": 41740 }, { "epoch": 10.03, "learning_rate": 9.777082420468433e-05, "loss": 0.2222, "step": 41750 }, { "epoch": 10.03, "learning_rate": 9.776976421949288e-05, "loss": 0.2863, "step": 41760 }, { "epoch": 10.03, "learning_rate": 9.776870398809567e-05, "loss": 0.2057, "step": 41770 }, { "epoch": 10.03, "learning_rate": 9.776764351049816e-05, "loss": 0.2614, "step": 41780 }, { "epoch": 10.04, "learning_rate": 9.776658278670581e-05, "loss": 0.2517, "step": 41790 }, { "epoch": 10.04, "learning_rate": 9.77655218167241e-05, "loss": 0.2208, "step": 41800 }, { "epoch": 10.04, "learning_rate": 9.776446060055849e-05, "loss": 0.2555, "step": 41810 }, { "epoch": 10.04, "learning_rate": 9.776339913821446e-05, "loss": 0.2771, "step": 41820 }, { "epoch": 10.05, "learning_rate": 9.776233742969745e-05, "loss": 0.258, "step": 41830 }, { "epoch": 10.05, "learning_rate": 9.776127547501297e-05, "loss": 0.2244, "step": 41840 }, { "epoch": 10.05, "learning_rate": 9.776021327416647e-05, "loss": 0.3137, "step": 41850 }, { "epoch": 10.05, "learning_rate": 9.775915082716343e-05, "loss": 0.2489, "step": 41860 }, { "epoch": 10.05, "learning_rate": 9.775808813400934e-05, "loss": 0.2307, "step": 41870 }, { "epoch": 10.06, "learning_rate": 9.775702519470963e-05, "loss": 0.2444, "step": 41880 }, { "epoch": 10.06, "learning_rate": 9.775596200926985e-05, "loss": 0.2863, "step": 41890 }, { "epoch": 10.06, "learning_rate": 9.775489857769543e-05, "loss": 0.257, "step": 41900 }, { "epoch": 10.06, "learning_rate": 9.775383489999186e-05, "loss": 0.2651, "step": 41910 }, { "epoch": 10.07, "learning_rate": 9.775277097616465e-05, "loss": 0.2901, "step": 41920 }, { "epoch": 10.07, "learning_rate": 9.775170680621922e-05, "loss": 0.2877, "step": 41930 }, { "epoch": 10.07, "learning_rate": 9.775064239016112e-05, "loss": 0.2946, "step": 41940 }, { "epoch": 10.07, "learning_rate": 9.77495777279958e-05, "loss": 0.2749, "step": 41950 }, { "epoch": 10.08, "learning_rate": 9.774851281972877e-05, "loss": 0.251, "step": 41960 }, { "epoch": 10.08, "learning_rate": 9.774744766536548e-05, "loss": 0.2056, "step": 41970 }, { "epoch": 10.08, "learning_rate": 9.774638226491147e-05, "loss": 0.2619, "step": 41980 }, { "epoch": 10.08, "learning_rate": 9.774531661837219e-05, "loss": 0.2158, "step": 41990 }, { "epoch": 10.08, "learning_rate": 9.774425072575317e-05, "loss": 0.2635, "step": 42000 }, { "epoch": 10.09, "learning_rate": 9.774318458705986e-05, "loss": 0.2564, "step": 42010 }, { "epoch": 10.09, "learning_rate": 9.774211820229779e-05, "loss": 0.2774, "step": 42020 }, { "epoch": 10.09, "learning_rate": 9.774105157147245e-05, "loss": 0.2818, "step": 42030 }, { "epoch": 10.09, "learning_rate": 9.773998469458932e-05, "loss": 0.2896, "step": 42040 }, { "epoch": 10.1, "learning_rate": 9.77389175716539e-05, "loss": 0.2315, "step": 42050 }, { "epoch": 10.1, "learning_rate": 9.773785020267172e-05, "loss": 0.266, "step": 42060 }, { "epoch": 10.1, "learning_rate": 9.773678258764825e-05, "loss": 0.2008, "step": 42070 }, { "epoch": 10.1, "learning_rate": 9.773571472658901e-05, "loss": 0.2746, "step": 42080 }, { "epoch": 10.11, "learning_rate": 9.773464661949949e-05, "loss": 0.2433, "step": 42090 }, { "epoch": 10.11, "learning_rate": 9.773357826638521e-05, "loss": 0.2181, "step": 42100 }, { "epoch": 10.11, "learning_rate": 9.773250966725167e-05, "loss": 0.3072, "step": 42110 }, { "epoch": 10.11, "learning_rate": 9.773144082210437e-05, "loss": 0.2532, "step": 42120 }, { "epoch": 10.11, "learning_rate": 9.773037173094883e-05, "loss": 0.2343, "step": 42130 }, { "epoch": 10.12, "learning_rate": 9.772930239379055e-05, "loss": 0.2039, "step": 42140 }, { "epoch": 10.12, "learning_rate": 9.772823281063504e-05, "loss": 0.2203, "step": 42150 }, { "epoch": 10.12, "learning_rate": 9.772716298148782e-05, "loss": 0.2273, "step": 42160 }, { "epoch": 10.12, "learning_rate": 9.772609290635442e-05, "loss": 0.2458, "step": 42170 }, { "epoch": 10.13, "learning_rate": 9.772502258524032e-05, "loss": 0.2889, "step": 42180 }, { "epoch": 10.13, "learning_rate": 9.772395201815108e-05, "loss": 0.3026, "step": 42190 }, { "epoch": 10.13, "learning_rate": 9.772288120509217e-05, "loss": 0.1985, "step": 42200 }, { "epoch": 10.13, "learning_rate": 9.772181014606914e-05, "loss": 0.2343, "step": 42210 }, { "epoch": 10.13, "learning_rate": 9.772073884108749e-05, "loss": 0.2584, "step": 42220 }, { "epoch": 10.14, "learning_rate": 9.771966729015276e-05, "loss": 0.2693, "step": 42230 }, { "epoch": 10.14, "learning_rate": 9.771859549327047e-05, "loss": 0.2675, "step": 42240 }, { "epoch": 10.14, "learning_rate": 9.771752345044614e-05, "loss": 0.1922, "step": 42250 }, { "epoch": 10.14, "learning_rate": 9.771645116168528e-05, "loss": 0.2677, "step": 42260 }, { "epoch": 10.15, "learning_rate": 9.771537862699344e-05, "loss": 0.2757, "step": 42270 }, { "epoch": 10.15, "learning_rate": 9.771430584637616e-05, "loss": 0.253, "step": 42280 }, { "epoch": 10.15, "learning_rate": 9.771323281983893e-05, "loss": 0.2777, "step": 42290 }, { "epoch": 10.15, "learning_rate": 9.771215954738731e-05, "loss": 0.2399, "step": 42300 }, { "epoch": 10.16, "learning_rate": 9.771108602902681e-05, "loss": 0.2219, "step": 42310 }, { "epoch": 10.16, "learning_rate": 9.771001226476297e-05, "loss": 0.2381, "step": 42320 }, { "epoch": 10.16, "learning_rate": 9.770893825460134e-05, "loss": 0.2474, "step": 42330 }, { "epoch": 10.16, "learning_rate": 9.770786399854744e-05, "loss": 0.2639, "step": 42340 }, { "epoch": 10.16, "learning_rate": 9.77067894966068e-05, "loss": 0.193, "step": 42350 }, { "epoch": 10.17, "learning_rate": 9.770571474878498e-05, "loss": 0.3213, "step": 42360 }, { "epoch": 10.17, "learning_rate": 9.77046397550875e-05, "loss": 0.2099, "step": 42370 }, { "epoch": 10.17, "learning_rate": 9.770356451551992e-05, "loss": 0.2934, "step": 42380 }, { "epoch": 10.17, "learning_rate": 9.770248903008777e-05, "loss": 0.2516, "step": 42390 }, { "epoch": 10.18, "learning_rate": 9.770141329879657e-05, "loss": 0.3113, "step": 42400 }, { "epoch": 10.18, "learning_rate": 9.77003373216519e-05, "loss": 0.2017, "step": 42410 }, { "epoch": 10.18, "learning_rate": 9.76992610986593e-05, "loss": 0.2623, "step": 42420 }, { "epoch": 10.18, "learning_rate": 9.76981846298243e-05, "loss": 0.2446, "step": 42430 }, { "epoch": 10.19, "learning_rate": 9.769710791515246e-05, "loss": 0.2571, "step": 42440 }, { "epoch": 10.19, "learning_rate": 9.769603095464933e-05, "loss": 0.1987, "step": 42450 }, { "epoch": 10.19, "learning_rate": 9.769495374832046e-05, "loss": 0.2726, "step": 42460 }, { "epoch": 10.19, "learning_rate": 9.76938762961714e-05, "loss": 0.219, "step": 42470 }, { "epoch": 10.19, "learning_rate": 9.76927985982077e-05, "loss": 0.2325, "step": 42480 }, { "epoch": 10.2, "learning_rate": 9.76917206544349e-05, "loss": 0.2374, "step": 42490 }, { "epoch": 10.2, "learning_rate": 9.76906424648586e-05, "loss": 0.2314, "step": 42500 }, { "epoch": 10.2, "learning_rate": 9.768956402948432e-05, "loss": 0.2014, "step": 42510 }, { "epoch": 10.2, "learning_rate": 9.768848534831762e-05, "loss": 0.2567, "step": 42520 }, { "epoch": 10.21, "learning_rate": 9.76874064213641e-05, "loss": 0.2029, "step": 42530 }, { "epoch": 10.21, "learning_rate": 9.768632724862925e-05, "loss": 0.283, "step": 42540 }, { "epoch": 10.21, "learning_rate": 9.768524783011869e-05, "loss": 0.2266, "step": 42550 }, { "epoch": 10.21, "learning_rate": 9.768416816583795e-05, "loss": 0.2764, "step": 42560 }, { "epoch": 10.21, "learning_rate": 9.768308825579263e-05, "loss": 0.2791, "step": 42570 }, { "epoch": 10.22, "learning_rate": 9.768200809998827e-05, "loss": 0.2163, "step": 42580 }, { "epoch": 10.22, "learning_rate": 9.768092769843042e-05, "loss": 0.1989, "step": 42590 }, { "epoch": 10.22, "learning_rate": 9.767984705112469e-05, "loss": 0.2177, "step": 42600 }, { "epoch": 10.22, "learning_rate": 9.767876615807662e-05, "loss": 0.2316, "step": 42610 }, { "epoch": 10.23, "learning_rate": 9.76776850192918e-05, "loss": 0.1706, "step": 42620 }, { "epoch": 10.23, "learning_rate": 9.767660363477578e-05, "loss": 0.2434, "step": 42630 }, { "epoch": 10.23, "learning_rate": 9.767552200453416e-05, "loss": 0.3078, "step": 42640 }, { "epoch": 10.23, "learning_rate": 9.76744401285725e-05, "loss": 0.2126, "step": 42650 }, { "epoch": 10.24, "learning_rate": 9.767335800689637e-05, "loss": 0.2133, "step": 42660 }, { "epoch": 10.24, "learning_rate": 9.767227563951136e-05, "loss": 0.2279, "step": 42670 }, { "epoch": 10.24, "learning_rate": 9.767119302642302e-05, "loss": 0.2266, "step": 42680 }, { "epoch": 10.24, "learning_rate": 9.767011016763698e-05, "loss": 0.2561, "step": 42690 }, { "epoch": 10.24, "learning_rate": 9.766902706315879e-05, "loss": 0.2221, "step": 42700 }, { "epoch": 10.25, "learning_rate": 9.766794371299403e-05, "loss": 0.2836, "step": 42710 }, { "epoch": 10.25, "learning_rate": 9.766686011714829e-05, "loss": 0.2382, "step": 42720 }, { "epoch": 10.25, "learning_rate": 9.766577627562716e-05, "loss": 0.2077, "step": 42730 }, { "epoch": 10.25, "learning_rate": 9.766469218843621e-05, "loss": 0.2661, "step": 42740 }, { "epoch": 10.26, "learning_rate": 9.766360785558106e-05, "loss": 0.2198, "step": 42750 }, { "epoch": 10.26, "learning_rate": 9.766252327706727e-05, "loss": 0.2101, "step": 42760 }, { "epoch": 10.26, "learning_rate": 9.766143845290041e-05, "loss": 0.2829, "step": 42770 }, { "epoch": 10.26, "learning_rate": 9.766035338308612e-05, "loss": 0.2453, "step": 42780 }, { "epoch": 10.27, "learning_rate": 9.765926806762998e-05, "loss": 0.2106, "step": 42790 }, { "epoch": 10.27, "learning_rate": 9.765818250653756e-05, "loss": 0.2351, "step": 42800 }, { "epoch": 10.27, "learning_rate": 9.765709669981446e-05, "loss": 0.1822, "step": 42810 }, { "epoch": 10.27, "learning_rate": 9.76560106474663e-05, "loss": 0.261, "step": 42820 }, { "epoch": 10.27, "learning_rate": 9.765492434949866e-05, "loss": 0.2142, "step": 42830 }, { "epoch": 10.28, "learning_rate": 9.765383780591713e-05, "loss": 0.2265, "step": 42840 }, { "epoch": 10.28, "learning_rate": 9.765275101672733e-05, "loss": 0.2487, "step": 42850 }, { "epoch": 10.28, "learning_rate": 9.765166398193485e-05, "loss": 0.2326, "step": 42860 }, { "epoch": 10.28, "learning_rate": 9.76505767015453e-05, "loss": 0.202, "step": 42870 }, { "epoch": 10.29, "learning_rate": 9.764948917556429e-05, "loss": 0.2382, "step": 42880 }, { "epoch": 10.29, "learning_rate": 9.764840140399739e-05, "loss": 0.2427, "step": 42890 }, { "epoch": 10.29, "learning_rate": 9.764731338685025e-05, "loss": 0.2502, "step": 42900 }, { "epoch": 10.29, "learning_rate": 9.764622512412844e-05, "loss": 0.1917, "step": 42910 }, { "epoch": 10.29, "learning_rate": 9.764513661583761e-05, "loss": 0.2191, "step": 42920 }, { "epoch": 10.3, "learning_rate": 9.764404786198334e-05, "loss": 0.2035, "step": 42930 }, { "epoch": 10.3, "learning_rate": 9.764295886257124e-05, "loss": 0.2431, "step": 42940 }, { "epoch": 10.3, "learning_rate": 9.764186961760694e-05, "loss": 0.2111, "step": 42950 }, { "epoch": 10.3, "learning_rate": 9.764078012709605e-05, "loss": 0.161, "step": 42960 }, { "epoch": 10.31, "learning_rate": 9.763969039104417e-05, "loss": 0.1996, "step": 42970 }, { "epoch": 10.31, "learning_rate": 9.763860040945694e-05, "loss": 0.1919, "step": 42980 }, { "epoch": 10.31, "learning_rate": 9.763751018233995e-05, "loss": 0.2362, "step": 42990 }, { "epoch": 10.31, "learning_rate": 9.763641970969885e-05, "loss": 0.3039, "step": 43000 }, { "epoch": 10.32, "learning_rate": 9.763532899153923e-05, "loss": 0.1979, "step": 43010 }, { "epoch": 10.32, "learning_rate": 9.763423802786673e-05, "loss": 0.185, "step": 43020 }, { "epoch": 10.32, "learning_rate": 9.763314681868699e-05, "loss": 0.2352, "step": 43030 }, { "epoch": 10.32, "learning_rate": 9.763205536400558e-05, "loss": 0.2329, "step": 43040 }, { "epoch": 10.32, "learning_rate": 9.763096366382818e-05, "loss": 0.2288, "step": 43050 }, { "epoch": 10.33, "learning_rate": 9.762987171816038e-05, "loss": 0.1742, "step": 43060 }, { "epoch": 10.33, "learning_rate": 9.762877952700784e-05, "loss": 0.2182, "step": 43070 }, { "epoch": 10.33, "learning_rate": 9.762768709037616e-05, "loss": 0.2112, "step": 43080 }, { "epoch": 10.33, "learning_rate": 9.7626594408271e-05, "loss": 0.1909, "step": 43090 }, { "epoch": 10.34, "learning_rate": 9.762550148069795e-05, "loss": 0.2651, "step": 43100 }, { "epoch": 10.34, "learning_rate": 9.762440830766269e-05, "loss": 0.234, "step": 43110 }, { "epoch": 10.34, "learning_rate": 9.76233148891708e-05, "loss": 0.1667, "step": 43120 }, { "epoch": 10.34, "learning_rate": 9.762222122522798e-05, "loss": 0.3253, "step": 43130 }, { "epoch": 10.35, "learning_rate": 9.762112731583982e-05, "loss": 0.2008, "step": 43140 }, { "epoch": 10.35, "learning_rate": 9.762003316101197e-05, "loss": 0.2178, "step": 43150 }, { "epoch": 10.35, "learning_rate": 9.761893876075008e-05, "loss": 0.2218, "step": 43160 }, { "epoch": 10.35, "learning_rate": 9.761784411505976e-05, "loss": 0.2065, "step": 43170 }, { "epoch": 10.35, "learning_rate": 9.76167492239467e-05, "loss": 0.2283, "step": 43180 }, { "epoch": 10.36, "learning_rate": 9.76156540874165e-05, "loss": 0.2201, "step": 43190 }, { "epoch": 10.36, "learning_rate": 9.761455870547482e-05, "loss": 0.1955, "step": 43200 }, { "epoch": 10.36, "learning_rate": 9.761346307812732e-05, "loss": 0.2229, "step": 43210 }, { "epoch": 10.36, "learning_rate": 9.761236720537963e-05, "loss": 0.2406, "step": 43220 }, { "epoch": 10.37, "learning_rate": 9.76112710872374e-05, "loss": 0.2034, "step": 43230 }, { "epoch": 10.37, "learning_rate": 9.761017472370627e-05, "loss": 0.2189, "step": 43240 }, { "epoch": 10.37, "learning_rate": 9.760907811479192e-05, "loss": 0.2771, "step": 43250 }, { "epoch": 10.37, "learning_rate": 9.760798126049997e-05, "loss": 0.21, "step": 43260 }, { "epoch": 10.37, "learning_rate": 9.760688416083607e-05, "loss": 0.2258, "step": 43270 }, { "epoch": 10.38, "learning_rate": 9.760578681580592e-05, "loss": 0.1964, "step": 43280 }, { "epoch": 10.38, "learning_rate": 9.760468922541515e-05, "loss": 0.176, "step": 43290 }, { "epoch": 10.38, "learning_rate": 9.76035913896694e-05, "loss": 0.2297, "step": 43300 }, { "epoch": 10.38, "learning_rate": 9.760249330857433e-05, "loss": 0.2232, "step": 43310 }, { "epoch": 10.39, "learning_rate": 9.760139498213562e-05, "loss": 0.254, "step": 43320 }, { "epoch": 10.39, "learning_rate": 9.760029641035893e-05, "loss": 0.2339, "step": 43330 }, { "epoch": 10.39, "learning_rate": 9.759919759324992e-05, "loss": 0.2513, "step": 43340 }, { "epoch": 10.39, "learning_rate": 9.759809853081424e-05, "loss": 0.2483, "step": 43350 }, { "epoch": 10.4, "learning_rate": 9.759699922305756e-05, "loss": 0.2694, "step": 43360 }, { "epoch": 10.4, "learning_rate": 9.759589966998554e-05, "loss": 0.1991, "step": 43370 }, { "epoch": 10.4, "learning_rate": 9.759479987160388e-05, "loss": 0.2188, "step": 43380 }, { "epoch": 10.4, "learning_rate": 9.75936998279182e-05, "loss": 0.2325, "step": 43390 }, { "epoch": 10.4, "learning_rate": 9.75925995389342e-05, "loss": 0.1827, "step": 43400 }, { "epoch": 10.41, "learning_rate": 9.759149900465756e-05, "loss": 0.2138, "step": 43410 }, { "epoch": 10.41, "learning_rate": 9.759039822509391e-05, "loss": 0.2512, "step": 43420 }, { "epoch": 10.41, "learning_rate": 9.758929720024897e-05, "loss": 0.1708, "step": 43430 }, { "epoch": 10.41, "learning_rate": 9.758819593012838e-05, "loss": 0.2116, "step": 43440 }, { "epoch": 10.42, "learning_rate": 9.758709441473784e-05, "loss": 0.2188, "step": 43450 }, { "epoch": 10.42, "learning_rate": 9.758599265408302e-05, "loss": 0.2128, "step": 43460 }, { "epoch": 10.42, "learning_rate": 9.758489064816957e-05, "loss": 0.2543, "step": 43470 }, { "epoch": 10.42, "learning_rate": 9.758378839700324e-05, "loss": 0.1914, "step": 43480 }, { "epoch": 10.43, "learning_rate": 9.758268590058964e-05, "loss": 0.2519, "step": 43490 }, { "epoch": 10.43, "learning_rate": 9.758158315893449e-05, "loss": 0.2177, "step": 43500 }, { "epoch": 10.43, "learning_rate": 9.758048017204344e-05, "loss": 0.2206, "step": 43510 }, { "epoch": 10.43, "learning_rate": 9.757937693992222e-05, "loss": 0.1826, "step": 43520 }, { "epoch": 10.43, "learning_rate": 9.757827346257648e-05, "loss": 0.1761, "step": 43530 }, { "epoch": 10.44, "learning_rate": 9.757716974001193e-05, "loss": 0.1572, "step": 43540 }, { "epoch": 10.44, "learning_rate": 9.757606577223425e-05, "loss": 0.1848, "step": 43550 }, { "epoch": 10.44, "learning_rate": 9.757496155924912e-05, "loss": 0.2144, "step": 43560 }, { "epoch": 10.44, "learning_rate": 9.757385710106227e-05, "loss": 0.2601, "step": 43570 }, { "epoch": 10.45, "learning_rate": 9.757275239767932e-05, "loss": 0.1803, "step": 43580 }, { "epoch": 10.45, "learning_rate": 9.757164744910602e-05, "loss": 0.2236, "step": 43590 }, { "epoch": 10.45, "learning_rate": 9.757054225534808e-05, "loss": 0.1781, "step": 43600 }, { "epoch": 10.45, "learning_rate": 9.756943681641113e-05, "loss": 0.2256, "step": 43610 }, { "epoch": 10.45, "learning_rate": 9.756833113230093e-05, "loss": 0.1569, "step": 43620 }, { "epoch": 10.46, "learning_rate": 9.756722520302312e-05, "loss": 0.221, "step": 43630 }, { "epoch": 10.46, "learning_rate": 9.756611902858348e-05, "loss": 0.1958, "step": 43640 }, { "epoch": 10.46, "learning_rate": 9.756501260898763e-05, "loss": 0.2078, "step": 43650 }, { "epoch": 10.46, "learning_rate": 9.756390594424132e-05, "loss": 0.1989, "step": 43660 }, { "epoch": 10.47, "learning_rate": 9.756279903435024e-05, "loss": 0.1814, "step": 43670 }, { "epoch": 10.47, "learning_rate": 9.756169187932011e-05, "loss": 0.2344, "step": 43680 }, { "epoch": 10.47, "learning_rate": 9.75605844791566e-05, "loss": 0.1781, "step": 43690 }, { "epoch": 10.47, "learning_rate": 9.755947683386546e-05, "loss": 0.2071, "step": 43700 }, { "epoch": 10.48, "learning_rate": 9.755836894345236e-05, "loss": 0.2605, "step": 43710 }, { "epoch": 10.48, "learning_rate": 9.755726080792304e-05, "loss": 0.2061, "step": 43720 }, { "epoch": 10.48, "learning_rate": 9.75561524272832e-05, "loss": 0.2255, "step": 43730 }, { "epoch": 10.48, "learning_rate": 9.755504380153855e-05, "loss": 0.2344, "step": 43740 }, { "epoch": 10.48, "learning_rate": 9.75539349306948e-05, "loss": 0.1795, "step": 43750 }, { "epoch": 10.49, "learning_rate": 9.755282581475769e-05, "loss": 0.152, "step": 43760 }, { "epoch": 10.49, "learning_rate": 9.75517164537329e-05, "loss": 0.2225, "step": 43770 }, { "epoch": 10.49, "learning_rate": 9.755060684762619e-05, "loss": 0.2269, "step": 43780 }, { "epoch": 10.49, "learning_rate": 9.754949699644322e-05, "loss": 0.2639, "step": 43790 }, { "epoch": 10.5, "learning_rate": 9.754838690018976e-05, "loss": 0.1982, "step": 43800 }, { "epoch": 10.5, "learning_rate": 9.754727655887153e-05, "loss": 0.2596, "step": 43810 }, { "epoch": 10.5, "learning_rate": 9.754616597249422e-05, "loss": 0.2425, "step": 43820 }, { "epoch": 10.5, "learning_rate": 9.754505514106358e-05, "loss": 0.2292, "step": 43830 }, { "epoch": 10.51, "learning_rate": 9.754394406458533e-05, "loss": 0.2094, "step": 43840 }, { "epoch": 10.51, "learning_rate": 9.75428327430652e-05, "loss": 0.2861, "step": 43850 }, { "epoch": 10.51, "learning_rate": 9.75417211765089e-05, "loss": 0.3044, "step": 43860 }, { "epoch": 10.51, "learning_rate": 9.75406093649222e-05, "loss": 0.2375, "step": 43870 }, { "epoch": 10.51, "learning_rate": 9.753949730831077e-05, "loss": 0.2727, "step": 43880 }, { "epoch": 10.52, "learning_rate": 9.753838500668039e-05, "loss": 0.2735, "step": 43890 }, { "epoch": 10.52, "learning_rate": 9.753727246003676e-05, "loss": 0.2372, "step": 43900 }, { "epoch": 10.52, "learning_rate": 9.753615966838565e-05, "loss": 0.2618, "step": 43910 }, { "epoch": 10.52, "learning_rate": 9.753504663173276e-05, "loss": 0.2622, "step": 43920 }, { "epoch": 10.53, "learning_rate": 9.753393335008386e-05, "loss": 0.2706, "step": 43930 }, { "epoch": 10.53, "learning_rate": 9.753281982344466e-05, "loss": 0.3246, "step": 43940 }, { "epoch": 10.53, "learning_rate": 9.753170605182092e-05, "loss": 0.3307, "step": 43950 }, { "epoch": 10.53, "learning_rate": 9.753059203521834e-05, "loss": 0.2992, "step": 43960 }, { "epoch": 10.53, "learning_rate": 9.752947777364272e-05, "loss": 0.325, "step": 43970 }, { "epoch": 10.54, "learning_rate": 9.752836326709977e-05, "loss": 0.3321, "step": 43980 }, { "epoch": 10.54, "learning_rate": 9.752724851559523e-05, "loss": 0.315, "step": 43990 }, { "epoch": 10.54, "learning_rate": 9.752613351913485e-05, "loss": 0.3091, "step": 44000 }, { "epoch": 10.54, "learning_rate": 9.752501827772438e-05, "loss": 0.3232, "step": 44010 }, { "epoch": 10.55, "learning_rate": 9.752390279136958e-05, "loss": 0.3188, "step": 44020 }, { "epoch": 10.55, "learning_rate": 9.752278706007619e-05, "loss": 0.2497, "step": 44030 }, { "epoch": 10.55, "learning_rate": 9.752167108384995e-05, "loss": 0.2873, "step": 44040 }, { "epoch": 10.55, "learning_rate": 9.752055486269662e-05, "loss": 0.3492, "step": 44050 }, { "epoch": 10.56, "learning_rate": 9.751943839662197e-05, "loss": 0.3839, "step": 44060 }, { "epoch": 10.56, "learning_rate": 9.75183216856317e-05, "loss": 0.3136, "step": 44070 }, { "epoch": 10.56, "learning_rate": 9.751720472973164e-05, "loss": 0.3029, "step": 44080 }, { "epoch": 10.56, "learning_rate": 9.751608752892749e-05, "loss": 0.2964, "step": 44090 }, { "epoch": 10.56, "learning_rate": 9.751497008322503e-05, "loss": 0.2721, "step": 44100 }, { "epoch": 10.57, "learning_rate": 9.751385239263002e-05, "loss": 0.2844, "step": 44110 }, { "epoch": 10.57, "learning_rate": 9.751273445714823e-05, "loss": 0.2885, "step": 44120 }, { "epoch": 10.57, "learning_rate": 9.75116162767854e-05, "loss": 0.3175, "step": 44130 }, { "epoch": 10.57, "learning_rate": 9.75104978515473e-05, "loss": 0.2599, "step": 44140 }, { "epoch": 10.58, "learning_rate": 9.750937918143968e-05, "loss": 0.2901, "step": 44150 }, { "epoch": 10.58, "learning_rate": 9.750826026646836e-05, "loss": 0.3191, "step": 44160 }, { "epoch": 10.58, "learning_rate": 9.750714110663903e-05, "loss": 0.2054, "step": 44170 }, { "epoch": 10.58, "learning_rate": 9.750602170195753e-05, "loss": 0.2493, "step": 44180 }, { "epoch": 10.59, "learning_rate": 9.750490205242957e-05, "loss": 0.2405, "step": 44190 }, { "epoch": 10.59, "learning_rate": 9.750378215806097e-05, "loss": 0.2584, "step": 44200 }, { "epoch": 10.59, "learning_rate": 9.750266201885747e-05, "loss": 0.3308, "step": 44210 }, { "epoch": 10.59, "learning_rate": 9.750154163482485e-05, "loss": 0.3048, "step": 44220 }, { "epoch": 10.59, "learning_rate": 9.75004210059689e-05, "loss": 0.3018, "step": 44230 }, { "epoch": 10.6, "learning_rate": 9.749930013229536e-05, "loss": 0.2576, "step": 44240 }, { "epoch": 10.6, "learning_rate": 9.749817901381005e-05, "loss": 0.2295, "step": 44250 }, { "epoch": 10.6, "learning_rate": 9.749705765051872e-05, "loss": 0.2823, "step": 44260 }, { "epoch": 10.6, "learning_rate": 9.749593604242716e-05, "loss": 0.2251, "step": 44270 }, { "epoch": 10.61, "learning_rate": 9.749481418954114e-05, "loss": 0.237, "step": 44280 }, { "epoch": 10.61, "learning_rate": 9.749369209186648e-05, "loss": 0.2426, "step": 44290 }, { "epoch": 10.61, "learning_rate": 9.74925697494089e-05, "loss": 0.3264, "step": 44300 }, { "epoch": 10.61, "learning_rate": 9.749144716217424e-05, "loss": 0.2737, "step": 44310 }, { "epoch": 10.61, "learning_rate": 9.749032433016825e-05, "loss": 0.2884, "step": 44320 }, { "epoch": 10.62, "learning_rate": 9.748920125339673e-05, "loss": 0.2379, "step": 44330 }, { "epoch": 10.62, "learning_rate": 9.748807793186548e-05, "loss": 0.233, "step": 44340 }, { "epoch": 10.62, "learning_rate": 9.748695436558029e-05, "loss": 0.257, "step": 44350 }, { "epoch": 10.62, "learning_rate": 9.748583055454692e-05, "loss": 0.3333, "step": 44360 }, { "epoch": 10.63, "learning_rate": 9.748470649877119e-05, "loss": 0.3051, "step": 44370 }, { "epoch": 10.63, "learning_rate": 9.748358219825888e-05, "loss": 0.251, "step": 44380 }, { "epoch": 10.63, "learning_rate": 9.74824576530158e-05, "loss": 0.2797, "step": 44390 }, { "epoch": 10.63, "learning_rate": 9.748133286304774e-05, "loss": 0.2777, "step": 44400 }, { "epoch": 10.64, "learning_rate": 9.748020782836049e-05, "loss": 0.2512, "step": 44410 }, { "epoch": 10.64, "learning_rate": 9.747908254895983e-05, "loss": 0.2842, "step": 44420 }, { "epoch": 10.64, "learning_rate": 9.747795702485161e-05, "loss": 0.2053, "step": 44430 }, { "epoch": 10.64, "learning_rate": 9.74768312560416e-05, "loss": 0.215, "step": 44440 }, { "epoch": 10.64, "learning_rate": 9.747570524253559e-05, "loss": 0.3086, "step": 44450 }, { "epoch": 10.65, "learning_rate": 9.74745789843394e-05, "loss": 0.2923, "step": 44460 }, { "epoch": 10.65, "learning_rate": 9.747345248145884e-05, "loss": 0.2466, "step": 44470 }, { "epoch": 10.65, "learning_rate": 9.747232573389971e-05, "loss": 0.252, "step": 44480 }, { "epoch": 10.65, "learning_rate": 9.747119874166782e-05, "loss": 0.3392, "step": 44490 }, { "epoch": 10.66, "learning_rate": 9.747007150476897e-05, "loss": 0.2571, "step": 44500 }, { "epoch": 10.66, "learning_rate": 9.746894402320897e-05, "loss": 0.2654, "step": 44510 }, { "epoch": 10.66, "learning_rate": 9.746781629699364e-05, "loss": 0.2228, "step": 44520 }, { "epoch": 10.66, "learning_rate": 9.746668832612878e-05, "loss": 0.2565, "step": 44530 }, { "epoch": 10.66, "learning_rate": 9.746556011062023e-05, "loss": 0.2764, "step": 44540 }, { "epoch": 10.67, "learning_rate": 9.746443165047376e-05, "loss": 0.2418, "step": 44550 }, { "epoch": 10.67, "learning_rate": 9.746330294569523e-05, "loss": 0.2958, "step": 44560 }, { "epoch": 10.67, "learning_rate": 9.746217399629044e-05, "loss": 0.2938, "step": 44570 }, { "epoch": 10.67, "learning_rate": 9.746104480226522e-05, "loss": 0.2749, "step": 44580 }, { "epoch": 10.68, "learning_rate": 9.745991536362536e-05, "loss": 0.2703, "step": 44590 }, { "epoch": 10.68, "learning_rate": 9.74587856803767e-05, "loss": 0.3522, "step": 44600 }, { "epoch": 10.68, "learning_rate": 9.745765575252506e-05, "loss": 0.2518, "step": 44610 }, { "epoch": 10.68, "learning_rate": 9.745652558007627e-05, "loss": 0.3206, "step": 44620 }, { "epoch": 10.69, "learning_rate": 9.745539516303616e-05, "loss": 0.3011, "step": 44630 }, { "epoch": 10.69, "learning_rate": 9.745426450141053e-05, "loss": 0.1878, "step": 44640 }, { "epoch": 10.69, "learning_rate": 9.745313359520524e-05, "loss": 0.2719, "step": 44650 }, { "epoch": 10.69, "learning_rate": 9.745200244442609e-05, "loss": 0.2267, "step": 44660 }, { "epoch": 10.69, "learning_rate": 9.745087104907893e-05, "loss": 0.3046, "step": 44670 }, { "epoch": 10.7, "learning_rate": 9.744973940916959e-05, "loss": 0.1901, "step": 44680 }, { "epoch": 10.7, "learning_rate": 9.744860752470389e-05, "loss": 0.227, "step": 44690 }, { "epoch": 10.7, "learning_rate": 9.744747539568766e-05, "loss": 0.2854, "step": 44700 }, { "epoch": 10.7, "learning_rate": 9.744634302212676e-05, "loss": 0.2916, "step": 44710 }, { "epoch": 10.71, "learning_rate": 9.7445210404027e-05, "loss": 0.1854, "step": 44720 }, { "epoch": 10.71, "learning_rate": 9.744407754139424e-05, "loss": 0.2548, "step": 44730 }, { "epoch": 10.71, "learning_rate": 9.74429444342343e-05, "loss": 0.2775, "step": 44740 }, { "epoch": 10.71, "learning_rate": 9.744181108255303e-05, "loss": 0.2821, "step": 44750 }, { "epoch": 10.72, "learning_rate": 9.744067748635627e-05, "loss": 0.2761, "step": 44760 }, { "epoch": 10.72, "learning_rate": 9.743954364564987e-05, "loss": 0.2785, "step": 44770 }, { "epoch": 10.72, "learning_rate": 9.743840956043965e-05, "loss": 0.2608, "step": 44780 }, { "epoch": 10.72, "learning_rate": 9.743727523073147e-05, "loss": 0.2207, "step": 44790 }, { "epoch": 10.72, "learning_rate": 9.743614065653119e-05, "loss": 0.239, "step": 44800 }, { "epoch": 10.73, "learning_rate": 9.743500583784464e-05, "loss": 0.2898, "step": 44810 }, { "epoch": 10.73, "learning_rate": 9.743387077467767e-05, "loss": 0.2402, "step": 44820 }, { "epoch": 10.73, "learning_rate": 9.743273546703613e-05, "loss": 0.2056, "step": 44830 }, { "epoch": 10.73, "learning_rate": 9.743159991492589e-05, "loss": 0.2142, "step": 44840 }, { "epoch": 10.74, "learning_rate": 9.743046411835277e-05, "loss": 0.2745, "step": 44850 }, { "epoch": 10.74, "learning_rate": 9.742932807732265e-05, "loss": 0.2641, "step": 44860 }, { "epoch": 10.74, "learning_rate": 9.742819179184138e-05, "loss": 0.2803, "step": 44870 }, { "epoch": 10.74, "learning_rate": 9.74270552619148e-05, "loss": 0.2409, "step": 44880 }, { "epoch": 10.74, "learning_rate": 9.742591848754879e-05, "loss": 0.2426, "step": 44890 }, { "epoch": 10.75, "learning_rate": 9.74247814687492e-05, "loss": 0.2741, "step": 44900 }, { "epoch": 10.75, "learning_rate": 9.74236442055219e-05, "loss": 0.2132, "step": 44910 }, { "epoch": 10.75, "learning_rate": 9.742250669787272e-05, "loss": 0.2147, "step": 44920 }, { "epoch": 10.75, "learning_rate": 9.742136894580755e-05, "loss": 0.2613, "step": 44930 }, { "epoch": 10.76, "learning_rate": 9.742023094933226e-05, "loss": 0.2433, "step": 44940 }, { "epoch": 10.76, "learning_rate": 9.741909270845271e-05, "loss": 0.2306, "step": 44950 }, { "epoch": 10.76, "learning_rate": 9.741795422317474e-05, "loss": 0.316, "step": 44960 }, { "epoch": 10.76, "learning_rate": 9.741681549350424e-05, "loss": 0.2806, "step": 44970 }, { "epoch": 10.77, "learning_rate": 9.741567651944707e-05, "loss": 0.23, "step": 44980 }, { "epoch": 10.77, "learning_rate": 9.741453730100913e-05, "loss": 0.2136, "step": 44990 }, { "epoch": 10.77, "learning_rate": 9.741339783819625e-05, "loss": 0.1847, "step": 45000 }, { "epoch": 10.77, "learning_rate": 9.741225813101433e-05, "loss": 0.2553, "step": 45010 }, { "epoch": 10.77, "learning_rate": 9.741111817946924e-05, "loss": 0.2423, "step": 45020 }, { "epoch": 10.78, "learning_rate": 9.740997798356684e-05, "loss": 0.1646, "step": 45030 }, { "epoch": 10.78, "learning_rate": 9.740883754331302e-05, "loss": 0.2348, "step": 45040 }, { "epoch": 10.78, "learning_rate": 9.740769685871365e-05, "loss": 0.2504, "step": 45050 }, { "epoch": 10.78, "learning_rate": 9.740655592977462e-05, "loss": 0.2279, "step": 45060 }, { "epoch": 10.79, "learning_rate": 9.74054147565018e-05, "loss": 0.2054, "step": 45070 }, { "epoch": 10.79, "learning_rate": 9.740427333890109e-05, "loss": 0.1784, "step": 45080 }, { "epoch": 10.79, "learning_rate": 9.740313167697834e-05, "loss": 0.2344, "step": 45090 }, { "epoch": 10.79, "learning_rate": 9.740198977073946e-05, "loss": 0.2313, "step": 45100 }, { "epoch": 10.8, "learning_rate": 9.740084762019034e-05, "loss": 0.3031, "step": 45110 }, { "epoch": 10.8, "learning_rate": 9.739970522533685e-05, "loss": 0.2479, "step": 45120 }, { "epoch": 10.8, "learning_rate": 9.739856258618488e-05, "loss": 0.1925, "step": 45130 }, { "epoch": 10.8, "learning_rate": 9.739741970274031e-05, "loss": 0.2138, "step": 45140 }, { "epoch": 10.8, "learning_rate": 9.739627657500904e-05, "loss": 0.2298, "step": 45150 }, { "epoch": 10.81, "learning_rate": 9.7395133202997e-05, "loss": 0.2738, "step": 45160 }, { "epoch": 10.81, "learning_rate": 9.739398958671001e-05, "loss": 0.2125, "step": 45170 }, { "epoch": 10.81, "learning_rate": 9.739284572615403e-05, "loss": 0.2203, "step": 45180 }, { "epoch": 10.81, "learning_rate": 9.739170162133491e-05, "loss": 0.2542, "step": 45190 }, { "epoch": 10.82, "learning_rate": 9.739055727225856e-05, "loss": 0.2342, "step": 45200 }, { "epoch": 10.82, "learning_rate": 9.738941267893089e-05, "loss": 0.2044, "step": 45210 }, { "epoch": 10.82, "learning_rate": 9.73882678413578e-05, "loss": 0.189, "step": 45220 }, { "epoch": 10.82, "learning_rate": 9.738712275954517e-05, "loss": 0.183, "step": 45230 }, { "epoch": 10.82, "learning_rate": 9.738597743349892e-05, "loss": 0.291, "step": 45240 }, { "epoch": 10.83, "learning_rate": 9.738483186322494e-05, "loss": 0.2282, "step": 45250 }, { "epoch": 10.83, "learning_rate": 9.738368604872914e-05, "loss": 0.2524, "step": 45260 }, { "epoch": 10.83, "learning_rate": 9.738253999001743e-05, "loss": 0.2042, "step": 45270 }, { "epoch": 10.83, "learning_rate": 9.73813936870957e-05, "loss": 0.2684, "step": 45280 }, { "epoch": 10.84, "learning_rate": 9.738024713996989e-05, "loss": 0.1474, "step": 45290 }, { "epoch": 10.84, "learning_rate": 9.737910034864587e-05, "loss": 0.2577, "step": 45300 }, { "epoch": 10.84, "learning_rate": 9.73779533131296e-05, "loss": 0.1689, "step": 45310 }, { "epoch": 10.84, "learning_rate": 9.737680603342693e-05, "loss": 0.2733, "step": 45320 }, { "epoch": 10.85, "learning_rate": 9.737565850954382e-05, "loss": 0.2375, "step": 45330 }, { "epoch": 10.85, "learning_rate": 9.737451074148618e-05, "loss": 0.2781, "step": 45340 }, { "epoch": 10.85, "learning_rate": 9.73733627292599e-05, "loss": 0.221, "step": 45350 }, { "epoch": 10.85, "learning_rate": 9.737221447287093e-05, "loss": 0.2092, "step": 45360 }, { "epoch": 10.85, "learning_rate": 9.737106597232515e-05, "loss": 0.2469, "step": 45370 }, { "epoch": 10.86, "learning_rate": 9.736991722762852e-05, "loss": 0.2482, "step": 45380 }, { "epoch": 10.86, "learning_rate": 9.736876823878691e-05, "loss": 0.1618, "step": 45390 }, { "epoch": 10.86, "learning_rate": 9.73676190058063e-05, "loss": 0.2609, "step": 45400 }, { "epoch": 10.86, "learning_rate": 9.736646952869257e-05, "loss": 0.2827, "step": 45410 }, { "epoch": 10.87, "learning_rate": 9.736531980745167e-05, "loss": 0.2927, "step": 45420 }, { "epoch": 10.87, "learning_rate": 9.736416984208951e-05, "loss": 0.2149, "step": 45430 }, { "epoch": 10.87, "learning_rate": 9.736301963261203e-05, "loss": 0.2756, "step": 45440 }, { "epoch": 10.87, "learning_rate": 9.736186917902516e-05, "loss": 0.2124, "step": 45450 }, { "epoch": 10.88, "learning_rate": 9.736071848133481e-05, "loss": 0.2308, "step": 45460 }, { "epoch": 10.88, "learning_rate": 9.735956753954691e-05, "loss": 0.2098, "step": 45470 }, { "epoch": 10.88, "learning_rate": 9.735841635366742e-05, "loss": 0.1926, "step": 45480 }, { "epoch": 10.88, "learning_rate": 9.735726492370225e-05, "loss": 0.2567, "step": 45490 }, { "epoch": 10.88, "learning_rate": 9.735611324965733e-05, "loss": 0.1845, "step": 45500 }, { "epoch": 10.89, "learning_rate": 9.735496133153861e-05, "loss": 0.221, "step": 45510 }, { "epoch": 10.89, "learning_rate": 9.735380916935203e-05, "loss": 0.2006, "step": 45520 }, { "epoch": 10.89, "learning_rate": 9.735265676310352e-05, "loss": 0.228, "step": 45530 }, { "epoch": 10.89, "learning_rate": 9.735150411279903e-05, "loss": 0.2934, "step": 45540 }, { "epoch": 10.9, "learning_rate": 9.735035121844449e-05, "loss": 0.2509, "step": 45550 }, { "epoch": 10.9, "learning_rate": 9.734919808004583e-05, "loss": 0.218, "step": 45560 }, { "epoch": 10.9, "learning_rate": 9.734804469760902e-05, "loss": 0.2188, "step": 45570 }, { "epoch": 10.9, "learning_rate": 9.734689107113998e-05, "loss": 0.1592, "step": 45580 }, { "epoch": 10.9, "learning_rate": 9.734573720064468e-05, "loss": 0.2656, "step": 45590 }, { "epoch": 10.91, "learning_rate": 9.734458308612906e-05, "loss": 0.2632, "step": 45600 }, { "epoch": 10.91, "learning_rate": 9.734342872759906e-05, "loss": 0.2324, "step": 45610 }, { "epoch": 10.91, "learning_rate": 9.73422741250606e-05, "loss": 0.2668, "step": 45620 }, { "epoch": 10.91, "learning_rate": 9.73411192785197e-05, "loss": 0.2467, "step": 45630 }, { "epoch": 10.92, "learning_rate": 9.733996418798226e-05, "loss": 0.2268, "step": 45640 }, { "epoch": 10.92, "learning_rate": 9.733880885345425e-05, "loss": 0.2222, "step": 45650 }, { "epoch": 10.92, "learning_rate": 9.733765327494164e-05, "loss": 0.2379, "step": 45660 }, { "epoch": 10.92, "learning_rate": 9.733649745245034e-05, "loss": 0.2456, "step": 45670 }, { "epoch": 10.93, "learning_rate": 9.733534138598636e-05, "loss": 0.2798, "step": 45680 }, { "epoch": 10.93, "learning_rate": 9.733418507555563e-05, "loss": 0.2416, "step": 45690 }, { "epoch": 10.93, "learning_rate": 9.733302852116411e-05, "loss": 0.2947, "step": 45700 }, { "epoch": 10.93, "learning_rate": 9.733187172281777e-05, "loss": 0.1919, "step": 45710 }, { "epoch": 10.93, "learning_rate": 9.733071468052256e-05, "loss": 0.1651, "step": 45720 }, { "epoch": 10.94, "learning_rate": 9.732955739428447e-05, "loss": 0.2618, "step": 45730 }, { "epoch": 10.94, "learning_rate": 9.732839986410942e-05, "loss": 0.2451, "step": 45740 }, { "epoch": 10.94, "learning_rate": 9.732724209000341e-05, "loss": 0.2816, "step": 45750 }, { "epoch": 10.94, "learning_rate": 9.73260840719724e-05, "loss": 0.1905, "step": 45760 }, { "epoch": 10.95, "learning_rate": 9.732492581002236e-05, "loss": 0.2182, "step": 45770 }, { "epoch": 10.95, "learning_rate": 9.732376730415926e-05, "loss": 0.1791, "step": 45780 }, { "epoch": 10.95, "learning_rate": 9.732260855438907e-05, "loss": 0.245, "step": 45790 }, { "epoch": 11.0, "learning_rate": 9.732144956071774e-05, "loss": 0.1933, "step": 45800 }, { "epoch": 11.0, "learning_rate": 9.732029032315129e-05, "loss": 0.2473, "step": 45810 }, { "epoch": 11.01, "learning_rate": 9.731913084169564e-05, "loss": 0.1886, "step": 45820 }, { "epoch": 11.01, "learning_rate": 9.731797111635681e-05, "loss": 0.2094, "step": 45830 }, { "epoch": 11.01, "learning_rate": 9.731681114714076e-05, "loss": 0.1932, "step": 45840 }, { "epoch": 11.01, "learning_rate": 9.731565093405347e-05, "loss": 0.1693, "step": 45850 }, { "epoch": 11.02, "learning_rate": 9.731449047710093e-05, "loss": 0.2821, "step": 45860 }, { "epoch": 11.02, "learning_rate": 9.731332977628909e-05, "loss": 0.166, "step": 45870 }, { "epoch": 11.02, "learning_rate": 9.731216883162397e-05, "loss": 0.2441, "step": 45880 }, { "epoch": 11.02, "learning_rate": 9.731100764311152e-05, "loss": 0.2217, "step": 45890 }, { "epoch": 11.02, "learning_rate": 9.730984621075776e-05, "loss": 0.1624, "step": 45900 }, { "epoch": 11.03, "learning_rate": 9.730868453456863e-05, "loss": 0.2363, "step": 45910 }, { "epoch": 11.03, "learning_rate": 9.730752261455017e-05, "loss": 0.1734, "step": 45920 }, { "epoch": 11.03, "learning_rate": 9.730636045070834e-05, "loss": 0.1736, "step": 45930 }, { "epoch": 11.03, "learning_rate": 9.730519804304913e-05, "loss": 0.2096, "step": 45940 }, { "epoch": 11.04, "learning_rate": 9.730403539157853e-05, "loss": 0.139, "step": 45950 }, { "epoch": 11.04, "learning_rate": 9.730287249630253e-05, "loss": 0.2217, "step": 45960 }, { "epoch": 11.04, "learning_rate": 9.730170935722714e-05, "loss": 0.252, "step": 45970 }, { "epoch": 11.04, "learning_rate": 9.730054597435835e-05, "loss": 0.164, "step": 45980 }, { "epoch": 11.05, "learning_rate": 9.729938234770214e-05, "loss": 0.1998, "step": 45990 }, { "epoch": 11.05, "learning_rate": 9.729821847726452e-05, "loss": 0.2051, "step": 46000 }, { "epoch": 11.05, "learning_rate": 9.729705436305148e-05, "loss": 0.2372, "step": 46010 }, { "epoch": 11.05, "learning_rate": 9.729589000506904e-05, "loss": 0.1966, "step": 46020 }, { "epoch": 11.05, "learning_rate": 9.729472540332318e-05, "loss": 0.217, "step": 46030 }, { "epoch": 11.06, "learning_rate": 9.729356055781991e-05, "loss": 0.2187, "step": 46040 }, { "epoch": 11.06, "learning_rate": 9.729239546856523e-05, "loss": 0.2506, "step": 46050 }, { "epoch": 11.06, "learning_rate": 9.729123013556516e-05, "loss": 0.2336, "step": 46060 }, { "epoch": 11.06, "learning_rate": 9.729006455882569e-05, "loss": 0.2476, "step": 46070 }, { "epoch": 11.07, "learning_rate": 9.728889873835283e-05, "loss": 0.2543, "step": 46080 }, { "epoch": 11.07, "learning_rate": 9.728773267415258e-05, "loss": 0.1672, "step": 46090 }, { "epoch": 11.07, "learning_rate": 9.728656636623099e-05, "loss": 0.1762, "step": 46100 }, { "epoch": 11.07, "learning_rate": 9.728539981459402e-05, "loss": 0.2721, "step": 46110 }, { "epoch": 11.07, "learning_rate": 9.728423301924771e-05, "loss": 0.2691, "step": 46120 }, { "epoch": 11.08, "learning_rate": 9.728306598019805e-05, "loss": 0.2258, "step": 46130 }, { "epoch": 11.08, "learning_rate": 9.72818986974511e-05, "loss": 0.2129, "step": 46140 }, { "epoch": 11.08, "learning_rate": 9.728073117101285e-05, "loss": 0.226, "step": 46150 }, { "epoch": 11.08, "learning_rate": 9.727956340088928e-05, "loss": 0.2731, "step": 46160 }, { "epoch": 11.09, "learning_rate": 9.727839538708647e-05, "loss": 0.165, "step": 46170 }, { "epoch": 11.09, "learning_rate": 9.727722712961042e-05, "loss": 0.2036, "step": 46180 }, { "epoch": 11.09, "learning_rate": 9.727605862846713e-05, "loss": 0.202, "step": 46190 }, { "epoch": 11.09, "learning_rate": 9.727488988366264e-05, "loss": 0.1876, "step": 46200 }, { "epoch": 11.1, "learning_rate": 9.727372089520299e-05, "loss": 0.2081, "step": 46210 }, { "epoch": 11.1, "learning_rate": 9.727255166309418e-05, "loss": 0.2911, "step": 46220 }, { "epoch": 11.1, "learning_rate": 9.727138218734224e-05, "loss": 0.1762, "step": 46230 }, { "epoch": 11.1, "learning_rate": 9.72702124679532e-05, "loss": 0.2151, "step": 46240 }, { "epoch": 11.1, "learning_rate": 9.726904250493309e-05, "loss": 0.1847, "step": 46250 }, { "epoch": 11.11, "learning_rate": 9.726787229828795e-05, "loss": 0.1531, "step": 46260 }, { "epoch": 11.11, "learning_rate": 9.726670184802379e-05, "loss": 0.1968, "step": 46270 }, { "epoch": 11.11, "learning_rate": 9.726553115414665e-05, "loss": 0.1752, "step": 46280 }, { "epoch": 11.11, "learning_rate": 9.726436021666259e-05, "loss": 0.1906, "step": 46290 }, { "epoch": 11.12, "learning_rate": 9.726318903557759e-05, "loss": 0.2233, "step": 46300 }, { "epoch": 11.12, "learning_rate": 9.726201761089774e-05, "loss": 0.1932, "step": 46310 }, { "epoch": 11.12, "learning_rate": 9.726084594262906e-05, "loss": 0.2086, "step": 46320 }, { "epoch": 11.12, "learning_rate": 9.725967403077757e-05, "loss": 0.1735, "step": 46330 }, { "epoch": 11.12, "learning_rate": 9.725850187534933e-05, "loss": 0.1702, "step": 46340 }, { "epoch": 11.13, "learning_rate": 9.725732947635038e-05, "loss": 0.1702, "step": 46350 }, { "epoch": 11.13, "learning_rate": 9.725615683378675e-05, "loss": 0.1753, "step": 46360 }, { "epoch": 11.13, "learning_rate": 9.72549839476645e-05, "loss": 0.2409, "step": 46370 }, { "epoch": 11.13, "learning_rate": 9.725381081798967e-05, "loss": 0.2111, "step": 46380 }, { "epoch": 11.14, "learning_rate": 9.725263744476829e-05, "loss": 0.1481, "step": 46390 }, { "epoch": 11.14, "learning_rate": 9.725146382800643e-05, "loss": 0.2171, "step": 46400 }, { "epoch": 11.14, "learning_rate": 9.725028996771015e-05, "loss": 0.1806, "step": 46410 }, { "epoch": 11.14, "learning_rate": 9.724911586388545e-05, "loss": 0.1999, "step": 46420 }, { "epoch": 11.15, "learning_rate": 9.724794151653844e-05, "loss": 0.214, "step": 46430 }, { "epoch": 11.15, "learning_rate": 9.724676692567512e-05, "loss": 0.133, "step": 46440 }, { "epoch": 11.15, "learning_rate": 9.724559209130157e-05, "loss": 0.203, "step": 46450 }, { "epoch": 11.15, "learning_rate": 9.724441701342387e-05, "loss": 0.1918, "step": 46460 }, { "epoch": 11.15, "learning_rate": 9.724324169204801e-05, "loss": 0.1789, "step": 46470 }, { "epoch": 11.16, "learning_rate": 9.724206612718012e-05, "loss": 0.175, "step": 46480 }, { "epoch": 11.16, "learning_rate": 9.724089031882622e-05, "loss": 0.2588, "step": 46490 }, { "epoch": 11.16, "learning_rate": 9.723971426699236e-05, "loss": 0.1787, "step": 46500 }, { "epoch": 11.16, "learning_rate": 9.723853797168464e-05, "loss": 0.2433, "step": 46510 }, { "epoch": 11.17, "learning_rate": 9.723736143290909e-05, "loss": 0.2501, "step": 46520 }, { "epoch": 11.17, "learning_rate": 9.723618465067178e-05, "loss": 0.208, "step": 46530 }, { "epoch": 11.17, "learning_rate": 9.723500762497879e-05, "loss": 0.2267, "step": 46540 }, { "epoch": 11.17, "learning_rate": 9.723383035583617e-05, "loss": 0.2195, "step": 46550 }, { "epoch": 11.18, "learning_rate": 9.723265284324998e-05, "loss": 0.2221, "step": 46560 }, { "epoch": 11.18, "learning_rate": 9.723147508722632e-05, "loss": 0.21, "step": 46570 }, { "epoch": 11.18, "learning_rate": 9.723029708777124e-05, "loss": 0.194, "step": 46580 }, { "epoch": 11.18, "learning_rate": 9.722911884489081e-05, "loss": 0.2367, "step": 46590 }, { "epoch": 11.18, "learning_rate": 9.722794035859111e-05, "loss": 0.2079, "step": 46600 }, { "epoch": 11.19, "learning_rate": 9.72267616288782e-05, "loss": 0.178, "step": 46610 }, { "epoch": 11.19, "learning_rate": 9.722558265575819e-05, "loss": 0.1821, "step": 46620 }, { "epoch": 11.19, "learning_rate": 9.722440343923711e-05, "loss": 0.2504, "step": 46630 }, { "epoch": 11.19, "learning_rate": 9.722322397932107e-05, "loss": 0.1385, "step": 46640 }, { "epoch": 11.2, "learning_rate": 9.722204427601613e-05, "loss": 0.1848, "step": 46650 }, { "epoch": 11.2, "learning_rate": 9.72208643293284e-05, "loss": 0.189, "step": 46660 }, { "epoch": 11.2, "learning_rate": 9.721968413926392e-05, "loss": 0.1629, "step": 46670 }, { "epoch": 11.2, "learning_rate": 9.721850370582879e-05, "loss": 0.2516, "step": 46680 }, { "epoch": 11.2, "learning_rate": 9.72173230290291e-05, "loss": 0.18, "step": 46690 }, { "epoch": 11.21, "learning_rate": 9.721614210887096e-05, "loss": 0.1524, "step": 46700 }, { "epoch": 11.21, "learning_rate": 9.72149609453604e-05, "loss": 0.2448, "step": 46710 }, { "epoch": 11.21, "learning_rate": 9.721377953850355e-05, "loss": 0.1158, "step": 46720 }, { "epoch": 11.21, "learning_rate": 9.721259788830648e-05, "loss": 0.2158, "step": 46730 }, { "epoch": 11.22, "learning_rate": 9.721141599477528e-05, "loss": 0.1686, "step": 46740 }, { "epoch": 11.22, "learning_rate": 9.721023385791605e-05, "loss": 0.2432, "step": 46750 }, { "epoch": 11.22, "learning_rate": 9.720905147773489e-05, "loss": 0.2425, "step": 46760 }, { "epoch": 11.22, "learning_rate": 9.720786885423787e-05, "loss": 0.2344, "step": 46770 }, { "epoch": 11.23, "learning_rate": 9.72066859874311e-05, "loss": 0.145, "step": 46780 }, { "epoch": 11.23, "learning_rate": 9.720550287732069e-05, "loss": 0.169, "step": 46790 }, { "epoch": 11.23, "learning_rate": 9.720431952391271e-05, "loss": 0.2056, "step": 46800 }, { "epoch": 11.23, "learning_rate": 9.720313592721329e-05, "loss": 0.1994, "step": 46810 }, { "epoch": 11.23, "learning_rate": 9.72019520872285e-05, "loss": 0.1833, "step": 46820 }, { "epoch": 11.24, "learning_rate": 9.720076800396445e-05, "loss": 0.1924, "step": 46830 }, { "epoch": 11.24, "learning_rate": 9.719958367742725e-05, "loss": 0.2329, "step": 46840 }, { "epoch": 11.24, "learning_rate": 9.719839910762301e-05, "loss": 0.1748, "step": 46850 }, { "epoch": 11.24, "learning_rate": 9.719721429455782e-05, "loss": 0.1892, "step": 46860 }, { "epoch": 11.25, "learning_rate": 9.719602923823779e-05, "loss": 0.1672, "step": 46870 }, { "epoch": 11.25, "learning_rate": 9.719484393866903e-05, "loss": 0.1509, "step": 46880 }, { "epoch": 11.25, "learning_rate": 9.719365839585765e-05, "loss": 0.1817, "step": 46890 }, { "epoch": 11.25, "learning_rate": 9.719247260980977e-05, "loss": 0.1948, "step": 46900 }, { "epoch": 11.26, "learning_rate": 9.71912865805315e-05, "loss": 0.21, "step": 46910 }, { "epoch": 11.26, "learning_rate": 9.719010030802891e-05, "loss": 0.2088, "step": 46920 }, { "epoch": 11.26, "learning_rate": 9.718891379230818e-05, "loss": 0.1658, "step": 46930 }, { "epoch": 11.26, "learning_rate": 9.718772703337539e-05, "loss": 0.1434, "step": 46940 }, { "epoch": 11.26, "learning_rate": 9.718654003123664e-05, "loss": 0.1667, "step": 46950 }, { "epoch": 11.27, "learning_rate": 9.718535278589808e-05, "loss": 0.2759, "step": 46960 }, { "epoch": 11.27, "learning_rate": 9.718416529736583e-05, "loss": 0.1456, "step": 46970 }, { "epoch": 11.27, "learning_rate": 9.718297756564598e-05, "loss": 0.1642, "step": 46980 }, { "epoch": 11.27, "learning_rate": 9.718178959074469e-05, "loss": 0.2126, "step": 46990 }, { "epoch": 11.28, "learning_rate": 9.718060137266804e-05, "loss": 0.2251, "step": 47000 }, { "epoch": 11.28, "learning_rate": 9.717941291142219e-05, "loss": 0.2724, "step": 47010 }, { "epoch": 11.28, "learning_rate": 9.717822420701324e-05, "loss": 0.1398, "step": 47020 }, { "epoch": 11.28, "learning_rate": 9.717703525944733e-05, "loss": 0.2233, "step": 47030 }, { "epoch": 11.28, "learning_rate": 9.71758460687306e-05, "loss": 0.219, "step": 47040 }, { "epoch": 11.29, "learning_rate": 9.717465663486916e-05, "loss": 0.2155, "step": 47050 }, { "epoch": 11.29, "learning_rate": 9.717346695786913e-05, "loss": 0.1941, "step": 47060 }, { "epoch": 11.29, "learning_rate": 9.717227703773666e-05, "loss": 0.2101, "step": 47070 }, { "epoch": 11.29, "learning_rate": 9.717108687447789e-05, "loss": 0.1736, "step": 47080 }, { "epoch": 11.3, "learning_rate": 9.716989646809894e-05, "loss": 0.196, "step": 47090 }, { "epoch": 11.3, "learning_rate": 9.716870581860596e-05, "loss": 0.177, "step": 47100 }, { "epoch": 11.3, "learning_rate": 9.716751492600506e-05, "loss": 0.1941, "step": 47110 }, { "epoch": 11.3, "learning_rate": 9.716632379030239e-05, "loss": 0.1766, "step": 47120 }, { "epoch": 11.31, "learning_rate": 9.71651324115041e-05, "loss": 0.2436, "step": 47130 }, { "epoch": 11.31, "learning_rate": 9.716394078961634e-05, "loss": 0.2343, "step": 47140 }, { "epoch": 11.31, "learning_rate": 9.716274892464522e-05, "loss": 0.1546, "step": 47150 }, { "epoch": 11.31, "learning_rate": 9.71615568165969e-05, "loss": 0.2013, "step": 47160 }, { "epoch": 11.31, "learning_rate": 9.716036446547752e-05, "loss": 0.1745, "step": 47170 }, { "epoch": 11.32, "learning_rate": 9.715917187129322e-05, "loss": 0.1492, "step": 47180 }, { "epoch": 11.32, "learning_rate": 9.715797903405018e-05, "loss": 0.2316, "step": 47190 }, { "epoch": 11.32, "learning_rate": 9.715678595375449e-05, "loss": 0.1802, "step": 47200 }, { "epoch": 11.32, "learning_rate": 9.715559263041236e-05, "loss": 0.1671, "step": 47210 }, { "epoch": 11.33, "learning_rate": 9.71543990640299e-05, "loss": 0.2082, "step": 47220 }, { "epoch": 11.33, "learning_rate": 9.715320525461326e-05, "loss": 0.1678, "step": 47230 }, { "epoch": 11.33, "learning_rate": 9.715201120216861e-05, "loss": 0.1536, "step": 47240 }, { "epoch": 11.33, "learning_rate": 9.715081690670212e-05, "loss": 0.2338, "step": 47250 }, { "epoch": 11.34, "learning_rate": 9.71496223682199e-05, "loss": 0.1438, "step": 47260 }, { "epoch": 11.34, "learning_rate": 9.714842758672814e-05, "loss": 0.2145, "step": 47270 }, { "epoch": 11.34, "learning_rate": 9.714723256223299e-05, "loss": 0.1793, "step": 47280 }, { "epoch": 11.34, "learning_rate": 9.714603729474063e-05, "loss": 0.1651, "step": 47290 }, { "epoch": 11.34, "learning_rate": 9.714484178425718e-05, "loss": 0.2326, "step": 47300 }, { "epoch": 11.35, "learning_rate": 9.714364603078882e-05, "loss": 0.1672, "step": 47310 }, { "epoch": 11.35, "learning_rate": 9.714245003434171e-05, "loss": 0.1385, "step": 47320 }, { "epoch": 11.35, "learning_rate": 9.714125379492203e-05, "loss": 0.2736, "step": 47330 }, { "epoch": 11.35, "learning_rate": 9.714005731253592e-05, "loss": 0.2399, "step": 47340 }, { "epoch": 11.36, "learning_rate": 9.713886058718958e-05, "loss": 0.1752, "step": 47350 }, { "epoch": 11.36, "learning_rate": 9.713766361888916e-05, "loss": 0.2496, "step": 47360 }, { "epoch": 11.36, "learning_rate": 9.713646640764081e-05, "loss": 0.1764, "step": 47370 }, { "epoch": 11.36, "learning_rate": 9.713526895345074e-05, "loss": 0.2306, "step": 47380 }, { "epoch": 11.36, "learning_rate": 9.713407125632508e-05, "loss": 0.1983, "step": 47390 }, { "epoch": 11.37, "learning_rate": 9.713287331627001e-05, "loss": 0.186, "step": 47400 }, { "epoch": 11.37, "learning_rate": 9.713167513329175e-05, "loss": 0.1232, "step": 47410 }, { "epoch": 11.37, "learning_rate": 9.713047670739642e-05, "loss": 0.1776, "step": 47420 }, { "epoch": 11.37, "learning_rate": 9.712927803859022e-05, "loss": 0.2096, "step": 47430 }, { "epoch": 11.38, "learning_rate": 9.712807912687933e-05, "loss": 0.1401, "step": 47440 }, { "epoch": 11.38, "learning_rate": 9.712687997226994e-05, "loss": 0.1525, "step": 47450 }, { "epoch": 11.38, "learning_rate": 9.71256805747682e-05, "loss": 0.2069, "step": 47460 }, { "epoch": 11.38, "learning_rate": 9.712448093438032e-05, "loss": 0.1759, "step": 47470 }, { "epoch": 11.39, "learning_rate": 9.712328105111248e-05, "loss": 0.2046, "step": 47480 }, { "epoch": 11.39, "learning_rate": 9.712208092497084e-05, "loss": 0.1754, "step": 47490 }, { "epoch": 11.39, "learning_rate": 9.712088055596161e-05, "loss": 0.1416, "step": 47500 }, { "epoch": 11.39, "learning_rate": 9.711967994409094e-05, "loss": 0.1687, "step": 47510 }, { "epoch": 11.39, "learning_rate": 9.711847908936506e-05, "loss": 0.1675, "step": 47520 }, { "epoch": 11.4, "learning_rate": 9.711727799179016e-05, "loss": 0.1696, "step": 47530 }, { "epoch": 11.4, "learning_rate": 9.71160766513724e-05, "loss": 0.1565, "step": 47540 }, { "epoch": 11.4, "learning_rate": 9.7114875068118e-05, "loss": 0.1885, "step": 47550 }, { "epoch": 11.4, "learning_rate": 9.711367324203313e-05, "loss": 0.1239, "step": 47560 }, { "epoch": 11.41, "learning_rate": 9.711247117312401e-05, "loss": 0.211, "step": 47570 }, { "epoch": 11.41, "learning_rate": 9.711126886139681e-05, "loss": 0.1553, "step": 47580 }, { "epoch": 11.41, "learning_rate": 9.711006630685773e-05, "loss": 0.1878, "step": 47590 }, { "epoch": 11.41, "learning_rate": 9.710886350951298e-05, "loss": 0.1702, "step": 47600 }, { "epoch": 11.42, "learning_rate": 9.710766046936876e-05, "loss": 0.2302, "step": 47610 }, { "epoch": 11.42, "learning_rate": 9.710645718643125e-05, "loss": 0.1558, "step": 47620 }, { "epoch": 11.42, "learning_rate": 9.710525366070667e-05, "loss": 0.1935, "step": 47630 }, { "epoch": 11.42, "learning_rate": 9.710404989220123e-05, "loss": 0.1513, "step": 47640 }, { "epoch": 11.42, "learning_rate": 9.710284588092111e-05, "loss": 0.2558, "step": 47650 }, { "epoch": 11.43, "learning_rate": 9.710164162687253e-05, "loss": 0.1617, "step": 47660 }, { "epoch": 11.43, "learning_rate": 9.71004371300617e-05, "loss": 0.2416, "step": 47670 }, { "epoch": 11.43, "learning_rate": 9.709923239049483e-05, "loss": 0.1886, "step": 47680 }, { "epoch": 11.43, "learning_rate": 9.70980274081781e-05, "loss": 0.1801, "step": 47690 }, { "epoch": 11.44, "learning_rate": 9.709682218311776e-05, "loss": 0.1718, "step": 47700 }, { "epoch": 11.44, "learning_rate": 9.709561671532001e-05, "loss": 0.1724, "step": 47710 }, { "epoch": 11.44, "learning_rate": 9.709441100479104e-05, "loss": 0.1219, "step": 47720 }, { "epoch": 11.44, "learning_rate": 9.70932050515371e-05, "loss": 0.2029, "step": 47730 }, { "epoch": 11.44, "learning_rate": 9.709199885556438e-05, "loss": 0.1969, "step": 47740 }, { "epoch": 11.45, "learning_rate": 9.709079241687911e-05, "loss": 0.2217, "step": 47750 }, { "epoch": 11.45, "learning_rate": 9.70895857354875e-05, "loss": 0.1863, "step": 47760 }, { "epoch": 11.45, "learning_rate": 9.708837881139576e-05, "loss": 0.1919, "step": 47770 }, { "epoch": 11.45, "learning_rate": 9.708717164461013e-05, "loss": 0.179, "step": 47780 }, { "epoch": 11.46, "learning_rate": 9.708596423513683e-05, "loss": 0.2114, "step": 47790 }, { "epoch": 11.46, "learning_rate": 9.708475658298206e-05, "loss": 0.1772, "step": 47800 }, { "epoch": 11.46, "learning_rate": 9.708354868815209e-05, "loss": 0.1831, "step": 47810 }, { "epoch": 11.46, "learning_rate": 9.708234055065308e-05, "loss": 0.2072, "step": 47820 }, { "epoch": 11.47, "learning_rate": 9.708113217049131e-05, "loss": 0.202, "step": 47830 }, { "epoch": 11.47, "learning_rate": 9.707992354767299e-05, "loss": 0.1801, "step": 47840 }, { "epoch": 11.47, "learning_rate": 9.707871468220435e-05, "loss": 0.2634, "step": 47850 }, { "epoch": 11.47, "learning_rate": 9.707750557409163e-05, "loss": 0.1736, "step": 47860 }, { "epoch": 11.47, "learning_rate": 9.707629622334104e-05, "loss": 0.203, "step": 47870 }, { "epoch": 11.48, "learning_rate": 9.707508662995885e-05, "loss": 0.1544, "step": 47880 }, { "epoch": 11.48, "learning_rate": 9.707387679395124e-05, "loss": 0.1868, "step": 47890 }, { "epoch": 11.48, "learning_rate": 9.707266671532449e-05, "loss": 0.1018, "step": 47900 }, { "epoch": 11.48, "learning_rate": 9.707145639408483e-05, "loss": 0.1079, "step": 47910 }, { "epoch": 11.49, "learning_rate": 9.707024583023847e-05, "loss": 0.1753, "step": 47920 }, { "epoch": 11.49, "learning_rate": 9.706903502379169e-05, "loss": 0.1856, "step": 47930 }, { "epoch": 11.49, "learning_rate": 9.706782397475069e-05, "loss": 0.209, "step": 47940 }, { "epoch": 11.49, "learning_rate": 9.706661268312175e-05, "loss": 0.1714, "step": 47950 }, { "epoch": 11.5, "learning_rate": 9.706540114891108e-05, "loss": 0.2764, "step": 47960 }, { "epoch": 11.5, "learning_rate": 9.706418937212495e-05, "loss": 0.2028, "step": 47970 }, { "epoch": 11.5, "learning_rate": 9.706297735276958e-05, "loss": 0.1413, "step": 47980 }, { "epoch": 11.5, "learning_rate": 9.706176509085125e-05, "loss": 0.1706, "step": 47990 }, { "epoch": 11.5, "learning_rate": 9.706055258637619e-05, "loss": 0.1977, "step": 48000 }, { "epoch": 11.51, "learning_rate": 9.705933983935062e-05, "loss": 0.1846, "step": 48010 }, { "epoch": 11.51, "learning_rate": 9.705812684978085e-05, "loss": 0.1738, "step": 48020 }, { "epoch": 11.51, "learning_rate": 9.705691361767308e-05, "loss": 0.1665, "step": 48030 }, { "epoch": 11.51, "learning_rate": 9.70557001430336e-05, "loss": 0.2018, "step": 48040 }, { "epoch": 11.52, "learning_rate": 9.705448642586866e-05, "loss": 0.201, "step": 48050 }, { "epoch": 11.52, "learning_rate": 9.705327246618447e-05, "loss": 0.1699, "step": 48060 }, { "epoch": 11.52, "learning_rate": 9.705205826398734e-05, "loss": 0.194, "step": 48070 }, { "epoch": 11.52, "learning_rate": 9.70508438192835e-05, "loss": 0.1709, "step": 48080 }, { "epoch": 11.52, "learning_rate": 9.704962913207922e-05, "loss": 0.1944, "step": 48090 }, { "epoch": 11.53, "learning_rate": 9.704841420238076e-05, "loss": 0.1883, "step": 48100 }, { "epoch": 11.53, "learning_rate": 9.704719903019439e-05, "loss": 0.2111, "step": 48110 }, { "epoch": 11.53, "learning_rate": 9.704598361552635e-05, "loss": 0.2532, "step": 48120 }, { "epoch": 11.53, "learning_rate": 9.704476795838292e-05, "loss": 0.1981, "step": 48130 }, { "epoch": 11.54, "learning_rate": 9.704355205877036e-05, "loss": 0.2851, "step": 48140 }, { "epoch": 11.54, "learning_rate": 9.704233591669494e-05, "loss": 0.305, "step": 48150 }, { "epoch": 11.54, "learning_rate": 9.704111953216293e-05, "loss": 0.2922, "step": 48160 }, { "epoch": 11.54, "learning_rate": 9.70399029051806e-05, "loss": 0.2902, "step": 48170 }, { "epoch": 11.55, "learning_rate": 9.703868603575421e-05, "loss": 0.2782, "step": 48180 }, { "epoch": 11.55, "learning_rate": 9.703746892389005e-05, "loss": 0.3698, "step": 48190 }, { "epoch": 11.55, "learning_rate": 9.703625156959438e-05, "loss": 0.2988, "step": 48200 }, { "epoch": 11.55, "learning_rate": 9.703503397287346e-05, "loss": 0.3271, "step": 48210 }, { "epoch": 11.55, "learning_rate": 9.70338161337336e-05, "loss": 0.3151, "step": 48220 }, { "epoch": 11.56, "learning_rate": 9.703259805218105e-05, "loss": 0.2702, "step": 48230 }, { "epoch": 11.56, "learning_rate": 9.703137972822209e-05, "loss": 0.2584, "step": 48240 }, { "epoch": 11.56, "learning_rate": 9.703016116186301e-05, "loss": 0.2473, "step": 48250 }, { "epoch": 11.56, "learning_rate": 9.70289423531101e-05, "loss": 0.2813, "step": 48260 }, { "epoch": 11.57, "learning_rate": 9.70277233019696e-05, "loss": 0.2863, "step": 48270 }, { "epoch": 11.57, "learning_rate": 9.702650400844785e-05, "loss": 0.2379, "step": 48280 }, { "epoch": 11.57, "learning_rate": 9.70252844725511e-05, "loss": 0.247, "step": 48290 }, { "epoch": 11.57, "learning_rate": 9.702406469428564e-05, "loss": 0.2475, "step": 48300 }, { "epoch": 11.58, "learning_rate": 9.702284467365774e-05, "loss": 0.311, "step": 48310 }, { "epoch": 11.58, "learning_rate": 9.702162441067372e-05, "loss": 0.2229, "step": 48320 }, { "epoch": 11.58, "learning_rate": 9.702040390533987e-05, "loss": 0.2133, "step": 48330 }, { "epoch": 11.58, "learning_rate": 9.701918315766243e-05, "loss": 0.2651, "step": 48340 }, { "epoch": 11.58, "learning_rate": 9.701796216764774e-05, "loss": 0.2397, "step": 48350 }, { "epoch": 11.59, "learning_rate": 9.701674093530208e-05, "loss": 0.3088, "step": 48360 }, { "epoch": 11.59, "learning_rate": 9.701551946063177e-05, "loss": 0.169, "step": 48370 }, { "epoch": 11.59, "learning_rate": 9.701429774364306e-05, "loss": 0.3094, "step": 48380 }, { "epoch": 11.59, "learning_rate": 9.701307578434225e-05, "loss": 0.3244, "step": 48390 }, { "epoch": 11.6, "learning_rate": 9.701185358273567e-05, "loss": 0.2117, "step": 48400 }, { "epoch": 11.6, "learning_rate": 9.701063113882962e-05, "loss": 0.2842, "step": 48410 }, { "epoch": 11.6, "learning_rate": 9.700940845263035e-05, "loss": 0.3492, "step": 48420 }, { "epoch": 11.6, "learning_rate": 9.700818552414421e-05, "loss": 0.3227, "step": 48430 }, { "epoch": 11.6, "learning_rate": 9.70069623533775e-05, "loss": 0.3123, "step": 48440 }, { "epoch": 11.61, "learning_rate": 9.700573894033652e-05, "loss": 0.3152, "step": 48450 }, { "epoch": 11.61, "learning_rate": 9.700451528502755e-05, "loss": 0.2563, "step": 48460 }, { "epoch": 11.61, "learning_rate": 9.700329138745692e-05, "loss": 0.2328, "step": 48470 }, { "epoch": 11.61, "learning_rate": 9.700206724763093e-05, "loss": 0.3038, "step": 48480 }, { "epoch": 11.62, "learning_rate": 9.700084286555589e-05, "loss": 0.3175, "step": 48490 }, { "epoch": 11.62, "learning_rate": 9.699961824123811e-05, "loss": 0.2632, "step": 48500 }, { "epoch": 11.62, "learning_rate": 9.699839337468392e-05, "loss": 0.2578, "step": 48510 }, { "epoch": 11.62, "learning_rate": 9.699716826589962e-05, "loss": 0.239, "step": 48520 }, { "epoch": 11.63, "learning_rate": 9.69959429148915e-05, "loss": 0.198, "step": 48530 }, { "epoch": 11.63, "learning_rate": 9.699471732166592e-05, "loss": 0.2165, "step": 48540 }, { "epoch": 11.63, "learning_rate": 9.699349148622915e-05, "loss": 0.2458, "step": 48550 }, { "epoch": 11.63, "learning_rate": 9.699226540858755e-05, "loss": 0.2333, "step": 48560 }, { "epoch": 11.63, "learning_rate": 9.699103908874742e-05, "loss": 0.2109, "step": 48570 }, { "epoch": 11.64, "learning_rate": 9.698981252671509e-05, "loss": 0.256, "step": 48580 }, { "epoch": 11.64, "learning_rate": 9.698858572249684e-05, "loss": 0.2478, "step": 48590 }, { "epoch": 11.64, "learning_rate": 9.698735867609906e-05, "loss": 0.2532, "step": 48600 }, { "epoch": 11.64, "learning_rate": 9.698613138752804e-05, "loss": 0.1968, "step": 48610 }, { "epoch": 11.65, "learning_rate": 9.698490385679009e-05, "loss": 0.2173, "step": 48620 }, { "epoch": 11.65, "learning_rate": 9.698367608389156e-05, "loss": 0.2604, "step": 48630 }, { "epoch": 11.65, "learning_rate": 9.698244806883876e-05, "loss": 0.2249, "step": 48640 }, { "epoch": 11.65, "learning_rate": 9.698121981163803e-05, "loss": 0.3011, "step": 48650 }, { "epoch": 11.66, "learning_rate": 9.697999131229571e-05, "loss": 0.247, "step": 48660 }, { "epoch": 11.66, "learning_rate": 9.697876257081813e-05, "loss": 0.2473, "step": 48670 }, { "epoch": 11.66, "learning_rate": 9.697753358721161e-05, "loss": 0.2386, "step": 48680 }, { "epoch": 11.66, "learning_rate": 9.697630436148248e-05, "loss": 0.2247, "step": 48690 }, { "epoch": 11.66, "learning_rate": 9.69750748936371e-05, "loss": 0.2486, "step": 48700 }, { "epoch": 11.67, "learning_rate": 9.697384518368177e-05, "loss": 0.2692, "step": 48710 }, { "epoch": 11.67, "learning_rate": 9.697261523162287e-05, "loss": 0.2436, "step": 48720 }, { "epoch": 11.67, "learning_rate": 9.69713850374667e-05, "loss": 0.2177, "step": 48730 }, { "epoch": 11.67, "learning_rate": 9.697015460121963e-05, "loss": 0.1896, "step": 48740 }, { "epoch": 11.68, "learning_rate": 9.696892392288798e-05, "loss": 0.2913, "step": 48750 }, { "epoch": 11.68, "learning_rate": 9.696769300247812e-05, "loss": 0.2624, "step": 48760 }, { "epoch": 11.68, "learning_rate": 9.696646183999637e-05, "loss": 0.2033, "step": 48770 }, { "epoch": 11.68, "learning_rate": 9.69652304354491e-05, "loss": 0.2138, "step": 48780 }, { "epoch": 11.68, "learning_rate": 9.696399878884262e-05, "loss": 0.2508, "step": 48790 }, { "epoch": 11.69, "learning_rate": 9.696276690018329e-05, "loss": 0.2376, "step": 48800 }, { "epoch": 11.69, "learning_rate": 9.696153476947749e-05, "loss": 0.2204, "step": 48810 }, { "epoch": 11.69, "learning_rate": 9.696030239673152e-05, "loss": 0.247, "step": 48820 }, { "epoch": 11.69, "learning_rate": 9.695906978195179e-05, "loss": 0.225, "step": 48830 }, { "epoch": 11.7, "learning_rate": 9.69578369251446e-05, "loss": 0.1832, "step": 48840 }, { "epoch": 11.7, "learning_rate": 9.695660382631632e-05, "loss": 0.2318, "step": 48850 }, { "epoch": 11.7, "learning_rate": 9.695537048547334e-05, "loss": 0.1847, "step": 48860 }, { "epoch": 11.7, "learning_rate": 9.695413690262196e-05, "loss": 0.1801, "step": 48870 }, { "epoch": 11.71, "learning_rate": 9.695290307776859e-05, "loss": 0.245, "step": 48880 }, { "epoch": 11.71, "learning_rate": 9.695166901091954e-05, "loss": 0.2005, "step": 48890 }, { "epoch": 11.71, "learning_rate": 9.69504347020812e-05, "loss": 0.1425, "step": 48900 }, { "epoch": 11.71, "learning_rate": 9.694920015125994e-05, "loss": 0.2888, "step": 48910 }, { "epoch": 11.71, "learning_rate": 9.69479653584621e-05, "loss": 0.2683, "step": 48920 }, { "epoch": 11.72, "learning_rate": 9.694673032369407e-05, "loss": 0.2812, "step": 48930 }, { "epoch": 11.72, "learning_rate": 9.694549504696219e-05, "loss": 0.2102, "step": 48940 }, { "epoch": 11.72, "learning_rate": 9.694425952827283e-05, "loss": 0.2106, "step": 48950 }, { "epoch": 11.72, "learning_rate": 9.694302376763236e-05, "loss": 0.1496, "step": 48960 }, { "epoch": 11.73, "learning_rate": 9.694178776504717e-05, "loss": 0.2824, "step": 48970 }, { "epoch": 11.73, "learning_rate": 9.69405515205236e-05, "loss": 0.2436, "step": 48980 }, { "epoch": 11.73, "learning_rate": 9.693931503406805e-05, "loss": 0.2547, "step": 48990 }, { "epoch": 11.73, "learning_rate": 9.693807830568686e-05, "loss": 0.1706, "step": 49000 }, { "epoch": 11.74, "learning_rate": 9.693684133538643e-05, "loss": 0.2612, "step": 49010 }, { "epoch": 11.74, "learning_rate": 9.693560412317312e-05, "loss": 0.1545, "step": 49020 }, { "epoch": 11.74, "learning_rate": 9.693436666905333e-05, "loss": 0.2493, "step": 49030 }, { "epoch": 11.74, "learning_rate": 9.693312897303341e-05, "loss": 0.2358, "step": 49040 }, { "epoch": 11.74, "learning_rate": 9.693189103511976e-05, "loss": 0.197, "step": 49050 }, { "epoch": 11.75, "learning_rate": 9.693065285531875e-05, "loss": 0.235, "step": 49060 }, { "epoch": 11.75, "learning_rate": 9.692941443363675e-05, "loss": 0.2033, "step": 49070 }, { "epoch": 11.75, "learning_rate": 9.692817577008016e-05, "loss": 0.2187, "step": 49080 }, { "epoch": 11.75, "learning_rate": 9.692693686465537e-05, "loss": 0.2399, "step": 49090 }, { "epoch": 11.76, "learning_rate": 9.692569771736874e-05, "loss": 0.1932, "step": 49100 }, { "epoch": 11.76, "learning_rate": 9.69244583282267e-05, "loss": 0.2419, "step": 49110 }, { "epoch": 11.76, "learning_rate": 9.692321869723558e-05, "loss": 0.206, "step": 49120 }, { "epoch": 11.76, "learning_rate": 9.692197882440181e-05, "loss": 0.1916, "step": 49130 }, { "epoch": 11.76, "learning_rate": 9.692073870973177e-05, "loss": 0.188, "step": 49140 }, { "epoch": 11.77, "learning_rate": 9.691949835323184e-05, "loss": 0.2588, "step": 49150 }, { "epoch": 11.77, "learning_rate": 9.691825775490844e-05, "loss": 0.2478, "step": 49160 }, { "epoch": 11.77, "learning_rate": 9.691701691476793e-05, "loss": 0.2785, "step": 49170 }, { "epoch": 11.77, "learning_rate": 9.691577583281675e-05, "loss": 0.2427, "step": 49180 }, { "epoch": 11.78, "learning_rate": 9.691453450906124e-05, "loss": 0.1986, "step": 49190 }, { "epoch": 11.78, "learning_rate": 9.691329294350784e-05, "loss": 0.2216, "step": 49200 }, { "epoch": 11.78, "learning_rate": 9.691205113616293e-05, "loss": 0.2186, "step": 49210 }, { "epoch": 11.78, "learning_rate": 9.691080908703292e-05, "loss": 0.1944, "step": 49220 }, { "epoch": 11.79, "learning_rate": 9.690956679612421e-05, "loss": 0.2649, "step": 49230 }, { "epoch": 11.79, "learning_rate": 9.69083242634432e-05, "loss": 0.2178, "step": 49240 }, { "epoch": 11.79, "learning_rate": 9.69070814889963e-05, "loss": 0.2209, "step": 49250 }, { "epoch": 11.79, "learning_rate": 9.690583847278989e-05, "loss": 0.2276, "step": 49260 }, { "epoch": 11.79, "learning_rate": 9.690459521483042e-05, "loss": 0.2712, "step": 49270 }, { "epoch": 11.8, "learning_rate": 9.690335171512426e-05, "loss": 0.1609, "step": 49280 }, { "epoch": 11.8, "learning_rate": 9.690210797367785e-05, "loss": 0.1837, "step": 49290 }, { "epoch": 11.8, "learning_rate": 9.690086399049756e-05, "loss": 0.2346, "step": 49300 }, { "epoch": 11.8, "learning_rate": 9.689961976558984e-05, "loss": 0.2143, "step": 49310 }, { "epoch": 11.81, "learning_rate": 9.689837529896109e-05, "loss": 0.17, "step": 49320 }, { "epoch": 11.81, "learning_rate": 9.68971305906177e-05, "loss": 0.2202, "step": 49330 }, { "epoch": 11.81, "learning_rate": 9.689588564056613e-05, "loss": 0.2246, "step": 49340 }, { "epoch": 11.81, "learning_rate": 9.689464044881276e-05, "loss": 0.2309, "step": 49350 }, { "epoch": 11.82, "learning_rate": 9.689339501536403e-05, "loss": 0.2201, "step": 49360 }, { "epoch": 11.82, "learning_rate": 9.689214934022635e-05, "loss": 0.2472, "step": 49370 }, { "epoch": 11.82, "learning_rate": 9.689090342340613e-05, "loss": 0.2275, "step": 49380 }, { "epoch": 11.82, "learning_rate": 9.688965726490982e-05, "loss": 0.1989, "step": 49390 }, { "epoch": 11.82, "learning_rate": 9.688841086474381e-05, "loss": 0.1551, "step": 49400 }, { "epoch": 11.83, "learning_rate": 9.688716422291453e-05, "loss": 0.1903, "step": 49410 }, { "epoch": 11.83, "learning_rate": 9.688591733942844e-05, "loss": 0.259, "step": 49420 }, { "epoch": 11.83, "learning_rate": 9.688467021429192e-05, "loss": 0.1848, "step": 49430 }, { "epoch": 11.83, "learning_rate": 9.688342284751141e-05, "loss": 0.2556, "step": 49440 }, { "epoch": 11.84, "learning_rate": 9.688217523909338e-05, "loss": 0.2011, "step": 49450 }, { "epoch": 11.84, "learning_rate": 9.68809273890442e-05, "loss": 0.1777, "step": 49460 }, { "epoch": 11.84, "learning_rate": 9.687967929737034e-05, "loss": 0.3386, "step": 49470 }, { "epoch": 11.84, "learning_rate": 9.68784309640782e-05, "loss": 0.2256, "step": 49480 }, { "epoch": 11.84, "learning_rate": 9.687718238917427e-05, "loss": 0.1849, "step": 49490 }, { "epoch": 11.85, "learning_rate": 9.687593357266492e-05, "loss": 0.1418, "step": 49500 }, { "epoch": 11.85, "learning_rate": 9.687468451455663e-05, "loss": 0.1891, "step": 49510 }, { "epoch": 11.85, "learning_rate": 9.687343521485582e-05, "loss": 0.2201, "step": 49520 }, { "epoch": 11.85, "learning_rate": 9.687218567356894e-05, "loss": 0.2116, "step": 49530 }, { "epoch": 11.86, "learning_rate": 9.687093589070242e-05, "loss": 0.2581, "step": 49540 }, { "epoch": 11.86, "learning_rate": 9.686968586626271e-05, "loss": 0.2294, "step": 49550 }, { "epoch": 11.86, "learning_rate": 9.686843560025623e-05, "loss": 0.213, "step": 49560 }, { "epoch": 11.86, "learning_rate": 9.686718509268946e-05, "loss": 0.2569, "step": 49570 }, { "epoch": 11.87, "learning_rate": 9.686593434356881e-05, "loss": 0.215, "step": 49580 }, { "epoch": 11.87, "learning_rate": 9.686468335290075e-05, "loss": 0.2083, "step": 49590 }, { "epoch": 11.87, "learning_rate": 9.686343212069174e-05, "loss": 0.1385, "step": 49600 }, { "epoch": 11.87, "learning_rate": 9.686218064694817e-05, "loss": 0.3043, "step": 49610 }, { "epoch": 11.87, "learning_rate": 9.686092893167655e-05, "loss": 0.238, "step": 49620 }, { "epoch": 11.88, "learning_rate": 9.685967697488331e-05, "loss": 0.1537, "step": 49630 }, { "epoch": 11.88, "learning_rate": 9.68584247765749e-05, "loss": 0.2281, "step": 49640 }, { "epoch": 11.88, "learning_rate": 9.685717233675779e-05, "loss": 0.2431, "step": 49650 }, { "epoch": 11.88, "learning_rate": 9.685591965543841e-05, "loss": 0.2135, "step": 49660 }, { "epoch": 11.89, "learning_rate": 9.685466673262323e-05, "loss": 0.1721, "step": 49670 }, { "epoch": 11.89, "learning_rate": 9.685341356831871e-05, "loss": 0.2217, "step": 49680 }, { "epoch": 11.89, "learning_rate": 9.685216016253131e-05, "loss": 0.1574, "step": 49690 }, { "epoch": 11.89, "learning_rate": 9.685090651526747e-05, "loss": 0.1965, "step": 49700 }, { "epoch": 11.9, "learning_rate": 9.684965262653367e-05, "loss": 0.1495, "step": 49710 }, { "epoch": 11.9, "learning_rate": 9.684839849633638e-05, "loss": 0.2245, "step": 49720 }, { "epoch": 11.9, "learning_rate": 9.684714412468203e-05, "loss": 0.2402, "step": 49730 }, { "epoch": 11.9, "learning_rate": 9.684588951157712e-05, "loss": 0.1868, "step": 49740 }, { "epoch": 11.9, "learning_rate": 9.684463465702811e-05, "loss": 0.2088, "step": 49750 }, { "epoch": 11.91, "learning_rate": 9.684337956104146e-05, "loss": 0.1925, "step": 49760 }, { "epoch": 11.91, "learning_rate": 9.684212422362365e-05, "loss": 0.2279, "step": 49770 }, { "epoch": 11.91, "learning_rate": 9.684086864478112e-05, "loss": 0.198, "step": 49780 }, { "epoch": 11.91, "learning_rate": 9.683961282452036e-05, "loss": 0.2405, "step": 49790 }, { "epoch": 11.92, "learning_rate": 9.683835676284784e-05, "loss": 0.2376, "step": 49800 }, { "epoch": 11.92, "learning_rate": 9.683710045977005e-05, "loss": 0.2383, "step": 49810 }, { "epoch": 11.92, "learning_rate": 9.683584391529347e-05, "loss": 0.2113, "step": 49820 }, { "epoch": 11.92, "learning_rate": 9.683458712942455e-05, "loss": 0.2225, "step": 49830 }, { "epoch": 11.92, "learning_rate": 9.683333010216976e-05, "loss": 0.2623, "step": 49840 }, { "epoch": 11.93, "learning_rate": 9.68320728335356e-05, "loss": 0.1388, "step": 49850 }, { "epoch": 11.93, "learning_rate": 9.683081532352856e-05, "loss": 0.2267, "step": 49860 }, { "epoch": 11.93, "learning_rate": 9.682955757215508e-05, "loss": 0.1802, "step": 49870 }, { "epoch": 11.93, "learning_rate": 9.68282995794217e-05, "loss": 0.1774, "step": 49880 }, { "epoch": 11.94, "learning_rate": 9.682704134533484e-05, "loss": 0.1871, "step": 49890 }, { "epoch": 11.94, "learning_rate": 9.682578286990105e-05, "loss": 0.1913, "step": 49900 }, { "epoch": 11.94, "learning_rate": 9.682452415312677e-05, "loss": 0.2159, "step": 49910 }, { "epoch": 11.94, "learning_rate": 9.68232651950185e-05, "loss": 0.135, "step": 49920 }, { "epoch": 11.95, "learning_rate": 9.682200599558272e-05, "loss": 0.1912, "step": 49930 }, { "epoch": 11.95, "learning_rate": 9.682074655482593e-05, "loss": 0.1933, "step": 49940 }, { "epoch": 11.95, "learning_rate": 9.681948687275463e-05, "loss": 0.1574, "step": 49950 }, { "epoch": 12.0, "learning_rate": 9.681822694937532e-05, "loss": 0.179, "step": 49960 }, { "epoch": 12.0, "learning_rate": 9.681696678469446e-05, "loss": 0.2246, "step": 49970 }, { "epoch": 12.01, "learning_rate": 9.681570637871855e-05, "loss": 0.1732, "step": 49980 }, { "epoch": 12.01, "learning_rate": 9.68144457314541e-05, "loss": 0.2352, "step": 49990 }, { "epoch": 12.01, "learning_rate": 9.681318484290762e-05, "loss": 0.1596, "step": 50000 }, { "epoch": 12.01, "learning_rate": 9.68119237130856e-05, "loss": 0.194, "step": 50010 }, { "epoch": 12.01, "learning_rate": 9.681066234199451e-05, "loss": 0.1941, "step": 50020 }, { "epoch": 12.02, "learning_rate": 9.680940072964089e-05, "loss": 0.1953, "step": 50030 }, { "epoch": 12.02, "learning_rate": 9.680813887603124e-05, "loss": 0.1463, "step": 50040 }, { "epoch": 12.02, "learning_rate": 9.680687678117203e-05, "loss": 0.1714, "step": 50050 }, { "epoch": 12.02, "learning_rate": 9.68056144450698e-05, "loss": 0.2111, "step": 50060 }, { "epoch": 12.03, "learning_rate": 9.680435186773103e-05, "loss": 0.1798, "step": 50070 }, { "epoch": 12.03, "learning_rate": 9.680308904916224e-05, "loss": 0.1559, "step": 50080 }, { "epoch": 12.03, "learning_rate": 9.680182598936993e-05, "loss": 0.1646, "step": 50090 }, { "epoch": 12.03, "learning_rate": 9.680056268836064e-05, "loss": 0.1228, "step": 50100 }, { "epoch": 12.04, "learning_rate": 9.679929914614085e-05, "loss": 0.181, "step": 50110 }, { "epoch": 12.04, "learning_rate": 9.679803536271707e-05, "loss": 0.1559, "step": 50120 }, { "epoch": 12.04, "learning_rate": 9.679677133809584e-05, "loss": 0.2223, "step": 50130 }, { "epoch": 12.04, "learning_rate": 9.679550707228365e-05, "loss": 0.1473, "step": 50140 }, { "epoch": 12.04, "learning_rate": 9.679424256528702e-05, "loss": 0.1641, "step": 50150 }, { "epoch": 12.05, "learning_rate": 9.67929778171125e-05, "loss": 0.1453, "step": 50160 }, { "epoch": 12.05, "learning_rate": 9.679171282776656e-05, "loss": 0.1765, "step": 50170 }, { "epoch": 12.05, "learning_rate": 9.679044759725573e-05, "loss": 0.1978, "step": 50180 }, { "epoch": 12.05, "learning_rate": 9.678918212558657e-05, "loss": 0.206, "step": 50190 }, { "epoch": 12.06, "learning_rate": 9.678791641276554e-05, "loss": 0.2381, "step": 50200 }, { "epoch": 12.06, "learning_rate": 9.678665045879923e-05, "loss": 0.1377, "step": 50210 }, { "epoch": 12.06, "learning_rate": 9.678538426369411e-05, "loss": 0.1554, "step": 50220 }, { "epoch": 12.06, "learning_rate": 9.678411782745674e-05, "loss": 0.1588, "step": 50230 }, { "epoch": 12.06, "learning_rate": 9.678285115009364e-05, "loss": 0.1559, "step": 50240 }, { "epoch": 12.07, "learning_rate": 9.678158423161133e-05, "loss": 0.126, "step": 50250 }, { "epoch": 12.07, "learning_rate": 9.678031707201634e-05, "loss": 0.1705, "step": 50260 }, { "epoch": 12.07, "learning_rate": 9.677904967131519e-05, "loss": 0.156, "step": 50270 }, { "epoch": 12.07, "learning_rate": 9.677778202951445e-05, "loss": 0.1959, "step": 50280 }, { "epoch": 12.08, "learning_rate": 9.677651414662062e-05, "loss": 0.2031, "step": 50290 }, { "epoch": 12.08, "learning_rate": 9.677524602264026e-05, "loss": 0.2119, "step": 50300 }, { "epoch": 12.08, "learning_rate": 9.677397765757987e-05, "loss": 0.1919, "step": 50310 }, { "epoch": 12.08, "learning_rate": 9.677270905144602e-05, "loss": 0.2109, "step": 50320 }, { "epoch": 12.09, "learning_rate": 9.677144020424523e-05, "loss": 0.1499, "step": 50330 }, { "epoch": 12.09, "learning_rate": 9.677017111598405e-05, "loss": 0.1994, "step": 50340 }, { "epoch": 12.09, "learning_rate": 9.676890178666903e-05, "loss": 0.1649, "step": 50350 }, { "epoch": 12.09, "learning_rate": 9.676763221630668e-05, "loss": 0.1492, "step": 50360 }, { "epoch": 12.09, "learning_rate": 9.676636240490357e-05, "loss": 0.2292, "step": 50370 }, { "epoch": 12.1, "learning_rate": 9.676509235246624e-05, "loss": 0.1454, "step": 50380 }, { "epoch": 12.1, "learning_rate": 9.676382205900123e-05, "loss": 0.1137, "step": 50390 }, { "epoch": 12.1, "learning_rate": 9.676255152451508e-05, "loss": 0.2011, "step": 50400 }, { "epoch": 12.1, "learning_rate": 9.676128074901436e-05, "loss": 0.175, "step": 50410 }, { "epoch": 12.11, "learning_rate": 9.67600097325056e-05, "loss": 0.139, "step": 50420 }, { "epoch": 12.11, "learning_rate": 9.675873847499537e-05, "loss": 0.1979, "step": 50430 }, { "epoch": 12.11, "learning_rate": 9.675746697649021e-05, "loss": 0.2396, "step": 50440 }, { "epoch": 12.11, "learning_rate": 9.675619523699669e-05, "loss": 0.2183, "step": 50450 }, { "epoch": 12.12, "learning_rate": 9.675492325652131e-05, "loss": 0.1269, "step": 50460 }, { "epoch": 12.12, "learning_rate": 9.675365103507069e-05, "loss": 0.1955, "step": 50470 }, { "epoch": 12.12, "learning_rate": 9.675237857265136e-05, "loss": 0.155, "step": 50480 }, { "epoch": 12.12, "learning_rate": 9.675110586926988e-05, "loss": 0.2159, "step": 50490 }, { "epoch": 12.12, "learning_rate": 9.67498329249328e-05, "loss": 0.2452, "step": 50500 }, { "epoch": 12.13, "learning_rate": 9.67485597396467e-05, "loss": 0.1718, "step": 50510 }, { "epoch": 12.13, "learning_rate": 9.674728631341811e-05, "loss": 0.1644, "step": 50520 }, { "epoch": 12.13, "learning_rate": 9.674601264625364e-05, "loss": 0.2188, "step": 50530 }, { "epoch": 12.13, "learning_rate": 9.674473873815983e-05, "loss": 0.1838, "step": 50540 }, { "epoch": 12.14, "learning_rate": 9.674346458914326e-05, "loss": 0.2427, "step": 50550 }, { "epoch": 12.14, "learning_rate": 9.674219019921044e-05, "loss": 0.1802, "step": 50560 }, { "epoch": 12.14, "learning_rate": 9.674091556836801e-05, "loss": 0.1937, "step": 50570 }, { "epoch": 12.14, "learning_rate": 9.673964069662252e-05, "loss": 0.2227, "step": 50580 }, { "epoch": 12.14, "learning_rate": 9.673836558398051e-05, "loss": 0.1523, "step": 50590 }, { "epoch": 12.15, "learning_rate": 9.673709023044857e-05, "loss": 0.2192, "step": 50600 }, { "epoch": 12.15, "learning_rate": 9.673581463603329e-05, "loss": 0.2148, "step": 50610 }, { "epoch": 12.15, "learning_rate": 9.673453880074122e-05, "loss": 0.1662, "step": 50620 }, { "epoch": 12.15, "learning_rate": 9.673326272457896e-05, "loss": 0.2073, "step": 50630 }, { "epoch": 12.16, "learning_rate": 9.673198640755306e-05, "loss": 0.1605, "step": 50640 }, { "epoch": 12.16, "learning_rate": 9.673070984967012e-05, "loss": 0.1487, "step": 50650 }, { "epoch": 12.16, "learning_rate": 9.672943305093672e-05, "loss": 0.1437, "step": 50660 }, { "epoch": 12.16, "learning_rate": 9.67281560113594e-05, "loss": 0.1822, "step": 50670 }, { "epoch": 12.17, "learning_rate": 9.672687873094479e-05, "loss": 0.1703, "step": 50680 }, { "epoch": 12.17, "learning_rate": 9.672560120969946e-05, "loss": 0.1763, "step": 50690 }, { "epoch": 12.17, "learning_rate": 9.672432344763e-05, "loss": 0.2377, "step": 50700 }, { "epoch": 12.17, "learning_rate": 9.672304544474298e-05, "loss": 0.1877, "step": 50710 }, { "epoch": 12.17, "learning_rate": 9.672176720104497e-05, "loss": 0.1838, "step": 50720 }, { "epoch": 12.18, "learning_rate": 9.672048871654261e-05, "loss": 0.2208, "step": 50730 }, { "epoch": 12.18, "learning_rate": 9.671920999124246e-05, "loss": 0.1244, "step": 50740 }, { "epoch": 12.18, "learning_rate": 9.67179310251511e-05, "loss": 0.1696, "step": 50750 }, { "epoch": 12.18, "learning_rate": 9.671665181827514e-05, "loss": 0.207, "step": 50760 }, { "epoch": 12.19, "learning_rate": 9.671537237062117e-05, "loss": 0.1672, "step": 50770 }, { "epoch": 12.19, "learning_rate": 9.671409268219576e-05, "loss": 0.1522, "step": 50780 }, { "epoch": 12.19, "learning_rate": 9.671281275300553e-05, "loss": 0.1814, "step": 50790 }, { "epoch": 12.19, "learning_rate": 9.671153258305709e-05, "loss": 0.1285, "step": 50800 }, { "epoch": 12.2, "learning_rate": 9.671025217235701e-05, "loss": 0.2788, "step": 50810 }, { "epoch": 12.2, "learning_rate": 9.670897152091189e-05, "loss": 0.2057, "step": 50820 }, { "epoch": 12.2, "learning_rate": 9.670769062872835e-05, "loss": 0.1657, "step": 50830 }, { "epoch": 12.2, "learning_rate": 9.6706409495813e-05, "loss": 0.1287, "step": 50840 }, { "epoch": 12.2, "learning_rate": 9.670512812217241e-05, "loss": 0.164, "step": 50850 }, { "epoch": 12.21, "learning_rate": 9.670384650781319e-05, "loss": 0.2473, "step": 50860 }, { "epoch": 12.21, "learning_rate": 9.670256465274197e-05, "loss": 0.1776, "step": 50870 }, { "epoch": 12.21, "learning_rate": 9.670128255696533e-05, "loss": 0.1167, "step": 50880 }, { "epoch": 12.21, "learning_rate": 9.670000022048988e-05, "loss": 0.1938, "step": 50890 }, { "epoch": 12.22, "learning_rate": 9.669871764332225e-05, "loss": 0.1927, "step": 50900 }, { "epoch": 12.22, "learning_rate": 9.669743482546905e-05, "loss": 0.204, "step": 50910 }, { "epoch": 12.22, "learning_rate": 9.669615176693686e-05, "loss": 0.1757, "step": 50920 }, { "epoch": 12.22, "learning_rate": 9.669486846773233e-05, "loss": 0.172, "step": 50930 }, { "epoch": 12.22, "learning_rate": 9.669358492786206e-05, "loss": 0.2151, "step": 50940 }, { "epoch": 12.23, "learning_rate": 9.669230114733266e-05, "loss": 0.1411, "step": 50950 }, { "epoch": 12.23, "learning_rate": 9.669101712615074e-05, "loss": 0.1822, "step": 50960 }, { "epoch": 12.23, "learning_rate": 9.668973286432292e-05, "loss": 0.2111, "step": 50970 }, { "epoch": 12.23, "learning_rate": 9.668844836185584e-05, "loss": 0.1903, "step": 50980 }, { "epoch": 12.24, "learning_rate": 9.668716361875612e-05, "loss": 0.1315, "step": 50990 }, { "epoch": 12.24, "learning_rate": 9.668587863503035e-05, "loss": 0.1962, "step": 51000 }, { "epoch": 12.24, "learning_rate": 9.668459341068517e-05, "loss": 0.1466, "step": 51010 }, { "epoch": 12.24, "learning_rate": 9.668330794572722e-05, "loss": 0.1578, "step": 51020 }, { "epoch": 12.25, "learning_rate": 9.66820222401631e-05, "loss": 0.1984, "step": 51030 }, { "epoch": 12.25, "learning_rate": 9.668073629399945e-05, "loss": 0.1536, "step": 51040 }, { "epoch": 12.25, "learning_rate": 9.667945010724289e-05, "loss": 0.1941, "step": 51050 }, { "epoch": 12.25, "learning_rate": 9.667816367990006e-05, "loss": 0.157, "step": 51060 }, { "epoch": 12.25, "learning_rate": 9.667687701197759e-05, "loss": 0.1887, "step": 51070 }, { "epoch": 12.26, "learning_rate": 9.667559010348209e-05, "loss": 0.1498, "step": 51080 }, { "epoch": 12.26, "learning_rate": 9.667430295442022e-05, "loss": 0.1688, "step": 51090 }, { "epoch": 12.26, "learning_rate": 9.66730155647986e-05, "loss": 0.0909, "step": 51100 }, { "epoch": 12.26, "learning_rate": 9.667172793462386e-05, "loss": 0.1256, "step": 51110 }, { "epoch": 12.27, "learning_rate": 9.667044006390264e-05, "loss": 0.1671, "step": 51120 }, { "epoch": 12.27, "learning_rate": 9.66691519526416e-05, "loss": 0.1651, "step": 51130 }, { "epoch": 12.27, "learning_rate": 9.666786360084736e-05, "loss": 0.1797, "step": 51140 }, { "epoch": 12.27, "learning_rate": 9.666657500852654e-05, "loss": 0.1482, "step": 51150 }, { "epoch": 12.28, "learning_rate": 9.666528617568582e-05, "loss": 0.2115, "step": 51160 }, { "epoch": 12.28, "learning_rate": 9.666399710233183e-05, "loss": 0.1812, "step": 51170 }, { "epoch": 12.28, "learning_rate": 9.66627077884712e-05, "loss": 0.1955, "step": 51180 }, { "epoch": 12.28, "learning_rate": 9.666141823411057e-05, "loss": 0.1429, "step": 51190 }, { "epoch": 12.28, "learning_rate": 9.666012843925663e-05, "loss": 0.1316, "step": 51200 }, { "epoch": 12.29, "learning_rate": 9.665883840391596e-05, "loss": 0.1531, "step": 51210 }, { "epoch": 12.29, "learning_rate": 9.665754812809529e-05, "loss": 0.1833, "step": 51220 }, { "epoch": 12.29, "learning_rate": 9.66562576118012e-05, "loss": 0.1031, "step": 51230 }, { "epoch": 12.29, "learning_rate": 9.665496685504037e-05, "loss": 0.2265, "step": 51240 }, { "epoch": 12.3, "learning_rate": 9.665367585781946e-05, "loss": 0.1367, "step": 51250 }, { "epoch": 12.3, "learning_rate": 9.66523846201451e-05, "loss": 0.1085, "step": 51260 }, { "epoch": 12.3, "learning_rate": 9.665109314202398e-05, "loss": 0.2098, "step": 51270 }, { "epoch": 12.3, "learning_rate": 9.664980142346271e-05, "loss": 0.1628, "step": 51280 }, { "epoch": 12.3, "learning_rate": 9.6648509464468e-05, "loss": 0.1219, "step": 51290 }, { "epoch": 12.31, "learning_rate": 9.664721726504646e-05, "loss": 0.1883, "step": 51300 }, { "epoch": 12.31, "learning_rate": 9.66459248252048e-05, "loss": 0.1704, "step": 51310 }, { "epoch": 12.31, "learning_rate": 9.664463214494963e-05, "loss": 0.1694, "step": 51320 }, { "epoch": 12.31, "learning_rate": 9.664333922428765e-05, "loss": 0.1306, "step": 51330 }, { "epoch": 12.32, "learning_rate": 9.66420460632255e-05, "loss": 0.1296, "step": 51340 }, { "epoch": 12.32, "learning_rate": 9.664075266176986e-05, "loss": 0.151, "step": 51350 }, { "epoch": 12.32, "learning_rate": 9.66394590199274e-05, "loss": 0.2568, "step": 51360 }, { "epoch": 12.32, "learning_rate": 9.663816513770475e-05, "loss": 0.1343, "step": 51370 }, { "epoch": 12.33, "learning_rate": 9.663687101510863e-05, "loss": 0.234, "step": 51380 }, { "epoch": 12.33, "learning_rate": 9.663557665214567e-05, "loss": 0.1822, "step": 51390 }, { "epoch": 12.33, "learning_rate": 9.663428204882258e-05, "loss": 0.1217, "step": 51400 }, { "epoch": 12.33, "learning_rate": 9.663298720514599e-05, "loss": 0.1061, "step": 51410 }, { "epoch": 12.33, "learning_rate": 9.663169212112261e-05, "loss": 0.1606, "step": 51420 }, { "epoch": 12.34, "learning_rate": 9.66303967967591e-05, "loss": 0.166, "step": 51430 }, { "epoch": 12.34, "learning_rate": 9.662910123206212e-05, "loss": 0.1347, "step": 51440 }, { "epoch": 12.34, "learning_rate": 9.662780542703837e-05, "loss": 0.1528, "step": 51450 }, { "epoch": 12.34, "learning_rate": 9.662650938169453e-05, "loss": 0.2452, "step": 51460 }, { "epoch": 12.35, "learning_rate": 9.662521309603725e-05, "loss": 0.166, "step": 51470 }, { "epoch": 12.35, "learning_rate": 9.662391657007324e-05, "loss": 0.1772, "step": 51480 }, { "epoch": 12.35, "learning_rate": 9.662261980380919e-05, "loss": 0.1413, "step": 51490 }, { "epoch": 12.35, "learning_rate": 9.662132279725176e-05, "loss": 0.2249, "step": 51500 }, { "epoch": 12.36, "learning_rate": 9.662002555040764e-05, "loss": 0.1543, "step": 51510 }, { "epoch": 12.36, "learning_rate": 9.661872806328352e-05, "loss": 0.1567, "step": 51520 }, { "epoch": 12.36, "learning_rate": 9.661743033588607e-05, "loss": 0.1534, "step": 51530 }, { "epoch": 12.36, "learning_rate": 9.661613236822201e-05, "loss": 0.1688, "step": 51540 }, { "epoch": 12.36, "learning_rate": 9.661483416029801e-05, "loss": 0.2035, "step": 51550 }, { "epoch": 12.37, "learning_rate": 9.661353571212077e-05, "loss": 0.1836, "step": 51560 }, { "epoch": 12.37, "learning_rate": 9.661223702369698e-05, "loss": 0.1447, "step": 51570 }, { "epoch": 12.37, "learning_rate": 9.661093809503332e-05, "loss": 0.1316, "step": 51580 }, { "epoch": 12.37, "learning_rate": 9.660963892613651e-05, "loss": 0.1617, "step": 51590 }, { "epoch": 12.38, "learning_rate": 9.660833951701321e-05, "loss": 0.155, "step": 51600 }, { "epoch": 12.38, "learning_rate": 9.660703986767015e-05, "loss": 0.1706, "step": 51610 }, { "epoch": 12.38, "learning_rate": 9.660573997811402e-05, "loss": 0.1819, "step": 51620 }, { "epoch": 12.38, "learning_rate": 9.660443984835152e-05, "loss": 0.1287, "step": 51630 }, { "epoch": 12.38, "learning_rate": 9.660313947838934e-05, "loss": 0.1896, "step": 51640 }, { "epoch": 12.39, "learning_rate": 9.66018388682342e-05, "loss": 0.1757, "step": 51650 }, { "epoch": 12.39, "learning_rate": 9.660053801789277e-05, "loss": 0.2436, "step": 51660 }, { "epoch": 12.39, "learning_rate": 9.659923692737179e-05, "loss": 0.1381, "step": 51670 }, { "epoch": 12.39, "learning_rate": 9.659793559667795e-05, "loss": 0.1454, "step": 51680 }, { "epoch": 12.4, "learning_rate": 9.659663402581798e-05, "loss": 0.1852, "step": 51690 }, { "epoch": 12.4, "learning_rate": 9.659533221479855e-05, "loss": 0.1727, "step": 51700 }, { "epoch": 12.4, "learning_rate": 9.659403016362639e-05, "loss": 0.1212, "step": 51710 }, { "epoch": 12.4, "learning_rate": 9.659272787230822e-05, "loss": 0.1317, "step": 51720 }, { "epoch": 12.41, "learning_rate": 9.659142534085073e-05, "loss": 0.1632, "step": 51730 }, { "epoch": 12.41, "learning_rate": 9.659012256926064e-05, "loss": 0.144, "step": 51740 }, { "epoch": 12.41, "learning_rate": 9.658881955754469e-05, "loss": 0.1355, "step": 51750 }, { "epoch": 12.41, "learning_rate": 9.658751630570955e-05, "loss": 0.1403, "step": 51760 }, { "epoch": 12.41, "learning_rate": 9.658621281376197e-05, "loss": 0.1864, "step": 51770 }, { "epoch": 12.42, "learning_rate": 9.658490908170867e-05, "loss": 0.1722, "step": 51780 }, { "epoch": 12.42, "learning_rate": 9.658360510955635e-05, "loss": 0.1932, "step": 51790 }, { "epoch": 12.42, "learning_rate": 9.658230089731174e-05, "loss": 0.1542, "step": 51800 }, { "epoch": 12.42, "learning_rate": 9.658099644498155e-05, "loss": 0.133, "step": 51810 }, { "epoch": 12.43, "learning_rate": 9.657969175257253e-05, "loss": 0.2532, "step": 51820 }, { "epoch": 12.43, "learning_rate": 9.657838682009139e-05, "loss": 0.1462, "step": 51830 }, { "epoch": 12.43, "learning_rate": 9.657708164754487e-05, "loss": 0.1265, "step": 51840 }, { "epoch": 12.43, "learning_rate": 9.657577623493965e-05, "loss": 0.2078, "step": 51850 }, { "epoch": 12.44, "learning_rate": 9.65744705822825e-05, "loss": 0.1641, "step": 51860 }, { "epoch": 12.44, "learning_rate": 9.657316468958015e-05, "loss": 0.1397, "step": 51870 }, { "epoch": 12.44, "learning_rate": 9.657185855683932e-05, "loss": 0.1563, "step": 51880 }, { "epoch": 12.44, "learning_rate": 9.657055218406672e-05, "loss": 0.1301, "step": 51890 }, { "epoch": 12.44, "learning_rate": 9.656924557126913e-05, "loss": 0.1654, "step": 51900 }, { "epoch": 12.45, "learning_rate": 9.656793871845324e-05, "loss": 0.1377, "step": 51910 }, { "epoch": 12.45, "learning_rate": 9.656663162562582e-05, "loss": 0.1283, "step": 51920 }, { "epoch": 12.45, "learning_rate": 9.65653242927936e-05, "loss": 0.1477, "step": 51930 }, { "epoch": 12.45, "learning_rate": 9.656401671996328e-05, "loss": 0.1699, "step": 51940 }, { "epoch": 12.46, "learning_rate": 9.656270890714164e-05, "loss": 0.1547, "step": 51950 }, { "epoch": 12.46, "learning_rate": 9.65614008543354e-05, "loss": 0.242, "step": 51960 }, { "epoch": 12.46, "learning_rate": 9.656009256155134e-05, "loss": 0.1165, "step": 51970 }, { "epoch": 12.46, "learning_rate": 9.655878402879614e-05, "loss": 0.1321, "step": 51980 }, { "epoch": 12.46, "learning_rate": 9.655747525607662e-05, "loss": 0.1648, "step": 51990 }, { "epoch": 12.47, "learning_rate": 9.655616624339945e-05, "loss": 0.178, "step": 52000 }, { "epoch": 12.47, "learning_rate": 9.655485699077141e-05, "loss": 0.1638, "step": 52010 }, { "epoch": 12.47, "learning_rate": 9.655354749819925e-05, "loss": 0.144, "step": 52020 }, { "epoch": 12.47, "learning_rate": 9.655223776568974e-05, "loss": 0.1885, "step": 52030 }, { "epoch": 12.48, "learning_rate": 9.655092779324958e-05, "loss": 0.1655, "step": 52040 }, { "epoch": 12.48, "learning_rate": 9.654961758088556e-05, "loss": 0.1244, "step": 52050 }, { "epoch": 12.48, "learning_rate": 9.654830712860442e-05, "loss": 0.1641, "step": 52060 }, { "epoch": 12.48, "learning_rate": 9.654699643641292e-05, "loss": 0.0997, "step": 52070 }, { "epoch": 12.49, "learning_rate": 9.65456855043178e-05, "loss": 0.1615, "step": 52080 }, { "epoch": 12.49, "learning_rate": 9.654437433232584e-05, "loss": 0.1503, "step": 52090 }, { "epoch": 12.49, "learning_rate": 9.654306292044379e-05, "loss": 0.1412, "step": 52100 }, { "epoch": 12.49, "learning_rate": 9.65417512686784e-05, "loss": 0.1426, "step": 52110 }, { "epoch": 12.49, "learning_rate": 9.654043937703642e-05, "loss": 0.164, "step": 52120 }, { "epoch": 12.5, "learning_rate": 9.653912724552463e-05, "loss": 0.1344, "step": 52130 }, { "epoch": 12.5, "learning_rate": 9.65378148741498e-05, "loss": 0.1178, "step": 52140 }, { "epoch": 12.5, "learning_rate": 9.653650226291869e-05, "loss": 0.1154, "step": 52150 }, { "epoch": 12.5, "learning_rate": 9.653518941183803e-05, "loss": 0.2099, "step": 52160 }, { "epoch": 12.51, "learning_rate": 9.653387632091464e-05, "loss": 0.1671, "step": 52170 }, { "epoch": 12.51, "learning_rate": 9.653256299015526e-05, "loss": 0.1813, "step": 52180 }, { "epoch": 12.51, "learning_rate": 9.653124941956667e-05, "loss": 0.1854, "step": 52190 }, { "epoch": 12.51, "learning_rate": 9.65299356091556e-05, "loss": 0.1882, "step": 52200 }, { "epoch": 12.52, "learning_rate": 9.652862155892887e-05, "loss": 0.1431, "step": 52210 }, { "epoch": 12.52, "learning_rate": 9.652730726889325e-05, "loss": 0.129, "step": 52220 }, { "epoch": 12.52, "learning_rate": 9.652599273905549e-05, "loss": 0.1435, "step": 52230 }, { "epoch": 12.52, "learning_rate": 9.652467796942236e-05, "loss": 0.1485, "step": 52240 }, { "epoch": 12.52, "learning_rate": 9.652336296000066e-05, "loss": 0.2231, "step": 52250 }, { "epoch": 12.53, "learning_rate": 9.652204771079715e-05, "loss": 0.1779, "step": 52260 }, { "epoch": 12.53, "learning_rate": 9.652073222181865e-05, "loss": 0.1488, "step": 52270 }, { "epoch": 12.53, "learning_rate": 9.651941649307189e-05, "loss": 0.2299, "step": 52280 }, { "epoch": 12.53, "learning_rate": 9.651810052456365e-05, "loss": 0.3081, "step": 52290 }, { "epoch": 12.54, "learning_rate": 9.651678431630074e-05, "loss": 0.2503, "step": 52300 }, { "epoch": 12.54, "learning_rate": 9.651546786828995e-05, "loss": 0.3033, "step": 52310 }, { "epoch": 12.54, "learning_rate": 9.651415118053804e-05, "loss": 0.1996, "step": 52320 }, { "epoch": 12.54, "learning_rate": 9.65128342530518e-05, "loss": 0.2788, "step": 52330 }, { "epoch": 12.54, "learning_rate": 9.651151708583803e-05, "loss": 0.2827, "step": 52340 }, { "epoch": 12.55, "learning_rate": 9.651019967890351e-05, "loss": 0.1919, "step": 52350 }, { "epoch": 12.55, "learning_rate": 9.650888203225503e-05, "loss": 0.228, "step": 52360 }, { "epoch": 12.55, "learning_rate": 9.650756414589939e-05, "loss": 0.1993, "step": 52370 }, { "epoch": 12.55, "learning_rate": 9.650624601984337e-05, "loss": 0.2916, "step": 52380 }, { "epoch": 12.56, "learning_rate": 9.650492765409377e-05, "loss": 0.3621, "step": 52390 }, { "epoch": 12.56, "learning_rate": 9.650360904865738e-05, "loss": 0.2483, "step": 52400 }, { "epoch": 12.56, "learning_rate": 9.650229020354101e-05, "loss": 0.2496, "step": 52410 }, { "epoch": 12.56, "learning_rate": 9.650097111875145e-05, "loss": 0.2152, "step": 52420 }, { "epoch": 12.57, "learning_rate": 9.649965179429547e-05, "loss": 0.2549, "step": 52430 }, { "epoch": 12.57, "learning_rate": 9.649833223017993e-05, "loss": 0.2313, "step": 52440 }, { "epoch": 12.57, "learning_rate": 9.649701242641158e-05, "loss": 0.2563, "step": 52450 }, { "epoch": 12.57, "learning_rate": 9.649569238299724e-05, "loss": 0.211, "step": 52460 }, { "epoch": 12.57, "learning_rate": 9.649437209994371e-05, "loss": 0.2459, "step": 52470 }, { "epoch": 12.58, "learning_rate": 9.64930515772578e-05, "loss": 0.2508, "step": 52480 }, { "epoch": 12.58, "learning_rate": 9.649173081494633e-05, "loss": 0.2201, "step": 52490 }, { "epoch": 12.58, "learning_rate": 9.649040981301608e-05, "loss": 0.1796, "step": 52500 }, { "epoch": 12.58, "learning_rate": 9.648908857147385e-05, "loss": 0.2679, "step": 52510 }, { "epoch": 12.59, "learning_rate": 9.64877670903265e-05, "loss": 0.1935, "step": 52520 }, { "epoch": 12.59, "learning_rate": 9.648644536958078e-05, "loss": 0.2616, "step": 52530 }, { "epoch": 12.59, "learning_rate": 9.648512340924355e-05, "loss": 0.2029, "step": 52540 }, { "epoch": 12.59, "learning_rate": 9.64838012093216e-05, "loss": 0.2492, "step": 52550 }, { "epoch": 12.6, "learning_rate": 9.648247876982175e-05, "loss": 0.2391, "step": 52560 }, { "epoch": 12.6, "learning_rate": 9.648115609075081e-05, "loss": 0.2477, "step": 52570 }, { "epoch": 12.6, "learning_rate": 9.647983317211562e-05, "loss": 0.3059, "step": 52580 }, { "epoch": 12.6, "learning_rate": 9.647851001392297e-05, "loss": 0.2293, "step": 52590 }, { "epoch": 12.6, "learning_rate": 9.64771866161797e-05, "loss": 0.1927, "step": 52600 }, { "epoch": 12.61, "learning_rate": 9.647586297889261e-05, "loss": 0.2529, "step": 52610 }, { "epoch": 12.61, "learning_rate": 9.647453910206854e-05, "loss": 0.2671, "step": 52620 }, { "epoch": 12.61, "learning_rate": 9.64732149857143e-05, "loss": 0.2929, "step": 52630 }, { "epoch": 12.61, "learning_rate": 9.647189062983673e-05, "loss": 0.1913, "step": 52640 }, { "epoch": 12.62, "learning_rate": 9.647056603444264e-05, "loss": 0.2241, "step": 52650 }, { "epoch": 12.62, "learning_rate": 9.646924119953886e-05, "loss": 0.261, "step": 52660 }, { "epoch": 12.62, "learning_rate": 9.646791612513224e-05, "loss": 0.1723, "step": 52670 }, { "epoch": 12.62, "learning_rate": 9.646659081122959e-05, "loss": 0.1639, "step": 52680 }, { "epoch": 12.62, "learning_rate": 9.646526525783773e-05, "loss": 0.2536, "step": 52690 }, { "epoch": 12.63, "learning_rate": 9.64639394649635e-05, "loss": 0.221, "step": 52700 }, { "epoch": 12.63, "learning_rate": 9.646261343261376e-05, "loss": 0.219, "step": 52710 }, { "epoch": 12.63, "learning_rate": 9.64612871607953e-05, "loss": 0.303, "step": 52720 }, { "epoch": 12.63, "learning_rate": 9.645996064951499e-05, "loss": 0.2919, "step": 52730 }, { "epoch": 12.64, "learning_rate": 9.645863389877965e-05, "loss": 0.1684, "step": 52740 }, { "epoch": 12.64, "learning_rate": 9.645730690859613e-05, "loss": 0.2243, "step": 52750 }, { "epoch": 12.64, "learning_rate": 9.645597967897124e-05, "loss": 0.2074, "step": 52760 }, { "epoch": 12.64, "learning_rate": 9.645465220991187e-05, "loss": 0.1993, "step": 52770 }, { "epoch": 12.65, "learning_rate": 9.645332450142482e-05, "loss": 0.246, "step": 52780 }, { "epoch": 12.65, "learning_rate": 9.645199655351696e-05, "loss": 0.1935, "step": 52790 }, { "epoch": 12.65, "learning_rate": 9.64506683661951e-05, "loss": 0.1087, "step": 52800 }, { "epoch": 12.65, "learning_rate": 9.644933993946613e-05, "loss": 0.2294, "step": 52810 }, { "epoch": 12.65, "learning_rate": 9.644801127333685e-05, "loss": 0.2146, "step": 52820 }, { "epoch": 12.66, "learning_rate": 9.644668236781414e-05, "loss": 0.2341, "step": 52830 }, { "epoch": 12.66, "learning_rate": 9.644535322290484e-05, "loss": 0.2296, "step": 52840 }, { "epoch": 12.66, "learning_rate": 9.644402383861581e-05, "loss": 0.2697, "step": 52850 }, { "epoch": 12.66, "learning_rate": 9.644269421495388e-05, "loss": 0.1604, "step": 52860 }, { "epoch": 12.67, "learning_rate": 9.644136435192593e-05, "loss": 0.2738, "step": 52870 }, { "epoch": 12.67, "learning_rate": 9.64400342495388e-05, "loss": 0.2466, "step": 52880 }, { "epoch": 12.67, "learning_rate": 9.643870390779935e-05, "loss": 0.2321, "step": 52890 }, { "epoch": 12.67, "learning_rate": 9.64373733267144e-05, "loss": 0.1937, "step": 52900 }, { "epoch": 12.68, "learning_rate": 9.643604250629087e-05, "loss": 0.1719, "step": 52910 }, { "epoch": 12.68, "learning_rate": 9.643471144653557e-05, "loss": 0.2132, "step": 52920 }, { "epoch": 12.68, "learning_rate": 9.64333801474554e-05, "loss": 0.173, "step": 52930 }, { "epoch": 12.68, "learning_rate": 9.64320486090572e-05, "loss": 0.2028, "step": 52940 }, { "epoch": 12.68, "learning_rate": 9.643071683134782e-05, "loss": 0.2333, "step": 52950 }, { "epoch": 12.69, "learning_rate": 9.642938481433412e-05, "loss": 0.1826, "step": 52960 }, { "epoch": 12.69, "learning_rate": 9.6428052558023e-05, "loss": 0.1976, "step": 52970 }, { "epoch": 12.69, "learning_rate": 9.642672006242132e-05, "loss": 0.2941, "step": 52980 }, { "epoch": 12.69, "learning_rate": 9.642538732753593e-05, "loss": 0.3072, "step": 52990 }, { "epoch": 12.7, "learning_rate": 9.64240543533737e-05, "loss": 0.1975, "step": 53000 }, { "epoch": 12.7, "learning_rate": 9.642272113994151e-05, "loss": 0.2543, "step": 53010 }, { "epoch": 12.7, "learning_rate": 9.642138768724623e-05, "loss": 0.2337, "step": 53020 }, { "epoch": 12.7, "learning_rate": 9.642005399529473e-05, "loss": 0.2469, "step": 53030 }, { "epoch": 12.7, "learning_rate": 9.641872006409387e-05, "loss": 0.2204, "step": 53040 }, { "epoch": 12.71, "learning_rate": 9.641738589365055e-05, "loss": 0.2047, "step": 53050 }, { "epoch": 12.71, "learning_rate": 9.641605148397163e-05, "loss": 0.2206, "step": 53060 }, { "epoch": 12.71, "learning_rate": 9.6414716835064e-05, "loss": 0.216, "step": 53070 }, { "epoch": 12.71, "learning_rate": 9.641338194693454e-05, "loss": 0.2688, "step": 53080 }, { "epoch": 12.72, "learning_rate": 9.641204681959011e-05, "loss": 0.2504, "step": 53090 }, { "epoch": 12.72, "learning_rate": 9.641071145303759e-05, "loss": 0.2003, "step": 53100 }, { "epoch": 12.72, "learning_rate": 9.64093758472839e-05, "loss": 0.2445, "step": 53110 }, { "epoch": 12.72, "learning_rate": 9.640804000233589e-05, "loss": 0.1861, "step": 53120 }, { "epoch": 12.73, "learning_rate": 9.640670391820045e-05, "loss": 0.1321, "step": 53130 }, { "epoch": 12.73, "learning_rate": 9.640536759488446e-05, "loss": 0.144, "step": 53140 }, { "epoch": 12.73, "learning_rate": 9.640403103239484e-05, "loss": 0.2113, "step": 53150 }, { "epoch": 12.73, "learning_rate": 9.640269423073844e-05, "loss": 0.1649, "step": 53160 }, { "epoch": 12.73, "learning_rate": 9.640135718992217e-05, "loss": 0.2419, "step": 53170 }, { "epoch": 12.74, "learning_rate": 9.640001990995292e-05, "loss": 0.1802, "step": 53180 }, { "epoch": 12.74, "learning_rate": 9.639868239083758e-05, "loss": 0.1928, "step": 53190 }, { "epoch": 12.74, "learning_rate": 9.639734463258303e-05, "loss": 0.2546, "step": 53200 }, { "epoch": 12.74, "learning_rate": 9.63960066351962e-05, "loss": 0.1851, "step": 53210 }, { "epoch": 12.75, "learning_rate": 9.639466839868393e-05, "loss": 0.2735, "step": 53220 }, { "epoch": 12.75, "learning_rate": 9.639332992305319e-05, "loss": 0.1731, "step": 53230 }, { "epoch": 12.75, "learning_rate": 9.639199120831083e-05, "loss": 0.1372, "step": 53240 }, { "epoch": 12.75, "learning_rate": 9.639065225446375e-05, "loss": 0.2662, "step": 53250 }, { "epoch": 12.76, "learning_rate": 9.638931306151886e-05, "loss": 0.1884, "step": 53260 }, { "epoch": 12.76, "learning_rate": 9.638797362948306e-05, "loss": 0.2501, "step": 53270 }, { "epoch": 12.76, "learning_rate": 9.638663395836327e-05, "loss": 0.227, "step": 53280 }, { "epoch": 12.76, "learning_rate": 9.638529404816637e-05, "loss": 0.1543, "step": 53290 }, { "epoch": 12.76, "learning_rate": 9.63839538988993e-05, "loss": 0.1755, "step": 53300 }, { "epoch": 12.77, "learning_rate": 9.638261351056891e-05, "loss": 0.1883, "step": 53310 }, { "epoch": 12.77, "learning_rate": 9.638127288318215e-05, "loss": 0.216, "step": 53320 }, { "epoch": 12.77, "learning_rate": 9.637993201674593e-05, "loss": 0.2021, "step": 53330 }, { "epoch": 12.77, "learning_rate": 9.637859091126715e-05, "loss": 0.1599, "step": 53340 }, { "epoch": 12.78, "learning_rate": 9.637724956675274e-05, "loss": 0.1584, "step": 53350 }, { "epoch": 12.78, "learning_rate": 9.637590798320957e-05, "loss": 0.1907, "step": 53360 }, { "epoch": 12.78, "learning_rate": 9.63745661606446e-05, "loss": 0.1951, "step": 53370 }, { "epoch": 12.78, "learning_rate": 9.637322409906472e-05, "loss": 0.1753, "step": 53380 }, { "epoch": 12.78, "learning_rate": 9.637188179847686e-05, "loss": 0.1852, "step": 53390 }, { "epoch": 12.79, "learning_rate": 9.637053925888794e-05, "loss": 0.1764, "step": 53400 }, { "epoch": 12.79, "learning_rate": 9.636919648030487e-05, "loss": 0.1877, "step": 53410 }, { "epoch": 12.79, "learning_rate": 9.636785346273456e-05, "loss": 0.2093, "step": 53420 }, { "epoch": 12.79, "learning_rate": 9.636651020618397e-05, "loss": 0.1828, "step": 53430 }, { "epoch": 12.8, "learning_rate": 9.636516671065998e-05, "loss": 0.199, "step": 53440 }, { "epoch": 12.8, "learning_rate": 9.636382297616954e-05, "loss": 0.2495, "step": 53450 }, { "epoch": 12.8, "learning_rate": 9.636247900271957e-05, "loss": 0.1378, "step": 53460 }, { "epoch": 12.8, "learning_rate": 9.636113479031699e-05, "loss": 0.2307, "step": 53470 }, { "epoch": 12.81, "learning_rate": 9.635979033896874e-05, "loss": 0.1492, "step": 53480 }, { "epoch": 12.81, "learning_rate": 9.635844564868172e-05, "loss": 0.1511, "step": 53490 }, { "epoch": 12.81, "learning_rate": 9.635710071946291e-05, "loss": 0.1936, "step": 53500 }, { "epoch": 12.81, "learning_rate": 9.635575555131922e-05, "loss": 0.1418, "step": 53510 }, { "epoch": 12.81, "learning_rate": 9.635441014425757e-05, "loss": 0.239, "step": 53520 }, { "epoch": 12.82, "learning_rate": 9.635306449828489e-05, "loss": 0.1897, "step": 53530 }, { "epoch": 12.82, "learning_rate": 9.635171861340813e-05, "loss": 0.1846, "step": 53540 }, { "epoch": 12.82, "learning_rate": 9.635037248963423e-05, "loss": 0.1554, "step": 53550 }, { "epoch": 12.82, "learning_rate": 9.634902612697014e-05, "loss": 0.1771, "step": 53560 }, { "epoch": 12.83, "learning_rate": 9.634767952542277e-05, "loss": 0.1778, "step": 53570 }, { "epoch": 12.83, "learning_rate": 9.634633268499906e-05, "loss": 0.2054, "step": 53580 }, { "epoch": 12.83, "learning_rate": 9.634498560570598e-05, "loss": 0.1422, "step": 53590 }, { "epoch": 12.83, "learning_rate": 9.634363828755044e-05, "loss": 0.1581, "step": 53600 }, { "epoch": 12.84, "learning_rate": 9.634229073053942e-05, "loss": 0.1731, "step": 53610 }, { "epoch": 12.84, "learning_rate": 9.634094293467983e-05, "loss": 0.1183, "step": 53620 }, { "epoch": 12.84, "learning_rate": 9.633959489997864e-05, "loss": 0.2081, "step": 53630 }, { "epoch": 12.84, "learning_rate": 9.633824662644279e-05, "loss": 0.1825, "step": 53640 }, { "epoch": 12.84, "learning_rate": 9.633689811407925e-05, "loss": 0.192, "step": 53650 }, { "epoch": 12.85, "learning_rate": 9.633554936289492e-05, "loss": 0.1803, "step": 53660 }, { "epoch": 12.85, "learning_rate": 9.633420037289679e-05, "loss": 0.1955, "step": 53670 }, { "epoch": 12.85, "learning_rate": 9.633285114409181e-05, "loss": 0.1599, "step": 53680 }, { "epoch": 12.85, "learning_rate": 9.633150167648693e-05, "loss": 0.1813, "step": 53690 }, { "epoch": 12.86, "learning_rate": 9.633015197008908e-05, "loss": 0.1989, "step": 53700 }, { "epoch": 12.86, "learning_rate": 9.632880202490526e-05, "loss": 0.1662, "step": 53710 }, { "epoch": 12.86, "learning_rate": 9.63274518409424e-05, "loss": 0.1112, "step": 53720 }, { "epoch": 12.86, "learning_rate": 9.632610141820748e-05, "loss": 0.1735, "step": 53730 }, { "epoch": 12.86, "learning_rate": 9.632475075670743e-05, "loss": 0.2018, "step": 53740 }, { "epoch": 12.87, "learning_rate": 9.632339985644923e-05, "loss": 0.1391, "step": 53750 }, { "epoch": 12.87, "learning_rate": 9.632204871743984e-05, "loss": 0.2103, "step": 53760 }, { "epoch": 12.87, "learning_rate": 9.632069733968623e-05, "loss": 0.1361, "step": 53770 }, { "epoch": 12.87, "learning_rate": 9.631934572319535e-05, "loss": 0.1318, "step": 53780 }, { "epoch": 12.88, "learning_rate": 9.631799386797417e-05, "loss": 0.2063, "step": 53790 }, { "epoch": 12.88, "learning_rate": 9.631664177402968e-05, "loss": 0.1425, "step": 53800 }, { "epoch": 12.88, "learning_rate": 9.631528944136882e-05, "loss": 0.1645, "step": 53810 }, { "epoch": 12.88, "learning_rate": 9.631393686999858e-05, "loss": 0.1837, "step": 53820 }, { "epoch": 12.89, "learning_rate": 9.631258405992592e-05, "loss": 0.1414, "step": 53830 }, { "epoch": 12.89, "learning_rate": 9.631123101115781e-05, "loss": 0.1971, "step": 53840 }, { "epoch": 12.89, "learning_rate": 9.630987772370123e-05, "loss": 0.1741, "step": 53850 }, { "epoch": 12.89, "learning_rate": 9.630852419756315e-05, "loss": 0.1763, "step": 53860 }, { "epoch": 12.89, "learning_rate": 9.630717043275055e-05, "loss": 0.2282, "step": 53870 }, { "epoch": 12.9, "learning_rate": 9.630581642927042e-05, "loss": 0.2278, "step": 53880 }, { "epoch": 12.9, "learning_rate": 9.63044621871297e-05, "loss": 0.2213, "step": 53890 }, { "epoch": 12.9, "learning_rate": 9.630310770633542e-05, "loss": 0.1383, "step": 53900 }, { "epoch": 12.9, "learning_rate": 9.630175298689453e-05, "loss": 0.1913, "step": 53910 }, { "epoch": 12.91, "learning_rate": 9.6300398028814e-05, "loss": 0.1534, "step": 53920 }, { "epoch": 12.91, "learning_rate": 9.629904283210086e-05, "loss": 0.1298, "step": 53930 }, { "epoch": 12.91, "learning_rate": 9.629768739676203e-05, "loss": 0.1723, "step": 53940 }, { "epoch": 12.91, "learning_rate": 9.629633172280457e-05, "loss": 0.1781, "step": 53950 }, { "epoch": 12.91, "learning_rate": 9.62949758102354e-05, "loss": 0.1157, "step": 53960 }, { "epoch": 12.92, "learning_rate": 9.629361965906155e-05, "loss": 0.1796, "step": 53970 }, { "epoch": 12.92, "learning_rate": 9.629226326929e-05, "loss": 0.1297, "step": 53980 }, { "epoch": 12.92, "learning_rate": 9.629090664092773e-05, "loss": 0.1304, "step": 53990 }, { "epoch": 12.92, "learning_rate": 9.628954977398175e-05, "loss": 0.123, "step": 54000 }, { "epoch": 12.93, "learning_rate": 9.628819266845904e-05, "loss": 0.1088, "step": 54010 }, { "epoch": 12.93, "learning_rate": 9.62868353243666e-05, "loss": 0.1758, "step": 54020 }, { "epoch": 12.93, "learning_rate": 9.628547774171142e-05, "loss": 0.1478, "step": 54030 }, { "epoch": 12.93, "learning_rate": 9.628411992050049e-05, "loss": 0.1642, "step": 54040 }, { "epoch": 12.94, "learning_rate": 9.628276186074083e-05, "loss": 0.1706, "step": 54050 }, { "epoch": 12.94, "learning_rate": 9.628140356243943e-05, "loss": 0.1858, "step": 54060 }, { "epoch": 12.94, "learning_rate": 9.628004502560329e-05, "loss": 0.2148, "step": 54070 }, { "epoch": 12.94, "learning_rate": 9.627868625023942e-05, "loss": 0.1759, "step": 54080 }, { "epoch": 12.94, "learning_rate": 9.627732723635478e-05, "loss": 0.1213, "step": 54090 }, { "epoch": 12.95, "learning_rate": 9.627596798395644e-05, "loss": 0.1583, "step": 54100 }, { "epoch": 12.95, "learning_rate": 9.627460849305136e-05, "loss": 0.168, "step": 54110 }, { "epoch": 13.0, "learning_rate": 9.627324876364658e-05, "loss": 0.2142, "step": 54120 }, { "epoch": 13.0, "learning_rate": 9.627188879574908e-05, "loss": 0.1404, "step": 54130 }, { "epoch": 13.0, "learning_rate": 9.627052858936587e-05, "loss": 0.2054, "step": 54140 }, { "epoch": 13.01, "learning_rate": 9.626916814450397e-05, "loss": 0.2181, "step": 54150 }, { "epoch": 13.01, "learning_rate": 9.62678074611704e-05, "loss": 0.1877, "step": 54160 }, { "epoch": 13.01, "learning_rate": 9.626644653937216e-05, "loss": 0.1443, "step": 54170 }, { "epoch": 13.01, "learning_rate": 9.626508537911625e-05, "loss": 0.2032, "step": 54180 }, { "epoch": 13.02, "learning_rate": 9.626372398040973e-05, "loss": 0.1915, "step": 54190 }, { "epoch": 13.02, "learning_rate": 9.626236234325958e-05, "loss": 0.1882, "step": 54200 }, { "epoch": 13.02, "learning_rate": 9.626100046767282e-05, "loss": 0.1579, "step": 54210 }, { "epoch": 13.02, "learning_rate": 9.625963835365649e-05, "loss": 0.1571, "step": 54220 }, { "epoch": 13.03, "learning_rate": 9.62582760012176e-05, "loss": 0.1883, "step": 54230 }, { "epoch": 13.03, "learning_rate": 9.625691341036314e-05, "loss": 0.1553, "step": 54240 }, { "epoch": 13.03, "learning_rate": 9.625555058110018e-05, "loss": 0.1754, "step": 54250 }, { "epoch": 13.03, "learning_rate": 9.625418751343573e-05, "loss": 0.1728, "step": 54260 }, { "epoch": 13.03, "learning_rate": 9.625282420737681e-05, "loss": 0.1572, "step": 54270 }, { "epoch": 13.04, "learning_rate": 9.625146066293045e-05, "loss": 0.1889, "step": 54280 }, { "epoch": 13.04, "learning_rate": 9.625009688010367e-05, "loss": 0.176, "step": 54290 }, { "epoch": 13.04, "learning_rate": 9.62487328589035e-05, "loss": 0.1858, "step": 54300 }, { "epoch": 13.04, "learning_rate": 9.624736859933698e-05, "loss": 0.1194, "step": 54310 }, { "epoch": 13.05, "learning_rate": 9.624600410141113e-05, "loss": 0.1553, "step": 54320 }, { "epoch": 13.05, "learning_rate": 9.624463936513299e-05, "loss": 0.1681, "step": 54330 }, { "epoch": 13.05, "learning_rate": 9.62432743905096e-05, "loss": 0.1531, "step": 54340 }, { "epoch": 13.05, "learning_rate": 9.624190917754799e-05, "loss": 0.1716, "step": 54350 }, { "epoch": 13.06, "learning_rate": 9.624054372625518e-05, "loss": 0.1624, "step": 54360 }, { "epoch": 13.06, "learning_rate": 9.623917803663823e-05, "loss": 0.2272, "step": 54370 }, { "epoch": 13.06, "learning_rate": 9.623781210870417e-05, "loss": 0.1214, "step": 54380 }, { "epoch": 13.06, "learning_rate": 9.623644594246005e-05, "loss": 0.154, "step": 54390 }, { "epoch": 13.06, "learning_rate": 9.623507953791287e-05, "loss": 0.1845, "step": 54400 }, { "epoch": 13.07, "learning_rate": 9.623371289506973e-05, "loss": 0.1846, "step": 54410 }, { "epoch": 13.07, "learning_rate": 9.623234601393762e-05, "loss": 0.1398, "step": 54420 }, { "epoch": 13.07, "learning_rate": 9.623097889452363e-05, "loss": 0.1647, "step": 54430 }, { "epoch": 13.07, "learning_rate": 9.62296115368348e-05, "loss": 0.1822, "step": 54440 }, { "epoch": 13.08, "learning_rate": 9.622824394087815e-05, "loss": 0.1318, "step": 54450 }, { "epoch": 13.08, "learning_rate": 9.622687610666075e-05, "loss": 0.1598, "step": 54460 }, { "epoch": 13.08, "learning_rate": 9.622550803418965e-05, "loss": 0.2095, "step": 54470 }, { "epoch": 13.08, "learning_rate": 9.622413972347188e-05, "loss": 0.1139, "step": 54480 }, { "epoch": 13.08, "learning_rate": 9.622277117451452e-05, "loss": 0.1298, "step": 54490 }, { "epoch": 13.09, "learning_rate": 9.62214023873246e-05, "loss": 0.1467, "step": 54500 }, { "epoch": 13.09, "learning_rate": 9.62200333619092e-05, "loss": 0.1863, "step": 54510 }, { "epoch": 13.09, "learning_rate": 9.621866409827536e-05, "loss": 0.1451, "step": 54520 }, { "epoch": 13.09, "learning_rate": 9.621729459643013e-05, "loss": 0.2273, "step": 54530 }, { "epoch": 13.1, "learning_rate": 9.621592485638058e-05, "loss": 0.1518, "step": 54540 }, { "epoch": 13.1, "learning_rate": 9.621455487813378e-05, "loss": 0.1951, "step": 54550 }, { "epoch": 13.1, "learning_rate": 9.621318466169675e-05, "loss": 0.1729, "step": 54560 }, { "epoch": 13.1, "learning_rate": 9.62118142070766e-05, "loss": 0.1364, "step": 54570 }, { "epoch": 13.11, "learning_rate": 9.621044351428037e-05, "loss": 0.1415, "step": 54580 }, { "epoch": 13.11, "learning_rate": 9.620907258331513e-05, "loss": 0.1615, "step": 54590 }, { "epoch": 13.11, "learning_rate": 9.620770141418793e-05, "loss": 0.1574, "step": 54600 }, { "epoch": 13.11, "learning_rate": 9.620633000690587e-05, "loss": 0.1776, "step": 54610 }, { "epoch": 13.11, "learning_rate": 9.620495836147598e-05, "loss": 0.1423, "step": 54620 }, { "epoch": 13.12, "learning_rate": 9.620358647790537e-05, "loss": 0.1417, "step": 54630 }, { "epoch": 13.12, "learning_rate": 9.620221435620107e-05, "loss": 0.1612, "step": 54640 }, { "epoch": 13.12, "learning_rate": 9.620084199637019e-05, "loss": 0.2335, "step": 54650 }, { "epoch": 13.12, "learning_rate": 9.619946939841977e-05, "loss": 0.1507, "step": 54660 }, { "epoch": 13.13, "learning_rate": 9.61980965623569e-05, "loss": 0.1579, "step": 54670 }, { "epoch": 13.13, "learning_rate": 9.619672348818864e-05, "loss": 0.1573, "step": 54680 }, { "epoch": 13.13, "learning_rate": 9.619535017592211e-05, "loss": 0.2068, "step": 54690 }, { "epoch": 13.13, "learning_rate": 9.619397662556435e-05, "loss": 0.1075, "step": 54700 }, { "epoch": 13.14, "learning_rate": 9.619260283712244e-05, "loss": 0.1416, "step": 54710 }, { "epoch": 13.14, "learning_rate": 9.619122881060347e-05, "loss": 0.1714, "step": 54720 }, { "epoch": 13.14, "learning_rate": 9.618985454601453e-05, "loss": 0.1231, "step": 54730 }, { "epoch": 13.14, "learning_rate": 9.618848004336267e-05, "loss": 0.1539, "step": 54740 }, { "epoch": 13.14, "learning_rate": 9.618710530265503e-05, "loss": 0.206, "step": 54750 }, { "epoch": 13.15, "learning_rate": 9.618573032389863e-05, "loss": 0.1791, "step": 54760 }, { "epoch": 13.15, "learning_rate": 9.618435510710063e-05, "loss": 0.122, "step": 54770 }, { "epoch": 13.15, "learning_rate": 9.618297965226805e-05, "loss": 0.1374, "step": 54780 }, { "epoch": 13.15, "learning_rate": 9.6181603959408e-05, "loss": 0.1486, "step": 54790 }, { "epoch": 13.16, "learning_rate": 9.61802280285276e-05, "loss": 0.1774, "step": 54800 }, { "epoch": 13.16, "learning_rate": 9.617885185963391e-05, "loss": 0.1957, "step": 54810 }, { "epoch": 13.16, "learning_rate": 9.617747545273402e-05, "loss": 0.1926, "step": 54820 }, { "epoch": 13.16, "learning_rate": 9.617609880783505e-05, "loss": 0.1168, "step": 54830 }, { "epoch": 13.16, "learning_rate": 9.617472192494408e-05, "loss": 0.1894, "step": 54840 }, { "epoch": 13.17, "learning_rate": 9.61733448040682e-05, "loss": 0.1543, "step": 54850 }, { "epoch": 13.17, "learning_rate": 9.617196744521451e-05, "loss": 0.1804, "step": 54860 }, { "epoch": 13.17, "learning_rate": 9.617058984839014e-05, "loss": 0.182, "step": 54870 }, { "epoch": 13.17, "learning_rate": 9.616921201360214e-05, "loss": 0.1531, "step": 54880 }, { "epoch": 13.18, "learning_rate": 9.616783394085763e-05, "loss": 0.176, "step": 54890 }, { "epoch": 13.18, "learning_rate": 9.616645563016373e-05, "loss": 0.1175, "step": 54900 }, { "epoch": 13.18, "learning_rate": 9.616507708152753e-05, "loss": 0.1757, "step": 54910 }, { "epoch": 13.18, "learning_rate": 9.616369829495615e-05, "loss": 0.1358, "step": 54920 }, { "epoch": 13.19, "learning_rate": 9.616231927045666e-05, "loss": 0.159, "step": 54930 }, { "epoch": 13.19, "learning_rate": 9.616094000803621e-05, "loss": 0.0997, "step": 54940 }, { "epoch": 13.19, "learning_rate": 9.615956050770187e-05, "loss": 0.1577, "step": 54950 }, { "epoch": 13.19, "learning_rate": 9.61581807694608e-05, "loss": 0.1407, "step": 54960 }, { "epoch": 13.19, "learning_rate": 9.615680079332006e-05, "loss": 0.1691, "step": 54970 }, { "epoch": 13.2, "learning_rate": 9.615542057928677e-05, "loss": 0.1565, "step": 54980 }, { "epoch": 13.2, "learning_rate": 9.615404012736808e-05, "loss": 0.1894, "step": 54990 }, { "epoch": 13.2, "learning_rate": 9.615265943757106e-05, "loss": 0.1808, "step": 55000 }, { "epoch": 13.2, "learning_rate": 9.615127850990287e-05, "loss": 0.1915, "step": 55010 }, { "epoch": 13.21, "learning_rate": 9.61498973443706e-05, "loss": 0.1289, "step": 55020 }, { "epoch": 13.21, "learning_rate": 9.614851594098136e-05, "loss": 0.1686, "step": 55030 }, { "epoch": 13.21, "learning_rate": 9.614713429974229e-05, "loss": 0.1312, "step": 55040 }, { "epoch": 13.21, "learning_rate": 9.614575242066051e-05, "loss": 0.2146, "step": 55050 }, { "epoch": 13.22, "learning_rate": 9.614437030374312e-05, "loss": 0.1332, "step": 55060 }, { "epoch": 13.22, "learning_rate": 9.614298794899727e-05, "loss": 0.1421, "step": 55070 }, { "epoch": 13.22, "learning_rate": 9.614160535643008e-05, "loss": 0.158, "step": 55080 }, { "epoch": 13.22, "learning_rate": 9.614022252604867e-05, "loss": 0.1624, "step": 55090 }, { "epoch": 13.22, "learning_rate": 9.613883945786015e-05, "loss": 0.1724, "step": 55100 }, { "epoch": 13.23, "learning_rate": 9.613745615187169e-05, "loss": 0.1734, "step": 55110 }, { "epoch": 13.23, "learning_rate": 9.613607260809037e-05, "loss": 0.1599, "step": 55120 }, { "epoch": 13.23, "learning_rate": 9.613468882652337e-05, "loss": 0.1425, "step": 55130 }, { "epoch": 13.23, "learning_rate": 9.613330480717778e-05, "loss": 0.17, "step": 55140 }, { "epoch": 13.24, "learning_rate": 9.613192055006076e-05, "loss": 0.183, "step": 55150 }, { "epoch": 13.24, "learning_rate": 9.613053605517943e-05, "loss": 0.178, "step": 55160 }, { "epoch": 13.24, "learning_rate": 9.612915132254095e-05, "loss": 0.1696, "step": 55170 }, { "epoch": 13.24, "learning_rate": 9.612776635215241e-05, "loss": 0.1712, "step": 55180 }, { "epoch": 13.24, "learning_rate": 9.6126381144021e-05, "loss": 0.1102, "step": 55190 }, { "epoch": 13.25, "learning_rate": 9.612499569815383e-05, "loss": 0.1524, "step": 55200 }, { "epoch": 13.25, "learning_rate": 9.612361001455805e-05, "loss": 0.1181, "step": 55210 }, { "epoch": 13.25, "learning_rate": 9.612222409324079e-05, "loss": 0.1773, "step": 55220 }, { "epoch": 13.25, "learning_rate": 9.612083793420921e-05, "loss": 0.1112, "step": 55230 }, { "epoch": 13.26, "learning_rate": 9.611945153747044e-05, "loss": 0.1439, "step": 55240 }, { "epoch": 13.26, "learning_rate": 9.611806490303163e-05, "loss": 0.106, "step": 55250 }, { "epoch": 13.26, "learning_rate": 9.611667803089993e-05, "loss": 0.1701, "step": 55260 }, { "epoch": 13.26, "learning_rate": 9.611529092108248e-05, "loss": 0.2111, "step": 55270 }, { "epoch": 13.27, "learning_rate": 9.611390357358644e-05, "loss": 0.1696, "step": 55280 }, { "epoch": 13.27, "learning_rate": 9.611251598841895e-05, "loss": 0.1873, "step": 55290 }, { "epoch": 13.27, "learning_rate": 9.611112816558718e-05, "loss": 0.1417, "step": 55300 }, { "epoch": 13.27, "learning_rate": 9.610974010509827e-05, "loss": 0.1484, "step": 55310 }, { "epoch": 13.27, "learning_rate": 9.610835180695936e-05, "loss": 0.1161, "step": 55320 }, { "epoch": 13.28, "learning_rate": 9.610696327117763e-05, "loss": 0.1257, "step": 55330 }, { "epoch": 13.28, "learning_rate": 9.610557449776023e-05, "loss": 0.166, "step": 55340 }, { "epoch": 13.28, "learning_rate": 9.61041854867143e-05, "loss": 0.1474, "step": 55350 }, { "epoch": 13.28, "learning_rate": 9.610279623804701e-05, "loss": 0.1036, "step": 55360 }, { "epoch": 13.29, "learning_rate": 9.610140675176554e-05, "loss": 0.145, "step": 55370 }, { "epoch": 13.29, "learning_rate": 9.610001702787704e-05, "loss": 0.1856, "step": 55380 }, { "epoch": 13.29, "learning_rate": 9.609862706638864e-05, "loss": 0.1414, "step": 55390 }, { "epoch": 13.29, "learning_rate": 9.609723686730753e-05, "loss": 0.1579, "step": 55400 }, { "epoch": 13.3, "learning_rate": 9.60958464306409e-05, "loss": 0.1175, "step": 55410 }, { "epoch": 13.3, "learning_rate": 9.609445575639589e-05, "loss": 0.1425, "step": 55420 }, { "epoch": 13.3, "learning_rate": 9.609306484457965e-05, "loss": 0.1288, "step": 55430 }, { "epoch": 13.3, "learning_rate": 9.609167369519938e-05, "loss": 0.1517, "step": 55440 }, { "epoch": 13.3, "learning_rate": 9.609028230826225e-05, "loss": 0.1645, "step": 55450 }, { "epoch": 13.31, "learning_rate": 9.60888906837754e-05, "loss": 0.1485, "step": 55460 }, { "epoch": 13.31, "learning_rate": 9.608749882174604e-05, "loss": 0.1397, "step": 55470 }, { "epoch": 13.31, "learning_rate": 9.608610672218132e-05, "loss": 0.1301, "step": 55480 }, { "epoch": 13.31, "learning_rate": 9.608471438508841e-05, "loss": 0.1535, "step": 55490 }, { "epoch": 13.32, "learning_rate": 9.60833218104745e-05, "loss": 0.181, "step": 55500 }, { "epoch": 13.32, "learning_rate": 9.608192899834677e-05, "loss": 0.1079, "step": 55510 }, { "epoch": 13.32, "learning_rate": 9.608053594871239e-05, "loss": 0.1483, "step": 55520 }, { "epoch": 13.32, "learning_rate": 9.607914266157854e-05, "loss": 0.1655, "step": 55530 }, { "epoch": 13.32, "learning_rate": 9.60777491369524e-05, "loss": 0.1371, "step": 55540 }, { "epoch": 13.33, "learning_rate": 9.607635537484117e-05, "loss": 0.1131, "step": 55550 }, { "epoch": 13.33, "learning_rate": 9.607496137525202e-05, "loss": 0.0995, "step": 55560 }, { "epoch": 13.33, "learning_rate": 9.607356713819212e-05, "loss": 0.1858, "step": 55570 }, { "epoch": 13.33, "learning_rate": 9.607217266366868e-05, "loss": 0.1456, "step": 55580 }, { "epoch": 13.34, "learning_rate": 9.607077795168887e-05, "loss": 0.1437, "step": 55590 }, { "epoch": 13.34, "learning_rate": 9.606938300225989e-05, "loss": 0.1221, "step": 55600 }, { "epoch": 13.34, "learning_rate": 9.606798781538892e-05, "loss": 0.0969, "step": 55610 }, { "epoch": 13.34, "learning_rate": 9.606659239108315e-05, "loss": 0.1244, "step": 55620 }, { "epoch": 13.35, "learning_rate": 9.60651967293498e-05, "loss": 0.2022, "step": 55630 }, { "epoch": 13.35, "learning_rate": 9.606380083019603e-05, "loss": 0.1439, "step": 55640 }, { "epoch": 13.35, "learning_rate": 9.606240469362903e-05, "loss": 0.1812, "step": 55650 }, { "epoch": 13.35, "learning_rate": 9.606100831965603e-05, "loss": 0.1613, "step": 55660 }, { "epoch": 13.35, "learning_rate": 9.60596117082842e-05, "loss": 0.1492, "step": 55670 }, { "epoch": 13.36, "learning_rate": 9.605821485952075e-05, "loss": 0.1191, "step": 55680 }, { "epoch": 13.36, "learning_rate": 9.605681777337288e-05, "loss": 0.1168, "step": 55690 }, { "epoch": 13.36, "learning_rate": 9.605542044984778e-05, "loss": 0.161, "step": 55700 }, { "epoch": 13.36, "learning_rate": 9.605402288895265e-05, "loss": 0.1382, "step": 55710 }, { "epoch": 13.37, "learning_rate": 9.605262509069471e-05, "loss": 0.1392, "step": 55720 }, { "epoch": 13.37, "learning_rate": 9.605122705508116e-05, "loss": 0.1501, "step": 55730 }, { "epoch": 13.37, "learning_rate": 9.60498287821192e-05, "loss": 0.1175, "step": 55740 }, { "epoch": 13.37, "learning_rate": 9.604843027181602e-05, "loss": 0.1284, "step": 55750 }, { "epoch": 13.38, "learning_rate": 9.604703152417887e-05, "loss": 0.1376, "step": 55760 }, { "epoch": 13.38, "learning_rate": 9.604563253921493e-05, "loss": 0.1155, "step": 55770 }, { "epoch": 13.38, "learning_rate": 9.60442333169314e-05, "loss": 0.1309, "step": 55780 }, { "epoch": 13.38, "learning_rate": 9.604283385733553e-05, "loss": 0.1197, "step": 55790 }, { "epoch": 13.38, "learning_rate": 9.604143416043449e-05, "loss": 0.1903, "step": 55800 }, { "epoch": 13.39, "learning_rate": 9.604003422623552e-05, "loss": 0.1226, "step": 55810 }, { "epoch": 13.39, "learning_rate": 9.603863405474582e-05, "loss": 0.1491, "step": 55820 }, { "epoch": 13.39, "learning_rate": 9.603723364597261e-05, "loss": 0.1172, "step": 55830 }, { "epoch": 13.39, "learning_rate": 9.603583299992313e-05, "loss": 0.1075, "step": 55840 }, { "epoch": 13.4, "learning_rate": 9.603443211660459e-05, "loss": 0.142, "step": 55850 }, { "epoch": 13.4, "learning_rate": 9.603303099602418e-05, "loss": 0.2034, "step": 55860 }, { "epoch": 13.4, "learning_rate": 9.603162963818915e-05, "loss": 0.1309, "step": 55870 }, { "epoch": 13.4, "learning_rate": 9.603022804310672e-05, "loss": 0.1321, "step": 55880 }, { "epoch": 13.4, "learning_rate": 9.602882621078411e-05, "loss": 0.1262, "step": 55890 }, { "epoch": 13.41, "learning_rate": 9.602742414122853e-05, "loss": 0.1612, "step": 55900 }, { "epoch": 13.41, "learning_rate": 9.602602183444725e-05, "loss": 0.1408, "step": 55910 }, { "epoch": 13.41, "learning_rate": 9.602461929044744e-05, "loss": 0.1489, "step": 55920 }, { "epoch": 13.41, "learning_rate": 9.602321650923637e-05, "loss": 0.1414, "step": 55930 }, { "epoch": 13.42, "learning_rate": 9.602181349082126e-05, "loss": 0.1147, "step": 55940 }, { "epoch": 13.42, "learning_rate": 9.602041023520935e-05, "loss": 0.1221, "step": 55950 }, { "epoch": 13.42, "learning_rate": 9.601900674240785e-05, "loss": 0.1825, "step": 55960 }, { "epoch": 13.42, "learning_rate": 9.6017603012424e-05, "loss": 0.1382, "step": 55970 }, { "epoch": 13.43, "learning_rate": 9.601619904526505e-05, "loss": 0.178, "step": 55980 }, { "epoch": 13.43, "learning_rate": 9.60147948409382e-05, "loss": 0.14, "step": 55990 }, { "epoch": 13.43, "learning_rate": 9.601339039945074e-05, "loss": 0.1155, "step": 56000 }, { "epoch": 13.43, "learning_rate": 9.601198572080987e-05, "loss": 0.108, "step": 56010 }, { "epoch": 13.43, "learning_rate": 9.601058080502285e-05, "loss": 0.1321, "step": 56020 }, { "epoch": 13.44, "learning_rate": 9.60091756520969e-05, "loss": 0.1359, "step": 56030 }, { "epoch": 13.44, "learning_rate": 9.600777026203927e-05, "loss": 0.1131, "step": 56040 }, { "epoch": 13.44, "learning_rate": 9.600636463485721e-05, "loss": 0.1114, "step": 56050 }, { "epoch": 13.44, "learning_rate": 9.600495877055798e-05, "loss": 0.0959, "step": 56060 }, { "epoch": 13.45, "learning_rate": 9.60035526691488e-05, "loss": 0.1682, "step": 56070 }, { "epoch": 13.45, "learning_rate": 9.60021463306369e-05, "loss": 0.1745, "step": 56080 }, { "epoch": 13.45, "learning_rate": 9.600073975502959e-05, "loss": 0.1407, "step": 56090 }, { "epoch": 13.45, "learning_rate": 9.599933294233406e-05, "loss": 0.1147, "step": 56100 }, { "epoch": 13.45, "learning_rate": 9.599792589255759e-05, "loss": 0.1457, "step": 56110 }, { "epoch": 13.46, "learning_rate": 9.599651860570743e-05, "loss": 0.1463, "step": 56120 }, { "epoch": 13.46, "learning_rate": 9.599511108179082e-05, "loss": 0.1431, "step": 56130 }, { "epoch": 13.46, "learning_rate": 9.599370332081503e-05, "loss": 0.1299, "step": 56140 }, { "epoch": 13.46, "learning_rate": 9.59922953227873e-05, "loss": 0.1522, "step": 56150 }, { "epoch": 13.47, "learning_rate": 9.599088708771491e-05, "loss": 0.1908, "step": 56160 }, { "epoch": 13.47, "learning_rate": 9.59894786156051e-05, "loss": 0.1507, "step": 56170 }, { "epoch": 13.47, "learning_rate": 9.598806990646513e-05, "loss": 0.1191, "step": 56180 }, { "epoch": 13.47, "learning_rate": 9.598666096030226e-05, "loss": 0.1131, "step": 56190 }, { "epoch": 13.48, "learning_rate": 9.598525177712375e-05, "loss": 0.171, "step": 56200 }, { "epoch": 13.48, "learning_rate": 9.598384235693688e-05, "loss": 0.141, "step": 56210 }, { "epoch": 13.48, "learning_rate": 9.598243269974889e-05, "loss": 0.1479, "step": 56220 }, { "epoch": 13.48, "learning_rate": 9.598102280556706e-05, "loss": 0.0971, "step": 56230 }, { "epoch": 13.48, "learning_rate": 9.597961267439867e-05, "loss": 0.1535, "step": 56240 }, { "epoch": 13.49, "learning_rate": 9.597820230625097e-05, "loss": 0.1828, "step": 56250 }, { "epoch": 13.49, "learning_rate": 9.597679170113121e-05, "loss": 0.1912, "step": 56260 }, { "epoch": 13.49, "learning_rate": 9.59753808590467e-05, "loss": 0.1086, "step": 56270 }, { "epoch": 13.49, "learning_rate": 9.597396978000468e-05, "loss": 0.1551, "step": 56280 }, { "epoch": 13.5, "learning_rate": 9.597255846401243e-05, "loss": 0.1664, "step": 56290 }, { "epoch": 13.5, "learning_rate": 9.597114691107725e-05, "loss": 0.1458, "step": 56300 }, { "epoch": 13.5, "learning_rate": 9.596973512120638e-05, "loss": 0.1558, "step": 56310 }, { "epoch": 13.5, "learning_rate": 9.596832309440712e-05, "loss": 0.1509, "step": 56320 }, { "epoch": 13.51, "learning_rate": 9.596691083068673e-05, "loss": 0.1692, "step": 56330 }, { "epoch": 13.51, "learning_rate": 9.596549833005251e-05, "loss": 0.172, "step": 56340 }, { "epoch": 13.51, "learning_rate": 9.596408559251171e-05, "loss": 0.1486, "step": 56350 }, { "epoch": 13.51, "learning_rate": 9.596267261807163e-05, "loss": 0.1454, "step": 56360 }, { "epoch": 13.51, "learning_rate": 9.596125940673956e-05, "loss": 0.1351, "step": 56370 }, { "epoch": 13.52, "learning_rate": 9.595984595852279e-05, "loss": 0.1327, "step": 56380 }, { "epoch": 13.52, "learning_rate": 9.595843227342856e-05, "loss": 0.185, "step": 56390 }, { "epoch": 13.52, "learning_rate": 9.59570183514642e-05, "loss": 0.1879, "step": 56400 }, { "epoch": 13.52, "learning_rate": 9.595560419263699e-05, "loss": 0.1385, "step": 56410 }, { "epoch": 13.53, "learning_rate": 9.59541897969542e-05, "loss": 0.205, "step": 56420 }, { "epoch": 13.53, "learning_rate": 9.595277516442313e-05, "loss": 0.1877, "step": 56430 }, { "epoch": 13.53, "learning_rate": 9.595136029505108e-05, "loss": 0.1727, "step": 56440 }, { "epoch": 13.53, "learning_rate": 9.594994518884535e-05, "loss": 0.1399, "step": 56450 }, { "epoch": 13.53, "learning_rate": 9.594852984581319e-05, "loss": 0.2329, "step": 56460 }, { "epoch": 13.54, "learning_rate": 9.594711426596193e-05, "loss": 0.2129, "step": 56470 }, { "epoch": 13.54, "learning_rate": 9.594569844929888e-05, "loss": 0.1865, "step": 56480 }, { "epoch": 13.54, "learning_rate": 9.594428239583129e-05, "loss": 0.213, "step": 56490 }, { "epoch": 13.54, "learning_rate": 9.59428661055665e-05, "loss": 0.229, "step": 56500 }, { "epoch": 13.55, "learning_rate": 9.594144957851178e-05, "loss": 0.2328, "step": 56510 }, { "epoch": 13.55, "learning_rate": 9.594003281467445e-05, "loss": 0.2156, "step": 56520 }, { "epoch": 13.55, "learning_rate": 9.593861581406183e-05, "loss": 0.2443, "step": 56530 }, { "epoch": 13.55, "learning_rate": 9.593719857668118e-05, "loss": 0.2207, "step": 56540 }, { "epoch": 13.56, "learning_rate": 9.593578110253982e-05, "loss": 0.2396, "step": 56550 }, { "epoch": 13.56, "learning_rate": 9.593436339164506e-05, "loss": 0.1611, "step": 56560 }, { "epoch": 13.56, "learning_rate": 9.593294544400422e-05, "loss": 0.2241, "step": 56570 }, { "epoch": 13.56, "learning_rate": 9.593152725962458e-05, "loss": 0.1965, "step": 56580 }, { "epoch": 13.56, "learning_rate": 9.593010883851348e-05, "loss": 0.2, "step": 56590 }, { "epoch": 13.57, "learning_rate": 9.59286901806782e-05, "loss": 0.227, "step": 56600 }, { "epoch": 13.57, "learning_rate": 9.592727128612607e-05, "loss": 0.1518, "step": 56610 }, { "epoch": 13.57, "learning_rate": 9.59258521548644e-05, "loss": 0.1678, "step": 56620 }, { "epoch": 13.57, "learning_rate": 9.592443278690051e-05, "loss": 0.2325, "step": 56630 }, { "epoch": 13.58, "learning_rate": 9.592301318224171e-05, "loss": 0.1756, "step": 56640 }, { "epoch": 13.58, "learning_rate": 9.592159334089532e-05, "loss": 0.2098, "step": 56650 }, { "epoch": 13.58, "learning_rate": 9.592017326286866e-05, "loss": 0.1917, "step": 56660 }, { "epoch": 13.58, "learning_rate": 9.591875294816902e-05, "loss": 0.1771, "step": 56670 }, { "epoch": 13.59, "learning_rate": 9.591733239680376e-05, "loss": 0.2475, "step": 56680 }, { "epoch": 13.59, "learning_rate": 9.591591160878017e-05, "loss": 0.2509, "step": 56690 }, { "epoch": 13.59, "learning_rate": 9.59144905841056e-05, "loss": 0.1775, "step": 56700 }, { "epoch": 13.59, "learning_rate": 9.591306932278737e-05, "loss": 0.2185, "step": 56710 }, { "epoch": 13.59, "learning_rate": 9.591164782483277e-05, "loss": 0.1747, "step": 56720 }, { "epoch": 13.6, "learning_rate": 9.591022609024918e-05, "loss": 0.2252, "step": 56730 }, { "epoch": 13.6, "learning_rate": 9.590880411904388e-05, "loss": 0.2046, "step": 56740 }, { "epoch": 13.6, "learning_rate": 9.590738191122423e-05, "loss": 0.1782, "step": 56750 }, { "epoch": 13.6, "learning_rate": 9.590595946679755e-05, "loss": 0.1814, "step": 56760 }, { "epoch": 13.61, "learning_rate": 9.590453678577118e-05, "loss": 0.1877, "step": 56770 }, { "epoch": 13.61, "learning_rate": 9.590311386815244e-05, "loss": 0.2013, "step": 56780 }, { "epoch": 13.61, "learning_rate": 9.590169071394866e-05, "loss": 0.1486, "step": 56790 }, { "epoch": 13.61, "learning_rate": 9.59002673231672e-05, "loss": 0.1921, "step": 56800 }, { "epoch": 13.61, "learning_rate": 9.589884369581534e-05, "loss": 0.2368, "step": 56810 }, { "epoch": 13.62, "learning_rate": 9.589741983190048e-05, "loss": 0.2098, "step": 56820 }, { "epoch": 13.62, "learning_rate": 9.589599573142994e-05, "loss": 0.182, "step": 56830 }, { "epoch": 13.62, "learning_rate": 9.589457139441105e-05, "loss": 0.1771, "step": 56840 }, { "epoch": 13.62, "learning_rate": 9.589314682085116e-05, "loss": 0.2204, "step": 56850 }, { "epoch": 13.63, "learning_rate": 9.58917220107576e-05, "loss": 0.1851, "step": 56860 }, { "epoch": 13.63, "learning_rate": 9.589029696413772e-05, "loss": 0.2054, "step": 56870 }, { "epoch": 13.63, "learning_rate": 9.588887168099887e-05, "loss": 0.1661, "step": 56880 }, { "epoch": 13.63, "learning_rate": 9.58874461613484e-05, "loss": 0.1804, "step": 56890 }, { "epoch": 13.64, "learning_rate": 9.588602040519363e-05, "loss": 0.1972, "step": 56900 }, { "epoch": 13.64, "learning_rate": 9.588459441254194e-05, "loss": 0.2033, "step": 56910 }, { "epoch": 13.64, "learning_rate": 9.588316818340067e-05, "loss": 0.1369, "step": 56920 }, { "epoch": 13.64, "learning_rate": 9.588174171777715e-05, "loss": 0.1373, "step": 56930 }, { "epoch": 13.64, "learning_rate": 9.588031501567875e-05, "loss": 0.1486, "step": 56940 }, { "epoch": 13.65, "learning_rate": 9.587888807711284e-05, "loss": 0.1867, "step": 56950 }, { "epoch": 13.65, "learning_rate": 9.587746090208676e-05, "loss": 0.178, "step": 56960 }, { "epoch": 13.65, "learning_rate": 9.587603349060786e-05, "loss": 0.1685, "step": 56970 }, { "epoch": 13.65, "learning_rate": 9.587460584268349e-05, "loss": 0.199, "step": 56980 }, { "epoch": 13.66, "learning_rate": 9.587317795832102e-05, "loss": 0.1809, "step": 56990 }, { "epoch": 13.66, "learning_rate": 9.587174983752781e-05, "loss": 0.1662, "step": 57000 }, { "epoch": 13.66, "learning_rate": 9.58703214803112e-05, "loss": 0.1805, "step": 57010 }, { "epoch": 13.66, "learning_rate": 9.58688928866786e-05, "loss": 0.2058, "step": 57020 }, { "epoch": 13.67, "learning_rate": 9.586746405663734e-05, "loss": 0.2324, "step": 57030 }, { "epoch": 13.67, "learning_rate": 9.586603499019476e-05, "loss": 0.202, "step": 57040 }, { "epoch": 13.67, "learning_rate": 9.586460568735826e-05, "loss": 0.1548, "step": 57050 }, { "epoch": 13.67, "learning_rate": 9.586317614813522e-05, "loss": 0.1992, "step": 57060 }, { "epoch": 13.67, "learning_rate": 9.586174637253297e-05, "loss": 0.1421, "step": 57070 }, { "epoch": 13.68, "learning_rate": 9.58603163605589e-05, "loss": 0.1999, "step": 57080 }, { "epoch": 13.68, "learning_rate": 9.585888611222039e-05, "loss": 0.2056, "step": 57090 }, { "epoch": 13.68, "learning_rate": 9.585745562752478e-05, "loss": 0.2024, "step": 57100 }, { "epoch": 13.68, "learning_rate": 9.585602490647947e-05, "loss": 0.1727, "step": 57110 }, { "epoch": 13.69, "learning_rate": 9.585459394909181e-05, "loss": 0.2269, "step": 57120 }, { "epoch": 13.69, "learning_rate": 9.585316275536919e-05, "loss": 0.1962, "step": 57130 }, { "epoch": 13.69, "learning_rate": 9.5851731325319e-05, "loss": 0.231, "step": 57140 }, { "epoch": 13.69, "learning_rate": 9.58502996589486e-05, "loss": 0.1531, "step": 57150 }, { "epoch": 13.69, "learning_rate": 9.584886775626537e-05, "loss": 0.1909, "step": 57160 }, { "epoch": 13.7, "learning_rate": 9.58474356172767e-05, "loss": 0.2169, "step": 57170 }, { "epoch": 13.7, "learning_rate": 9.584600324198996e-05, "loss": 0.2269, "step": 57180 }, { "epoch": 13.7, "learning_rate": 9.584457063041252e-05, "loss": 0.1266, "step": 57190 }, { "epoch": 13.7, "learning_rate": 9.584313778255179e-05, "loss": 0.1549, "step": 57200 }, { "epoch": 13.71, "learning_rate": 9.584170469841516e-05, "loss": 0.1686, "step": 57210 }, { "epoch": 13.71, "learning_rate": 9.584027137800997e-05, "loss": 0.2097, "step": 57220 }, { "epoch": 13.71, "learning_rate": 9.583883782134366e-05, "loss": 0.1232, "step": 57230 }, { "epoch": 13.71, "learning_rate": 9.583740402842359e-05, "loss": 0.206, "step": 57240 }, { "epoch": 13.72, "learning_rate": 9.583596999925717e-05, "loss": 0.2156, "step": 57250 }, { "epoch": 13.72, "learning_rate": 9.583453573385176e-05, "loss": 0.2339, "step": 57260 }, { "epoch": 13.72, "learning_rate": 9.583310123221478e-05, "loss": 0.1679, "step": 57270 }, { "epoch": 13.72, "learning_rate": 9.58316664943536e-05, "loss": 0.2264, "step": 57280 }, { "epoch": 13.72, "learning_rate": 9.583023152027564e-05, "loss": 0.1392, "step": 57290 }, { "epoch": 13.73, "learning_rate": 9.582879630998829e-05, "loss": 0.1394, "step": 57300 }, { "epoch": 13.73, "learning_rate": 9.582736086349893e-05, "loss": 0.1428, "step": 57310 }, { "epoch": 13.73, "learning_rate": 9.582592518081497e-05, "loss": 0.1874, "step": 57320 }, { "epoch": 13.73, "learning_rate": 9.582448926194381e-05, "loss": 0.1773, "step": 57330 }, { "epoch": 13.74, "learning_rate": 9.582305310689283e-05, "loss": 0.2009, "step": 57340 }, { "epoch": 13.74, "learning_rate": 9.582161671566949e-05, "loss": 0.1857, "step": 57350 }, { "epoch": 13.74, "learning_rate": 9.582018008828113e-05, "loss": 0.1398, "step": 57360 }, { "epoch": 13.74, "learning_rate": 9.581874322473517e-05, "loss": 0.1595, "step": 57370 }, { "epoch": 13.75, "learning_rate": 9.581730612503905e-05, "loss": 0.1548, "step": 57380 }, { "epoch": 13.75, "learning_rate": 9.581586878920013e-05, "loss": 0.1947, "step": 57390 }, { "epoch": 13.75, "learning_rate": 9.581443121722585e-05, "loss": 0.1821, "step": 57400 }, { "epoch": 13.75, "learning_rate": 9.581299340912361e-05, "loss": 0.179, "step": 57410 }, { "epoch": 13.75, "learning_rate": 9.58115553649008e-05, "loss": 0.2321, "step": 57420 }, { "epoch": 13.76, "learning_rate": 9.581011708456488e-05, "loss": 0.2003, "step": 57430 }, { "epoch": 13.76, "learning_rate": 9.580867856812322e-05, "loss": 0.1526, "step": 57440 }, { "epoch": 13.76, "learning_rate": 9.580723981558324e-05, "loss": 0.1318, "step": 57450 }, { "epoch": 13.76, "learning_rate": 9.580580082695237e-05, "loss": 0.2391, "step": 57460 }, { "epoch": 13.77, "learning_rate": 9.580436160223803e-05, "loss": 0.1372, "step": 57470 }, { "epoch": 13.77, "learning_rate": 9.580292214144762e-05, "loss": 0.1764, "step": 57480 }, { "epoch": 13.77, "learning_rate": 9.580148244458855e-05, "loss": 0.1483, "step": 57490 }, { "epoch": 13.77, "learning_rate": 9.580004251166827e-05, "loss": 0.1433, "step": 57500 }, { "epoch": 13.77, "learning_rate": 9.57986023426942e-05, "loss": 0.1304, "step": 57510 }, { "epoch": 13.78, "learning_rate": 9.579716193767374e-05, "loss": 0.1505, "step": 57520 }, { "epoch": 13.78, "learning_rate": 9.579572129661432e-05, "loss": 0.1632, "step": 57530 }, { "epoch": 13.78, "learning_rate": 9.579428041952337e-05, "loss": 0.1763, "step": 57540 }, { "epoch": 13.78, "learning_rate": 9.579283930640832e-05, "loss": 0.1482, "step": 57550 }, { "epoch": 13.79, "learning_rate": 9.57913979572766e-05, "loss": 0.148, "step": 57560 }, { "epoch": 13.79, "learning_rate": 9.578995637213562e-05, "loss": 0.1842, "step": 57570 }, { "epoch": 13.79, "learning_rate": 9.578851455099282e-05, "loss": 0.13, "step": 57580 }, { "epoch": 13.79, "learning_rate": 9.578707249385565e-05, "loss": 0.1385, "step": 57590 }, { "epoch": 13.8, "learning_rate": 9.578563020073153e-05, "loss": 0.1629, "step": 57600 }, { "epoch": 13.8, "learning_rate": 9.578418767162786e-05, "loss": 0.1571, "step": 57610 }, { "epoch": 13.8, "learning_rate": 9.578274490655213e-05, "loss": 0.1552, "step": 57620 }, { "epoch": 13.8, "learning_rate": 9.578130190551174e-05, "loss": 0.1235, "step": 57630 }, { "epoch": 13.8, "learning_rate": 9.577985866851413e-05, "loss": 0.1302, "step": 57640 }, { "epoch": 13.81, "learning_rate": 9.577841519556675e-05, "loss": 0.1561, "step": 57650 }, { "epoch": 13.81, "learning_rate": 9.577697148667703e-05, "loss": 0.1843, "step": 57660 }, { "epoch": 13.81, "learning_rate": 9.577552754185244e-05, "loss": 0.1654, "step": 57670 }, { "epoch": 13.81, "learning_rate": 9.577408336110038e-05, "loss": 0.175, "step": 57680 }, { "epoch": 13.82, "learning_rate": 9.577263894442832e-05, "loss": 0.1575, "step": 57690 }, { "epoch": 13.82, "learning_rate": 9.577119429184368e-05, "loss": 0.1737, "step": 57700 }, { "epoch": 13.82, "learning_rate": 9.576974940335393e-05, "loss": 0.146, "step": 57710 }, { "epoch": 13.82, "learning_rate": 9.576830427896652e-05, "loss": 0.1256, "step": 57720 }, { "epoch": 13.83, "learning_rate": 9.576685891868888e-05, "loss": 0.1487, "step": 57730 }, { "epoch": 13.83, "learning_rate": 9.576541332252847e-05, "loss": 0.1106, "step": 57740 }, { "epoch": 13.83, "learning_rate": 9.576396749049272e-05, "loss": 0.1492, "step": 57750 }, { "epoch": 13.83, "learning_rate": 9.576252142258912e-05, "loss": 0.1308, "step": 57760 }, { "epoch": 13.83, "learning_rate": 9.576107511882508e-05, "loss": 0.1618, "step": 57770 }, { "epoch": 13.84, "learning_rate": 9.575962857920811e-05, "loss": 0.2204, "step": 57780 }, { "epoch": 13.84, "learning_rate": 9.57581818037456e-05, "loss": 0.1568, "step": 57790 }, { "epoch": 13.84, "learning_rate": 9.575673479244505e-05, "loss": 0.1197, "step": 57800 }, { "epoch": 13.84, "learning_rate": 9.575528754531392e-05, "loss": 0.1472, "step": 57810 }, { "epoch": 13.85, "learning_rate": 9.575384006235963e-05, "loss": 0.1645, "step": 57820 }, { "epoch": 13.85, "learning_rate": 9.575239234358968e-05, "loss": 0.2002, "step": 57830 }, { "epoch": 13.85, "learning_rate": 9.575094438901151e-05, "loss": 0.1244, "step": 57840 }, { "epoch": 13.85, "learning_rate": 9.57494961986326e-05, "loss": 0.1562, "step": 57850 }, { "epoch": 13.85, "learning_rate": 9.57480477724604e-05, "loss": 0.2077, "step": 57860 }, { "epoch": 13.86, "learning_rate": 9.57465991105024e-05, "loss": 0.1286, "step": 57870 }, { "epoch": 13.86, "learning_rate": 9.5745150212766e-05, "loss": 0.1767, "step": 57880 }, { "epoch": 13.86, "learning_rate": 9.574370107925874e-05, "loss": 0.2192, "step": 57890 }, { "epoch": 13.86, "learning_rate": 9.574225170998808e-05, "loss": 0.1669, "step": 57900 }, { "epoch": 13.87, "learning_rate": 9.574080210496143e-05, "loss": 0.1596, "step": 57910 }, { "epoch": 13.87, "learning_rate": 9.573935226418634e-05, "loss": 0.1557, "step": 57920 }, { "epoch": 13.87, "learning_rate": 9.573790218767023e-05, "loss": 0.1721, "step": 57930 }, { "epoch": 13.87, "learning_rate": 9.573645187542059e-05, "loss": 0.1492, "step": 57940 }, { "epoch": 13.88, "learning_rate": 9.573500132744491e-05, "loss": 0.1751, "step": 57950 }, { "epoch": 13.88, "learning_rate": 9.573355054375063e-05, "loss": 0.111, "step": 57960 }, { "epoch": 13.88, "learning_rate": 9.573209952434525e-05, "loss": 0.1369, "step": 57970 }, { "epoch": 13.88, "learning_rate": 9.573064826923626e-05, "loss": 0.1292, "step": 57980 }, { "epoch": 13.88, "learning_rate": 9.572919677843112e-05, "loss": 0.1463, "step": 57990 }, { "epoch": 13.89, "learning_rate": 9.572774505193731e-05, "loss": 0.1182, "step": 58000 }, { "epoch": 13.89, "learning_rate": 9.572629308976234e-05, "loss": 0.1526, "step": 58010 }, { "epoch": 13.89, "learning_rate": 9.572484089191364e-05, "loss": 0.1991, "step": 58020 }, { "epoch": 13.89, "learning_rate": 9.572338845839877e-05, "loss": 0.1949, "step": 58030 }, { "epoch": 13.9, "learning_rate": 9.572193578922515e-05, "loss": 0.2237, "step": 58040 }, { "epoch": 13.9, "learning_rate": 9.572048288440028e-05, "loss": 0.1053, "step": 58050 }, { "epoch": 13.9, "learning_rate": 9.571902974393168e-05, "loss": 0.1553, "step": 58060 }, { "epoch": 13.9, "learning_rate": 9.571757636782682e-05, "loss": 0.1412, "step": 58070 }, { "epoch": 13.91, "learning_rate": 9.571612275609318e-05, "loss": 0.1361, "step": 58080 }, { "epoch": 13.91, "learning_rate": 9.571466890873825e-05, "loss": 0.1372, "step": 58090 }, { "epoch": 13.91, "learning_rate": 9.571321482576954e-05, "loss": 0.1112, "step": 58100 }, { "epoch": 13.91, "learning_rate": 9.571176050719455e-05, "loss": 0.1769, "step": 58110 }, { "epoch": 13.91, "learning_rate": 9.571030595302076e-05, "loss": 0.1768, "step": 58120 }, { "epoch": 13.92, "learning_rate": 9.570885116325568e-05, "loss": 0.1933, "step": 58130 }, { "epoch": 13.92, "learning_rate": 9.570739613790678e-05, "loss": 0.1331, "step": 58140 }, { "epoch": 13.92, "learning_rate": 9.57059408769816e-05, "loss": 0.1121, "step": 58150 }, { "epoch": 13.92, "learning_rate": 9.57044853804876e-05, "loss": 0.1775, "step": 58160 }, { "epoch": 13.93, "learning_rate": 9.57030296484323e-05, "loss": 0.1634, "step": 58170 }, { "epoch": 13.93, "learning_rate": 9.57015736808232e-05, "loss": 0.1592, "step": 58180 }, { "epoch": 13.93, "learning_rate": 9.570011747766783e-05, "loss": 0.128, "step": 58190 }, { "epoch": 13.93, "learning_rate": 9.569866103897365e-05, "loss": 0.1521, "step": 58200 }, { "epoch": 13.93, "learning_rate": 9.56972043647482e-05, "loss": 0.1768, "step": 58210 }, { "epoch": 13.94, "learning_rate": 9.569574745499898e-05, "loss": 0.1193, "step": 58220 }, { "epoch": 13.94, "learning_rate": 9.569429030973348e-05, "loss": 0.0957, "step": 58230 }, { "epoch": 13.94, "learning_rate": 9.569283292895923e-05, "loss": 0.1162, "step": 58240 }, { "epoch": 13.94, "learning_rate": 9.569137531268375e-05, "loss": 0.0985, "step": 58250 }, { "epoch": 13.95, "learning_rate": 9.568991746091453e-05, "loss": 0.1137, "step": 58260 }, { "epoch": 13.95, "learning_rate": 9.56884593736591e-05, "loss": 0.1435, "step": 58270 }, { "epoch": 13.95, "learning_rate": 9.568700105092497e-05, "loss": 0.115, "step": 58280 }, { "epoch": 14.0, "learning_rate": 9.568554249271964e-05, "loss": 0.1444, "step": 58290 }, { "epoch": 14.0, "learning_rate": 9.568408369905065e-05, "loss": 0.1379, "step": 58300 }, { "epoch": 14.01, "learning_rate": 9.568262466992552e-05, "loss": 0.1596, "step": 58310 }, { "epoch": 14.01, "learning_rate": 9.568116540535175e-05, "loss": 0.1169, "step": 58320 }, { "epoch": 14.01, "learning_rate": 9.567970590533689e-05, "loss": 0.0883, "step": 58330 }, { "epoch": 14.01, "learning_rate": 9.56782461698884e-05, "loss": 0.0724, "step": 58340 }, { "epoch": 14.02, "learning_rate": 9.567678619901389e-05, "loss": 0.139, "step": 58350 }, { "epoch": 14.02, "learning_rate": 9.567532599272082e-05, "loss": 0.1433, "step": 58360 }, { "epoch": 14.02, "learning_rate": 9.567386555101675e-05, "loss": 0.1129, "step": 58370 }, { "epoch": 14.02, "learning_rate": 9.56724048739092e-05, "loss": 0.1431, "step": 58380 }, { "epoch": 14.02, "learning_rate": 9.567094396140568e-05, "loss": 0.0937, "step": 58390 }, { "epoch": 14.03, "learning_rate": 9.566948281351373e-05, "loss": 0.1793, "step": 58400 }, { "epoch": 14.03, "learning_rate": 9.566802143024089e-05, "loss": 0.1533, "step": 58410 }, { "epoch": 14.03, "learning_rate": 9.566655981159469e-05, "loss": 0.1084, "step": 58420 }, { "epoch": 14.03, "learning_rate": 9.566509795758266e-05, "loss": 0.1042, "step": 58430 }, { "epoch": 14.04, "learning_rate": 9.566363586821233e-05, "loss": 0.1747, "step": 58440 }, { "epoch": 14.04, "learning_rate": 9.566217354349124e-05, "loss": 0.1212, "step": 58450 }, { "epoch": 14.04, "learning_rate": 9.566071098342692e-05, "loss": 0.1116, "step": 58460 }, { "epoch": 14.04, "learning_rate": 9.565924818802692e-05, "loss": 0.1519, "step": 58470 }, { "epoch": 14.05, "learning_rate": 9.565778515729878e-05, "loss": 0.1578, "step": 58480 }, { "epoch": 14.05, "learning_rate": 9.565632189125002e-05, "loss": 0.1131, "step": 58490 }, { "epoch": 14.05, "learning_rate": 9.56548583898882e-05, "loss": 0.0875, "step": 58500 }, { "epoch": 14.05, "learning_rate": 9.565339465322086e-05, "loss": 0.1272, "step": 58510 }, { "epoch": 14.05, "learning_rate": 9.565193068125554e-05, "loss": 0.1262, "step": 58520 }, { "epoch": 14.06, "learning_rate": 9.565046647399979e-05, "loss": 0.1525, "step": 58530 }, { "epoch": 14.06, "learning_rate": 9.564900203146116e-05, "loss": 0.1687, "step": 58540 }, { "epoch": 14.06, "learning_rate": 9.564753735364718e-05, "loss": 0.2085, "step": 58550 }, { "epoch": 14.06, "learning_rate": 9.564607244056543e-05, "loss": 0.1384, "step": 58560 }, { "epoch": 14.07, "learning_rate": 9.564460729222342e-05, "loss": 0.1469, "step": 58570 }, { "epoch": 14.07, "learning_rate": 9.564314190862873e-05, "loss": 0.0948, "step": 58580 }, { "epoch": 14.07, "learning_rate": 9.56416762897889e-05, "loss": 0.1291, "step": 58590 }, { "epoch": 14.07, "learning_rate": 9.56402104357115e-05, "loss": 0.1221, "step": 58600 }, { "epoch": 14.07, "learning_rate": 9.563874434640405e-05, "loss": 0.1124, "step": 58610 }, { "epoch": 14.08, "learning_rate": 9.563727802187416e-05, "loss": 0.1635, "step": 58620 }, { "epoch": 14.08, "learning_rate": 9.563581146212934e-05, "loss": 0.1814, "step": 58630 }, { "epoch": 14.08, "learning_rate": 9.563434466717718e-05, "loss": 0.1667, "step": 58640 }, { "epoch": 14.08, "learning_rate": 9.563287763702522e-05, "loss": 0.1101, "step": 58650 }, { "epoch": 14.09, "learning_rate": 9.563141037168102e-05, "loss": 0.1054, "step": 58660 }, { "epoch": 14.09, "learning_rate": 9.562994287115216e-05, "loss": 0.1656, "step": 58670 }, { "epoch": 14.09, "learning_rate": 9.562847513544618e-05, "loss": 0.1172, "step": 58680 }, { "epoch": 14.09, "learning_rate": 9.562700716457067e-05, "loss": 0.1492, "step": 58690 }, { "epoch": 14.1, "learning_rate": 9.562553895853316e-05, "loss": 0.1592, "step": 58700 }, { "epoch": 14.1, "learning_rate": 9.562407051734128e-05, "loss": 0.1245, "step": 58710 }, { "epoch": 14.1, "learning_rate": 9.562260184100253e-05, "loss": 0.1557, "step": 58720 }, { "epoch": 14.1, "learning_rate": 9.562113292952452e-05, "loss": 0.1681, "step": 58730 }, { "epoch": 14.1, "learning_rate": 9.56196637829148e-05, "loss": 0.1108, "step": 58740 }, { "epoch": 14.11, "learning_rate": 9.561819440118098e-05, "loss": 0.1017, "step": 58750 }, { "epoch": 14.11, "learning_rate": 9.561672478433058e-05, "loss": 0.1358, "step": 58760 }, { "epoch": 14.11, "learning_rate": 9.56152549323712e-05, "loss": 0.0989, "step": 58770 }, { "epoch": 14.11, "learning_rate": 9.561378484531041e-05, "loss": 0.131, "step": 58780 }, { "epoch": 14.12, "learning_rate": 9.56123145231558e-05, "loss": 0.1152, "step": 58790 }, { "epoch": 14.12, "learning_rate": 9.561084396591494e-05, "loss": 0.1651, "step": 58800 }, { "epoch": 14.12, "learning_rate": 9.560937317359542e-05, "loss": 0.1791, "step": 58810 }, { "epoch": 14.12, "learning_rate": 9.560790214620478e-05, "loss": 0.1573, "step": 58820 }, { "epoch": 14.13, "learning_rate": 9.560643088375066e-05, "loss": 0.1377, "step": 58830 }, { "epoch": 14.13, "learning_rate": 9.56049593862406e-05, "loss": 0.1215, "step": 58840 }, { "epoch": 14.13, "learning_rate": 9.56034876536822e-05, "loss": 0.2118, "step": 58850 }, { "epoch": 14.13, "learning_rate": 9.560201568608304e-05, "loss": 0.1142, "step": 58860 }, { "epoch": 14.13, "learning_rate": 9.560054348345071e-05, "loss": 0.1023, "step": 58870 }, { "epoch": 14.14, "learning_rate": 9.559907104579282e-05, "loss": 0.2034, "step": 58880 }, { "epoch": 14.14, "learning_rate": 9.55975983731169e-05, "loss": 0.0841, "step": 58890 }, { "epoch": 14.14, "learning_rate": 9.559612546543059e-05, "loss": 0.1482, "step": 58900 }, { "epoch": 14.14, "learning_rate": 9.55946523227415e-05, "loss": 0.0955, "step": 58910 }, { "epoch": 14.15, "learning_rate": 9.559317894505715e-05, "loss": 0.166, "step": 58920 }, { "epoch": 14.15, "learning_rate": 9.559170533238519e-05, "loss": 0.1229, "step": 58930 }, { "epoch": 14.15, "learning_rate": 9.559023148473321e-05, "loss": 0.1092, "step": 58940 }, { "epoch": 14.15, "learning_rate": 9.558875740210877e-05, "loss": 0.1523, "step": 58950 }, { "epoch": 14.15, "learning_rate": 9.558728308451952e-05, "loss": 0.0961, "step": 58960 }, { "epoch": 14.16, "learning_rate": 9.558580853197301e-05, "loss": 0.1607, "step": 58970 }, { "epoch": 14.16, "learning_rate": 9.558433374447688e-05, "loss": 0.1257, "step": 58980 }, { "epoch": 14.16, "learning_rate": 9.558285872203869e-05, "loss": 0.0976, "step": 58990 }, { "epoch": 14.16, "learning_rate": 9.558138346466609e-05, "loss": 0.1558, "step": 59000 }, { "epoch": 14.17, "learning_rate": 9.557990797236665e-05, "loss": 0.1312, "step": 59010 }, { "epoch": 14.17, "learning_rate": 9.557843224514797e-05, "loss": 0.1134, "step": 59020 }, { "epoch": 14.17, "learning_rate": 9.557695628301768e-05, "loss": 0.1373, "step": 59030 }, { "epoch": 14.17, "learning_rate": 9.557548008598338e-05, "loss": 0.1585, "step": 59040 }, { "epoch": 14.18, "learning_rate": 9.557400365405266e-05, "loss": 0.1308, "step": 59050 }, { "epoch": 14.18, "learning_rate": 9.557252698723317e-05, "loss": 0.093, "step": 59060 }, { "epoch": 14.18, "learning_rate": 9.557105008553249e-05, "loss": 0.1262, "step": 59070 }, { "epoch": 14.18, "learning_rate": 9.556957294895822e-05, "loss": 0.1622, "step": 59080 }, { "epoch": 14.18, "learning_rate": 9.5568095577518e-05, "loss": 0.1153, "step": 59090 }, { "epoch": 14.19, "learning_rate": 9.556661797121943e-05, "loss": 0.0998, "step": 59100 }, { "epoch": 14.19, "learning_rate": 9.556514013007014e-05, "loss": 0.1053, "step": 59110 }, { "epoch": 14.19, "learning_rate": 9.556366205407772e-05, "loss": 0.1241, "step": 59120 }, { "epoch": 14.19, "learning_rate": 9.556218374324981e-05, "loss": 0.1512, "step": 59130 }, { "epoch": 14.2, "learning_rate": 9.556070519759403e-05, "loss": 0.1256, "step": 59140 }, { "epoch": 14.2, "learning_rate": 9.5559226417118e-05, "loss": 0.1398, "step": 59150 }, { "epoch": 14.2, "learning_rate": 9.555774740182932e-05, "loss": 0.1361, "step": 59160 }, { "epoch": 14.2, "learning_rate": 9.555626815173564e-05, "loss": 0.184, "step": 59170 }, { "epoch": 14.21, "learning_rate": 9.555478866684457e-05, "loss": 0.1123, "step": 59180 }, { "epoch": 14.21, "learning_rate": 9.555330894716375e-05, "loss": 0.1433, "step": 59190 }, { "epoch": 14.21, "learning_rate": 9.555182899270079e-05, "loss": 0.1317, "step": 59200 }, { "epoch": 14.21, "learning_rate": 9.555034880346332e-05, "loss": 0.0843, "step": 59210 }, { "epoch": 14.21, "learning_rate": 9.554886837945896e-05, "loss": 0.1183, "step": 59220 }, { "epoch": 14.22, "learning_rate": 9.554738772069536e-05, "loss": 0.17, "step": 59230 }, { "epoch": 14.22, "learning_rate": 9.554590682718014e-05, "loss": 0.2095, "step": 59240 }, { "epoch": 14.22, "learning_rate": 9.554442569892094e-05, "loss": 0.1473, "step": 59250 }, { "epoch": 14.22, "learning_rate": 9.554294433592539e-05, "loss": 0.1341, "step": 59260 }, { "epoch": 14.23, "learning_rate": 9.554146273820112e-05, "loss": 0.1403, "step": 59270 }, { "epoch": 14.23, "learning_rate": 9.553998090575577e-05, "loss": 0.1822, "step": 59280 }, { "epoch": 14.23, "learning_rate": 9.5538498838597e-05, "loss": 0.1028, "step": 59290 }, { "epoch": 14.23, "learning_rate": 9.55370165367324e-05, "loss": 0.1231, "step": 59300 }, { "epoch": 14.23, "learning_rate": 9.553553400016963e-05, "loss": 0.1895, "step": 59310 }, { "epoch": 14.24, "learning_rate": 9.553405122891637e-05, "loss": 0.1311, "step": 59320 }, { "epoch": 14.24, "learning_rate": 9.55325682229802e-05, "loss": 0.1405, "step": 59330 }, { "epoch": 14.24, "learning_rate": 9.55310849823688e-05, "loss": 0.1494, "step": 59340 }, { "epoch": 14.24, "learning_rate": 9.552960150708981e-05, "loss": 0.0983, "step": 59350 }, { "epoch": 14.25, "learning_rate": 9.552811779715087e-05, "loss": 0.1231, "step": 59360 }, { "epoch": 14.25, "learning_rate": 9.552663385255964e-05, "loss": 0.1201, "step": 59370 }, { "epoch": 14.25, "learning_rate": 9.552514967332376e-05, "loss": 0.1233, "step": 59380 }, { "epoch": 14.25, "learning_rate": 9.552366525945087e-05, "loss": 0.1211, "step": 59390 }, { "epoch": 14.26, "learning_rate": 9.552218061094863e-05, "loss": 0.1671, "step": 59400 }, { "epoch": 14.26, "learning_rate": 9.552069572782467e-05, "loss": 0.1343, "step": 59410 }, { "epoch": 14.26, "learning_rate": 9.55192106100867e-05, "loss": 0.0979, "step": 59420 }, { "epoch": 14.26, "learning_rate": 9.551772525774232e-05, "loss": 0.1625, "step": 59430 }, { "epoch": 14.26, "learning_rate": 9.55162396707992e-05, "loss": 0.0916, "step": 59440 }, { "epoch": 14.27, "learning_rate": 9.5514753849265e-05, "loss": 0.1309, "step": 59450 }, { "epoch": 14.27, "learning_rate": 9.551326779314739e-05, "loss": 0.1264, "step": 59460 }, { "epoch": 14.27, "learning_rate": 9.5511781502454e-05, "loss": 0.1479, "step": 59470 }, { "epoch": 14.27, "learning_rate": 9.551029497719253e-05, "loss": 0.1305, "step": 59480 }, { "epoch": 14.28, "learning_rate": 9.55088082173706e-05, "loss": 0.1293, "step": 59490 }, { "epoch": 14.28, "learning_rate": 9.550732122299591e-05, "loss": 0.1387, "step": 59500 }, { "epoch": 14.28, "learning_rate": 9.550583399407608e-05, "loss": 0.1228, "step": 59510 }, { "epoch": 14.28, "learning_rate": 9.550434653061883e-05, "loss": 0.1003, "step": 59520 }, { "epoch": 14.29, "learning_rate": 9.550285883263178e-05, "loss": 0.1128, "step": 59530 }, { "epoch": 14.29, "learning_rate": 9.550137090012262e-05, "loss": 0.1331, "step": 59540 }, { "epoch": 14.29, "learning_rate": 9.549988273309902e-05, "loss": 0.1709, "step": 59550 }, { "epoch": 14.29, "learning_rate": 9.549839433156865e-05, "loss": 0.1255, "step": 59560 }, { "epoch": 14.29, "learning_rate": 9.549690569553915e-05, "loss": 0.1249, "step": 59570 }, { "epoch": 14.3, "learning_rate": 9.549541682501823e-05, "loss": 0.1165, "step": 59580 }, { "epoch": 14.3, "learning_rate": 9.549392772001355e-05, "loss": 0.1746, "step": 59590 }, { "epoch": 14.3, "learning_rate": 9.549243838053279e-05, "loss": 0.115, "step": 59600 }, { "epoch": 14.3, "learning_rate": 9.549094880658363e-05, "loss": 0.1131, "step": 59610 }, { "epoch": 14.31, "learning_rate": 9.548945899817372e-05, "loss": 0.1266, "step": 59620 }, { "epoch": 14.31, "learning_rate": 9.548796895531077e-05, "loss": 0.1076, "step": 59630 }, { "epoch": 14.31, "learning_rate": 9.548647867800244e-05, "loss": 0.1361, "step": 59640 }, { "epoch": 14.31, "learning_rate": 9.548498816625643e-05, "loss": 0.1366, "step": 59650 }, { "epoch": 14.31, "learning_rate": 9.54834974200804e-05, "loss": 0.096, "step": 59660 }, { "epoch": 14.32, "learning_rate": 9.548200643948206e-05, "loss": 0.1238, "step": 59670 }, { "epoch": 14.32, "learning_rate": 9.548051522446906e-05, "loss": 0.1485, "step": 59680 }, { "epoch": 14.32, "learning_rate": 9.547902377504912e-05, "loss": 0.1025, "step": 59690 }, { "epoch": 14.32, "learning_rate": 9.54775320912299e-05, "loss": 0.1132, "step": 59700 }, { "epoch": 14.33, "learning_rate": 9.54760401730191e-05, "loss": 0.1679, "step": 59710 }, { "epoch": 14.33, "learning_rate": 9.547454802042441e-05, "loss": 0.1516, "step": 59720 }, { "epoch": 14.33, "learning_rate": 9.547305563345353e-05, "loss": 0.1261, "step": 59730 }, { "epoch": 14.33, "learning_rate": 9.547156301211412e-05, "loss": 0.1076, "step": 59740 }, { "epoch": 14.34, "learning_rate": 9.547007015641391e-05, "loss": 0.1258, "step": 59750 }, { "epoch": 14.34, "learning_rate": 9.546857706636059e-05, "loss": 0.1417, "step": 59760 }, { "epoch": 14.34, "learning_rate": 9.546708374196182e-05, "loss": 0.1332, "step": 59770 }, { "epoch": 14.34, "learning_rate": 9.546559018322534e-05, "loss": 0.1275, "step": 59780 }, { "epoch": 14.34, "learning_rate": 9.546409639015881e-05, "loss": 0.1276, "step": 59790 }, { "epoch": 14.35, "learning_rate": 9.546260236276996e-05, "loss": 0.1007, "step": 59800 }, { "epoch": 14.35, "learning_rate": 9.546110810106648e-05, "loss": 0.1419, "step": 59810 }, { "epoch": 14.35, "learning_rate": 9.545961360505606e-05, "loss": 0.1238, "step": 59820 }, { "epoch": 14.35, "learning_rate": 9.545811887474641e-05, "loss": 0.1382, "step": 59830 }, { "epoch": 14.36, "learning_rate": 9.545662391014524e-05, "loss": 0.1717, "step": 59840 }, { "epoch": 14.36, "learning_rate": 9.545512871126025e-05, "loss": 0.0881, "step": 59850 }, { "epoch": 14.36, "learning_rate": 9.545363327809915e-05, "loss": 0.1092, "step": 59860 }, { "epoch": 14.36, "learning_rate": 9.545213761066962e-05, "loss": 0.1083, "step": 59870 }, { "epoch": 14.37, "learning_rate": 9.545064170897941e-05, "loss": 0.0894, "step": 59880 }, { "epoch": 14.37, "learning_rate": 9.544914557303622e-05, "loss": 0.1062, "step": 59890 }, { "epoch": 14.37, "learning_rate": 9.544764920284775e-05, "loss": 0.1718, "step": 59900 }, { "epoch": 14.37, "learning_rate": 9.544615259842173e-05, "loss": 0.0808, "step": 59910 }, { "epoch": 14.37, "learning_rate": 9.544465575976583e-05, "loss": 0.1173, "step": 59920 }, { "epoch": 14.38, "learning_rate": 9.544315868688781e-05, "loss": 0.1505, "step": 59930 }, { "epoch": 14.38, "learning_rate": 9.544166137979538e-05, "loss": 0.1122, "step": 59940 }, { "epoch": 14.38, "learning_rate": 9.544016383849623e-05, "loss": 0.1145, "step": 59950 }, { "epoch": 14.38, "learning_rate": 9.543866606299811e-05, "loss": 0.1004, "step": 59960 }, { "epoch": 14.39, "learning_rate": 9.543716805330871e-05, "loss": 0.1394, "step": 59970 }, { "epoch": 14.39, "learning_rate": 9.543566980943576e-05, "loss": 0.1564, "step": 59980 }, { "epoch": 14.39, "learning_rate": 9.5434171331387e-05, "loss": 0.1035, "step": 59990 }, { "epoch": 14.39, "learning_rate": 9.543267261917016e-05, "loss": 0.107, "step": 60000 }, { "epoch": 14.39, "learning_rate": 9.543117367279293e-05, "loss": 0.1274, "step": 60010 }, { "epoch": 14.4, "learning_rate": 9.542967449226305e-05, "loss": 0.1176, "step": 60020 }, { "epoch": 14.4, "learning_rate": 9.542817507758825e-05, "loss": 0.1208, "step": 60030 }, { "epoch": 14.4, "learning_rate": 9.542667542877625e-05, "loss": 0.0972, "step": 60040 }, { "epoch": 14.4, "learning_rate": 9.542517554583479e-05, "loss": 0.118, "step": 60050 }, { "epoch": 14.41, "learning_rate": 9.54236754287716e-05, "loss": 0.1995, "step": 60060 }, { "epoch": 14.41, "learning_rate": 9.542217507759439e-05, "loss": 0.0975, "step": 60070 }, { "epoch": 14.41, "learning_rate": 9.542067449231093e-05, "loss": 0.0981, "step": 60080 }, { "epoch": 14.41, "learning_rate": 9.541917367292892e-05, "loss": 0.136, "step": 60090 }, { "epoch": 14.42, "learning_rate": 9.541767261945612e-05, "loss": 0.1209, "step": 60100 }, { "epoch": 14.42, "learning_rate": 9.541617133190024e-05, "loss": 0.1531, "step": 60110 }, { "epoch": 14.42, "learning_rate": 9.541466981026905e-05, "loss": 0.1445, "step": 60120 }, { "epoch": 14.42, "learning_rate": 9.541316805457026e-05, "loss": 0.1074, "step": 60130 }, { "epoch": 14.42, "learning_rate": 9.541166606481163e-05, "loss": 0.1172, "step": 60140 }, { "epoch": 14.43, "learning_rate": 9.54101638410009e-05, "loss": 0.0743, "step": 60150 }, { "epoch": 14.43, "learning_rate": 9.540866138314579e-05, "loss": 0.1265, "step": 60160 }, { "epoch": 14.43, "learning_rate": 9.540715869125407e-05, "loss": 0.1261, "step": 60170 }, { "epoch": 14.43, "learning_rate": 9.540565576533347e-05, "loss": 0.1071, "step": 60180 }, { "epoch": 14.44, "learning_rate": 9.540415260539175e-05, "loss": 0.1197, "step": 60190 }, { "epoch": 14.44, "learning_rate": 9.540264921143664e-05, "loss": 0.112, "step": 60200 }, { "epoch": 14.44, "learning_rate": 9.540114558347589e-05, "loss": 0.0868, "step": 60210 }, { "epoch": 14.44, "learning_rate": 9.539964172151726e-05, "loss": 0.1815, "step": 60220 }, { "epoch": 14.45, "learning_rate": 9.53981376255685e-05, "loss": 0.1365, "step": 60230 }, { "epoch": 14.45, "learning_rate": 9.539663329563736e-05, "loss": 0.1219, "step": 60240 }, { "epoch": 14.45, "learning_rate": 9.53951287317316e-05, "loss": 0.0933, "step": 60250 }, { "epoch": 14.45, "learning_rate": 9.539362393385895e-05, "loss": 0.1247, "step": 60260 }, { "epoch": 14.45, "learning_rate": 9.539211890202719e-05, "loss": 0.1453, "step": 60270 }, { "epoch": 14.46, "learning_rate": 9.539061363624408e-05, "loss": 0.065, "step": 60280 }, { "epoch": 14.46, "learning_rate": 9.538910813651736e-05, "loss": 0.1258, "step": 60290 }, { "epoch": 14.46, "learning_rate": 9.538760240285479e-05, "loss": 0.1644, "step": 60300 }, { "epoch": 14.46, "learning_rate": 9.538609643526415e-05, "loss": 0.1195, "step": 60310 }, { "epoch": 14.47, "learning_rate": 9.53845902337532e-05, "loss": 0.1177, "step": 60320 }, { "epoch": 14.47, "learning_rate": 9.538308379832965e-05, "loss": 0.0835, "step": 60330 }, { "epoch": 14.47, "learning_rate": 9.538157712900134e-05, "loss": 0.1252, "step": 60340 }, { "epoch": 14.47, "learning_rate": 9.5380070225776e-05, "loss": 0.1866, "step": 60350 }, { "epoch": 14.47, "learning_rate": 9.53785630886614e-05, "loss": 0.0887, "step": 60360 }, { "epoch": 14.48, "learning_rate": 9.537705571766528e-05, "loss": 0.1281, "step": 60370 }, { "epoch": 14.48, "learning_rate": 9.537554811279548e-05, "loss": 0.1606, "step": 60380 }, { "epoch": 14.48, "learning_rate": 9.53740402740597e-05, "loss": 0.1019, "step": 60390 }, { "epoch": 14.48, "learning_rate": 9.537253220146574e-05, "loss": 0.1299, "step": 60400 }, { "epoch": 14.49, "learning_rate": 9.537102389502136e-05, "loss": 0.0987, "step": 60410 }, { "epoch": 14.49, "learning_rate": 9.536951535473435e-05, "loss": 0.102, "step": 60420 }, { "epoch": 14.49, "learning_rate": 9.536800658061249e-05, "loss": 0.0709, "step": 60430 }, { "epoch": 14.49, "learning_rate": 9.536649757266354e-05, "loss": 0.1469, "step": 60440 }, { "epoch": 14.5, "learning_rate": 9.536498833089526e-05, "loss": 0.0966, "step": 60450 }, { "epoch": 14.5, "learning_rate": 9.536347885531548e-05, "loss": 0.0953, "step": 60460 }, { "epoch": 14.5, "learning_rate": 9.536196914593193e-05, "loss": 0.1188, "step": 60470 }, { "epoch": 14.5, "learning_rate": 9.536045920275242e-05, "loss": 0.0909, "step": 60480 }, { "epoch": 14.5, "learning_rate": 9.535894902578473e-05, "loss": 0.0715, "step": 60490 }, { "epoch": 14.51, "learning_rate": 9.535743861503664e-05, "loss": 0.1808, "step": 60500 }, { "epoch": 14.51, "learning_rate": 9.535592797051594e-05, "loss": 0.1374, "step": 60510 }, { "epoch": 14.51, "learning_rate": 9.535441709223039e-05, "loss": 0.1318, "step": 60520 }, { "epoch": 14.51, "learning_rate": 9.53529059801878e-05, "loss": 0.1445, "step": 60530 }, { "epoch": 14.52, "learning_rate": 9.535139463439595e-05, "loss": 0.1044, "step": 60540 }, { "epoch": 14.52, "learning_rate": 9.534988305486263e-05, "loss": 0.0776, "step": 60550 }, { "epoch": 14.52, "learning_rate": 9.534837124159563e-05, "loss": 0.0752, "step": 60560 }, { "epoch": 14.52, "learning_rate": 9.534685919460277e-05, "loss": 0.1311, "step": 60570 }, { "epoch": 14.53, "learning_rate": 9.53453469138918e-05, "loss": 0.1104, "step": 60580 }, { "epoch": 14.53, "learning_rate": 9.534383439947054e-05, "loss": 0.0925, "step": 60590 }, { "epoch": 14.53, "learning_rate": 9.534232165134678e-05, "loss": 0.1098, "step": 60600 }, { "epoch": 14.53, "learning_rate": 9.53408086695283e-05, "loss": 0.1567, "step": 60610 }, { "epoch": 14.53, "learning_rate": 9.533929545402293e-05, "loss": 0.1926, "step": 60620 }, { "epoch": 14.54, "learning_rate": 9.533778200483843e-05, "loss": 0.2112, "step": 60630 }, { "epoch": 14.54, "learning_rate": 9.533626832198264e-05, "loss": 0.2621, "step": 60640 }, { "epoch": 14.54, "learning_rate": 9.533475440546336e-05, "loss": 0.2181, "step": 60650 }, { "epoch": 14.54, "learning_rate": 9.533324025528836e-05, "loss": 0.2156, "step": 60660 }, { "epoch": 14.55, "learning_rate": 9.533172587146545e-05, "loss": 0.2048, "step": 60670 }, { "epoch": 14.55, "learning_rate": 9.533021125400246e-05, "loss": 0.2568, "step": 60680 }, { "epoch": 14.55, "learning_rate": 9.532869640290718e-05, "loss": 0.1734, "step": 60690 }, { "epoch": 14.55, "learning_rate": 9.532718131818741e-05, "loss": 0.169, "step": 60700 }, { "epoch": 14.55, "learning_rate": 9.532566599985097e-05, "loss": 0.1697, "step": 60710 }, { "epoch": 14.56, "learning_rate": 9.532415044790568e-05, "loss": 0.1777, "step": 60720 }, { "epoch": 14.56, "learning_rate": 9.532263466235934e-05, "loss": 0.1621, "step": 60730 }, { "epoch": 14.56, "learning_rate": 9.532111864321975e-05, "loss": 0.1611, "step": 60740 }, { "epoch": 14.56, "learning_rate": 9.531960239049476e-05, "loss": 0.2323, "step": 60750 }, { "epoch": 14.57, "learning_rate": 9.531808590419214e-05, "loss": 0.1763, "step": 60760 }, { "epoch": 14.57, "learning_rate": 9.531656918431973e-05, "loss": 0.1863, "step": 60770 }, { "epoch": 14.57, "learning_rate": 9.531505223088534e-05, "loss": 0.1962, "step": 60780 }, { "epoch": 14.57, "learning_rate": 9.53135350438968e-05, "loss": 0.1556, "step": 60790 }, { "epoch": 14.58, "learning_rate": 9.53120176233619e-05, "loss": 0.1881, "step": 60800 }, { "epoch": 14.58, "learning_rate": 9.531049996928851e-05, "loss": 0.2225, "step": 60810 }, { "epoch": 14.58, "learning_rate": 9.530898208168441e-05, "loss": 0.1591, "step": 60820 }, { "epoch": 14.58, "learning_rate": 9.530746396055745e-05, "loss": 0.1596, "step": 60830 }, { "epoch": 14.58, "learning_rate": 9.530594560591544e-05, "loss": 0.2134, "step": 60840 }, { "epoch": 14.59, "learning_rate": 9.530442701776618e-05, "loss": 0.2498, "step": 60850 }, { "epoch": 14.59, "learning_rate": 9.530290819611756e-05, "loss": 0.1951, "step": 60860 }, { "epoch": 14.59, "learning_rate": 9.530138914097735e-05, "loss": 0.1262, "step": 60870 }, { "epoch": 14.59, "learning_rate": 9.529986985235342e-05, "loss": 0.1844, "step": 60880 }, { "epoch": 14.6, "learning_rate": 9.529835033025356e-05, "loss": 0.1835, "step": 60890 }, { "epoch": 14.6, "learning_rate": 9.529683057468564e-05, "loss": 0.1768, "step": 60900 }, { "epoch": 14.6, "learning_rate": 9.529531058565748e-05, "loss": 0.1219, "step": 60910 }, { "epoch": 14.6, "learning_rate": 9.52937903631769e-05, "loss": 0.2038, "step": 60920 }, { "epoch": 14.61, "learning_rate": 9.529226990725175e-05, "loss": 0.1866, "step": 60930 }, { "epoch": 14.61, "learning_rate": 9.529074921788985e-05, "loss": 0.2058, "step": 60940 }, { "epoch": 14.61, "learning_rate": 9.528922829509908e-05, "loss": 0.1535, "step": 60950 }, { "epoch": 14.61, "learning_rate": 9.528770713888721e-05, "loss": 0.155, "step": 60960 }, { "epoch": 14.61, "learning_rate": 9.528618574926214e-05, "loss": 0.2102, "step": 60970 }, { "epoch": 14.62, "learning_rate": 9.528466412623169e-05, "loss": 0.2162, "step": 60980 }, { "epoch": 14.62, "learning_rate": 9.52831422698037e-05, "loss": 0.1981, "step": 60990 }, { "epoch": 14.62, "learning_rate": 9.528162017998603e-05, "loss": 0.1033, "step": 61000 }, { "epoch": 14.62, "learning_rate": 9.528009785678649e-05, "loss": 0.1713, "step": 61010 }, { "epoch": 14.63, "learning_rate": 9.527857530021296e-05, "loss": 0.1589, "step": 61020 }, { "epoch": 14.63, "learning_rate": 9.527705251027327e-05, "loss": 0.2166, "step": 61030 }, { "epoch": 14.63, "learning_rate": 9.527552948697527e-05, "loss": 0.1221, "step": 61040 }, { "epoch": 14.63, "learning_rate": 9.527400623032682e-05, "loss": 0.1789, "step": 61050 }, { "epoch": 14.63, "learning_rate": 9.527248274033576e-05, "loss": 0.1995, "step": 61060 }, { "epoch": 14.64, "learning_rate": 9.527095901700996e-05, "loss": 0.1455, "step": 61070 }, { "epoch": 14.64, "learning_rate": 9.526943506035723e-05, "loss": 0.1919, "step": 61080 }, { "epoch": 14.64, "learning_rate": 9.526791087038547e-05, "loss": 0.1766, "step": 61090 }, { "epoch": 14.64, "learning_rate": 9.52663864471025e-05, "loss": 0.2243, "step": 61100 }, { "epoch": 14.65, "learning_rate": 9.526486179051623e-05, "loss": 0.1956, "step": 61110 }, { "epoch": 14.65, "learning_rate": 9.526333690063446e-05, "loss": 0.1874, "step": 61120 }, { "epoch": 14.65, "learning_rate": 9.526181177746507e-05, "loss": 0.1803, "step": 61130 }, { "epoch": 14.65, "learning_rate": 9.526028642101594e-05, "loss": 0.1787, "step": 61140 }, { "epoch": 14.66, "learning_rate": 9.525876083129491e-05, "loss": 0.1881, "step": 61150 }, { "epoch": 14.66, "learning_rate": 9.525723500830985e-05, "loss": 0.181, "step": 61160 }, { "epoch": 14.66, "learning_rate": 9.525570895206861e-05, "loss": 0.1646, "step": 61170 }, { "epoch": 14.66, "learning_rate": 9.525418266257908e-05, "loss": 0.1554, "step": 61180 }, { "epoch": 14.66, "learning_rate": 9.525265613984912e-05, "loss": 0.1984, "step": 61190 }, { "epoch": 14.67, "learning_rate": 9.525112938388658e-05, "loss": 0.1163, "step": 61200 }, { "epoch": 14.67, "learning_rate": 9.524960239469934e-05, "loss": 0.0997, "step": 61210 }, { "epoch": 14.67, "learning_rate": 9.524807517229528e-05, "loss": 0.1562, "step": 61220 }, { "epoch": 14.67, "learning_rate": 9.524654771668226e-05, "loss": 0.1595, "step": 61230 }, { "epoch": 14.68, "learning_rate": 9.524502002786814e-05, "loss": 0.1523, "step": 61240 }, { "epoch": 14.68, "learning_rate": 9.524349210586083e-05, "loss": 0.2123, "step": 61250 }, { "epoch": 14.68, "learning_rate": 9.524196395066818e-05, "loss": 0.1134, "step": 61260 }, { "epoch": 14.68, "learning_rate": 9.524043556229806e-05, "loss": 0.1556, "step": 61270 }, { "epoch": 14.69, "learning_rate": 9.523890694075836e-05, "loss": 0.221, "step": 61280 }, { "epoch": 14.69, "learning_rate": 9.523737808605695e-05, "loss": 0.19, "step": 61290 }, { "epoch": 14.69, "learning_rate": 9.523584899820173e-05, "loss": 0.1541, "step": 61300 }, { "epoch": 14.69, "learning_rate": 9.523431967720055e-05, "loss": 0.1315, "step": 61310 }, { "epoch": 14.69, "learning_rate": 9.523279012306132e-05, "loss": 0.157, "step": 61320 }, { "epoch": 14.7, "learning_rate": 9.52312603357919e-05, "loss": 0.2007, "step": 61330 }, { "epoch": 14.7, "learning_rate": 9.52297303154002e-05, "loss": 0.1993, "step": 61340 }, { "epoch": 14.7, "learning_rate": 9.522820006189408e-05, "loss": 0.1225, "step": 61350 }, { "epoch": 14.7, "learning_rate": 9.522666957528146e-05, "loss": 0.1407, "step": 61360 }, { "epoch": 14.71, "learning_rate": 9.522513885557019e-05, "loss": 0.1306, "step": 61370 }, { "epoch": 14.71, "learning_rate": 9.522360790276817e-05, "loss": 0.1685, "step": 61380 }, { "epoch": 14.71, "learning_rate": 9.52220767168833e-05, "loss": 0.1543, "step": 61390 }, { "epoch": 14.71, "learning_rate": 9.522054529792347e-05, "loss": 0.1895, "step": 61400 }, { "epoch": 14.71, "learning_rate": 9.521901364589658e-05, "loss": 0.142, "step": 61410 }, { "epoch": 14.72, "learning_rate": 9.521748176081052e-05, "loss": 0.2196, "step": 61420 }, { "epoch": 14.72, "learning_rate": 9.521594964267318e-05, "loss": 0.1924, "step": 61430 }, { "epoch": 14.72, "learning_rate": 9.521441729149244e-05, "loss": 0.1442, "step": 61440 }, { "epoch": 14.72, "learning_rate": 9.521288470727623e-05, "loss": 0.1125, "step": 61450 }, { "epoch": 14.73, "learning_rate": 9.521135189003243e-05, "loss": 0.1545, "step": 61460 }, { "epoch": 14.73, "learning_rate": 9.520981883976894e-05, "loss": 0.1828, "step": 61470 }, { "epoch": 14.73, "learning_rate": 9.520828555649365e-05, "loss": 0.127, "step": 61480 }, { "epoch": 14.73, "learning_rate": 9.520675204021452e-05, "loss": 0.2031, "step": 61490 }, { "epoch": 14.74, "learning_rate": 9.520521829093938e-05, "loss": 0.2306, "step": 61500 }, { "epoch": 14.74, "learning_rate": 9.520368430867619e-05, "loss": 0.1721, "step": 61510 }, { "epoch": 14.74, "learning_rate": 9.52021500934328e-05, "loss": 0.1559, "step": 61520 }, { "epoch": 14.74, "learning_rate": 9.520061564521719e-05, "loss": 0.1417, "step": 61530 }, { "epoch": 14.74, "learning_rate": 9.51990809640372e-05, "loss": 0.1678, "step": 61540 }, { "epoch": 14.75, "learning_rate": 9.519754604990079e-05, "loss": 0.1707, "step": 61550 }, { "epoch": 14.75, "learning_rate": 9.519601090281583e-05, "loss": 0.1499, "step": 61560 }, { "epoch": 14.75, "learning_rate": 9.519447552279026e-05, "loss": 0.133, "step": 61570 }, { "epoch": 14.75, "learning_rate": 9.519293990983198e-05, "loss": 0.1457, "step": 61580 }, { "epoch": 14.76, "learning_rate": 9.519140406394892e-05, "loss": 0.1714, "step": 61590 }, { "epoch": 14.76, "learning_rate": 9.518986798514898e-05, "loss": 0.1238, "step": 61600 }, { "epoch": 14.76, "learning_rate": 9.51883316734401e-05, "loss": 0.12, "step": 61610 }, { "epoch": 14.76, "learning_rate": 9.518679512883015e-05, "loss": 0.1352, "step": 61620 }, { "epoch": 14.77, "learning_rate": 9.51852583513271e-05, "loss": 0.1362, "step": 61630 }, { "epoch": 14.77, "learning_rate": 9.518372134093884e-05, "loss": 0.1611, "step": 61640 }, { "epoch": 14.77, "learning_rate": 9.518218409767332e-05, "loss": 0.1555, "step": 61650 }, { "epoch": 14.77, "learning_rate": 9.518064662153843e-05, "loss": 0.1463, "step": 61660 }, { "epoch": 14.77, "learning_rate": 9.517910891254212e-05, "loss": 0.1407, "step": 61670 }, { "epoch": 14.78, "learning_rate": 9.517757097069229e-05, "loss": 0.1537, "step": 61680 }, { "epoch": 14.78, "learning_rate": 9.51760327959969e-05, "loss": 0.1761, "step": 61690 }, { "epoch": 14.78, "learning_rate": 9.517449438846384e-05, "loss": 0.0961, "step": 61700 }, { "epoch": 14.78, "learning_rate": 9.517295574810107e-05, "loss": 0.1565, "step": 61710 }, { "epoch": 14.79, "learning_rate": 9.51714168749165e-05, "loss": 0.1808, "step": 61720 }, { "epoch": 14.79, "learning_rate": 9.516987776891808e-05, "loss": 0.139, "step": 61730 }, { "epoch": 14.79, "learning_rate": 9.516833843011372e-05, "loss": 0.0849, "step": 61740 }, { "epoch": 14.79, "learning_rate": 9.516679885851138e-05, "loss": 0.2319, "step": 61750 }, { "epoch": 14.79, "learning_rate": 9.516525905411898e-05, "loss": 0.0852, "step": 61760 }, { "epoch": 14.8, "learning_rate": 9.516371901694445e-05, "loss": 0.1598, "step": 61770 }, { "epoch": 14.8, "learning_rate": 9.516217874699573e-05, "loss": 0.1775, "step": 61780 }, { "epoch": 14.8, "learning_rate": 9.516063824428078e-05, "loss": 0.1098, "step": 61790 }, { "epoch": 14.8, "learning_rate": 9.515909750880752e-05, "loss": 0.1448, "step": 61800 }, { "epoch": 14.81, "learning_rate": 9.515755654058389e-05, "loss": 0.1392, "step": 61810 }, { "epoch": 14.81, "learning_rate": 9.515601533961784e-05, "loss": 0.1144, "step": 61820 }, { "epoch": 14.81, "learning_rate": 9.51544739059173e-05, "loss": 0.1228, "step": 61830 }, { "epoch": 14.81, "learning_rate": 9.515293223949022e-05, "loss": 0.1163, "step": 61840 }, { "epoch": 14.82, "learning_rate": 9.515139034034456e-05, "loss": 0.1014, "step": 61850 }, { "epoch": 14.82, "learning_rate": 9.514984820848826e-05, "loss": 0.1851, "step": 61860 }, { "epoch": 14.82, "learning_rate": 9.514830584392925e-05, "loss": 0.1057, "step": 61870 }, { "epoch": 14.82, "learning_rate": 9.514676324667551e-05, "loss": 0.1662, "step": 61880 }, { "epoch": 14.82, "learning_rate": 9.514522041673496e-05, "loss": 0.1408, "step": 61890 }, { "epoch": 14.83, "learning_rate": 9.514367735411558e-05, "loss": 0.12, "step": 61900 }, { "epoch": 14.83, "learning_rate": 9.514213405882531e-05, "loss": 0.1178, "step": 61910 }, { "epoch": 14.83, "learning_rate": 9.51405905308721e-05, "loss": 0.0983, "step": 61920 }, { "epoch": 14.83, "learning_rate": 9.51390467702639e-05, "loss": 0.1448, "step": 61930 }, { "epoch": 14.84, "learning_rate": 9.513750277700869e-05, "loss": 0.131, "step": 61940 }, { "epoch": 14.84, "learning_rate": 9.513595855111441e-05, "loss": 0.1362, "step": 61950 }, { "epoch": 14.84, "learning_rate": 9.513441409258901e-05, "loss": 0.1882, "step": 61960 }, { "epoch": 14.84, "learning_rate": 9.513286940144048e-05, "loss": 0.1602, "step": 61970 }, { "epoch": 14.85, "learning_rate": 9.513132447767675e-05, "loss": 0.1108, "step": 61980 }, { "epoch": 14.85, "learning_rate": 9.51297793213058e-05, "loss": 0.1226, "step": 61990 }, { "epoch": 14.85, "learning_rate": 9.512823393233558e-05, "loss": 0.1385, "step": 62000 }, { "epoch": 14.85, "learning_rate": 9.51266883107741e-05, "loss": 0.17, "step": 62010 }, { "epoch": 14.85, "learning_rate": 9.512514245662925e-05, "loss": 0.0905, "step": 62020 }, { "epoch": 14.86, "learning_rate": 9.512359636990907e-05, "loss": 0.1219, "step": 62030 }, { "epoch": 14.86, "learning_rate": 9.512205005062149e-05, "loss": 0.0798, "step": 62040 }, { "epoch": 14.86, "learning_rate": 9.512050349877448e-05, "loss": 0.1608, "step": 62050 }, { "epoch": 14.86, "learning_rate": 9.511895671437601e-05, "loss": 0.1264, "step": 62060 }, { "epoch": 14.87, "learning_rate": 9.511740969743406e-05, "loss": 0.1259, "step": 62070 }, { "epoch": 14.87, "learning_rate": 9.511586244795662e-05, "loss": 0.1221, "step": 62080 }, { "epoch": 14.87, "learning_rate": 9.511431496595165e-05, "loss": 0.1908, "step": 62090 }, { "epoch": 14.87, "learning_rate": 9.51127672514271e-05, "loss": 0.1713, "step": 62100 }, { "epoch": 14.87, "learning_rate": 9.511121930439099e-05, "loss": 0.149, "step": 62110 }, { "epoch": 14.88, "learning_rate": 9.510967112485128e-05, "loss": 0.1622, "step": 62120 }, { "epoch": 14.88, "learning_rate": 9.510812271281593e-05, "loss": 0.1621, "step": 62130 }, { "epoch": 14.88, "learning_rate": 9.510657406829295e-05, "loss": 0.1773, "step": 62140 }, { "epoch": 14.88, "learning_rate": 9.51050251912903e-05, "loss": 0.1303, "step": 62150 }, { "epoch": 14.89, "learning_rate": 9.510347608181599e-05, "loss": 0.1817, "step": 62160 }, { "epoch": 14.89, "learning_rate": 9.510192673987799e-05, "loss": 0.1693, "step": 62170 }, { "epoch": 14.89, "learning_rate": 9.510037716548425e-05, "loss": 0.171, "step": 62180 }, { "epoch": 14.89, "learning_rate": 9.509882735864282e-05, "loss": 0.11, "step": 62190 }, { "epoch": 14.9, "learning_rate": 9.509727731936165e-05, "loss": 0.1262, "step": 62200 }, { "epoch": 14.9, "learning_rate": 9.509572704764873e-05, "loss": 0.1569, "step": 62210 }, { "epoch": 14.9, "learning_rate": 9.509417654351208e-05, "loss": 0.1092, "step": 62220 }, { "epoch": 14.9, "learning_rate": 9.509262580695963e-05, "loss": 0.1847, "step": 62230 }, { "epoch": 14.9, "learning_rate": 9.509107483799943e-05, "loss": 0.1211, "step": 62240 }, { "epoch": 14.91, "learning_rate": 9.508952363663946e-05, "loss": 0.123, "step": 62250 }, { "epoch": 14.91, "learning_rate": 9.50879722028877e-05, "loss": 0.1568, "step": 62260 }, { "epoch": 14.91, "learning_rate": 9.508642053675214e-05, "loss": 0.1406, "step": 62270 }, { "epoch": 14.91, "learning_rate": 9.50848686382408e-05, "loss": 0.152, "step": 62280 }, { "epoch": 14.92, "learning_rate": 9.508331650736169e-05, "loss": 0.1415, "step": 62290 }, { "epoch": 14.92, "learning_rate": 9.508176414412277e-05, "loss": 0.1308, "step": 62300 }, { "epoch": 14.92, "learning_rate": 9.508021154853206e-05, "loss": 0.1257, "step": 62310 }, { "epoch": 14.92, "learning_rate": 9.507865872059757e-05, "loss": 0.1319, "step": 62320 }, { "epoch": 14.93, "learning_rate": 9.507710566032729e-05, "loss": 0.113, "step": 62330 }, { "epoch": 14.93, "learning_rate": 9.507555236772924e-05, "loss": 0.1142, "step": 62340 }, { "epoch": 14.93, "learning_rate": 9.50739988428114e-05, "loss": 0.1645, "step": 62350 }, { "epoch": 14.93, "learning_rate": 9.507244508558182e-05, "loss": 0.1354, "step": 62360 }, { "epoch": 14.93, "learning_rate": 9.507089109604845e-05, "loss": 0.1409, "step": 62370 }, { "epoch": 14.94, "learning_rate": 9.506933687421935e-05, "loss": 0.1268, "step": 62380 }, { "epoch": 14.94, "learning_rate": 9.506778242010252e-05, "loss": 0.1005, "step": 62390 }, { "epoch": 14.94, "learning_rate": 9.506622773370594e-05, "loss": 0.1154, "step": 62400 }, { "epoch": 14.94, "learning_rate": 9.506467281503766e-05, "loss": 0.1396, "step": 62410 }, { "epoch": 14.95, "learning_rate": 9.506311766410567e-05, "loss": 0.1354, "step": 62420 }, { "epoch": 14.95, "learning_rate": 9.506156228091801e-05, "loss": 0.1069, "step": 62430 }, { "epoch": 14.95, "learning_rate": 9.506000666548267e-05, "loss": 0.1341, "step": 62440 }, { "epoch": 15.0, "learning_rate": 9.505845081780768e-05, "loss": 0.1392, "step": 62450 }, { "epoch": 15.0, "learning_rate": 9.505689473790104e-05, "loss": 0.1426, "step": 62460 }, { "epoch": 15.01, "learning_rate": 9.505533842577081e-05, "loss": 0.1121, "step": 62470 }, { "epoch": 15.01, "learning_rate": 9.5053781881425e-05, "loss": 0.1182, "step": 62480 }, { "epoch": 15.01, "learning_rate": 9.505222510487159e-05, "loss": 0.1124, "step": 62490 }, { "epoch": 15.01, "learning_rate": 9.505066809611866e-05, "loss": 0.1296, "step": 62500 }, { "epoch": 15.01, "learning_rate": 9.50491108551742e-05, "loss": 0.1499, "step": 62510 }, { "epoch": 15.02, "learning_rate": 9.504755338204625e-05, "loss": 0.1613, "step": 62520 }, { "epoch": 15.02, "learning_rate": 9.504599567674283e-05, "loss": 0.1278, "step": 62530 }, { "epoch": 15.02, "learning_rate": 9.504443773927199e-05, "loss": 0.1252, "step": 62540 }, { "epoch": 15.02, "learning_rate": 9.50428795696417e-05, "loss": 0.1159, "step": 62550 }, { "epoch": 15.03, "learning_rate": 9.504132116786006e-05, "loss": 0.104, "step": 62560 }, { "epoch": 15.03, "learning_rate": 9.503976253393508e-05, "loss": 0.1097, "step": 62570 }, { "epoch": 15.03, "learning_rate": 9.503820366787478e-05, "loss": 0.1366, "step": 62580 }, { "epoch": 15.03, "learning_rate": 9.503664456968719e-05, "loss": 0.1034, "step": 62590 }, { "epoch": 15.04, "learning_rate": 9.503508523938039e-05, "loss": 0.0937, "step": 62600 }, { "epoch": 15.04, "learning_rate": 9.503352567696235e-05, "loss": 0.1161, "step": 62610 }, { "epoch": 15.04, "learning_rate": 9.503196588244116e-05, "loss": 0.1064, "step": 62620 }, { "epoch": 15.04, "learning_rate": 9.503040585582484e-05, "loss": 0.131, "step": 62630 }, { "epoch": 15.04, "learning_rate": 9.502884559712142e-05, "loss": 0.1256, "step": 62640 }, { "epoch": 15.05, "learning_rate": 9.502728510633897e-05, "loss": 0.1318, "step": 62650 }, { "epoch": 15.05, "learning_rate": 9.502572438348549e-05, "loss": 0.1146, "step": 62660 }, { "epoch": 15.05, "learning_rate": 9.502416342856908e-05, "loss": 0.1165, "step": 62670 }, { "epoch": 15.05, "learning_rate": 9.502260224159774e-05, "loss": 0.1253, "step": 62680 }, { "epoch": 15.06, "learning_rate": 9.502104082257953e-05, "loss": 0.105, "step": 62690 }, { "epoch": 15.06, "learning_rate": 9.50194791715225e-05, "loss": 0.1505, "step": 62700 }, { "epoch": 15.06, "learning_rate": 9.50179172884347e-05, "loss": 0.1146, "step": 62710 }, { "epoch": 15.06, "learning_rate": 9.50163551733242e-05, "loss": 0.1192, "step": 62720 }, { "epoch": 15.07, "learning_rate": 9.5014792826199e-05, "loss": 0.1169, "step": 62730 }, { "epoch": 15.07, "learning_rate": 9.501323024706719e-05, "loss": 0.079, "step": 62740 }, { "epoch": 15.07, "learning_rate": 9.501166743593682e-05, "loss": 0.0684, "step": 62750 }, { "epoch": 15.07, "learning_rate": 9.501010439281592e-05, "loss": 0.1185, "step": 62760 }, { "epoch": 15.07, "learning_rate": 9.500854111771258e-05, "loss": 0.1531, "step": 62770 }, { "epoch": 15.08, "learning_rate": 9.500697761063485e-05, "loss": 0.092, "step": 62780 }, { "epoch": 15.08, "learning_rate": 9.500541387159078e-05, "loss": 0.1548, "step": 62790 }, { "epoch": 15.08, "learning_rate": 9.500384990058841e-05, "loss": 0.0962, "step": 62800 }, { "epoch": 15.08, "learning_rate": 9.500228569763585e-05, "loss": 0.1059, "step": 62810 }, { "epoch": 15.09, "learning_rate": 9.50007212627411e-05, "loss": 0.1188, "step": 62820 }, { "epoch": 15.09, "learning_rate": 9.499915659591229e-05, "loss": 0.1503, "step": 62830 }, { "epoch": 15.09, "learning_rate": 9.499759169715746e-05, "loss": 0.1499, "step": 62840 }, { "epoch": 15.09, "learning_rate": 9.499602656648463e-05, "loss": 0.1325, "step": 62850 }, { "epoch": 15.09, "learning_rate": 9.499446120390192e-05, "loss": 0.1181, "step": 62860 }, { "epoch": 15.1, "learning_rate": 9.499289560941737e-05, "loss": 0.0825, "step": 62870 }, { "epoch": 15.1, "learning_rate": 9.499132978303907e-05, "loss": 0.1303, "step": 62880 }, { "epoch": 15.1, "learning_rate": 9.498976372477508e-05, "loss": 0.1352, "step": 62890 }, { "epoch": 15.1, "learning_rate": 9.498819743463347e-05, "loss": 0.1204, "step": 62900 }, { "epoch": 15.11, "learning_rate": 9.49866309126223e-05, "loss": 0.0828, "step": 62910 }, { "epoch": 15.11, "learning_rate": 9.498506415874968e-05, "loss": 0.1064, "step": 62920 }, { "epoch": 15.11, "learning_rate": 9.498349717302367e-05, "loss": 0.1685, "step": 62930 }, { "epoch": 15.11, "learning_rate": 9.498192995545232e-05, "loss": 0.1192, "step": 62940 }, { "epoch": 15.12, "learning_rate": 9.498036250604373e-05, "loss": 0.1009, "step": 62950 }, { "epoch": 15.12, "learning_rate": 9.497879482480597e-05, "loss": 0.125, "step": 62960 }, { "epoch": 15.12, "learning_rate": 9.497722691174713e-05, "loss": 0.1299, "step": 62970 }, { "epoch": 15.12, "learning_rate": 9.49756587668753e-05, "loss": 0.0723, "step": 62980 }, { "epoch": 15.12, "learning_rate": 9.497409039019853e-05, "loss": 0.1474, "step": 62990 }, { "epoch": 15.13, "learning_rate": 9.497252178172493e-05, "loss": 0.0735, "step": 63000 }, { "epoch": 15.13, "learning_rate": 9.497095294146259e-05, "loss": 0.0971, "step": 63010 }, { "epoch": 15.13, "learning_rate": 9.496938386941956e-05, "loss": 0.1808, "step": 63020 }, { "epoch": 15.13, "learning_rate": 9.496781456560397e-05, "loss": 0.1043, "step": 63030 }, { "epoch": 15.14, "learning_rate": 9.496624503002387e-05, "loss": 0.1319, "step": 63040 }, { "epoch": 15.14, "learning_rate": 9.496467526268738e-05, "loss": 0.1419, "step": 63050 }, { "epoch": 15.14, "learning_rate": 9.496310526360257e-05, "loss": 0.1181, "step": 63060 }, { "epoch": 15.14, "learning_rate": 9.496153503277754e-05, "loss": 0.1133, "step": 63070 }, { "epoch": 15.15, "learning_rate": 9.495996457022038e-05, "loss": 0.1693, "step": 63080 }, { "epoch": 15.15, "learning_rate": 9.49583938759392e-05, "loss": 0.1249, "step": 63090 }, { "epoch": 15.15, "learning_rate": 9.495682294994208e-05, "loss": 0.1255, "step": 63100 }, { "epoch": 15.15, "learning_rate": 9.495525179223711e-05, "loss": 0.1173, "step": 63110 }, { "epoch": 15.15, "learning_rate": 9.495368040283241e-05, "loss": 0.1461, "step": 63120 }, { "epoch": 15.16, "learning_rate": 9.495210878173604e-05, "loss": 0.1365, "step": 63130 }, { "epoch": 15.16, "learning_rate": 9.495053692895615e-05, "loss": 0.1736, "step": 63140 }, { "epoch": 15.16, "learning_rate": 9.49489648445008e-05, "loss": 0.0995, "step": 63150 }, { "epoch": 15.16, "learning_rate": 9.494739252837813e-05, "loss": 0.1334, "step": 63160 }, { "epoch": 15.17, "learning_rate": 9.494581998059619e-05, "loss": 0.1239, "step": 63170 }, { "epoch": 15.17, "learning_rate": 9.494424720116315e-05, "loss": 0.0862, "step": 63180 }, { "epoch": 15.17, "learning_rate": 9.494267419008707e-05, "loss": 0.1136, "step": 63190 }, { "epoch": 15.17, "learning_rate": 9.494110094737607e-05, "loss": 0.1413, "step": 63200 }, { "epoch": 15.17, "learning_rate": 9.493952747303826e-05, "loss": 0.1406, "step": 63210 }, { "epoch": 15.18, "learning_rate": 9.493795376708177e-05, "loss": 0.1138, "step": 63220 }, { "epoch": 15.18, "learning_rate": 9.493637982951467e-05, "loss": 0.0869, "step": 63230 }, { "epoch": 15.18, "learning_rate": 9.493480566034509e-05, "loss": 0.1148, "step": 63240 }, { "epoch": 15.18, "learning_rate": 9.493323125958115e-05, "loss": 0.1308, "step": 63250 }, { "epoch": 15.19, "learning_rate": 9.493165662723097e-05, "loss": 0.1121, "step": 63260 }, { "epoch": 15.19, "learning_rate": 9.493008176330265e-05, "loss": 0.1092, "step": 63270 }, { "epoch": 15.19, "learning_rate": 9.49285066678043e-05, "loss": 0.1428, "step": 63280 }, { "epoch": 15.19, "learning_rate": 9.492693134074409e-05, "loss": 0.1031, "step": 63290 }, { "epoch": 15.2, "learning_rate": 9.492535578213007e-05, "loss": 0.0845, "step": 63300 }, { "epoch": 15.2, "learning_rate": 9.492377999197038e-05, "loss": 0.1184, "step": 63310 }, { "epoch": 15.2, "learning_rate": 9.492220397027318e-05, "loss": 0.142, "step": 63320 }, { "epoch": 15.2, "learning_rate": 9.492062771704655e-05, "loss": 0.0722, "step": 63330 }, { "epoch": 15.2, "learning_rate": 9.491905123229863e-05, "loss": 0.1832, "step": 63340 }, { "epoch": 15.21, "learning_rate": 9.491747451603755e-05, "loss": 0.1324, "step": 63350 }, { "epoch": 15.21, "learning_rate": 9.491589756827141e-05, "loss": 0.0893, "step": 63360 }, { "epoch": 15.21, "learning_rate": 9.49143203890084e-05, "loss": 0.0727, "step": 63370 }, { "epoch": 15.21, "learning_rate": 9.491274297825657e-05, "loss": 0.1294, "step": 63380 }, { "epoch": 15.22, "learning_rate": 9.491116533602411e-05, "loss": 0.1174, "step": 63390 }, { "epoch": 15.22, "learning_rate": 9.49095874623191e-05, "loss": 0.1074, "step": 63400 }, { "epoch": 15.22, "learning_rate": 9.490800935714975e-05, "loss": 0.1209, "step": 63410 }, { "epoch": 15.22, "learning_rate": 9.49064310205241e-05, "loss": 0.0895, "step": 63420 }, { "epoch": 15.23, "learning_rate": 9.490485245245033e-05, "loss": 0.0957, "step": 63430 }, { "epoch": 15.23, "learning_rate": 9.49032736529366e-05, "loss": 0.1082, "step": 63440 }, { "epoch": 15.23, "learning_rate": 9.490169462199101e-05, "loss": 0.1404, "step": 63450 }, { "epoch": 15.23, "learning_rate": 9.49001153596217e-05, "loss": 0.1185, "step": 63460 }, { "epoch": 15.23, "learning_rate": 9.489853586583684e-05, "loss": 0.1013, "step": 63470 }, { "epoch": 15.24, "learning_rate": 9.489695614064454e-05, "loss": 0.0892, "step": 63480 }, { "epoch": 15.24, "learning_rate": 9.489537618405295e-05, "loss": 0.1051, "step": 63490 }, { "epoch": 15.24, "learning_rate": 9.489379599607022e-05, "loss": 0.112, "step": 63500 }, { "epoch": 15.24, "learning_rate": 9.48922155767045e-05, "loss": 0.1043, "step": 63510 }, { "epoch": 15.25, "learning_rate": 9.489063492596392e-05, "loss": 0.1044, "step": 63520 }, { "epoch": 15.25, "learning_rate": 9.488905404385664e-05, "loss": 0.1107, "step": 63530 }, { "epoch": 15.25, "learning_rate": 9.488747293039077e-05, "loss": 0.0897, "step": 63540 }, { "epoch": 15.25, "learning_rate": 9.488589158557453e-05, "loss": 0.1328, "step": 63550 }, { "epoch": 15.25, "learning_rate": 9.4884310009416e-05, "loss": 0.101, "step": 63560 }, { "epoch": 15.26, "learning_rate": 9.488272820192337e-05, "loss": 0.0871, "step": 63570 }, { "epoch": 15.26, "learning_rate": 9.488114616310477e-05, "loss": 0.1099, "step": 63580 }, { "epoch": 15.26, "learning_rate": 9.48795638929684e-05, "loss": 0.0846, "step": 63590 }, { "epoch": 15.26, "learning_rate": 9.487798139152235e-05, "loss": 0.0974, "step": 63600 }, { "epoch": 15.27, "learning_rate": 9.487639865877482e-05, "loss": 0.0756, "step": 63610 }, { "epoch": 15.27, "learning_rate": 9.487481569473397e-05, "loss": 0.1143, "step": 63620 }, { "epoch": 15.27, "learning_rate": 9.487323249940792e-05, "loss": 0.1007, "step": 63630 }, { "epoch": 15.27, "learning_rate": 9.487164907280488e-05, "loss": 0.1232, "step": 63640 }, { "epoch": 15.28, "learning_rate": 9.487006541493296e-05, "loss": 0.1219, "step": 63650 }, { "epoch": 15.28, "learning_rate": 9.486848152580037e-05, "loss": 0.1499, "step": 63660 }, { "epoch": 15.28, "learning_rate": 9.486689740541523e-05, "loss": 0.1736, "step": 63670 }, { "epoch": 15.28, "learning_rate": 9.486531305378574e-05, "loss": 0.1574, "step": 63680 }, { "epoch": 15.28, "learning_rate": 9.486372847092005e-05, "loss": 0.1181, "step": 63690 }, { "epoch": 15.29, "learning_rate": 9.486214365682633e-05, "loss": 0.1274, "step": 63700 }, { "epoch": 15.29, "learning_rate": 9.486055861151276e-05, "loss": 0.1041, "step": 63710 }, { "epoch": 15.29, "learning_rate": 9.485897333498747e-05, "loss": 0.0942, "step": 63720 }, { "epoch": 15.29, "learning_rate": 9.485738782725866e-05, "loss": 0.1213, "step": 63730 }, { "epoch": 15.3, "learning_rate": 9.485580208833451e-05, "loss": 0.1132, "step": 63740 }, { "epoch": 15.3, "learning_rate": 9.485421611822318e-05, "loss": 0.1314, "step": 63750 }, { "epoch": 15.3, "learning_rate": 9.485262991693284e-05, "loss": 0.1386, "step": 63760 }, { "epoch": 15.3, "learning_rate": 9.485104348447167e-05, "loss": 0.1301, "step": 63770 }, { "epoch": 15.31, "learning_rate": 9.484945682084785e-05, "loss": 0.0843, "step": 63780 }, { "epoch": 15.31, "learning_rate": 9.484786992606956e-05, "loss": 0.1123, "step": 63790 }, { "epoch": 15.31, "learning_rate": 9.484628280014496e-05, "loss": 0.1243, "step": 63800 }, { "epoch": 15.31, "learning_rate": 9.484469544308226e-05, "loss": 0.1059, "step": 63810 }, { "epoch": 15.31, "learning_rate": 9.484310785488961e-05, "loss": 0.0601, "step": 63820 }, { "epoch": 15.32, "learning_rate": 9.48415200355752e-05, "loss": 0.097, "step": 63830 }, { "epoch": 15.32, "learning_rate": 9.483993198514725e-05, "loss": 0.1018, "step": 63840 }, { "epoch": 15.32, "learning_rate": 9.483834370361388e-05, "loss": 0.1213, "step": 63850 }, { "epoch": 15.32, "learning_rate": 9.483675519098334e-05, "loss": 0.1425, "step": 63860 }, { "epoch": 15.33, "learning_rate": 9.483516644726378e-05, "loss": 0.1136, "step": 63870 }, { "epoch": 15.33, "learning_rate": 9.48335774724634e-05, "loss": 0.1114, "step": 63880 }, { "epoch": 15.33, "learning_rate": 9.483198826659039e-05, "loss": 0.1212, "step": 63890 }, { "epoch": 15.33, "learning_rate": 9.483039882965292e-05, "loss": 0.1025, "step": 63900 }, { "epoch": 15.33, "learning_rate": 9.482880916165922e-05, "loss": 0.1103, "step": 63910 }, { "epoch": 15.34, "learning_rate": 9.482721926261747e-05, "loss": 0.0915, "step": 63920 }, { "epoch": 15.34, "learning_rate": 9.482562913253584e-05, "loss": 0.0905, "step": 63930 }, { "epoch": 15.34, "learning_rate": 9.482403877142253e-05, "loss": 0.1236, "step": 63940 }, { "epoch": 15.34, "learning_rate": 9.482244817928577e-05, "loss": 0.1087, "step": 63950 }, { "epoch": 15.35, "learning_rate": 9.482085735613372e-05, "loss": 0.1188, "step": 63960 }, { "epoch": 15.35, "learning_rate": 9.481926630197461e-05, "loss": 0.1278, "step": 63970 }, { "epoch": 15.35, "learning_rate": 9.481767501681664e-05, "loss": 0.1031, "step": 63980 }, { "epoch": 15.35, "learning_rate": 9.481608350066798e-05, "loss": 0.107, "step": 63990 }, { "epoch": 15.36, "learning_rate": 9.481449175353685e-05, "loss": 0.1358, "step": 64000 }, { "epoch": 15.36, "learning_rate": 9.481289977543146e-05, "loss": 0.1162, "step": 64010 }, { "epoch": 15.36, "learning_rate": 9.481130756636e-05, "loss": 0.0817, "step": 64020 }, { "epoch": 15.36, "learning_rate": 9.48097151263307e-05, "loss": 0.1036, "step": 64030 }, { "epoch": 15.36, "learning_rate": 9.480812245535176e-05, "loss": 0.1314, "step": 64040 }, { "epoch": 15.37, "learning_rate": 9.480652955343137e-05, "loss": 0.0672, "step": 64050 }, { "epoch": 15.37, "learning_rate": 9.480493642057775e-05, "loss": 0.0676, "step": 64060 }, { "epoch": 15.37, "learning_rate": 9.480334305679912e-05, "loss": 0.1239, "step": 64070 }, { "epoch": 15.37, "learning_rate": 9.480174946210367e-05, "loss": 0.0928, "step": 64080 }, { "epoch": 15.38, "learning_rate": 9.480015563649965e-05, "loss": 0.1317, "step": 64090 }, { "epoch": 15.38, "learning_rate": 9.479856157999524e-05, "loss": 0.1534, "step": 64100 }, { "epoch": 15.38, "learning_rate": 9.479696729259869e-05, "loss": 0.1136, "step": 64110 }, { "epoch": 15.38, "learning_rate": 9.479537277431816e-05, "loss": 0.0942, "step": 64120 }, { "epoch": 15.39, "learning_rate": 9.479377802516193e-05, "loss": 0.0909, "step": 64130 }, { "epoch": 15.39, "learning_rate": 9.479218304513819e-05, "loss": 0.1182, "step": 64140 }, { "epoch": 15.39, "learning_rate": 9.479058783425517e-05, "loss": 0.1097, "step": 64150 }, { "epoch": 15.39, "learning_rate": 9.478899239252107e-05, "loss": 0.084, "step": 64160 }, { "epoch": 15.39, "learning_rate": 9.478739671994413e-05, "loss": 0.1012, "step": 64170 }, { "epoch": 15.4, "learning_rate": 9.478580081653259e-05, "loss": 0.1122, "step": 64180 }, { "epoch": 15.4, "learning_rate": 9.478420468229464e-05, "loss": 0.0948, "step": 64190 }, { "epoch": 15.4, "learning_rate": 9.478260831723853e-05, "loss": 0.1034, "step": 64200 }, { "epoch": 15.4, "learning_rate": 9.478101172137247e-05, "loss": 0.1194, "step": 64210 }, { "epoch": 15.41, "learning_rate": 9.477941489470473e-05, "loss": 0.1033, "step": 64220 }, { "epoch": 15.41, "learning_rate": 9.477781783724352e-05, "loss": 0.1071, "step": 64230 }, { "epoch": 15.41, "learning_rate": 9.477622054899702e-05, "loss": 0.1555, "step": 64240 }, { "epoch": 15.41, "learning_rate": 9.477462302997353e-05, "loss": 0.1072, "step": 64250 }, { "epoch": 15.41, "learning_rate": 9.477302528018125e-05, "loss": 0.1072, "step": 64260 }, { "epoch": 15.42, "learning_rate": 9.477142729962842e-05, "loss": 0.1229, "step": 64270 }, { "epoch": 15.42, "learning_rate": 9.47698290883233e-05, "loss": 0.0915, "step": 64280 }, { "epoch": 15.42, "learning_rate": 9.476823064627409e-05, "loss": 0.0743, "step": 64290 }, { "epoch": 15.42, "learning_rate": 9.476663197348905e-05, "loss": 0.0967, "step": 64300 }, { "epoch": 15.43, "learning_rate": 9.476503306997642e-05, "loss": 0.1358, "step": 64310 }, { "epoch": 15.43, "learning_rate": 9.476343393574442e-05, "loss": 0.16, "step": 64320 }, { "epoch": 15.43, "learning_rate": 9.476183457080132e-05, "loss": 0.1051, "step": 64330 }, { "epoch": 15.43, "learning_rate": 9.476023497515533e-05, "loss": 0.1065, "step": 64340 }, { "epoch": 15.44, "learning_rate": 9.475863514881473e-05, "loss": 0.1173, "step": 64350 }, { "epoch": 15.44, "learning_rate": 9.475703509178777e-05, "loss": 0.0846, "step": 64360 }, { "epoch": 15.44, "learning_rate": 9.475543480408264e-05, "loss": 0.1169, "step": 64370 }, { "epoch": 15.44, "learning_rate": 9.475383428570765e-05, "loss": 0.119, "step": 64380 }, { "epoch": 15.44, "learning_rate": 9.475223353667102e-05, "loss": 0.1272, "step": 64390 }, { "epoch": 15.45, "learning_rate": 9.4750632556981e-05, "loss": 0.0925, "step": 64400 }, { "epoch": 15.45, "learning_rate": 9.474903134664586e-05, "loss": 0.1245, "step": 64410 }, { "epoch": 15.45, "learning_rate": 9.474742990567382e-05, "loss": 0.0854, "step": 64420 }, { "epoch": 15.45, "learning_rate": 9.474582823407315e-05, "loss": 0.1349, "step": 64430 }, { "epoch": 15.46, "learning_rate": 9.474422633185212e-05, "loss": 0.1188, "step": 64440 }, { "epoch": 15.46, "learning_rate": 9.474262419901897e-05, "loss": 0.1346, "step": 64450 }, { "epoch": 15.46, "learning_rate": 9.474102183558196e-05, "loss": 0.1469, "step": 64460 }, { "epoch": 15.46, "learning_rate": 9.473941924154934e-05, "loss": 0.0951, "step": 64470 }, { "epoch": 15.47, "learning_rate": 9.473781641692939e-05, "loss": 0.1285, "step": 64480 }, { "epoch": 15.47, "learning_rate": 9.473621336173037e-05, "loss": 0.1322, "step": 64490 }, { "epoch": 15.47, "learning_rate": 9.473461007596051e-05, "loss": 0.1068, "step": 64500 }, { "epoch": 15.47, "learning_rate": 9.473300655962811e-05, "loss": 0.0972, "step": 64510 }, { "epoch": 15.47, "learning_rate": 9.473140281274143e-05, "loss": 0.0906, "step": 64520 }, { "epoch": 15.48, "learning_rate": 9.47297988353087e-05, "loss": 0.159, "step": 64530 }, { "epoch": 15.48, "learning_rate": 9.472819462733823e-05, "loss": 0.0955, "step": 64540 }, { "epoch": 15.48, "learning_rate": 9.472659018883827e-05, "loss": 0.1066, "step": 64550 }, { "epoch": 15.48, "learning_rate": 9.472498551981708e-05, "loss": 0.121, "step": 64560 }, { "epoch": 15.49, "learning_rate": 9.472338062028294e-05, "loss": 0.0853, "step": 64570 }, { "epoch": 15.49, "learning_rate": 9.472177549024414e-05, "loss": 0.1182, "step": 64580 }, { "epoch": 15.49, "learning_rate": 9.472017012970893e-05, "loss": 0.1484, "step": 64590 }, { "epoch": 15.49, "learning_rate": 9.471856453868558e-05, "loss": 0.0992, "step": 64600 }, { "epoch": 15.49, "learning_rate": 9.471695871718238e-05, "loss": 0.0866, "step": 64610 }, { "epoch": 15.5, "learning_rate": 9.47153526652076e-05, "loss": 0.0757, "step": 64620 }, { "epoch": 15.5, "learning_rate": 9.471374638276951e-05, "loss": 0.1435, "step": 64630 }, { "epoch": 15.5, "learning_rate": 9.471213986987642e-05, "loss": 0.0963, "step": 64640 }, { "epoch": 15.5, "learning_rate": 9.471053312653658e-05, "loss": 0.1366, "step": 64650 }, { "epoch": 15.51, "learning_rate": 9.470892615275826e-05, "loss": 0.1081, "step": 64660 }, { "epoch": 15.51, "learning_rate": 9.470731894854978e-05, "loss": 0.126, "step": 64670 }, { "epoch": 15.51, "learning_rate": 9.47057115139194e-05, "loss": 0.096, "step": 64680 }, { "epoch": 15.51, "learning_rate": 9.47041038488754e-05, "loss": 0.1592, "step": 64690 }, { "epoch": 15.52, "learning_rate": 9.470249595342609e-05, "loss": 0.1286, "step": 64700 }, { "epoch": 15.52, "learning_rate": 9.470088782757974e-05, "loss": 0.0661, "step": 64710 }, { "epoch": 15.52, "learning_rate": 9.469927947134462e-05, "loss": 0.1354, "step": 64720 }, { "epoch": 15.52, "learning_rate": 9.469767088472906e-05, "loss": 0.1048, "step": 64730 }, { "epoch": 15.52, "learning_rate": 9.469606206774133e-05, "loss": 0.0943, "step": 64740 }, { "epoch": 15.53, "learning_rate": 9.46944530203897e-05, "loss": 0.1293, "step": 64750 }, { "epoch": 15.53, "learning_rate": 9.469284374268251e-05, "loss": 0.1316, "step": 64760 }, { "epoch": 15.53, "learning_rate": 9.469123423462802e-05, "loss": 0.1639, "step": 64770 }, { "epoch": 15.53, "learning_rate": 9.468962449623455e-05, "loss": 0.1582, "step": 64780 }, { "epoch": 15.54, "learning_rate": 9.468801452751036e-05, "loss": 0.1454, "step": 64790 }, { "epoch": 15.54, "learning_rate": 9.468640432846378e-05, "loss": 0.2093, "step": 64800 }, { "epoch": 15.54, "learning_rate": 9.46847938991031e-05, "loss": 0.2058, "step": 64810 }, { "epoch": 15.54, "learning_rate": 9.468318323943662e-05, "loss": 0.231, "step": 64820 }, { "epoch": 15.55, "learning_rate": 9.468157234947264e-05, "loss": 0.1618, "step": 64830 }, { "epoch": 15.55, "learning_rate": 9.467996122921946e-05, "loss": 0.1677, "step": 64840 }, { "epoch": 15.55, "learning_rate": 9.46783498786854e-05, "loss": 0.1774, "step": 64850 }, { "epoch": 15.55, "learning_rate": 9.467673829787872e-05, "loss": 0.1925, "step": 64860 }, { "epoch": 15.55, "learning_rate": 9.467512648680779e-05, "loss": 0.1356, "step": 64870 }, { "epoch": 15.56, "learning_rate": 9.467351444548086e-05, "loss": 0.1565, "step": 64880 }, { "epoch": 15.56, "learning_rate": 9.467190217390626e-05, "loss": 0.1955, "step": 64890 }, { "epoch": 15.56, "learning_rate": 9.467028967209233e-05, "loss": 0.176, "step": 64900 }, { "epoch": 15.56, "learning_rate": 9.466867694004733e-05, "loss": 0.1942, "step": 64910 }, { "epoch": 15.57, "learning_rate": 9.466706397777961e-05, "loss": 0.1715, "step": 64920 }, { "epoch": 15.57, "learning_rate": 9.466545078529747e-05, "loss": 0.1779, "step": 64930 }, { "epoch": 15.57, "learning_rate": 9.466383736260922e-05, "loss": 0.1886, "step": 64940 }, { "epoch": 15.57, "learning_rate": 9.466222370972317e-05, "loss": 0.1296, "step": 64950 }, { "epoch": 15.57, "learning_rate": 9.466060982664765e-05, "loss": 0.2133, "step": 64960 }, { "epoch": 15.58, "learning_rate": 9.465899571339097e-05, "loss": 0.1831, "step": 64970 }, { "epoch": 15.58, "learning_rate": 9.465738136996146e-05, "loss": 0.1662, "step": 64980 }, { "epoch": 15.58, "learning_rate": 9.465576679636743e-05, "loss": 0.1258, "step": 64990 }, { "epoch": 15.58, "learning_rate": 9.465415199261721e-05, "loss": 0.1672, "step": 65000 }, { "epoch": 15.59, "learning_rate": 9.465253695871912e-05, "loss": 0.1448, "step": 65010 }, { "epoch": 15.59, "learning_rate": 9.465092169468147e-05, "loss": 0.1867, "step": 65020 }, { "epoch": 15.59, "learning_rate": 9.46493062005126e-05, "loss": 0.1608, "step": 65030 }, { "epoch": 15.59, "learning_rate": 9.464769047622084e-05, "loss": 0.1368, "step": 65040 }, { "epoch": 15.6, "learning_rate": 9.46460745218145e-05, "loss": 0.1523, "step": 65050 }, { "epoch": 15.6, "learning_rate": 9.464445833730192e-05, "loss": 0.1899, "step": 65060 }, { "epoch": 15.6, "learning_rate": 9.464284192269143e-05, "loss": 0.1103, "step": 65070 }, { "epoch": 15.6, "learning_rate": 9.464122527799135e-05, "loss": 0.1242, "step": 65080 }, { "epoch": 15.6, "learning_rate": 9.463960840321004e-05, "loss": 0.1326, "step": 65090 }, { "epoch": 15.61, "learning_rate": 9.463799129835582e-05, "loss": 0.2036, "step": 65100 }, { "epoch": 15.61, "learning_rate": 9.463637396343699e-05, "loss": 0.1344, "step": 65110 }, { "epoch": 15.61, "learning_rate": 9.463475639846193e-05, "loss": 0.1351, "step": 65120 }, { "epoch": 15.61, "learning_rate": 9.463313860343897e-05, "loss": 0.177, "step": 65130 }, { "epoch": 15.62, "learning_rate": 9.463152057837644e-05, "loss": 0.1108, "step": 65140 }, { "epoch": 15.62, "learning_rate": 9.462990232328268e-05, "loss": 0.1749, "step": 65150 }, { "epoch": 15.62, "learning_rate": 9.462828383816603e-05, "loss": 0.1226, "step": 65160 }, { "epoch": 15.62, "learning_rate": 9.462666512303481e-05, "loss": 0.1685, "step": 65170 }, { "epoch": 15.62, "learning_rate": 9.462504617789741e-05, "loss": 0.1213, "step": 65180 }, { "epoch": 15.63, "learning_rate": 9.462342700276215e-05, "loss": 0.152, "step": 65190 }, { "epoch": 15.63, "learning_rate": 9.462180759763737e-05, "loss": 0.1088, "step": 65200 }, { "epoch": 15.63, "learning_rate": 9.46201879625314e-05, "loss": 0.1101, "step": 65210 }, { "epoch": 15.63, "learning_rate": 9.461856809745263e-05, "loss": 0.2018, "step": 65220 }, { "epoch": 15.64, "learning_rate": 9.461694800240939e-05, "loss": 0.148, "step": 65230 }, { "epoch": 15.64, "learning_rate": 9.461532767741001e-05, "loss": 0.1329, "step": 65240 }, { "epoch": 15.64, "learning_rate": 9.461370712246286e-05, "loss": 0.1369, "step": 65250 }, { "epoch": 15.64, "learning_rate": 9.461208633757631e-05, "loss": 0.1361, "step": 65260 }, { "epoch": 15.65, "learning_rate": 9.461046532275868e-05, "loss": 0.1336, "step": 65270 }, { "epoch": 15.65, "learning_rate": 9.460884407801835e-05, "loss": 0.1691, "step": 65280 }, { "epoch": 15.65, "learning_rate": 9.460722260336365e-05, "loss": 0.0927, "step": 65290 }, { "epoch": 15.65, "learning_rate": 9.460560089880294e-05, "loss": 0.1424, "step": 65300 }, { "epoch": 15.65, "learning_rate": 9.460397896434464e-05, "loss": 0.2066, "step": 65310 }, { "epoch": 15.66, "learning_rate": 9.4602356799997e-05, "loss": 0.1159, "step": 65320 }, { "epoch": 15.66, "learning_rate": 9.460073440576848e-05, "loss": 0.1203, "step": 65330 }, { "epoch": 15.66, "learning_rate": 9.459911178166738e-05, "loss": 0.1129, "step": 65340 }, { "epoch": 15.66, "learning_rate": 9.45974889277021e-05, "loss": 0.1499, "step": 65350 }, { "epoch": 15.67, "learning_rate": 9.459586584388098e-05, "loss": 0.1405, "step": 65360 }, { "epoch": 15.67, "learning_rate": 9.459424253021241e-05, "loss": 0.127, "step": 65370 }, { "epoch": 15.67, "learning_rate": 9.459261898670473e-05, "loss": 0.1146, "step": 65380 }, { "epoch": 15.67, "learning_rate": 9.459099521336632e-05, "loss": 0.1111, "step": 65390 }, { "epoch": 15.68, "learning_rate": 9.458937121020554e-05, "loss": 0.1891, "step": 65400 }, { "epoch": 15.68, "learning_rate": 9.458774697723077e-05, "loss": 0.1578, "step": 65410 }, { "epoch": 15.68, "learning_rate": 9.458612251445039e-05, "loss": 0.1146, "step": 65420 }, { "epoch": 15.68, "learning_rate": 9.458449782187276e-05, "loss": 0.1449, "step": 65430 }, { "epoch": 15.68, "learning_rate": 9.458287289950624e-05, "loss": 0.1342, "step": 65440 }, { "epoch": 15.69, "learning_rate": 9.458124774735923e-05, "loss": 0.125, "step": 65450 }, { "epoch": 15.69, "learning_rate": 9.457962236544011e-05, "loss": 0.1192, "step": 65460 }, { "epoch": 15.69, "learning_rate": 9.457799675375722e-05, "loss": 0.1342, "step": 65470 }, { "epoch": 15.69, "learning_rate": 9.457637091231899e-05, "loss": 0.1493, "step": 65480 }, { "epoch": 15.7, "learning_rate": 9.457474484113375e-05, "loss": 0.1048, "step": 65490 }, { "epoch": 15.7, "learning_rate": 9.457311854020992e-05, "loss": 0.2051, "step": 65500 }, { "epoch": 15.7, "learning_rate": 9.457149200955585e-05, "loss": 0.1936, "step": 65510 }, { "epoch": 15.7, "learning_rate": 9.456986524917993e-05, "loss": 0.0931, "step": 65520 }, { "epoch": 15.7, "learning_rate": 9.456823825909056e-05, "loss": 0.1255, "step": 65530 }, { "epoch": 15.71, "learning_rate": 9.456661103929612e-05, "loss": 0.1649, "step": 65540 }, { "epoch": 15.71, "learning_rate": 9.4564983589805e-05, "loss": 0.1522, "step": 65550 }, { "epoch": 15.71, "learning_rate": 9.456335591062558e-05, "loss": 0.1315, "step": 65560 }, { "epoch": 15.71, "learning_rate": 9.456172800176624e-05, "loss": 0.1392, "step": 65570 }, { "epoch": 15.72, "learning_rate": 9.45600998632354e-05, "loss": 0.1596, "step": 65580 }, { "epoch": 15.72, "learning_rate": 9.455847149504141e-05, "loss": 0.1522, "step": 65590 }, { "epoch": 15.72, "learning_rate": 9.45568428971927e-05, "loss": 0.105, "step": 65600 }, { "epoch": 15.72, "learning_rate": 9.455521406969766e-05, "loss": 0.1452, "step": 65610 }, { "epoch": 15.73, "learning_rate": 9.455358501256465e-05, "loss": 0.1582, "step": 65620 }, { "epoch": 15.73, "learning_rate": 9.45519557258021e-05, "loss": 0.13, "step": 65630 }, { "epoch": 15.73, "learning_rate": 9.45503262094184e-05, "loss": 0.1451, "step": 65640 }, { "epoch": 15.73, "learning_rate": 9.454869646342194e-05, "loss": 0.15, "step": 65650 }, { "epoch": 15.73, "learning_rate": 9.454706648782114e-05, "loss": 0.1174, "step": 65660 }, { "epoch": 15.74, "learning_rate": 9.454543628262438e-05, "loss": 0.1265, "step": 65670 }, { "epoch": 15.74, "learning_rate": 9.454380584784006e-05, "loss": 0.1554, "step": 65680 }, { "epoch": 15.74, "learning_rate": 9.45421751834766e-05, "loss": 0.1352, "step": 65690 }, { "epoch": 15.74, "learning_rate": 9.45405442895424e-05, "loss": 0.1831, "step": 65700 }, { "epoch": 15.75, "learning_rate": 9.453891316604587e-05, "loss": 0.0946, "step": 65710 }, { "epoch": 15.75, "learning_rate": 9.453728181299538e-05, "loss": 0.1243, "step": 65720 }, { "epoch": 15.75, "learning_rate": 9.453565023039939e-05, "loss": 0.1343, "step": 65730 }, { "epoch": 15.75, "learning_rate": 9.453401841826627e-05, "loss": 0.1193, "step": 65740 }, { "epoch": 15.76, "learning_rate": 9.453238637660447e-05, "loss": 0.1626, "step": 65750 }, { "epoch": 15.76, "learning_rate": 9.453075410542236e-05, "loss": 0.1432, "step": 65760 }, { "epoch": 15.76, "learning_rate": 9.452912160472838e-05, "loss": 0.0955, "step": 65770 }, { "epoch": 15.76, "learning_rate": 9.452748887453093e-05, "loss": 0.1469, "step": 65780 }, { "epoch": 15.76, "learning_rate": 9.452585591483844e-05, "loss": 0.1123, "step": 65790 }, { "epoch": 15.77, "learning_rate": 9.45242227256593e-05, "loss": 0.1538, "step": 65800 }, { "epoch": 15.77, "learning_rate": 9.452258930700197e-05, "loss": 0.1183, "step": 65810 }, { "epoch": 15.77, "learning_rate": 9.452095565887483e-05, "loss": 0.1256, "step": 65820 }, { "epoch": 15.77, "learning_rate": 9.45193217812863e-05, "loss": 0.0981, "step": 65830 }, { "epoch": 15.78, "learning_rate": 9.451768767424482e-05, "loss": 0.1313, "step": 65840 }, { "epoch": 15.78, "learning_rate": 9.451605333775881e-05, "loss": 0.1219, "step": 65850 }, { "epoch": 15.78, "learning_rate": 9.451441877183669e-05, "loss": 0.144, "step": 65860 }, { "epoch": 15.78, "learning_rate": 9.451278397648687e-05, "loss": 0.1294, "step": 65870 }, { "epoch": 15.78, "learning_rate": 9.45111489517178e-05, "loss": 0.1189, "step": 65880 }, { "epoch": 15.79, "learning_rate": 9.450951369753792e-05, "loss": 0.1384, "step": 65890 }, { "epoch": 15.79, "learning_rate": 9.450787821395559e-05, "loss": 0.0901, "step": 65900 }, { "epoch": 15.79, "learning_rate": 9.45062425009793e-05, "loss": 0.078, "step": 65910 }, { "epoch": 15.79, "learning_rate": 9.450460655861748e-05, "loss": 0.0881, "step": 65920 }, { "epoch": 15.8, "learning_rate": 9.450297038687853e-05, "loss": 0.1679, "step": 65930 }, { "epoch": 15.8, "learning_rate": 9.45013339857709e-05, "loss": 0.1346, "step": 65940 }, { "epoch": 15.8, "learning_rate": 9.449969735530302e-05, "loss": 0.1909, "step": 65950 }, { "epoch": 15.8, "learning_rate": 9.449806049548333e-05, "loss": 0.1238, "step": 65960 }, { "epoch": 15.81, "learning_rate": 9.449642340632028e-05, "loss": 0.1479, "step": 65970 }, { "epoch": 15.81, "learning_rate": 9.449478608782227e-05, "loss": 0.1461, "step": 65980 }, { "epoch": 15.81, "learning_rate": 9.449314853999778e-05, "loss": 0.1376, "step": 65990 }, { "epoch": 15.81, "learning_rate": 9.449151076285521e-05, "loss": 0.119, "step": 66000 }, { "epoch": 15.81, "learning_rate": 9.448987275640305e-05, "loss": 0.1125, "step": 66010 }, { "epoch": 15.82, "learning_rate": 9.448823452064968e-05, "loss": 0.1441, "step": 66020 }, { "epoch": 15.82, "learning_rate": 9.44865960556036e-05, "loss": 0.1348, "step": 66030 }, { "epoch": 15.82, "learning_rate": 9.448495736127322e-05, "loss": 0.1251, "step": 66040 }, { "epoch": 15.82, "learning_rate": 9.4483318437667e-05, "loss": 0.126, "step": 66050 }, { "epoch": 15.83, "learning_rate": 9.448167928479339e-05, "loss": 0.1385, "step": 66060 }, { "epoch": 15.83, "learning_rate": 9.448003990266084e-05, "loss": 0.1012, "step": 66070 }, { "epoch": 15.83, "learning_rate": 9.447840029127777e-05, "loss": 0.1507, "step": 66080 }, { "epoch": 15.83, "learning_rate": 9.447676045065268e-05, "loss": 0.1425, "step": 66090 }, { "epoch": 15.84, "learning_rate": 9.447512038079398e-05, "loss": 0.1148, "step": 66100 }, { "epoch": 15.84, "learning_rate": 9.447348008171013e-05, "loss": 0.1103, "step": 66110 }, { "epoch": 15.84, "learning_rate": 9.447183955340962e-05, "loss": 0.0875, "step": 66120 }, { "epoch": 15.84, "learning_rate": 9.447019879590084e-05, "loss": 0.1079, "step": 66130 }, { "epoch": 15.84, "learning_rate": 9.44685578091923e-05, "loss": 0.1517, "step": 66140 }, { "epoch": 15.85, "learning_rate": 9.446691659329245e-05, "loss": 0.073, "step": 66150 }, { "epoch": 15.85, "learning_rate": 9.446527514820973e-05, "loss": 0.1196, "step": 66160 }, { "epoch": 15.85, "learning_rate": 9.446363347395262e-05, "loss": 0.1775, "step": 66170 }, { "epoch": 15.85, "learning_rate": 9.446199157052956e-05, "loss": 0.0772, "step": 66180 }, { "epoch": 15.86, "learning_rate": 9.446034943794904e-05, "loss": 0.1273, "step": 66190 }, { "epoch": 15.86, "learning_rate": 9.445870707621948e-05, "loss": 0.1621, "step": 66200 }, { "epoch": 15.86, "learning_rate": 9.44570644853494e-05, "loss": 0.1129, "step": 66210 }, { "epoch": 15.86, "learning_rate": 9.445542166534723e-05, "loss": 0.1015, "step": 66220 }, { "epoch": 15.86, "learning_rate": 9.445377861622145e-05, "loss": 0.129, "step": 66230 }, { "epoch": 15.87, "learning_rate": 9.44521353379805e-05, "loss": 0.0841, "step": 66240 }, { "epoch": 15.87, "learning_rate": 9.44504918306329e-05, "loss": 0.1661, "step": 66250 }, { "epoch": 15.87, "learning_rate": 9.444884809418708e-05, "loss": 0.1073, "step": 66260 }, { "epoch": 15.87, "learning_rate": 9.444720412865152e-05, "loss": 0.1154, "step": 66270 }, { "epoch": 15.88, "learning_rate": 9.44455599340347e-05, "loss": 0.0931, "step": 66280 }, { "epoch": 15.88, "learning_rate": 9.444391551034511e-05, "loss": 0.0995, "step": 66290 }, { "epoch": 15.88, "learning_rate": 9.444227085759119e-05, "loss": 0.1239, "step": 66300 }, { "epoch": 15.88, "learning_rate": 9.444062597578145e-05, "loss": 0.1051, "step": 66310 }, { "epoch": 15.89, "learning_rate": 9.443898086492434e-05, "loss": 0.0745, "step": 66320 }, { "epoch": 15.89, "learning_rate": 9.443733552502835e-05, "loss": 0.1374, "step": 66330 }, { "epoch": 15.89, "learning_rate": 9.443568995610198e-05, "loss": 0.1205, "step": 66340 }, { "epoch": 15.89, "learning_rate": 9.443404415815367e-05, "loss": 0.1347, "step": 66350 }, { "epoch": 15.89, "learning_rate": 9.443239813119192e-05, "loss": 0.1927, "step": 66360 }, { "epoch": 15.9, "learning_rate": 9.443075187522524e-05, "loss": 0.1478, "step": 66370 }, { "epoch": 15.9, "learning_rate": 9.442910539026208e-05, "loss": 0.1044, "step": 66380 }, { "epoch": 15.9, "learning_rate": 9.442745867631096e-05, "loss": 0.0904, "step": 66390 }, { "epoch": 15.9, "learning_rate": 9.442581173338032e-05, "loss": 0.0924, "step": 66400 }, { "epoch": 15.91, "learning_rate": 9.442416456147869e-05, "loss": 0.1354, "step": 66410 }, { "epoch": 15.91, "learning_rate": 9.442251716061454e-05, "loss": 0.0886, "step": 66420 }, { "epoch": 15.91, "learning_rate": 9.442086953079636e-05, "loss": 0.1753, "step": 66430 }, { "epoch": 15.91, "learning_rate": 9.441922167203265e-05, "loss": 0.0983, "step": 66440 }, { "epoch": 15.92, "learning_rate": 9.441757358433191e-05, "loss": 0.0814, "step": 66450 }, { "epoch": 15.92, "learning_rate": 9.441592526770262e-05, "loss": 0.1014, "step": 66460 }, { "epoch": 15.92, "learning_rate": 9.441427672215327e-05, "loss": 0.1048, "step": 66470 }, { "epoch": 15.92, "learning_rate": 9.441262794769238e-05, "loss": 0.1226, "step": 66480 }, { "epoch": 15.92, "learning_rate": 9.441097894432842e-05, "loss": 0.1193, "step": 66490 }, { "epoch": 15.93, "learning_rate": 9.440932971206991e-05, "loss": 0.1148, "step": 66500 }, { "epoch": 15.93, "learning_rate": 9.440768025092535e-05, "loss": 0.0864, "step": 66510 }, { "epoch": 15.93, "learning_rate": 9.440603056090323e-05, "loss": 0.1506, "step": 66520 }, { "epoch": 15.93, "learning_rate": 9.440438064201206e-05, "loss": 0.1402, "step": 66530 }, { "epoch": 15.94, "learning_rate": 9.440273049426033e-05, "loss": 0.098, "step": 66540 }, { "epoch": 15.94, "learning_rate": 9.440108011765657e-05, "loss": 0.1122, "step": 66550 }, { "epoch": 15.94, "learning_rate": 9.439942951220928e-05, "loss": 0.1037, "step": 66560 }, { "epoch": 15.94, "learning_rate": 9.439777867792695e-05, "loss": 0.0765, "step": 66570 }, { "epoch": 15.94, "learning_rate": 9.439612761481808e-05, "loss": 0.077, "step": 66580 }, { "epoch": 15.95, "learning_rate": 9.43944763228912e-05, "loss": 0.0972, "step": 66590 }, { "epoch": 15.95, "learning_rate": 9.439282480215484e-05, "loss": 0.1278, "step": 66600 }, { "epoch": 16.0, "learning_rate": 9.439117305261747e-05, "loss": 0.1044, "step": 66610 }, { "epoch": 16.0, "learning_rate": 9.438952107428763e-05, "loss": 0.0691, "step": 66620 }, { "epoch": 16.01, "learning_rate": 9.438786886717384e-05, "loss": 0.107, "step": 66630 }, { "epoch": 16.01, "learning_rate": 9.438621643128458e-05, "loss": 0.103, "step": 66640 }, { "epoch": 16.01, "learning_rate": 9.438456376662842e-05, "loss": 0.1452, "step": 66650 }, { "epoch": 16.01, "learning_rate": 9.43829108732138e-05, "loss": 0.1093, "step": 66660 }, { "epoch": 16.01, "learning_rate": 9.438125775104932e-05, "loss": 0.1503, "step": 66670 }, { "epoch": 16.02, "learning_rate": 9.437960440014346e-05, "loss": 0.1292, "step": 66680 }, { "epoch": 16.02, "learning_rate": 9.437795082050476e-05, "loss": 0.1195, "step": 66690 }, { "epoch": 16.02, "learning_rate": 9.437629701214171e-05, "loss": 0.1341, "step": 66700 }, { "epoch": 16.02, "learning_rate": 9.437464297506287e-05, "loss": 0.1223, "step": 66710 }, { "epoch": 16.03, "learning_rate": 9.437298870927675e-05, "loss": 0.1204, "step": 66720 }, { "epoch": 16.03, "learning_rate": 9.437133421479186e-05, "loss": 0.0731, "step": 66730 }, { "epoch": 16.03, "learning_rate": 9.436967949161674e-05, "loss": 0.1351, "step": 66740 }, { "epoch": 16.03, "learning_rate": 9.436802453975994e-05, "loss": 0.1064, "step": 66750 }, { "epoch": 16.03, "learning_rate": 9.436636935922997e-05, "loss": 0.0799, "step": 66760 }, { "epoch": 16.04, "learning_rate": 9.436471395003534e-05, "loss": 0.0684, "step": 66770 }, { "epoch": 16.04, "learning_rate": 9.436305831218462e-05, "loss": 0.0905, "step": 66780 }, { "epoch": 16.04, "learning_rate": 9.436140244568633e-05, "loss": 0.1602, "step": 66790 }, { "epoch": 16.04, "learning_rate": 9.4359746350549e-05, "loss": 0.1004, "step": 66800 }, { "epoch": 16.05, "learning_rate": 9.435809002678115e-05, "loss": 0.1442, "step": 66810 }, { "epoch": 16.05, "learning_rate": 9.435643347439135e-05, "loss": 0.1179, "step": 66820 }, { "epoch": 16.05, "learning_rate": 9.435477669338812e-05, "loss": 0.0737, "step": 66830 }, { "epoch": 16.05, "learning_rate": 9.435311968378e-05, "loss": 0.1427, "step": 66840 }, { "epoch": 16.06, "learning_rate": 9.435146244557552e-05, "loss": 0.1523, "step": 66850 }, { "epoch": 16.06, "learning_rate": 9.434980497878324e-05, "loss": 0.106, "step": 66860 }, { "epoch": 16.06, "learning_rate": 9.434814728341169e-05, "loss": 0.1147, "step": 66870 }, { "epoch": 16.06, "learning_rate": 9.434648935946942e-05, "loss": 0.1159, "step": 66880 }, { "epoch": 16.06, "learning_rate": 9.434483120696498e-05, "loss": 0.0856, "step": 66890 }, { "epoch": 16.07, "learning_rate": 9.43431728259069e-05, "loss": 0.1144, "step": 66900 }, { "epoch": 16.07, "learning_rate": 9.434151421630374e-05, "loss": 0.0996, "step": 66910 }, { "epoch": 16.07, "learning_rate": 9.433985537816404e-05, "loss": 0.0649, "step": 66920 }, { "epoch": 16.07, "learning_rate": 9.433819631149636e-05, "loss": 0.1479, "step": 66930 }, { "epoch": 16.08, "learning_rate": 9.433653701630924e-05, "loss": 0.1239, "step": 66940 }, { "epoch": 16.08, "learning_rate": 9.433487749261126e-05, "loss": 0.1133, "step": 66950 }, { "epoch": 16.08, "learning_rate": 9.433321774041093e-05, "loss": 0.1063, "step": 66960 }, { "epoch": 16.08, "learning_rate": 9.433155775971683e-05, "loss": 0.0641, "step": 66970 }, { "epoch": 16.09, "learning_rate": 9.43298975505375e-05, "loss": 0.0999, "step": 66980 }, { "epoch": 16.09, "learning_rate": 9.432823711288153e-05, "loss": 0.1132, "step": 66990 }, { "epoch": 16.09, "learning_rate": 9.432657644675744e-05, "loss": 0.1024, "step": 67000 }, { "epoch": 16.09, "learning_rate": 9.43249155521738e-05, "loss": 0.1403, "step": 67010 }, { "epoch": 16.09, "learning_rate": 9.432325442913919e-05, "loss": 0.129, "step": 67020 }, { "epoch": 16.1, "learning_rate": 9.432159307766216e-05, "loss": 0.0742, "step": 67030 }, { "epoch": 16.1, "learning_rate": 9.431993149775125e-05, "loss": 0.0674, "step": 67040 }, { "epoch": 16.1, "learning_rate": 9.431826968941503e-05, "loss": 0.1133, "step": 67050 }, { "epoch": 16.1, "learning_rate": 9.43166076526621e-05, "loss": 0.0952, "step": 67060 }, { "epoch": 16.11, "learning_rate": 9.431494538750101e-05, "loss": 0.1128, "step": 67070 }, { "epoch": 16.11, "learning_rate": 9.43132828939403e-05, "loss": 0.119, "step": 67080 }, { "epoch": 16.11, "learning_rate": 9.431162017198858e-05, "loss": 0.0968, "step": 67090 }, { "epoch": 16.11, "learning_rate": 9.430995722165439e-05, "loss": 0.0988, "step": 67100 }, { "epoch": 16.11, "learning_rate": 9.430829404294632e-05, "loss": 0.1036, "step": 67110 }, { "epoch": 16.12, "learning_rate": 9.430663063587291e-05, "loss": 0.0857, "step": 67120 }, { "epoch": 16.12, "learning_rate": 9.430496700044278e-05, "loss": 0.1179, "step": 67130 }, { "epoch": 16.12, "learning_rate": 9.430330313666447e-05, "loss": 0.0827, "step": 67140 }, { "epoch": 16.12, "learning_rate": 9.430163904454656e-05, "loss": 0.1007, "step": 67150 }, { "epoch": 16.13, "learning_rate": 9.429997472409763e-05, "loss": 0.1008, "step": 67160 }, { "epoch": 16.13, "learning_rate": 9.429831017532627e-05, "loss": 0.0827, "step": 67170 }, { "epoch": 16.13, "learning_rate": 9.429664539824103e-05, "loss": 0.0944, "step": 67180 }, { "epoch": 16.13, "learning_rate": 9.429498039285054e-05, "loss": 0.0669, "step": 67190 }, { "epoch": 16.14, "learning_rate": 9.429331515916333e-05, "loss": 0.117, "step": 67200 }, { "epoch": 16.14, "learning_rate": 9.429164969718801e-05, "loss": 0.1324, "step": 67210 }, { "epoch": 16.14, "learning_rate": 9.428998400693315e-05, "loss": 0.0896, "step": 67220 }, { "epoch": 16.14, "learning_rate": 9.428831808840734e-05, "loss": 0.0952, "step": 67230 }, { "epoch": 16.14, "learning_rate": 9.428665194161919e-05, "loss": 0.077, "step": 67240 }, { "epoch": 16.15, "learning_rate": 9.428498556657725e-05, "loss": 0.1387, "step": 67250 }, { "epoch": 16.15, "learning_rate": 9.428331896329013e-05, "loss": 0.0715, "step": 67260 }, { "epoch": 16.15, "learning_rate": 9.428165213176641e-05, "loss": 0.1208, "step": 67270 }, { "epoch": 16.15, "learning_rate": 9.427998507201468e-05, "loss": 0.118, "step": 67280 }, { "epoch": 16.16, "learning_rate": 9.427831778404354e-05, "loss": 0.126, "step": 67290 }, { "epoch": 16.16, "learning_rate": 9.427665026786159e-05, "loss": 0.063, "step": 67300 }, { "epoch": 16.16, "learning_rate": 9.42749825234774e-05, "loss": 0.0762, "step": 67310 }, { "epoch": 16.16, "learning_rate": 9.427331455089958e-05, "loss": 0.1157, "step": 67320 }, { "epoch": 16.16, "learning_rate": 9.427164635013674e-05, "loss": 0.1023, "step": 67330 }, { "epoch": 16.17, "learning_rate": 9.426997792119745e-05, "loss": 0.1003, "step": 67340 }, { "epoch": 16.17, "learning_rate": 9.426830926409034e-05, "loss": 0.1059, "step": 67350 }, { "epoch": 16.17, "learning_rate": 9.426664037882398e-05, "loss": 0.103, "step": 67360 }, { "epoch": 16.17, "learning_rate": 9.426497126540699e-05, "loss": 0.0771, "step": 67370 }, { "epoch": 16.18, "learning_rate": 9.426330192384796e-05, "loss": 0.0929, "step": 67380 }, { "epoch": 16.18, "learning_rate": 9.426163235415551e-05, "loss": 0.1416, "step": 67390 }, { "epoch": 16.18, "learning_rate": 9.425996255633824e-05, "loss": 0.109, "step": 67400 }, { "epoch": 16.18, "learning_rate": 9.425829253040476e-05, "loss": 0.154, "step": 67410 }, { "epoch": 16.19, "learning_rate": 9.425662227636364e-05, "loss": 0.1181, "step": 67420 }, { "epoch": 16.19, "learning_rate": 9.425495179422355e-05, "loss": 0.0651, "step": 67430 }, { "epoch": 16.19, "learning_rate": 9.425328108399306e-05, "loss": 0.112, "step": 67440 }, { "epoch": 16.19, "learning_rate": 9.42516101456808e-05, "loss": 0.0983, "step": 67450 }, { "epoch": 16.19, "learning_rate": 9.424993897929534e-05, "loss": 0.1282, "step": 67460 }, { "epoch": 16.2, "learning_rate": 9.424826758484535e-05, "loss": 0.1121, "step": 67470 }, { "epoch": 16.2, "learning_rate": 9.424659596233942e-05, "loss": 0.1404, "step": 67480 }, { "epoch": 16.2, "learning_rate": 9.424492411178616e-05, "loss": 0.0987, "step": 67490 }, { "epoch": 16.2, "learning_rate": 9.424325203319417e-05, "loss": 0.1265, "step": 67500 }, { "epoch": 16.21, "learning_rate": 9.424157972657212e-05, "loss": 0.0836, "step": 67510 }, { "epoch": 16.21, "learning_rate": 9.423990719192858e-05, "loss": 0.0949, "step": 67520 }, { "epoch": 16.21, "learning_rate": 9.423823442927219e-05, "loss": 0.1096, "step": 67530 }, { "epoch": 16.21, "learning_rate": 9.423656143861158e-05, "loss": 0.0681, "step": 67540 }, { "epoch": 16.22, "learning_rate": 9.423488821995537e-05, "loss": 0.1085, "step": 67550 }, { "epoch": 16.22, "learning_rate": 9.423321477331215e-05, "loss": 0.1142, "step": 67560 }, { "epoch": 16.22, "learning_rate": 9.423154109869059e-05, "loss": 0.0958, "step": 67570 }, { "epoch": 16.22, "learning_rate": 9.42298671960993e-05, "loss": 0.1091, "step": 67580 }, { "epoch": 16.22, "learning_rate": 9.422819306554689e-05, "loss": 0.106, "step": 67590 }, { "epoch": 16.23, "learning_rate": 9.4226518707042e-05, "loss": 0.1174, "step": 67600 }, { "epoch": 16.23, "learning_rate": 9.422484412059329e-05, "loss": 0.1092, "step": 67610 }, { "epoch": 16.23, "learning_rate": 9.422316930620933e-05, "loss": 0.1248, "step": 67620 }, { "epoch": 16.23, "learning_rate": 9.422149426389882e-05, "loss": 0.1331, "step": 67630 }, { "epoch": 16.24, "learning_rate": 9.421981899367034e-05, "loss": 0.0881, "step": 67640 }, { "epoch": 16.24, "learning_rate": 9.421814349553253e-05, "loss": 0.1705, "step": 67650 }, { "epoch": 16.24, "learning_rate": 9.421646776949407e-05, "loss": 0.0633, "step": 67660 }, { "epoch": 16.24, "learning_rate": 9.421479181556355e-05, "loss": 0.0992, "step": 67670 }, { "epoch": 16.24, "learning_rate": 9.421311563374962e-05, "loss": 0.1176, "step": 67680 }, { "epoch": 16.25, "learning_rate": 9.421143922406091e-05, "loss": 0.0714, "step": 67690 }, { "epoch": 16.25, "learning_rate": 9.420976258650609e-05, "loss": 0.0862, "step": 67700 }, { "epoch": 16.25, "learning_rate": 9.420808572109379e-05, "loss": 0.1166, "step": 67710 }, { "epoch": 16.25, "learning_rate": 9.420640862783263e-05, "loss": 0.1009, "step": 67720 }, { "epoch": 16.26, "learning_rate": 9.420473130673129e-05, "loss": 0.0972, "step": 67730 }, { "epoch": 16.26, "learning_rate": 9.420305375779838e-05, "loss": 0.1254, "step": 67740 }, { "epoch": 16.26, "learning_rate": 9.420137598104257e-05, "loss": 0.1283, "step": 67750 }, { "epoch": 16.26, "learning_rate": 9.419969797647249e-05, "loss": 0.0962, "step": 67760 }, { "epoch": 16.27, "learning_rate": 9.41980197440968e-05, "loss": 0.1353, "step": 67770 }, { "epoch": 16.27, "learning_rate": 9.419634128392414e-05, "loss": 0.1089, "step": 67780 }, { "epoch": 16.27, "learning_rate": 9.419466259596319e-05, "loss": 0.1372, "step": 67790 }, { "epoch": 16.27, "learning_rate": 9.419298368022256e-05, "loss": 0.1572, "step": 67800 }, { "epoch": 16.27, "learning_rate": 9.419130453671092e-05, "loss": 0.1212, "step": 67810 }, { "epoch": 16.28, "learning_rate": 9.418962516543694e-05, "loss": 0.1134, "step": 67820 }, { "epoch": 16.28, "learning_rate": 9.418794556640927e-05, "loss": 0.072, "step": 67830 }, { "epoch": 16.28, "learning_rate": 9.418626573963654e-05, "loss": 0.1297, "step": 67840 }, { "epoch": 16.28, "learning_rate": 9.418458568512742e-05, "loss": 0.0891, "step": 67850 }, { "epoch": 16.29, "learning_rate": 9.418290540289061e-05, "loss": 0.0855, "step": 67860 }, { "epoch": 16.29, "learning_rate": 9.41812248929347e-05, "loss": 0.0655, "step": 67870 }, { "epoch": 16.29, "learning_rate": 9.417954415526842e-05, "loss": 0.1134, "step": 67880 }, { "epoch": 16.29, "learning_rate": 9.417786318990038e-05, "loss": 0.0875, "step": 67890 }, { "epoch": 16.3, "learning_rate": 9.417618199683926e-05, "loss": 0.0912, "step": 67900 }, { "epoch": 16.3, "learning_rate": 9.417450057609374e-05, "loss": 0.1206, "step": 67910 }, { "epoch": 16.3, "learning_rate": 9.417281892767247e-05, "loss": 0.09, "step": 67920 }, { "epoch": 16.3, "learning_rate": 9.417113705158413e-05, "loss": 0.107, "step": 67930 }, { "epoch": 16.3, "learning_rate": 9.416945494783736e-05, "loss": 0.0767, "step": 67940 }, { "epoch": 16.31, "learning_rate": 9.416777261644087e-05, "loss": 0.1457, "step": 67950 }, { "epoch": 16.31, "learning_rate": 9.416609005740331e-05, "loss": 0.1251, "step": 67960 }, { "epoch": 16.31, "learning_rate": 9.416440727073335e-05, "loss": 0.0773, "step": 67970 }, { "epoch": 16.31, "learning_rate": 9.416272425643966e-05, "loss": 0.1073, "step": 67980 }, { "epoch": 16.32, "learning_rate": 9.416104101453092e-05, "loss": 0.1154, "step": 67990 }, { "epoch": 16.32, "learning_rate": 9.415935754501582e-05, "loss": 0.0744, "step": 68000 }, { "epoch": 16.32, "learning_rate": 9.4157673847903e-05, "loss": 0.0745, "step": 68010 }, { "epoch": 16.32, "learning_rate": 9.415598992320117e-05, "loss": 0.0823, "step": 68020 }, { "epoch": 16.32, "learning_rate": 9.4154305770919e-05, "loss": 0.1131, "step": 68030 }, { "epoch": 16.33, "learning_rate": 9.415262139106517e-05, "loss": 0.1358, "step": 68040 }, { "epoch": 16.33, "learning_rate": 9.415093678364836e-05, "loss": 0.1558, "step": 68050 }, { "epoch": 16.33, "learning_rate": 9.414925194867725e-05, "loss": 0.1028, "step": 68060 }, { "epoch": 16.33, "learning_rate": 9.414756688616054e-05, "loss": 0.0938, "step": 68070 }, { "epoch": 16.34, "learning_rate": 9.414588159610688e-05, "loss": 0.1109, "step": 68080 }, { "epoch": 16.34, "learning_rate": 9.414419607852498e-05, "loss": 0.0968, "step": 68090 }, { "epoch": 16.34, "learning_rate": 9.414251033342353e-05, "loss": 0.0895, "step": 68100 }, { "epoch": 16.34, "learning_rate": 9.414082436081122e-05, "loss": 0.089, "step": 68110 }, { "epoch": 16.35, "learning_rate": 9.413913816069672e-05, "loss": 0.1157, "step": 68120 }, { "epoch": 16.35, "learning_rate": 9.413745173308874e-05, "loss": 0.0853, "step": 68130 }, { "epoch": 16.35, "learning_rate": 9.413576507799596e-05, "loss": 0.1042, "step": 68140 }, { "epoch": 16.35, "learning_rate": 9.413407819542708e-05, "loss": 0.1354, "step": 68150 }, { "epoch": 16.35, "learning_rate": 9.41323910853908e-05, "loss": 0.058, "step": 68160 }, { "epoch": 16.36, "learning_rate": 9.41307037478958e-05, "loss": 0.1495, "step": 68170 }, { "epoch": 16.36, "learning_rate": 9.412901618295078e-05, "loss": 0.0758, "step": 68180 }, { "epoch": 16.36, "learning_rate": 9.412732839056444e-05, "loss": 0.0839, "step": 68190 }, { "epoch": 16.36, "learning_rate": 9.41256403707455e-05, "loss": 0.0759, "step": 68200 }, { "epoch": 16.37, "learning_rate": 9.412395212350262e-05, "loss": 0.1068, "step": 68210 }, { "epoch": 16.37, "learning_rate": 9.412226364884453e-05, "loss": 0.1137, "step": 68220 }, { "epoch": 16.37, "learning_rate": 9.412057494677992e-05, "loss": 0.0819, "step": 68230 }, { "epoch": 16.37, "learning_rate": 9.41188860173175e-05, "loss": 0.0861, "step": 68240 }, { "epoch": 16.38, "learning_rate": 9.411719686046598e-05, "loss": 0.1215, "step": 68250 }, { "epoch": 16.38, "learning_rate": 9.411550747623405e-05, "loss": 0.0863, "step": 68260 }, { "epoch": 16.38, "learning_rate": 9.411381786463044e-05, "loss": 0.1072, "step": 68270 }, { "epoch": 16.38, "learning_rate": 9.411212802566382e-05, "loss": 0.1091, "step": 68280 }, { "epoch": 16.38, "learning_rate": 9.411043795934295e-05, "loss": 0.1367, "step": 68290 }, { "epoch": 16.39, "learning_rate": 9.41087476656765e-05, "loss": 0.1028, "step": 68300 }, { "epoch": 16.39, "learning_rate": 9.41070571446732e-05, "loss": 0.0947, "step": 68310 }, { "epoch": 16.39, "learning_rate": 9.410536639634175e-05, "loss": 0.0765, "step": 68320 }, { "epoch": 16.39, "learning_rate": 9.410367542069088e-05, "loss": 0.0764, "step": 68330 }, { "epoch": 16.4, "learning_rate": 9.41019842177293e-05, "loss": 0.1545, "step": 68340 }, { "epoch": 16.4, "learning_rate": 9.410029278746572e-05, "loss": 0.0979, "step": 68350 }, { "epoch": 16.4, "learning_rate": 9.409860112990886e-05, "loss": 0.0979, "step": 68360 }, { "epoch": 16.4, "learning_rate": 9.409690924506745e-05, "loss": 0.0583, "step": 68370 }, { "epoch": 16.4, "learning_rate": 9.40952171329502e-05, "loss": 0.1211, "step": 68380 }, { "epoch": 16.41, "learning_rate": 9.409352479356582e-05, "loss": 0.1243, "step": 68390 }, { "epoch": 16.41, "learning_rate": 9.409183222692305e-05, "loss": 0.0912, "step": 68400 }, { "epoch": 16.41, "learning_rate": 9.409013943303062e-05, "loss": 0.1338, "step": 68410 }, { "epoch": 16.41, "learning_rate": 9.408844641189722e-05, "loss": 0.099, "step": 68420 }, { "epoch": 16.42, "learning_rate": 9.408675316353162e-05, "loss": 0.0742, "step": 68430 }, { "epoch": 16.42, "learning_rate": 9.408505968794253e-05, "loss": 0.0818, "step": 68440 }, { "epoch": 16.42, "learning_rate": 9.408336598513865e-05, "loss": 0.0694, "step": 68450 }, { "epoch": 16.42, "learning_rate": 9.408167205512875e-05, "loss": 0.0892, "step": 68460 }, { "epoch": 16.43, "learning_rate": 9.407997789792154e-05, "loss": 0.075, "step": 68470 }, { "epoch": 16.43, "learning_rate": 9.407828351352574e-05, "loss": 0.1033, "step": 68480 }, { "epoch": 16.43, "learning_rate": 9.407658890195013e-05, "loss": 0.1446, "step": 68490 }, { "epoch": 16.43, "learning_rate": 9.407489406320339e-05, "loss": 0.1172, "step": 68500 }, { "epoch": 16.43, "learning_rate": 9.407319899729427e-05, "loss": 0.0826, "step": 68510 }, { "epoch": 16.44, "learning_rate": 9.407150370423155e-05, "loss": 0.0827, "step": 68520 }, { "epoch": 16.44, "learning_rate": 9.40698081840239e-05, "loss": 0.094, "step": 68530 }, { "epoch": 16.44, "learning_rate": 9.40681124366801e-05, "loss": 0.1058, "step": 68540 }, { "epoch": 16.44, "learning_rate": 9.406641646220888e-05, "loss": 0.0814, "step": 68550 }, { "epoch": 16.45, "learning_rate": 9.406472026061898e-05, "loss": 0.0818, "step": 68560 }, { "epoch": 16.45, "learning_rate": 9.406302383191914e-05, "loss": 0.0531, "step": 68570 }, { "epoch": 16.45, "learning_rate": 9.406132717611811e-05, "loss": 0.094, "step": 68580 }, { "epoch": 16.45, "learning_rate": 9.405963029322464e-05, "loss": 0.1176, "step": 68590 }, { "epoch": 16.46, "learning_rate": 9.405793318324744e-05, "loss": 0.07, "step": 68600 }, { "epoch": 16.46, "learning_rate": 9.405623584619531e-05, "loss": 0.0941, "step": 68610 }, { "epoch": 16.46, "learning_rate": 9.405453828207697e-05, "loss": 0.0901, "step": 68620 }, { "epoch": 16.46, "learning_rate": 9.405284049090117e-05, "loss": 0.1109, "step": 68630 }, { "epoch": 16.46, "learning_rate": 9.405114247267665e-05, "loss": 0.1005, "step": 68640 }, { "epoch": 16.47, "learning_rate": 9.404944422741219e-05, "loss": 0.1252, "step": 68650 }, { "epoch": 16.47, "learning_rate": 9.404774575511652e-05, "loss": 0.07, "step": 68660 }, { "epoch": 16.47, "learning_rate": 9.404604705579839e-05, "loss": 0.0972, "step": 68670 }, { "epoch": 16.47, "learning_rate": 9.404434812946658e-05, "loss": 0.0841, "step": 68680 }, { "epoch": 16.48, "learning_rate": 9.404264897612983e-05, "loss": 0.0784, "step": 68690 }, { "epoch": 16.48, "learning_rate": 9.404094959579688e-05, "loss": 0.086, "step": 68700 }, { "epoch": 16.48, "learning_rate": 9.403924998847653e-05, "loss": 0.1376, "step": 68710 }, { "epoch": 16.48, "learning_rate": 9.403755015417751e-05, "loss": 0.0955, "step": 68720 }, { "epoch": 16.48, "learning_rate": 9.403585009290859e-05, "loss": 0.1206, "step": 68730 }, { "epoch": 16.49, "learning_rate": 9.403414980467852e-05, "loss": 0.0822, "step": 68740 }, { "epoch": 16.49, "learning_rate": 9.403244928949608e-05, "loss": 0.0776, "step": 68750 }, { "epoch": 16.49, "learning_rate": 9.403074854737004e-05, "loss": 0.1253, "step": 68760 }, { "epoch": 16.49, "learning_rate": 9.402904757830915e-05, "loss": 0.0991, "step": 68770 }, { "epoch": 16.5, "learning_rate": 9.402734638232217e-05, "loss": 0.078, "step": 68780 }, { "epoch": 16.5, "learning_rate": 9.402564495941789e-05, "loss": 0.0794, "step": 68790 }, { "epoch": 16.5, "learning_rate": 9.402394330960506e-05, "loss": 0.0984, "step": 68800 }, { "epoch": 16.5, "learning_rate": 9.402224143289245e-05, "loss": 0.0585, "step": 68810 }, { "epoch": 16.51, "learning_rate": 9.402053932928885e-05, "loss": 0.121, "step": 68820 }, { "epoch": 16.51, "learning_rate": 9.401883699880302e-05, "loss": 0.0839, "step": 68830 }, { "epoch": 16.51, "learning_rate": 9.401713444144374e-05, "loss": 0.0838, "step": 68840 }, { "epoch": 16.51, "learning_rate": 9.401543165721977e-05, "loss": 0.0911, "step": 68850 }, { "epoch": 16.51, "learning_rate": 9.401372864613992e-05, "loss": 0.1003, "step": 68860 }, { "epoch": 16.52, "learning_rate": 9.401202540821294e-05, "loss": 0.0974, "step": 68870 }, { "epoch": 16.52, "learning_rate": 9.40103219434476e-05, "loss": 0.127, "step": 68880 }, { "epoch": 16.52, "learning_rate": 9.400861825185269e-05, "loss": 0.0994, "step": 68890 }, { "epoch": 16.52, "learning_rate": 9.4006914333437e-05, "loss": 0.1107, "step": 68900 }, { "epoch": 16.53, "learning_rate": 9.400521018820932e-05, "loss": 0.1028, "step": 68910 }, { "epoch": 16.53, "learning_rate": 9.40035058161784e-05, "loss": 0.1322, "step": 68920 }, { "epoch": 16.53, "learning_rate": 9.400180121735305e-05, "loss": 0.1465, "step": 68930 }, { "epoch": 16.53, "learning_rate": 9.400009639174205e-05, "loss": 0.1408, "step": 68940 }, { "epoch": 16.54, "learning_rate": 9.399839133935417e-05, "loss": 0.1304, "step": 68950 }, { "epoch": 16.54, "learning_rate": 9.399668606019823e-05, "loss": 0.1246, "step": 68960 }, { "epoch": 16.54, "learning_rate": 9.3994980554283e-05, "loss": 0.1588, "step": 68970 }, { "epoch": 16.54, "learning_rate": 9.399327482161728e-05, "loss": 0.2279, "step": 68980 }, { "epoch": 16.54, "learning_rate": 9.399156886220984e-05, "loss": 0.1983, "step": 68990 }, { "epoch": 16.55, "learning_rate": 9.398986267606948e-05, "loss": 0.1971, "step": 69000 }, { "epoch": 16.55, "learning_rate": 9.398815626320503e-05, "loss": 0.1033, "step": 69010 }, { "epoch": 16.55, "learning_rate": 9.398644962362523e-05, "loss": 0.1166, "step": 69020 }, { "epoch": 16.55, "learning_rate": 9.398474275733891e-05, "loss": 0.1714, "step": 69030 }, { "epoch": 16.56, "learning_rate": 9.398303566435485e-05, "loss": 0.1625, "step": 69040 }, { "epoch": 16.56, "learning_rate": 9.398132834468187e-05, "loss": 0.1674, "step": 69050 }, { "epoch": 16.56, "learning_rate": 9.397962079832873e-05, "loss": 0.1808, "step": 69060 }, { "epoch": 16.56, "learning_rate": 9.397791302530429e-05, "loss": 0.1045, "step": 69070 }, { "epoch": 16.56, "learning_rate": 9.39762050256173e-05, "loss": 0.1783, "step": 69080 }, { "epoch": 16.57, "learning_rate": 9.39744967992766e-05, "loss": 0.1535, "step": 69090 }, { "epoch": 16.57, "learning_rate": 9.397278834629096e-05, "loss": 0.1414, "step": 69100 }, { "epoch": 16.57, "learning_rate": 9.397107966666919e-05, "loss": 0.1512, "step": 69110 }, { "epoch": 16.57, "learning_rate": 9.396937076042012e-05, "loss": 0.1142, "step": 69120 }, { "epoch": 16.58, "learning_rate": 9.396766162755255e-05, "loss": 0.1322, "step": 69130 }, { "epoch": 16.58, "learning_rate": 9.396595226807528e-05, "loss": 0.1428, "step": 69140 }, { "epoch": 16.58, "learning_rate": 9.396424268199712e-05, "loss": 0.108, "step": 69150 }, { "epoch": 16.58, "learning_rate": 9.396253286932689e-05, "loss": 0.1603, "step": 69160 }, { "epoch": 16.59, "learning_rate": 9.396082283007339e-05, "loss": 0.1036, "step": 69170 }, { "epoch": 16.59, "learning_rate": 9.395911256424545e-05, "loss": 0.1003, "step": 69180 }, { "epoch": 16.59, "learning_rate": 9.395740207185188e-05, "loss": 0.0914, "step": 69190 }, { "epoch": 16.59, "learning_rate": 9.39556913529015e-05, "loss": 0.1077, "step": 69200 }, { "epoch": 16.59, "learning_rate": 9.39539804074031e-05, "loss": 0.1755, "step": 69210 }, { "epoch": 16.6, "learning_rate": 9.395226923536553e-05, "loss": 0.1179, "step": 69220 }, { "epoch": 16.6, "learning_rate": 9.39505578367976e-05, "loss": 0.1513, "step": 69230 }, { "epoch": 16.6, "learning_rate": 9.394884621170812e-05, "loss": 0.1336, "step": 69240 }, { "epoch": 16.6, "learning_rate": 9.394713436010591e-05, "loss": 0.1248, "step": 69250 }, { "epoch": 16.61, "learning_rate": 9.394542228199981e-05, "loss": 0.1671, "step": 69260 }, { "epoch": 16.61, "learning_rate": 9.394370997739864e-05, "loss": 0.1623, "step": 69270 }, { "epoch": 16.61, "learning_rate": 9.394199744631123e-05, "loss": 0.1058, "step": 69280 }, { "epoch": 16.61, "learning_rate": 9.394028468874638e-05, "loss": 0.0894, "step": 69290 }, { "epoch": 16.62, "learning_rate": 9.393857170471294e-05, "loss": 0.0968, "step": 69300 }, { "epoch": 16.62, "learning_rate": 9.393685849421974e-05, "loss": 0.1063, "step": 69310 }, { "epoch": 16.62, "learning_rate": 9.39351450572756e-05, "loss": 0.1096, "step": 69320 }, { "epoch": 16.62, "learning_rate": 9.393343139388936e-05, "loss": 0.1222, "step": 69330 }, { "epoch": 16.62, "learning_rate": 9.393171750406984e-05, "loss": 0.1362, "step": 69340 }, { "epoch": 16.63, "learning_rate": 9.393000338782588e-05, "loss": 0.1407, "step": 69350 }, { "epoch": 16.63, "learning_rate": 9.392828904516633e-05, "loss": 0.1127, "step": 69360 }, { "epoch": 16.63, "learning_rate": 9.39265744761e-05, "loss": 0.1284, "step": 69370 }, { "epoch": 16.63, "learning_rate": 9.392485968063574e-05, "loss": 0.2367, "step": 69380 }, { "epoch": 16.64, "learning_rate": 9.392314465878238e-05, "loss": 0.102, "step": 69390 }, { "epoch": 16.64, "learning_rate": 9.392142941054878e-05, "loss": 0.1523, "step": 69400 }, { "epoch": 16.64, "learning_rate": 9.391971393594374e-05, "loss": 0.1578, "step": 69410 }, { "epoch": 16.64, "learning_rate": 9.391799823497614e-05, "loss": 0.1106, "step": 69420 }, { "epoch": 16.64, "learning_rate": 9.391628230765482e-05, "loss": 0.1153, "step": 69430 }, { "epoch": 16.65, "learning_rate": 9.391456615398861e-05, "loss": 0.1143, "step": 69440 }, { "epoch": 16.65, "learning_rate": 9.391284977398636e-05, "loss": 0.1324, "step": 69450 }, { "epoch": 16.65, "learning_rate": 9.39111331676569e-05, "loss": 0.1286, "step": 69460 }, { "epoch": 16.65, "learning_rate": 9.390941633500911e-05, "loss": 0.143, "step": 69470 }, { "epoch": 16.66, "learning_rate": 9.390769927605181e-05, "loss": 0.118, "step": 69480 }, { "epoch": 16.66, "learning_rate": 9.390598199079387e-05, "loss": 0.1125, "step": 69490 }, { "epoch": 16.66, "learning_rate": 9.390426447924412e-05, "loss": 0.135, "step": 69500 }, { "epoch": 16.66, "learning_rate": 9.390254674141143e-05, "loss": 0.1804, "step": 69510 }, { "epoch": 16.67, "learning_rate": 9.390082877730466e-05, "loss": 0.092, "step": 69520 }, { "epoch": 16.67, "learning_rate": 9.389911058693264e-05, "loss": 0.0759, "step": 69530 }, { "epoch": 16.67, "learning_rate": 9.389739217030425e-05, "loss": 0.1297, "step": 69540 }, { "epoch": 16.67, "learning_rate": 9.389567352742831e-05, "loss": 0.1876, "step": 69550 }, { "epoch": 16.67, "learning_rate": 9.389395465831371e-05, "loss": 0.1032, "step": 69560 }, { "epoch": 16.68, "learning_rate": 9.38922355629693e-05, "loss": 0.1332, "step": 69570 }, { "epoch": 16.68, "learning_rate": 9.389051624140395e-05, "loss": 0.1194, "step": 69580 }, { "epoch": 16.68, "learning_rate": 9.388879669362651e-05, "loss": 0.1111, "step": 69590 }, { "epoch": 16.68, "learning_rate": 9.388707691964584e-05, "loss": 0.1014, "step": 69600 }, { "epoch": 16.69, "learning_rate": 9.38853569194708e-05, "loss": 0.0845, "step": 69610 }, { "epoch": 16.69, "learning_rate": 9.388363669311028e-05, "loss": 0.095, "step": 69620 }, { "epoch": 16.69, "learning_rate": 9.388191624057314e-05, "loss": 0.1121, "step": 69630 }, { "epoch": 16.69, "learning_rate": 9.388019556186822e-05, "loss": 0.1668, "step": 69640 }, { "epoch": 16.7, "learning_rate": 9.387847465700439e-05, "loss": 0.1277, "step": 69650 }, { "epoch": 16.7, "learning_rate": 9.387675352599055e-05, "loss": 0.1192, "step": 69660 }, { "epoch": 16.7, "learning_rate": 9.387503216883557e-05, "loss": 0.1294, "step": 69670 }, { "epoch": 16.7, "learning_rate": 9.387331058554829e-05, "loss": 0.1146, "step": 69680 }, { "epoch": 16.7, "learning_rate": 9.38715887761376e-05, "loss": 0.1031, "step": 69690 }, { "epoch": 16.71, "learning_rate": 9.386986674061238e-05, "loss": 0.1092, "step": 69700 }, { "epoch": 16.71, "learning_rate": 9.38681444789815e-05, "loss": 0.0667, "step": 69710 }, { "epoch": 16.71, "learning_rate": 9.386642199125384e-05, "loss": 0.1499, "step": 69720 }, { "epoch": 16.71, "learning_rate": 9.386469927743826e-05, "loss": 0.138, "step": 69730 }, { "epoch": 16.72, "learning_rate": 9.386297633754368e-05, "loss": 0.0516, "step": 69740 }, { "epoch": 16.72, "learning_rate": 9.386125317157892e-05, "loss": 0.087, "step": 69750 }, { "epoch": 16.72, "learning_rate": 9.385952977955292e-05, "loss": 0.078, "step": 69760 }, { "epoch": 16.72, "learning_rate": 9.385780616147452e-05, "loss": 0.1009, "step": 69770 }, { "epoch": 16.72, "learning_rate": 9.385608231735263e-05, "loss": 0.132, "step": 69780 }, { "epoch": 16.73, "learning_rate": 9.385435824719612e-05, "loss": 0.0985, "step": 69790 }, { "epoch": 16.73, "learning_rate": 9.38526339510139e-05, "loss": 0.1351, "step": 69800 }, { "epoch": 16.73, "learning_rate": 9.385090942881482e-05, "loss": 0.0844, "step": 69810 }, { "epoch": 16.73, "learning_rate": 9.384918468060779e-05, "loss": 0.1356, "step": 69820 }, { "epoch": 16.74, "learning_rate": 9.38474597064017e-05, "loss": 0.1244, "step": 69830 }, { "epoch": 16.74, "learning_rate": 9.384573450620543e-05, "loss": 0.13, "step": 69840 }, { "epoch": 16.74, "learning_rate": 9.384400908002789e-05, "loss": 0.0909, "step": 69850 }, { "epoch": 16.74, "learning_rate": 9.384228342787793e-05, "loss": 0.085, "step": 69860 }, { "epoch": 16.75, "learning_rate": 9.38405575497645e-05, "loss": 0.1386, "step": 69870 }, { "epoch": 16.75, "learning_rate": 9.383883144569648e-05, "loss": 0.0823, "step": 69880 }, { "epoch": 16.75, "learning_rate": 9.383710511568274e-05, "loss": 0.0822, "step": 69890 }, { "epoch": 16.75, "learning_rate": 9.383537855973218e-05, "loss": 0.1026, "step": 69900 }, { "epoch": 16.75, "learning_rate": 9.383365177785373e-05, "loss": 0.1471, "step": 69910 }, { "epoch": 16.76, "learning_rate": 9.383192477005627e-05, "loss": 0.1679, "step": 69920 }, { "epoch": 16.76, "learning_rate": 9.38301975363487e-05, "loss": 0.1313, "step": 69930 }, { "epoch": 16.76, "learning_rate": 9.382847007673994e-05, "loss": 0.1046, "step": 69940 }, { "epoch": 16.76, "learning_rate": 9.382674239123885e-05, "loss": 0.0721, "step": 69950 }, { "epoch": 16.77, "learning_rate": 9.382501447985439e-05, "loss": 0.1081, "step": 69960 }, { "epoch": 16.77, "learning_rate": 9.382328634259543e-05, "loss": 0.1623, "step": 69970 }, { "epoch": 16.77, "learning_rate": 9.382155797947089e-05, "loss": 0.1069, "step": 69980 }, { "epoch": 16.77, "learning_rate": 9.381982939048967e-05, "loss": 0.1374, "step": 69990 }, { "epoch": 16.78, "learning_rate": 9.381810057566068e-05, "loss": 0.1384, "step": 70000 }, { "epoch": 16.78, "learning_rate": 9.381637153499283e-05, "loss": 0.0783, "step": 70010 }, { "epoch": 16.78, "learning_rate": 9.381464226849504e-05, "loss": 0.1419, "step": 70020 }, { "epoch": 16.78, "learning_rate": 9.381291277617623e-05, "loss": 0.0912, "step": 70030 }, { "epoch": 16.78, "learning_rate": 9.381118305804528e-05, "loss": 0.1063, "step": 70040 }, { "epoch": 16.79, "learning_rate": 9.380945311411113e-05, "loss": 0.1281, "step": 70050 }, { "epoch": 16.79, "learning_rate": 9.380772294438271e-05, "loss": 0.1231, "step": 70060 }, { "epoch": 16.79, "learning_rate": 9.38059925488689e-05, "loss": 0.0853, "step": 70070 }, { "epoch": 16.79, "learning_rate": 9.380426192757865e-05, "loss": 0.1097, "step": 70080 }, { "epoch": 16.8, "learning_rate": 9.380253108052086e-05, "loss": 0.1124, "step": 70090 }, { "epoch": 16.8, "learning_rate": 9.380080000770447e-05, "loss": 0.0988, "step": 70100 }, { "epoch": 16.8, "learning_rate": 9.379906870913838e-05, "loss": 0.0889, "step": 70110 }, { "epoch": 16.8, "learning_rate": 9.379733718483154e-05, "loss": 0.1193, "step": 70120 }, { "epoch": 16.8, "learning_rate": 9.379560543479284e-05, "loss": 0.121, "step": 70130 }, { "epoch": 16.81, "learning_rate": 9.379387345903123e-05, "loss": 0.0694, "step": 70140 }, { "epoch": 16.81, "learning_rate": 9.379214125755562e-05, "loss": 0.0973, "step": 70150 }, { "epoch": 16.81, "learning_rate": 9.379040883037497e-05, "loss": 0.0978, "step": 70160 }, { "epoch": 16.81, "learning_rate": 9.378867617749815e-05, "loss": 0.0956, "step": 70170 }, { "epoch": 16.82, "learning_rate": 9.378694329893416e-05, "loss": 0.0954, "step": 70180 }, { "epoch": 16.82, "learning_rate": 9.37852101946919e-05, "loss": 0.1133, "step": 70190 }, { "epoch": 16.82, "learning_rate": 9.378347686478028e-05, "loss": 0.0821, "step": 70200 }, { "epoch": 16.82, "learning_rate": 9.378174330920827e-05, "loss": 0.112, "step": 70210 }, { "epoch": 16.83, "learning_rate": 9.378000952798478e-05, "loss": 0.1696, "step": 70220 }, { "epoch": 16.83, "learning_rate": 9.377827552111876e-05, "loss": 0.1229, "step": 70230 }, { "epoch": 16.83, "learning_rate": 9.377654128861914e-05, "loss": 0.0992, "step": 70240 }, { "epoch": 16.83, "learning_rate": 9.377480683049487e-05, "loss": 0.1274, "step": 70250 }, { "epoch": 16.83, "learning_rate": 9.377307214675486e-05, "loss": 0.1459, "step": 70260 }, { "epoch": 16.84, "learning_rate": 9.377133723740809e-05, "loss": 0.1224, "step": 70270 }, { "epoch": 16.84, "learning_rate": 9.376960210246346e-05, "loss": 0.1046, "step": 70280 }, { "epoch": 16.84, "learning_rate": 9.376786674192995e-05, "loss": 0.1021, "step": 70290 }, { "epoch": 16.84, "learning_rate": 9.37661311558165e-05, "loss": 0.0715, "step": 70300 }, { "epoch": 16.85, "learning_rate": 9.376439534413202e-05, "loss": 0.096, "step": 70310 }, { "epoch": 16.85, "learning_rate": 9.376265930688548e-05, "loss": 0.0856, "step": 70320 }, { "epoch": 16.85, "learning_rate": 9.376092304408585e-05, "loss": 0.1006, "step": 70330 }, { "epoch": 16.85, "learning_rate": 9.375918655574205e-05, "loss": 0.1513, "step": 70340 }, { "epoch": 16.86, "learning_rate": 9.375744984186304e-05, "loss": 0.0941, "step": 70350 }, { "epoch": 16.86, "learning_rate": 9.375571290245774e-05, "loss": 0.0917, "step": 70360 }, { "epoch": 16.86, "learning_rate": 9.375397573753516e-05, "loss": 0.1153, "step": 70370 }, { "epoch": 16.86, "learning_rate": 9.37522383471042e-05, "loss": 0.081, "step": 70380 }, { "epoch": 16.86, "learning_rate": 9.375050073117387e-05, "loss": 0.0932, "step": 70390 }, { "epoch": 16.87, "learning_rate": 9.374876288975308e-05, "loss": 0.1107, "step": 70400 }, { "epoch": 16.87, "learning_rate": 9.374702482285079e-05, "loss": 0.1444, "step": 70410 }, { "epoch": 16.87, "learning_rate": 9.374528653047596e-05, "loss": 0.1467, "step": 70420 }, { "epoch": 16.87, "learning_rate": 9.374354801263759e-05, "loss": 0.1015, "step": 70430 }, { "epoch": 16.88, "learning_rate": 9.374180926934458e-05, "loss": 0.122, "step": 70440 }, { "epoch": 16.88, "learning_rate": 9.374007030060592e-05, "loss": 0.129, "step": 70450 }, { "epoch": 16.88, "learning_rate": 9.373833110643059e-05, "loss": 0.1334, "step": 70460 }, { "epoch": 16.88, "learning_rate": 9.373659168682753e-05, "loss": 0.1039, "step": 70470 }, { "epoch": 16.88, "learning_rate": 9.37348520418057e-05, "loss": 0.1298, "step": 70480 }, { "epoch": 16.89, "learning_rate": 9.373311217137408e-05, "loss": 0.0984, "step": 70490 }, { "epoch": 16.89, "learning_rate": 9.373137207554164e-05, "loss": 0.0951, "step": 70500 }, { "epoch": 16.89, "learning_rate": 9.372963175431735e-05, "loss": 0.0814, "step": 70510 }, { "epoch": 16.89, "learning_rate": 9.372789120771016e-05, "loss": 0.129, "step": 70520 }, { "epoch": 16.9, "learning_rate": 9.372615043572905e-05, "loss": 0.0854, "step": 70530 }, { "epoch": 16.9, "learning_rate": 9.3724409438383e-05, "loss": 0.0994, "step": 70540 }, { "epoch": 16.9, "learning_rate": 9.372266821568098e-05, "loss": 0.1147, "step": 70550 }, { "epoch": 16.9, "learning_rate": 9.372092676763197e-05, "loss": 0.0903, "step": 70560 }, { "epoch": 16.91, "learning_rate": 9.371918509424493e-05, "loss": 0.1013, "step": 70570 }, { "epoch": 16.91, "learning_rate": 9.371744319552886e-05, "loss": 0.0848, "step": 70580 }, { "epoch": 16.91, "learning_rate": 9.37157010714927e-05, "loss": 0.0816, "step": 70590 }, { "epoch": 16.91, "learning_rate": 9.371395872214546e-05, "loss": 0.1322, "step": 70600 }, { "epoch": 16.91, "learning_rate": 9.37122161474961e-05, "loss": 0.0881, "step": 70610 }, { "epoch": 16.92, "learning_rate": 9.371047334755363e-05, "loss": 0.0922, "step": 70620 }, { "epoch": 16.92, "learning_rate": 9.3708730322327e-05, "loss": 0.0904, "step": 70630 }, { "epoch": 16.92, "learning_rate": 9.370698707182524e-05, "loss": 0.0836, "step": 70640 }, { "epoch": 16.92, "learning_rate": 9.370524359605726e-05, "loss": 0.1006, "step": 70650 }, { "epoch": 16.93, "learning_rate": 9.370349989503211e-05, "loss": 0.0896, "step": 70660 }, { "epoch": 16.93, "learning_rate": 9.370175596875876e-05, "loss": 0.0707, "step": 70670 }, { "epoch": 16.93, "learning_rate": 9.37000118172462e-05, "loss": 0.0677, "step": 70680 }, { "epoch": 16.93, "learning_rate": 9.36982674405034e-05, "loss": 0.0869, "step": 70690 }, { "epoch": 16.94, "learning_rate": 9.369652283853937e-05, "loss": 0.0668, "step": 70700 }, { "epoch": 16.94, "learning_rate": 9.36947780113631e-05, "loss": 0.084, "step": 70710 }, { "epoch": 16.94, "learning_rate": 9.369303295898356e-05, "loss": 0.1034, "step": 70720 }, { "epoch": 16.94, "learning_rate": 9.369128768140978e-05, "loss": 0.105, "step": 70730 }, { "epoch": 16.94, "learning_rate": 9.368954217865073e-05, "loss": 0.1524, "step": 70740 }, { "epoch": 16.95, "learning_rate": 9.368779645071542e-05, "loss": 0.1134, "step": 70750 }, { "epoch": 16.95, "learning_rate": 9.368605049761284e-05, "loss": 0.0845, "step": 70760 }, { "epoch": 16.95, "learning_rate": 9.3684304319352e-05, "loss": 0.0882, "step": 70770 }, { "epoch": 17.0, "learning_rate": 9.368255791594187e-05, "loss": 0.1035, "step": 70780 }, { "epoch": 17.0, "learning_rate": 9.368081128739149e-05, "loss": 0.1362, "step": 70790 }, { "epoch": 17.01, "learning_rate": 9.367906443370984e-05, "loss": 0.0628, "step": 70800 }, { "epoch": 17.01, "learning_rate": 9.367731735490592e-05, "loss": 0.1587, "step": 70810 }, { "epoch": 17.01, "learning_rate": 9.367557005098875e-05, "loss": 0.0892, "step": 70820 }, { "epoch": 17.01, "learning_rate": 9.367382252196731e-05, "loss": 0.1332, "step": 70830 }, { "epoch": 17.02, "learning_rate": 9.367207476785065e-05, "loss": 0.1028, "step": 70840 }, { "epoch": 17.02, "learning_rate": 9.367032678864774e-05, "loss": 0.1112, "step": 70850 }, { "epoch": 17.02, "learning_rate": 9.366857858436759e-05, "loss": 0.1329, "step": 70860 }, { "epoch": 17.02, "learning_rate": 9.366683015501922e-05, "loss": 0.1083, "step": 70870 }, { "epoch": 17.02, "learning_rate": 9.366508150061166e-05, "loss": 0.097, "step": 70880 }, { "epoch": 17.03, "learning_rate": 9.36633326211539e-05, "loss": 0.0655, "step": 70890 }, { "epoch": 17.03, "learning_rate": 9.366158351665495e-05, "loss": 0.1079, "step": 70900 }, { "epoch": 17.03, "learning_rate": 9.365983418712383e-05, "loss": 0.1002, "step": 70910 }, { "epoch": 17.03, "learning_rate": 9.365808463256958e-05, "loss": 0.0971, "step": 70920 }, { "epoch": 17.04, "learning_rate": 9.365633485300117e-05, "loss": 0.0888, "step": 70930 }, { "epoch": 17.04, "learning_rate": 9.365458484842766e-05, "loss": 0.0934, "step": 70940 }, { "epoch": 17.04, "learning_rate": 9.365283461885805e-05, "loss": 0.0789, "step": 70950 }, { "epoch": 17.04, "learning_rate": 9.365108416430137e-05, "loss": 0.0948, "step": 70960 }, { "epoch": 17.05, "learning_rate": 9.364933348476664e-05, "loss": 0.1136, "step": 70970 }, { "epoch": 17.05, "learning_rate": 9.364758258026289e-05, "loss": 0.0539, "step": 70980 }, { "epoch": 17.05, "learning_rate": 9.364583145079911e-05, "loss": 0.1067, "step": 70990 }, { "epoch": 17.05, "learning_rate": 9.364408009638437e-05, "loss": 0.0886, "step": 71000 }, { "epoch": 17.05, "learning_rate": 9.364232851702766e-05, "loss": 0.0727, "step": 71010 }, { "epoch": 17.06, "learning_rate": 9.364057671273805e-05, "loss": 0.1177, "step": 71020 }, { "epoch": 17.06, "learning_rate": 9.363882468352451e-05, "loss": 0.1262, "step": 71030 }, { "epoch": 17.06, "learning_rate": 9.363707242939612e-05, "loss": 0.1097, "step": 71040 }, { "epoch": 17.06, "learning_rate": 9.363531995036189e-05, "loss": 0.1055, "step": 71050 }, { "epoch": 17.07, "learning_rate": 9.363356724643086e-05, "loss": 0.1228, "step": 71060 }, { "epoch": 17.07, "learning_rate": 9.363181431761205e-05, "loss": 0.0626, "step": 71070 }, { "epoch": 17.07, "learning_rate": 9.363006116391453e-05, "loss": 0.1089, "step": 71080 }, { "epoch": 17.07, "learning_rate": 9.362830778534728e-05, "loss": 0.1035, "step": 71090 }, { "epoch": 17.08, "learning_rate": 9.362655418191939e-05, "loss": 0.0849, "step": 71100 }, { "epoch": 17.08, "learning_rate": 9.362480035363986e-05, "loss": 0.0878, "step": 71110 }, { "epoch": 17.08, "learning_rate": 9.362304630051775e-05, "loss": 0.1337, "step": 71120 }, { "epoch": 17.08, "learning_rate": 9.362129202256209e-05, "loss": 0.1183, "step": 71130 }, { "epoch": 17.08, "learning_rate": 9.361953751978193e-05, "loss": 0.0768, "step": 71140 }, { "epoch": 17.09, "learning_rate": 9.361778279218632e-05, "loss": 0.0932, "step": 71150 }, { "epoch": 17.09, "learning_rate": 9.361602783978428e-05, "loss": 0.0785, "step": 71160 }, { "epoch": 17.09, "learning_rate": 9.361427266258487e-05, "loss": 0.0733, "step": 71170 }, { "epoch": 17.09, "learning_rate": 9.361251726059712e-05, "loss": 0.0788, "step": 71180 }, { "epoch": 17.1, "learning_rate": 9.361076163383011e-05, "loss": 0.1241, "step": 71190 }, { "epoch": 17.1, "learning_rate": 9.360900578229288e-05, "loss": 0.1717, "step": 71200 }, { "epoch": 17.1, "learning_rate": 9.360724970599443e-05, "loss": 0.0961, "step": 71210 }, { "epoch": 17.1, "learning_rate": 9.360549340494389e-05, "loss": 0.0729, "step": 71220 }, { "epoch": 17.1, "learning_rate": 9.360373687915025e-05, "loss": 0.0503, "step": 71230 }, { "epoch": 17.11, "learning_rate": 9.36019801286226e-05, "loss": 0.0894, "step": 71240 }, { "epoch": 17.11, "learning_rate": 9.360022315336998e-05, "loss": 0.089, "step": 71250 }, { "epoch": 17.11, "learning_rate": 9.359846595340143e-05, "loss": 0.1155, "step": 71260 }, { "epoch": 17.11, "learning_rate": 9.359670852872604e-05, "loss": 0.0888, "step": 71270 }, { "epoch": 17.12, "learning_rate": 9.359495087935284e-05, "loss": 0.105, "step": 71280 }, { "epoch": 17.12, "learning_rate": 9.35931930052909e-05, "loss": 0.0942, "step": 71290 }, { "epoch": 17.12, "learning_rate": 9.359143490654927e-05, "loss": 0.1283, "step": 71300 }, { "epoch": 17.12, "learning_rate": 9.358967658313704e-05, "loss": 0.0799, "step": 71310 }, { "epoch": 17.13, "learning_rate": 9.358791803506324e-05, "loss": 0.1135, "step": 71320 }, { "epoch": 17.13, "learning_rate": 9.358615926233694e-05, "loss": 0.0828, "step": 71330 }, { "epoch": 17.13, "learning_rate": 9.358440026496723e-05, "loss": 0.1237, "step": 71340 }, { "epoch": 17.13, "learning_rate": 9.358264104296314e-05, "loss": 0.0819, "step": 71350 }, { "epoch": 17.13, "learning_rate": 9.358088159633376e-05, "loss": 0.1021, "step": 71360 }, { "epoch": 17.14, "learning_rate": 9.357912192508814e-05, "loss": 0.0907, "step": 71370 }, { "epoch": 17.14, "learning_rate": 9.357736202923537e-05, "loss": 0.1229, "step": 71380 }, { "epoch": 17.14, "learning_rate": 9.357560190878452e-05, "loss": 0.0862, "step": 71390 }, { "epoch": 17.14, "learning_rate": 9.357384156374464e-05, "loss": 0.118, "step": 71400 }, { "epoch": 17.15, "learning_rate": 9.357208099412484e-05, "loss": 0.1329, "step": 71410 }, { "epoch": 17.15, "learning_rate": 9.357032019993415e-05, "loss": 0.0606, "step": 71420 }, { "epoch": 17.15, "learning_rate": 9.356855918118167e-05, "loss": 0.1004, "step": 71430 }, { "epoch": 17.15, "learning_rate": 9.356679793787646e-05, "loss": 0.1284, "step": 71440 }, { "epoch": 17.16, "learning_rate": 9.356503647002763e-05, "loss": 0.0833, "step": 71450 }, { "epoch": 17.16, "learning_rate": 9.356327477764423e-05, "loss": 0.0592, "step": 71460 }, { "epoch": 17.16, "learning_rate": 9.356151286073535e-05, "loss": 0.0923, "step": 71470 }, { "epoch": 17.16, "learning_rate": 9.355975071931006e-05, "loss": 0.1143, "step": 71480 }, { "epoch": 17.16, "learning_rate": 9.355798835337745e-05, "loss": 0.0815, "step": 71490 }, { "epoch": 17.17, "learning_rate": 9.355622576294661e-05, "loss": 0.1036, "step": 71500 }, { "epoch": 17.17, "learning_rate": 9.355446294802663e-05, "loss": 0.079, "step": 71510 }, { "epoch": 17.17, "learning_rate": 9.355269990862657e-05, "loss": 0.1116, "step": 71520 }, { "epoch": 17.17, "learning_rate": 9.355093664475553e-05, "loss": 0.0539, "step": 71530 }, { "epoch": 17.18, "learning_rate": 9.35491731564226e-05, "loss": 0.0897, "step": 71540 }, { "epoch": 17.18, "learning_rate": 9.354740944363686e-05, "loss": 0.0924, "step": 71550 }, { "epoch": 17.18, "learning_rate": 9.354564550640741e-05, "loss": 0.1294, "step": 71560 }, { "epoch": 17.18, "learning_rate": 9.354388134474336e-05, "loss": 0.1167, "step": 71570 }, { "epoch": 17.18, "learning_rate": 9.354211695865376e-05, "loss": 0.101, "step": 71580 }, { "epoch": 17.19, "learning_rate": 9.354035234814773e-05, "loss": 0.1126, "step": 71590 }, { "epoch": 17.19, "learning_rate": 9.353858751323436e-05, "loss": 0.0716, "step": 71600 }, { "epoch": 17.19, "learning_rate": 9.353682245392275e-05, "loss": 0.1112, "step": 71610 }, { "epoch": 17.19, "learning_rate": 9.3535057170222e-05, "loss": 0.1034, "step": 71620 }, { "epoch": 17.2, "learning_rate": 9.353329166214119e-05, "loss": 0.0496, "step": 71630 }, { "epoch": 17.2, "learning_rate": 9.353152592968943e-05, "loss": 0.0654, "step": 71640 }, { "epoch": 17.2, "learning_rate": 9.352975997287583e-05, "loss": 0.0779, "step": 71650 }, { "epoch": 17.2, "learning_rate": 9.352799379170946e-05, "loss": 0.1003, "step": 71660 }, { "epoch": 17.21, "learning_rate": 9.352622738619947e-05, "loss": 0.0713, "step": 71670 }, { "epoch": 17.21, "learning_rate": 9.352446075635495e-05, "loss": 0.0922, "step": 71680 }, { "epoch": 17.21, "learning_rate": 9.352269390218498e-05, "loss": 0.1079, "step": 71690 }, { "epoch": 17.21, "learning_rate": 9.352092682369868e-05, "loss": 0.0974, "step": 71700 }, { "epoch": 17.21, "learning_rate": 9.351915952090515e-05, "loss": 0.0894, "step": 71710 }, { "epoch": 17.22, "learning_rate": 9.351739199381353e-05, "loss": 0.0724, "step": 71720 }, { "epoch": 17.22, "learning_rate": 9.351562424243289e-05, "loss": 0.0681, "step": 71730 }, { "epoch": 17.22, "learning_rate": 9.351385626677237e-05, "loss": 0.0619, "step": 71740 }, { "epoch": 17.22, "learning_rate": 9.351208806684106e-05, "loss": 0.0872, "step": 71750 }, { "epoch": 17.23, "learning_rate": 9.351031964264809e-05, "loss": 0.1019, "step": 71760 }, { "epoch": 17.23, "learning_rate": 9.350855099420257e-05, "loss": 0.1072, "step": 71770 }, { "epoch": 17.23, "learning_rate": 9.350678212151363e-05, "loss": 0.1134, "step": 71780 }, { "epoch": 17.23, "learning_rate": 9.350501302459036e-05, "loss": 0.1147, "step": 71790 }, { "epoch": 17.24, "learning_rate": 9.350324370344188e-05, "loss": 0.0667, "step": 71800 }, { "epoch": 17.24, "learning_rate": 9.350147415807733e-05, "loss": 0.0893, "step": 71810 }, { "epoch": 17.24, "learning_rate": 9.349970438850581e-05, "loss": 0.1142, "step": 71820 }, { "epoch": 17.24, "learning_rate": 9.349793439473645e-05, "loss": 0.0862, "step": 71830 }, { "epoch": 17.24, "learning_rate": 9.349616417677837e-05, "loss": 0.0915, "step": 71840 }, { "epoch": 17.25, "learning_rate": 9.349439373464071e-05, "loss": 0.0821, "step": 71850 }, { "epoch": 17.25, "learning_rate": 9.349262306833257e-05, "loss": 0.1231, "step": 71860 }, { "epoch": 17.25, "learning_rate": 9.349085217786308e-05, "loss": 0.0859, "step": 71870 }, { "epoch": 17.25, "learning_rate": 9.348908106324139e-05, "loss": 0.053, "step": 71880 }, { "epoch": 17.26, "learning_rate": 9.348730972447661e-05, "loss": 0.0968, "step": 71890 }, { "epoch": 17.26, "learning_rate": 9.348553816157786e-05, "loss": 0.0863, "step": 71900 }, { "epoch": 17.26, "learning_rate": 9.34837663745543e-05, "loss": 0.0961, "step": 71910 }, { "epoch": 17.26, "learning_rate": 9.348199436341502e-05, "loss": 0.111, "step": 71920 }, { "epoch": 17.26, "learning_rate": 9.34802221281692e-05, "loss": 0.1071, "step": 71930 }, { "epoch": 17.27, "learning_rate": 9.347844966882595e-05, "loss": 0.072, "step": 71940 }, { "epoch": 17.27, "learning_rate": 9.34766769853944e-05, "loss": 0.078, "step": 71950 }, { "epoch": 17.27, "learning_rate": 9.34749040778837e-05, "loss": 0.0691, "step": 71960 }, { "epoch": 17.27, "learning_rate": 9.347313094630297e-05, "loss": 0.0698, "step": 71970 }, { "epoch": 17.28, "learning_rate": 9.347135759066137e-05, "loss": 0.0999, "step": 71980 }, { "epoch": 17.28, "learning_rate": 9.346958401096804e-05, "loss": 0.1044, "step": 71990 }, { "epoch": 17.28, "learning_rate": 9.346781020723209e-05, "loss": 0.1066, "step": 72000 }, { "epoch": 17.28, "learning_rate": 9.346603617946268e-05, "loss": 0.1299, "step": 72010 }, { "epoch": 17.29, "learning_rate": 9.346426192766898e-05, "loss": 0.0928, "step": 72020 }, { "epoch": 17.29, "learning_rate": 9.346248745186009e-05, "loss": 0.0716, "step": 72030 }, { "epoch": 17.29, "learning_rate": 9.346071275204519e-05, "loss": 0.0676, "step": 72040 }, { "epoch": 17.29, "learning_rate": 9.34589378282334e-05, "loss": 0.0975, "step": 72050 }, { "epoch": 17.29, "learning_rate": 9.34571626804339e-05, "loss": 0.068, "step": 72060 }, { "epoch": 17.3, "learning_rate": 9.34553873086558e-05, "loss": 0.0453, "step": 72070 }, { "epoch": 17.3, "learning_rate": 9.345361171290827e-05, "loss": 0.1291, "step": 72080 }, { "epoch": 17.3, "learning_rate": 9.345183589320048e-05, "loss": 0.0963, "step": 72090 }, { "epoch": 17.3, "learning_rate": 9.345005984954155e-05, "loss": 0.051, "step": 72100 }, { "epoch": 17.31, "learning_rate": 9.344828358194065e-05, "loss": 0.1269, "step": 72110 }, { "epoch": 17.31, "learning_rate": 9.344650709040694e-05, "loss": 0.0994, "step": 72120 }, { "epoch": 17.31, "learning_rate": 9.344473037494956e-05, "loss": 0.0743, "step": 72130 }, { "epoch": 17.31, "learning_rate": 9.344295343557769e-05, "loss": 0.1009, "step": 72140 }, { "epoch": 17.32, "learning_rate": 9.344117627230047e-05, "loss": 0.0678, "step": 72150 }, { "epoch": 17.32, "learning_rate": 9.343939888512705e-05, "loss": 0.0914, "step": 72160 }, { "epoch": 17.32, "learning_rate": 9.343762127406662e-05, "loss": 0.0889, "step": 72170 }, { "epoch": 17.32, "learning_rate": 9.343584343912833e-05, "loss": 0.0837, "step": 72180 }, { "epoch": 17.32, "learning_rate": 9.343406538032133e-05, "loss": 0.0857, "step": 72190 }, { "epoch": 17.33, "learning_rate": 9.34322870976548e-05, "loss": 0.1199, "step": 72200 }, { "epoch": 17.33, "learning_rate": 9.343050859113789e-05, "loss": 0.1218, "step": 72210 }, { "epoch": 17.33, "learning_rate": 9.342872986077978e-05, "loss": 0.0889, "step": 72220 }, { "epoch": 17.33, "learning_rate": 9.342695090658964e-05, "loss": 0.0985, "step": 72230 }, { "epoch": 17.34, "learning_rate": 9.342517172857664e-05, "loss": 0.0835, "step": 72240 }, { "epoch": 17.34, "learning_rate": 9.342339232674992e-05, "loss": 0.0936, "step": 72250 }, { "epoch": 17.34, "learning_rate": 9.34216127011187e-05, "loss": 0.1089, "step": 72260 }, { "epoch": 17.34, "learning_rate": 9.341983285169209e-05, "loss": 0.0732, "step": 72270 }, { "epoch": 17.34, "learning_rate": 9.341805277847932e-05, "loss": 0.1074, "step": 72280 }, { "epoch": 17.35, "learning_rate": 9.341627248148954e-05, "loss": 0.0762, "step": 72290 }, { "epoch": 17.35, "learning_rate": 9.341449196073191e-05, "loss": 0.082, "step": 72300 }, { "epoch": 17.35, "learning_rate": 9.341271121621566e-05, "loss": 0.0973, "step": 72310 }, { "epoch": 17.35, "learning_rate": 9.341093024794991e-05, "loss": 0.0683, "step": 72320 }, { "epoch": 17.36, "learning_rate": 9.340914905594387e-05, "loss": 0.1007, "step": 72330 }, { "epoch": 17.36, "learning_rate": 9.340736764020673e-05, "loss": 0.0934, "step": 72340 }, { "epoch": 17.36, "learning_rate": 9.340558600074762e-05, "loss": 0.1149, "step": 72350 }, { "epoch": 17.36, "learning_rate": 9.340380413757578e-05, "loss": 0.1132, "step": 72360 }, { "epoch": 17.37, "learning_rate": 9.340202205070036e-05, "loss": 0.0819, "step": 72370 }, { "epoch": 17.37, "learning_rate": 9.340023974013057e-05, "loss": 0.0667, "step": 72380 }, { "epoch": 17.37, "learning_rate": 9.339845720587557e-05, "loss": 0.0694, "step": 72390 }, { "epoch": 17.37, "learning_rate": 9.339667444794455e-05, "loss": 0.1106, "step": 72400 }, { "epoch": 17.37, "learning_rate": 9.339489146634673e-05, "loss": 0.0725, "step": 72410 }, { "epoch": 17.38, "learning_rate": 9.339310826109126e-05, "loss": 0.1076, "step": 72420 }, { "epoch": 17.38, "learning_rate": 9.339132483218735e-05, "loss": 0.0885, "step": 72430 }, { "epoch": 17.38, "learning_rate": 9.338954117964419e-05, "loss": 0.1004, "step": 72440 }, { "epoch": 17.38, "learning_rate": 9.338775730347098e-05, "loss": 0.0906, "step": 72450 }, { "epoch": 17.39, "learning_rate": 9.33859732036769e-05, "loss": 0.0817, "step": 72460 }, { "epoch": 17.39, "learning_rate": 9.338418888027114e-05, "loss": 0.0896, "step": 72470 }, { "epoch": 17.39, "learning_rate": 9.338240433326292e-05, "loss": 0.1225, "step": 72480 }, { "epoch": 17.39, "learning_rate": 9.338061956266142e-05, "loss": 0.1282, "step": 72490 }, { "epoch": 17.4, "learning_rate": 9.337883456847585e-05, "loss": 0.0765, "step": 72500 }, { "epoch": 17.4, "learning_rate": 9.33770493507154e-05, "loss": 0.1117, "step": 72510 }, { "epoch": 17.4, "learning_rate": 9.337526390938929e-05, "loss": 0.0998, "step": 72520 }, { "epoch": 17.4, "learning_rate": 9.337347824450669e-05, "loss": 0.0564, "step": 72530 }, { "epoch": 17.4, "learning_rate": 9.337169235607682e-05, "loss": 0.0406, "step": 72540 }, { "epoch": 17.41, "learning_rate": 9.336990624410888e-05, "loss": 0.066, "step": 72550 }, { "epoch": 17.41, "learning_rate": 9.336811990861211e-05, "loss": 0.0573, "step": 72560 }, { "epoch": 17.41, "learning_rate": 9.336633334959566e-05, "loss": 0.072, "step": 72570 }, { "epoch": 17.41, "learning_rate": 9.336454656706877e-05, "loss": 0.1054, "step": 72580 }, { "epoch": 17.42, "learning_rate": 9.336275956104066e-05, "loss": 0.0562, "step": 72590 }, { "epoch": 17.42, "learning_rate": 9.33609723315205e-05, "loss": 0.0666, "step": 72600 }, { "epoch": 17.42, "learning_rate": 9.335918487851755e-05, "loss": 0.0928, "step": 72610 }, { "epoch": 17.42, "learning_rate": 9.335739720204099e-05, "loss": 0.0551, "step": 72620 }, { "epoch": 17.42, "learning_rate": 9.335560930210003e-05, "loss": 0.0822, "step": 72630 }, { "epoch": 17.43, "learning_rate": 9.335382117870392e-05, "loss": 0.0851, "step": 72640 }, { "epoch": 17.43, "learning_rate": 9.335203283186182e-05, "loss": 0.0677, "step": 72650 }, { "epoch": 17.43, "learning_rate": 9.335024426158301e-05, "loss": 0.1044, "step": 72660 }, { "epoch": 17.43, "learning_rate": 9.334845546787667e-05, "loss": 0.0775, "step": 72670 }, { "epoch": 17.44, "learning_rate": 9.334666645075203e-05, "loss": 0.0792, "step": 72680 }, { "epoch": 17.44, "learning_rate": 9.33448772102183e-05, "loss": 0.0794, "step": 72690 }, { "epoch": 17.44, "learning_rate": 9.334308774628473e-05, "loss": 0.0854, "step": 72700 }, { "epoch": 17.44, "learning_rate": 9.33412980589605e-05, "loss": 0.0803, "step": 72710 }, { "epoch": 17.45, "learning_rate": 9.333950814825487e-05, "loss": 0.0765, "step": 72720 }, { "epoch": 17.45, "learning_rate": 9.333771801417705e-05, "loss": 0.0953, "step": 72730 }, { "epoch": 17.45, "learning_rate": 9.333592765673627e-05, "loss": 0.0788, "step": 72740 }, { "epoch": 17.45, "learning_rate": 9.333413707594177e-05, "loss": 0.066, "step": 72750 }, { "epoch": 17.45, "learning_rate": 9.333234627180274e-05, "loss": 0.1053, "step": 72760 }, { "epoch": 17.46, "learning_rate": 9.333055524432845e-05, "loss": 0.0735, "step": 72770 }, { "epoch": 17.46, "learning_rate": 9.332876399352812e-05, "loss": 0.0815, "step": 72780 }, { "epoch": 17.46, "learning_rate": 9.332697251941097e-05, "loss": 0.0721, "step": 72790 }, { "epoch": 17.46, "learning_rate": 9.332518082198624e-05, "loss": 0.0707, "step": 72800 }, { "epoch": 17.47, "learning_rate": 9.332338890126318e-05, "loss": 0.0609, "step": 72810 }, { "epoch": 17.47, "learning_rate": 9.332159675725098e-05, "loss": 0.0855, "step": 72820 }, { "epoch": 17.47, "learning_rate": 9.331980438995893e-05, "loss": 0.044, "step": 72830 }, { "epoch": 17.47, "learning_rate": 9.331801179939625e-05, "loss": 0.0955, "step": 72840 }, { "epoch": 17.48, "learning_rate": 9.331621898557217e-05, "loss": 0.0847, "step": 72850 }, { "epoch": 17.48, "learning_rate": 9.331442594849594e-05, "loss": 0.092, "step": 72860 }, { "epoch": 17.48, "learning_rate": 9.33126326881768e-05, "loss": 0.0987, "step": 72870 }, { "epoch": 17.48, "learning_rate": 9.331083920462398e-05, "loss": 0.112, "step": 72880 }, { "epoch": 17.48, "learning_rate": 9.330904549784673e-05, "loss": 0.0834, "step": 72890 }, { "epoch": 17.49, "learning_rate": 9.33072515678543e-05, "loss": 0.1161, "step": 72900 }, { "epoch": 17.49, "learning_rate": 9.330545741465593e-05, "loss": 0.0565, "step": 72910 }, { "epoch": 17.49, "learning_rate": 9.330366303826088e-05, "loss": 0.1034, "step": 72920 }, { "epoch": 17.49, "learning_rate": 9.330186843867838e-05, "loss": 0.0676, "step": 72930 }, { "epoch": 17.5, "learning_rate": 9.330007361591769e-05, "loss": 0.0794, "step": 72940 }, { "epoch": 17.5, "learning_rate": 9.329827856998807e-05, "loss": 0.0945, "step": 72950 }, { "epoch": 17.5, "learning_rate": 9.329648330089874e-05, "loss": 0.0832, "step": 72960 }, { "epoch": 17.5, "learning_rate": 9.329468780865899e-05, "loss": 0.0972, "step": 72970 }, { "epoch": 17.5, "learning_rate": 9.329289209327805e-05, "loss": 0.0822, "step": 72980 }, { "epoch": 17.51, "learning_rate": 9.329109615476519e-05, "loss": 0.0759, "step": 72990 }, { "epoch": 17.51, "learning_rate": 9.328929999312964e-05, "loss": 0.0703, "step": 73000 }, { "epoch": 17.51, "learning_rate": 9.32875036083807e-05, "loss": 0.0742, "step": 73010 }, { "epoch": 17.51, "learning_rate": 9.328570700052759e-05, "loss": 0.0793, "step": 73020 }, { "epoch": 17.52, "learning_rate": 9.328391016957958e-05, "loss": 0.0848, "step": 73030 }, { "epoch": 17.52, "learning_rate": 9.328211311554595e-05, "loss": 0.1047, "step": 73040 }, { "epoch": 17.52, "learning_rate": 9.328031583843593e-05, "loss": 0.0799, "step": 73050 }, { "epoch": 17.52, "learning_rate": 9.327851833825881e-05, "loss": 0.0875, "step": 73060 }, { "epoch": 17.53, "learning_rate": 9.327672061502385e-05, "loss": 0.0772, "step": 73070 }, { "epoch": 17.53, "learning_rate": 9.32749226687403e-05, "loss": 0.1337, "step": 73080 }, { "epoch": 17.53, "learning_rate": 9.327312449941743e-05, "loss": 0.1254, "step": 73090 }, { "epoch": 17.53, "learning_rate": 9.327132610706454e-05, "loss": 0.1175, "step": 73100 }, { "epoch": 17.53, "learning_rate": 9.326952749169086e-05, "loss": 0.1409, "step": 73110 }, { "epoch": 17.54, "learning_rate": 9.326772865330566e-05, "loss": 0.1694, "step": 73120 }, { "epoch": 17.54, "learning_rate": 9.326592959191825e-05, "loss": 0.1652, "step": 73130 }, { "epoch": 17.54, "learning_rate": 9.326413030753787e-05, "loss": 0.137, "step": 73140 }, { "epoch": 17.54, "learning_rate": 9.32623308001738e-05, "loss": 0.1616, "step": 73150 }, { "epoch": 17.55, "learning_rate": 9.32605310698353e-05, "loss": 0.1498, "step": 73160 }, { "epoch": 17.55, "learning_rate": 9.325873111653168e-05, "loss": 0.1709, "step": 73170 }, { "epoch": 17.55, "learning_rate": 9.325693094027219e-05, "loss": 0.152, "step": 73180 }, { "epoch": 17.55, "learning_rate": 9.325513054106612e-05, "loss": 0.1407, "step": 73190 }, { "epoch": 17.56, "learning_rate": 9.325332991892273e-05, "loss": 0.107, "step": 73200 }, { "epoch": 17.56, "learning_rate": 9.325152907385133e-05, "loss": 0.1304, "step": 73210 }, { "epoch": 17.56, "learning_rate": 9.324972800586119e-05, "loss": 0.1581, "step": 73220 }, { "epoch": 17.56, "learning_rate": 9.324792671496159e-05, "loss": 0.1399, "step": 73230 }, { "epoch": 17.56, "learning_rate": 9.324612520116181e-05, "loss": 0.1631, "step": 73240 }, { "epoch": 17.57, "learning_rate": 9.324432346447114e-05, "loss": 0.142, "step": 73250 }, { "epoch": 17.57, "learning_rate": 9.324252150489888e-05, "loss": 0.1265, "step": 73260 }, { "epoch": 17.57, "learning_rate": 9.324071932245427e-05, "loss": 0.1388, "step": 73270 }, { "epoch": 17.57, "learning_rate": 9.323891691714665e-05, "loss": 0.1518, "step": 73280 }, { "epoch": 17.58, "learning_rate": 9.32371142889853e-05, "loss": 0.1299, "step": 73290 }, { "epoch": 17.58, "learning_rate": 9.323531143797949e-05, "loss": 0.1237, "step": 73300 }, { "epoch": 17.58, "learning_rate": 9.323350836413853e-05, "loss": 0.1372, "step": 73310 }, { "epoch": 17.58, "learning_rate": 9.32317050674717e-05, "loss": 0.1016, "step": 73320 }, { "epoch": 17.58, "learning_rate": 9.322990154798829e-05, "loss": 0.1072, "step": 73330 }, { "epoch": 17.59, "learning_rate": 9.322809780569762e-05, "loss": 0.1085, "step": 73340 }, { "epoch": 17.59, "learning_rate": 9.322629384060898e-05, "loss": 0.1539, "step": 73350 }, { "epoch": 17.59, "learning_rate": 9.322448965273165e-05, "loss": 0.1107, "step": 73360 }, { "epoch": 17.59, "learning_rate": 9.322268524207494e-05, "loss": 0.1068, "step": 73370 }, { "epoch": 17.6, "learning_rate": 9.322088060864815e-05, "loss": 0.1188, "step": 73380 }, { "epoch": 17.6, "learning_rate": 9.321907575246058e-05, "loss": 0.1234, "step": 73390 }, { "epoch": 17.6, "learning_rate": 9.321727067352153e-05, "loss": 0.1197, "step": 73400 }, { "epoch": 17.6, "learning_rate": 9.321546537184031e-05, "loss": 0.1534, "step": 73410 }, { "epoch": 17.61, "learning_rate": 9.321365984742621e-05, "loss": 0.1093, "step": 73420 }, { "epoch": 17.61, "learning_rate": 9.321185410028857e-05, "loss": 0.0952, "step": 73430 }, { "epoch": 17.61, "learning_rate": 9.321004813043666e-05, "loss": 0.103, "step": 73440 }, { "epoch": 17.61, "learning_rate": 9.320824193787978e-05, "loss": 0.1212, "step": 73450 }, { "epoch": 17.61, "learning_rate": 9.32064355226273e-05, "loss": 0.129, "step": 73460 }, { "epoch": 17.62, "learning_rate": 9.320462888468845e-05, "loss": 0.1448, "step": 73470 }, { "epoch": 17.62, "learning_rate": 9.32028220240726e-05, "loss": 0.1065, "step": 73480 }, { "epoch": 17.62, "learning_rate": 9.320101494078905e-05, "loss": 0.1091, "step": 73490 }, { "epoch": 17.62, "learning_rate": 9.31992076348471e-05, "loss": 0.1138, "step": 73500 }, { "epoch": 17.63, "learning_rate": 9.319740010625606e-05, "loss": 0.1483, "step": 73510 }, { "epoch": 17.63, "learning_rate": 9.319559235502528e-05, "loss": 0.1478, "step": 73520 }, { "epoch": 17.63, "learning_rate": 9.319378438116405e-05, "loss": 0.1671, "step": 73530 }, { "epoch": 17.63, "learning_rate": 9.31919761846817e-05, "loss": 0.1788, "step": 73540 }, { "epoch": 17.64, "learning_rate": 9.319016776558754e-05, "loss": 0.0948, "step": 73550 }, { "epoch": 17.64, "learning_rate": 9.318835912389088e-05, "loss": 0.1043, "step": 73560 }, { "epoch": 17.64, "learning_rate": 9.318655025960107e-05, "loss": 0.0937, "step": 73570 }, { "epoch": 17.64, "learning_rate": 9.318474117272742e-05, "loss": 0.1054, "step": 73580 }, { "epoch": 17.64, "learning_rate": 9.318293186327924e-05, "loss": 0.1396, "step": 73590 }, { "epoch": 17.65, "learning_rate": 9.318112233126589e-05, "loss": 0.1454, "step": 73600 }, { "epoch": 17.65, "learning_rate": 9.317931257669666e-05, "loss": 0.0622, "step": 73610 }, { "epoch": 17.65, "learning_rate": 9.31775025995809e-05, "loss": 0.1262, "step": 73620 }, { "epoch": 17.65, "learning_rate": 9.317569239992792e-05, "loss": 0.1116, "step": 73630 }, { "epoch": 17.66, "learning_rate": 9.317388197774706e-05, "loss": 0.1265, "step": 73640 }, { "epoch": 17.66, "learning_rate": 9.317207133304765e-05, "loss": 0.1197, "step": 73650 }, { "epoch": 17.66, "learning_rate": 9.317026046583903e-05, "loss": 0.1298, "step": 73660 }, { "epoch": 17.66, "learning_rate": 9.316844937613053e-05, "loss": 0.1212, "step": 73670 }, { "epoch": 17.66, "learning_rate": 9.316663806393148e-05, "loss": 0.0992, "step": 73680 }, { "epoch": 17.67, "learning_rate": 9.31648265292512e-05, "loss": 0.1394, "step": 73690 }, { "epoch": 17.67, "learning_rate": 9.316301477209906e-05, "loss": 0.137, "step": 73700 }, { "epoch": 17.67, "learning_rate": 9.31612027924844e-05, "loss": 0.0693, "step": 73710 }, { "epoch": 17.67, "learning_rate": 9.315939059041649e-05, "loss": 0.0886, "step": 73720 }, { "epoch": 17.68, "learning_rate": 9.315757816590476e-05, "loss": 0.1123, "step": 73730 }, { "epoch": 17.68, "learning_rate": 9.315576551895851e-05, "loss": 0.0844, "step": 73740 }, { "epoch": 17.68, "learning_rate": 9.315395264958706e-05, "loss": 0.0642, "step": 73750 }, { "epoch": 17.68, "learning_rate": 9.31521395577998e-05, "loss": 0.1024, "step": 73760 }, { "epoch": 17.69, "learning_rate": 9.315032624360605e-05, "loss": 0.1066, "step": 73770 }, { "epoch": 17.69, "learning_rate": 9.314851270701515e-05, "loss": 0.1663, "step": 73780 }, { "epoch": 17.69, "learning_rate": 9.314669894803644e-05, "loss": 0.1064, "step": 73790 }, { "epoch": 17.69, "learning_rate": 9.31448849666793e-05, "loss": 0.1149, "step": 73800 }, { "epoch": 17.69, "learning_rate": 9.314307076295307e-05, "loss": 0.1653, "step": 73810 }, { "epoch": 17.7, "learning_rate": 9.314125633686708e-05, "loss": 0.0956, "step": 73820 }, { "epoch": 17.7, "learning_rate": 9.31394416884307e-05, "loss": 0.1287, "step": 73830 }, { "epoch": 17.7, "learning_rate": 9.313762681765328e-05, "loss": 0.0933, "step": 73840 }, { "epoch": 17.7, "learning_rate": 9.313581172454417e-05, "loss": 0.074, "step": 73850 }, { "epoch": 17.71, "learning_rate": 9.313399640911271e-05, "loss": 0.1101, "step": 73860 }, { "epoch": 17.71, "learning_rate": 9.313218087136829e-05, "loss": 0.163, "step": 73870 }, { "epoch": 17.71, "learning_rate": 9.313036511132024e-05, "loss": 0.1159, "step": 73880 }, { "epoch": 17.71, "learning_rate": 9.312854912897793e-05, "loss": 0.0957, "step": 73890 }, { "epoch": 17.72, "learning_rate": 9.312673292435073e-05, "loss": 0.0982, "step": 73900 }, { "epoch": 17.72, "learning_rate": 9.312491649744797e-05, "loss": 0.0926, "step": 73910 }, { "epoch": 17.72, "learning_rate": 9.312309984827903e-05, "loss": 0.1185, "step": 73920 }, { "epoch": 17.72, "learning_rate": 9.312128297685327e-05, "loss": 0.1151, "step": 73930 }, { "epoch": 17.72, "learning_rate": 9.311946588318008e-05, "loss": 0.1056, "step": 73940 }, { "epoch": 17.73, "learning_rate": 9.311764856726879e-05, "loss": 0.1003, "step": 73950 }, { "epoch": 17.73, "learning_rate": 9.311583102912878e-05, "loss": 0.095, "step": 73960 }, { "epoch": 17.73, "learning_rate": 9.31140132687694e-05, "loss": 0.1026, "step": 73970 }, { "epoch": 17.73, "learning_rate": 9.311219528620005e-05, "loss": 0.104, "step": 73980 }, { "epoch": 17.74, "learning_rate": 9.31103770814301e-05, "loss": 0.0811, "step": 73990 }, { "epoch": 17.74, "learning_rate": 9.310855865446888e-05, "loss": 0.1024, "step": 74000 }, { "epoch": 17.74, "learning_rate": 9.31067400053258e-05, "loss": 0.0917, "step": 74010 }, { "epoch": 17.74, "learning_rate": 9.310492113401021e-05, "loss": 0.1146, "step": 74020 }, { "epoch": 17.74, "learning_rate": 9.310310204053152e-05, "loss": 0.0891, "step": 74030 }, { "epoch": 17.75, "learning_rate": 9.310128272489906e-05, "loss": 0.0982, "step": 74040 }, { "epoch": 17.75, "learning_rate": 9.309946318712224e-05, "loss": 0.1194, "step": 74050 }, { "epoch": 17.75, "learning_rate": 9.309764342721042e-05, "loss": 0.0939, "step": 74060 }, { "epoch": 17.75, "learning_rate": 9.309582344517299e-05, "loss": 0.1006, "step": 74070 }, { "epoch": 17.76, "learning_rate": 9.309400324101932e-05, "loss": 0.0978, "step": 74080 }, { "epoch": 17.76, "learning_rate": 9.30921828147588e-05, "loss": 0.0955, "step": 74090 }, { "epoch": 17.76, "learning_rate": 9.309036216640081e-05, "loss": 0.1428, "step": 74100 }, { "epoch": 17.76, "learning_rate": 9.308854129595474e-05, "loss": 0.1056, "step": 74110 }, { "epoch": 17.77, "learning_rate": 9.308672020342997e-05, "loss": 0.0613, "step": 74120 }, { "epoch": 17.77, "learning_rate": 9.308489888883587e-05, "loss": 0.0995, "step": 74130 }, { "epoch": 17.77, "learning_rate": 9.308307735218185e-05, "loss": 0.1083, "step": 74140 }, { "epoch": 17.77, "learning_rate": 9.308125559347729e-05, "loss": 0.107, "step": 74150 }, { "epoch": 17.77, "learning_rate": 9.307943361273157e-05, "loss": 0.109, "step": 74160 }, { "epoch": 17.78, "learning_rate": 9.30776114099541e-05, "loss": 0.0824, "step": 74170 }, { "epoch": 17.78, "learning_rate": 9.307578898515425e-05, "loss": 0.1099, "step": 74180 }, { "epoch": 17.78, "learning_rate": 9.307396633834143e-05, "loss": 0.0811, "step": 74190 }, { "epoch": 17.78, "learning_rate": 9.307214346952502e-05, "loss": 0.1013, "step": 74200 }, { "epoch": 17.79, "learning_rate": 9.307032037871443e-05, "loss": 0.0956, "step": 74210 }, { "epoch": 17.79, "learning_rate": 9.306849706591905e-05, "loss": 0.0867, "step": 74220 }, { "epoch": 17.79, "learning_rate": 9.306667353114827e-05, "loss": 0.0606, "step": 74230 }, { "epoch": 17.79, "learning_rate": 9.30648497744115e-05, "loss": 0.0855, "step": 74240 }, { "epoch": 17.8, "learning_rate": 9.306302579571813e-05, "loss": 0.1087, "step": 74250 }, { "epoch": 17.8, "learning_rate": 9.306120159507757e-05, "loss": 0.1064, "step": 74260 }, { "epoch": 17.8, "learning_rate": 9.305937717249922e-05, "loss": 0.1047, "step": 74270 }, { "epoch": 17.8, "learning_rate": 9.305755252799246e-05, "loss": 0.0843, "step": 74280 }, { "epoch": 17.8, "learning_rate": 9.305572766156674e-05, "loss": 0.0717, "step": 74290 }, { "epoch": 17.81, "learning_rate": 9.305390257323144e-05, "loss": 0.0576, "step": 74300 }, { "epoch": 17.81, "learning_rate": 9.305207726299594e-05, "loss": 0.1242, "step": 74310 }, { "epoch": 17.81, "learning_rate": 9.30502517308697e-05, "loss": 0.1111, "step": 74320 }, { "epoch": 17.81, "learning_rate": 9.304842597686207e-05, "loss": 0.092, "step": 74330 }, { "epoch": 17.82, "learning_rate": 9.304660000098254e-05, "loss": 0.0771, "step": 74340 }, { "epoch": 17.82, "learning_rate": 9.304477380324044e-05, "loss": 0.0871, "step": 74350 }, { "epoch": 17.82, "learning_rate": 9.304294738364521e-05, "loss": 0.0697, "step": 74360 }, { "epoch": 17.82, "learning_rate": 9.304112074220629e-05, "loss": 0.0764, "step": 74370 }, { "epoch": 17.82, "learning_rate": 9.303929387893306e-05, "loss": 0.0988, "step": 74380 }, { "epoch": 17.83, "learning_rate": 9.303746679383496e-05, "loss": 0.0949, "step": 74390 }, { "epoch": 17.83, "learning_rate": 9.30356394869214e-05, "loss": 0.0924, "step": 74400 }, { "epoch": 17.83, "learning_rate": 9.303381195820178e-05, "loss": 0.0844, "step": 74410 }, { "epoch": 17.83, "learning_rate": 9.303198420768555e-05, "loss": 0.1065, "step": 74420 }, { "epoch": 17.84, "learning_rate": 9.30301562353821e-05, "loss": 0.099, "step": 74430 }, { "epoch": 17.84, "learning_rate": 9.302832804130087e-05, "loss": 0.0862, "step": 74440 }, { "epoch": 17.84, "learning_rate": 9.302649962545128e-05, "loss": 0.1143, "step": 74450 }, { "epoch": 17.84, "learning_rate": 9.302467098784276e-05, "loss": 0.0935, "step": 74460 }, { "epoch": 17.85, "learning_rate": 9.30228421284847e-05, "loss": 0.1277, "step": 74470 }, { "epoch": 17.85, "learning_rate": 9.302101304738658e-05, "loss": 0.092, "step": 74480 }, { "epoch": 17.85, "learning_rate": 9.301918374455778e-05, "loss": 0.087, "step": 74490 }, { "epoch": 17.85, "learning_rate": 9.301735422000774e-05, "loss": 0.0592, "step": 74500 }, { "epoch": 17.85, "learning_rate": 9.301552447374592e-05, "loss": 0.0564, "step": 74510 }, { "epoch": 17.86, "learning_rate": 9.301369450578173e-05, "loss": 0.0958, "step": 74520 }, { "epoch": 17.86, "learning_rate": 9.301186431612458e-05, "loss": 0.1035, "step": 74530 }, { "epoch": 17.86, "learning_rate": 9.301003390478392e-05, "loss": 0.09, "step": 74540 }, { "epoch": 17.86, "learning_rate": 9.30082032717692e-05, "loss": 0.117, "step": 74550 }, { "epoch": 17.87, "learning_rate": 9.300637241708983e-05, "loss": 0.087, "step": 74560 }, { "epoch": 17.87, "learning_rate": 9.300454134075527e-05, "loss": 0.0817, "step": 74570 }, { "epoch": 17.87, "learning_rate": 9.300271004277493e-05, "loss": 0.0773, "step": 74580 }, { "epoch": 17.87, "learning_rate": 9.300087852315826e-05, "loss": 0.0809, "step": 74590 }, { "epoch": 17.88, "learning_rate": 9.299904678191472e-05, "loss": 0.0813, "step": 74600 }, { "epoch": 17.88, "learning_rate": 9.299721481905373e-05, "loss": 0.0938, "step": 74610 }, { "epoch": 17.88, "learning_rate": 9.299538263458473e-05, "loss": 0.0585, "step": 74620 }, { "epoch": 17.88, "learning_rate": 9.299355022851716e-05, "loss": 0.1089, "step": 74630 }, { "epoch": 17.88, "learning_rate": 9.299171760086049e-05, "loss": 0.0955, "step": 74640 }, { "epoch": 17.89, "learning_rate": 9.298988475162414e-05, "loss": 0.0962, "step": 74650 }, { "epoch": 17.89, "learning_rate": 9.298805168081757e-05, "loss": 0.0669, "step": 74660 }, { "epoch": 17.89, "learning_rate": 9.298621838845021e-05, "loss": 0.0949, "step": 74670 }, { "epoch": 17.89, "learning_rate": 9.298438487453154e-05, "loss": 0.0944, "step": 74680 }, { "epoch": 17.9, "learning_rate": 9.298255113907097e-05, "loss": 0.1002, "step": 74690 }, { "epoch": 17.9, "learning_rate": 9.298071718207799e-05, "loss": 0.098, "step": 74700 }, { "epoch": 17.9, "learning_rate": 9.297888300356201e-05, "loss": 0.0924, "step": 74710 }, { "epoch": 17.9, "learning_rate": 9.297704860353254e-05, "loss": 0.0788, "step": 74720 }, { "epoch": 17.9, "learning_rate": 9.297521398199897e-05, "loss": 0.0607, "step": 74730 }, { "epoch": 17.91, "learning_rate": 9.297337913897082e-05, "loss": 0.105, "step": 74740 }, { "epoch": 17.91, "learning_rate": 9.29715440744575e-05, "loss": 0.0786, "step": 74750 }, { "epoch": 17.91, "learning_rate": 9.296970878846847e-05, "loss": 0.0837, "step": 74760 }, { "epoch": 17.91, "learning_rate": 9.296787328101322e-05, "loss": 0.0718, "step": 74770 }, { "epoch": 17.92, "learning_rate": 9.296603755210118e-05, "loss": 0.0924, "step": 74780 }, { "epoch": 17.92, "learning_rate": 9.296420160174182e-05, "loss": 0.0934, "step": 74790 }, { "epoch": 17.92, "learning_rate": 9.296236542994463e-05, "loss": 0.1165, "step": 74800 }, { "epoch": 17.92, "learning_rate": 9.296052903671902e-05, "loss": 0.101, "step": 74810 }, { "epoch": 17.93, "learning_rate": 9.295869242207451e-05, "loss": 0.0929, "step": 74820 }, { "epoch": 17.93, "learning_rate": 9.295685558602053e-05, "loss": 0.0508, "step": 74830 }, { "epoch": 17.93, "learning_rate": 9.295501852856655e-05, "loss": 0.0855, "step": 74840 }, { "epoch": 17.93, "learning_rate": 9.295318124972205e-05, "loss": 0.072, "step": 74850 }, { "epoch": 17.93, "learning_rate": 9.29513437494965e-05, "loss": 0.0689, "step": 74860 }, { "epoch": 17.94, "learning_rate": 9.294950602789936e-05, "loss": 0.1089, "step": 74870 }, { "epoch": 17.94, "learning_rate": 9.294766808494012e-05, "loss": 0.1001, "step": 74880 }, { "epoch": 17.94, "learning_rate": 9.294582992062822e-05, "loss": 0.1007, "step": 74890 }, { "epoch": 17.94, "learning_rate": 9.294399153497315e-05, "loss": 0.1453, "step": 74900 }, { "epoch": 17.95, "learning_rate": 9.294215292798441e-05, "loss": 0.0957, "step": 74910 }, { "epoch": 17.95, "learning_rate": 9.294031409967143e-05, "loss": 0.0963, "step": 74920 }, { "epoch": 17.95, "learning_rate": 9.293847505004373e-05, "loss": 0.096, "step": 74930 }, { "epoch": 18.0, "learning_rate": 9.293663577911077e-05, "loss": 0.1167, "step": 74940 }, { "epoch": 18.0, "learning_rate": 9.293479628688201e-05, "loss": 0.0706, "step": 74950 }, { "epoch": 18.01, "learning_rate": 9.293295657336698e-05, "loss": 0.0856, "step": 74960 }, { "epoch": 18.01, "learning_rate": 9.293111663857514e-05, "loss": 0.101, "step": 74970 }, { "epoch": 18.01, "learning_rate": 9.292927648251594e-05, "loss": 0.1018, "step": 74980 }, { "epoch": 18.01, "learning_rate": 9.29274361051989e-05, "loss": 0.0723, "step": 74990 }, { "epoch": 18.02, "learning_rate": 9.292559550663349e-05, "loss": 0.1041, "step": 75000 }, { "epoch": 18.02, "learning_rate": 9.292375468682922e-05, "loss": 0.0923, "step": 75010 }, { "epoch": 18.02, "learning_rate": 9.292191364579552e-05, "loss": 0.0713, "step": 75020 }, { "epoch": 18.02, "learning_rate": 9.292007238354195e-05, "loss": 0.0986, "step": 75030 }, { "epoch": 18.02, "learning_rate": 9.291823090007797e-05, "loss": 0.1125, "step": 75040 }, { "epoch": 18.03, "learning_rate": 9.291638919541306e-05, "loss": 0.101, "step": 75050 }, { "epoch": 18.03, "learning_rate": 9.291454726955672e-05, "loss": 0.0932, "step": 75060 }, { "epoch": 18.03, "learning_rate": 9.291270512251845e-05, "loss": 0.1064, "step": 75070 }, { "epoch": 18.03, "learning_rate": 9.291086275430774e-05, "loss": 0.0933, "step": 75080 }, { "epoch": 18.04, "learning_rate": 9.290902016493407e-05, "loss": 0.0582, "step": 75090 }, { "epoch": 18.04, "learning_rate": 9.290717735440695e-05, "loss": 0.0934, "step": 75100 }, { "epoch": 18.04, "learning_rate": 9.290533432273591e-05, "loss": 0.1052, "step": 75110 }, { "epoch": 18.04, "learning_rate": 9.29034910699304e-05, "loss": 0.0791, "step": 75120 }, { "epoch": 18.04, "learning_rate": 9.290164759599993e-05, "loss": 0.1147, "step": 75130 }, { "epoch": 18.05, "learning_rate": 9.289980390095402e-05, "loss": 0.0928, "step": 75140 }, { "epoch": 18.05, "learning_rate": 9.289795998480216e-05, "loss": 0.0917, "step": 75150 }, { "epoch": 18.05, "learning_rate": 9.289611584755385e-05, "loss": 0.088, "step": 75160 }, { "epoch": 18.05, "learning_rate": 9.289427148921861e-05, "loss": 0.0839, "step": 75170 }, { "epoch": 18.06, "learning_rate": 9.289242690980593e-05, "loss": 0.109, "step": 75180 }, { "epoch": 18.06, "learning_rate": 9.289058210932533e-05, "loss": 0.086, "step": 75190 }, { "epoch": 18.06, "learning_rate": 9.288873708778631e-05, "loss": 0.0798, "step": 75200 }, { "epoch": 18.06, "learning_rate": 9.288689184519836e-05, "loss": 0.0954, "step": 75210 }, { "epoch": 18.07, "learning_rate": 9.288504638157104e-05, "loss": 0.111, "step": 75220 }, { "epoch": 18.07, "learning_rate": 9.288320069691383e-05, "loss": 0.0582, "step": 75230 }, { "epoch": 18.07, "learning_rate": 9.288135479123623e-05, "loss": 0.0548, "step": 75240 }, { "epoch": 18.07, "learning_rate": 9.287950866454778e-05, "loss": 0.0732, "step": 75250 }, { "epoch": 18.07, "learning_rate": 9.287766231685797e-05, "loss": 0.0893, "step": 75260 }, { "epoch": 18.08, "learning_rate": 9.287581574817635e-05, "loss": 0.1071, "step": 75270 }, { "epoch": 18.08, "learning_rate": 9.287396895851239e-05, "loss": 0.0809, "step": 75280 }, { "epoch": 18.08, "learning_rate": 9.287212194787564e-05, "loss": 0.1065, "step": 75290 }, { "epoch": 18.08, "learning_rate": 9.287027471627563e-05, "loss": 0.078, "step": 75300 }, { "epoch": 18.09, "learning_rate": 9.286842726372187e-05, "loss": 0.0862, "step": 75310 }, { "epoch": 18.09, "learning_rate": 9.286657959022387e-05, "loss": 0.0897, "step": 75320 }, { "epoch": 18.09, "learning_rate": 9.286473169579117e-05, "loss": 0.0752, "step": 75330 }, { "epoch": 18.09, "learning_rate": 9.286288358043327e-05, "loss": 0.0744, "step": 75340 }, { "epoch": 18.1, "learning_rate": 9.286103524415971e-05, "loss": 0.0756, "step": 75350 }, { "epoch": 18.1, "learning_rate": 9.285918668698002e-05, "loss": 0.0642, "step": 75360 }, { "epoch": 18.1, "learning_rate": 9.285733790890372e-05, "loss": 0.045, "step": 75370 }, { "epoch": 18.1, "learning_rate": 9.285548890994034e-05, "loss": 0.1033, "step": 75380 }, { "epoch": 18.1, "learning_rate": 9.285363969009942e-05, "loss": 0.0897, "step": 75390 }, { "epoch": 18.11, "learning_rate": 9.285179024939048e-05, "loss": 0.1158, "step": 75400 }, { "epoch": 18.11, "learning_rate": 9.284994058782306e-05, "loss": 0.0942, "step": 75410 }, { "epoch": 18.11, "learning_rate": 9.28480907054067e-05, "loss": 0.0756, "step": 75420 }, { "epoch": 18.11, "learning_rate": 9.28462406021509e-05, "loss": 0.0825, "step": 75430 }, { "epoch": 18.12, "learning_rate": 9.284439027806522e-05, "loss": 0.1137, "step": 75440 }, { "epoch": 18.12, "learning_rate": 9.28425397331592e-05, "loss": 0.0973, "step": 75450 }, { "epoch": 18.12, "learning_rate": 9.284068896744237e-05, "loss": 0.0793, "step": 75460 }, { "epoch": 18.12, "learning_rate": 9.283883798092427e-05, "loss": 0.0712, "step": 75470 }, { "epoch": 18.12, "learning_rate": 9.283698677361444e-05, "loss": 0.0844, "step": 75480 }, { "epoch": 18.13, "learning_rate": 9.283513534552243e-05, "loss": 0.0595, "step": 75490 }, { "epoch": 18.13, "learning_rate": 9.283328369665777e-05, "loss": 0.0728, "step": 75500 }, { "epoch": 18.13, "learning_rate": 9.283143182703e-05, "loss": 0.1039, "step": 75510 }, { "epoch": 18.13, "learning_rate": 9.282957973664868e-05, "loss": 0.1019, "step": 75520 }, { "epoch": 18.14, "learning_rate": 9.282772742552335e-05, "loss": 0.0686, "step": 75530 }, { "epoch": 18.14, "learning_rate": 9.282587489366356e-05, "loss": 0.1008, "step": 75540 }, { "epoch": 18.14, "learning_rate": 9.282402214107884e-05, "loss": 0.0918, "step": 75550 }, { "epoch": 18.14, "learning_rate": 9.282216916777874e-05, "loss": 0.0959, "step": 75560 }, { "epoch": 18.15, "learning_rate": 9.282031597377286e-05, "loss": 0.0778, "step": 75570 }, { "epoch": 18.15, "learning_rate": 9.28184625590707e-05, "loss": 0.0762, "step": 75580 }, { "epoch": 18.15, "learning_rate": 9.281660892368181e-05, "loss": 0.0799, "step": 75590 }, { "epoch": 18.15, "learning_rate": 9.281475506761577e-05, "loss": 0.0877, "step": 75600 }, { "epoch": 18.15, "learning_rate": 9.281290099088211e-05, "loss": 0.0861, "step": 75610 }, { "epoch": 18.16, "learning_rate": 9.281104669349043e-05, "loss": 0.1002, "step": 75620 }, { "epoch": 18.16, "learning_rate": 9.280919217545023e-05, "loss": 0.0621, "step": 75630 }, { "epoch": 18.16, "learning_rate": 9.28073374367711e-05, "loss": 0.0625, "step": 75640 }, { "epoch": 18.16, "learning_rate": 9.280548247746261e-05, "loss": 0.1083, "step": 75650 }, { "epoch": 18.17, "learning_rate": 9.28036272975343e-05, "loss": 0.1073, "step": 75660 }, { "epoch": 18.17, "learning_rate": 9.280177189699572e-05, "loss": 0.0676, "step": 75670 }, { "epoch": 18.17, "learning_rate": 9.279991627585648e-05, "loss": 0.0607, "step": 75680 }, { "epoch": 18.17, "learning_rate": 9.279806043412609e-05, "loss": 0.0839, "step": 75690 }, { "epoch": 18.18, "learning_rate": 9.279620437181416e-05, "loss": 0.0911, "step": 75700 }, { "epoch": 18.18, "learning_rate": 9.279434808893022e-05, "loss": 0.0832, "step": 75710 }, { "epoch": 18.18, "learning_rate": 9.279249158548384e-05, "loss": 0.0792, "step": 75720 }, { "epoch": 18.18, "learning_rate": 9.279063486148463e-05, "loss": 0.0729, "step": 75730 }, { "epoch": 18.18, "learning_rate": 9.27887779169421e-05, "loss": 0.085, "step": 75740 }, { "epoch": 18.19, "learning_rate": 9.278692075186587e-05, "loss": 0.133, "step": 75750 }, { "epoch": 18.19, "learning_rate": 9.27850633662655e-05, "loss": 0.1264, "step": 75760 }, { "epoch": 18.19, "learning_rate": 9.278320576015053e-05, "loss": 0.1094, "step": 75770 }, { "epoch": 18.19, "learning_rate": 9.278134793353057e-05, "loss": 0.1048, "step": 75780 }, { "epoch": 18.2, "learning_rate": 9.277948988641521e-05, "loss": 0.0818, "step": 75790 }, { "epoch": 18.2, "learning_rate": 9.277763161881397e-05, "loss": 0.0664, "step": 75800 }, { "epoch": 18.2, "learning_rate": 9.277577313073647e-05, "loss": 0.0971, "step": 75810 }, { "epoch": 18.2, "learning_rate": 9.277391442219228e-05, "loss": 0.1282, "step": 75820 }, { "epoch": 18.2, "learning_rate": 9.277205549319097e-05, "loss": 0.1093, "step": 75830 }, { "epoch": 18.21, "learning_rate": 9.277019634374214e-05, "loss": 0.0802, "step": 75840 }, { "epoch": 18.21, "learning_rate": 9.276833697385534e-05, "loss": 0.0708, "step": 75850 }, { "epoch": 18.21, "learning_rate": 9.27664773835402e-05, "loss": 0.0928, "step": 75860 }, { "epoch": 18.21, "learning_rate": 9.276461757280626e-05, "loss": 0.1133, "step": 75870 }, { "epoch": 18.22, "learning_rate": 9.276275754166312e-05, "loss": 0.1014, "step": 75880 }, { "epoch": 18.22, "learning_rate": 9.276089729012039e-05, "loss": 0.1035, "step": 75890 }, { "epoch": 18.22, "learning_rate": 9.275903681818763e-05, "loss": 0.0901, "step": 75900 }, { "epoch": 18.22, "learning_rate": 9.275717612587443e-05, "loss": 0.0969, "step": 75910 }, { "epoch": 18.23, "learning_rate": 9.275531521319039e-05, "loss": 0.0657, "step": 75920 }, { "epoch": 18.23, "learning_rate": 9.27534540801451e-05, "loss": 0.0774, "step": 75930 }, { "epoch": 18.23, "learning_rate": 9.275159272674816e-05, "loss": 0.0719, "step": 75940 }, { "epoch": 18.23, "learning_rate": 9.274973115300914e-05, "loss": 0.0553, "step": 75950 }, { "epoch": 18.23, "learning_rate": 9.274786935893765e-05, "loss": 0.0982, "step": 75960 }, { "epoch": 18.24, "learning_rate": 9.274600734454329e-05, "loss": 0.0747, "step": 75970 }, { "epoch": 18.24, "learning_rate": 9.274414510983565e-05, "loss": 0.0799, "step": 75980 }, { "epoch": 18.24, "learning_rate": 9.274228265482432e-05, "loss": 0.1126, "step": 75990 }, { "epoch": 18.24, "learning_rate": 9.27404199795189e-05, "loss": 0.0689, "step": 76000 }, { "epoch": 18.25, "learning_rate": 9.273855708392903e-05, "loss": 0.0845, "step": 76010 }, { "epoch": 18.25, "learning_rate": 9.273669396806426e-05, "loss": 0.0708, "step": 76020 }, { "epoch": 18.25, "learning_rate": 9.27348306319342e-05, "loss": 0.0875, "step": 76030 }, { "epoch": 18.25, "learning_rate": 9.273296707554849e-05, "loss": 0.1264, "step": 76040 }, { "epoch": 18.26, "learning_rate": 9.27311032989167e-05, "loss": 0.0995, "step": 76050 }, { "epoch": 18.26, "learning_rate": 9.272923930204845e-05, "loss": 0.0483, "step": 76060 }, { "epoch": 18.26, "learning_rate": 9.272737508495333e-05, "loss": 0.0888, "step": 76070 }, { "epoch": 18.26, "learning_rate": 9.272551064764097e-05, "loss": 0.0778, "step": 76080 }, { "epoch": 18.26, "learning_rate": 9.272364599012097e-05, "loss": 0.0666, "step": 76090 }, { "epoch": 18.27, "learning_rate": 9.272178111240294e-05, "loss": 0.0711, "step": 76100 }, { "epoch": 18.27, "learning_rate": 9.27199160144965e-05, "loss": 0.0477, "step": 76110 }, { "epoch": 18.27, "learning_rate": 9.271805069641125e-05, "loss": 0.1008, "step": 76120 }, { "epoch": 18.27, "learning_rate": 9.27161851581568e-05, "loss": 0.0558, "step": 76130 }, { "epoch": 18.28, "learning_rate": 9.27143193997428e-05, "loss": 0.0916, "step": 76140 }, { "epoch": 18.28, "learning_rate": 9.271245342117882e-05, "loss": 0.0734, "step": 76150 }, { "epoch": 18.28, "learning_rate": 9.271058722247452e-05, "loss": 0.0563, "step": 76160 }, { "epoch": 18.28, "learning_rate": 9.270872080363948e-05, "loss": 0.048, "step": 76170 }, { "epoch": 18.28, "learning_rate": 9.270685416468335e-05, "loss": 0.0911, "step": 76180 }, { "epoch": 18.29, "learning_rate": 9.27049873056157e-05, "loss": 0.0792, "step": 76190 }, { "epoch": 18.29, "learning_rate": 9.270312022644623e-05, "loss": 0.0769, "step": 76200 }, { "epoch": 18.29, "learning_rate": 9.27012529271845e-05, "loss": 0.0733, "step": 76210 }, { "epoch": 18.29, "learning_rate": 9.269938540784015e-05, "loss": 0.1059, "step": 76220 }, { "epoch": 18.3, "learning_rate": 9.269751766842283e-05, "loss": 0.0894, "step": 76230 }, { "epoch": 18.3, "learning_rate": 9.269564970894213e-05, "loss": 0.0865, "step": 76240 }, { "epoch": 18.3, "learning_rate": 9.26937815294077e-05, "loss": 0.0658, "step": 76250 }, { "epoch": 18.3, "learning_rate": 9.269191312982917e-05, "loss": 0.1032, "step": 76260 }, { "epoch": 18.31, "learning_rate": 9.269004451021616e-05, "loss": 0.0677, "step": 76270 }, { "epoch": 18.31, "learning_rate": 9.268817567057831e-05, "loss": 0.0583, "step": 76280 }, { "epoch": 18.31, "learning_rate": 9.268630661092523e-05, "loss": 0.0764, "step": 76290 }, { "epoch": 18.31, "learning_rate": 9.268443733126657e-05, "loss": 0.0503, "step": 76300 }, { "epoch": 18.31, "learning_rate": 9.268256783161198e-05, "loss": 0.0932, "step": 76310 }, { "epoch": 18.32, "learning_rate": 9.268069811197106e-05, "loss": 0.0828, "step": 76320 }, { "epoch": 18.32, "learning_rate": 9.267882817235347e-05, "loss": 0.0596, "step": 76330 }, { "epoch": 18.32, "learning_rate": 9.267695801276885e-05, "loss": 0.0592, "step": 76340 }, { "epoch": 18.32, "learning_rate": 9.267508763322684e-05, "loss": 0.1104, "step": 76350 }, { "epoch": 18.33, "learning_rate": 9.267321703373705e-05, "loss": 0.0821, "step": 76360 }, { "epoch": 18.33, "learning_rate": 9.267134621430916e-05, "loss": 0.0836, "step": 76370 }, { "epoch": 18.33, "learning_rate": 9.266947517495277e-05, "loss": 0.0736, "step": 76380 }, { "epoch": 18.33, "learning_rate": 9.266760391567757e-05, "loss": 0.0949, "step": 76390 }, { "epoch": 18.34, "learning_rate": 9.266573243649319e-05, "loss": 0.0722, "step": 76400 }, { "epoch": 18.34, "learning_rate": 9.266386073740925e-05, "loss": 0.0769, "step": 76410 }, { "epoch": 18.34, "learning_rate": 9.266198881843542e-05, "loss": 0.0803, "step": 76420 }, { "epoch": 18.34, "learning_rate": 9.266011667958134e-05, "loss": 0.0727, "step": 76430 }, { "epoch": 18.34, "learning_rate": 9.265824432085668e-05, "loss": 0.0716, "step": 76440 }, { "epoch": 18.35, "learning_rate": 9.265637174227106e-05, "loss": 0.0672, "step": 76450 }, { "epoch": 18.35, "learning_rate": 9.265449894383414e-05, "loss": 0.0856, "step": 76460 }, { "epoch": 18.35, "learning_rate": 9.265262592555557e-05, "loss": 0.0682, "step": 76470 }, { "epoch": 18.35, "learning_rate": 9.265075268744503e-05, "loss": 0.1142, "step": 76480 }, { "epoch": 18.36, "learning_rate": 9.264887922951212e-05, "loss": 0.0843, "step": 76490 }, { "epoch": 18.36, "learning_rate": 9.264700555176658e-05, "loss": 0.0836, "step": 76500 }, { "epoch": 18.36, "learning_rate": 9.264513165421798e-05, "loss": 0.0708, "step": 76510 }, { "epoch": 18.36, "learning_rate": 9.264325753687602e-05, "loss": 0.0636, "step": 76520 }, { "epoch": 18.36, "learning_rate": 9.264138319975036e-05, "loss": 0.0678, "step": 76530 }, { "epoch": 18.37, "learning_rate": 9.263950864285065e-05, "loss": 0.0907, "step": 76540 }, { "epoch": 18.37, "learning_rate": 9.263763386618656e-05, "loss": 0.0592, "step": 76550 }, { "epoch": 18.37, "learning_rate": 9.263575886976775e-05, "loss": 0.0846, "step": 76560 }, { "epoch": 18.37, "learning_rate": 9.263388365360388e-05, "loss": 0.0904, "step": 76570 }, { "epoch": 18.38, "learning_rate": 9.263200821770461e-05, "loss": 0.0961, "step": 76580 }, { "epoch": 18.38, "learning_rate": 9.263013256207963e-05, "loss": 0.0881, "step": 76590 }, { "epoch": 18.38, "learning_rate": 9.262825668673858e-05, "loss": 0.0801, "step": 76600 }, { "epoch": 18.38, "learning_rate": 9.262638059169113e-05, "loss": 0.0632, "step": 76610 }, { "epoch": 18.39, "learning_rate": 9.262450427694698e-05, "loss": 0.107, "step": 76620 }, { "epoch": 18.39, "learning_rate": 9.262262774251576e-05, "loss": 0.0377, "step": 76630 }, { "epoch": 18.39, "learning_rate": 9.262075098840717e-05, "loss": 0.0909, "step": 76640 }, { "epoch": 18.39, "learning_rate": 9.261887401463088e-05, "loss": 0.0745, "step": 76650 }, { "epoch": 18.39, "learning_rate": 9.261699682119653e-05, "loss": 0.069, "step": 76660 }, { "epoch": 18.4, "learning_rate": 9.261511940811384e-05, "loss": 0.0773, "step": 76670 }, { "epoch": 18.4, "learning_rate": 9.261324177539247e-05, "loss": 0.0679, "step": 76680 }, { "epoch": 18.4, "learning_rate": 9.261136392304209e-05, "loss": 0.0803, "step": 76690 }, { "epoch": 18.4, "learning_rate": 9.260948585107238e-05, "loss": 0.0806, "step": 76700 }, { "epoch": 18.41, "learning_rate": 9.260760755949305e-05, "loss": 0.0744, "step": 76710 }, { "epoch": 18.41, "learning_rate": 9.260572904831373e-05, "loss": 0.1177, "step": 76720 }, { "epoch": 18.41, "learning_rate": 9.260385031754413e-05, "loss": 0.0763, "step": 76730 }, { "epoch": 18.41, "learning_rate": 9.260197136719393e-05, "loss": 0.0852, "step": 76740 }, { "epoch": 18.41, "learning_rate": 9.260009219727282e-05, "loss": 0.0682, "step": 76750 }, { "epoch": 18.42, "learning_rate": 9.259821280779047e-05, "loss": 0.0758, "step": 76760 }, { "epoch": 18.42, "learning_rate": 9.259633319875658e-05, "loss": 0.1017, "step": 76770 }, { "epoch": 18.42, "learning_rate": 9.259445337018084e-05, "loss": 0.0821, "step": 76780 }, { "epoch": 18.42, "learning_rate": 9.259257332207292e-05, "loss": 0.0736, "step": 76790 }, { "epoch": 18.43, "learning_rate": 9.259069305444252e-05, "loss": 0.0736, "step": 76800 }, { "epoch": 18.43, "learning_rate": 9.258881256729934e-05, "loss": 0.0722, "step": 76810 }, { "epoch": 18.43, "learning_rate": 9.258693186065307e-05, "loss": 0.0534, "step": 76820 }, { "epoch": 18.43, "learning_rate": 9.258505093451337e-05, "loss": 0.0641, "step": 76830 }, { "epoch": 18.44, "learning_rate": 9.258316978888998e-05, "loss": 0.0453, "step": 76840 }, { "epoch": 18.44, "learning_rate": 9.258128842379257e-05, "loss": 0.1005, "step": 76850 }, { "epoch": 18.44, "learning_rate": 9.257940683923085e-05, "loss": 0.0726, "step": 76860 }, { "epoch": 18.44, "learning_rate": 9.25775250352145e-05, "loss": 0.1044, "step": 76870 }, { "epoch": 18.44, "learning_rate": 9.257564301175326e-05, "loss": 0.0553, "step": 76880 }, { "epoch": 18.45, "learning_rate": 9.257376076885678e-05, "loss": 0.1105, "step": 76890 }, { "epoch": 18.45, "learning_rate": 9.257187830653478e-05, "loss": 0.0758, "step": 76900 }, { "epoch": 18.45, "learning_rate": 9.256999562479696e-05, "loss": 0.0641, "step": 76910 }, { "epoch": 18.45, "learning_rate": 9.256811272365303e-05, "loss": 0.0842, "step": 76920 }, { "epoch": 18.46, "learning_rate": 9.25662296031127e-05, "loss": 0.1001, "step": 76930 }, { "epoch": 18.46, "learning_rate": 9.256434626318566e-05, "loss": 0.0668, "step": 76940 }, { "epoch": 18.46, "learning_rate": 9.256246270388161e-05, "loss": 0.0596, "step": 76950 }, { "epoch": 18.46, "learning_rate": 9.256057892521028e-05, "loss": 0.0615, "step": 76960 }, { "epoch": 18.47, "learning_rate": 9.255869492718138e-05, "loss": 0.0559, "step": 76970 }, { "epoch": 18.47, "learning_rate": 9.255681070980463e-05, "loss": 0.0635, "step": 76980 }, { "epoch": 18.47, "learning_rate": 9.255492627308968e-05, "loss": 0.0615, "step": 76990 }, { "epoch": 18.47, "learning_rate": 9.25530416170463e-05, "loss": 0.0637, "step": 77000 }, { "epoch": 18.47, "learning_rate": 9.25511567416842e-05, "loss": 0.063, "step": 77010 }, { "epoch": 18.48, "learning_rate": 9.254927164701305e-05, "loss": 0.0585, "step": 77020 }, { "epoch": 18.48, "learning_rate": 9.254738633304263e-05, "loss": 0.0717, "step": 77030 }, { "epoch": 18.48, "learning_rate": 9.254550079978261e-05, "loss": 0.0504, "step": 77040 }, { "epoch": 18.48, "learning_rate": 9.254361504724273e-05, "loss": 0.0649, "step": 77050 }, { "epoch": 18.49, "learning_rate": 9.254172907543271e-05, "loss": 0.0433, "step": 77060 }, { "epoch": 18.49, "learning_rate": 9.253984288436226e-05, "loss": 0.0654, "step": 77070 }, { "epoch": 18.49, "learning_rate": 9.253795647404108e-05, "loss": 0.0804, "step": 77080 }, { "epoch": 18.49, "learning_rate": 9.253606984447895e-05, "loss": 0.0786, "step": 77090 }, { "epoch": 18.49, "learning_rate": 9.253418299568555e-05, "loss": 0.0979, "step": 77100 }, { "epoch": 18.5, "learning_rate": 9.253229592767061e-05, "loss": 0.137, "step": 77110 }, { "epoch": 18.5, "learning_rate": 9.253040864044385e-05, "loss": 0.0571, "step": 77120 }, { "epoch": 18.5, "learning_rate": 9.252852113401502e-05, "loss": 0.0603, "step": 77130 }, { "epoch": 18.5, "learning_rate": 9.252663340839385e-05, "loss": 0.0714, "step": 77140 }, { "epoch": 18.51, "learning_rate": 9.252474546359004e-05, "loss": 0.1128, "step": 77150 }, { "epoch": 18.51, "learning_rate": 9.252285729961335e-05, "loss": 0.0603, "step": 77160 }, { "epoch": 18.51, "learning_rate": 9.252096891647348e-05, "loss": 0.0482, "step": 77170 }, { "epoch": 18.51, "learning_rate": 9.251908031418018e-05, "loss": 0.0753, "step": 77180 }, { "epoch": 18.52, "learning_rate": 9.25171914927432e-05, "loss": 0.0698, "step": 77190 }, { "epoch": 18.52, "learning_rate": 9.251530245217225e-05, "loss": 0.0802, "step": 77200 }, { "epoch": 18.52, "learning_rate": 9.251341319247709e-05, "loss": 0.0605, "step": 77210 }, { "epoch": 18.52, "learning_rate": 9.251152371366741e-05, "loss": 0.1072, "step": 77220 }, { "epoch": 18.52, "learning_rate": 9.250963401575302e-05, "loss": 0.078, "step": 77230 }, { "epoch": 18.53, "learning_rate": 9.250774409874359e-05, "loss": 0.0912, "step": 77240 }, { "epoch": 18.53, "learning_rate": 9.250585396264891e-05, "loss": 0.098, "step": 77250 }, { "epoch": 18.53, "learning_rate": 9.25039636074787e-05, "loss": 0.0933, "step": 77260 }, { "epoch": 18.53, "learning_rate": 9.250207303324269e-05, "loss": 0.0803, "step": 77270 }, { "epoch": 18.54, "learning_rate": 9.250018223995067e-05, "loss": 0.1407, "step": 77280 }, { "epoch": 18.54, "learning_rate": 9.249829122761233e-05, "loss": 0.1273, "step": 77290 }, { "epoch": 18.54, "learning_rate": 9.249639999623747e-05, "loss": 0.1596, "step": 77300 }, { "epoch": 18.54, "learning_rate": 9.249450854583579e-05, "loss": 0.1766, "step": 77310 }, { "epoch": 18.55, "learning_rate": 9.249261687641706e-05, "loss": 0.1551, "step": 77320 }, { "epoch": 18.55, "learning_rate": 9.249072498799103e-05, "loss": 0.1137, "step": 77330 }, { "epoch": 18.55, "learning_rate": 9.248883288056744e-05, "loss": 0.1327, "step": 77340 }, { "epoch": 18.55, "learning_rate": 9.248694055415605e-05, "loss": 0.114, "step": 77350 }, { "epoch": 18.55, "learning_rate": 9.248504800876662e-05, "loss": 0.0968, "step": 77360 }, { "epoch": 18.56, "learning_rate": 9.24831552444089e-05, "loss": 0.1077, "step": 77370 }, { "epoch": 18.56, "learning_rate": 9.248126226109264e-05, "loss": 0.0982, "step": 77380 }, { "epoch": 18.56, "learning_rate": 9.247936905882759e-05, "loss": 0.1429, "step": 77390 }, { "epoch": 18.56, "learning_rate": 9.247747563762353e-05, "loss": 0.1153, "step": 77400 }, { "epoch": 18.57, "learning_rate": 9.24755819974902e-05, "loss": 0.1225, "step": 77410 }, { "epoch": 18.57, "learning_rate": 9.247368813843737e-05, "loss": 0.132, "step": 77420 }, { "epoch": 18.57, "learning_rate": 9.247179406047479e-05, "loss": 0.0928, "step": 77430 }, { "epoch": 18.57, "learning_rate": 9.246989976361222e-05, "loss": 0.1039, "step": 77440 }, { "epoch": 18.57, "learning_rate": 9.246800524785946e-05, "loss": 0.139, "step": 77450 }, { "epoch": 18.58, "learning_rate": 9.246611051322622e-05, "loss": 0.1277, "step": 77460 }, { "epoch": 18.58, "learning_rate": 9.24642155597223e-05, "loss": 0.1124, "step": 77470 }, { "epoch": 18.58, "learning_rate": 9.246232038735744e-05, "loss": 0.092, "step": 77480 }, { "epoch": 18.58, "learning_rate": 9.246042499614146e-05, "loss": 0.081, "step": 77490 }, { "epoch": 18.59, "learning_rate": 9.245852938608408e-05, "loss": 0.1099, "step": 77500 }, { "epoch": 18.59, "learning_rate": 9.245663355719508e-05, "loss": 0.1235, "step": 77510 }, { "epoch": 18.59, "learning_rate": 9.245473750948423e-05, "loss": 0.0801, "step": 77520 }, { "epoch": 18.59, "learning_rate": 9.245284124296132e-05, "loss": 0.1322, "step": 77530 }, { "epoch": 18.6, "learning_rate": 9.245094475763612e-05, "loss": 0.1498, "step": 77540 }, { "epoch": 18.6, "learning_rate": 9.244904805351837e-05, "loss": 0.1008, "step": 77550 }, { "epoch": 18.6, "learning_rate": 9.24471511306179e-05, "loss": 0.0856, "step": 77560 }, { "epoch": 18.6, "learning_rate": 9.244525398894443e-05, "loss": 0.1113, "step": 77570 }, { "epoch": 18.6, "learning_rate": 9.244335662850778e-05, "loss": 0.1061, "step": 77580 }, { "epoch": 18.61, "learning_rate": 9.244145904931771e-05, "loss": 0.0852, "step": 77590 }, { "epoch": 18.61, "learning_rate": 9.243956125138402e-05, "loss": 0.1053, "step": 77600 }, { "epoch": 18.61, "learning_rate": 9.243766323471646e-05, "loss": 0.1074, "step": 77610 }, { "epoch": 18.61, "learning_rate": 9.243576499932485e-05, "loss": 0.1061, "step": 77620 }, { "epoch": 18.62, "learning_rate": 9.243386654521892e-05, "loss": 0.1141, "step": 77630 }, { "epoch": 18.62, "learning_rate": 9.24319678724085e-05, "loss": 0.1336, "step": 77640 }, { "epoch": 18.62, "learning_rate": 9.243006898090338e-05, "loss": 0.1545, "step": 77650 }, { "epoch": 18.62, "learning_rate": 9.242816987071332e-05, "loss": 0.1031, "step": 77660 }, { "epoch": 18.63, "learning_rate": 9.242627054184812e-05, "loss": 0.0678, "step": 77670 }, { "epoch": 18.63, "learning_rate": 9.242437099431755e-05, "loss": 0.097, "step": 77680 }, { "epoch": 18.63, "learning_rate": 9.242247122813143e-05, "loss": 0.0929, "step": 77690 }, { "epoch": 18.63, "learning_rate": 9.242057124329954e-05, "loss": 0.1043, "step": 77700 }, { "epoch": 18.63, "learning_rate": 9.241867103983169e-05, "loss": 0.1186, "step": 77710 }, { "epoch": 18.64, "learning_rate": 9.241677061773762e-05, "loss": 0.0816, "step": 77720 }, { "epoch": 18.64, "learning_rate": 9.241486997702717e-05, "loss": 0.1184, "step": 77730 }, { "epoch": 18.64, "learning_rate": 9.241296911771014e-05, "loss": 0.0819, "step": 77740 }, { "epoch": 18.64, "learning_rate": 9.24110680397963e-05, "loss": 0.1246, "step": 77750 }, { "epoch": 18.65, "learning_rate": 9.240916674329547e-05, "loss": 0.1226, "step": 77760 }, { "epoch": 18.65, "learning_rate": 9.240726522821744e-05, "loss": 0.1401, "step": 77770 }, { "epoch": 18.65, "learning_rate": 9.2405363494572e-05, "loss": 0.0885, "step": 77780 }, { "epoch": 18.65, "learning_rate": 9.240346154236897e-05, "loss": 0.0642, "step": 77790 }, { "epoch": 18.65, "learning_rate": 9.240155937161813e-05, "loss": 0.1101, "step": 77800 }, { "epoch": 18.66, "learning_rate": 9.23996569823293e-05, "loss": 0.1088, "step": 77810 }, { "epoch": 18.66, "learning_rate": 9.23977543745123e-05, "loss": 0.087, "step": 77820 }, { "epoch": 18.66, "learning_rate": 9.239585154817691e-05, "loss": 0.0707, "step": 77830 }, { "epoch": 18.66, "learning_rate": 9.239394850333296e-05, "loss": 0.1004, "step": 77840 }, { "epoch": 18.67, "learning_rate": 9.239204523999023e-05, "loss": 0.1075, "step": 77850 }, { "epoch": 18.67, "learning_rate": 9.239014175815854e-05, "loss": 0.0808, "step": 77860 }, { "epoch": 18.67, "learning_rate": 9.238823805784774e-05, "loss": 0.0785, "step": 77870 }, { "epoch": 18.67, "learning_rate": 9.238633413906756e-05, "loss": 0.0711, "step": 77880 }, { "epoch": 18.68, "learning_rate": 9.238443000182789e-05, "loss": 0.0703, "step": 77890 }, { "epoch": 18.68, "learning_rate": 9.23825256461385e-05, "loss": 0.089, "step": 77900 }, { "epoch": 18.68, "learning_rate": 9.238062107200922e-05, "loss": 0.0711, "step": 77910 }, { "epoch": 18.68, "learning_rate": 9.237871627944987e-05, "loss": 0.0646, "step": 77920 }, { "epoch": 18.68, "learning_rate": 9.237681126847026e-05, "loss": 0.1113, "step": 77930 }, { "epoch": 18.69, "learning_rate": 9.237490603908021e-05, "loss": 0.083, "step": 77940 }, { "epoch": 18.69, "learning_rate": 9.237300059128954e-05, "loss": 0.0881, "step": 77950 }, { "epoch": 18.69, "learning_rate": 9.237109492510807e-05, "loss": 0.1265, "step": 77960 }, { "epoch": 18.69, "learning_rate": 9.236918904054562e-05, "loss": 0.1156, "step": 77970 }, { "epoch": 18.7, "learning_rate": 9.236728293761204e-05, "loss": 0.089, "step": 77980 }, { "epoch": 18.7, "learning_rate": 9.236537661631709e-05, "loss": 0.0945, "step": 77990 }, { "epoch": 18.7, "learning_rate": 9.236347007667066e-05, "loss": 0.1023, "step": 78000 }, { "epoch": 18.7, "learning_rate": 9.236156331868253e-05, "loss": 0.0971, "step": 78010 }, { "epoch": 18.71, "learning_rate": 9.235965634236257e-05, "loss": 0.0957, "step": 78020 }, { "epoch": 18.71, "learning_rate": 9.235774914772058e-05, "loss": 0.0951, "step": 78030 }, { "epoch": 18.71, "learning_rate": 9.23558417347664e-05, "loss": 0.0898, "step": 78040 }, { "epoch": 18.71, "learning_rate": 9.235393410350985e-05, "loss": 0.1446, "step": 78050 }, { "epoch": 18.71, "learning_rate": 9.235202625396078e-05, "loss": 0.095, "step": 78060 }, { "epoch": 18.72, "learning_rate": 9.2350118186129e-05, "loss": 0.0812, "step": 78070 }, { "epoch": 18.72, "learning_rate": 9.234820990002437e-05, "loss": 0.0774, "step": 78080 }, { "epoch": 18.72, "learning_rate": 9.23463013956567e-05, "loss": 0.1149, "step": 78090 }, { "epoch": 18.72, "learning_rate": 9.234439267303585e-05, "loss": 0.0593, "step": 78100 }, { "epoch": 18.73, "learning_rate": 9.234248373217163e-05, "loss": 0.1156, "step": 78110 }, { "epoch": 18.73, "learning_rate": 9.234057457307392e-05, "loss": 0.1351, "step": 78120 }, { "epoch": 18.73, "learning_rate": 9.233866519575252e-05, "loss": 0.0979, "step": 78130 }, { "epoch": 18.73, "learning_rate": 9.233675560021729e-05, "loss": 0.0879, "step": 78140 }, { "epoch": 18.73, "learning_rate": 9.233484578647806e-05, "loss": 0.07, "step": 78150 }, { "epoch": 18.74, "learning_rate": 9.233293575454467e-05, "loss": 0.0912, "step": 78160 }, { "epoch": 18.74, "learning_rate": 9.2331025504427e-05, "loss": 0.1113, "step": 78170 }, { "epoch": 18.74, "learning_rate": 9.232911503613486e-05, "loss": 0.1393, "step": 78180 }, { "epoch": 18.74, "learning_rate": 9.232720434967811e-05, "loss": 0.0797, "step": 78190 }, { "epoch": 18.75, "learning_rate": 9.23252934450666e-05, "loss": 0.0593, "step": 78200 }, { "epoch": 18.75, "learning_rate": 9.232338232231015e-05, "loss": 0.0842, "step": 78210 }, { "epoch": 18.75, "learning_rate": 9.232147098141866e-05, "loss": 0.0677, "step": 78220 }, { "epoch": 18.75, "learning_rate": 9.231955942240194e-05, "loss": 0.0846, "step": 78230 }, { "epoch": 18.76, "learning_rate": 9.231764764526987e-05, "loss": 0.086, "step": 78240 }, { "epoch": 18.76, "learning_rate": 9.231573565003228e-05, "loss": 0.1113, "step": 78250 }, { "epoch": 18.76, "learning_rate": 9.231382343669903e-05, "loss": 0.076, "step": 78260 }, { "epoch": 18.76, "learning_rate": 9.231191100527999e-05, "loss": 0.1043, "step": 78270 }, { "epoch": 18.76, "learning_rate": 9.2309998355785e-05, "loss": 0.0986, "step": 78280 }, { "epoch": 18.77, "learning_rate": 9.230808548822393e-05, "loss": 0.0617, "step": 78290 }, { "epoch": 18.77, "learning_rate": 9.230617240260664e-05, "loss": 0.0668, "step": 78300 }, { "epoch": 18.77, "learning_rate": 9.230425909894297e-05, "loss": 0.098, "step": 78310 }, { "epoch": 18.77, "learning_rate": 9.23023455772428e-05, "loss": 0.114, "step": 78320 }, { "epoch": 18.78, "learning_rate": 9.2300431837516e-05, "loss": 0.1118, "step": 78330 }, { "epoch": 18.78, "learning_rate": 9.229851787977242e-05, "loss": 0.0937, "step": 78340 }, { "epoch": 18.78, "learning_rate": 9.229660370402191e-05, "loss": 0.0726, "step": 78350 }, { "epoch": 18.78, "learning_rate": 9.229468931027435e-05, "loss": 0.0953, "step": 78360 }, { "epoch": 18.79, "learning_rate": 9.229277469853962e-05, "loss": 0.0689, "step": 78370 }, { "epoch": 18.79, "learning_rate": 9.229085986882757e-05, "loss": 0.0995, "step": 78380 }, { "epoch": 18.79, "learning_rate": 9.228894482114807e-05, "loss": 0.0871, "step": 78390 }, { "epoch": 18.79, "learning_rate": 9.228702955551101e-05, "loss": 0.1025, "step": 78400 }, { "epoch": 18.79, "learning_rate": 9.228511407192622e-05, "loss": 0.1014, "step": 78410 }, { "epoch": 18.8, "learning_rate": 9.228319837040362e-05, "loss": 0.0985, "step": 78420 }, { "epoch": 18.8, "learning_rate": 9.228128245095307e-05, "loss": 0.0733, "step": 78430 }, { "epoch": 18.8, "learning_rate": 9.227936631358441e-05, "loss": 0.0717, "step": 78440 }, { "epoch": 18.8, "learning_rate": 9.227744995830756e-05, "loss": 0.0641, "step": 78450 }, { "epoch": 18.81, "learning_rate": 9.227553338513237e-05, "loss": 0.091, "step": 78460 }, { "epoch": 18.81, "learning_rate": 9.227361659406873e-05, "loss": 0.0935, "step": 78470 }, { "epoch": 18.81, "learning_rate": 9.227169958512652e-05, "loss": 0.0677, "step": 78480 }, { "epoch": 18.81, "learning_rate": 9.226978235831563e-05, "loss": 0.0968, "step": 78490 }, { "epoch": 18.81, "learning_rate": 9.22678649136459e-05, "loss": 0.0668, "step": 78500 }, { "epoch": 18.82, "learning_rate": 9.226594725112727e-05, "loss": 0.0889, "step": 78510 }, { "epoch": 18.82, "learning_rate": 9.226402937076958e-05, "loss": 0.089, "step": 78520 }, { "epoch": 18.82, "learning_rate": 9.226211127258273e-05, "loss": 0.0749, "step": 78530 }, { "epoch": 18.82, "learning_rate": 9.22601929565766e-05, "loss": 0.1102, "step": 78540 }, { "epoch": 18.83, "learning_rate": 9.22582744227611e-05, "loss": 0.1245, "step": 78550 }, { "epoch": 18.83, "learning_rate": 9.225635567114608e-05, "loss": 0.0749, "step": 78560 }, { "epoch": 18.83, "learning_rate": 9.225443670174145e-05, "loss": 0.1168, "step": 78570 }, { "epoch": 18.83, "learning_rate": 9.225251751455711e-05, "loss": 0.0887, "step": 78580 }, { "epoch": 18.84, "learning_rate": 9.225059810960295e-05, "loss": 0.0827, "step": 78590 }, { "epoch": 18.84, "learning_rate": 9.224867848688883e-05, "loss": 0.0752, "step": 78600 }, { "epoch": 18.84, "learning_rate": 9.224675864642469e-05, "loss": 0.0684, "step": 78610 }, { "epoch": 18.84, "learning_rate": 9.22448385882204e-05, "loss": 0.0998, "step": 78620 }, { "epoch": 18.84, "learning_rate": 9.224291831228585e-05, "loss": 0.0823, "step": 78630 }, { "epoch": 18.85, "learning_rate": 9.224099781863094e-05, "loss": 0.086, "step": 78640 }, { "epoch": 18.85, "learning_rate": 9.223907710726558e-05, "loss": 0.0699, "step": 78650 }, { "epoch": 18.85, "learning_rate": 9.223715617819968e-05, "loss": 0.1051, "step": 78660 }, { "epoch": 18.85, "learning_rate": 9.22352350314431e-05, "loss": 0.0757, "step": 78670 }, { "epoch": 18.86, "learning_rate": 9.223331366700578e-05, "loss": 0.0724, "step": 78680 }, { "epoch": 18.86, "learning_rate": 9.22313920848976e-05, "loss": 0.1024, "step": 78690 }, { "epoch": 18.86, "learning_rate": 9.222947028512847e-05, "loss": 0.1024, "step": 78700 }, { "epoch": 18.86, "learning_rate": 9.222754826770832e-05, "loss": 0.1291, "step": 78710 }, { "epoch": 18.87, "learning_rate": 9.222562603264702e-05, "loss": 0.0893, "step": 78720 }, { "epoch": 18.87, "learning_rate": 9.222370357995448e-05, "loss": 0.1058, "step": 78730 }, { "epoch": 18.87, "learning_rate": 9.222178090964062e-05, "loss": 0.103, "step": 78740 }, { "epoch": 18.87, "learning_rate": 9.221985802171536e-05, "loss": 0.0725, "step": 78750 }, { "epoch": 18.87, "learning_rate": 9.22179349161886e-05, "loss": 0.1219, "step": 78760 }, { "epoch": 18.88, "learning_rate": 9.221601159307023e-05, "loss": 0.1007, "step": 78770 }, { "epoch": 18.88, "learning_rate": 9.22140880523702e-05, "loss": 0.0512, "step": 78780 }, { "epoch": 18.88, "learning_rate": 9.22121642940984e-05, "loss": 0.0905, "step": 78790 }, { "epoch": 18.88, "learning_rate": 9.221024031826476e-05, "loss": 0.1137, "step": 78800 }, { "epoch": 18.89, "learning_rate": 9.220831612487919e-05, "loss": 0.0992, "step": 78810 }, { "epoch": 18.89, "learning_rate": 9.22063917139516e-05, "loss": 0.0824, "step": 78820 }, { "epoch": 18.89, "learning_rate": 9.220446708549192e-05, "loss": 0.0855, "step": 78830 }, { "epoch": 18.89, "learning_rate": 9.220254223951006e-05, "loss": 0.0866, "step": 78840 }, { "epoch": 18.89, "learning_rate": 9.220061717601593e-05, "loss": 0.0739, "step": 78850 }, { "epoch": 18.9, "learning_rate": 9.21986918950195e-05, "loss": 0.112, "step": 78860 }, { "epoch": 18.9, "learning_rate": 9.219676639653063e-05, "loss": 0.0713, "step": 78870 }, { "epoch": 18.9, "learning_rate": 9.21948406805593e-05, "loss": 0.0696, "step": 78880 }, { "epoch": 18.9, "learning_rate": 9.219291474711538e-05, "loss": 0.0953, "step": 78890 }, { "epoch": 18.91, "learning_rate": 9.219098859620884e-05, "loss": 0.0829, "step": 78900 }, { "epoch": 18.91, "learning_rate": 9.218906222784958e-05, "loss": 0.0675, "step": 78910 }, { "epoch": 18.91, "learning_rate": 9.218713564204755e-05, "loss": 0.0793, "step": 78920 }, { "epoch": 18.91, "learning_rate": 9.218520883881267e-05, "loss": 0.12, "step": 78930 }, { "epoch": 18.92, "learning_rate": 9.218328181815488e-05, "loss": 0.0737, "step": 78940 }, { "epoch": 18.92, "learning_rate": 9.218135458008409e-05, "loss": 0.0851, "step": 78950 }, { "epoch": 18.92, "learning_rate": 9.217942712461026e-05, "loss": 0.0642, "step": 78960 }, { "epoch": 18.92, "learning_rate": 9.217749945174329e-05, "loss": 0.0771, "step": 78970 }, { "epoch": 18.92, "learning_rate": 9.217557156149314e-05, "loss": 0.0627, "step": 78980 }, { "epoch": 18.93, "learning_rate": 9.217364345386974e-05, "loss": 0.053, "step": 78990 }, { "epoch": 18.93, "learning_rate": 9.217171512888304e-05, "loss": 0.0582, "step": 79000 }, { "epoch": 18.93, "learning_rate": 9.216978658654296e-05, "loss": 0.0764, "step": 79010 }, { "epoch": 18.93, "learning_rate": 9.216785782685946e-05, "loss": 0.0951, "step": 79020 }, { "epoch": 18.94, "learning_rate": 9.216592884984246e-05, "loss": 0.0706, "step": 79030 }, { "epoch": 18.94, "learning_rate": 9.216399965550191e-05, "loss": 0.0917, "step": 79040 }, { "epoch": 18.94, "learning_rate": 9.216207024384774e-05, "loss": 0.1096, "step": 79050 }, { "epoch": 18.94, "learning_rate": 9.216014061488993e-05, "loss": 0.0918, "step": 79060 }, { "epoch": 18.95, "learning_rate": 9.215821076863839e-05, "loss": 0.0659, "step": 79070 }, { "epoch": 18.95, "learning_rate": 9.215628070510307e-05, "loss": 0.0862, "step": 79080 }, { "epoch": 18.95, "learning_rate": 9.215435042429395e-05, "loss": 0.0674, "step": 79090 }, { "epoch": 19.0, "learning_rate": 9.215241992622095e-05, "loss": 0.082, "step": 79100 }, { "epoch": 19.0, "learning_rate": 9.215048921089402e-05, "loss": 0.1087, "step": 79110 }, { "epoch": 19.01, "learning_rate": 9.214855827832312e-05, "loss": 0.0744, "step": 79120 }, { "epoch": 19.01, "learning_rate": 9.214662712851818e-05, "loss": 0.0785, "step": 79130 }, { "epoch": 19.01, "learning_rate": 9.214469576148918e-05, "loss": 0.1173, "step": 79140 }, { "epoch": 19.01, "learning_rate": 9.214276417724607e-05, "loss": 0.063, "step": 79150 }, { "epoch": 19.01, "learning_rate": 9.214083237579882e-05, "loss": 0.0826, "step": 79160 }, { "epoch": 19.02, "learning_rate": 9.213890035715734e-05, "loss": 0.1077, "step": 79170 }, { "epoch": 19.02, "learning_rate": 9.213696812133164e-05, "loss": 0.0848, "step": 79180 }, { "epoch": 19.02, "learning_rate": 9.213503566833164e-05, "loss": 0.0909, "step": 79190 }, { "epoch": 19.02, "learning_rate": 9.213310299816731e-05, "loss": 0.0726, "step": 79200 }, { "epoch": 19.03, "learning_rate": 9.213117011084861e-05, "loss": 0.0432, "step": 79210 }, { "epoch": 19.03, "learning_rate": 9.212923700638552e-05, "loss": 0.0694, "step": 79220 }, { "epoch": 19.03, "learning_rate": 9.212730368478799e-05, "loss": 0.0906, "step": 79230 }, { "epoch": 19.03, "learning_rate": 9.212537014606597e-05, "loss": 0.0884, "step": 79240 }, { "epoch": 19.03, "learning_rate": 9.212343639022945e-05, "loss": 0.0824, "step": 79250 }, { "epoch": 19.04, "learning_rate": 9.212150241728839e-05, "loss": 0.0957, "step": 79260 }, { "epoch": 19.04, "learning_rate": 9.211956822725276e-05, "loss": 0.0561, "step": 79270 }, { "epoch": 19.04, "learning_rate": 9.211763382013253e-05, "loss": 0.1106, "step": 79280 }, { "epoch": 19.04, "learning_rate": 9.211569919593763e-05, "loss": 0.0912, "step": 79290 }, { "epoch": 19.05, "learning_rate": 9.211376435467809e-05, "loss": 0.0696, "step": 79300 }, { "epoch": 19.05, "learning_rate": 9.211182929636384e-05, "loss": 0.0786, "step": 79310 }, { "epoch": 19.05, "learning_rate": 9.210989402100489e-05, "loss": 0.0806, "step": 79320 }, { "epoch": 19.05, "learning_rate": 9.210795852861118e-05, "loss": 0.0668, "step": 79330 }, { "epoch": 19.06, "learning_rate": 9.210602281919269e-05, "loss": 0.0845, "step": 79340 }, { "epoch": 19.06, "learning_rate": 9.210408689275944e-05, "loss": 0.0677, "step": 79350 }, { "epoch": 19.06, "learning_rate": 9.210215074932134e-05, "loss": 0.0478, "step": 79360 }, { "epoch": 19.06, "learning_rate": 9.210021438888843e-05, "loss": 0.0615, "step": 79370 }, { "epoch": 19.06, "learning_rate": 9.209827781147064e-05, "loss": 0.0618, "step": 79380 }, { "epoch": 19.07, "learning_rate": 9.209634101707799e-05, "loss": 0.074, "step": 79390 }, { "epoch": 19.07, "learning_rate": 9.209440400572044e-05, "loss": 0.0785, "step": 79400 }, { "epoch": 19.07, "learning_rate": 9.209246677740798e-05, "loss": 0.1039, "step": 79410 }, { "epoch": 19.07, "learning_rate": 9.20905293321506e-05, "loss": 0.0938, "step": 79420 }, { "epoch": 19.08, "learning_rate": 9.208859166995827e-05, "loss": 0.0869, "step": 79430 }, { "epoch": 19.08, "learning_rate": 9.2086653790841e-05, "loss": 0.0791, "step": 79440 }, { "epoch": 19.08, "learning_rate": 9.208471569480875e-05, "loss": 0.0492, "step": 79450 }, { "epoch": 19.08, "learning_rate": 9.208277738187154e-05, "loss": 0.1109, "step": 79460 }, { "epoch": 19.09, "learning_rate": 9.208083885203933e-05, "loss": 0.0996, "step": 79470 }, { "epoch": 19.09, "learning_rate": 9.207890010532211e-05, "loss": 0.0594, "step": 79480 }, { "epoch": 19.09, "learning_rate": 9.207696114172992e-05, "loss": 0.0489, "step": 79490 }, { "epoch": 19.09, "learning_rate": 9.207502196127271e-05, "loss": 0.0977, "step": 79500 }, { "epoch": 19.09, "learning_rate": 9.207308256396048e-05, "loss": 0.072, "step": 79510 }, { "epoch": 19.1, "learning_rate": 9.207114294980323e-05, "loss": 0.0741, "step": 79520 }, { "epoch": 19.1, "learning_rate": 9.206920311881096e-05, "loss": 0.1004, "step": 79530 }, { "epoch": 19.1, "learning_rate": 9.206726307099367e-05, "loss": 0.0906, "step": 79540 }, { "epoch": 19.1, "learning_rate": 9.206532280636136e-05, "loss": 0.1082, "step": 79550 }, { "epoch": 19.11, "learning_rate": 9.2063382324924e-05, "loss": 0.0737, "step": 79560 }, { "epoch": 19.11, "learning_rate": 9.206144162669164e-05, "loss": 0.0543, "step": 79570 }, { "epoch": 19.11, "learning_rate": 9.205950071167424e-05, "loss": 0.0845, "step": 79580 }, { "epoch": 19.11, "learning_rate": 9.205755957988182e-05, "loss": 0.043, "step": 79590 }, { "epoch": 19.11, "learning_rate": 9.205561823132441e-05, "loss": 0.076, "step": 79600 }, { "epoch": 19.12, "learning_rate": 9.205367666601198e-05, "loss": 0.0783, "step": 79610 }, { "epoch": 19.12, "learning_rate": 9.205173488395454e-05, "loss": 0.0678, "step": 79620 }, { "epoch": 19.12, "learning_rate": 9.204979288516212e-05, "loss": 0.0988, "step": 79630 }, { "epoch": 19.12, "learning_rate": 9.204785066964472e-05, "loss": 0.0653, "step": 79640 }, { "epoch": 19.13, "learning_rate": 9.204590823741232e-05, "loss": 0.0896, "step": 79650 }, { "epoch": 19.13, "learning_rate": 9.2043965588475e-05, "loss": 0.0466, "step": 79660 }, { "epoch": 19.13, "learning_rate": 9.204202272284267e-05, "loss": 0.0813, "step": 79670 }, { "epoch": 19.13, "learning_rate": 9.204007964052545e-05, "loss": 0.083, "step": 79680 }, { "epoch": 19.14, "learning_rate": 9.20381363415333e-05, "loss": 0.0602, "step": 79690 }, { "epoch": 19.14, "learning_rate": 9.203619282587625e-05, "loss": 0.104, "step": 79700 }, { "epoch": 19.14, "learning_rate": 9.203424909356429e-05, "loss": 0.0845, "step": 79710 }, { "epoch": 19.14, "learning_rate": 9.203230514460747e-05, "loss": 0.0832, "step": 79720 }, { "epoch": 19.14, "learning_rate": 9.20303609790158e-05, "loss": 0.104, "step": 79730 }, { "epoch": 19.15, "learning_rate": 9.202841659679929e-05, "loss": 0.0841, "step": 79740 }, { "epoch": 19.15, "learning_rate": 9.202647199796798e-05, "loss": 0.1218, "step": 79750 }, { "epoch": 19.15, "learning_rate": 9.202452718253187e-05, "loss": 0.0935, "step": 79760 }, { "epoch": 19.15, "learning_rate": 9.202258215050102e-05, "loss": 0.0506, "step": 79770 }, { "epoch": 19.16, "learning_rate": 9.20206369018854e-05, "loss": 0.0766, "step": 79780 }, { "epoch": 19.16, "learning_rate": 9.201869143669508e-05, "loss": 0.0838, "step": 79790 }, { "epoch": 19.16, "learning_rate": 9.201674575494008e-05, "loss": 0.0476, "step": 79800 }, { "epoch": 19.16, "learning_rate": 9.201479985663042e-05, "loss": 0.0501, "step": 79810 }, { "epoch": 19.17, "learning_rate": 9.201285374177611e-05, "loss": 0.0823, "step": 79820 }, { "epoch": 19.17, "learning_rate": 9.201090741038721e-05, "loss": 0.0931, "step": 79830 }, { "epoch": 19.17, "learning_rate": 9.200896086247375e-05, "loss": 0.0737, "step": 79840 }, { "epoch": 19.17, "learning_rate": 9.200701409804576e-05, "loss": 0.0481, "step": 79850 }, { "epoch": 19.17, "learning_rate": 9.200506711711326e-05, "loss": 0.0657, "step": 79860 }, { "epoch": 19.18, "learning_rate": 9.200311991968629e-05, "loss": 0.0637, "step": 79870 }, { "epoch": 19.18, "learning_rate": 9.200117250577489e-05, "loss": 0.0591, "step": 79880 }, { "epoch": 19.18, "learning_rate": 9.19992248753891e-05, "loss": 0.1246, "step": 79890 }, { "epoch": 19.18, "learning_rate": 9.199727702853895e-05, "loss": 0.0832, "step": 79900 }, { "epoch": 19.19, "learning_rate": 9.199532896523449e-05, "loss": 0.054, "step": 79910 }, { "epoch": 19.19, "learning_rate": 9.199338068548574e-05, "loss": 0.0645, "step": 79920 }, { "epoch": 19.19, "learning_rate": 9.199143218930276e-05, "loss": 0.0997, "step": 79930 }, { "epoch": 19.19, "learning_rate": 9.19894834766956e-05, "loss": 0.059, "step": 79940 }, { "epoch": 19.19, "learning_rate": 9.198753454767428e-05, "loss": 0.0624, "step": 79950 }, { "epoch": 19.2, "learning_rate": 9.198558540224885e-05, "loss": 0.0723, "step": 79960 }, { "epoch": 19.2, "learning_rate": 9.198363604042937e-05, "loss": 0.0852, "step": 79970 }, { "epoch": 19.2, "learning_rate": 9.198168646222587e-05, "loss": 0.0832, "step": 79980 }, { "epoch": 19.2, "learning_rate": 9.197973666764843e-05, "loss": 0.0711, "step": 79990 }, { "epoch": 19.21, "learning_rate": 9.197778665670706e-05, "loss": 0.0967, "step": 80000 }, { "epoch": 19.21, "learning_rate": 9.197583642941183e-05, "loss": 0.0727, "step": 80010 }, { "epoch": 19.21, "learning_rate": 9.197388598577278e-05, "loss": 0.0504, "step": 80020 }, { "epoch": 19.21, "learning_rate": 9.197193532579997e-05, "loss": 0.0795, "step": 80030 }, { "epoch": 19.22, "learning_rate": 9.196998444950347e-05, "loss": 0.0689, "step": 80040 }, { "epoch": 19.22, "learning_rate": 9.196803335689331e-05, "loss": 0.0612, "step": 80050 }, { "epoch": 19.22, "learning_rate": 9.196608204797957e-05, "loss": 0.0667, "step": 80060 }, { "epoch": 19.22, "learning_rate": 9.196413052277227e-05, "loss": 0.0766, "step": 80070 }, { "epoch": 19.22, "learning_rate": 9.19621787812815e-05, "loss": 0.0773, "step": 80080 }, { "epoch": 19.23, "learning_rate": 9.19602268235173e-05, "loss": 0.0629, "step": 80090 }, { "epoch": 19.23, "learning_rate": 9.195827464948976e-05, "loss": 0.0652, "step": 80100 }, { "epoch": 19.23, "learning_rate": 9.19563222592089e-05, "loss": 0.0615, "step": 80110 }, { "epoch": 19.23, "learning_rate": 9.195436965268483e-05, "loss": 0.0872, "step": 80120 }, { "epoch": 19.24, "learning_rate": 9.195241682992757e-05, "loss": 0.0871, "step": 80130 }, { "epoch": 19.24, "learning_rate": 9.19504637909472e-05, "loss": 0.0876, "step": 80140 }, { "epoch": 19.24, "learning_rate": 9.194851053575379e-05, "loss": 0.09, "step": 80150 }, { "epoch": 19.24, "learning_rate": 9.194655706435741e-05, "loss": 0.0822, "step": 80160 }, { "epoch": 19.25, "learning_rate": 9.194460337676813e-05, "loss": 0.0614, "step": 80170 }, { "epoch": 19.25, "learning_rate": 9.194264947299601e-05, "loss": 0.0568, "step": 80180 }, { "epoch": 19.25, "learning_rate": 9.194069535305112e-05, "loss": 0.0774, "step": 80190 }, { "epoch": 19.25, "learning_rate": 9.193874101694355e-05, "loss": 0.0532, "step": 80200 }, { "epoch": 19.25, "learning_rate": 9.193678646468334e-05, "loss": 0.095, "step": 80210 }, { "epoch": 19.26, "learning_rate": 9.193483169628059e-05, "loss": 0.0887, "step": 80220 }, { "epoch": 19.26, "learning_rate": 9.193287671174537e-05, "loss": 0.0757, "step": 80230 }, { "epoch": 19.26, "learning_rate": 9.193092151108776e-05, "loss": 0.0645, "step": 80240 }, { "epoch": 19.26, "learning_rate": 9.19289660943178e-05, "loss": 0.0569, "step": 80250 }, { "epoch": 19.27, "learning_rate": 9.192701046144562e-05, "loss": 0.0746, "step": 80260 }, { "epoch": 19.27, "learning_rate": 9.192505461248127e-05, "loss": 0.0856, "step": 80270 }, { "epoch": 19.27, "learning_rate": 9.192309854743485e-05, "loss": 0.0836, "step": 80280 }, { "epoch": 19.27, "learning_rate": 9.192114226631643e-05, "loss": 0.0676, "step": 80290 }, { "epoch": 19.27, "learning_rate": 9.191918576913608e-05, "loss": 0.0676, "step": 80300 }, { "epoch": 19.28, "learning_rate": 9.191722905590389e-05, "loss": 0.0832, "step": 80310 }, { "epoch": 19.28, "learning_rate": 9.191527212662998e-05, "loss": 0.0623, "step": 80320 }, { "epoch": 19.28, "learning_rate": 9.191331498132439e-05, "loss": 0.0863, "step": 80330 }, { "epoch": 19.28, "learning_rate": 9.191135761999722e-05, "loss": 0.0486, "step": 80340 }, { "epoch": 19.29, "learning_rate": 9.190940004265855e-05, "loss": 0.0615, "step": 80350 }, { "epoch": 19.29, "learning_rate": 9.19074422493185e-05, "loss": 0.1221, "step": 80360 }, { "epoch": 19.29, "learning_rate": 9.190548423998715e-05, "loss": 0.0445, "step": 80370 }, { "epoch": 19.29, "learning_rate": 9.190352601467458e-05, "loss": 0.0574, "step": 80380 }, { "epoch": 19.3, "learning_rate": 9.190156757339087e-05, "loss": 0.0611, "step": 80390 }, { "epoch": 19.3, "learning_rate": 9.189960891614615e-05, "loss": 0.0918, "step": 80400 }, { "epoch": 19.3, "learning_rate": 9.189765004295048e-05, "loss": 0.07, "step": 80410 }, { "epoch": 19.3, "learning_rate": 9.189569095381398e-05, "loss": 0.0728, "step": 80420 }, { "epoch": 19.3, "learning_rate": 9.189373164874674e-05, "loss": 0.071, "step": 80430 }, { "epoch": 19.31, "learning_rate": 9.189177212775886e-05, "loss": 0.0898, "step": 80440 }, { "epoch": 19.31, "learning_rate": 9.188981239086043e-05, "loss": 0.0814, "step": 80450 }, { "epoch": 19.31, "learning_rate": 9.188785243806155e-05, "loss": 0.0813, "step": 80460 }, { "epoch": 19.31, "learning_rate": 9.188589226937234e-05, "loss": 0.048, "step": 80470 }, { "epoch": 19.32, "learning_rate": 9.188393188480289e-05, "loss": 0.0796, "step": 80480 }, { "epoch": 19.32, "learning_rate": 9.18819712843633e-05, "loss": 0.0627, "step": 80490 }, { "epoch": 19.32, "learning_rate": 9.188001046806367e-05, "loss": 0.0752, "step": 80500 }, { "epoch": 19.32, "learning_rate": 9.187804943591413e-05, "loss": 0.1088, "step": 80510 }, { "epoch": 19.33, "learning_rate": 9.187608818792476e-05, "loss": 0.0783, "step": 80520 }, { "epoch": 19.33, "learning_rate": 9.187412672410572e-05, "loss": 0.0826, "step": 80530 }, { "epoch": 19.33, "learning_rate": 9.187216504446704e-05, "loss": 0.1177, "step": 80540 }, { "epoch": 19.33, "learning_rate": 9.187020314901889e-05, "loss": 0.0804, "step": 80550 }, { "epoch": 19.33, "learning_rate": 9.186824103777135e-05, "loss": 0.0918, "step": 80560 }, { "epoch": 19.34, "learning_rate": 9.186627871073455e-05, "loss": 0.0713, "step": 80570 }, { "epoch": 19.34, "learning_rate": 9.18643161679186e-05, "loss": 0.0566, "step": 80580 }, { "epoch": 19.34, "learning_rate": 9.186235340933363e-05, "loss": 0.0612, "step": 80590 }, { "epoch": 19.34, "learning_rate": 9.186039043498972e-05, "loss": 0.0705, "step": 80600 }, { "epoch": 19.35, "learning_rate": 9.185842724489701e-05, "loss": 0.0667, "step": 80610 }, { "epoch": 19.35, "learning_rate": 9.185646383906564e-05, "loss": 0.0729, "step": 80620 }, { "epoch": 19.35, "learning_rate": 9.185450021750567e-05, "loss": 0.0853, "step": 80630 }, { "epoch": 19.35, "learning_rate": 9.185253638022729e-05, "loss": 0.0763, "step": 80640 }, { "epoch": 19.35, "learning_rate": 9.185057232724056e-05, "loss": 0.0573, "step": 80650 }, { "epoch": 19.36, "learning_rate": 9.184860805855565e-05, "loss": 0.0845, "step": 80660 }, { "epoch": 19.36, "learning_rate": 9.184664357418265e-05, "loss": 0.0658, "step": 80670 }, { "epoch": 19.36, "learning_rate": 9.184467887413171e-05, "loss": 0.0737, "step": 80680 }, { "epoch": 19.36, "learning_rate": 9.184271395841293e-05, "loss": 0.0568, "step": 80690 }, { "epoch": 19.37, "learning_rate": 9.184074882703646e-05, "loss": 0.0727, "step": 80700 }, { "epoch": 19.37, "learning_rate": 9.183878348001242e-05, "loss": 0.0563, "step": 80710 }, { "epoch": 19.37, "learning_rate": 9.183681791735095e-05, "loss": 0.0717, "step": 80720 }, { "epoch": 19.37, "learning_rate": 9.183485213906217e-05, "loss": 0.0611, "step": 80730 }, { "epoch": 19.38, "learning_rate": 9.18328861451562e-05, "loss": 0.0365, "step": 80740 }, { "epoch": 19.38, "learning_rate": 9.183091993564319e-05, "loss": 0.0901, "step": 80750 }, { "epoch": 19.38, "learning_rate": 9.182895351053327e-05, "loss": 0.0632, "step": 80760 }, { "epoch": 19.38, "learning_rate": 9.182698686983657e-05, "loss": 0.0797, "step": 80770 }, { "epoch": 19.38, "learning_rate": 9.182502001356324e-05, "loss": 0.0669, "step": 80780 }, { "epoch": 19.39, "learning_rate": 9.18230529417234e-05, "loss": 0.0817, "step": 80790 }, { "epoch": 19.39, "learning_rate": 9.18210856543272e-05, "loss": 0.0591, "step": 80800 }, { "epoch": 19.39, "learning_rate": 9.181911815138478e-05, "loss": 0.0503, "step": 80810 }, { "epoch": 19.39, "learning_rate": 9.181715043290626e-05, "loss": 0.0666, "step": 80820 }, { "epoch": 19.4, "learning_rate": 9.18151824989018e-05, "loss": 0.0636, "step": 80830 }, { "epoch": 19.4, "learning_rate": 9.181321434938154e-05, "loss": 0.0513, "step": 80840 }, { "epoch": 19.4, "learning_rate": 9.181124598435564e-05, "loss": 0.0707, "step": 80850 }, { "epoch": 19.4, "learning_rate": 9.180927740383423e-05, "loss": 0.077, "step": 80860 }, { "epoch": 19.41, "learning_rate": 9.180730860782743e-05, "loss": 0.0869, "step": 80870 }, { "epoch": 19.41, "learning_rate": 9.180533959634544e-05, "loss": 0.0912, "step": 80880 }, { "epoch": 19.41, "learning_rate": 9.180337036939835e-05, "loss": 0.0676, "step": 80890 }, { "epoch": 19.41, "learning_rate": 9.180140092699637e-05, "loss": 0.0435, "step": 80900 }, { "epoch": 19.41, "learning_rate": 9.179943126914958e-05, "loss": 0.0493, "step": 80910 }, { "epoch": 19.42, "learning_rate": 9.17974613958682e-05, "loss": 0.0831, "step": 80920 }, { "epoch": 19.42, "learning_rate": 9.179549130716236e-05, "loss": 0.0893, "step": 80930 }, { "epoch": 19.42, "learning_rate": 9.179352100304219e-05, "loss": 0.0542, "step": 80940 }, { "epoch": 19.42, "learning_rate": 9.179155048351789e-05, "loss": 0.0621, "step": 80950 }, { "epoch": 19.43, "learning_rate": 9.178957974859956e-05, "loss": 0.08, "step": 80960 }, { "epoch": 19.43, "learning_rate": 9.17876087982974e-05, "loss": 0.073, "step": 80970 }, { "epoch": 19.43, "learning_rate": 9.178563763262155e-05, "loss": 0.0447, "step": 80980 }, { "epoch": 19.43, "learning_rate": 9.178366625158218e-05, "loss": 0.0705, "step": 80990 }, { "epoch": 19.43, "learning_rate": 9.178169465518944e-05, "loss": 0.0806, "step": 81000 }, { "epoch": 19.44, "learning_rate": 9.177972284345351e-05, "loss": 0.0451, "step": 81010 }, { "epoch": 19.44, "learning_rate": 9.177775081638453e-05, "loss": 0.0471, "step": 81020 }, { "epoch": 19.44, "learning_rate": 9.177577857399267e-05, "loss": 0.0544, "step": 81030 }, { "epoch": 19.44, "learning_rate": 9.177380611628809e-05, "loss": 0.0606, "step": 81040 }, { "epoch": 19.45, "learning_rate": 9.177183344328097e-05, "loss": 0.0584, "step": 81050 }, { "epoch": 19.45, "learning_rate": 9.176986055498149e-05, "loss": 0.0737, "step": 81060 }, { "epoch": 19.45, "learning_rate": 9.176788745139978e-05, "loss": 0.0727, "step": 81070 }, { "epoch": 19.45, "learning_rate": 9.176591413254603e-05, "loss": 0.0585, "step": 81080 }, { "epoch": 19.46, "learning_rate": 9.176394059843042e-05, "loss": 0.0644, "step": 81090 }, { "epoch": 19.46, "learning_rate": 9.176196684906311e-05, "loss": 0.0641, "step": 81100 }, { "epoch": 19.46, "learning_rate": 9.175999288445426e-05, "loss": 0.1048, "step": 81110 }, { "epoch": 19.46, "learning_rate": 9.175801870461407e-05, "loss": 0.0566, "step": 81120 }, { "epoch": 19.46, "learning_rate": 9.17560443095527e-05, "loss": 0.0723, "step": 81130 }, { "epoch": 19.47, "learning_rate": 9.175406969928033e-05, "loss": 0.048, "step": 81140 }, { "epoch": 19.47, "learning_rate": 9.175209487380713e-05, "loss": 0.0366, "step": 81150 }, { "epoch": 19.47, "learning_rate": 9.175011983314328e-05, "loss": 0.0942, "step": 81160 }, { "epoch": 19.47, "learning_rate": 9.174814457729896e-05, "loss": 0.0602, "step": 81170 }, { "epoch": 19.48, "learning_rate": 9.174616910628438e-05, "loss": 0.0941, "step": 81180 }, { "epoch": 19.48, "learning_rate": 9.174419342010968e-05, "loss": 0.0797, "step": 81190 }, { "epoch": 19.48, "learning_rate": 9.174221751878505e-05, "loss": 0.0587, "step": 81200 }, { "epoch": 19.48, "learning_rate": 9.17402414023207e-05, "loss": 0.0838, "step": 81210 }, { "epoch": 19.49, "learning_rate": 9.173826507072678e-05, "loss": 0.0753, "step": 81220 }, { "epoch": 19.49, "learning_rate": 9.173628852401351e-05, "loss": 0.0607, "step": 81230 }, { "epoch": 19.49, "learning_rate": 9.173431176219104e-05, "loss": 0.0559, "step": 81240 }, { "epoch": 19.49, "learning_rate": 9.17323347852696e-05, "loss": 0.0607, "step": 81250 }, { "epoch": 19.49, "learning_rate": 9.173035759325933e-05, "loss": 0.0669, "step": 81260 }, { "epoch": 19.5, "learning_rate": 9.172838018617047e-05, "loss": 0.1161, "step": 81270 }, { "epoch": 19.5, "learning_rate": 9.172640256401318e-05, "loss": 0.0538, "step": 81280 }, { "epoch": 19.5, "learning_rate": 9.172442472679767e-05, "loss": 0.0655, "step": 81290 }, { "epoch": 19.5, "learning_rate": 9.172244667453411e-05, "loss": 0.0854, "step": 81300 }, { "epoch": 19.51, "learning_rate": 9.172046840723273e-05, "loss": 0.087, "step": 81310 }, { "epoch": 19.51, "learning_rate": 9.171848992490371e-05, "loss": 0.0573, "step": 81320 }, { "epoch": 19.51, "learning_rate": 9.171651122755722e-05, "loss": 0.0543, "step": 81330 }, { "epoch": 19.51, "learning_rate": 9.171453231520351e-05, "loss": 0.0552, "step": 81340 }, { "epoch": 19.51, "learning_rate": 9.171255318785272e-05, "loss": 0.0775, "step": 81350 }, { "epoch": 19.52, "learning_rate": 9.171057384551511e-05, "loss": 0.0569, "step": 81360 }, { "epoch": 19.52, "learning_rate": 9.170859428820084e-05, "loss": 0.0706, "step": 81370 }, { "epoch": 19.52, "learning_rate": 9.170661451592013e-05, "loss": 0.0741, "step": 81380 }, { "epoch": 19.52, "learning_rate": 9.170463452868319e-05, "loss": 0.0877, "step": 81390 }, { "epoch": 19.53, "learning_rate": 9.17026543265002e-05, "loss": 0.0773, "step": 81400 }, { "epoch": 19.53, "learning_rate": 9.170067390938139e-05, "loss": 0.0682, "step": 81410 }, { "epoch": 19.53, "learning_rate": 9.169869327733696e-05, "loss": 0.053, "step": 81420 }, { "epoch": 19.53, "learning_rate": 9.169671243037711e-05, "loss": 0.1014, "step": 81430 }, { "epoch": 19.54, "learning_rate": 9.169473136851205e-05, "loss": 0.0744, "step": 81440 }, { "epoch": 19.54, "learning_rate": 9.1692750091752e-05, "loss": 0.0918, "step": 81450 }, { "epoch": 19.54, "learning_rate": 9.169076860010718e-05, "loss": 0.1011, "step": 81460 }, { "epoch": 19.54, "learning_rate": 9.168878689358777e-05, "loss": 0.1052, "step": 81470 }, { "epoch": 19.54, "learning_rate": 9.168680497220404e-05, "loss": 0.1152, "step": 81480 }, { "epoch": 19.55, "learning_rate": 9.168482283596614e-05, "loss": 0.1232, "step": 81490 }, { "epoch": 19.55, "learning_rate": 9.168284048488431e-05, "loss": 0.1173, "step": 81500 }, { "epoch": 19.55, "learning_rate": 9.168085791896878e-05, "loss": 0.1021, "step": 81510 }, { "epoch": 19.55, "learning_rate": 9.167887513822976e-05, "loss": 0.1152, "step": 81520 }, { "epoch": 19.56, "learning_rate": 9.167689214267748e-05, "loss": 0.0994, "step": 81530 }, { "epoch": 19.56, "learning_rate": 9.167490893232214e-05, "loss": 0.0576, "step": 81540 }, { "epoch": 19.56, "learning_rate": 9.167292550717396e-05, "loss": 0.1242, "step": 81550 }, { "epoch": 19.56, "learning_rate": 9.167094186724318e-05, "loss": 0.1058, "step": 81560 }, { "epoch": 19.57, "learning_rate": 9.166895801254002e-05, "loss": 0.1477, "step": 81570 }, { "epoch": 19.57, "learning_rate": 9.166697394307471e-05, "loss": 0.0563, "step": 81580 }, { "epoch": 19.57, "learning_rate": 9.166498965885746e-05, "loss": 0.0915, "step": 81590 }, { "epoch": 19.57, "learning_rate": 9.16630051598985e-05, "loss": 0.1052, "step": 81600 }, { "epoch": 19.57, "learning_rate": 9.166102044620807e-05, "loss": 0.1392, "step": 81610 }, { "epoch": 19.58, "learning_rate": 9.165903551779638e-05, "loss": 0.1015, "step": 81620 }, { "epoch": 19.58, "learning_rate": 9.165705037467369e-05, "loss": 0.1582, "step": 81630 }, { "epoch": 19.58, "learning_rate": 9.165506501685022e-05, "loss": 0.1047, "step": 81640 }, { "epoch": 19.58, "learning_rate": 9.165307944433617e-05, "loss": 0.157, "step": 81650 }, { "epoch": 19.59, "learning_rate": 9.165109365714182e-05, "loss": 0.1062, "step": 81660 }, { "epoch": 19.59, "learning_rate": 9.164910765527738e-05, "loss": 0.1164, "step": 81670 }, { "epoch": 19.59, "learning_rate": 9.16471214387531e-05, "loss": 0.0941, "step": 81680 }, { "epoch": 19.59, "learning_rate": 9.164513500757918e-05, "loss": 0.0896, "step": 81690 }, { "epoch": 19.59, "learning_rate": 9.164314836176592e-05, "loss": 0.0946, "step": 81700 }, { "epoch": 19.6, "learning_rate": 9.164116150132352e-05, "loss": 0.0783, "step": 81710 }, { "epoch": 19.6, "learning_rate": 9.163917442626219e-05, "loss": 0.101, "step": 81720 }, { "epoch": 19.6, "learning_rate": 9.163718713659224e-05, "loss": 0.0921, "step": 81730 }, { "epoch": 19.6, "learning_rate": 9.163519963232388e-05, "loss": 0.1195, "step": 81740 }, { "epoch": 19.61, "learning_rate": 9.163321191346735e-05, "loss": 0.1434, "step": 81750 }, { "epoch": 19.61, "learning_rate": 9.163122398003289e-05, "loss": 0.0889, "step": 81760 }, { "epoch": 19.61, "learning_rate": 9.162923583203076e-05, "loss": 0.0819, "step": 81770 }, { "epoch": 19.61, "learning_rate": 9.16272474694712e-05, "loss": 0.0849, "step": 81780 }, { "epoch": 19.62, "learning_rate": 9.162525889236445e-05, "loss": 0.0799, "step": 81790 }, { "epoch": 19.62, "learning_rate": 9.162327010072079e-05, "loss": 0.0799, "step": 81800 }, { "epoch": 19.62, "learning_rate": 9.162128109455041e-05, "loss": 0.1159, "step": 81810 }, { "epoch": 19.62, "learning_rate": 9.161929187386362e-05, "loss": 0.0597, "step": 81820 }, { "epoch": 19.62, "learning_rate": 9.161730243867067e-05, "loss": 0.0784, "step": 81830 }, { "epoch": 19.63, "learning_rate": 9.161531278898176e-05, "loss": 0.0984, "step": 81840 }, { "epoch": 19.63, "learning_rate": 9.161332292480721e-05, "loss": 0.1091, "step": 81850 }, { "epoch": 19.63, "learning_rate": 9.161133284615724e-05, "loss": 0.0607, "step": 81860 }, { "epoch": 19.63, "learning_rate": 9.16093425530421e-05, "loss": 0.0887, "step": 81870 }, { "epoch": 19.64, "learning_rate": 9.160735204547206e-05, "loss": 0.1083, "step": 81880 }, { "epoch": 19.64, "learning_rate": 9.160536132345739e-05, "loss": 0.1026, "step": 81890 }, { "epoch": 19.64, "learning_rate": 9.160337038700835e-05, "loss": 0.0902, "step": 81900 }, { "epoch": 19.64, "learning_rate": 9.160137923613516e-05, "loss": 0.0726, "step": 81910 }, { "epoch": 19.65, "learning_rate": 9.159938787084814e-05, "loss": 0.1115, "step": 81920 }, { "epoch": 19.65, "learning_rate": 9.159739629115753e-05, "loss": 0.0717, "step": 81930 }, { "epoch": 19.65, "learning_rate": 9.159540449707358e-05, "loss": 0.1004, "step": 81940 }, { "epoch": 19.65, "learning_rate": 9.159341248860656e-05, "loss": 0.1122, "step": 81950 }, { "epoch": 19.65, "learning_rate": 9.159142026576675e-05, "loss": 0.0661, "step": 81960 }, { "epoch": 19.66, "learning_rate": 9.158942782856443e-05, "loss": 0.0695, "step": 81970 }, { "epoch": 19.66, "learning_rate": 9.158743517700983e-05, "loss": 0.076, "step": 81980 }, { "epoch": 19.66, "learning_rate": 9.158544231111324e-05, "loss": 0.0737, "step": 81990 }, { "epoch": 19.66, "learning_rate": 9.158344923088496e-05, "loss": 0.0966, "step": 82000 }, { "epoch": 19.67, "learning_rate": 9.15814559363352e-05, "loss": 0.0762, "step": 82010 }, { "epoch": 19.67, "learning_rate": 9.157946242747428e-05, "loss": 0.0621, "step": 82020 }, { "epoch": 19.67, "learning_rate": 9.157746870431247e-05, "loss": 0.0691, "step": 82030 }, { "epoch": 19.67, "learning_rate": 9.157547476686005e-05, "loss": 0.0698, "step": 82040 }, { "epoch": 19.67, "learning_rate": 9.157348061512727e-05, "loss": 0.1137, "step": 82050 }, { "epoch": 19.68, "learning_rate": 9.157148624912442e-05, "loss": 0.0929, "step": 82060 }, { "epoch": 19.68, "learning_rate": 9.15694916688618e-05, "loss": 0.0478, "step": 82070 }, { "epoch": 19.68, "learning_rate": 9.156749687434965e-05, "loss": 0.0836, "step": 82080 }, { "epoch": 19.68, "learning_rate": 9.15655018655983e-05, "loss": 0.1083, "step": 82090 }, { "epoch": 19.69, "learning_rate": 9.156350664261797e-05, "loss": 0.0615, "step": 82100 }, { "epoch": 19.69, "learning_rate": 9.1561511205419e-05, "loss": 0.0908, "step": 82110 }, { "epoch": 19.69, "learning_rate": 9.155951555401165e-05, "loss": 0.0893, "step": 82120 }, { "epoch": 19.69, "learning_rate": 9.155751968840622e-05, "loss": 0.067, "step": 82130 }, { "epoch": 19.7, "learning_rate": 9.155552360861298e-05, "loss": 0.0945, "step": 82140 }, { "epoch": 19.7, "learning_rate": 9.155352731464222e-05, "loss": 0.0906, "step": 82150 }, { "epoch": 19.7, "learning_rate": 9.155153080650424e-05, "loss": 0.0568, "step": 82160 }, { "epoch": 19.7, "learning_rate": 9.154953408420933e-05, "loss": 0.0766, "step": 82170 }, { "epoch": 19.7, "learning_rate": 9.154753714776775e-05, "loss": 0.0889, "step": 82180 }, { "epoch": 19.71, "learning_rate": 9.154553999718982e-05, "loss": 0.0845, "step": 82190 }, { "epoch": 19.71, "learning_rate": 9.154354263248585e-05, "loss": 0.0907, "step": 82200 }, { "epoch": 19.71, "learning_rate": 9.15415450536661e-05, "loss": 0.1014, "step": 82210 }, { "epoch": 19.71, "learning_rate": 9.153954726074088e-05, "loss": 0.0657, "step": 82220 }, { "epoch": 19.72, "learning_rate": 9.153754925372048e-05, "loss": 0.09, "step": 82230 }, { "epoch": 19.72, "learning_rate": 9.153555103261522e-05, "loss": 0.0632, "step": 82240 }, { "epoch": 19.72, "learning_rate": 9.153355259743537e-05, "loss": 0.1107, "step": 82250 }, { "epoch": 19.72, "learning_rate": 9.153155394819126e-05, "loss": 0.1083, "step": 82260 }, { "epoch": 19.73, "learning_rate": 9.152955508489315e-05, "loss": 0.0586, "step": 82270 }, { "epoch": 19.73, "learning_rate": 9.152755600755138e-05, "loss": 0.095, "step": 82280 }, { "epoch": 19.73, "learning_rate": 9.152555671617624e-05, "loss": 0.0751, "step": 82290 }, { "epoch": 19.73, "learning_rate": 9.152355721077803e-05, "loss": 0.0665, "step": 82300 }, { "epoch": 19.73, "learning_rate": 9.152155749136706e-05, "loss": 0.0705, "step": 82310 }, { "epoch": 19.74, "learning_rate": 9.151955755795363e-05, "loss": 0.0765, "step": 82320 }, { "epoch": 19.74, "learning_rate": 9.151755741054806e-05, "loss": 0.1028, "step": 82330 }, { "epoch": 19.74, "learning_rate": 9.151555704916066e-05, "loss": 0.1134, "step": 82340 }, { "epoch": 19.74, "learning_rate": 9.15135564738017e-05, "loss": 0.0635, "step": 82350 }, { "epoch": 19.75, "learning_rate": 9.151155568448157e-05, "loss": 0.0735, "step": 82360 }, { "epoch": 19.75, "learning_rate": 9.15095546812105e-05, "loss": 0.0606, "step": 82370 }, { "epoch": 19.75, "learning_rate": 9.150755346399885e-05, "loss": 0.0726, "step": 82380 }, { "epoch": 19.75, "learning_rate": 9.150555203285693e-05, "loss": 0.0961, "step": 82390 }, { "epoch": 19.75, "learning_rate": 9.150355038779504e-05, "loss": 0.0993, "step": 82400 }, { "epoch": 19.76, "learning_rate": 9.15015485288235e-05, "loss": 0.07, "step": 82410 }, { "epoch": 19.76, "learning_rate": 9.149954645595262e-05, "loss": 0.1012, "step": 82420 }, { "epoch": 19.76, "learning_rate": 9.149754416919276e-05, "loss": 0.0624, "step": 82430 }, { "epoch": 19.76, "learning_rate": 9.149554166855418e-05, "loss": 0.0778, "step": 82440 }, { "epoch": 19.77, "learning_rate": 9.149353895404727e-05, "loss": 0.0531, "step": 82450 }, { "epoch": 19.77, "learning_rate": 9.149153602568228e-05, "loss": 0.102, "step": 82460 }, { "epoch": 19.77, "learning_rate": 9.148953288346957e-05, "loss": 0.1056, "step": 82470 }, { "epoch": 19.77, "learning_rate": 9.148752952741948e-05, "loss": 0.1152, "step": 82480 }, { "epoch": 19.78, "learning_rate": 9.14855259575423e-05, "loss": 0.0629, "step": 82490 }, { "epoch": 19.78, "learning_rate": 9.148352217384838e-05, "loss": 0.0775, "step": 82500 }, { "epoch": 19.78, "learning_rate": 9.148151817634804e-05, "loss": 0.095, "step": 82510 }, { "epoch": 19.78, "learning_rate": 9.14795139650516e-05, "loss": 0.0908, "step": 82520 }, { "epoch": 19.78, "learning_rate": 9.147750953996941e-05, "loss": 0.0745, "step": 82530 }, { "epoch": 19.79, "learning_rate": 9.147550490111178e-05, "loss": 0.0945, "step": 82540 }, { "epoch": 19.79, "learning_rate": 9.147350004848905e-05, "loss": 0.0501, "step": 82550 }, { "epoch": 19.79, "learning_rate": 9.147149498211157e-05, "loss": 0.0683, "step": 82560 }, { "epoch": 19.79, "learning_rate": 9.146948970198963e-05, "loss": 0.0707, "step": 82570 }, { "epoch": 19.8, "learning_rate": 9.146748420813361e-05, "loss": 0.0889, "step": 82580 }, { "epoch": 19.8, "learning_rate": 9.146547850055384e-05, "loss": 0.0842, "step": 82590 }, { "epoch": 19.8, "learning_rate": 9.146347257926062e-05, "loss": 0.0762, "step": 82600 }, { "epoch": 19.8, "learning_rate": 9.146146644426434e-05, "loss": 0.0878, "step": 82610 }, { "epoch": 19.81, "learning_rate": 9.14594600955753e-05, "loss": 0.0463, "step": 82620 }, { "epoch": 19.81, "learning_rate": 9.145745353320387e-05, "loss": 0.0829, "step": 82630 }, { "epoch": 19.81, "learning_rate": 9.145544675716038e-05, "loss": 0.0638, "step": 82640 }, { "epoch": 19.81, "learning_rate": 9.145343976745515e-05, "loss": 0.065, "step": 82650 }, { "epoch": 19.81, "learning_rate": 9.145143256409856e-05, "loss": 0.0911, "step": 82660 }, { "epoch": 19.82, "learning_rate": 9.144942514710094e-05, "loss": 0.0725, "step": 82670 }, { "epoch": 19.82, "learning_rate": 9.144741751647263e-05, "loss": 0.0874, "step": 82680 }, { "epoch": 19.82, "learning_rate": 9.144540967222399e-05, "loss": 0.099, "step": 82690 }, { "epoch": 19.82, "learning_rate": 9.144340161436537e-05, "loss": 0.0813, "step": 82700 }, { "epoch": 19.83, "learning_rate": 9.14413933429071e-05, "loss": 0.1072, "step": 82710 }, { "epoch": 19.83, "learning_rate": 9.143938485785955e-05, "loss": 0.0725, "step": 82720 }, { "epoch": 19.83, "learning_rate": 9.143737615923305e-05, "loss": 0.0629, "step": 82730 }, { "epoch": 19.83, "learning_rate": 9.143536724703798e-05, "loss": 0.0807, "step": 82740 }, { "epoch": 19.83, "learning_rate": 9.143335812128468e-05, "loss": 0.0597, "step": 82750 }, { "epoch": 19.84, "learning_rate": 9.143134878198349e-05, "loss": 0.0576, "step": 82760 }, { "epoch": 19.84, "learning_rate": 9.14293392291448e-05, "loss": 0.0475, "step": 82770 }, { "epoch": 19.84, "learning_rate": 9.142732946277895e-05, "loss": 0.069, "step": 82780 }, { "epoch": 19.84, "learning_rate": 9.142531948289627e-05, "loss": 0.0922, "step": 82790 }, { "epoch": 19.85, "learning_rate": 9.142330928950718e-05, "loss": 0.0533, "step": 82800 }, { "epoch": 19.85, "learning_rate": 9.142129888262198e-05, "loss": 0.069, "step": 82810 }, { "epoch": 19.85, "learning_rate": 9.141928826225108e-05, "loss": 0.0919, "step": 82820 }, { "epoch": 19.85, "learning_rate": 9.141727742840483e-05, "loss": 0.0853, "step": 82830 }, { "epoch": 19.86, "learning_rate": 9.141526638109357e-05, "loss": 0.0773, "step": 82840 }, { "epoch": 19.86, "learning_rate": 9.141325512032768e-05, "loss": 0.0668, "step": 82850 }, { "epoch": 19.86, "learning_rate": 9.141124364611753e-05, "loss": 0.0491, "step": 82860 }, { "epoch": 19.86, "learning_rate": 9.140923195847348e-05, "loss": 0.0706, "step": 82870 }, { "epoch": 19.86, "learning_rate": 9.140722005740592e-05, "loss": 0.0627, "step": 82880 }, { "epoch": 19.87, "learning_rate": 9.140520794292518e-05, "loss": 0.0707, "step": 82890 }, { "epoch": 19.87, "learning_rate": 9.140319561504167e-05, "loss": 0.0714, "step": 82900 }, { "epoch": 19.87, "learning_rate": 9.140118307376573e-05, "loss": 0.0797, "step": 82910 }, { "epoch": 19.87, "learning_rate": 9.139917031910775e-05, "loss": 0.0601, "step": 82920 }, { "epoch": 19.88, "learning_rate": 9.13971573510781e-05, "loss": 0.1288, "step": 82930 }, { "epoch": 19.88, "learning_rate": 9.139514416968715e-05, "loss": 0.0991, "step": 82940 }, { "epoch": 19.88, "learning_rate": 9.139313077494529e-05, "loss": 0.0683, "step": 82950 }, { "epoch": 19.88, "learning_rate": 9.139111716686289e-05, "loss": 0.0635, "step": 82960 }, { "epoch": 19.89, "learning_rate": 9.138910334545032e-05, "loss": 0.1131, "step": 82970 }, { "epoch": 19.89, "learning_rate": 9.138708931071797e-05, "loss": 0.0859, "step": 82980 }, { "epoch": 19.89, "learning_rate": 9.138507506267621e-05, "loss": 0.049, "step": 82990 }, { "epoch": 19.89, "learning_rate": 9.138306060133544e-05, "loss": 0.0548, "step": 83000 }, { "epoch": 19.89, "learning_rate": 9.138104592670601e-05, "loss": 0.0728, "step": 83010 }, { "epoch": 19.9, "learning_rate": 9.137903103879833e-05, "loss": 0.0639, "step": 83020 }, { "epoch": 19.9, "learning_rate": 9.137701593762278e-05, "loss": 0.0554, "step": 83030 }, { "epoch": 19.9, "learning_rate": 9.137500062318976e-05, "loss": 0.0644, "step": 83040 }, { "epoch": 19.9, "learning_rate": 9.13729850955096e-05, "loss": 0.074, "step": 83050 }, { "epoch": 19.91, "learning_rate": 9.137096935459277e-05, "loss": 0.0568, "step": 83060 }, { "epoch": 19.91, "learning_rate": 9.13689534004496e-05, "loss": 0.0729, "step": 83070 }, { "epoch": 19.91, "learning_rate": 9.13669372330905e-05, "loss": 0.0631, "step": 83080 }, { "epoch": 19.91, "learning_rate": 9.136492085252587e-05, "loss": 0.0927, "step": 83090 }, { "epoch": 19.91, "learning_rate": 9.136290425876608e-05, "loss": 0.0691, "step": 83100 }, { "epoch": 19.92, "learning_rate": 9.136088745182154e-05, "loss": 0.0812, "step": 83110 }, { "epoch": 19.92, "learning_rate": 9.135887043170264e-05, "loss": 0.0839, "step": 83120 }, { "epoch": 19.92, "learning_rate": 9.135685319841978e-05, "loss": 0.0629, "step": 83130 }, { "epoch": 19.92, "learning_rate": 9.135483575198333e-05, "loss": 0.068, "step": 83140 }, { "epoch": 19.93, "learning_rate": 9.135281809240373e-05, "loss": 0.1224, "step": 83150 }, { "epoch": 19.93, "learning_rate": 9.135080021969137e-05, "loss": 0.0824, "step": 83160 }, { "epoch": 19.93, "learning_rate": 9.134878213385663e-05, "loss": 0.0835, "step": 83170 }, { "epoch": 19.93, "learning_rate": 9.134676383490992e-05, "loss": 0.05, "step": 83180 }, { "epoch": 19.94, "learning_rate": 9.134474532286164e-05, "loss": 0.0808, "step": 83190 }, { "epoch": 19.94, "learning_rate": 9.134272659772221e-05, "loss": 0.0862, "step": 83200 }, { "epoch": 19.94, "learning_rate": 9.1340707659502e-05, "loss": 0.0792, "step": 83210 }, { "epoch": 19.94, "learning_rate": 9.133868850821146e-05, "loss": 0.0681, "step": 83220 }, { "epoch": 19.94, "learning_rate": 9.133666914386096e-05, "loss": 0.0762, "step": 83230 }, { "epoch": 19.95, "learning_rate": 9.133464956646091e-05, "loss": 0.0662, "step": 83240 }, { "epoch": 19.95, "learning_rate": 9.133262977602175e-05, "loss": 0.0531, "step": 83250 }, { "epoch": 19.95, "learning_rate": 9.133060977255388e-05, "loss": 0.0787, "step": 83260 }, { "epoch": 20.0, "learning_rate": 9.132858955606769e-05, "loss": 0.0834, "step": 83270 }, { "epoch": 20.0, "learning_rate": 9.13265691265736e-05, "loss": 0.0783, "step": 83280 }, { "epoch": 20.01, "learning_rate": 9.132454848408203e-05, "loss": 0.0807, "step": 83290 }, { "epoch": 20.01, "learning_rate": 9.132252762860338e-05, "loss": 0.0798, "step": 83300 }, { "epoch": 20.01, "learning_rate": 9.13205065601481e-05, "loss": 0.0643, "step": 83310 }, { "epoch": 20.01, "learning_rate": 9.131848527872657e-05, "loss": 0.0648, "step": 83320 }, { "epoch": 20.02, "learning_rate": 9.131646378434921e-05, "loss": 0.065, "step": 83330 }, { "epoch": 20.02, "learning_rate": 9.131444207702648e-05, "loss": 0.049, "step": 83340 }, { "epoch": 20.02, "learning_rate": 9.131242015676875e-05, "loss": 0.0851, "step": 83350 }, { "epoch": 20.02, "learning_rate": 9.131039802358647e-05, "loss": 0.0829, "step": 83360 }, { "epoch": 20.03, "learning_rate": 9.130837567749004e-05, "loss": 0.053, "step": 83370 }, { "epoch": 20.03, "learning_rate": 9.13063531184899e-05, "loss": 0.0589, "step": 83380 }, { "epoch": 20.03, "learning_rate": 9.130433034659649e-05, "loss": 0.0782, "step": 83390 }, { "epoch": 20.03, "learning_rate": 9.13023073618202e-05, "loss": 0.0661, "step": 83400 }, { "epoch": 20.03, "learning_rate": 9.130028416417147e-05, "loss": 0.0626, "step": 83410 }, { "epoch": 20.04, "learning_rate": 9.129826075366073e-05, "loss": 0.0647, "step": 83420 }, { "epoch": 20.04, "learning_rate": 9.129623713029842e-05, "loss": 0.0786, "step": 83430 }, { "epoch": 20.04, "learning_rate": 9.129421329409495e-05, "loss": 0.0806, "step": 83440 }, { "epoch": 20.04, "learning_rate": 9.129218924506076e-05, "loss": 0.0725, "step": 83450 }, { "epoch": 20.05, "learning_rate": 9.129016498320628e-05, "loss": 0.0644, "step": 83460 }, { "epoch": 20.05, "learning_rate": 9.128814050854195e-05, "loss": 0.0798, "step": 83470 }, { "epoch": 20.05, "learning_rate": 9.12861158210782e-05, "loss": 0.0627, "step": 83480 }, { "epoch": 20.05, "learning_rate": 9.128409092082546e-05, "loss": 0.0906, "step": 83490 }, { "epoch": 20.05, "learning_rate": 9.128206580779418e-05, "loss": 0.0647, "step": 83500 }, { "epoch": 20.06, "learning_rate": 9.128004048199477e-05, "loss": 0.0847, "step": 83510 }, { "epoch": 20.06, "learning_rate": 9.127801494343771e-05, "loss": 0.0311, "step": 83520 }, { "epoch": 20.06, "learning_rate": 9.127598919213338e-05, "loss": 0.0543, "step": 83530 }, { "epoch": 20.06, "learning_rate": 9.127396322809229e-05, "loss": 0.0683, "step": 83540 }, { "epoch": 20.07, "learning_rate": 9.127193705132484e-05, "loss": 0.0867, "step": 83550 }, { "epoch": 20.07, "learning_rate": 9.126991066184148e-05, "loss": 0.0686, "step": 83560 }, { "epoch": 20.07, "learning_rate": 9.126788405965265e-05, "loss": 0.0685, "step": 83570 }, { "epoch": 20.07, "learning_rate": 9.12658572447688e-05, "loss": 0.0698, "step": 83580 }, { "epoch": 20.08, "learning_rate": 9.126383021720038e-05, "loss": 0.0574, "step": 83590 }, { "epoch": 20.08, "learning_rate": 9.126180297695783e-05, "loss": 0.0371, "step": 83600 }, { "epoch": 20.08, "learning_rate": 9.125977552405161e-05, "loss": 0.0721, "step": 83610 }, { "epoch": 20.08, "learning_rate": 9.125774785849216e-05, "loss": 0.0584, "step": 83620 }, { "epoch": 20.08, "learning_rate": 9.125571998028994e-05, "loss": 0.0667, "step": 83630 }, { "epoch": 20.09, "learning_rate": 9.125369188945539e-05, "loss": 0.0534, "step": 83640 }, { "epoch": 20.09, "learning_rate": 9.125166358599895e-05, "loss": 0.06, "step": 83650 }, { "epoch": 20.09, "learning_rate": 9.124963506993111e-05, "loss": 0.1133, "step": 83660 }, { "epoch": 20.09, "learning_rate": 9.12476063412623e-05, "loss": 0.0799, "step": 83670 }, { "epoch": 20.1, "learning_rate": 9.124557740000298e-05, "loss": 0.0597, "step": 83680 }, { "epoch": 20.1, "learning_rate": 9.124354824616362e-05, "loss": 0.0434, "step": 83690 }, { "epoch": 20.1, "learning_rate": 9.124151887975465e-05, "loss": 0.0741, "step": 83700 }, { "epoch": 20.1, "learning_rate": 9.123948930078656e-05, "loss": 0.0689, "step": 83710 }, { "epoch": 20.11, "learning_rate": 9.12374595092698e-05, "loss": 0.0472, "step": 83720 }, { "epoch": 20.11, "learning_rate": 9.123542950521482e-05, "loss": 0.0667, "step": 83730 }, { "epoch": 20.11, "learning_rate": 9.123339928863209e-05, "loss": 0.0505, "step": 83740 }, { "epoch": 20.11, "learning_rate": 9.123136885953208e-05, "loss": 0.0732, "step": 83750 }, { "epoch": 20.11, "learning_rate": 9.122933821792525e-05, "loss": 0.0788, "step": 83760 }, { "epoch": 20.12, "learning_rate": 9.122730736382207e-05, "loss": 0.0583, "step": 83770 }, { "epoch": 20.12, "learning_rate": 9.1225276297233e-05, "loss": 0.0721, "step": 83780 }, { "epoch": 20.12, "learning_rate": 9.122324501816852e-05, "loss": 0.0877, "step": 83790 }, { "epoch": 20.12, "learning_rate": 9.122121352663908e-05, "loss": 0.061, "step": 83800 }, { "epoch": 20.13, "learning_rate": 9.121918182265517e-05, "loss": 0.0646, "step": 83810 }, { "epoch": 20.13, "learning_rate": 9.121714990622723e-05, "loss": 0.0939, "step": 83820 }, { "epoch": 20.13, "learning_rate": 9.121511777736578e-05, "loss": 0.06, "step": 83830 }, { "epoch": 20.13, "learning_rate": 9.121308543608125e-05, "loss": 0.0689, "step": 83840 }, { "epoch": 20.13, "learning_rate": 9.121105288238415e-05, "loss": 0.0861, "step": 83850 }, { "epoch": 20.14, "learning_rate": 9.120902011628491e-05, "loss": 0.0506, "step": 83860 }, { "epoch": 20.14, "learning_rate": 9.120698713779408e-05, "loss": 0.0455, "step": 83870 }, { "epoch": 20.14, "learning_rate": 9.120495394692206e-05, "loss": 0.0445, "step": 83880 }, { "epoch": 20.14, "learning_rate": 9.120292054367937e-05, "loss": 0.0724, "step": 83890 }, { "epoch": 20.15, "learning_rate": 9.12008869280765e-05, "loss": 0.0703, "step": 83900 }, { "epoch": 20.15, "learning_rate": 9.119885310012389e-05, "loss": 0.0507, "step": 83910 }, { "epoch": 20.15, "learning_rate": 9.119681905983206e-05, "loss": 0.0623, "step": 83920 }, { "epoch": 20.15, "learning_rate": 9.119478480721148e-05, "loss": 0.0753, "step": 83930 }, { "epoch": 20.16, "learning_rate": 9.119275034227264e-05, "loss": 0.0888, "step": 83940 }, { "epoch": 20.16, "learning_rate": 9.119071566502599e-05, "loss": 0.0526, "step": 83950 }, { "epoch": 20.16, "learning_rate": 9.118868077548208e-05, "loss": 0.0728, "step": 83960 }, { "epoch": 20.16, "learning_rate": 9.118664567365136e-05, "loss": 0.0642, "step": 83970 }, { "epoch": 20.16, "learning_rate": 9.11846103595443e-05, "loss": 0.0543, "step": 83980 }, { "epoch": 20.17, "learning_rate": 9.118257483317146e-05, "loss": 0.0621, "step": 83990 }, { "epoch": 20.17, "learning_rate": 9.118053909454325e-05, "loss": 0.0614, "step": 84000 }, { "epoch": 20.17, "learning_rate": 9.11785031436702e-05, "loss": 0.1088, "step": 84010 }, { "epoch": 20.17, "learning_rate": 9.117646698056282e-05, "loss": 0.065, "step": 84020 }, { "epoch": 20.18, "learning_rate": 9.117443060523157e-05, "loss": 0.0822, "step": 84030 }, { "epoch": 20.18, "learning_rate": 9.117239401768695e-05, "loss": 0.0545, "step": 84040 }, { "epoch": 20.18, "learning_rate": 9.117035721793947e-05, "loss": 0.0985, "step": 84050 }, { "epoch": 20.18, "learning_rate": 9.116832020599963e-05, "loss": 0.0436, "step": 84060 }, { "epoch": 20.19, "learning_rate": 9.116628298187794e-05, "loss": 0.0578, "step": 84070 }, { "epoch": 20.19, "learning_rate": 9.116424554558487e-05, "loss": 0.1054, "step": 84080 }, { "epoch": 20.19, "learning_rate": 9.116220789713094e-05, "loss": 0.0468, "step": 84090 }, { "epoch": 20.19, "learning_rate": 9.116017003652664e-05, "loss": 0.0864, "step": 84100 }, { "epoch": 20.19, "learning_rate": 9.115813196378248e-05, "loss": 0.0309, "step": 84110 }, { "epoch": 20.2, "learning_rate": 9.115609367890896e-05, "loss": 0.0714, "step": 84120 }, { "epoch": 20.2, "learning_rate": 9.11540551819166e-05, "loss": 0.0837, "step": 84130 }, { "epoch": 20.2, "learning_rate": 9.115201647281588e-05, "loss": 0.0844, "step": 84140 }, { "epoch": 20.2, "learning_rate": 9.114997755161734e-05, "loss": 0.0901, "step": 84150 }, { "epoch": 20.21, "learning_rate": 9.114793841833146e-05, "loss": 0.0641, "step": 84160 }, { "epoch": 20.21, "learning_rate": 9.114589907296877e-05, "loss": 0.0695, "step": 84170 }, { "epoch": 20.21, "learning_rate": 9.114385951553976e-05, "loss": 0.079, "step": 84180 }, { "epoch": 20.21, "learning_rate": 9.114181974605497e-05, "loss": 0.0716, "step": 84190 }, { "epoch": 20.21, "learning_rate": 9.113977976452488e-05, "loss": 0.0965, "step": 84200 }, { "epoch": 20.22, "learning_rate": 9.113773957096003e-05, "loss": 0.0873, "step": 84210 }, { "epoch": 20.22, "learning_rate": 9.113569916537093e-05, "loss": 0.0657, "step": 84220 }, { "epoch": 20.22, "learning_rate": 9.11336585477681e-05, "loss": 0.0777, "step": 84230 }, { "epoch": 20.22, "learning_rate": 9.113161771816203e-05, "loss": 0.0424, "step": 84240 }, { "epoch": 20.23, "learning_rate": 9.112957667656326e-05, "loss": 0.1005, "step": 84250 }, { "epoch": 20.23, "learning_rate": 9.112753542298233e-05, "loss": 0.0597, "step": 84260 }, { "epoch": 20.23, "learning_rate": 9.112549395742972e-05, "loss": 0.0603, "step": 84270 }, { "epoch": 20.23, "learning_rate": 9.112345227991598e-05, "loss": 0.064, "step": 84280 }, { "epoch": 20.24, "learning_rate": 9.112141039045161e-05, "loss": 0.0479, "step": 84290 }, { "epoch": 20.24, "learning_rate": 9.111936828904716e-05, "loss": 0.118, "step": 84300 }, { "epoch": 20.24, "learning_rate": 9.111732597571314e-05, "loss": 0.0448, "step": 84310 }, { "epoch": 20.24, "learning_rate": 9.111528345046008e-05, "loss": 0.085, "step": 84320 }, { "epoch": 20.24, "learning_rate": 9.11132407132985e-05, "loss": 0.0653, "step": 84330 }, { "epoch": 20.25, "learning_rate": 9.111119776423893e-05, "loss": 0.0899, "step": 84340 }, { "epoch": 20.25, "learning_rate": 9.11091546032919e-05, "loss": 0.0509, "step": 84350 }, { "epoch": 20.25, "learning_rate": 9.110711123046796e-05, "loss": 0.0562, "step": 84360 }, { "epoch": 20.25, "learning_rate": 9.110506764577761e-05, "loss": 0.0525, "step": 84370 }, { "epoch": 20.26, "learning_rate": 9.110302384923141e-05, "loss": 0.0824, "step": 84380 }, { "epoch": 20.26, "learning_rate": 9.110097984083987e-05, "loss": 0.0579, "step": 84390 }, { "epoch": 20.26, "learning_rate": 9.109893562061354e-05, "loss": 0.0585, "step": 84400 }, { "epoch": 20.26, "learning_rate": 9.109689118856297e-05, "loss": 0.0674, "step": 84410 }, { "epoch": 20.27, "learning_rate": 9.109484654469866e-05, "loss": 0.1074, "step": 84420 }, { "epoch": 20.27, "learning_rate": 9.109280168903116e-05, "loss": 0.0613, "step": 84430 }, { "epoch": 20.27, "learning_rate": 9.109075662157103e-05, "loss": 0.0624, "step": 84440 }, { "epoch": 20.27, "learning_rate": 9.10887113423288e-05, "loss": 0.0506, "step": 84450 }, { "epoch": 20.27, "learning_rate": 9.1086665851315e-05, "loss": 0.056, "step": 84460 }, { "epoch": 20.28, "learning_rate": 9.108462014854018e-05, "loss": 0.0778, "step": 84470 }, { "epoch": 20.28, "learning_rate": 9.108257423401489e-05, "loss": 0.0602, "step": 84480 }, { "epoch": 20.28, "learning_rate": 9.108052810774967e-05, "loss": 0.0458, "step": 84490 }, { "epoch": 20.28, "learning_rate": 9.107848176975507e-05, "loss": 0.0958, "step": 84500 }, { "epoch": 20.29, "learning_rate": 9.107643522004161e-05, "loss": 0.0474, "step": 84510 }, { "epoch": 20.29, "learning_rate": 9.107438845861987e-05, "loss": 0.1075, "step": 84520 }, { "epoch": 20.29, "learning_rate": 9.107234148550038e-05, "loss": 0.088, "step": 84530 }, { "epoch": 20.29, "learning_rate": 9.107029430069373e-05, "loss": 0.0661, "step": 84540 }, { "epoch": 20.29, "learning_rate": 9.106824690421042e-05, "loss": 0.0604, "step": 84550 }, { "epoch": 20.3, "learning_rate": 9.106619929606102e-05, "loss": 0.0733, "step": 84560 }, { "epoch": 20.3, "learning_rate": 9.106415147625609e-05, "loss": 0.0408, "step": 84570 }, { "epoch": 20.3, "learning_rate": 9.106210344480616e-05, "loss": 0.0636, "step": 84580 }, { "epoch": 20.3, "learning_rate": 9.106005520172184e-05, "loss": 0.0675, "step": 84590 }, { "epoch": 20.31, "learning_rate": 9.105800674701364e-05, "loss": 0.0546, "step": 84600 }, { "epoch": 20.31, "learning_rate": 9.105595808069212e-05, "loss": 0.0676, "step": 84610 }, { "epoch": 20.31, "learning_rate": 9.105390920276787e-05, "loss": 0.1032, "step": 84620 }, { "epoch": 20.31, "learning_rate": 9.10518601132514e-05, "loss": 0.0536, "step": 84630 }, { "epoch": 20.32, "learning_rate": 9.104981081215331e-05, "loss": 0.066, "step": 84640 }, { "epoch": 20.32, "learning_rate": 9.104776129948416e-05, "loss": 0.0501, "step": 84650 }, { "epoch": 20.32, "learning_rate": 9.10457115752545e-05, "loss": 0.0773, "step": 84660 }, { "epoch": 20.32, "learning_rate": 9.10436616394749e-05, "loss": 0.0603, "step": 84670 }, { "epoch": 20.32, "learning_rate": 9.104161149215593e-05, "loss": 0.0526, "step": 84680 }, { "epoch": 20.33, "learning_rate": 9.103956113330813e-05, "loss": 0.0648, "step": 84690 }, { "epoch": 20.33, "learning_rate": 9.103751056294212e-05, "loss": 0.0591, "step": 84700 }, { "epoch": 20.33, "learning_rate": 9.103545978106843e-05, "loss": 0.0886, "step": 84710 }, { "epoch": 20.33, "learning_rate": 9.103340878769762e-05, "loss": 0.083, "step": 84720 }, { "epoch": 20.34, "learning_rate": 9.103135758284028e-05, "loss": 0.0572, "step": 84730 }, { "epoch": 20.34, "learning_rate": 9.1029306166507e-05, "loss": 0.0461, "step": 84740 }, { "epoch": 20.34, "learning_rate": 9.10272545387083e-05, "loss": 0.0692, "step": 84750 }, { "epoch": 20.34, "learning_rate": 9.102520269945483e-05, "loss": 0.0802, "step": 84760 }, { "epoch": 20.35, "learning_rate": 9.102315064875709e-05, "loss": 0.0861, "step": 84770 }, { "epoch": 20.35, "learning_rate": 9.102109838662569e-05, "loss": 0.059, "step": 84780 }, { "epoch": 20.35, "learning_rate": 9.101904591307123e-05, "loss": 0.0548, "step": 84790 }, { "epoch": 20.35, "learning_rate": 9.101699322810424e-05, "loss": 0.0459, "step": 84800 }, { "epoch": 20.35, "learning_rate": 9.101494033173535e-05, "loss": 0.0851, "step": 84810 }, { "epoch": 20.36, "learning_rate": 9.101288722397509e-05, "loss": 0.0577, "step": 84820 }, { "epoch": 20.36, "learning_rate": 9.101083390483407e-05, "loss": 0.0606, "step": 84830 }, { "epoch": 20.36, "learning_rate": 9.100878037432288e-05, "loss": 0.0455, "step": 84840 }, { "epoch": 20.36, "learning_rate": 9.100672663245209e-05, "loss": 0.0508, "step": 84850 }, { "epoch": 20.37, "learning_rate": 9.100467267923227e-05, "loss": 0.062, "step": 84860 }, { "epoch": 20.37, "learning_rate": 9.100261851467404e-05, "loss": 0.0461, "step": 84870 }, { "epoch": 20.37, "learning_rate": 9.100056413878797e-05, "loss": 0.0522, "step": 84880 }, { "epoch": 20.37, "learning_rate": 9.099850955158465e-05, "loss": 0.0452, "step": 84890 }, { "epoch": 20.37, "learning_rate": 9.099645475307468e-05, "loss": 0.0531, "step": 84900 }, { "epoch": 20.38, "learning_rate": 9.099439974326863e-05, "loss": 0.0811, "step": 84910 }, { "epoch": 20.38, "learning_rate": 9.09923445221771e-05, "loss": 0.072, "step": 84920 }, { "epoch": 20.38, "learning_rate": 9.099028908981069e-05, "loss": 0.1019, "step": 84930 }, { "epoch": 20.38, "learning_rate": 9.098823344617997e-05, "loss": 0.0519, "step": 84940 }, { "epoch": 20.39, "learning_rate": 9.098617759129558e-05, "loss": 0.0509, "step": 84950 }, { "epoch": 20.39, "learning_rate": 9.098412152516807e-05, "loss": 0.0613, "step": 84960 }, { "epoch": 20.39, "learning_rate": 9.098206524780804e-05, "loss": 0.0538, "step": 84970 }, { "epoch": 20.39, "learning_rate": 9.098000875922612e-05, "loss": 0.0783, "step": 84980 }, { "epoch": 20.4, "learning_rate": 9.09779520594329e-05, "loss": 0.0478, "step": 84990 }, { "epoch": 20.4, "learning_rate": 9.097589514843896e-05, "loss": 0.0792, "step": 85000 }, { "epoch": 20.4, "learning_rate": 9.097383802625491e-05, "loss": 0.077, "step": 85010 }, { "epoch": 20.4, "learning_rate": 9.097178069289139e-05, "loss": 0.0584, "step": 85020 }, { "epoch": 20.4, "learning_rate": 9.096972314835895e-05, "loss": 0.0641, "step": 85030 }, { "epoch": 20.41, "learning_rate": 9.09676653926682e-05, "loss": 0.0368, "step": 85040 }, { "epoch": 20.41, "learning_rate": 9.096560742582976e-05, "loss": 0.0687, "step": 85050 }, { "epoch": 20.41, "learning_rate": 9.096354924785425e-05, "loss": 0.053, "step": 85060 }, { "epoch": 20.41, "learning_rate": 9.096149085875226e-05, "loss": 0.0589, "step": 85070 }, { "epoch": 20.42, "learning_rate": 9.095943225853441e-05, "loss": 0.0728, "step": 85080 }, { "epoch": 20.42, "learning_rate": 9.09573734472113e-05, "loss": 0.0609, "step": 85090 }, { "epoch": 20.42, "learning_rate": 9.095531442479355e-05, "loss": 0.0577, "step": 85100 }, { "epoch": 20.42, "learning_rate": 9.095325519129174e-05, "loss": 0.0687, "step": 85110 }, { "epoch": 20.43, "learning_rate": 9.095119574671653e-05, "loss": 0.0441, "step": 85120 }, { "epoch": 20.43, "learning_rate": 9.094913609107852e-05, "loss": 0.0759, "step": 85130 }, { "epoch": 20.43, "learning_rate": 9.094707622438831e-05, "loss": 0.0376, "step": 85140 }, { "epoch": 20.43, "learning_rate": 9.094501614665655e-05, "loss": 0.0635, "step": 85150 }, { "epoch": 20.43, "learning_rate": 9.094295585789381e-05, "loss": 0.082, "step": 85160 }, { "epoch": 20.44, "learning_rate": 9.094089535811074e-05, "loss": 0.0728, "step": 85170 }, { "epoch": 20.44, "learning_rate": 9.093883464731796e-05, "loss": 0.0723, "step": 85180 }, { "epoch": 20.44, "learning_rate": 9.093677372552607e-05, "loss": 0.0359, "step": 85190 }, { "epoch": 20.44, "learning_rate": 9.093471259274572e-05, "loss": 0.0431, "step": 85200 }, { "epoch": 20.45, "learning_rate": 9.093265124898751e-05, "loss": 0.0536, "step": 85210 }, { "epoch": 20.45, "learning_rate": 9.093058969426207e-05, "loss": 0.0525, "step": 85220 }, { "epoch": 20.45, "learning_rate": 9.092852792858004e-05, "loss": 0.0607, "step": 85230 }, { "epoch": 20.45, "learning_rate": 9.092646595195205e-05, "loss": 0.068, "step": 85240 }, { "epoch": 20.45, "learning_rate": 9.092440376438869e-05, "loss": 0.0292, "step": 85250 }, { "epoch": 20.46, "learning_rate": 9.092234136590062e-05, "loss": 0.1121, "step": 85260 }, { "epoch": 20.46, "learning_rate": 9.092027875649845e-05, "loss": 0.0497, "step": 85270 }, { "epoch": 20.46, "learning_rate": 9.091821593619281e-05, "loss": 0.0897, "step": 85280 }, { "epoch": 20.46, "learning_rate": 9.091615290499435e-05, "loss": 0.0565, "step": 85290 }, { "epoch": 20.47, "learning_rate": 9.091408966291372e-05, "loss": 0.0697, "step": 85300 }, { "epoch": 20.47, "learning_rate": 9.091202620996151e-05, "loss": 0.0787, "step": 85310 }, { "epoch": 20.47, "learning_rate": 9.090996254614838e-05, "loss": 0.0609, "step": 85320 }, { "epoch": 20.47, "learning_rate": 9.090789867148495e-05, "loss": 0.0818, "step": 85330 }, { "epoch": 20.48, "learning_rate": 9.090583458598189e-05, "loss": 0.0341, "step": 85340 }, { "epoch": 20.48, "learning_rate": 9.090377028964981e-05, "loss": 0.0477, "step": 85350 }, { "epoch": 20.48, "learning_rate": 9.090170578249934e-05, "loss": 0.0654, "step": 85360 }, { "epoch": 20.48, "learning_rate": 9.089964106454116e-05, "loss": 0.0402, "step": 85370 }, { "epoch": 20.48, "learning_rate": 9.089757613578587e-05, "loss": 0.0534, "step": 85380 }, { "epoch": 20.49, "learning_rate": 9.089551099624414e-05, "loss": 0.0568, "step": 85390 }, { "epoch": 20.49, "learning_rate": 9.089344564592659e-05, "loss": 0.0683, "step": 85400 }, { "epoch": 20.49, "learning_rate": 9.08913800848439e-05, "loss": 0.06, "step": 85410 }, { "epoch": 20.49, "learning_rate": 9.088931431300668e-05, "loss": 0.0756, "step": 85420 }, { "epoch": 20.5, "learning_rate": 9.088724833042559e-05, "loss": 0.0539, "step": 85430 }, { "epoch": 20.5, "learning_rate": 9.08851821371113e-05, "loss": 0.0372, "step": 85440 }, { "epoch": 20.5, "learning_rate": 9.088311573307441e-05, "loss": 0.0641, "step": 85450 }, { "epoch": 20.5, "learning_rate": 9.088104911832563e-05, "loss": 0.0759, "step": 85460 }, { "epoch": 20.51, "learning_rate": 9.087898229287557e-05, "loss": 0.0656, "step": 85470 }, { "epoch": 20.51, "learning_rate": 9.087691525673489e-05, "loss": 0.0491, "step": 85480 }, { "epoch": 20.51, "learning_rate": 9.087484800991425e-05, "loss": 0.068, "step": 85490 }, { "epoch": 20.51, "learning_rate": 9.08727805524243e-05, "loss": 0.052, "step": 85500 }, { "epoch": 20.51, "learning_rate": 9.08707128842757e-05, "loss": 0.0492, "step": 85510 }, { "epoch": 20.52, "learning_rate": 9.08686450054791e-05, "loss": 0.0628, "step": 85520 }, { "epoch": 20.52, "learning_rate": 9.086657691604516e-05, "loss": 0.0976, "step": 85530 }, { "epoch": 20.52, "learning_rate": 9.086450861598455e-05, "loss": 0.0443, "step": 85540 }, { "epoch": 20.52, "learning_rate": 9.086244010530792e-05, "loss": 0.0444, "step": 85550 }, { "epoch": 20.53, "learning_rate": 9.086037138402592e-05, "loss": 0.0483, "step": 85560 }, { "epoch": 20.53, "learning_rate": 9.085830245214924e-05, "loss": 0.07, "step": 85570 }, { "epoch": 20.53, "learning_rate": 9.085623330968852e-05, "loss": 0.0908, "step": 85580 }, { "epoch": 20.53, "learning_rate": 9.085416395665444e-05, "loss": 0.0917, "step": 85590 }, { "epoch": 20.53, "learning_rate": 9.085209439305764e-05, "loss": 0.0553, "step": 85600 }, { "epoch": 20.54, "learning_rate": 9.085002461890881e-05, "loss": 0.0825, "step": 85610 }, { "epoch": 20.54, "learning_rate": 9.084795463421862e-05, "loss": 0.1381, "step": 85620 }, { "epoch": 20.54, "learning_rate": 9.084588443899774e-05, "loss": 0.0993, "step": 85630 }, { "epoch": 20.54, "learning_rate": 9.084381403325681e-05, "loss": 0.0873, "step": 85640 }, { "epoch": 20.55, "learning_rate": 9.084174341700654e-05, "loss": 0.1009, "step": 85650 }, { "epoch": 20.55, "learning_rate": 9.083967259025757e-05, "loss": 0.0896, "step": 85660 }, { "epoch": 20.55, "learning_rate": 9.083760155302057e-05, "loss": 0.1086, "step": 85670 }, { "epoch": 20.55, "learning_rate": 9.083553030530625e-05, "loss": 0.1233, "step": 85680 }, { "epoch": 20.56, "learning_rate": 9.083345884712527e-05, "loss": 0.0925, "step": 85690 }, { "epoch": 20.56, "learning_rate": 9.08313871784883e-05, "loss": 0.114, "step": 85700 }, { "epoch": 20.56, "learning_rate": 9.082931529940599e-05, "loss": 0.0866, "step": 85710 }, { "epoch": 20.56, "learning_rate": 9.082724320988908e-05, "loss": 0.087, "step": 85720 }, { "epoch": 20.56, "learning_rate": 9.082517090994821e-05, "loss": 0.1082, "step": 85730 }, { "epoch": 20.57, "learning_rate": 9.082309839959406e-05, "loss": 0.0719, "step": 85740 }, { "epoch": 20.57, "learning_rate": 9.082102567883733e-05, "loss": 0.0693, "step": 85750 }, { "epoch": 20.57, "learning_rate": 9.081895274768868e-05, "loss": 0.0626, "step": 85760 }, { "epoch": 20.57, "learning_rate": 9.081687960615882e-05, "loss": 0.0943, "step": 85770 }, { "epoch": 20.58, "learning_rate": 9.081480625425843e-05, "loss": 0.1077, "step": 85780 }, { "epoch": 20.58, "learning_rate": 9.081273269199818e-05, "loss": 0.1131, "step": 85790 }, { "epoch": 20.58, "learning_rate": 9.081065891938873e-05, "loss": 0.099, "step": 85800 }, { "epoch": 20.58, "learning_rate": 9.080858493644084e-05, "loss": 0.0964, "step": 85810 }, { "epoch": 20.59, "learning_rate": 9.080651074316515e-05, "loss": 0.0901, "step": 85820 }, { "epoch": 20.59, "learning_rate": 9.080443633957236e-05, "loss": 0.1141, "step": 85830 }, { "epoch": 20.59, "learning_rate": 9.080236172567318e-05, "loss": 0.0621, "step": 85840 }, { "epoch": 20.59, "learning_rate": 9.080028690147828e-05, "loss": 0.101, "step": 85850 }, { "epoch": 20.59, "learning_rate": 9.079821186699834e-05, "loss": 0.079, "step": 85860 }, { "epoch": 20.6, "learning_rate": 9.079613662224409e-05, "loss": 0.1387, "step": 85870 }, { "epoch": 20.6, "learning_rate": 9.079406116722622e-05, "loss": 0.0793, "step": 85880 }, { "epoch": 20.6, "learning_rate": 9.079198550195541e-05, "loss": 0.1048, "step": 85890 }, { "epoch": 20.6, "learning_rate": 9.078990962644235e-05, "loss": 0.0948, "step": 85900 }, { "epoch": 20.61, "learning_rate": 9.078783354069779e-05, "loss": 0.0837, "step": 85910 }, { "epoch": 20.61, "learning_rate": 9.078575724473238e-05, "loss": 0.0978, "step": 85920 }, { "epoch": 20.61, "learning_rate": 9.078368073855683e-05, "loss": 0.1227, "step": 85930 }, { "epoch": 20.61, "learning_rate": 9.078160402218184e-05, "loss": 0.0644, "step": 85940 }, { "epoch": 20.61, "learning_rate": 9.077952709561815e-05, "loss": 0.0781, "step": 85950 }, { "epoch": 20.62, "learning_rate": 9.077744995887641e-05, "loss": 0.0632, "step": 85960 }, { "epoch": 20.62, "learning_rate": 9.077537261196736e-05, "loss": 0.0742, "step": 85970 }, { "epoch": 20.62, "learning_rate": 9.07732950549017e-05, "loss": 0.0842, "step": 85980 }, { "epoch": 20.62, "learning_rate": 9.077121728769014e-05, "loss": 0.0798, "step": 85990 }, { "epoch": 20.63, "learning_rate": 9.076913931034337e-05, "loss": 0.0776, "step": 86000 }, { "epoch": 20.63, "learning_rate": 9.076706112287214e-05, "loss": 0.0779, "step": 86010 }, { "epoch": 20.63, "learning_rate": 9.07649827252871e-05, "loss": 0.0822, "step": 86020 }, { "epoch": 20.63, "learning_rate": 9.076290411759903e-05, "loss": 0.1109, "step": 86030 }, { "epoch": 20.64, "learning_rate": 9.07608252998186e-05, "loss": 0.081, "step": 86040 }, { "epoch": 20.64, "learning_rate": 9.075874627195654e-05, "loss": 0.0797, "step": 86050 }, { "epoch": 20.64, "learning_rate": 9.075666703402357e-05, "loss": 0.0506, "step": 86060 }, { "epoch": 20.64, "learning_rate": 9.075458758603039e-05, "loss": 0.0947, "step": 86070 }, { "epoch": 20.64, "learning_rate": 9.07525079279877e-05, "loss": 0.0665, "step": 86080 }, { "epoch": 20.65, "learning_rate": 9.075042805990628e-05, "loss": 0.0981, "step": 86090 }, { "epoch": 20.65, "learning_rate": 9.074834798179679e-05, "loss": 0.0654, "step": 86100 }, { "epoch": 20.65, "learning_rate": 9.074626769366998e-05, "loss": 0.0705, "step": 86110 }, { "epoch": 20.65, "learning_rate": 9.074418719553656e-05, "loss": 0.0741, "step": 86120 }, { "epoch": 20.66, "learning_rate": 9.074210648740729e-05, "loss": 0.0688, "step": 86130 }, { "epoch": 20.66, "learning_rate": 9.074002556929283e-05, "loss": 0.086, "step": 86140 }, { "epoch": 20.66, "learning_rate": 9.073794444120395e-05, "loss": 0.0827, "step": 86150 }, { "epoch": 20.66, "learning_rate": 9.073586310315136e-05, "loss": 0.0867, "step": 86160 }, { "epoch": 20.66, "learning_rate": 9.073378155514578e-05, "loss": 0.0695, "step": 86170 }, { "epoch": 20.67, "learning_rate": 9.073169979719797e-05, "loss": 0.0647, "step": 86180 }, { "epoch": 20.67, "learning_rate": 9.072961782931862e-05, "loss": 0.0697, "step": 86190 }, { "epoch": 20.67, "learning_rate": 9.07275356515185e-05, "loss": 0.0906, "step": 86200 }, { "epoch": 20.67, "learning_rate": 9.07254532638083e-05, "loss": 0.0831, "step": 86210 }, { "epoch": 20.68, "learning_rate": 9.072337066619879e-05, "loss": 0.0881, "step": 86220 }, { "epoch": 20.68, "learning_rate": 9.072128785870069e-05, "loss": 0.0647, "step": 86230 }, { "epoch": 20.68, "learning_rate": 9.071920484132471e-05, "loss": 0.0673, "step": 86240 }, { "epoch": 20.68, "learning_rate": 9.071712161408162e-05, "loss": 0.0673, "step": 86250 }, { "epoch": 20.69, "learning_rate": 9.071503817698215e-05, "loss": 0.0677, "step": 86260 }, { "epoch": 20.69, "learning_rate": 9.071295453003702e-05, "loss": 0.0669, "step": 86270 }, { "epoch": 20.69, "learning_rate": 9.071087067325699e-05, "loss": 0.0451, "step": 86280 }, { "epoch": 20.69, "learning_rate": 9.07087866066528e-05, "loss": 0.0766, "step": 86290 }, { "epoch": 20.69, "learning_rate": 9.070670233023517e-05, "loss": 0.0421, "step": 86300 }, { "epoch": 20.7, "learning_rate": 9.070461784401487e-05, "loss": 0.0797, "step": 86310 }, { "epoch": 20.7, "learning_rate": 9.070253314800261e-05, "loss": 0.0893, "step": 86320 }, { "epoch": 20.7, "learning_rate": 9.070044824220917e-05, "loss": 0.0845, "step": 86330 }, { "epoch": 20.7, "learning_rate": 9.069836312664528e-05, "loss": 0.1002, "step": 86340 }, { "epoch": 20.71, "learning_rate": 9.069627780132169e-05, "loss": 0.0784, "step": 86350 }, { "epoch": 20.71, "learning_rate": 9.069419226624913e-05, "loss": 0.0653, "step": 86360 }, { "epoch": 20.71, "learning_rate": 9.069210652143836e-05, "loss": 0.0732, "step": 86370 }, { "epoch": 20.71, "learning_rate": 9.069002056690015e-05, "loss": 0.0718, "step": 86380 }, { "epoch": 20.72, "learning_rate": 9.068793440264522e-05, "loss": 0.0996, "step": 86390 }, { "epoch": 20.72, "learning_rate": 9.068584802868433e-05, "loss": 0.0785, "step": 86400 }, { "epoch": 20.72, "learning_rate": 9.068376144502826e-05, "loss": 0.0656, "step": 86410 }, { "epoch": 20.72, "learning_rate": 9.068167465168773e-05, "loss": 0.096, "step": 86420 }, { "epoch": 20.72, "learning_rate": 9.067958764867351e-05, "loss": 0.0568, "step": 86430 }, { "epoch": 20.73, "learning_rate": 9.067750043599637e-05, "loss": 0.0732, "step": 86440 }, { "epoch": 20.73, "learning_rate": 9.067541301366703e-05, "loss": 0.0811, "step": 86450 }, { "epoch": 20.73, "learning_rate": 9.067332538169628e-05, "loss": 0.0689, "step": 86460 }, { "epoch": 20.73, "learning_rate": 9.067123754009488e-05, "loss": 0.1065, "step": 86470 }, { "epoch": 20.74, "learning_rate": 9.066914948887357e-05, "loss": 0.0738, "step": 86480 }, { "epoch": 20.74, "learning_rate": 9.066706122804312e-05, "loss": 0.0673, "step": 86490 }, { "epoch": 20.74, "learning_rate": 9.066497275761433e-05, "loss": 0.053, "step": 86500 }, { "epoch": 20.74, "learning_rate": 9.066288407759789e-05, "loss": 0.0914, "step": 86510 }, { "epoch": 20.74, "learning_rate": 9.066079518800462e-05, "loss": 0.051, "step": 86520 }, { "epoch": 20.75, "learning_rate": 9.065870608884527e-05, "loss": 0.0611, "step": 86530 }, { "epoch": 20.75, "learning_rate": 9.065661678013061e-05, "loss": 0.05, "step": 86540 }, { "epoch": 20.75, "learning_rate": 9.06545272618714e-05, "loss": 0.0972, "step": 86550 }, { "epoch": 20.75, "learning_rate": 9.065243753407844e-05, "loss": 0.091, "step": 86560 }, { "epoch": 20.76, "learning_rate": 9.065034759676246e-05, "loss": 0.0548, "step": 86570 }, { "epoch": 20.76, "learning_rate": 9.064825744993425e-05, "loss": 0.108, "step": 86580 }, { "epoch": 20.76, "learning_rate": 9.064616709360458e-05, "loss": 0.0805, "step": 86590 }, { "epoch": 20.76, "learning_rate": 9.064407652778423e-05, "loss": 0.0776, "step": 86600 }, { "epoch": 20.77, "learning_rate": 9.064198575248397e-05, "loss": 0.0418, "step": 86610 }, { "epoch": 20.77, "learning_rate": 9.063989476771458e-05, "loss": 0.0678, "step": 86620 }, { "epoch": 20.77, "learning_rate": 9.063780357348681e-05, "loss": 0.0649, "step": 86630 }, { "epoch": 20.77, "learning_rate": 9.063571216981149e-05, "loss": 0.09, "step": 86640 }, { "epoch": 20.77, "learning_rate": 9.063362055669935e-05, "loss": 0.0964, "step": 86650 }, { "epoch": 20.78, "learning_rate": 9.063152873416118e-05, "loss": 0.0796, "step": 86660 }, { "epoch": 20.78, "learning_rate": 9.06294367022078e-05, "loss": 0.101, "step": 86670 }, { "epoch": 20.78, "learning_rate": 9.062734446084995e-05, "loss": 0.0412, "step": 86680 }, { "epoch": 20.78, "learning_rate": 9.062525201009842e-05, "loss": 0.0793, "step": 86690 }, { "epoch": 20.79, "learning_rate": 9.062315934996401e-05, "loss": 0.0511, "step": 86700 }, { "epoch": 20.79, "learning_rate": 9.062106648045749e-05, "loss": 0.0773, "step": 86710 }, { "epoch": 20.79, "learning_rate": 9.061897340158967e-05, "loss": 0.0759, "step": 86720 }, { "epoch": 20.79, "learning_rate": 9.06168801133713e-05, "loss": 0.0729, "step": 86730 }, { "epoch": 20.8, "learning_rate": 9.061478661581321e-05, "loss": 0.0908, "step": 86740 }, { "epoch": 20.8, "learning_rate": 9.061269290892618e-05, "loss": 0.049, "step": 86750 }, { "epoch": 20.8, "learning_rate": 9.061059899272096e-05, "loss": 0.0782, "step": 86760 }, { "epoch": 20.8, "learning_rate": 9.06085048672084e-05, "loss": 0.0652, "step": 86770 }, { "epoch": 20.8, "learning_rate": 9.060641053239925e-05, "loss": 0.048, "step": 86780 }, { "epoch": 20.81, "learning_rate": 9.060431598830432e-05, "loss": 0.0619, "step": 86790 }, { "epoch": 20.81, "learning_rate": 9.060222123493441e-05, "loss": 0.0664, "step": 86800 }, { "epoch": 20.81, "learning_rate": 9.060012627230031e-05, "loss": 0.0367, "step": 86810 }, { "epoch": 20.81, "learning_rate": 9.059803110041283e-05, "loss": 0.0585, "step": 86820 }, { "epoch": 20.82, "learning_rate": 9.059593571928276e-05, "loss": 0.0767, "step": 86830 }, { "epoch": 20.82, "learning_rate": 9.059384012892088e-05, "loss": 0.0648, "step": 86840 }, { "epoch": 20.82, "learning_rate": 9.0591744329338e-05, "loss": 0.0813, "step": 86850 }, { "epoch": 20.82, "learning_rate": 9.058964832054496e-05, "loss": 0.1101, "step": 86860 }, { "epoch": 20.82, "learning_rate": 9.058755210255252e-05, "loss": 0.0925, "step": 86870 }, { "epoch": 20.83, "learning_rate": 9.058545567537151e-05, "loss": 0.0426, "step": 86880 }, { "epoch": 20.83, "learning_rate": 9.058335903901271e-05, "loss": 0.0608, "step": 86890 }, { "epoch": 20.83, "learning_rate": 9.058126219348693e-05, "loss": 0.063, "step": 86900 }, { "epoch": 20.83, "learning_rate": 9.0579165138805e-05, "loss": 0.0573, "step": 86910 }, { "epoch": 20.84, "learning_rate": 9.05770678749777e-05, "loss": 0.0779, "step": 86920 }, { "epoch": 20.84, "learning_rate": 9.057497040201585e-05, "loss": 0.0539, "step": 86930 }, { "epoch": 20.84, "learning_rate": 9.057287271993028e-05, "loss": 0.07, "step": 86940 }, { "epoch": 20.84, "learning_rate": 9.05707748287318e-05, "loss": 0.0589, "step": 86950 }, { "epoch": 20.85, "learning_rate": 9.056867672843118e-05, "loss": 0.0557, "step": 86960 }, { "epoch": 20.85, "learning_rate": 9.056657841903926e-05, "loss": 0.0684, "step": 86970 }, { "epoch": 20.85, "learning_rate": 9.056447990056687e-05, "loss": 0.0722, "step": 86980 }, { "epoch": 20.85, "learning_rate": 9.05623811730248e-05, "loss": 0.0582, "step": 86990 }, { "epoch": 20.85, "learning_rate": 9.056028223642389e-05, "loss": 0.1014, "step": 87000 }, { "epoch": 20.86, "learning_rate": 9.055818309077493e-05, "loss": 0.059, "step": 87010 }, { "epoch": 20.86, "learning_rate": 9.055608373608877e-05, "loss": 0.0889, "step": 87020 }, { "epoch": 20.86, "learning_rate": 9.055398417237622e-05, "loss": 0.0622, "step": 87030 }, { "epoch": 20.86, "learning_rate": 9.055188439964807e-05, "loss": 0.0833, "step": 87040 }, { "epoch": 20.87, "learning_rate": 9.05497844179152e-05, "loss": 0.0571, "step": 87050 }, { "epoch": 20.87, "learning_rate": 9.054768422718839e-05, "loss": 0.0575, "step": 87060 }, { "epoch": 20.87, "learning_rate": 9.054558382747846e-05, "loss": 0.0677, "step": 87070 }, { "epoch": 20.87, "learning_rate": 9.054348321879628e-05, "loss": 0.074, "step": 87080 }, { "epoch": 20.88, "learning_rate": 9.054138240115263e-05, "loss": 0.0455, "step": 87090 }, { "epoch": 20.88, "learning_rate": 9.053928137455836e-05, "loss": 0.0727, "step": 87100 }, { "epoch": 20.88, "learning_rate": 9.053718013902431e-05, "loss": 0.0647, "step": 87110 }, { "epoch": 20.88, "learning_rate": 9.053507869456127e-05, "loss": 0.0968, "step": 87120 }, { "epoch": 20.88, "learning_rate": 9.05329770411801e-05, "loss": 0.0416, "step": 87130 }, { "epoch": 20.89, "learning_rate": 9.053087517889165e-05, "loss": 0.0545, "step": 87140 }, { "epoch": 20.89, "learning_rate": 9.052877310770672e-05, "loss": 0.0637, "step": 87150 }, { "epoch": 20.89, "learning_rate": 9.052667082763612e-05, "loss": 0.068, "step": 87160 }, { "epoch": 20.89, "learning_rate": 9.052456833869077e-05, "loss": 0.0686, "step": 87170 }, { "epoch": 20.9, "learning_rate": 9.052246564088143e-05, "loss": 0.0528, "step": 87180 }, { "epoch": 20.9, "learning_rate": 9.052036273421897e-05, "loss": 0.0892, "step": 87190 }, { "epoch": 20.9, "learning_rate": 9.051825961871423e-05, "loss": 0.08, "step": 87200 }, { "epoch": 20.9, "learning_rate": 9.051615629437802e-05, "loss": 0.0481, "step": 87210 }, { "epoch": 20.9, "learning_rate": 9.051405276122122e-05, "loss": 0.0961, "step": 87220 }, { "epoch": 20.91, "learning_rate": 9.051194901925465e-05, "loss": 0.05, "step": 87230 }, { "epoch": 20.91, "learning_rate": 9.050984506848915e-05, "loss": 0.0773, "step": 87240 }, { "epoch": 20.91, "learning_rate": 9.050774090893557e-05, "loss": 0.0605, "step": 87250 }, { "epoch": 20.91, "learning_rate": 9.050563654060476e-05, "loss": 0.0736, "step": 87260 }, { "epoch": 20.92, "learning_rate": 9.050353196350756e-05, "loss": 0.0344, "step": 87270 }, { "epoch": 20.92, "learning_rate": 9.050142717765481e-05, "loss": 0.0949, "step": 87280 }, { "epoch": 20.92, "learning_rate": 9.049932218305738e-05, "loss": 0.0696, "step": 87290 }, { "epoch": 20.92, "learning_rate": 9.04972169797261e-05, "loss": 0.0766, "step": 87300 }, { "epoch": 20.93, "learning_rate": 9.049511156767182e-05, "loss": 0.0634, "step": 87310 }, { "epoch": 20.93, "learning_rate": 9.049300594690539e-05, "loss": 0.0761, "step": 87320 }, { "epoch": 20.93, "learning_rate": 9.049090011743768e-05, "loss": 0.0842, "step": 87330 }, { "epoch": 20.93, "learning_rate": 9.048879407927952e-05, "loss": 0.058, "step": 87340 }, { "epoch": 20.93, "learning_rate": 9.04866878324418e-05, "loss": 0.0461, "step": 87350 }, { "epoch": 20.94, "learning_rate": 9.048458137693535e-05, "loss": 0.0592, "step": 87360 }, { "epoch": 20.94, "learning_rate": 9.048247471277101e-05, "loss": 0.069, "step": 87370 }, { "epoch": 20.94, "learning_rate": 9.048036783995965e-05, "loss": 0.0541, "step": 87380 }, { "epoch": 20.94, "learning_rate": 9.047826075851215e-05, "loss": 0.0598, "step": 87390 }, { "epoch": 20.95, "learning_rate": 9.047615346843938e-05, "loss": 0.0705, "step": 87400 }, { "epoch": 20.95, "learning_rate": 9.047404596975214e-05, "loss": 0.0693, "step": 87410 }, { "epoch": 20.95, "learning_rate": 9.047193826246135e-05, "loss": 0.1004, "step": 87420 }, { "epoch": 21.0, "learning_rate": 9.046983034657785e-05, "loss": 0.0659, "step": 87430 }, { "epoch": 21.0, "learning_rate": 9.046772222211249e-05, "loss": 0.0629, "step": 87440 }, { "epoch": 21.01, "learning_rate": 9.046561388907617e-05, "loss": 0.0618, "step": 87450 }, { "epoch": 21.01, "learning_rate": 9.046350534747971e-05, "loss": 0.0564, "step": 87460 }, { "epoch": 21.01, "learning_rate": 9.046139659733403e-05, "loss": 0.086, "step": 87470 }, { "epoch": 21.01, "learning_rate": 9.045928763864997e-05, "loss": 0.058, "step": 87480 }, { "epoch": 21.02, "learning_rate": 9.045717847143841e-05, "loss": 0.0425, "step": 87490 }, { "epoch": 21.02, "learning_rate": 9.045506909571019e-05, "loss": 0.0431, "step": 87500 }, { "epoch": 21.02, "learning_rate": 9.045295951147623e-05, "loss": 0.0627, "step": 87510 }, { "epoch": 21.02, "learning_rate": 9.045084971874738e-05, "loss": 0.0446, "step": 87520 }, { "epoch": 21.02, "learning_rate": 9.04487397175345e-05, "loss": 0.1038, "step": 87530 }, { "epoch": 21.03, "learning_rate": 9.044662950784849e-05, "loss": 0.0544, "step": 87540 }, { "epoch": 21.03, "learning_rate": 9.04445190897002e-05, "loss": 0.0757, "step": 87550 }, { "epoch": 21.03, "learning_rate": 9.044240846310053e-05, "loss": 0.0461, "step": 87560 }, { "epoch": 21.03, "learning_rate": 9.044029762806032e-05, "loss": 0.0456, "step": 87570 }, { "epoch": 21.04, "learning_rate": 9.043818658459051e-05, "loss": 0.0586, "step": 87580 }, { "epoch": 21.04, "learning_rate": 9.043607533270194e-05, "loss": 0.0442, "step": 87590 }, { "epoch": 21.04, "learning_rate": 9.043396387240551e-05, "loss": 0.072, "step": 87600 }, { "epoch": 21.04, "learning_rate": 9.043185220371206e-05, "loss": 0.0649, "step": 87610 }, { "epoch": 21.05, "learning_rate": 9.042974032663254e-05, "loss": 0.0459, "step": 87620 }, { "epoch": 21.05, "learning_rate": 9.042762824117778e-05, "loss": 0.0314, "step": 87630 }, { "epoch": 21.05, "learning_rate": 9.042551594735869e-05, "loss": 0.0727, "step": 87640 }, { "epoch": 21.05, "learning_rate": 9.042340344518617e-05, "loss": 0.0718, "step": 87650 }, { "epoch": 21.05, "learning_rate": 9.042129073467107e-05, "loss": 0.0822, "step": 87660 }, { "epoch": 21.06, "learning_rate": 9.041917781582431e-05, "loss": 0.0633, "step": 87670 }, { "epoch": 21.06, "learning_rate": 9.041706468865676e-05, "loss": 0.0977, "step": 87680 }, { "epoch": 21.06, "learning_rate": 9.041495135317932e-05, "loss": 0.0671, "step": 87690 }, { "epoch": 21.06, "learning_rate": 9.04128378094029e-05, "loss": 0.0582, "step": 87700 }, { "epoch": 21.07, "learning_rate": 9.041072405733837e-05, "loss": 0.0381, "step": 87710 }, { "epoch": 21.07, "learning_rate": 9.040861009699661e-05, "loss": 0.0861, "step": 87720 }, { "epoch": 21.07, "learning_rate": 9.040649592838857e-05, "loss": 0.0502, "step": 87730 }, { "epoch": 21.07, "learning_rate": 9.040438155152509e-05, "loss": 0.0679, "step": 87740 }, { "epoch": 21.07, "learning_rate": 9.040226696641709e-05, "loss": 0.0546, "step": 87750 }, { "epoch": 21.08, "learning_rate": 9.040015217307547e-05, "loss": 0.055, "step": 87760 }, { "epoch": 21.08, "learning_rate": 9.039803717151115e-05, "loss": 0.0426, "step": 87770 }, { "epoch": 21.08, "learning_rate": 9.039592196173497e-05, "loss": 0.0648, "step": 87780 }, { "epoch": 21.08, "learning_rate": 9.03938065437579e-05, "loss": 0.0313, "step": 87790 }, { "epoch": 21.09, "learning_rate": 9.03916909175908e-05, "loss": 0.0525, "step": 87800 }, { "epoch": 21.09, "learning_rate": 9.038957508324459e-05, "loss": 0.0417, "step": 87810 }, { "epoch": 21.09, "learning_rate": 9.038745904073018e-05, "loss": 0.0795, "step": 87820 }, { "epoch": 21.09, "learning_rate": 9.038534279005846e-05, "loss": 0.0645, "step": 87830 }, { "epoch": 21.1, "learning_rate": 9.038322633124035e-05, "loss": 0.0705, "step": 87840 }, { "epoch": 21.1, "learning_rate": 9.038110966428674e-05, "loss": 0.041, "step": 87850 }, { "epoch": 21.1, "learning_rate": 9.037899278920856e-05, "loss": 0.0639, "step": 87860 }, { "epoch": 21.1, "learning_rate": 9.037687570601672e-05, "loss": 0.0308, "step": 87870 }, { "epoch": 21.1, "learning_rate": 9.037475841472212e-05, "loss": 0.063, "step": 87880 }, { "epoch": 21.11, "learning_rate": 9.037264091533569e-05, "loss": 0.0715, "step": 87890 }, { "epoch": 21.11, "learning_rate": 9.037052320786832e-05, "loss": 0.0895, "step": 87900 }, { "epoch": 21.11, "learning_rate": 9.036840529233093e-05, "loss": 0.0467, "step": 87910 }, { "epoch": 21.11, "learning_rate": 9.036628716873445e-05, "loss": 0.0799, "step": 87920 }, { "epoch": 21.12, "learning_rate": 9.036416883708981e-05, "loss": 0.0599, "step": 87930 }, { "epoch": 21.12, "learning_rate": 9.036205029740788e-05, "loss": 0.0555, "step": 87940 }, { "epoch": 21.12, "learning_rate": 9.035993154969961e-05, "loss": 0.0386, "step": 87950 }, { "epoch": 21.12, "learning_rate": 9.035781259397592e-05, "loss": 0.0665, "step": 87960 }, { "epoch": 21.12, "learning_rate": 9.035569343024771e-05, "loss": 0.0859, "step": 87970 }, { "epoch": 21.13, "learning_rate": 9.035357405852594e-05, "loss": 0.0598, "step": 87980 }, { "epoch": 21.13, "learning_rate": 9.03514544788215e-05, "loss": 0.0738, "step": 87990 }, { "epoch": 21.13, "learning_rate": 9.034933469114532e-05, "loss": 0.0477, "step": 88000 }, { "epoch": 21.13, "learning_rate": 9.034721469550835e-05, "loss": 0.0417, "step": 88010 }, { "epoch": 21.14, "learning_rate": 9.034509449192148e-05, "loss": 0.0635, "step": 88020 }, { "epoch": 21.14, "learning_rate": 9.034297408039567e-05, "loss": 0.054, "step": 88030 }, { "epoch": 21.14, "learning_rate": 9.034085346094183e-05, "loss": 0.0681, "step": 88040 }, { "epoch": 21.14, "learning_rate": 9.033873263357089e-05, "loss": 0.0605, "step": 88050 }, { "epoch": 21.15, "learning_rate": 9.033661159829379e-05, "loss": 0.0508, "step": 88060 }, { "epoch": 21.15, "learning_rate": 9.033449035512145e-05, "loss": 0.0449, "step": 88070 }, { "epoch": 21.15, "learning_rate": 9.033236890406482e-05, "loss": 0.0671, "step": 88080 }, { "epoch": 21.15, "learning_rate": 9.033024724513482e-05, "loss": 0.0937, "step": 88090 }, { "epoch": 21.15, "learning_rate": 9.032812537834239e-05, "loss": 0.0445, "step": 88100 }, { "epoch": 21.16, "learning_rate": 9.032600330369846e-05, "loss": 0.0418, "step": 88110 }, { "epoch": 21.16, "learning_rate": 9.032388102121396e-05, "loss": 0.0894, "step": 88120 }, { "epoch": 21.16, "learning_rate": 9.032175853089985e-05, "loss": 0.0594, "step": 88130 }, { "epoch": 21.16, "learning_rate": 9.031963583276708e-05, "loss": 0.0579, "step": 88140 }, { "epoch": 21.17, "learning_rate": 9.031751292682655e-05, "loss": 0.0565, "step": 88150 }, { "epoch": 21.17, "learning_rate": 9.031538981308923e-05, "loss": 0.0642, "step": 88160 }, { "epoch": 21.17, "learning_rate": 9.031326649156604e-05, "loss": 0.0822, "step": 88170 }, { "epoch": 21.17, "learning_rate": 9.031114296226794e-05, "loss": 0.0779, "step": 88180 }, { "epoch": 21.18, "learning_rate": 9.030901922520589e-05, "loss": 0.0624, "step": 88190 }, { "epoch": 21.18, "learning_rate": 9.03068952803908e-05, "loss": 0.0648, "step": 88200 }, { "epoch": 21.18, "learning_rate": 9.030477112783365e-05, "loss": 0.0572, "step": 88210 }, { "epoch": 21.18, "learning_rate": 9.030264676754535e-05, "loss": 0.0784, "step": 88220 }, { "epoch": 21.18, "learning_rate": 9.030052219953688e-05, "loss": 0.0646, "step": 88230 }, { "epoch": 21.19, "learning_rate": 9.029839742381919e-05, "loss": 0.0595, "step": 88240 }, { "epoch": 21.19, "learning_rate": 9.029627244040324e-05, "loss": 0.0438, "step": 88250 }, { "epoch": 21.19, "learning_rate": 9.029414724929994e-05, "loss": 0.0614, "step": 88260 }, { "epoch": 21.19, "learning_rate": 9.029202185052026e-05, "loss": 0.0508, "step": 88270 }, { "epoch": 21.2, "learning_rate": 9.028989624407517e-05, "loss": 0.0446, "step": 88280 }, { "epoch": 21.2, "learning_rate": 9.028777042997563e-05, "loss": 0.0755, "step": 88290 }, { "epoch": 21.2, "learning_rate": 9.028564440823257e-05, "loss": 0.0674, "step": 88300 }, { "epoch": 21.2, "learning_rate": 9.028351817885699e-05, "loss": 0.0294, "step": 88310 }, { "epoch": 21.2, "learning_rate": 9.028139174185979e-05, "loss": 0.0502, "step": 88320 }, { "epoch": 21.21, "learning_rate": 9.027926509725198e-05, "loss": 0.0785, "step": 88330 }, { "epoch": 21.21, "learning_rate": 9.027713824504448e-05, "loss": 0.0701, "step": 88340 }, { "epoch": 21.21, "learning_rate": 9.027501118524828e-05, "loss": 0.0518, "step": 88350 }, { "epoch": 21.21, "learning_rate": 9.027288391787434e-05, "loss": 0.0746, "step": 88360 }, { "epoch": 21.22, "learning_rate": 9.027075644293363e-05, "loss": 0.0506, "step": 88370 }, { "epoch": 21.22, "learning_rate": 9.026862876043709e-05, "loss": 0.0551, "step": 88380 }, { "epoch": 21.22, "learning_rate": 9.026650087039572e-05, "loss": 0.0494, "step": 88390 }, { "epoch": 21.22, "learning_rate": 9.026437277282044e-05, "loss": 0.0537, "step": 88400 }, { "epoch": 21.23, "learning_rate": 9.026224446772225e-05, "loss": 0.0648, "step": 88410 }, { "epoch": 21.23, "learning_rate": 9.026011595511214e-05, "loss": 0.0471, "step": 88420 }, { "epoch": 21.23, "learning_rate": 9.025798723500102e-05, "loss": 0.0656, "step": 88430 }, { "epoch": 21.23, "learning_rate": 9.025585830739993e-05, "loss": 0.0402, "step": 88440 }, { "epoch": 21.23, "learning_rate": 9.02537291723198e-05, "loss": 0.0854, "step": 88450 }, { "epoch": 21.24, "learning_rate": 9.02515998297716e-05, "loss": 0.0519, "step": 88460 }, { "epoch": 21.24, "learning_rate": 9.024947027976634e-05, "loss": 0.0406, "step": 88470 }, { "epoch": 21.24, "learning_rate": 9.024734052231495e-05, "loss": 0.0826, "step": 88480 }, { "epoch": 21.24, "learning_rate": 9.024521055742845e-05, "loss": 0.0526, "step": 88490 }, { "epoch": 21.25, "learning_rate": 9.024308038511779e-05, "loss": 0.0747, "step": 88500 }, { "epoch": 21.25, "learning_rate": 9.024095000539396e-05, "loss": 0.0688, "step": 88510 }, { "epoch": 21.25, "learning_rate": 9.023881941826795e-05, "loss": 0.0665, "step": 88520 }, { "epoch": 21.25, "learning_rate": 9.023668862375071e-05, "loss": 0.0574, "step": 88530 }, { "epoch": 21.26, "learning_rate": 9.023455762185325e-05, "loss": 0.0514, "step": 88540 }, { "epoch": 21.26, "learning_rate": 9.023242641258654e-05, "loss": 0.0623, "step": 88550 }, { "epoch": 21.26, "learning_rate": 9.023029499596156e-05, "loss": 0.0439, "step": 88560 }, { "epoch": 21.26, "learning_rate": 9.022816337198932e-05, "loss": 0.0348, "step": 88570 }, { "epoch": 21.26, "learning_rate": 9.022603154068077e-05, "loss": 0.0582, "step": 88580 }, { "epoch": 21.27, "learning_rate": 9.022389950204692e-05, "loss": 0.0436, "step": 88590 }, { "epoch": 21.27, "learning_rate": 9.022176725609877e-05, "loss": 0.06, "step": 88600 }, { "epoch": 21.27, "learning_rate": 9.02196348028473e-05, "loss": 0.0611, "step": 88610 }, { "epoch": 21.27, "learning_rate": 9.021750214230347e-05, "loss": 0.0649, "step": 88620 }, { "epoch": 21.28, "learning_rate": 9.021536927447831e-05, "loss": 0.0593, "step": 88630 }, { "epoch": 21.28, "learning_rate": 9.02132361993828e-05, "loss": 0.0457, "step": 88640 }, { "epoch": 21.28, "learning_rate": 9.021110291702795e-05, "loss": 0.0557, "step": 88650 }, { "epoch": 21.28, "learning_rate": 9.020896942742473e-05, "loss": 0.0624, "step": 88660 }, { "epoch": 21.28, "learning_rate": 9.020683573058413e-05, "loss": 0.0524, "step": 88670 }, { "epoch": 21.29, "learning_rate": 9.020470182651718e-05, "loss": 0.0562, "step": 88680 }, { "epoch": 21.29, "learning_rate": 9.020256771523485e-05, "loss": 0.0555, "step": 88690 }, { "epoch": 21.29, "learning_rate": 9.020043339674816e-05, "loss": 0.0309, "step": 88700 }, { "epoch": 21.29, "learning_rate": 9.01982988710681e-05, "loss": 0.0315, "step": 88710 }, { "epoch": 21.3, "learning_rate": 9.019616413820566e-05, "loss": 0.0665, "step": 88720 }, { "epoch": 21.3, "learning_rate": 9.019402919817187e-05, "loss": 0.0521, "step": 88730 }, { "epoch": 21.3, "learning_rate": 9.01918940509777e-05, "loss": 0.0831, "step": 88740 }, { "epoch": 21.3, "learning_rate": 9.018975869663419e-05, "loss": 0.0402, "step": 88750 }, { "epoch": 21.31, "learning_rate": 9.018762313515232e-05, "loss": 0.0537, "step": 88760 }, { "epoch": 21.31, "learning_rate": 9.01854873665431e-05, "loss": 0.0703, "step": 88770 }, { "epoch": 21.31, "learning_rate": 9.018335139081755e-05, "loss": 0.0857, "step": 88780 }, { "epoch": 21.31, "learning_rate": 9.018121520798665e-05, "loss": 0.047, "step": 88790 }, { "epoch": 21.31, "learning_rate": 9.017907881806146e-05, "loss": 0.0317, "step": 88800 }, { "epoch": 21.32, "learning_rate": 9.017694222105296e-05, "loss": 0.0356, "step": 88810 }, { "epoch": 21.32, "learning_rate": 9.017480541697214e-05, "loss": 0.0685, "step": 88820 }, { "epoch": 21.32, "learning_rate": 9.017266840583005e-05, "loss": 0.035, "step": 88830 }, { "epoch": 21.32, "learning_rate": 9.01705311876377e-05, "loss": 0.0713, "step": 88840 }, { "epoch": 21.33, "learning_rate": 9.016839376240607e-05, "loss": 0.047, "step": 88850 }, { "epoch": 21.33, "learning_rate": 9.016625613014624e-05, "loss": 0.051, "step": 88860 }, { "epoch": 21.33, "learning_rate": 9.016411829086916e-05, "loss": 0.0306, "step": 88870 }, { "epoch": 21.33, "learning_rate": 9.016198024458588e-05, "loss": 0.0472, "step": 88880 }, { "epoch": 21.34, "learning_rate": 9.015984199130745e-05, "loss": 0.0617, "step": 88890 }, { "epoch": 21.34, "learning_rate": 9.015770353104482e-05, "loss": 0.0434, "step": 88900 }, { "epoch": 21.34, "learning_rate": 9.015556486380907e-05, "loss": 0.0575, "step": 88910 }, { "epoch": 21.34, "learning_rate": 9.015342598961121e-05, "loss": 0.0705, "step": 88920 }, { "epoch": 21.34, "learning_rate": 9.015128690846224e-05, "loss": 0.0956, "step": 88930 }, { "epoch": 21.35, "learning_rate": 9.014914762037321e-05, "loss": 0.0675, "step": 88940 }, { "epoch": 21.35, "learning_rate": 9.014700812535514e-05, "loss": 0.0706, "step": 88950 }, { "epoch": 21.35, "learning_rate": 9.014486842341906e-05, "loss": 0.0529, "step": 88960 }, { "epoch": 21.35, "learning_rate": 9.014272851457597e-05, "loss": 0.0459, "step": 88970 }, { "epoch": 21.36, "learning_rate": 9.014058839883694e-05, "loss": 0.0741, "step": 88980 }, { "epoch": 21.36, "learning_rate": 9.013844807621297e-05, "loss": 0.0532, "step": 88990 }, { "epoch": 21.36, "learning_rate": 9.013630754671511e-05, "loss": 0.0491, "step": 89000 }, { "epoch": 21.36, "learning_rate": 9.013416681035438e-05, "loss": 0.0572, "step": 89010 }, { "epoch": 21.36, "learning_rate": 9.013202586714183e-05, "loss": 0.0852, "step": 89020 }, { "epoch": 21.37, "learning_rate": 9.012988471708848e-05, "loss": 0.0436, "step": 89030 }, { "epoch": 21.37, "learning_rate": 9.012774336020537e-05, "loss": 0.0719, "step": 89040 }, { "epoch": 21.37, "learning_rate": 9.012560179650352e-05, "loss": 0.047, "step": 89050 }, { "epoch": 21.37, "learning_rate": 9.0123460025994e-05, "loss": 0.0668, "step": 89060 }, { "epoch": 21.38, "learning_rate": 9.012131804868782e-05, "loss": 0.0574, "step": 89070 }, { "epoch": 21.38, "learning_rate": 9.011917586459603e-05, "loss": 0.0528, "step": 89080 }, { "epoch": 21.38, "learning_rate": 9.011703347372968e-05, "loss": 0.0695, "step": 89090 }, { "epoch": 21.38, "learning_rate": 9.011489087609982e-05, "loss": 0.0573, "step": 89100 }, { "epoch": 21.39, "learning_rate": 9.011274807171745e-05, "loss": 0.0494, "step": 89110 }, { "epoch": 21.39, "learning_rate": 9.011060506059366e-05, "loss": 0.053, "step": 89120 }, { "epoch": 21.39, "learning_rate": 9.010846184273947e-05, "loss": 0.0484, "step": 89130 }, { "epoch": 21.39, "learning_rate": 9.010631841816592e-05, "loss": 0.0655, "step": 89140 }, { "epoch": 21.39, "learning_rate": 9.01041747868841e-05, "loss": 0.0749, "step": 89150 }, { "epoch": 21.4, "learning_rate": 9.010203094890499e-05, "loss": 0.0712, "step": 89160 }, { "epoch": 21.4, "learning_rate": 9.00998869042397e-05, "loss": 0.0546, "step": 89170 }, { "epoch": 21.4, "learning_rate": 9.009774265289925e-05, "loss": 0.0443, "step": 89180 }, { "epoch": 21.4, "learning_rate": 9.00955981948947e-05, "loss": 0.0718, "step": 89190 }, { "epoch": 21.41, "learning_rate": 9.009345353023711e-05, "loss": 0.0709, "step": 89200 }, { "epoch": 21.41, "learning_rate": 9.009130865893751e-05, "loss": 0.0431, "step": 89210 }, { "epoch": 21.41, "learning_rate": 9.008916358100699e-05, "loss": 0.0864, "step": 89220 }, { "epoch": 21.41, "learning_rate": 9.008701829645657e-05, "loss": 0.0579, "step": 89230 }, { "epoch": 21.42, "learning_rate": 9.008487280529734e-05, "loss": 0.044, "step": 89240 }, { "epoch": 21.42, "learning_rate": 9.008272710754032e-05, "loss": 0.0445, "step": 89250 }, { "epoch": 21.42, "learning_rate": 9.00805812031966e-05, "loss": 0.0381, "step": 89260 }, { "epoch": 21.42, "learning_rate": 9.007843509227723e-05, "loss": 0.0455, "step": 89270 }, { "epoch": 21.42, "learning_rate": 9.007628877479326e-05, "loss": 0.045, "step": 89280 }, { "epoch": 21.43, "learning_rate": 9.007414225075576e-05, "loss": 0.0452, "step": 89290 }, { "epoch": 21.43, "learning_rate": 9.007199552017583e-05, "loss": 0.0569, "step": 89300 }, { "epoch": 21.43, "learning_rate": 9.006984858306446e-05, "loss": 0.0463, "step": 89310 }, { "epoch": 21.43, "learning_rate": 9.006770143943279e-05, "loss": 0.0532, "step": 89320 }, { "epoch": 21.44, "learning_rate": 9.006555408929182e-05, "loss": 0.0436, "step": 89330 }, { "epoch": 21.44, "learning_rate": 9.006340653265266e-05, "loss": 0.0481, "step": 89340 }, { "epoch": 21.44, "learning_rate": 9.006125876952639e-05, "loss": 0.0542, "step": 89350 }, { "epoch": 21.44, "learning_rate": 9.005911079992402e-05, "loss": 0.0724, "step": 89360 }, { "epoch": 21.44, "learning_rate": 9.005696262385668e-05, "loss": 0.0385, "step": 89370 }, { "epoch": 21.45, "learning_rate": 9.005481424133542e-05, "loss": 0.0699, "step": 89380 }, { "epoch": 21.45, "learning_rate": 9.005266565237132e-05, "loss": 0.0609, "step": 89390 }, { "epoch": 21.45, "learning_rate": 9.005051685697543e-05, "loss": 0.0543, "step": 89400 }, { "epoch": 21.45, "learning_rate": 9.004836785515884e-05, "loss": 0.0479, "step": 89410 }, { "epoch": 21.46, "learning_rate": 9.004621864693263e-05, "loss": 0.0545, "step": 89420 }, { "epoch": 21.46, "learning_rate": 9.004406923230788e-05, "loss": 0.0515, "step": 89430 }, { "epoch": 21.46, "learning_rate": 9.004191961129567e-05, "loss": 0.0724, "step": 89440 }, { "epoch": 21.46, "learning_rate": 9.003976978390705e-05, "loss": 0.0516, "step": 89450 }, { "epoch": 21.47, "learning_rate": 9.003761975015315e-05, "loss": 0.0397, "step": 89460 }, { "epoch": 21.47, "learning_rate": 9.0035469510045e-05, "loss": 0.0394, "step": 89470 }, { "epoch": 21.47, "learning_rate": 9.003331906359371e-05, "loss": 0.0349, "step": 89480 }, { "epoch": 21.47, "learning_rate": 9.003116841081037e-05, "loss": 0.0546, "step": 89490 }, { "epoch": 21.47, "learning_rate": 9.002901755170603e-05, "loss": 0.0319, "step": 89500 }, { "epoch": 21.48, "learning_rate": 9.002686648629181e-05, "loss": 0.0629, "step": 89510 }, { "epoch": 21.48, "learning_rate": 9.002471521457881e-05, "loss": 0.0402, "step": 89520 }, { "epoch": 21.48, "learning_rate": 9.002256373657808e-05, "loss": 0.0481, "step": 89530 }, { "epoch": 21.48, "learning_rate": 9.00204120523007e-05, "loss": 0.0562, "step": 89540 }, { "epoch": 21.49, "learning_rate": 9.001826016175781e-05, "loss": 0.0364, "step": 89550 }, { "epoch": 21.49, "learning_rate": 9.001610806496045e-05, "loss": 0.0364, "step": 89560 }, { "epoch": 21.49, "learning_rate": 9.001395576191973e-05, "loss": 0.0419, "step": 89570 }, { "epoch": 21.49, "learning_rate": 9.001180325264677e-05, "loss": 0.0419, "step": 89580 }, { "epoch": 21.5, "learning_rate": 9.000965053715263e-05, "loss": 0.0427, "step": 89590 }, { "epoch": 21.5, "learning_rate": 9.000749761544842e-05, "loss": 0.0483, "step": 89600 }, { "epoch": 21.5, "learning_rate": 9.000534448754524e-05, "loss": 0.0457, "step": 89610 }, { "epoch": 21.5, "learning_rate": 9.000319115345418e-05, "loss": 0.0487, "step": 89620 }, { "epoch": 21.5, "learning_rate": 9.000103761318632e-05, "loss": 0.0689, "step": 89630 }, { "epoch": 21.51, "learning_rate": 8.999888386675279e-05, "loss": 0.0547, "step": 89640 }, { "epoch": 21.51, "learning_rate": 8.999672991416468e-05, "loss": 0.0498, "step": 89650 }, { "epoch": 21.51, "learning_rate": 8.999457575543308e-05, "loss": 0.0866, "step": 89660 }, { "epoch": 21.51, "learning_rate": 8.999242139056911e-05, "loss": 0.0505, "step": 89670 }, { "epoch": 21.52, "learning_rate": 8.999026681958387e-05, "loss": 0.0493, "step": 89680 }, { "epoch": 21.52, "learning_rate": 8.998811204248845e-05, "loss": 0.0904, "step": 89690 }, { "epoch": 21.52, "learning_rate": 8.998595705929398e-05, "loss": 0.056, "step": 89700 }, { "epoch": 21.52, "learning_rate": 8.998380187001153e-05, "loss": 0.1287, "step": 89710 }, { "epoch": 21.52, "learning_rate": 8.998164647465226e-05, "loss": 0.0522, "step": 89720 }, { "epoch": 21.53, "learning_rate": 8.997949087322724e-05, "loss": 0.0803, "step": 89730 }, { "epoch": 21.53, "learning_rate": 8.997733506574756e-05, "loss": 0.0888, "step": 89740 }, { "epoch": 21.53, "learning_rate": 8.997517905222441e-05, "loss": 0.0745, "step": 89750 }, { "epoch": 21.53, "learning_rate": 8.997302283266882e-05, "loss": 0.1041, "step": 89760 }, { "epoch": 21.54, "learning_rate": 8.997086640709195e-05, "loss": 0.1025, "step": 89770 }, { "epoch": 21.54, "learning_rate": 8.99687097755049e-05, "loss": 0.0645, "step": 89780 }, { "epoch": 21.54, "learning_rate": 8.996655293791879e-05, "loss": 0.1232, "step": 89790 }, { "epoch": 21.54, "learning_rate": 8.996439589434471e-05, "loss": 0.1201, "step": 89800 }, { "epoch": 21.55, "learning_rate": 8.996223864479382e-05, "loss": 0.0997, "step": 89810 }, { "epoch": 21.55, "learning_rate": 8.996008118927721e-05, "loss": 0.0941, "step": 89820 }, { "epoch": 21.55, "learning_rate": 8.995792352780601e-05, "loss": 0.0821, "step": 89830 }, { "epoch": 21.55, "learning_rate": 8.995576566039133e-05, "loss": 0.1039, "step": 89840 }, { "epoch": 21.55, "learning_rate": 8.995360758704431e-05, "loss": 0.079, "step": 89850 }, { "epoch": 21.56, "learning_rate": 8.995144930777606e-05, "loss": 0.0764, "step": 89860 }, { "epoch": 21.56, "learning_rate": 8.994929082259771e-05, "loss": 0.1158, "step": 89870 }, { "epoch": 21.56, "learning_rate": 8.994713213152038e-05, "loss": 0.1286, "step": 89880 }, { "epoch": 21.56, "learning_rate": 8.994497323455518e-05, "loss": 0.1335, "step": 89890 }, { "epoch": 21.57, "learning_rate": 8.994281413171328e-05, "loss": 0.0802, "step": 89900 }, { "epoch": 21.57, "learning_rate": 8.994065482300577e-05, "loss": 0.0565, "step": 89910 }, { "epoch": 21.57, "learning_rate": 8.993849530844379e-05, "loss": 0.111, "step": 89920 }, { "epoch": 21.57, "learning_rate": 8.993633558803847e-05, "loss": 0.0689, "step": 89930 }, { "epoch": 21.58, "learning_rate": 8.993417566180095e-05, "loss": 0.0738, "step": 89940 }, { "epoch": 21.58, "learning_rate": 8.993201552974235e-05, "loss": 0.1035, "step": 89950 }, { "epoch": 21.58, "learning_rate": 8.99298551918738e-05, "loss": 0.0799, "step": 89960 }, { "epoch": 21.58, "learning_rate": 8.992769464820645e-05, "loss": 0.0647, "step": 89970 }, { "epoch": 21.58, "learning_rate": 8.992553389875144e-05, "loss": 0.1049, "step": 89980 }, { "epoch": 21.59, "learning_rate": 8.992337294351988e-05, "loss": 0.0835, "step": 89990 }, { "epoch": 21.59, "learning_rate": 8.992121178252292e-05, "loss": 0.0474, "step": 90000 }, { "epoch": 21.59, "learning_rate": 8.991905041577171e-05, "loss": 0.092, "step": 90010 }, { "epoch": 21.59, "learning_rate": 8.991688884327738e-05, "loss": 0.0954, "step": 90020 }, { "epoch": 21.6, "learning_rate": 8.991472706505106e-05, "loss": 0.0896, "step": 90030 }, { "epoch": 21.6, "learning_rate": 8.991256508110391e-05, "loss": 0.1211, "step": 90040 }, { "epoch": 21.6, "learning_rate": 8.991040289144708e-05, "loss": 0.0934, "step": 90050 }, { "epoch": 21.6, "learning_rate": 8.990824049609168e-05, "loss": 0.0947, "step": 90060 }, { "epoch": 21.6, "learning_rate": 8.990607789504888e-05, "loss": 0.0856, "step": 90070 }, { "epoch": 21.61, "learning_rate": 8.990391508832983e-05, "loss": 0.0844, "step": 90080 }, { "epoch": 21.61, "learning_rate": 8.990175207594566e-05, "loss": 0.0763, "step": 90090 }, { "epoch": 21.61, "learning_rate": 8.989958885790752e-05, "loss": 0.0771, "step": 90100 }, { "epoch": 21.61, "learning_rate": 8.989742543422658e-05, "loss": 0.0812, "step": 90110 }, { "epoch": 21.62, "learning_rate": 8.989526180491396e-05, "loss": 0.0847, "step": 90120 }, { "epoch": 21.62, "learning_rate": 8.989309796998084e-05, "loss": 0.0449, "step": 90130 }, { "epoch": 21.62, "learning_rate": 8.989093392943836e-05, "loss": 0.0694, "step": 90140 }, { "epoch": 21.62, "learning_rate": 8.988876968329766e-05, "loss": 0.0606, "step": 90150 }, { "epoch": 21.63, "learning_rate": 8.988660523156993e-05, "loss": 0.055, "step": 90160 }, { "epoch": 21.63, "learning_rate": 8.988444057426629e-05, "loss": 0.069, "step": 90170 }, { "epoch": 21.63, "learning_rate": 8.98822757113979e-05, "loss": 0.084, "step": 90180 }, { "epoch": 21.63, "learning_rate": 8.988011064297594e-05, "loss": 0.1022, "step": 90190 }, { "epoch": 21.63, "learning_rate": 8.987794536901156e-05, "loss": 0.0904, "step": 90200 }, { "epoch": 21.64, "learning_rate": 8.98757798895159e-05, "loss": 0.076, "step": 90210 }, { "epoch": 21.64, "learning_rate": 8.987361420450015e-05, "loss": 0.1208, "step": 90220 }, { "epoch": 21.64, "learning_rate": 8.987144831397544e-05, "loss": 0.0627, "step": 90230 }, { "epoch": 21.64, "learning_rate": 8.986928221795299e-05, "loss": 0.0624, "step": 90240 }, { "epoch": 21.65, "learning_rate": 8.98671159164439e-05, "loss": 0.0767, "step": 90250 }, { "epoch": 21.65, "learning_rate": 8.986494940945935e-05, "loss": 0.0723, "step": 90260 }, { "epoch": 21.65, "learning_rate": 8.986278269701054e-05, "loss": 0.0709, "step": 90270 }, { "epoch": 21.65, "learning_rate": 8.986061577910861e-05, "loss": 0.0634, "step": 90280 }, { "epoch": 21.66, "learning_rate": 8.985844865576474e-05, "loss": 0.0815, "step": 90290 }, { "epoch": 21.66, "learning_rate": 8.985628132699008e-05, "loss": 0.0704, "step": 90300 }, { "epoch": 21.66, "learning_rate": 8.985411379279581e-05, "loss": 0.0865, "step": 90310 }, { "epoch": 21.66, "learning_rate": 8.985194605319312e-05, "loss": 0.1177, "step": 90320 }, { "epoch": 21.66, "learning_rate": 8.984977810819315e-05, "loss": 0.0756, "step": 90330 }, { "epoch": 21.67, "learning_rate": 8.98476099578071e-05, "loss": 0.038, "step": 90340 }, { "epoch": 21.67, "learning_rate": 8.984544160204613e-05, "loss": 0.079, "step": 90350 }, { "epoch": 21.67, "learning_rate": 8.984327304092143e-05, "loss": 0.0515, "step": 90360 }, { "epoch": 21.67, "learning_rate": 8.984110427444416e-05, "loss": 0.0996, "step": 90370 }, { "epoch": 21.68, "learning_rate": 8.98389353026255e-05, "loss": 0.0756, "step": 90380 }, { "epoch": 21.68, "learning_rate": 8.983676612547664e-05, "loss": 0.0417, "step": 90390 }, { "epoch": 21.68, "learning_rate": 8.983459674300876e-05, "loss": 0.0668, "step": 90400 }, { "epoch": 21.68, "learning_rate": 8.983242715523304e-05, "loss": 0.0395, "step": 90410 }, { "epoch": 21.68, "learning_rate": 8.983025736216065e-05, "loss": 0.0531, "step": 90420 }, { "epoch": 21.69, "learning_rate": 8.982808736380276e-05, "loss": 0.0702, "step": 90430 }, { "epoch": 21.69, "learning_rate": 8.982591716017062e-05, "loss": 0.0531, "step": 90440 }, { "epoch": 21.69, "learning_rate": 8.982374675127534e-05, "loss": 0.0603, "step": 90450 }, { "epoch": 21.69, "learning_rate": 8.982157613712814e-05, "loss": 0.0736, "step": 90460 }, { "epoch": 21.7, "learning_rate": 8.98194053177402e-05, "loss": 0.0842, "step": 90470 }, { "epoch": 21.7, "learning_rate": 8.981723429312271e-05, "loss": 0.0499, "step": 90480 }, { "epoch": 21.7, "learning_rate": 8.981506306328687e-05, "loss": 0.0843, "step": 90490 }, { "epoch": 21.7, "learning_rate": 8.981289162824387e-05, "loss": 0.0938, "step": 90500 }, { "epoch": 21.71, "learning_rate": 8.981071998800488e-05, "loss": 0.0449, "step": 90510 }, { "epoch": 21.71, "learning_rate": 8.980854814258111e-05, "loss": 0.051, "step": 90520 }, { "epoch": 21.71, "learning_rate": 8.980637609198374e-05, "loss": 0.0424, "step": 90530 }, { "epoch": 21.71, "learning_rate": 8.9804203836224e-05, "loss": 0.0674, "step": 90540 }, { "epoch": 21.71, "learning_rate": 8.980203137531305e-05, "loss": 0.0436, "step": 90550 }, { "epoch": 21.72, "learning_rate": 8.979985870926209e-05, "loss": 0.0628, "step": 90560 }, { "epoch": 21.72, "learning_rate": 8.979768583808232e-05, "loss": 0.0573, "step": 90570 }, { "epoch": 21.72, "learning_rate": 8.979551276178497e-05, "loss": 0.0491, "step": 90580 }, { "epoch": 21.72, "learning_rate": 8.97933394803812e-05, "loss": 0.0749, "step": 90590 }, { "epoch": 21.73, "learning_rate": 8.979116599388222e-05, "loss": 0.0621, "step": 90600 }, { "epoch": 21.73, "learning_rate": 8.978899230229925e-05, "loss": 0.0499, "step": 90610 }, { "epoch": 21.73, "learning_rate": 8.978681840564346e-05, "loss": 0.1159, "step": 90620 }, { "epoch": 21.73, "learning_rate": 8.97846443039261e-05, "loss": 0.0966, "step": 90630 }, { "epoch": 21.74, "learning_rate": 8.978246999715834e-05, "loss": 0.0978, "step": 90640 }, { "epoch": 21.74, "learning_rate": 8.978029548535138e-05, "loss": 0.0672, "step": 90650 }, { "epoch": 21.74, "learning_rate": 8.977812076851648e-05, "loss": 0.0766, "step": 90660 }, { "epoch": 21.74, "learning_rate": 8.977594584666477e-05, "loss": 0.053, "step": 90670 }, { "epoch": 21.74, "learning_rate": 8.977377071980755e-05, "loss": 0.0563, "step": 90680 }, { "epoch": 21.75, "learning_rate": 8.977159538795596e-05, "loss": 0.0607, "step": 90690 }, { "epoch": 21.75, "learning_rate": 8.976941985112122e-05, "loss": 0.0698, "step": 90700 }, { "epoch": 21.75, "learning_rate": 8.976724410931459e-05, "loss": 0.0798, "step": 90710 }, { "epoch": 21.75, "learning_rate": 8.976506816254721e-05, "loss": 0.0983, "step": 90720 }, { "epoch": 21.76, "learning_rate": 8.976289201083037e-05, "loss": 0.0942, "step": 90730 }, { "epoch": 21.76, "learning_rate": 8.976071565417525e-05, "loss": 0.0778, "step": 90740 }, { "epoch": 21.76, "learning_rate": 8.975853909259307e-05, "loss": 0.1109, "step": 90750 }, { "epoch": 21.76, "learning_rate": 8.975636232609503e-05, "loss": 0.0392, "step": 90760 }, { "epoch": 21.76, "learning_rate": 8.975418535469238e-05, "loss": 0.0978, "step": 90770 }, { "epoch": 21.77, "learning_rate": 8.97520081783963e-05, "loss": 0.0706, "step": 90780 }, { "epoch": 21.77, "learning_rate": 8.974983079721809e-05, "loss": 0.0806, "step": 90790 }, { "epoch": 21.77, "learning_rate": 8.974765321116886e-05, "loss": 0.0598, "step": 90800 }, { "epoch": 21.77, "learning_rate": 8.974547542025994e-05, "loss": 0.076, "step": 90810 }, { "epoch": 21.78, "learning_rate": 8.974329742450249e-05, "loss": 0.0514, "step": 90820 }, { "epoch": 21.78, "learning_rate": 8.974111922390776e-05, "loss": 0.0799, "step": 90830 }, { "epoch": 21.78, "learning_rate": 8.973894081848695e-05, "loss": 0.0512, "step": 90840 }, { "epoch": 21.78, "learning_rate": 8.973676220825132e-05, "loss": 0.0482, "step": 90850 }, { "epoch": 21.79, "learning_rate": 8.973458339321208e-05, "loss": 0.0544, "step": 90860 }, { "epoch": 21.79, "learning_rate": 8.973240437338047e-05, "loss": 0.0689, "step": 90870 }, { "epoch": 21.79, "learning_rate": 8.973022514876772e-05, "loss": 0.1186, "step": 90880 }, { "epoch": 21.79, "learning_rate": 8.972804571938504e-05, "loss": 0.0762, "step": 90890 }, { "epoch": 21.79, "learning_rate": 8.972586608524371e-05, "loss": 0.0637, "step": 90900 }, { "epoch": 21.8, "learning_rate": 8.972368624635492e-05, "loss": 0.0481, "step": 90910 }, { "epoch": 21.8, "learning_rate": 8.972150620272991e-05, "loss": 0.0675, "step": 90920 }, { "epoch": 21.8, "learning_rate": 8.971932595437993e-05, "loss": 0.1073, "step": 90930 }, { "epoch": 21.8, "learning_rate": 8.971714550131622e-05, "loss": 0.0936, "step": 90940 }, { "epoch": 21.81, "learning_rate": 8.971496484355e-05, "loss": 0.0542, "step": 90950 }, { "epoch": 21.81, "learning_rate": 8.971278398109251e-05, "loss": 0.0702, "step": 90960 }, { "epoch": 21.81, "learning_rate": 8.971060291395503e-05, "loss": 0.0465, "step": 90970 }, { "epoch": 21.81, "learning_rate": 8.970842164214874e-05, "loss": 0.0578, "step": 90980 }, { "epoch": 21.82, "learning_rate": 8.970624016568493e-05, "loss": 0.0812, "step": 90990 }, { "epoch": 21.82, "learning_rate": 8.970405848457482e-05, "loss": 0.0604, "step": 91000 }, { "epoch": 21.82, "learning_rate": 8.970187659882966e-05, "loss": 0.0484, "step": 91010 }, { "epoch": 21.82, "learning_rate": 8.969969450846069e-05, "loss": 0.0485, "step": 91020 }, { "epoch": 21.82, "learning_rate": 8.969751221347917e-05, "loss": 0.0654, "step": 91030 }, { "epoch": 21.83, "learning_rate": 8.969532971389636e-05, "loss": 0.0412, "step": 91040 }, { "epoch": 21.83, "learning_rate": 8.969314700972347e-05, "loss": 0.0461, "step": 91050 }, { "epoch": 21.83, "learning_rate": 8.969096410097176e-05, "loss": 0.0901, "step": 91060 }, { "epoch": 21.83, "learning_rate": 8.96887809876525e-05, "loss": 0.0545, "step": 91070 }, { "epoch": 21.84, "learning_rate": 8.968659766977693e-05, "loss": 0.047, "step": 91080 }, { "epoch": 21.84, "learning_rate": 8.96844141473563e-05, "loss": 0.0589, "step": 91090 }, { "epoch": 21.84, "learning_rate": 8.968223042040187e-05, "loss": 0.0695, "step": 91100 }, { "epoch": 21.84, "learning_rate": 8.96800464889249e-05, "loss": 0.0873, "step": 91110 }, { "epoch": 21.84, "learning_rate": 8.967786235293662e-05, "loss": 0.048, "step": 91120 }, { "epoch": 21.85, "learning_rate": 8.967567801244833e-05, "loss": 0.0816, "step": 91130 }, { "epoch": 21.85, "learning_rate": 8.967349346747125e-05, "loss": 0.0527, "step": 91140 }, { "epoch": 21.85, "learning_rate": 8.967130871801666e-05, "loss": 0.0675, "step": 91150 }, { "epoch": 21.85, "learning_rate": 8.96691237640958e-05, "loss": 0.0437, "step": 91160 }, { "epoch": 21.86, "learning_rate": 8.966693860571995e-05, "loss": 0.0831, "step": 91170 }, { "epoch": 21.86, "learning_rate": 8.966475324290037e-05, "loss": 0.0462, "step": 91180 }, { "epoch": 21.86, "learning_rate": 8.966256767564832e-05, "loss": 0.0543, "step": 91190 }, { "epoch": 21.86, "learning_rate": 8.966038190397508e-05, "loss": 0.0462, "step": 91200 }, { "epoch": 21.87, "learning_rate": 8.965819592789187e-05, "loss": 0.0711, "step": 91210 }, { "epoch": 21.87, "learning_rate": 8.965600974741e-05, "loss": 0.0634, "step": 91220 }, { "epoch": 21.87, "learning_rate": 8.965382336254074e-05, "loss": 0.0821, "step": 91230 }, { "epoch": 21.87, "learning_rate": 8.96516367732953e-05, "loss": 0.0712, "step": 91240 }, { "epoch": 21.87, "learning_rate": 8.964944997968505e-05, "loss": 0.0429, "step": 91250 }, { "epoch": 21.88, "learning_rate": 8.964726298172117e-05, "loss": 0.0378, "step": 91260 }, { "epoch": 21.88, "learning_rate": 8.964507577941497e-05, "loss": 0.0612, "step": 91270 }, { "epoch": 21.88, "learning_rate": 8.96428883727777e-05, "loss": 0.0546, "step": 91280 }, { "epoch": 21.88, "learning_rate": 8.964070076182068e-05, "loss": 0.0704, "step": 91290 }, { "epoch": 21.89, "learning_rate": 8.963851294655516e-05, "loss": 0.0666, "step": 91300 }, { "epoch": 21.89, "learning_rate": 8.963632492699238e-05, "loss": 0.0642, "step": 91310 }, { "epoch": 21.89, "learning_rate": 8.963413670314368e-05, "loss": 0.0546, "step": 91320 }, { "epoch": 21.89, "learning_rate": 8.96319482750203e-05, "loss": 0.0481, "step": 91330 }, { "epoch": 21.9, "learning_rate": 8.962975964263351e-05, "loss": 0.0649, "step": 91340 }, { "epoch": 21.9, "learning_rate": 8.962757080599463e-05, "loss": 0.071, "step": 91350 }, { "epoch": 21.9, "learning_rate": 8.962538176511492e-05, "loss": 0.0622, "step": 91360 }, { "epoch": 21.9, "learning_rate": 8.962319252000565e-05, "loss": 0.0546, "step": 91370 }, { "epoch": 21.9, "learning_rate": 8.962100307067811e-05, "loss": 0.0577, "step": 91380 }, { "epoch": 21.91, "learning_rate": 8.96188134171436e-05, "loss": 0.0527, "step": 91390 }, { "epoch": 21.91, "learning_rate": 8.961662355941339e-05, "loss": 0.0566, "step": 91400 }, { "epoch": 21.91, "learning_rate": 8.961443349749877e-05, "loss": 0.054, "step": 91410 }, { "epoch": 21.91, "learning_rate": 8.961224323141104e-05, "loss": 0.0706, "step": 91420 }, { "epoch": 21.92, "learning_rate": 8.961005276116145e-05, "loss": 0.0701, "step": 91430 }, { "epoch": 21.92, "learning_rate": 8.960786208676135e-05, "loss": 0.0442, "step": 91440 }, { "epoch": 21.92, "learning_rate": 8.960567120822199e-05, "loss": 0.1005, "step": 91450 }, { "epoch": 21.92, "learning_rate": 8.960348012555465e-05, "loss": 0.1068, "step": 91460 }, { "epoch": 21.92, "learning_rate": 8.960128883877066e-05, "loss": 0.0392, "step": 91470 }, { "epoch": 21.93, "learning_rate": 8.959909734788128e-05, "loss": 0.051, "step": 91480 }, { "epoch": 21.93, "learning_rate": 8.959690565289785e-05, "loss": 0.1027, "step": 91490 }, { "epoch": 21.93, "learning_rate": 8.95947137538316e-05, "loss": 0.1017, "step": 91500 }, { "epoch": 21.93, "learning_rate": 8.959252165069389e-05, "loss": 0.0608, "step": 91510 }, { "epoch": 21.94, "learning_rate": 8.959032934349598e-05, "loss": 0.0604, "step": 91520 }, { "epoch": 21.94, "learning_rate": 8.958813683224921e-05, "loss": 0.0628, "step": 91530 }, { "epoch": 21.94, "learning_rate": 8.958594411696481e-05, "loss": 0.0729, "step": 91540 }, { "epoch": 21.94, "learning_rate": 8.958375119765414e-05, "loss": 0.0859, "step": 91550 }, { "epoch": 21.95, "learning_rate": 8.958155807432848e-05, "loss": 0.0583, "step": 91560 }, { "epoch": 21.95, "learning_rate": 8.957936474699916e-05, "loss": 0.0403, "step": 91570 }, { "epoch": 21.95, "learning_rate": 8.957717121567746e-05, "loss": 0.0467, "step": 91580 }, { "epoch": 22.0, "learning_rate": 8.957497748037467e-05, "loss": 0.0633, "step": 91590 }, { "epoch": 22.0, "learning_rate": 8.957278354110212e-05, "loss": 0.1064, "step": 91600 }, { "epoch": 22.01, "learning_rate": 8.957058939787112e-05, "loss": 0.0524, "step": 91610 }, { "epoch": 22.01, "learning_rate": 8.956839505069297e-05, "loss": 0.0544, "step": 91620 }, { "epoch": 22.01, "learning_rate": 8.956620049957898e-05, "loss": 0.0504, "step": 91630 }, { "epoch": 22.01, "learning_rate": 8.956400574454046e-05, "loss": 0.0395, "step": 91640 }, { "epoch": 22.01, "learning_rate": 8.956181078558872e-05, "loss": 0.0476, "step": 91650 }, { "epoch": 22.02, "learning_rate": 8.95596156227351e-05, "loss": 0.0679, "step": 91660 }, { "epoch": 22.02, "learning_rate": 8.955742025599085e-05, "loss": 0.0741, "step": 91670 }, { "epoch": 22.02, "learning_rate": 8.955522468536736e-05, "loss": 0.0796, "step": 91680 }, { "epoch": 22.02, "learning_rate": 8.955302891087589e-05, "loss": 0.0589, "step": 91690 }, { "epoch": 22.03, "learning_rate": 8.95508329325278e-05, "loss": 0.0501, "step": 91700 }, { "epoch": 22.03, "learning_rate": 8.954863675033438e-05, "loss": 0.0736, "step": 91710 }, { "epoch": 22.03, "learning_rate": 8.954644036430694e-05, "loss": 0.048, "step": 91720 }, { "epoch": 22.03, "learning_rate": 8.954424377445682e-05, "loss": 0.0698, "step": 91730 }, { "epoch": 22.04, "learning_rate": 8.954204698079534e-05, "loss": 0.0519, "step": 91740 }, { "epoch": 22.04, "learning_rate": 8.953984998333382e-05, "loss": 0.066, "step": 91750 }, { "epoch": 22.04, "learning_rate": 8.953765278208359e-05, "loss": 0.0506, "step": 91760 }, { "epoch": 22.04, "learning_rate": 8.953545537705597e-05, "loss": 0.0427, "step": 91770 }, { "epoch": 22.04, "learning_rate": 8.953325776826227e-05, "loss": 0.0467, "step": 91780 }, { "epoch": 22.05, "learning_rate": 8.953105995571382e-05, "loss": 0.0432, "step": 91790 }, { "epoch": 22.05, "learning_rate": 8.952886193942198e-05, "loss": 0.0951, "step": 91800 }, { "epoch": 22.05, "learning_rate": 8.952666371939804e-05, "loss": 0.0306, "step": 91810 }, { "epoch": 22.05, "learning_rate": 8.952446529565334e-05, "loss": 0.0716, "step": 91820 }, { "epoch": 22.06, "learning_rate": 8.952226666819924e-05, "loss": 0.0861, "step": 91830 }, { "epoch": 22.06, "learning_rate": 8.952006783704703e-05, "loss": 0.0433, "step": 91840 }, { "epoch": 22.06, "learning_rate": 8.951786880220806e-05, "loss": 0.0699, "step": 91850 }, { "epoch": 22.06, "learning_rate": 8.951566956369366e-05, "loss": 0.0518, "step": 91860 }, { "epoch": 22.06, "learning_rate": 8.951347012151518e-05, "loss": 0.063, "step": 91870 }, { "epoch": 22.07, "learning_rate": 8.951127047568395e-05, "loss": 0.0587, "step": 91880 }, { "epoch": 22.07, "learning_rate": 8.950907062621127e-05, "loss": 0.0534, "step": 91890 }, { "epoch": 22.07, "learning_rate": 8.950687057310854e-05, "loss": 0.0711, "step": 91900 }, { "epoch": 22.07, "learning_rate": 8.950467031638706e-05, "loss": 0.0642, "step": 91910 }, { "epoch": 22.08, "learning_rate": 8.950246985605818e-05, "loss": 0.055, "step": 91920 }, { "epoch": 22.08, "learning_rate": 8.950026919213323e-05, "loss": 0.0626, "step": 91930 }, { "epoch": 22.08, "learning_rate": 8.949806832462359e-05, "loss": 0.0532, "step": 91940 }, { "epoch": 22.08, "learning_rate": 8.949586725354056e-05, "loss": 0.0686, "step": 91950 }, { "epoch": 22.09, "learning_rate": 8.949366597889548e-05, "loss": 0.0548, "step": 91960 }, { "epoch": 22.09, "learning_rate": 8.949146450069975e-05, "loss": 0.0505, "step": 91970 }, { "epoch": 22.09, "learning_rate": 8.948926281896465e-05, "loss": 0.0521, "step": 91980 }, { "epoch": 22.09, "learning_rate": 8.948706093370159e-05, "loss": 0.051, "step": 91990 }, { "epoch": 22.09, "learning_rate": 8.948485884492186e-05, "loss": 0.0537, "step": 92000 }, { "epoch": 22.1, "learning_rate": 8.948265655263685e-05, "loss": 0.0588, "step": 92010 }, { "epoch": 22.1, "learning_rate": 8.94804540568579e-05, "loss": 0.0889, "step": 92020 }, { "epoch": 22.1, "learning_rate": 8.947825135759636e-05, "loss": 0.0791, "step": 92030 }, { "epoch": 22.1, "learning_rate": 8.947604845486357e-05, "loss": 0.1017, "step": 92040 }, { "epoch": 22.11, "learning_rate": 8.947384534867092e-05, "loss": 0.0406, "step": 92050 }, { "epoch": 22.11, "learning_rate": 8.947164203902971e-05, "loss": 0.0324, "step": 92060 }, { "epoch": 22.11, "learning_rate": 8.946943852595134e-05, "loss": 0.0427, "step": 92070 }, { "epoch": 22.11, "learning_rate": 8.946723480944717e-05, "loss": 0.0483, "step": 92080 }, { "epoch": 22.12, "learning_rate": 8.946503088952854e-05, "loss": 0.0357, "step": 92090 }, { "epoch": 22.12, "learning_rate": 8.946282676620678e-05, "loss": 0.0397, "step": 92100 }, { "epoch": 22.12, "learning_rate": 8.946062243949331e-05, "loss": 0.0707, "step": 92110 }, { "epoch": 22.12, "learning_rate": 8.945841790939947e-05, "loss": 0.0413, "step": 92120 }, { "epoch": 22.12, "learning_rate": 8.945621317593657e-05, "loss": 0.045, "step": 92130 }, { "epoch": 22.13, "learning_rate": 8.945400823911606e-05, "loss": 0.0484, "step": 92140 }, { "epoch": 22.13, "learning_rate": 8.945180309894923e-05, "loss": 0.0511, "step": 92150 }, { "epoch": 22.13, "learning_rate": 8.94495977554475e-05, "loss": 0.0532, "step": 92160 }, { "epoch": 22.13, "learning_rate": 8.944739220862221e-05, "loss": 0.044, "step": 92170 }, { "epoch": 22.14, "learning_rate": 8.944518645848473e-05, "loss": 0.0528, "step": 92180 }, { "epoch": 22.14, "learning_rate": 8.944298050504642e-05, "loss": 0.0357, "step": 92190 }, { "epoch": 22.14, "learning_rate": 8.944077434831867e-05, "loss": 0.0799, "step": 92200 }, { "epoch": 22.14, "learning_rate": 8.943856798831284e-05, "loss": 0.0644, "step": 92210 }, { "epoch": 22.14, "learning_rate": 8.94363614250403e-05, "loss": 0.0559, "step": 92220 }, { "epoch": 22.15, "learning_rate": 8.943415465851241e-05, "loss": 0.0706, "step": 92230 }, { "epoch": 22.15, "learning_rate": 8.943194768874058e-05, "loss": 0.0322, "step": 92240 }, { "epoch": 22.15, "learning_rate": 8.942974051573615e-05, "loss": 0.0525, "step": 92250 }, { "epoch": 22.15, "learning_rate": 8.942753313951051e-05, "loss": 0.0422, "step": 92260 }, { "epoch": 22.16, "learning_rate": 8.942532556007504e-05, "loss": 0.048, "step": 92270 }, { "epoch": 22.16, "learning_rate": 8.942311777744111e-05, "loss": 0.0413, "step": 92280 }, { "epoch": 22.16, "learning_rate": 8.942090979162007e-05, "loss": 0.0503, "step": 92290 }, { "epoch": 22.16, "learning_rate": 8.941870160262337e-05, "loss": 0.0607, "step": 92300 }, { "epoch": 22.17, "learning_rate": 8.941649321046234e-05, "loss": 0.0387, "step": 92310 }, { "epoch": 22.17, "learning_rate": 8.941428461514837e-05, "loss": 0.0501, "step": 92320 }, { "epoch": 22.17, "learning_rate": 8.941207581669285e-05, "loss": 0.0354, "step": 92330 }, { "epoch": 22.17, "learning_rate": 8.940986681510717e-05, "loss": 0.0589, "step": 92340 }, { "epoch": 22.17, "learning_rate": 8.94076576104027e-05, "loss": 0.0653, "step": 92350 }, { "epoch": 22.18, "learning_rate": 8.940544820259082e-05, "loss": 0.0333, "step": 92360 }, { "epoch": 22.18, "learning_rate": 8.940323859168296e-05, "loss": 0.0545, "step": 92370 }, { "epoch": 22.18, "learning_rate": 8.940102877769046e-05, "loss": 0.0563, "step": 92380 }, { "epoch": 22.18, "learning_rate": 8.939881876062473e-05, "loss": 0.0566, "step": 92390 }, { "epoch": 22.19, "learning_rate": 8.939660854049716e-05, "loss": 0.0468, "step": 92400 }, { "epoch": 22.19, "learning_rate": 8.939439811731915e-05, "loss": 0.1032, "step": 92410 }, { "epoch": 22.19, "learning_rate": 8.939218749110207e-05, "loss": 0.0488, "step": 92420 }, { "epoch": 22.19, "learning_rate": 8.938997666185734e-05, "loss": 0.0395, "step": 92430 }, { "epoch": 22.2, "learning_rate": 8.938776562959632e-05, "loss": 0.0401, "step": 92440 }, { "epoch": 22.2, "learning_rate": 8.938555439433044e-05, "loss": 0.061, "step": 92450 }, { "epoch": 22.2, "learning_rate": 8.938334295607108e-05, "loss": 0.0619, "step": 92460 }, { "epoch": 22.2, "learning_rate": 8.938113131482963e-05, "loss": 0.0312, "step": 92470 }, { "epoch": 22.2, "learning_rate": 8.937891947061753e-05, "loss": 0.052, "step": 92480 }, { "epoch": 22.21, "learning_rate": 8.937670742344612e-05, "loss": 0.0548, "step": 92490 }, { "epoch": 22.21, "learning_rate": 8.937449517332685e-05, "loss": 0.0841, "step": 92500 }, { "epoch": 22.21, "learning_rate": 8.93722827202711e-05, "loss": 0.0544, "step": 92510 }, { "epoch": 22.21, "learning_rate": 8.937007006429027e-05, "loss": 0.0706, "step": 92520 }, { "epoch": 22.22, "learning_rate": 8.936785720539578e-05, "loss": 0.0494, "step": 92530 }, { "epoch": 22.22, "learning_rate": 8.9365644143599e-05, "loss": 0.0695, "step": 92540 }, { "epoch": 22.22, "learning_rate": 8.936343087891139e-05, "loss": 0.0521, "step": 92550 }, { "epoch": 22.22, "learning_rate": 8.936121741134431e-05, "loss": 0.0664, "step": 92560 }, { "epoch": 22.22, "learning_rate": 8.93590037409092e-05, "loss": 0.0743, "step": 92570 }, { "epoch": 22.23, "learning_rate": 8.935678986761744e-05, "loss": 0.0597, "step": 92580 }, { "epoch": 22.23, "learning_rate": 8.935457579148047e-05, "loss": 0.0312, "step": 92590 }, { "epoch": 22.23, "learning_rate": 8.935236151250967e-05, "loss": 0.0416, "step": 92600 }, { "epoch": 22.23, "learning_rate": 8.935014703071649e-05, "loss": 0.0395, "step": 92610 }, { "epoch": 22.24, "learning_rate": 8.934793234611231e-05, "loss": 0.0396, "step": 92620 }, { "epoch": 22.24, "learning_rate": 8.934571745870857e-05, "loss": 0.0334, "step": 92630 }, { "epoch": 22.24, "learning_rate": 8.934350236851666e-05, "loss": 0.0445, "step": 92640 }, { "epoch": 22.24, "learning_rate": 8.934128707554802e-05, "loss": 0.0538, "step": 92650 }, { "epoch": 22.25, "learning_rate": 8.933907157981405e-05, "loss": 0.0551, "step": 92660 }, { "epoch": 22.25, "learning_rate": 8.933685588132619e-05, "loss": 0.051, "step": 92670 }, { "epoch": 22.25, "learning_rate": 8.933463998009582e-05, "loss": 0.0854, "step": 92680 }, { "epoch": 22.25, "learning_rate": 8.93324238761344e-05, "loss": 0.0585, "step": 92690 }, { "epoch": 22.25, "learning_rate": 8.933020756945335e-05, "loss": 0.0429, "step": 92700 }, { "epoch": 22.26, "learning_rate": 8.932799106006407e-05, "loss": 0.0408, "step": 92710 }, { "epoch": 22.26, "learning_rate": 8.9325774347978e-05, "loss": 0.054, "step": 92720 }, { "epoch": 22.26, "learning_rate": 8.932355743320657e-05, "loss": 0.0694, "step": 92730 }, { "epoch": 22.26, "learning_rate": 8.932134031576117e-05, "loss": 0.0316, "step": 92740 }, { "epoch": 22.27, "learning_rate": 8.931912299565327e-05, "loss": 0.0425, "step": 92750 }, { "epoch": 22.27, "learning_rate": 8.931690547289429e-05, "loss": 0.0833, "step": 92760 }, { "epoch": 22.27, "learning_rate": 8.931468774749562e-05, "loss": 0.0509, "step": 92770 }, { "epoch": 22.27, "learning_rate": 8.931246981946874e-05, "loss": 0.0432, "step": 92780 }, { "epoch": 22.28, "learning_rate": 8.931025168882508e-05, "loss": 0.0685, "step": 92790 }, { "epoch": 22.28, "learning_rate": 8.930803335557602e-05, "loss": 0.0478, "step": 92800 }, { "epoch": 22.28, "learning_rate": 8.930581481973306e-05, "loss": 0.0333, "step": 92810 }, { "epoch": 22.28, "learning_rate": 8.930359608130759e-05, "loss": 0.0416, "step": 92820 }, { "epoch": 22.28, "learning_rate": 8.930137714031104e-05, "loss": 0.0422, "step": 92830 }, { "epoch": 22.29, "learning_rate": 8.929915799675488e-05, "loss": 0.0455, "step": 92840 }, { "epoch": 22.29, "learning_rate": 8.929693865065053e-05, "loss": 0.05, "step": 92850 }, { "epoch": 22.29, "learning_rate": 8.929471910200943e-05, "loss": 0.0496, "step": 92860 }, { "epoch": 22.29, "learning_rate": 8.929249935084301e-05, "loss": 0.0462, "step": 92870 }, { "epoch": 22.3, "learning_rate": 8.929027939716272e-05, "loss": 0.0617, "step": 92880 }, { "epoch": 22.3, "learning_rate": 8.928805924098003e-05, "loss": 0.0477, "step": 92890 }, { "epoch": 22.3, "learning_rate": 8.928583888230632e-05, "loss": 0.0606, "step": 92900 }, { "epoch": 22.3, "learning_rate": 8.928361832115309e-05, "loss": 0.0584, "step": 92910 }, { "epoch": 22.3, "learning_rate": 8.928139755753174e-05, "loss": 0.0574, "step": 92920 }, { "epoch": 22.31, "learning_rate": 8.927917659145375e-05, "loss": 0.0676, "step": 92930 }, { "epoch": 22.31, "learning_rate": 8.927695542293057e-05, "loss": 0.0518, "step": 92940 }, { "epoch": 22.31, "learning_rate": 8.927473405197362e-05, "loss": 0.0597, "step": 92950 }, { "epoch": 22.31, "learning_rate": 8.927251247859436e-05, "loss": 0.0621, "step": 92960 }, { "epoch": 22.32, "learning_rate": 8.927029070280425e-05, "loss": 0.041, "step": 92970 }, { "epoch": 22.32, "learning_rate": 8.926806872461473e-05, "loss": 0.0531, "step": 92980 }, { "epoch": 22.32, "learning_rate": 8.926584654403724e-05, "loss": 0.0582, "step": 92990 }, { "epoch": 22.32, "learning_rate": 8.926362416108327e-05, "loss": 0.054, "step": 93000 }, { "epoch": 22.33, "learning_rate": 8.926140157576426e-05, "loss": 0.0476, "step": 93010 }, { "epoch": 22.33, "learning_rate": 8.925917878809165e-05, "loss": 0.0642, "step": 93020 }, { "epoch": 22.33, "learning_rate": 8.925695579807689e-05, "loss": 0.0431, "step": 93030 }, { "epoch": 22.33, "learning_rate": 8.925473260573145e-05, "loss": 0.0733, "step": 93040 }, { "epoch": 22.33, "learning_rate": 8.92525092110668e-05, "loss": 0.0478, "step": 93050 }, { "epoch": 22.34, "learning_rate": 8.92502856140944e-05, "loss": 0.0682, "step": 93060 }, { "epoch": 22.34, "learning_rate": 8.924806181482569e-05, "loss": 0.0654, "step": 93070 }, { "epoch": 22.34, "learning_rate": 8.924583781327213e-05, "loss": 0.0556, "step": 93080 }, { "epoch": 22.34, "learning_rate": 8.924361360944522e-05, "loss": 0.0755, "step": 93090 }, { "epoch": 22.35, "learning_rate": 8.924138920335639e-05, "loss": 0.0461, "step": 93100 }, { "epoch": 22.35, "learning_rate": 8.923916459501709e-05, "loss": 0.0405, "step": 93110 }, { "epoch": 22.35, "learning_rate": 8.923693978443884e-05, "loss": 0.04, "step": 93120 }, { "epoch": 22.35, "learning_rate": 8.923471477163304e-05, "loss": 0.0277, "step": 93130 }, { "epoch": 22.36, "learning_rate": 8.923248955661121e-05, "loss": 0.0649, "step": 93140 }, { "epoch": 22.36, "learning_rate": 8.92302641393848e-05, "loss": 0.0535, "step": 93150 }, { "epoch": 22.36, "learning_rate": 8.922803851996529e-05, "loss": 0.0568, "step": 93160 }, { "epoch": 22.36, "learning_rate": 8.922581269836412e-05, "loss": 0.0345, "step": 93170 }, { "epoch": 22.36, "learning_rate": 8.922358667459281e-05, "loss": 0.0301, "step": 93180 }, { "epoch": 22.37, "learning_rate": 8.922136044866278e-05, "loss": 0.0455, "step": 93190 }, { "epoch": 22.37, "learning_rate": 8.921913402058555e-05, "loss": 0.0583, "step": 93200 }, { "epoch": 22.37, "learning_rate": 8.921690739037256e-05, "loss": 0.0431, "step": 93210 }, { "epoch": 22.37, "learning_rate": 8.921468055803532e-05, "loss": 0.0307, "step": 93220 }, { "epoch": 22.38, "learning_rate": 8.921245352358528e-05, "loss": 0.0341, "step": 93230 }, { "epoch": 22.38, "learning_rate": 8.921022628703392e-05, "loss": 0.0539, "step": 93240 }, { "epoch": 22.38, "learning_rate": 8.920799884839272e-05, "loss": 0.056, "step": 93250 }, { "epoch": 22.38, "learning_rate": 8.920577120767319e-05, "loss": 0.0663, "step": 93260 }, { "epoch": 22.38, "learning_rate": 8.920354336488677e-05, "loss": 0.0383, "step": 93270 }, { "epoch": 22.39, "learning_rate": 8.920131532004497e-05, "loss": 0.0341, "step": 93280 }, { "epoch": 22.39, "learning_rate": 8.919908707315925e-05, "loss": 0.0806, "step": 93290 }, { "epoch": 22.39, "learning_rate": 8.919685862424112e-05, "loss": 0.0372, "step": 93300 }, { "epoch": 22.39, "learning_rate": 8.919462997330204e-05, "loss": 0.078, "step": 93310 }, { "epoch": 22.4, "learning_rate": 8.919240112035352e-05, "loss": 0.0317, "step": 93320 }, { "epoch": 22.4, "learning_rate": 8.919017206540703e-05, "loss": 0.047, "step": 93330 }, { "epoch": 22.4, "learning_rate": 8.918794280847407e-05, "loss": 0.0571, "step": 93340 }, { "epoch": 22.4, "learning_rate": 8.918571334956614e-05, "loss": 0.0502, "step": 93350 }, { "epoch": 22.41, "learning_rate": 8.918348368869469e-05, "loss": 0.0283, "step": 93360 }, { "epoch": 22.41, "learning_rate": 8.918125382587125e-05, "loss": 0.0454, "step": 93370 }, { "epoch": 22.41, "learning_rate": 8.91790237611073e-05, "loss": 0.0409, "step": 93380 }, { "epoch": 22.41, "learning_rate": 8.917679349441433e-05, "loss": 0.0565, "step": 93390 }, { "epoch": 22.41, "learning_rate": 8.917456302580385e-05, "loss": 0.0536, "step": 93400 }, { "epoch": 22.42, "learning_rate": 8.917233235528734e-05, "loss": 0.0689, "step": 93410 }, { "epoch": 22.42, "learning_rate": 8.917010148287629e-05, "loss": 0.0988, "step": 93420 }, { "epoch": 22.42, "learning_rate": 8.916787040858221e-05, "loss": 0.0399, "step": 93430 }, { "epoch": 22.42, "learning_rate": 8.91656391324166e-05, "loss": 0.057, "step": 93440 }, { "epoch": 22.43, "learning_rate": 8.916340765439097e-05, "loss": 0.0388, "step": 93450 }, { "epoch": 22.43, "learning_rate": 8.916117597451681e-05, "loss": 0.0562, "step": 93460 }, { "epoch": 22.43, "learning_rate": 8.915894409280562e-05, "loss": 0.0284, "step": 93470 }, { "epoch": 22.43, "learning_rate": 8.91567120092689e-05, "loss": 0.0554, "step": 93480 }, { "epoch": 22.44, "learning_rate": 8.915447972391816e-05, "loss": 0.0549, "step": 93490 }, { "epoch": 22.44, "learning_rate": 8.915224723676489e-05, "loss": 0.0838, "step": 93500 }, { "epoch": 22.44, "learning_rate": 8.915001454782064e-05, "loss": 0.0367, "step": 93510 }, { "epoch": 22.44, "learning_rate": 8.914778165709687e-05, "loss": 0.0377, "step": 93520 }, { "epoch": 22.44, "learning_rate": 8.91455485646051e-05, "loss": 0.0532, "step": 93530 }, { "epoch": 22.45, "learning_rate": 8.914331527035687e-05, "loss": 0.0456, "step": 93540 }, { "epoch": 22.45, "learning_rate": 8.914108177436364e-05, "loss": 0.0445, "step": 93550 }, { "epoch": 22.45, "learning_rate": 8.913884807663697e-05, "loss": 0.0641, "step": 93560 }, { "epoch": 22.45, "learning_rate": 8.913661417718832e-05, "loss": 0.058, "step": 93570 }, { "epoch": 22.46, "learning_rate": 8.913438007602926e-05, "loss": 0.0394, "step": 93580 }, { "epoch": 22.46, "learning_rate": 8.913214577317127e-05, "loss": 0.038, "step": 93590 }, { "epoch": 22.46, "learning_rate": 8.912991126862586e-05, "loss": 0.0469, "step": 93600 }, { "epoch": 22.46, "learning_rate": 8.912767656240459e-05, "loss": 0.0341, "step": 93610 }, { "epoch": 22.46, "learning_rate": 8.912544165451893e-05, "loss": 0.047, "step": 93620 }, { "epoch": 22.47, "learning_rate": 8.912320654498041e-05, "loss": 0.0661, "step": 93630 }, { "epoch": 22.47, "learning_rate": 8.912097123380057e-05, "loss": 0.0747, "step": 93640 }, { "epoch": 22.47, "learning_rate": 8.91187357209909e-05, "loss": 0.0319, "step": 93650 }, { "epoch": 22.47, "learning_rate": 8.911650000656295e-05, "loss": 0.0444, "step": 93660 }, { "epoch": 22.48, "learning_rate": 8.911426409052823e-05, "loss": 0.0652, "step": 93670 }, { "epoch": 22.48, "learning_rate": 8.911202797289829e-05, "loss": 0.0387, "step": 93680 }, { "epoch": 22.48, "learning_rate": 8.91097916536846e-05, "loss": 0.0499, "step": 93690 }, { "epoch": 22.48, "learning_rate": 8.910755513289873e-05, "loss": 0.0393, "step": 93700 }, { "epoch": 22.49, "learning_rate": 8.910531841055219e-05, "loss": 0.0476, "step": 93710 }, { "epoch": 22.49, "learning_rate": 8.91030814866565e-05, "loss": 0.0553, "step": 93720 }, { "epoch": 22.49, "learning_rate": 8.910084436122322e-05, "loss": 0.0503, "step": 93730 }, { "epoch": 22.49, "learning_rate": 8.909860703426384e-05, "loss": 0.0545, "step": 93740 }, { "epoch": 22.49, "learning_rate": 8.909636950578994e-05, "loss": 0.0449, "step": 93750 }, { "epoch": 22.5, "learning_rate": 8.909413177581301e-05, "loss": 0.0396, "step": 93760 }, { "epoch": 22.5, "learning_rate": 8.90918938443446e-05, "loss": 0.0394, "step": 93770 }, { "epoch": 22.5, "learning_rate": 8.908965571139623e-05, "loss": 0.0398, "step": 93780 }, { "epoch": 22.5, "learning_rate": 8.908741737697946e-05, "loss": 0.0408, "step": 93790 }, { "epoch": 22.51, "learning_rate": 8.908517884110582e-05, "loss": 0.078, "step": 93800 }, { "epoch": 22.51, "learning_rate": 8.908294010378684e-05, "loss": 0.0474, "step": 93810 }, { "epoch": 22.51, "learning_rate": 8.908070116503404e-05, "loss": 0.0374, "step": 93820 }, { "epoch": 22.51, "learning_rate": 8.907846202485901e-05, "loss": 0.0492, "step": 93830 }, { "epoch": 22.52, "learning_rate": 8.907622268327324e-05, "loss": 0.0457, "step": 93840 }, { "epoch": 22.52, "learning_rate": 8.90739831402883e-05, "loss": 0.0814, "step": 93850 }, { "epoch": 22.52, "learning_rate": 8.907174339591572e-05, "loss": 0.0909, "step": 93860 }, { "epoch": 22.52, "learning_rate": 8.906950345016705e-05, "loss": 0.0676, "step": 93870 }, { "epoch": 22.52, "learning_rate": 8.906726330305383e-05, "loss": 0.0252, "step": 93880 }, { "epoch": 22.53, "learning_rate": 8.90650229545876e-05, "loss": 0.0709, "step": 93890 }, { "epoch": 22.53, "learning_rate": 8.906278240477993e-05, "loss": 0.0524, "step": 93900 }, { "epoch": 22.53, "learning_rate": 8.906054165364235e-05, "loss": 0.066, "step": 93910 }, { "epoch": 22.53, "learning_rate": 8.905830070118642e-05, "loss": 0.0575, "step": 93920 }, { "epoch": 22.54, "learning_rate": 8.905605954742367e-05, "loss": 0.0679, "step": 93930 }, { "epoch": 22.54, "learning_rate": 8.905381819236565e-05, "loss": 0.0993, "step": 93940 }, { "epoch": 22.54, "learning_rate": 8.905157663602395e-05, "loss": 0.0778, "step": 93950 }, { "epoch": 22.54, "learning_rate": 8.904933487841007e-05, "loss": 0.0654, "step": 93960 }, { "epoch": 22.54, "learning_rate": 8.904709291953561e-05, "loss": 0.058, "step": 93970 }, { "epoch": 22.55, "learning_rate": 8.904485075941211e-05, "loss": 0.061, "step": 93980 }, { "epoch": 22.55, "learning_rate": 8.904260839805111e-05, "loss": 0.0664, "step": 93990 }, { "epoch": 22.55, "learning_rate": 8.90403658354642e-05, "loss": 0.08, "step": 94000 }, { "epoch": 22.55, "learning_rate": 8.903812307166291e-05, "loss": 0.0973, "step": 94010 }, { "epoch": 22.56, "learning_rate": 8.903588010665879e-05, "loss": 0.0775, "step": 94020 }, { "epoch": 22.56, "learning_rate": 8.903363694046343e-05, "loss": 0.0941, "step": 94030 }, { "epoch": 22.56, "learning_rate": 8.903139357308838e-05, "loss": 0.0979, "step": 94040 }, { "epoch": 22.56, "learning_rate": 8.902915000454521e-05, "loss": 0.0714, "step": 94050 }, { "epoch": 22.57, "learning_rate": 8.902690623484546e-05, "loss": 0.0623, "step": 94060 }, { "epoch": 22.57, "learning_rate": 8.902466226400073e-05, "loss": 0.0799, "step": 94070 }, { "epoch": 22.57, "learning_rate": 8.902241809202254e-05, "loss": 0.0643, "step": 94080 }, { "epoch": 22.57, "learning_rate": 8.902017371892248e-05, "loss": 0.0687, "step": 94090 }, { "epoch": 22.57, "learning_rate": 8.901792914471213e-05, "loss": 0.0539, "step": 94100 }, { "epoch": 22.58, "learning_rate": 8.901568436940304e-05, "loss": 0.0831, "step": 94110 }, { "epoch": 22.58, "learning_rate": 8.90134393930068e-05, "loss": 0.074, "step": 94120 }, { "epoch": 22.58, "learning_rate": 8.901119421553496e-05, "loss": 0.0875, "step": 94130 }, { "epoch": 22.58, "learning_rate": 8.900894883699911e-05, "loss": 0.0788, "step": 94140 }, { "epoch": 22.59, "learning_rate": 8.900670325741078e-05, "loss": 0.0744, "step": 94150 }, { "epoch": 22.59, "learning_rate": 8.900445747678161e-05, "loss": 0.0753, "step": 94160 }, { "epoch": 22.59, "learning_rate": 8.900221149512312e-05, "loss": 0.1189, "step": 94170 }, { "epoch": 22.59, "learning_rate": 8.899996531244691e-05, "loss": 0.0626, "step": 94180 }, { "epoch": 22.6, "learning_rate": 8.899771892876454e-05, "loss": 0.0745, "step": 94190 }, { "epoch": 22.6, "learning_rate": 8.899547234408763e-05, "loss": 0.0982, "step": 94200 }, { "epoch": 22.6, "learning_rate": 8.899322555842772e-05, "loss": 0.0702, "step": 94210 }, { "epoch": 22.6, "learning_rate": 8.899097857179639e-05, "loss": 0.0598, "step": 94220 }, { "epoch": 22.6, "learning_rate": 8.898873138420523e-05, "loss": 0.0597, "step": 94230 }, { "epoch": 22.61, "learning_rate": 8.898648399566583e-05, "loss": 0.0804, "step": 94240 }, { "epoch": 22.61, "learning_rate": 8.898423640618976e-05, "loss": 0.0542, "step": 94250 }, { "epoch": 22.61, "learning_rate": 8.898198861578862e-05, "loss": 0.0674, "step": 94260 }, { "epoch": 22.61, "learning_rate": 8.897974062447396e-05, "loss": 0.083, "step": 94270 }, { "epoch": 22.62, "learning_rate": 8.897749243225742e-05, "loss": 0.0971, "step": 94280 }, { "epoch": 22.62, "learning_rate": 8.897524403915054e-05, "loss": 0.0893, "step": 94290 }, { "epoch": 22.62, "learning_rate": 8.897299544516494e-05, "loss": 0.0842, "step": 94300 }, { "epoch": 22.62, "learning_rate": 8.89707466503122e-05, "loss": 0.078, "step": 94310 }, { "epoch": 22.62, "learning_rate": 8.896849765460389e-05, "loss": 0.0685, "step": 94320 }, { "epoch": 22.63, "learning_rate": 8.896624845805162e-05, "loss": 0.0957, "step": 94330 }, { "epoch": 22.63, "learning_rate": 8.896399906066697e-05, "loss": 0.0383, "step": 94340 }, { "epoch": 22.63, "learning_rate": 8.896174946246156e-05, "loss": 0.0937, "step": 94350 }, { "epoch": 22.63, "learning_rate": 8.895949966344697e-05, "loss": 0.0764, "step": 94360 }, { "epoch": 22.64, "learning_rate": 8.895724966363477e-05, "loss": 0.0515, "step": 94370 }, { "epoch": 22.64, "learning_rate": 8.89549994630366e-05, "loss": 0.0723, "step": 94380 }, { "epoch": 22.64, "learning_rate": 8.895274906166404e-05, "loss": 0.0775, "step": 94390 }, { "epoch": 22.64, "learning_rate": 8.895049845952868e-05, "loss": 0.0601, "step": 94400 }, { "epoch": 22.65, "learning_rate": 8.894824765664212e-05, "loss": 0.0647, "step": 94410 }, { "epoch": 22.65, "learning_rate": 8.894599665301597e-05, "loss": 0.0507, "step": 94420 }, { "epoch": 22.65, "learning_rate": 8.894374544866182e-05, "loss": 0.0662, "step": 94430 }, { "epoch": 22.65, "learning_rate": 8.894149404359129e-05, "loss": 0.0601, "step": 94440 }, { "epoch": 22.65, "learning_rate": 8.893924243781597e-05, "loss": 0.0755, "step": 94450 }, { "epoch": 22.66, "learning_rate": 8.893699063134748e-05, "loss": 0.0913, "step": 94460 }, { "epoch": 22.66, "learning_rate": 8.89347386241974e-05, "loss": 0.0694, "step": 94470 }, { "epoch": 22.66, "learning_rate": 8.893248641637736e-05, "loss": 0.064, "step": 94480 }, { "epoch": 22.66, "learning_rate": 8.893023400789895e-05, "loss": 0.0645, "step": 94490 }, { "epoch": 22.67, "learning_rate": 8.89279813987738e-05, "loss": 0.0622, "step": 94500 }, { "epoch": 22.67, "learning_rate": 8.89257285890135e-05, "loss": 0.0709, "step": 94510 }, { "epoch": 22.67, "learning_rate": 8.892347557862968e-05, "loss": 0.0558, "step": 94520 }, { "epoch": 22.67, "learning_rate": 8.892122236763393e-05, "loss": 0.0358, "step": 94530 }, { "epoch": 22.68, "learning_rate": 8.891896895603789e-05, "loss": 0.0549, "step": 94540 }, { "epoch": 22.68, "learning_rate": 8.891671534385314e-05, "loss": 0.06, "step": 94550 }, { "epoch": 22.68, "learning_rate": 8.891446153109132e-05, "loss": 0.051, "step": 94560 }, { "epoch": 22.68, "learning_rate": 8.891220751776403e-05, "loss": 0.053, "step": 94570 }, { "epoch": 22.68, "learning_rate": 8.890995330388292e-05, "loss": 0.0655, "step": 94580 }, { "epoch": 22.69, "learning_rate": 8.890769888945958e-05, "loss": 0.0449, "step": 94590 }, { "epoch": 22.69, "learning_rate": 8.890544427450563e-05, "loss": 0.0831, "step": 94600 }, { "epoch": 22.69, "learning_rate": 8.890318945903269e-05, "loss": 0.0616, "step": 94610 }, { "epoch": 22.69, "learning_rate": 8.890093444305239e-05, "loss": 0.0481, "step": 94620 }, { "epoch": 22.7, "learning_rate": 8.889867922657635e-05, "loss": 0.0789, "step": 94630 }, { "epoch": 22.7, "learning_rate": 8.88964238096162e-05, "loss": 0.0834, "step": 94640 }, { "epoch": 22.7, "learning_rate": 8.889416819218354e-05, "loss": 0.0559, "step": 94650 }, { "epoch": 22.7, "learning_rate": 8.889191237429002e-05, "loss": 0.0388, "step": 94660 }, { "epoch": 22.7, "learning_rate": 8.888965635594726e-05, "loss": 0.0726, "step": 94670 }, { "epoch": 22.71, "learning_rate": 8.888740013716688e-05, "loss": 0.0622, "step": 94680 }, { "epoch": 22.71, "learning_rate": 8.888514371796053e-05, "loss": 0.0554, "step": 94690 }, { "epoch": 22.71, "learning_rate": 8.888288709833981e-05, "loss": 0.0535, "step": 94700 }, { "epoch": 22.71, "learning_rate": 8.888063027831637e-05, "loss": 0.0631, "step": 94710 }, { "epoch": 22.72, "learning_rate": 8.887837325790183e-05, "loss": 0.063, "step": 94720 }, { "epoch": 22.72, "learning_rate": 8.887611603710784e-05, "loss": 0.0439, "step": 94730 }, { "epoch": 22.72, "learning_rate": 8.887385861594602e-05, "loss": 0.088, "step": 94740 }, { "epoch": 22.72, "learning_rate": 8.8871600994428e-05, "loss": 0.0907, "step": 94750 }, { "epoch": 22.73, "learning_rate": 8.886934317256542e-05, "loss": 0.0722, "step": 94760 }, { "epoch": 22.73, "learning_rate": 8.886708515036994e-05, "loss": 0.054, "step": 94770 }, { "epoch": 22.73, "learning_rate": 8.886482692785316e-05, "loss": 0.0916, "step": 94780 }, { "epoch": 22.73, "learning_rate": 8.886256850502675e-05, "loss": 0.055, "step": 94790 }, { "epoch": 22.73, "learning_rate": 8.886030988190232e-05, "loss": 0.0739, "step": 94800 }, { "epoch": 22.74, "learning_rate": 8.885805105849154e-05, "loss": 0.0777, "step": 94810 }, { "epoch": 22.74, "learning_rate": 8.885579203480606e-05, "loss": 0.0763, "step": 94820 }, { "epoch": 22.74, "learning_rate": 8.885353281085747e-05, "loss": 0.0475, "step": 94830 }, { "epoch": 22.74, "learning_rate": 8.885127338665746e-05, "loss": 0.0597, "step": 94840 }, { "epoch": 22.75, "learning_rate": 8.884901376221766e-05, "loss": 0.0776, "step": 94850 }, { "epoch": 22.75, "learning_rate": 8.88467539375497e-05, "loss": 0.0585, "step": 94860 }, { "epoch": 22.75, "learning_rate": 8.884449391266529e-05, "loss": 0.0579, "step": 94870 }, { "epoch": 22.75, "learning_rate": 8.8842233687576e-05, "loss": 0.0604, "step": 94880 }, { "epoch": 22.76, "learning_rate": 8.883997326229352e-05, "loss": 0.0609, "step": 94890 }, { "epoch": 22.76, "learning_rate": 8.88377126368295e-05, "loss": 0.0523, "step": 94900 }, { "epoch": 22.76, "learning_rate": 8.883545181119558e-05, "loss": 0.0834, "step": 94910 }, { "epoch": 22.76, "learning_rate": 8.883319078540342e-05, "loss": 0.0542, "step": 94920 }, { "epoch": 22.76, "learning_rate": 8.883092955946465e-05, "loss": 0.0554, "step": 94930 }, { "epoch": 22.77, "learning_rate": 8.882866813339096e-05, "loss": 0.0312, "step": 94940 }, { "epoch": 22.77, "learning_rate": 8.8826406507194e-05, "loss": 0.0658, "step": 94950 }, { "epoch": 22.77, "learning_rate": 8.882414468088541e-05, "loss": 0.1033, "step": 94960 }, { "epoch": 22.77, "learning_rate": 8.882188265447686e-05, "loss": 0.0552, "step": 94970 }, { "epoch": 22.78, "learning_rate": 8.881962042797999e-05, "loss": 0.0666, "step": 94980 }, { "epoch": 22.78, "learning_rate": 8.881735800140647e-05, "loss": 0.0726, "step": 94990 }, { "epoch": 22.78, "learning_rate": 8.881509537476797e-05, "loss": 0.0502, "step": 95000 }, { "epoch": 22.78, "learning_rate": 8.881283254807614e-05, "loss": 0.0457, "step": 95010 }, { "epoch": 22.78, "learning_rate": 8.881056952134265e-05, "loss": 0.0885, "step": 95020 }, { "epoch": 22.79, "learning_rate": 8.880830629457917e-05, "loss": 0.077, "step": 95030 }, { "epoch": 22.79, "learning_rate": 8.880604286779733e-05, "loss": 0.0533, "step": 95040 }, { "epoch": 22.79, "learning_rate": 8.880377924100885e-05, "loss": 0.0712, "step": 95050 }, { "epoch": 22.79, "learning_rate": 8.880151541422534e-05, "loss": 0.0597, "step": 95060 }, { "epoch": 22.8, "learning_rate": 8.87992513874585e-05, "loss": 0.0594, "step": 95070 }, { "epoch": 22.8, "learning_rate": 8.879698716072e-05, "loss": 0.0548, "step": 95080 }, { "epoch": 22.8, "learning_rate": 8.879472273402152e-05, "loss": 0.0703, "step": 95090 }, { "epoch": 22.8, "learning_rate": 8.879245810737469e-05, "loss": 0.0527, "step": 95100 }, { "epoch": 22.81, "learning_rate": 8.879019328079122e-05, "loss": 0.0569, "step": 95110 }, { "epoch": 22.81, "learning_rate": 8.878792825428277e-05, "loss": 0.0465, "step": 95120 }, { "epoch": 22.81, "learning_rate": 8.8785663027861e-05, "loss": 0.0739, "step": 95130 }, { "epoch": 22.81, "learning_rate": 8.878339760153762e-05, "loss": 0.0859, "step": 95140 }, { "epoch": 22.81, "learning_rate": 8.878113197532427e-05, "loss": 0.0683, "step": 95150 }, { "epoch": 22.82, "learning_rate": 8.877886614923264e-05, "loss": 0.0405, "step": 95160 }, { "epoch": 22.82, "learning_rate": 8.877660012327442e-05, "loss": 0.0566, "step": 95170 }, { "epoch": 22.82, "learning_rate": 8.877433389746126e-05, "loss": 0.0634, "step": 95180 }, { "epoch": 22.82, "learning_rate": 8.877206747180487e-05, "loss": 0.0512, "step": 95190 }, { "epoch": 22.83, "learning_rate": 8.876980084631693e-05, "loss": 0.0456, "step": 95200 }, { "epoch": 22.83, "learning_rate": 8.876753402100911e-05, "loss": 0.0443, "step": 95210 }, { "epoch": 22.83, "learning_rate": 8.87652669958931e-05, "loss": 0.0778, "step": 95220 }, { "epoch": 22.83, "learning_rate": 8.876299977098055e-05, "loss": 0.0712, "step": 95230 }, { "epoch": 22.84, "learning_rate": 8.87607323462832e-05, "loss": 0.0433, "step": 95240 }, { "epoch": 22.84, "learning_rate": 8.87584647218127e-05, "loss": 0.0731, "step": 95250 }, { "epoch": 22.84, "learning_rate": 8.875619689758076e-05, "loss": 0.0422, "step": 95260 }, { "epoch": 22.84, "learning_rate": 8.875392887359906e-05, "loss": 0.0479, "step": 95270 }, { "epoch": 22.84, "learning_rate": 8.875166064987928e-05, "loss": 0.0473, "step": 95280 }, { "epoch": 22.85, "learning_rate": 8.874939222643311e-05, "loss": 0.032, "step": 95290 }, { "epoch": 22.85, "learning_rate": 8.874712360327225e-05, "loss": 0.0578, "step": 95300 }, { "epoch": 22.85, "learning_rate": 8.874485478040839e-05, "loss": 0.0556, "step": 95310 }, { "epoch": 22.85, "learning_rate": 8.874258575785323e-05, "loss": 0.0476, "step": 95320 }, { "epoch": 22.86, "learning_rate": 8.874031653561847e-05, "loss": 0.0423, "step": 95330 }, { "epoch": 22.86, "learning_rate": 8.873804711371578e-05, "loss": 0.0682, "step": 95340 }, { "epoch": 22.86, "learning_rate": 8.873577749215687e-05, "loss": 0.0438, "step": 95350 }, { "epoch": 22.86, "learning_rate": 8.873350767095346e-05, "loss": 0.0688, "step": 95360 }, { "epoch": 22.86, "learning_rate": 8.873123765011721e-05, "loss": 0.0533, "step": 95370 }, { "epoch": 22.87, "learning_rate": 8.872896742965984e-05, "loss": 0.0564, "step": 95380 }, { "epoch": 22.87, "learning_rate": 8.872669700959305e-05, "loss": 0.069, "step": 95390 }, { "epoch": 22.87, "learning_rate": 8.872442638992853e-05, "loss": 0.0674, "step": 95400 }, { "epoch": 22.87, "learning_rate": 8.8722155570678e-05, "loss": 0.0351, "step": 95410 }, { "epoch": 22.88, "learning_rate": 8.871988455185317e-05, "loss": 0.0445, "step": 95420 }, { "epoch": 22.88, "learning_rate": 8.87176133334657e-05, "loss": 0.0491, "step": 95430 }, { "epoch": 22.88, "learning_rate": 8.871534191552735e-05, "loss": 0.0894, "step": 95440 }, { "epoch": 22.88, "learning_rate": 8.87130702980498e-05, "loss": 0.0498, "step": 95450 }, { "epoch": 22.89, "learning_rate": 8.871079848104476e-05, "loss": 0.0507, "step": 95460 }, { "epoch": 22.89, "learning_rate": 8.870852646452394e-05, "loss": 0.053, "step": 95470 }, { "epoch": 22.89, "learning_rate": 8.870625424849906e-05, "loss": 0.0463, "step": 95480 }, { "epoch": 22.89, "learning_rate": 8.870398183298181e-05, "loss": 0.058, "step": 95490 }, { "epoch": 22.89, "learning_rate": 8.870170921798393e-05, "loss": 0.0798, "step": 95500 }, { "epoch": 22.9, "learning_rate": 8.869943640351711e-05, "loss": 0.0484, "step": 95510 }, { "epoch": 22.9, "learning_rate": 8.869716338959307e-05, "loss": 0.0398, "step": 95520 }, { "epoch": 22.9, "learning_rate": 8.869489017622352e-05, "loss": 0.0346, "step": 95530 }, { "epoch": 22.9, "learning_rate": 8.869261676342019e-05, "loss": 0.055, "step": 95540 }, { "epoch": 22.91, "learning_rate": 8.869034315119479e-05, "loss": 0.0932, "step": 95550 }, { "epoch": 22.91, "learning_rate": 8.868806933955903e-05, "loss": 0.057, "step": 95560 }, { "epoch": 22.91, "learning_rate": 8.868579532852466e-05, "loss": 0.0406, "step": 95570 }, { "epoch": 22.91, "learning_rate": 8.868352111810335e-05, "loss": 0.0487, "step": 95580 }, { "epoch": 22.91, "learning_rate": 8.868124670830686e-05, "loss": 0.0743, "step": 95590 }, { "epoch": 22.92, "learning_rate": 8.86789720991469e-05, "loss": 0.0505, "step": 95600 }, { "epoch": 22.92, "learning_rate": 8.867669729063519e-05, "loss": 0.0384, "step": 95610 }, { "epoch": 22.92, "learning_rate": 8.867442228278346e-05, "loss": 0.0542, "step": 95620 }, { "epoch": 22.92, "learning_rate": 8.867214707560345e-05, "loss": 0.0411, "step": 95630 }, { "epoch": 22.93, "learning_rate": 8.866987166910685e-05, "loss": 0.0501, "step": 95640 }, { "epoch": 22.93, "learning_rate": 8.866759606330541e-05, "loss": 0.0547, "step": 95650 }, { "epoch": 22.93, "learning_rate": 8.866532025821088e-05, "loss": 0.0522, "step": 95660 }, { "epoch": 22.93, "learning_rate": 8.866304425383493e-05, "loss": 0.0537, "step": 95670 }, { "epoch": 22.94, "learning_rate": 8.866076805018937e-05, "loss": 0.0343, "step": 95680 }, { "epoch": 22.94, "learning_rate": 8.865849164728586e-05, "loss": 0.044, "step": 95690 }, { "epoch": 22.94, "learning_rate": 8.865621504513616e-05, "loss": 0.0626, "step": 95700 }, { "epoch": 22.94, "learning_rate": 8.865393824375201e-05, "loss": 0.0767, "step": 95710 }, { "epoch": 22.94, "learning_rate": 8.865166124314515e-05, "loss": 0.0566, "step": 95720 }, { "epoch": 22.95, "learning_rate": 8.864938404332729e-05, "loss": 0.0664, "step": 95730 }, { "epoch": 22.95, "learning_rate": 8.864710664431017e-05, "loss": 0.0564, "step": 95740 }, { "epoch": 23.0, "learning_rate": 8.864482904610557e-05, "loss": 0.0534, "step": 95750 }, { "epoch": 23.0, "learning_rate": 8.864255124872518e-05, "loss": 0.0531, "step": 95760 }, { "epoch": 23.0, "learning_rate": 8.864027325218076e-05, "loss": 0.0794, "step": 95770 }, { "epoch": 23.01, "learning_rate": 8.863799505648404e-05, "loss": 0.0473, "step": 95780 }, { "epoch": 23.01, "learning_rate": 8.86357166616468e-05, "loss": 0.0444, "step": 95790 }, { "epoch": 23.01, "learning_rate": 8.863343806768071e-05, "loss": 0.0414, "step": 95800 }, { "epoch": 23.01, "learning_rate": 8.863115927459759e-05, "loss": 0.0746, "step": 95810 }, { "epoch": 23.02, "learning_rate": 8.862888028240916e-05, "loss": 0.0705, "step": 95820 }, { "epoch": 23.02, "learning_rate": 8.862660109112712e-05, "loss": 0.0368, "step": 95830 }, { "epoch": 23.02, "learning_rate": 8.862432170076329e-05, "loss": 0.0504, "step": 95840 }, { "epoch": 23.02, "learning_rate": 8.862204211132936e-05, "loss": 0.0365, "step": 95850 }, { "epoch": 23.03, "learning_rate": 8.861976232283713e-05, "loss": 0.04, "step": 95860 }, { "epoch": 23.03, "learning_rate": 8.86174823352983e-05, "loss": 0.0507, "step": 95870 }, { "epoch": 23.03, "learning_rate": 8.861520214872464e-05, "loss": 0.051, "step": 95880 }, { "epoch": 23.03, "learning_rate": 8.861292176312791e-05, "loss": 0.0548, "step": 95890 }, { "epoch": 23.03, "learning_rate": 8.861064117851987e-05, "loss": 0.053, "step": 95900 }, { "epoch": 23.04, "learning_rate": 8.860836039491225e-05, "loss": 0.0534, "step": 95910 }, { "epoch": 23.04, "learning_rate": 8.860607941231682e-05, "loss": 0.0459, "step": 95920 }, { "epoch": 23.04, "learning_rate": 8.860379823074534e-05, "loss": 0.079, "step": 95930 }, { "epoch": 23.04, "learning_rate": 8.860151685020954e-05, "loss": 0.0513, "step": 95940 }, { "epoch": 23.05, "learning_rate": 8.859923527072122e-05, "loss": 0.0808, "step": 95950 }, { "epoch": 23.05, "learning_rate": 8.859695349229212e-05, "loss": 0.0612, "step": 95960 }, { "epoch": 23.05, "learning_rate": 8.859467151493399e-05, "loss": 0.0461, "step": 95970 }, { "epoch": 23.05, "learning_rate": 8.859238933865861e-05, "loss": 0.0486, "step": 95980 }, { "epoch": 23.06, "learning_rate": 8.859010696347772e-05, "loss": 0.0475, "step": 95990 }, { "epoch": 23.06, "learning_rate": 8.858782438940312e-05, "loss": 0.0546, "step": 96000 }, { "epoch": 23.06, "learning_rate": 8.858554161644652e-05, "loss": 0.0528, "step": 96010 }, { "epoch": 23.06, "learning_rate": 8.858325864461973e-05, "loss": 0.0704, "step": 96020 }, { "epoch": 23.06, "learning_rate": 8.85809754739345e-05, "loss": 0.0454, "step": 96030 }, { "epoch": 23.07, "learning_rate": 8.857869210440262e-05, "loss": 0.0402, "step": 96040 }, { "epoch": 23.07, "learning_rate": 8.857640853603581e-05, "loss": 0.0533, "step": 96050 }, { "epoch": 23.07, "learning_rate": 8.857412476884587e-05, "loss": 0.0327, "step": 96060 }, { "epoch": 23.07, "learning_rate": 8.857184080284459e-05, "loss": 0.0625, "step": 96070 }, { "epoch": 23.08, "learning_rate": 8.856955663804371e-05, "loss": 0.0515, "step": 96080 }, { "epoch": 23.08, "learning_rate": 8.856727227445501e-05, "loss": 0.078, "step": 96090 }, { "epoch": 23.08, "learning_rate": 8.856498771209026e-05, "loss": 0.0405, "step": 96100 }, { "epoch": 23.08, "learning_rate": 8.856270295096126e-05, "loss": 0.0629, "step": 96110 }, { "epoch": 23.08, "learning_rate": 8.856041799107974e-05, "loss": 0.041, "step": 96120 }, { "epoch": 23.09, "learning_rate": 8.855813283245752e-05, "loss": 0.0514, "step": 96130 }, { "epoch": 23.09, "learning_rate": 8.855584747510636e-05, "loss": 0.0416, "step": 96140 }, { "epoch": 23.09, "learning_rate": 8.855356191903802e-05, "loss": 0.0691, "step": 96150 }, { "epoch": 23.09, "learning_rate": 8.855127616426434e-05, "loss": 0.0544, "step": 96160 }, { "epoch": 23.1, "learning_rate": 8.854899021079703e-05, "loss": 0.0522, "step": 96170 }, { "epoch": 23.1, "learning_rate": 8.85467040586479e-05, "loss": 0.0764, "step": 96180 }, { "epoch": 23.1, "learning_rate": 8.854441770782876e-05, "loss": 0.0592, "step": 96190 }, { "epoch": 23.1, "learning_rate": 8.854213115835134e-05, "loss": 0.0553, "step": 96200 }, { "epoch": 23.11, "learning_rate": 8.853984441022748e-05, "loss": 0.061, "step": 96210 }, { "epoch": 23.11, "learning_rate": 8.853755746346892e-05, "loss": 0.0562, "step": 96220 }, { "epoch": 23.11, "learning_rate": 8.853527031808749e-05, "loss": 0.085, "step": 96230 }, { "epoch": 23.11, "learning_rate": 8.853298297409494e-05, "loss": 0.0378, "step": 96240 }, { "epoch": 23.11, "learning_rate": 8.853069543150307e-05, "loss": 0.0508, "step": 96250 }, { "epoch": 23.12, "learning_rate": 8.852840769032367e-05, "loss": 0.0328, "step": 96260 }, { "epoch": 23.12, "learning_rate": 8.852611975056855e-05, "loss": 0.061, "step": 96270 }, { "epoch": 23.12, "learning_rate": 8.852383161224946e-05, "loss": 0.0488, "step": 96280 }, { "epoch": 23.12, "learning_rate": 8.852154327537824e-05, "loss": 0.0592, "step": 96290 }, { "epoch": 23.13, "learning_rate": 8.851925473996667e-05, "loss": 0.0617, "step": 96300 }, { "epoch": 23.13, "learning_rate": 8.851696600602653e-05, "loss": 0.026, "step": 96310 }, { "epoch": 23.13, "learning_rate": 8.851467707356963e-05, "loss": 0.0664, "step": 96320 }, { "epoch": 23.13, "learning_rate": 8.851238794260776e-05, "loss": 0.0651, "step": 96330 }, { "epoch": 23.14, "learning_rate": 8.851009861315271e-05, "loss": 0.0457, "step": 96340 }, { "epoch": 23.14, "learning_rate": 8.85078090852163e-05, "loss": 0.0389, "step": 96350 }, { "epoch": 23.14, "learning_rate": 8.850551935881033e-05, "loss": 0.0309, "step": 96360 }, { "epoch": 23.14, "learning_rate": 8.850322943394658e-05, "loss": 0.0297, "step": 96370 }, { "epoch": 23.14, "learning_rate": 8.850093931063685e-05, "loss": 0.0319, "step": 96380 }, { "epoch": 23.15, "learning_rate": 8.849864898889299e-05, "loss": 0.0391, "step": 96390 }, { "epoch": 23.15, "learning_rate": 8.849635846872675e-05, "loss": 0.0565, "step": 96400 }, { "epoch": 23.15, "learning_rate": 8.849406775014996e-05, "loss": 0.0466, "step": 96410 }, { "epoch": 23.15, "learning_rate": 8.849177683317442e-05, "loss": 0.056, "step": 96420 }, { "epoch": 23.16, "learning_rate": 8.848948571781194e-05, "loss": 0.0712, "step": 96430 }, { "epoch": 23.16, "learning_rate": 8.848719440407434e-05, "loss": 0.0548, "step": 96440 }, { "epoch": 23.16, "learning_rate": 8.84849028919734e-05, "loss": 0.0688, "step": 96450 }, { "epoch": 23.16, "learning_rate": 8.848261118152096e-05, "loss": 0.071, "step": 96460 }, { "epoch": 23.16, "learning_rate": 8.848031927272881e-05, "loss": 0.0617, "step": 96470 }, { "epoch": 23.17, "learning_rate": 8.84780271656088e-05, "loss": 0.0652, "step": 96480 }, { "epoch": 23.17, "learning_rate": 8.847573486017268e-05, "loss": 0.045, "step": 96490 }, { "epoch": 23.17, "learning_rate": 8.847344235643233e-05, "loss": 0.0318, "step": 96500 }, { "epoch": 23.17, "learning_rate": 8.847114965439954e-05, "loss": 0.0899, "step": 96510 }, { "epoch": 23.18, "learning_rate": 8.84688567540861e-05, "loss": 0.078, "step": 96520 }, { "epoch": 23.18, "learning_rate": 8.846656365550385e-05, "loss": 0.0514, "step": 96530 }, { "epoch": 23.18, "learning_rate": 8.846427035866463e-05, "loss": 0.0549, "step": 96540 }, { "epoch": 23.18, "learning_rate": 8.846197686358023e-05, "loss": 0.0412, "step": 96550 }, { "epoch": 23.19, "learning_rate": 8.845968317026247e-05, "loss": 0.0469, "step": 96560 }, { "epoch": 23.19, "learning_rate": 8.845738927872319e-05, "loss": 0.0311, "step": 96570 }, { "epoch": 23.19, "learning_rate": 8.845509518897421e-05, "loss": 0.0391, "step": 96580 }, { "epoch": 23.19, "learning_rate": 8.845280090102734e-05, "loss": 0.0464, "step": 96590 }, { "epoch": 23.19, "learning_rate": 8.84505064148944e-05, "loss": 0.0575, "step": 96600 }, { "epoch": 23.2, "learning_rate": 8.844821173058726e-05, "loss": 0.0473, "step": 96610 }, { "epoch": 23.2, "learning_rate": 8.844591684811769e-05, "loss": 0.0346, "step": 96620 }, { "epoch": 23.2, "learning_rate": 8.844362176749755e-05, "loss": 0.0392, "step": 96630 }, { "epoch": 23.2, "learning_rate": 8.844132648873866e-05, "loss": 0.0549, "step": 96640 }, { "epoch": 23.21, "learning_rate": 8.843903101185287e-05, "loss": 0.0634, "step": 96650 }, { "epoch": 23.21, "learning_rate": 8.843673533685197e-05, "loss": 0.0622, "step": 96660 }, { "epoch": 23.21, "learning_rate": 8.843443946374784e-05, "loss": 0.0479, "step": 96670 }, { "epoch": 23.21, "learning_rate": 8.843214339255226e-05, "loss": 0.0417, "step": 96680 }, { "epoch": 23.22, "learning_rate": 8.84298471232771e-05, "loss": 0.0592, "step": 96690 }, { "epoch": 23.22, "learning_rate": 8.842755065593418e-05, "loss": 0.05, "step": 96700 }, { "epoch": 23.22, "learning_rate": 8.842525399053536e-05, "loss": 0.0474, "step": 96710 }, { "epoch": 23.22, "learning_rate": 8.842295712709245e-05, "loss": 0.041, "step": 96720 }, { "epoch": 23.22, "learning_rate": 8.84206600656173e-05, "loss": 0.0462, "step": 96730 }, { "epoch": 23.23, "learning_rate": 8.841836280612174e-05, "loss": 0.0573, "step": 96740 }, { "epoch": 23.23, "learning_rate": 8.841606534861763e-05, "loss": 0.0287, "step": 96750 }, { "epoch": 23.23, "learning_rate": 8.84137676931168e-05, "loss": 0.0504, "step": 96760 }, { "epoch": 23.23, "learning_rate": 8.841146983963107e-05, "loss": 0.0309, "step": 96770 }, { "epoch": 23.24, "learning_rate": 8.840917178817232e-05, "loss": 0.0448, "step": 96780 }, { "epoch": 23.24, "learning_rate": 8.840687353875237e-05, "loss": 0.0541, "step": 96790 }, { "epoch": 23.24, "learning_rate": 8.840457509138307e-05, "loss": 0.0453, "step": 96800 }, { "epoch": 23.24, "learning_rate": 8.840227644607629e-05, "loss": 0.05, "step": 96810 }, { "epoch": 23.24, "learning_rate": 8.839997760284383e-05, "loss": 0.0428, "step": 96820 }, { "epoch": 23.25, "learning_rate": 8.839767856169757e-05, "loss": 0.0318, "step": 96830 }, { "epoch": 23.25, "learning_rate": 8.839537932264936e-05, "loss": 0.0581, "step": 96840 }, { "epoch": 23.25, "learning_rate": 8.839307988571103e-05, "loss": 0.0613, "step": 96850 }, { "epoch": 23.25, "learning_rate": 8.839078025089448e-05, "loss": 0.0434, "step": 96860 }, { "epoch": 23.26, "learning_rate": 8.83884804182115e-05, "loss": 0.0471, "step": 96870 }, { "epoch": 23.26, "learning_rate": 8.838618038767397e-05, "loss": 0.0374, "step": 96880 }, { "epoch": 23.26, "learning_rate": 8.838388015929375e-05, "loss": 0.0303, "step": 96890 }, { "epoch": 23.26, "learning_rate": 8.83815797330827e-05, "loss": 0.0789, "step": 96900 }, { "epoch": 23.27, "learning_rate": 8.837927910905266e-05, "loss": 0.0408, "step": 96910 }, { "epoch": 23.27, "learning_rate": 8.83769782872155e-05, "loss": 0.0398, "step": 96920 }, { "epoch": 23.27, "learning_rate": 8.837467726758306e-05, "loss": 0.0484, "step": 96930 }, { "epoch": 23.27, "learning_rate": 8.837237605016723e-05, "loss": 0.0637, "step": 96940 }, { "epoch": 23.27, "learning_rate": 8.837007463497983e-05, "loss": 0.045, "step": 96950 }, { "epoch": 23.28, "learning_rate": 8.836777302203277e-05, "loss": 0.0638, "step": 96960 }, { "epoch": 23.28, "learning_rate": 8.836547121133786e-05, "loss": 0.0567, "step": 96970 }, { "epoch": 23.28, "learning_rate": 8.836316920290701e-05, "loss": 0.0484, "step": 96980 }, { "epoch": 23.28, "learning_rate": 8.836086699675206e-05, "loss": 0.0637, "step": 96990 }, { "epoch": 23.29, "learning_rate": 8.835856459288489e-05, "loss": 0.0576, "step": 97000 }, { "epoch": 23.29, "learning_rate": 8.835626199131736e-05, "loss": 0.0464, "step": 97010 }, { "epoch": 23.29, "learning_rate": 8.835395919206132e-05, "loss": 0.0495, "step": 97020 }, { "epoch": 23.29, "learning_rate": 8.835165619512867e-05, "loss": 0.0389, "step": 97030 }, { "epoch": 23.3, "learning_rate": 8.834935300053125e-05, "loss": 0.059, "step": 97040 }, { "epoch": 23.3, "learning_rate": 8.834704960828093e-05, "loss": 0.0447, "step": 97050 }, { "epoch": 23.3, "learning_rate": 8.834474601838962e-05, "loss": 0.0401, "step": 97060 }, { "epoch": 23.3, "learning_rate": 8.834244223086915e-05, "loss": 0.0398, "step": 97070 }, { "epoch": 23.3, "learning_rate": 8.834013824573143e-05, "loss": 0.0449, "step": 97080 }, { "epoch": 23.31, "learning_rate": 8.833783406298832e-05, "loss": 0.0637, "step": 97090 }, { "epoch": 23.31, "learning_rate": 8.833552968265168e-05, "loss": 0.0499, "step": 97100 }, { "epoch": 23.31, "learning_rate": 8.833322510473339e-05, "loss": 0.0273, "step": 97110 }, { "epoch": 23.31, "learning_rate": 8.833092032924535e-05, "loss": 0.0575, "step": 97120 }, { "epoch": 23.32, "learning_rate": 8.832861535619943e-05, "loss": 0.0584, "step": 97130 }, { "epoch": 23.32, "learning_rate": 8.83263101856075e-05, "loss": 0.0481, "step": 97140 }, { "epoch": 23.32, "learning_rate": 8.832400481748145e-05, "loss": 0.044, "step": 97150 }, { "epoch": 23.32, "learning_rate": 8.832169925183315e-05, "loss": 0.0463, "step": 97160 }, { "epoch": 23.32, "learning_rate": 8.831939348867451e-05, "loss": 0.0273, "step": 97170 }, { "epoch": 23.33, "learning_rate": 8.831708752801739e-05, "loss": 0.0405, "step": 97180 }, { "epoch": 23.33, "learning_rate": 8.831478136987367e-05, "loss": 0.0713, "step": 97190 }, { "epoch": 23.33, "learning_rate": 8.831247501425524e-05, "loss": 0.0591, "step": 97200 }, { "epoch": 23.33, "learning_rate": 8.831016846117402e-05, "loss": 0.0326, "step": 97210 }, { "epoch": 23.34, "learning_rate": 8.830786171064185e-05, "loss": 0.0332, "step": 97220 }, { "epoch": 23.34, "learning_rate": 8.830555476267065e-05, "loss": 0.0419, "step": 97230 }, { "epoch": 23.34, "learning_rate": 8.830324761727229e-05, "loss": 0.0404, "step": 97240 }, { "epoch": 23.34, "learning_rate": 8.830094027445868e-05, "loss": 0.0312, "step": 97250 }, { "epoch": 23.35, "learning_rate": 8.829863273424171e-05, "loss": 0.0332, "step": 97260 }, { "epoch": 23.35, "learning_rate": 8.829632499663327e-05, "loss": 0.0502, "step": 97270 }, { "epoch": 23.35, "learning_rate": 8.829401706164523e-05, "loss": 0.0561, "step": 97280 }, { "epoch": 23.35, "learning_rate": 8.829170892928951e-05, "loss": 0.0413, "step": 97290 }, { "epoch": 23.35, "learning_rate": 8.828940059957803e-05, "loss": 0.0618, "step": 97300 }, { "epoch": 23.36, "learning_rate": 8.828709207252262e-05, "loss": 0.0368, "step": 97310 }, { "epoch": 23.36, "learning_rate": 8.828478334813523e-05, "loss": 0.0548, "step": 97320 }, { "epoch": 23.36, "learning_rate": 8.828247442642777e-05, "loss": 0.0667, "step": 97330 }, { "epoch": 23.36, "learning_rate": 8.82801653074121e-05, "loss": 0.066, "step": 97340 }, { "epoch": 23.37, "learning_rate": 8.827785599110013e-05, "loss": 0.0323, "step": 97350 }, { "epoch": 23.37, "learning_rate": 8.827554647750378e-05, "loss": 0.0364, "step": 97360 }, { "epoch": 23.37, "learning_rate": 8.827323676663494e-05, "loss": 0.0578, "step": 97370 }, { "epoch": 23.37, "learning_rate": 8.827092685850552e-05, "loss": 0.0401, "step": 97380 }, { "epoch": 23.38, "learning_rate": 8.826861675312743e-05, "loss": 0.0287, "step": 97390 }, { "epoch": 23.38, "learning_rate": 8.826630645051255e-05, "loss": 0.0269, "step": 97400 }, { "epoch": 23.38, "learning_rate": 8.826399595067282e-05, "loss": 0.0433, "step": 97410 }, { "epoch": 23.38, "learning_rate": 8.826168525362012e-05, "loss": 0.0352, "step": 97420 }, { "epoch": 23.38, "learning_rate": 8.825937435936639e-05, "loss": 0.0326, "step": 97430 }, { "epoch": 23.39, "learning_rate": 8.825706326792354e-05, "loss": 0.0388, "step": 97440 }, { "epoch": 23.39, "learning_rate": 8.825475197930344e-05, "loss": 0.0534, "step": 97450 }, { "epoch": 23.39, "learning_rate": 8.825244049351804e-05, "loss": 0.0568, "step": 97460 }, { "epoch": 23.39, "learning_rate": 8.825012881057923e-05, "loss": 0.0632, "step": 97470 }, { "epoch": 23.4, "learning_rate": 8.824781693049895e-05, "loss": 0.0538, "step": 97480 }, { "epoch": 23.4, "learning_rate": 8.82455048532891e-05, "loss": 0.0323, "step": 97490 }, { "epoch": 23.4, "learning_rate": 8.82431925789616e-05, "loss": 0.0537, "step": 97500 }, { "epoch": 23.4, "learning_rate": 8.824088010752836e-05, "loss": 0.0326, "step": 97510 }, { "epoch": 23.4, "learning_rate": 8.82385674390013e-05, "loss": 0.0428, "step": 97520 }, { "epoch": 23.41, "learning_rate": 8.823625457339236e-05, "loss": 0.04, "step": 97530 }, { "epoch": 23.41, "learning_rate": 8.823394151071342e-05, "loss": 0.0479, "step": 97540 }, { "epoch": 23.41, "learning_rate": 8.823162825097645e-05, "loss": 0.0648, "step": 97550 }, { "epoch": 23.41, "learning_rate": 8.822931479419334e-05, "loss": 0.0349, "step": 97560 }, { "epoch": 23.42, "learning_rate": 8.822700114037601e-05, "loss": 0.0556, "step": 97570 }, { "epoch": 23.42, "learning_rate": 8.822468728953641e-05, "loss": 0.029, "step": 97580 }, { "epoch": 23.42, "learning_rate": 8.822237324168646e-05, "loss": 0.0803, "step": 97590 }, { "epoch": 23.42, "learning_rate": 8.822005899683805e-05, "loss": 0.0448, "step": 97600 }, { "epoch": 23.43, "learning_rate": 8.821774455500315e-05, "loss": 0.0362, "step": 97610 }, { "epoch": 23.43, "learning_rate": 8.821542991619369e-05, "loss": 0.0233, "step": 97620 }, { "epoch": 23.43, "learning_rate": 8.821311508042157e-05, "loss": 0.0328, "step": 97630 }, { "epoch": 23.43, "learning_rate": 8.821080004769874e-05, "loss": 0.0342, "step": 97640 }, { "epoch": 23.43, "learning_rate": 8.820848481803712e-05, "loss": 0.0651, "step": 97650 }, { "epoch": 23.44, "learning_rate": 8.820616939144865e-05, "loss": 0.0456, "step": 97660 }, { "epoch": 23.44, "learning_rate": 8.82038537679453e-05, "loss": 0.051, "step": 97670 }, { "epoch": 23.44, "learning_rate": 8.820153794753891e-05, "loss": 0.0342, "step": 97680 }, { "epoch": 23.44, "learning_rate": 8.819922193024152e-05, "loss": 0.0292, "step": 97690 }, { "epoch": 23.45, "learning_rate": 8.819690571606501e-05, "loss": 0.0285, "step": 97700 }, { "epoch": 23.45, "learning_rate": 8.819458930502132e-05, "loss": 0.0326, "step": 97710 }, { "epoch": 23.45, "learning_rate": 8.81922726971224e-05, "loss": 0.0609, "step": 97720 }, { "epoch": 23.45, "learning_rate": 8.818995589238018e-05, "loss": 0.0562, "step": 97730 }, { "epoch": 23.45, "learning_rate": 8.818763889080661e-05, "loss": 0.0451, "step": 97740 }, { "epoch": 23.46, "learning_rate": 8.818532169241363e-05, "loss": 0.0311, "step": 97750 }, { "epoch": 23.46, "learning_rate": 8.81830042972132e-05, "loss": 0.0314, "step": 97760 }, { "epoch": 23.46, "learning_rate": 8.818068670521723e-05, "loss": 0.0612, "step": 97770 }, { "epoch": 23.46, "learning_rate": 8.817836891643768e-05, "loss": 0.049, "step": 97780 }, { "epoch": 23.47, "learning_rate": 8.81760509308865e-05, "loss": 0.0427, "step": 97790 }, { "epoch": 23.47, "learning_rate": 8.817373274857564e-05, "loss": 0.059, "step": 97800 }, { "epoch": 23.47, "learning_rate": 8.817141436951703e-05, "loss": 0.0587, "step": 97810 }, { "epoch": 23.47, "learning_rate": 8.816909579372266e-05, "loss": 0.0584, "step": 97820 }, { "epoch": 23.48, "learning_rate": 8.816677702120443e-05, "loss": 0.0375, "step": 97830 }, { "epoch": 23.48, "learning_rate": 8.816445805197431e-05, "loss": 0.0529, "step": 97840 }, { "epoch": 23.48, "learning_rate": 8.816213888604425e-05, "loss": 0.0449, "step": 97850 }, { "epoch": 23.48, "learning_rate": 8.815981952342622e-05, "loss": 0.04, "step": 97860 }, { "epoch": 23.48, "learning_rate": 8.815749996413216e-05, "loss": 0.0479, "step": 97870 }, { "epoch": 23.49, "learning_rate": 8.815518020817402e-05, "loss": 0.0355, "step": 97880 }, { "epoch": 23.49, "learning_rate": 8.815286025556377e-05, "loss": 0.0571, "step": 97890 }, { "epoch": 23.49, "learning_rate": 8.815054010631337e-05, "loss": 0.0722, "step": 97900 }, { "epoch": 23.49, "learning_rate": 8.814821976043474e-05, "loss": 0.0353, "step": 97910 }, { "epoch": 23.5, "learning_rate": 8.814589921793987e-05, "loss": 0.0953, "step": 97920 }, { "epoch": 23.5, "learning_rate": 8.814357847884074e-05, "loss": 0.0449, "step": 97930 }, { "epoch": 23.5, "learning_rate": 8.814125754314926e-05, "loss": 0.0433, "step": 97940 }, { "epoch": 23.5, "learning_rate": 8.813893641087744e-05, "loss": 0.0499, "step": 97950 }, { "epoch": 23.51, "learning_rate": 8.813661508203721e-05, "loss": 0.0545, "step": 97960 }, { "epoch": 23.51, "learning_rate": 8.813429355664055e-05, "loss": 0.0495, "step": 97970 }, { "epoch": 23.51, "learning_rate": 8.813197183469944e-05, "loss": 0.0305, "step": 97980 }, { "epoch": 23.51, "learning_rate": 8.812964991622581e-05, "loss": 0.0444, "step": 97990 }, { "epoch": 23.51, "learning_rate": 8.812732780123165e-05, "loss": 0.0614, "step": 98000 }, { "epoch": 23.52, "learning_rate": 8.812500548972893e-05, "loss": 0.0384, "step": 98010 }, { "epoch": 23.52, "learning_rate": 8.812268298172961e-05, "loss": 0.0412, "step": 98020 }, { "epoch": 23.52, "learning_rate": 8.812036027724565e-05, "loss": 0.0863, "step": 98030 }, { "epoch": 23.52, "learning_rate": 8.811803737628905e-05, "loss": 0.0453, "step": 98040 }, { "epoch": 23.53, "learning_rate": 8.811571427887175e-05, "loss": 0.0936, "step": 98050 }, { "epoch": 23.53, "learning_rate": 8.811339098500575e-05, "loss": 0.0767, "step": 98060 }, { "epoch": 23.53, "learning_rate": 8.811106749470302e-05, "loss": 0.0535, "step": 98070 }, { "epoch": 23.53, "learning_rate": 8.810874380797553e-05, "loss": 0.0593, "step": 98080 }, { "epoch": 23.53, "learning_rate": 8.810641992483525e-05, "loss": 0.1066, "step": 98090 }, { "epoch": 23.54, "learning_rate": 8.810409584529415e-05, "loss": 0.0538, "step": 98100 }, { "epoch": 23.54, "learning_rate": 8.810177156936424e-05, "loss": 0.0681, "step": 98110 }, { "epoch": 23.54, "learning_rate": 8.809944709705748e-05, "loss": 0.0771, "step": 98120 }, { "epoch": 23.54, "learning_rate": 8.809712242838585e-05, "loss": 0.0952, "step": 98130 }, { "epoch": 23.55, "learning_rate": 8.809479756336132e-05, "loss": 0.083, "step": 98140 }, { "epoch": 23.55, "learning_rate": 8.80924725019959e-05, "loss": 0.0751, "step": 98150 }, { "epoch": 23.55, "learning_rate": 8.809014724430156e-05, "loss": 0.0776, "step": 98160 }, { "epoch": 23.55, "learning_rate": 8.808782179029028e-05, "loss": 0.0715, "step": 98170 }, { "epoch": 23.56, "learning_rate": 8.808549613997403e-05, "loss": 0.0677, "step": 98180 }, { "epoch": 23.56, "learning_rate": 8.808317029336484e-05, "loss": 0.0583, "step": 98190 }, { "epoch": 23.56, "learning_rate": 8.808084425047465e-05, "loss": 0.0555, "step": 98200 }, { "epoch": 23.56, "learning_rate": 8.807851801131548e-05, "loss": 0.0816, "step": 98210 }, { "epoch": 23.56, "learning_rate": 8.807619157589932e-05, "loss": 0.0756, "step": 98220 }, { "epoch": 23.57, "learning_rate": 8.807386494423814e-05, "loss": 0.0781, "step": 98230 }, { "epoch": 23.57, "learning_rate": 8.807153811634394e-05, "loss": 0.0535, "step": 98240 }, { "epoch": 23.57, "learning_rate": 8.806921109222873e-05, "loss": 0.0642, "step": 98250 }, { "epoch": 23.57, "learning_rate": 8.806688387190447e-05, "loss": 0.0758, "step": 98260 }, { "epoch": 23.58, "learning_rate": 8.806455645538316e-05, "loss": 0.0608, "step": 98270 }, { "epoch": 23.58, "learning_rate": 8.806222884267683e-05, "loss": 0.066, "step": 98280 }, { "epoch": 23.58, "learning_rate": 8.805990103379745e-05, "loss": 0.0579, "step": 98290 }, { "epoch": 23.58, "learning_rate": 8.805757302875704e-05, "loss": 0.0532, "step": 98300 }, { "epoch": 23.59, "learning_rate": 8.805524482756754e-05, "loss": 0.0564, "step": 98310 }, { "epoch": 23.59, "learning_rate": 8.805291643024102e-05, "loss": 0.0916, "step": 98320 }, { "epoch": 23.59, "learning_rate": 8.805058783678944e-05, "loss": 0.0638, "step": 98330 }, { "epoch": 23.59, "learning_rate": 8.804825904722483e-05, "loss": 0.0824, "step": 98340 }, { "epoch": 23.59, "learning_rate": 8.804593006155914e-05, "loss": 0.0649, "step": 98350 }, { "epoch": 23.6, "learning_rate": 8.804360087980443e-05, "loss": 0.054, "step": 98360 }, { "epoch": 23.6, "learning_rate": 8.804127150197268e-05, "loss": 0.0849, "step": 98370 }, { "epoch": 23.6, "learning_rate": 8.803894192807591e-05, "loss": 0.0718, "step": 98380 }, { "epoch": 23.6, "learning_rate": 8.80366121581261e-05, "loss": 0.0585, "step": 98390 }, { "epoch": 23.61, "learning_rate": 8.803428219213528e-05, "loss": 0.0568, "step": 98400 }, { "epoch": 23.61, "learning_rate": 8.803195203011545e-05, "loss": 0.0977, "step": 98410 }, { "epoch": 23.61, "learning_rate": 8.802962167207862e-05, "loss": 0.0975, "step": 98420 }, { "epoch": 23.61, "learning_rate": 8.80272911180368e-05, "loss": 0.0795, "step": 98430 }, { "epoch": 23.61, "learning_rate": 8.802496036800201e-05, "loss": 0.0475, "step": 98440 }, { "epoch": 23.62, "learning_rate": 8.802262942198626e-05, "loss": 0.0321, "step": 98450 }, { "epoch": 23.62, "learning_rate": 8.802029828000156e-05, "loss": 0.0632, "step": 98460 }, { "epoch": 23.62, "learning_rate": 8.80179669420599e-05, "loss": 0.0541, "step": 98470 }, { "epoch": 23.62, "learning_rate": 8.801563540817335e-05, "loss": 0.063, "step": 98480 }, { "epoch": 23.63, "learning_rate": 8.801330367835389e-05, "loss": 0.0629, "step": 98490 }, { "epoch": 23.63, "learning_rate": 8.801097175261354e-05, "loss": 0.0384, "step": 98500 }, { "epoch": 23.63, "learning_rate": 8.800863963096433e-05, "loss": 0.0511, "step": 98510 }, { "epoch": 23.63, "learning_rate": 8.800630731341825e-05, "loss": 0.0409, "step": 98520 }, { "epoch": 23.64, "learning_rate": 8.800397479998737e-05, "loss": 0.0669, "step": 98530 }, { "epoch": 23.64, "learning_rate": 8.80016420906837e-05, "loss": 0.0855, "step": 98540 }, { "epoch": 23.64, "learning_rate": 8.799930918551922e-05, "loss": 0.0591, "step": 98550 }, { "epoch": 23.64, "learning_rate": 8.799697608450599e-05, "loss": 0.039, "step": 98560 }, { "epoch": 23.64, "learning_rate": 8.799464278765603e-05, "loss": 0.0693, "step": 98570 }, { "epoch": 23.65, "learning_rate": 8.799230929498137e-05, "loss": 0.0809, "step": 98580 }, { "epoch": 23.65, "learning_rate": 8.798997560649402e-05, "loss": 0.0929, "step": 98590 }, { "epoch": 23.65, "learning_rate": 8.798764172220601e-05, "loss": 0.0822, "step": 98600 }, { "epoch": 23.65, "learning_rate": 8.798530764212939e-05, "loss": 0.0535, "step": 98610 }, { "epoch": 23.66, "learning_rate": 8.798297336627618e-05, "loss": 0.0703, "step": 98620 }, { "epoch": 23.66, "learning_rate": 8.798063889465839e-05, "loss": 0.0686, "step": 98630 }, { "epoch": 23.66, "learning_rate": 8.797830422728809e-05, "loss": 0.0339, "step": 98640 }, { "epoch": 23.66, "learning_rate": 8.797596936417729e-05, "loss": 0.0617, "step": 98650 }, { "epoch": 23.67, "learning_rate": 8.797363430533802e-05, "loss": 0.0561, "step": 98660 }, { "epoch": 23.67, "learning_rate": 8.797129905078232e-05, "loss": 0.0753, "step": 98670 }, { "epoch": 23.67, "learning_rate": 8.796896360052222e-05, "loss": 0.0495, "step": 98680 }, { "epoch": 23.67, "learning_rate": 8.796662795456979e-05, "loss": 0.0558, "step": 98690 }, { "epoch": 23.67, "learning_rate": 8.796429211293702e-05, "loss": 0.0755, "step": 98700 }, { "epoch": 23.68, "learning_rate": 8.796195607563597e-05, "loss": 0.078, "step": 98710 }, { "epoch": 23.68, "learning_rate": 8.795961984267869e-05, "loss": 0.0798, "step": 98720 }, { "epoch": 23.68, "learning_rate": 8.795728341407723e-05, "loss": 0.0634, "step": 98730 }, { "epoch": 23.68, "learning_rate": 8.795494678984359e-05, "loss": 0.0391, "step": 98740 }, { "epoch": 23.69, "learning_rate": 8.795260996998984e-05, "loss": 0.0673, "step": 98750 }, { "epoch": 23.69, "learning_rate": 8.795027295452802e-05, "loss": 0.0604, "step": 98760 }, { "epoch": 23.69, "learning_rate": 8.794793574347018e-05, "loss": 0.0523, "step": 98770 }, { "epoch": 23.69, "learning_rate": 8.794559833682837e-05, "loss": 0.065, "step": 98780 }, { "epoch": 23.69, "learning_rate": 8.794326073461461e-05, "loss": 0.0604, "step": 98790 }, { "epoch": 23.7, "learning_rate": 8.794092293684098e-05, "loss": 0.0881, "step": 98800 }, { "epoch": 23.7, "learning_rate": 8.793858494351952e-05, "loss": 0.0423, "step": 98810 }, { "epoch": 23.7, "learning_rate": 8.793624675466226e-05, "loss": 0.0579, "step": 98820 }, { "epoch": 23.7, "learning_rate": 8.793390837028128e-05, "loss": 0.0742, "step": 98830 }, { "epoch": 23.71, "learning_rate": 8.793156979038861e-05, "loss": 0.0385, "step": 98840 }, { "epoch": 23.71, "learning_rate": 8.792923101499632e-05, "loss": 0.043, "step": 98850 }, { "epoch": 23.71, "learning_rate": 8.792689204411646e-05, "loss": 0.0602, "step": 98860 }, { "epoch": 23.71, "learning_rate": 8.792455287776106e-05, "loss": 0.0384, "step": 98870 }, { "epoch": 23.72, "learning_rate": 8.792221351594222e-05, "loss": 0.0264, "step": 98880 }, { "epoch": 23.72, "learning_rate": 8.791987395867196e-05, "loss": 0.0411, "step": 98890 }, { "epoch": 23.72, "learning_rate": 8.791753420596238e-05, "loss": 0.081, "step": 98900 }, { "epoch": 23.72, "learning_rate": 8.791519425782548e-05, "loss": 0.0649, "step": 98910 }, { "epoch": 23.72, "learning_rate": 8.791285411427337e-05, "loss": 0.0977, "step": 98920 }, { "epoch": 23.73, "learning_rate": 8.791051377531808e-05, "loss": 0.0796, "step": 98930 }, { "epoch": 23.73, "learning_rate": 8.79081732409717e-05, "loss": 0.0661, "step": 98940 }, { "epoch": 23.73, "learning_rate": 8.790583251124627e-05, "loss": 0.0796, "step": 98950 }, { "epoch": 23.73, "learning_rate": 8.790349158615385e-05, "loss": 0.0351, "step": 98960 }, { "epoch": 23.74, "learning_rate": 8.790115046570653e-05, "loss": 0.0358, "step": 98970 }, { "epoch": 23.74, "learning_rate": 8.789880914991637e-05, "loss": 0.0565, "step": 98980 }, { "epoch": 23.74, "learning_rate": 8.789646763879542e-05, "loss": 0.0663, "step": 98990 }, { "epoch": 23.74, "learning_rate": 8.789412593235578e-05, "loss": 0.0774, "step": 99000 }, { "epoch": 23.75, "learning_rate": 8.789178403060947e-05, "loss": 0.0409, "step": 99010 }, { "epoch": 23.75, "learning_rate": 8.788944193356861e-05, "loss": 0.066, "step": 99020 }, { "epoch": 23.75, "learning_rate": 8.788709964124523e-05, "loss": 0.0548, "step": 99030 }, { "epoch": 23.75, "learning_rate": 8.788475715365144e-05, "loss": 0.0589, "step": 99040 }, { "epoch": 23.75, "learning_rate": 8.788241447079928e-05, "loss": 0.0476, "step": 99050 }, { "epoch": 23.76, "learning_rate": 8.788007159270084e-05, "loss": 0.07, "step": 99060 }, { "epoch": 23.76, "learning_rate": 8.78777285193682e-05, "loss": 0.0709, "step": 99070 }, { "epoch": 23.76, "learning_rate": 8.787538525081344e-05, "loss": 0.0607, "step": 99080 }, { "epoch": 23.76, "learning_rate": 8.787304178704861e-05, "loss": 0.0929, "step": 99090 }, { "epoch": 23.77, "learning_rate": 8.787069812808582e-05, "loss": 0.0487, "step": 99100 }, { "epoch": 23.77, "learning_rate": 8.786835427393712e-05, "loss": 0.0448, "step": 99110 }, { "epoch": 23.77, "learning_rate": 8.786601022461463e-05, "loss": 0.0582, "step": 99120 }, { "epoch": 23.77, "learning_rate": 8.786366598013039e-05, "loss": 0.0406, "step": 99130 }, { "epoch": 23.77, "learning_rate": 8.786132154049649e-05, "loss": 0.0669, "step": 99140 }, { "epoch": 23.78, "learning_rate": 8.785897690572504e-05, "loss": 0.0549, "step": 99150 }, { "epoch": 23.78, "learning_rate": 8.78566320758281e-05, "loss": 0.0583, "step": 99160 }, { "epoch": 23.78, "learning_rate": 8.785428705081776e-05, "loss": 0.0576, "step": 99170 }, { "epoch": 23.78, "learning_rate": 8.785194183070611e-05, "loss": 0.047, "step": 99180 }, { "epoch": 23.79, "learning_rate": 8.784959641550523e-05, "loss": 0.0628, "step": 99190 }, { "epoch": 23.79, "learning_rate": 8.784725080522723e-05, "loss": 0.0878, "step": 99200 }, { "epoch": 23.79, "learning_rate": 8.784490499988416e-05, "loss": 0.0831, "step": 99210 }, { "epoch": 23.79, "learning_rate": 8.784255899948814e-05, "loss": 0.06, "step": 99220 }, { "epoch": 23.8, "learning_rate": 8.784021280405128e-05, "loss": 0.0548, "step": 99230 }, { "epoch": 23.8, "learning_rate": 8.783786641358562e-05, "loss": 0.0859, "step": 99240 }, { "epoch": 23.8, "learning_rate": 8.783551982810328e-05, "loss": 0.047, "step": 99250 }, { "epoch": 23.8, "learning_rate": 8.783317304761635e-05, "loss": 0.0251, "step": 99260 }, { "epoch": 23.8, "learning_rate": 8.783082607213696e-05, "loss": 0.0376, "step": 99270 }, { "epoch": 23.81, "learning_rate": 8.782847890167716e-05, "loss": 0.0399, "step": 99280 }, { "epoch": 23.81, "learning_rate": 8.782613153624905e-05, "loss": 0.0426, "step": 99290 }, { "epoch": 23.81, "learning_rate": 8.782378397586477e-05, "loss": 0.0667, "step": 99300 }, { "epoch": 23.81, "learning_rate": 8.782143622053636e-05, "loss": 0.0485, "step": 99310 }, { "epoch": 23.82, "learning_rate": 8.781908827027596e-05, "loss": 0.0327, "step": 99320 }, { "epoch": 23.82, "learning_rate": 8.781674012509568e-05, "loss": 0.0297, "step": 99330 }, { "epoch": 23.82, "learning_rate": 8.781439178500759e-05, "loss": 0.062, "step": 99340 }, { "epoch": 23.82, "learning_rate": 8.781204325002381e-05, "loss": 0.0416, "step": 99350 }, { "epoch": 23.83, "learning_rate": 8.780969452015645e-05, "loss": 0.0477, "step": 99360 }, { "epoch": 23.83, "learning_rate": 8.780734559541761e-05, "loss": 0.0733, "step": 99370 }, { "epoch": 23.83, "learning_rate": 8.78049964758194e-05, "loss": 0.0614, "step": 99380 }, { "epoch": 23.83, "learning_rate": 8.78026471613739e-05, "loss": 0.057, "step": 99390 }, { "epoch": 23.83, "learning_rate": 8.780029765209325e-05, "loss": 0.0483, "step": 99400 }, { "epoch": 23.84, "learning_rate": 8.779794794798954e-05, "loss": 0.0497, "step": 99410 }, { "epoch": 23.84, "learning_rate": 8.779559804907491e-05, "loss": 0.0724, "step": 99420 }, { "epoch": 23.84, "learning_rate": 8.779324795536145e-05, "loss": 0.0414, "step": 99430 }, { "epoch": 23.84, "learning_rate": 8.779089766686127e-05, "loss": 0.0881, "step": 99440 }, { "epoch": 23.85, "learning_rate": 8.77885471835865e-05, "loss": 0.0414, "step": 99450 }, { "epoch": 23.85, "learning_rate": 8.77861965055492e-05, "loss": 0.0382, "step": 99460 }, { "epoch": 23.85, "learning_rate": 8.778384563276156e-05, "loss": 0.0271, "step": 99470 }, { "epoch": 23.85, "learning_rate": 8.778149456523565e-05, "loss": 0.0383, "step": 99480 }, { "epoch": 23.85, "learning_rate": 8.777914330298363e-05, "loss": 0.0424, "step": 99490 }, { "epoch": 23.86, "learning_rate": 8.777679184601756e-05, "loss": 0.0653, "step": 99500 }, { "epoch": 23.86, "learning_rate": 8.777444019434959e-05, "loss": 0.0552, "step": 99510 }, { "epoch": 23.86, "learning_rate": 8.777208834799187e-05, "loss": 0.0501, "step": 99520 }, { "epoch": 23.86, "learning_rate": 8.776973630695647e-05, "loss": 0.0452, "step": 99530 }, { "epoch": 23.87, "learning_rate": 8.776738407125551e-05, "loss": 0.0526, "step": 99540 }, { "epoch": 23.87, "learning_rate": 8.776503164090117e-05, "loss": 0.0473, "step": 99550 }, { "epoch": 23.87, "learning_rate": 8.776267901590552e-05, "loss": 0.0703, "step": 99560 }, { "epoch": 23.87, "learning_rate": 8.776032619628072e-05, "loss": 0.069, "step": 99570 }, { "epoch": 23.88, "learning_rate": 8.77579731820389e-05, "loss": 0.0555, "step": 99580 }, { "epoch": 23.88, "learning_rate": 8.775561997319214e-05, "loss": 0.021, "step": 99590 }, { "epoch": 23.88, "learning_rate": 8.77532665697526e-05, "loss": 0.0387, "step": 99600 }, { "epoch": 23.88, "learning_rate": 8.775091297173243e-05, "loss": 0.0538, "step": 99610 }, { "epoch": 23.88, "learning_rate": 8.774855917914372e-05, "loss": 0.0682, "step": 99620 }, { "epoch": 23.89, "learning_rate": 8.774620519199863e-05, "loss": 0.0284, "step": 99630 }, { "epoch": 23.89, "learning_rate": 8.774385101030928e-05, "loss": 0.0542, "step": 99640 }, { "epoch": 23.89, "learning_rate": 8.77414966340878e-05, "loss": 0.0504, "step": 99650 }, { "epoch": 23.89, "learning_rate": 8.773914206334635e-05, "loss": 0.0592, "step": 99660 }, { "epoch": 23.9, "learning_rate": 8.773678729809702e-05, "loss": 0.0683, "step": 99670 }, { "epoch": 23.9, "learning_rate": 8.773443233835199e-05, "loss": 0.0538, "step": 99680 }, { "epoch": 23.9, "learning_rate": 8.773207718412338e-05, "loss": 0.0341, "step": 99690 }, { "epoch": 23.9, "learning_rate": 8.772972183542333e-05, "loss": 0.0479, "step": 99700 }, { "epoch": 23.91, "learning_rate": 8.772736629226397e-05, "loss": 0.0467, "step": 99710 }, { "epoch": 23.91, "learning_rate": 8.772501055465745e-05, "loss": 0.0471, "step": 99720 }, { "epoch": 23.91, "learning_rate": 8.772265462261593e-05, "loss": 0.0688, "step": 99730 }, { "epoch": 23.91, "learning_rate": 8.772029849615151e-05, "loss": 0.0679, "step": 99740 }, { "epoch": 23.91, "learning_rate": 8.771794217527636e-05, "loss": 0.0332, "step": 99750 }, { "epoch": 23.92, "learning_rate": 8.771558566000261e-05, "loss": 0.0482, "step": 99760 }, { "epoch": 23.92, "learning_rate": 8.771322895034244e-05, "loss": 0.056, "step": 99770 }, { "epoch": 23.92, "learning_rate": 8.771087204630797e-05, "loss": 0.0545, "step": 99780 }, { "epoch": 23.92, "learning_rate": 8.770851494791133e-05, "loss": 0.0853, "step": 99790 }, { "epoch": 23.93, "learning_rate": 8.770615765516471e-05, "loss": 0.0378, "step": 99800 }, { "epoch": 23.93, "learning_rate": 8.770380016808023e-05, "loss": 0.0486, "step": 99810 }, { "epoch": 23.93, "learning_rate": 8.770144248667005e-05, "loss": 0.0365, "step": 99820 }, { "epoch": 23.93, "learning_rate": 8.769908461094632e-05, "loss": 0.0303, "step": 99830 }, { "epoch": 23.93, "learning_rate": 8.769672654092118e-05, "loss": 0.0246, "step": 99840 }, { "epoch": 23.94, "learning_rate": 8.769436827660682e-05, "loss": 0.0309, "step": 99850 }, { "epoch": 23.94, "learning_rate": 8.769200981801535e-05, "loss": 0.0411, "step": 99860 }, { "epoch": 23.94, "learning_rate": 8.768965116515896e-05, "loss": 0.0659, "step": 99870 }, { "epoch": 23.94, "learning_rate": 8.76872923180498e-05, "loss": 0.041, "step": 99880 }, { "epoch": 23.95, "learning_rate": 8.76849332767e-05, "loss": 0.0305, "step": 99890 }, { "epoch": 23.95, "learning_rate": 8.768257404112174e-05, "loss": 0.025, "step": 99900 }, { "epoch": 23.95, "learning_rate": 8.768021461132719e-05, "loss": 0.0735, "step": 99910 }, { "epoch": 24.0, "learning_rate": 8.767785498732849e-05, "loss": 0.0612, "step": 99920 }, { "epoch": 24.0, "learning_rate": 8.767549516913782e-05, "loss": 0.0625, "step": 99930 }, { "epoch": 24.01, "learning_rate": 8.767313515676731e-05, "loss": 0.0579, "step": 99940 }, { "epoch": 24.01, "learning_rate": 8.767077495022918e-05, "loss": 0.0268, "step": 99950 }, { "epoch": 24.01, "learning_rate": 8.766841454953554e-05, "loss": 0.0577, "step": 99960 }, { "epoch": 24.01, "learning_rate": 8.766605395469859e-05, "loss": 0.046, "step": 99970 }, { "epoch": 24.02, "learning_rate": 8.766369316573048e-05, "loss": 0.0332, "step": 99980 }, { "epoch": 24.02, "learning_rate": 8.766133218264337e-05, "loss": 0.0372, "step": 99990 }, { "epoch": 24.02, "learning_rate": 8.765897100544945e-05, "loss": 0.0575, "step": 100000 }, { "epoch": 24.02, "learning_rate": 8.765660963416086e-05, "loss": 0.057, "step": 100010 }, { "epoch": 24.02, "learning_rate": 8.765424806878982e-05, "loss": 0.0323, "step": 100020 }, { "epoch": 24.03, "learning_rate": 8.765188630934844e-05, "loss": 0.0451, "step": 100030 }, { "epoch": 24.03, "learning_rate": 8.764952435584894e-05, "loss": 0.0333, "step": 100040 }, { "epoch": 24.03, "learning_rate": 8.764716220830347e-05, "loss": 0.0471, "step": 100050 }, { "epoch": 24.03, "learning_rate": 8.764479986672422e-05, "loss": 0.0494, "step": 100060 }, { "epoch": 24.04, "learning_rate": 8.764243733112335e-05, "loss": 0.0327, "step": 100070 }, { "epoch": 24.04, "learning_rate": 8.764007460151304e-05, "loss": 0.0383, "step": 100080 }, { "epoch": 24.04, "learning_rate": 8.763771167790549e-05, "loss": 0.0604, "step": 100090 }, { "epoch": 24.04, "learning_rate": 8.763534856031284e-05, "loss": 0.0696, "step": 100100 }, { "epoch": 24.05, "learning_rate": 8.76329852487473e-05, "loss": 0.0562, "step": 100110 }, { "epoch": 24.05, "learning_rate": 8.763062174322103e-05, "loss": 0.0271, "step": 100120 }, { "epoch": 24.05, "learning_rate": 8.762825804374621e-05, "loss": 0.0339, "step": 100130 }, { "epoch": 24.05, "learning_rate": 8.762589415033506e-05, "loss": 0.0749, "step": 100140 }, { "epoch": 24.05, "learning_rate": 8.762353006299973e-05, "loss": 0.0439, "step": 100150 }, { "epoch": 24.06, "learning_rate": 8.76211657817524e-05, "loss": 0.055, "step": 100160 }, { "epoch": 24.06, "learning_rate": 8.761880130660527e-05, "loss": 0.0595, "step": 100170 }, { "epoch": 24.06, "learning_rate": 8.761643663757054e-05, "loss": 0.0643, "step": 100180 }, { "epoch": 24.06, "learning_rate": 8.761407177466036e-05, "loss": 0.0306, "step": 100190 }, { "epoch": 24.07, "learning_rate": 8.761170671788694e-05, "loss": 0.0331, "step": 100200 }, { "epoch": 24.07, "learning_rate": 8.760934146726249e-05, "loss": 0.0593, "step": 100210 }, { "epoch": 24.07, "learning_rate": 8.760697602279916e-05, "loss": 0.0417, "step": 100220 }, { "epoch": 24.07, "learning_rate": 8.760461038450918e-05, "loss": 0.0454, "step": 100230 }, { "epoch": 24.07, "learning_rate": 8.76022445524047e-05, "loss": 0.0468, "step": 100240 }, { "epoch": 24.08, "learning_rate": 8.759987852649795e-05, "loss": 0.0526, "step": 100250 }, { "epoch": 24.08, "learning_rate": 8.759751230680112e-05, "loss": 0.0376, "step": 100260 }, { "epoch": 24.08, "learning_rate": 8.759514589332638e-05, "loss": 0.0579, "step": 100270 }, { "epoch": 24.08, "learning_rate": 8.759277928608596e-05, "loss": 0.0448, "step": 100280 }, { "epoch": 24.09, "learning_rate": 8.759041248509203e-05, "loss": 0.0635, "step": 100290 }, { "epoch": 24.09, "learning_rate": 8.758804549035679e-05, "loss": 0.0511, "step": 100300 }, { "epoch": 24.09, "learning_rate": 8.758567830189247e-05, "loss": 0.041, "step": 100310 }, { "epoch": 24.09, "learning_rate": 8.758331091971123e-05, "loss": 0.0455, "step": 100320 }, { "epoch": 24.1, "learning_rate": 8.758094334382532e-05, "loss": 0.0411, "step": 100330 }, { "epoch": 24.1, "learning_rate": 8.75785755742469e-05, "loss": 0.0454, "step": 100340 }, { "epoch": 24.1, "learning_rate": 8.757620761098819e-05, "loss": 0.0481, "step": 100350 }, { "epoch": 24.1, "learning_rate": 8.757383945406138e-05, "loss": 0.0491, "step": 100360 }, { "epoch": 24.1, "learning_rate": 8.75714711034787e-05, "loss": 0.027, "step": 100370 }, { "epoch": 24.11, "learning_rate": 8.756910255925232e-05, "loss": 0.044, "step": 100380 }, { "epoch": 24.11, "learning_rate": 8.756673382139451e-05, "loss": 0.0436, "step": 100390 }, { "epoch": 24.11, "learning_rate": 8.756436488991741e-05, "loss": 0.0847, "step": 100400 }, { "epoch": 24.11, "learning_rate": 8.756199576483327e-05, "loss": 0.0474, "step": 100410 }, { "epoch": 24.12, "learning_rate": 8.75596264461543e-05, "loss": 0.0443, "step": 100420 }, { "epoch": 24.12, "learning_rate": 8.755725693389269e-05, "loss": 0.0372, "step": 100430 }, { "epoch": 24.12, "learning_rate": 8.755488722806066e-05, "loss": 0.0425, "step": 100440 }, { "epoch": 24.12, "learning_rate": 8.755251732867043e-05, "loss": 0.0474, "step": 100450 }, { "epoch": 24.13, "learning_rate": 8.75501472357342e-05, "loss": 0.0354, "step": 100460 }, { "epoch": 24.13, "learning_rate": 8.754777694926421e-05, "loss": 0.0428, "step": 100470 }, { "epoch": 24.13, "learning_rate": 8.754540646927267e-05, "loss": 0.0514, "step": 100480 }, { "epoch": 24.13, "learning_rate": 8.75430357957718e-05, "loss": 0.0669, "step": 100490 }, { "epoch": 24.13, "learning_rate": 8.754066492877379e-05, "loss": 0.0591, "step": 100500 }, { "epoch": 24.14, "learning_rate": 8.753829386829088e-05, "loss": 0.0323, "step": 100510 }, { "epoch": 24.14, "learning_rate": 8.75359226143353e-05, "loss": 0.0547, "step": 100520 }, { "epoch": 24.14, "learning_rate": 8.753355116691925e-05, "loss": 0.0531, "step": 100530 }, { "epoch": 24.14, "learning_rate": 8.753117952605496e-05, "loss": 0.0363, "step": 100540 }, { "epoch": 24.15, "learning_rate": 8.752880769175467e-05, "loss": 0.0706, "step": 100550 }, { "epoch": 24.15, "learning_rate": 8.75264356640306e-05, "loss": 0.0503, "step": 100560 }, { "epoch": 24.15, "learning_rate": 8.752406344289494e-05, "loss": 0.0615, "step": 100570 }, { "epoch": 24.15, "learning_rate": 8.752169102835996e-05, "loss": 0.0489, "step": 100580 }, { "epoch": 24.15, "learning_rate": 8.751931842043788e-05, "loss": 0.0912, "step": 100590 }, { "epoch": 24.16, "learning_rate": 8.75169456191409e-05, "loss": 0.0597, "step": 100600 }, { "epoch": 24.16, "learning_rate": 8.751457262448127e-05, "loss": 0.055, "step": 100610 }, { "epoch": 24.16, "learning_rate": 8.751219943647122e-05, "loss": 0.0425, "step": 100620 }, { "epoch": 24.16, "learning_rate": 8.750982605512299e-05, "loss": 0.0349, "step": 100630 }, { "epoch": 24.17, "learning_rate": 8.750745248044881e-05, "loss": 0.0483, "step": 100640 }, { "epoch": 24.17, "learning_rate": 8.750507871246089e-05, "loss": 0.035, "step": 100650 }, { "epoch": 24.17, "learning_rate": 8.750270475117149e-05, "loss": 0.0561, "step": 100660 }, { "epoch": 24.17, "learning_rate": 8.750033059659283e-05, "loss": 0.0284, "step": 100670 }, { "epoch": 24.18, "learning_rate": 8.749795624873716e-05, "loss": 0.0403, "step": 100680 }, { "epoch": 24.18, "learning_rate": 8.749558170761669e-05, "loss": 0.0529, "step": 100690 }, { "epoch": 24.18, "learning_rate": 8.74932069732437e-05, "loss": 0.0362, "step": 100700 }, { "epoch": 24.18, "learning_rate": 8.74908320456304e-05, "loss": 0.0424, "step": 100710 }, { "epoch": 24.18, "learning_rate": 8.748845692478905e-05, "loss": 0.0228, "step": 100720 }, { "epoch": 24.19, "learning_rate": 8.748608161073187e-05, "loss": 0.0673, "step": 100730 }, { "epoch": 24.19, "learning_rate": 8.748370610347109e-05, "loss": 0.0428, "step": 100740 }, { "epoch": 24.19, "learning_rate": 8.7481330403019e-05, "loss": 0.0246, "step": 100750 }, { "epoch": 24.19, "learning_rate": 8.747895450938782e-05, "loss": 0.0365, "step": 100760 }, { "epoch": 24.2, "learning_rate": 8.74765784225898e-05, "loss": 0.076, "step": 100770 }, { "epoch": 24.2, "learning_rate": 8.747420214263718e-05, "loss": 0.0547, "step": 100780 }, { "epoch": 24.2, "learning_rate": 8.74718256695422e-05, "loss": 0.0517, "step": 100790 }, { "epoch": 24.2, "learning_rate": 8.746944900331711e-05, "loss": 0.0424, "step": 100800 }, { "epoch": 24.21, "learning_rate": 8.746707214397418e-05, "loss": 0.034, "step": 100810 }, { "epoch": 24.21, "learning_rate": 8.746469509152564e-05, "loss": 0.0502, "step": 100820 }, { "epoch": 24.21, "learning_rate": 8.746231784598376e-05, "loss": 0.0335, "step": 100830 }, { "epoch": 24.21, "learning_rate": 8.745994040736077e-05, "loss": 0.0501, "step": 100840 }, { "epoch": 24.21, "learning_rate": 8.745756277566892e-05, "loss": 0.048, "step": 100850 }, { "epoch": 24.22, "learning_rate": 8.745518495092051e-05, "loss": 0.0398, "step": 100860 }, { "epoch": 24.22, "learning_rate": 8.745280693312774e-05, "loss": 0.0723, "step": 100870 }, { "epoch": 24.22, "learning_rate": 8.74504287223029e-05, "loss": 0.0355, "step": 100880 }, { "epoch": 24.22, "learning_rate": 8.744805031845824e-05, "loss": 0.0284, "step": 100890 }, { "epoch": 24.23, "learning_rate": 8.7445671721606e-05, "loss": 0.0558, "step": 100900 }, { "epoch": 24.23, "learning_rate": 8.744329293175846e-05, "loss": 0.0657, "step": 100910 }, { "epoch": 24.23, "learning_rate": 8.74409139489279e-05, "loss": 0.0526, "step": 100920 }, { "epoch": 24.23, "learning_rate": 8.743853477312654e-05, "loss": 0.0853, "step": 100930 }, { "epoch": 24.23, "learning_rate": 8.743615540436664e-05, "loss": 0.0443, "step": 100940 }, { "epoch": 24.24, "learning_rate": 8.74337758426605e-05, "loss": 0.0472, "step": 100950 }, { "epoch": 24.24, "learning_rate": 8.743139608802038e-05, "loss": 0.0738, "step": 100960 }, { "epoch": 24.24, "learning_rate": 8.742901614045851e-05, "loss": 0.0451, "step": 100970 }, { "epoch": 24.24, "learning_rate": 8.742663599998719e-05, "loss": 0.0334, "step": 100980 }, { "epoch": 24.25, "learning_rate": 8.742425566661868e-05, "loss": 0.032, "step": 100990 }, { "epoch": 24.25, "learning_rate": 8.742187514036522e-05, "loss": 0.0602, "step": 101000 }, { "epoch": 24.25, "learning_rate": 8.741949442123911e-05, "loss": 0.0352, "step": 101010 }, { "epoch": 24.25, "learning_rate": 8.741711350925262e-05, "loss": 0.0414, "step": 101020 }, { "epoch": 24.26, "learning_rate": 8.741473240441802e-05, "loss": 0.0322, "step": 101030 }, { "epoch": 24.26, "learning_rate": 8.741235110674757e-05, "loss": 0.0287, "step": 101040 }, { "epoch": 24.26, "learning_rate": 8.740996961625354e-05, "loss": 0.0567, "step": 101050 }, { "epoch": 24.26, "learning_rate": 8.740758793294823e-05, "loss": 0.0248, "step": 101060 }, { "epoch": 24.26, "learning_rate": 8.740520605684389e-05, "loss": 0.0518, "step": 101070 }, { "epoch": 24.27, "learning_rate": 8.740282398795281e-05, "loss": 0.043, "step": 101080 }, { "epoch": 24.27, "learning_rate": 8.740044172628726e-05, "loss": 0.0729, "step": 101090 }, { "epoch": 24.27, "learning_rate": 8.739805927185952e-05, "loss": 0.0523, "step": 101100 }, { "epoch": 24.27, "learning_rate": 8.739567662468186e-05, "loss": 0.0267, "step": 101110 }, { "epoch": 24.28, "learning_rate": 8.73932937847666e-05, "loss": 0.0383, "step": 101120 }, { "epoch": 24.28, "learning_rate": 8.739091075212597e-05, "loss": 0.0546, "step": 101130 }, { "epoch": 24.28, "learning_rate": 8.738852752677226e-05, "loss": 0.0498, "step": 101140 }, { "epoch": 24.28, "learning_rate": 8.738614410871779e-05, "loss": 0.0613, "step": 101150 }, { "epoch": 24.29, "learning_rate": 8.738376049797482e-05, "loss": 0.0469, "step": 101160 }, { "epoch": 24.29, "learning_rate": 8.738137669455563e-05, "loss": 0.0542, "step": 101170 }, { "epoch": 24.29, "learning_rate": 8.737899269847251e-05, "loss": 0.0491, "step": 101180 }, { "epoch": 24.29, "learning_rate": 8.737660850973774e-05, "loss": 0.04, "step": 101190 }, { "epoch": 24.29, "learning_rate": 8.737422412836364e-05, "loss": 0.0504, "step": 101200 }, { "epoch": 24.3, "learning_rate": 8.737183955436246e-05, "loss": 0.0309, "step": 101210 }, { "epoch": 24.3, "learning_rate": 8.736945478774652e-05, "loss": 0.0414, "step": 101220 }, { "epoch": 24.3, "learning_rate": 8.736706982852808e-05, "loss": 0.0394, "step": 101230 }, { "epoch": 24.3, "learning_rate": 8.736468467671945e-05, "loss": 0.0275, "step": 101240 }, { "epoch": 24.31, "learning_rate": 8.736229933233294e-05, "loss": 0.0478, "step": 101250 }, { "epoch": 24.31, "learning_rate": 8.735991379538082e-05, "loss": 0.0481, "step": 101260 }, { "epoch": 24.31, "learning_rate": 8.735752806587538e-05, "loss": 0.0481, "step": 101270 }, { "epoch": 24.31, "learning_rate": 8.735514214382894e-05, "loss": 0.0413, "step": 101280 }, { "epoch": 24.31, "learning_rate": 8.73527560292538e-05, "loss": 0.0362, "step": 101290 }, { "epoch": 24.32, "learning_rate": 8.735036972216222e-05, "loss": 0.0278, "step": 101300 }, { "epoch": 24.32, "learning_rate": 8.734798322256652e-05, "loss": 0.0391, "step": 101310 }, { "epoch": 24.32, "learning_rate": 8.734559653047901e-05, "loss": 0.0361, "step": 101320 }, { "epoch": 24.32, "learning_rate": 8.734320964591198e-05, "loss": 0.0515, "step": 101330 }, { "epoch": 24.33, "learning_rate": 8.734082256887775e-05, "loss": 0.0334, "step": 101340 }, { "epoch": 24.33, "learning_rate": 8.733843529938859e-05, "loss": 0.0254, "step": 101350 }, { "epoch": 24.33, "learning_rate": 8.733604783745683e-05, "loss": 0.0487, "step": 101360 }, { "epoch": 24.33, "learning_rate": 8.733366018309477e-05, "loss": 0.0375, "step": 101370 }, { "epoch": 24.34, "learning_rate": 8.733127233631472e-05, "loss": 0.0464, "step": 101380 }, { "epoch": 24.34, "learning_rate": 8.732888429712896e-05, "loss": 0.0448, "step": 101390 }, { "epoch": 24.34, "learning_rate": 8.732649606554984e-05, "loss": 0.0299, "step": 101400 }, { "epoch": 24.34, "learning_rate": 8.732410764158963e-05, "loss": 0.033, "step": 101410 }, { "epoch": 24.34, "learning_rate": 8.732171902526068e-05, "loss": 0.038, "step": 101420 }, { "epoch": 24.35, "learning_rate": 8.731933021657524e-05, "loss": 0.0326, "step": 101430 }, { "epoch": 24.35, "learning_rate": 8.731694121554569e-05, "loss": 0.0242, "step": 101440 }, { "epoch": 24.35, "learning_rate": 8.731455202218431e-05, "loss": 0.0507, "step": 101450 }, { "epoch": 24.35, "learning_rate": 8.731216263650342e-05, "loss": 0.023, "step": 101460 }, { "epoch": 24.36, "learning_rate": 8.730977305851531e-05, "loss": 0.0262, "step": 101470 }, { "epoch": 24.36, "learning_rate": 8.730738328823234e-05, "loss": 0.0404, "step": 101480 }, { "epoch": 24.36, "learning_rate": 8.73049933256668e-05, "loss": 0.0601, "step": 101490 }, { "epoch": 24.36, "learning_rate": 8.730260317083102e-05, "loss": 0.0491, "step": 101500 }, { "epoch": 24.37, "learning_rate": 8.730021282373728e-05, "loss": 0.036, "step": 101510 }, { "epoch": 24.37, "learning_rate": 8.729782228439796e-05, "loss": 0.05, "step": 101520 }, { "epoch": 24.37, "learning_rate": 8.729543155282533e-05, "loss": 0.0562, "step": 101530 }, { "epoch": 24.37, "learning_rate": 8.729304062903176e-05, "loss": 0.0531, "step": 101540 }, { "epoch": 24.37, "learning_rate": 8.729064951302953e-05, "loss": 0.0351, "step": 101550 }, { "epoch": 24.38, "learning_rate": 8.728825820483099e-05, "loss": 0.0774, "step": 101560 }, { "epoch": 24.38, "learning_rate": 8.728586670444845e-05, "loss": 0.0318, "step": 101570 }, { "epoch": 24.38, "learning_rate": 8.728347501189425e-05, "loss": 0.0536, "step": 101580 }, { "epoch": 24.38, "learning_rate": 8.72810831271807e-05, "loss": 0.0259, "step": 101590 }, { "epoch": 24.39, "learning_rate": 8.727869105032014e-05, "loss": 0.0383, "step": 101600 }, { "epoch": 24.39, "learning_rate": 8.727629878132489e-05, "loss": 0.0269, "step": 101610 }, { "epoch": 24.39, "learning_rate": 8.727390632020728e-05, "loss": 0.0344, "step": 101620 }, { "epoch": 24.39, "learning_rate": 8.727151366697965e-05, "loss": 0.0468, "step": 101630 }, { "epoch": 24.39, "learning_rate": 8.726912082165432e-05, "loss": 0.0422, "step": 101640 }, { "epoch": 24.4, "learning_rate": 8.726672778424365e-05, "loss": 0.0391, "step": 101650 }, { "epoch": 24.4, "learning_rate": 8.726433455475994e-05, "loss": 0.0515, "step": 101660 }, { "epoch": 24.4, "learning_rate": 8.726194113321554e-05, "loss": 0.0358, "step": 101670 }, { "epoch": 24.4, "learning_rate": 8.725954751962279e-05, "loss": 0.0324, "step": 101680 }, { "epoch": 24.41, "learning_rate": 8.725715371399402e-05, "loss": 0.03, "step": 101690 }, { "epoch": 24.41, "learning_rate": 8.725475971634156e-05, "loss": 0.0302, "step": 101700 }, { "epoch": 24.41, "learning_rate": 8.725236552667774e-05, "loss": 0.0394, "step": 101710 }, { "epoch": 24.41, "learning_rate": 8.724997114501495e-05, "loss": 0.0537, "step": 101720 }, { "epoch": 24.42, "learning_rate": 8.724757657136548e-05, "loss": 0.0331, "step": 101730 }, { "epoch": 24.42, "learning_rate": 8.724518180574171e-05, "loss": 0.0411, "step": 101740 }, { "epoch": 24.42, "learning_rate": 8.724278684815593e-05, "loss": 0.0558, "step": 101750 }, { "epoch": 24.42, "learning_rate": 8.724039169862053e-05, "loss": 0.0388, "step": 101760 }, { "epoch": 24.42, "learning_rate": 8.723799635714785e-05, "loss": 0.0612, "step": 101770 }, { "epoch": 24.43, "learning_rate": 8.723560082375021e-05, "loss": 0.0408, "step": 101780 }, { "epoch": 24.43, "learning_rate": 8.723320509843998e-05, "loss": 0.0506, "step": 101790 }, { "epoch": 24.43, "learning_rate": 8.72308091812295e-05, "loss": 0.0442, "step": 101800 }, { "epoch": 24.43, "learning_rate": 8.72284130721311e-05, "loss": 0.053, "step": 101810 }, { "epoch": 24.44, "learning_rate": 8.722601677115717e-05, "loss": 0.0455, "step": 101820 }, { "epoch": 24.44, "learning_rate": 8.722362027832003e-05, "loss": 0.0305, "step": 101830 }, { "epoch": 24.44, "learning_rate": 8.722122359363204e-05, "loss": 0.0531, "step": 101840 }, { "epoch": 24.44, "learning_rate": 8.721882671710556e-05, "loss": 0.037, "step": 101850 }, { "epoch": 24.45, "learning_rate": 8.721642964875292e-05, "loss": 0.0522, "step": 101860 }, { "epoch": 24.45, "learning_rate": 8.72140323885865e-05, "loss": 0.0388, "step": 101870 }, { "epoch": 24.45, "learning_rate": 8.721163493661865e-05, "loss": 0.0306, "step": 101880 }, { "epoch": 24.45, "learning_rate": 8.720923729286172e-05, "loss": 0.0492, "step": 101890 }, { "epoch": 24.45, "learning_rate": 8.720683945732808e-05, "loss": 0.0296, "step": 101900 }, { "epoch": 24.46, "learning_rate": 8.720444143003006e-05, "loss": 0.0365, "step": 101910 }, { "epoch": 24.46, "learning_rate": 8.720204321098004e-05, "loss": 0.0539, "step": 101920 }, { "epoch": 24.46, "learning_rate": 8.719964480019038e-05, "loss": 0.0334, "step": 101930 }, { "epoch": 24.46, "learning_rate": 8.719724619767345e-05, "loss": 0.0546, "step": 101940 }, { "epoch": 24.47, "learning_rate": 8.71948474034416e-05, "loss": 0.031, "step": 101950 }, { "epoch": 24.47, "learning_rate": 8.719244841750719e-05, "loss": 0.0344, "step": 101960 }, { "epoch": 24.47, "learning_rate": 8.719004923988258e-05, "loss": 0.0408, "step": 101970 }, { "epoch": 24.47, "learning_rate": 8.718764987058016e-05, "loss": 0.051, "step": 101980 }, { "epoch": 24.47, "learning_rate": 8.718525030961228e-05, "loss": 0.0344, "step": 101990 }, { "epoch": 24.48, "learning_rate": 8.718285055699131e-05, "loss": 0.0492, "step": 102000 }, { "epoch": 24.48, "learning_rate": 8.718045061272961e-05, "loss": 0.0373, "step": 102010 }, { "epoch": 24.48, "learning_rate": 8.717805047683957e-05, "loss": 0.0304, "step": 102020 }, { "epoch": 24.48, "learning_rate": 8.717565014933353e-05, "loss": 0.0272, "step": 102030 }, { "epoch": 24.49, "learning_rate": 8.71732496302239e-05, "loss": 0.0421, "step": 102040 }, { "epoch": 24.49, "learning_rate": 8.717084891952301e-05, "loss": 0.056, "step": 102050 }, { "epoch": 24.49, "learning_rate": 8.716844801724326e-05, "loss": 0.0475, "step": 102060 }, { "epoch": 24.49, "learning_rate": 8.716604692339702e-05, "loss": 0.0301, "step": 102070 }, { "epoch": 24.5, "learning_rate": 8.716364563799667e-05, "loss": 0.0387, "step": 102080 }, { "epoch": 24.5, "learning_rate": 8.716124416105458e-05, "loss": 0.0251, "step": 102090 }, { "epoch": 24.5, "learning_rate": 8.715884249258311e-05, "loss": 0.0548, "step": 102100 }, { "epoch": 24.5, "learning_rate": 8.715644063259466e-05, "loss": 0.038, "step": 102110 }, { "epoch": 24.5, "learning_rate": 8.715403858110161e-05, "loss": 0.0432, "step": 102120 }, { "epoch": 24.51, "learning_rate": 8.715163633811633e-05, "loss": 0.031, "step": 102130 }, { "epoch": 24.51, "learning_rate": 8.714923390365122e-05, "loss": 0.0482, "step": 102140 }, { "epoch": 24.51, "learning_rate": 8.714683127771863e-05, "loss": 0.0393, "step": 102150 }, { "epoch": 24.51, "learning_rate": 8.714442846033097e-05, "loss": 0.0372, "step": 102160 }, { "epoch": 24.52, "learning_rate": 8.714202545150063e-05, "loss": 0.0535, "step": 102170 }, { "epoch": 24.52, "learning_rate": 8.713962225123996e-05, "loss": 0.0461, "step": 102180 }, { "epoch": 24.52, "learning_rate": 8.713721885956136e-05, "loss": 0.0322, "step": 102190 }, { "epoch": 24.52, "learning_rate": 8.713481527647724e-05, "loss": 0.0589, "step": 102200 }, { "epoch": 24.53, "learning_rate": 8.713241150199997e-05, "loss": 0.0634, "step": 102210 }, { "epoch": 24.53, "learning_rate": 8.713000753614193e-05, "loss": 0.0449, "step": 102220 }, { "epoch": 24.53, "learning_rate": 8.712760337891554e-05, "loss": 0.0463, "step": 102230 }, { "epoch": 24.53, "learning_rate": 8.712519903033317e-05, "loss": 0.0744, "step": 102240 }, { "epoch": 24.53, "learning_rate": 8.712279449040719e-05, "loss": 0.0492, "step": 102250 }, { "epoch": 24.54, "learning_rate": 8.712038975915004e-05, "loss": 0.0717, "step": 102260 }, { "epoch": 24.54, "learning_rate": 8.711798483657407e-05, "loss": 0.1002, "step": 102270 }, { "epoch": 24.54, "learning_rate": 8.711557972269171e-05, "loss": 0.0886, "step": 102280 }, { "epoch": 24.54, "learning_rate": 8.711317441751535e-05, "loss": 0.0504, "step": 102290 }, { "epoch": 24.55, "learning_rate": 8.711076892105736e-05, "loss": 0.069, "step": 102300 }, { "epoch": 24.55, "learning_rate": 8.710836323333015e-05, "loss": 0.0833, "step": 102310 }, { "epoch": 24.55, "learning_rate": 8.710595735434615e-05, "loss": 0.0679, "step": 102320 }, { "epoch": 24.55, "learning_rate": 8.710355128411773e-05, "loss": 0.1018, "step": 102330 }, { "epoch": 24.55, "learning_rate": 8.71011450226573e-05, "loss": 0.0633, "step": 102340 }, { "epoch": 24.56, "learning_rate": 8.709873856997724e-05, "loss": 0.0486, "step": 102350 }, { "epoch": 24.56, "learning_rate": 8.709633192608999e-05, "loss": 0.0454, "step": 102360 }, { "epoch": 24.56, "learning_rate": 8.709392509100792e-05, "loss": 0.0536, "step": 102370 }, { "epoch": 24.56, "learning_rate": 8.709151806474346e-05, "loss": 0.1047, "step": 102380 }, { "epoch": 24.57, "learning_rate": 8.708911084730901e-05, "loss": 0.0979, "step": 102390 }, { "epoch": 24.57, "learning_rate": 8.708670343871697e-05, "loss": 0.0552, "step": 102400 }, { "epoch": 24.57, "learning_rate": 8.708429583897975e-05, "loss": 0.0502, "step": 102410 }, { "epoch": 24.57, "learning_rate": 8.708188804810975e-05, "loss": 0.0635, "step": 102420 }, { "epoch": 24.58, "learning_rate": 8.70794800661194e-05, "loss": 0.0639, "step": 102430 }, { "epoch": 24.58, "learning_rate": 8.707707189302108e-05, "loss": 0.0438, "step": 102440 }, { "epoch": 24.58, "learning_rate": 8.707466352882723e-05, "loss": 0.0398, "step": 102450 }, { "epoch": 24.58, "learning_rate": 8.707225497355027e-05, "loss": 0.0503, "step": 102460 }, { "epoch": 24.58, "learning_rate": 8.706984622720259e-05, "loss": 0.0604, "step": 102470 }, { "epoch": 24.59, "learning_rate": 8.70674372897966e-05, "loss": 0.0747, "step": 102480 }, { "epoch": 24.59, "learning_rate": 8.706502816134474e-05, "loss": 0.0458, "step": 102490 }, { "epoch": 24.59, "learning_rate": 8.706261884185942e-05, "loss": 0.0526, "step": 102500 }, { "epoch": 24.59, "learning_rate": 8.706020933135304e-05, "loss": 0.0446, "step": 102510 }, { "epoch": 24.6, "learning_rate": 8.705779962983804e-05, "loss": 0.0594, "step": 102520 }, { "epoch": 24.6, "learning_rate": 8.705538973732684e-05, "loss": 0.0869, "step": 102530 }, { "epoch": 24.6, "learning_rate": 8.705297965383184e-05, "loss": 0.0903, "step": 102540 }, { "epoch": 24.6, "learning_rate": 8.705056937936548e-05, "loss": 0.047, "step": 102550 }, { "epoch": 24.61, "learning_rate": 8.704815891394016e-05, "loss": 0.0433, "step": 102560 }, { "epoch": 24.61, "learning_rate": 8.704574825756834e-05, "loss": 0.0686, "step": 102570 }, { "epoch": 24.61, "learning_rate": 8.704333741026241e-05, "loss": 0.0766, "step": 102580 }, { "epoch": 24.61, "learning_rate": 8.704092637203481e-05, "loss": 0.0333, "step": 102590 }, { "epoch": 24.61, "learning_rate": 8.703851514289797e-05, "loss": 0.0505, "step": 102600 }, { "epoch": 24.62, "learning_rate": 8.703610372286432e-05, "loss": 0.0421, "step": 102610 }, { "epoch": 24.62, "learning_rate": 8.703369211194628e-05, "loss": 0.0821, "step": 102620 }, { "epoch": 24.62, "learning_rate": 8.703128031015626e-05, "loss": 0.0401, "step": 102630 }, { "epoch": 24.62, "learning_rate": 8.702886831750673e-05, "loss": 0.0761, "step": 102640 }, { "epoch": 24.63, "learning_rate": 8.702645613401011e-05, "loss": 0.0554, "step": 102650 }, { "epoch": 24.63, "learning_rate": 8.702404375967881e-05, "loss": 0.0632, "step": 102660 }, { "epoch": 24.63, "learning_rate": 8.702163119452528e-05, "loss": 0.0528, "step": 102670 }, { "epoch": 24.63, "learning_rate": 8.701921843856196e-05, "loss": 0.057, "step": 102680 }, { "epoch": 24.63, "learning_rate": 8.701680549180126e-05, "loss": 0.0695, "step": 102690 }, { "epoch": 24.64, "learning_rate": 8.701439235425566e-05, "loss": 0.0492, "step": 102700 }, { "epoch": 24.64, "learning_rate": 8.701197902593756e-05, "loss": 0.0527, "step": 102710 }, { "epoch": 24.64, "learning_rate": 8.700956550685942e-05, "loss": 0.0747, "step": 102720 }, { "epoch": 24.64, "learning_rate": 8.700715179703367e-05, "loss": 0.0281, "step": 102730 }, { "epoch": 24.65, "learning_rate": 8.700473789647275e-05, "loss": 0.0816, "step": 102740 }, { "epoch": 24.65, "learning_rate": 8.700232380518909e-05, "loss": 0.0778, "step": 102750 }, { "epoch": 24.65, "learning_rate": 8.699990952319515e-05, "loss": 0.0544, "step": 102760 }, { "epoch": 24.65, "learning_rate": 8.699749505050337e-05, "loss": 0.0495, "step": 102770 }, { "epoch": 24.66, "learning_rate": 8.699508038712619e-05, "loss": 0.0673, "step": 102780 }, { "epoch": 24.66, "learning_rate": 8.699266553307606e-05, "loss": 0.0798, "step": 102790 }, { "epoch": 24.66, "learning_rate": 8.699025048836541e-05, "loss": 0.0346, "step": 102800 }, { "epoch": 24.66, "learning_rate": 8.69878352530067e-05, "loss": 0.0473, "step": 102810 }, { "epoch": 24.66, "learning_rate": 8.69854198270124e-05, "loss": 0.0693, "step": 102820 }, { "epoch": 24.67, "learning_rate": 8.698300421039491e-05, "loss": 0.0486, "step": 102830 }, { "epoch": 24.67, "learning_rate": 8.698058840316672e-05, "loss": 0.0596, "step": 102840 }, { "epoch": 24.67, "learning_rate": 8.697817240534027e-05, "loss": 0.0428, "step": 102850 }, { "epoch": 24.67, "learning_rate": 8.697575621692801e-05, "loss": 0.0607, "step": 102860 }, { "epoch": 24.68, "learning_rate": 8.69733398379424e-05, "loss": 0.0589, "step": 102870 }, { "epoch": 24.68, "learning_rate": 8.697092326839586e-05, "loss": 0.0411, "step": 102880 }, { "epoch": 24.68, "learning_rate": 8.69685065083009e-05, "loss": 0.0715, "step": 102890 }, { "epoch": 24.68, "learning_rate": 8.696608955766994e-05, "loss": 0.0515, "step": 102900 }, { "epoch": 24.69, "learning_rate": 8.696367241651545e-05, "loss": 0.0502, "step": 102910 }, { "epoch": 24.69, "learning_rate": 8.696125508484989e-05, "loss": 0.035, "step": 102920 }, { "epoch": 24.69, "learning_rate": 8.695883756268569e-05, "loss": 0.0667, "step": 102930 }, { "epoch": 24.69, "learning_rate": 8.695641985003535e-05, "loss": 0.0379, "step": 102940 }, { "epoch": 24.69, "learning_rate": 8.69540019469113e-05, "loss": 0.05, "step": 102950 }, { "epoch": 24.7, "learning_rate": 8.695158385332603e-05, "loss": 0.0489, "step": 102960 }, { "epoch": 24.7, "learning_rate": 8.694916556929198e-05, "loss": 0.0317, "step": 102970 }, { "epoch": 24.7, "learning_rate": 8.694674709482161e-05, "loss": 0.0748, "step": 102980 }, { "epoch": 24.7, "learning_rate": 8.694432842992742e-05, "loss": 0.0417, "step": 102990 }, { "epoch": 24.71, "learning_rate": 8.694190957462183e-05, "loss": 0.0349, "step": 103000 }, { "epoch": 24.71, "learning_rate": 8.693949052891735e-05, "loss": 0.0647, "step": 103010 }, { "epoch": 24.71, "learning_rate": 8.693707129282642e-05, "loss": 0.0676, "step": 103020 }, { "epoch": 24.71, "learning_rate": 8.69346518663615e-05, "loss": 0.059, "step": 103030 }, { "epoch": 24.71, "learning_rate": 8.693223224953509e-05, "loss": 0.0436, "step": 103040 }, { "epoch": 24.72, "learning_rate": 8.692981244235965e-05, "loss": 0.0549, "step": 103050 }, { "epoch": 24.72, "learning_rate": 8.692739244484765e-05, "loss": 0.0521, "step": 103060 }, { "epoch": 24.72, "learning_rate": 8.692497225701155e-05, "loss": 0.0529, "step": 103070 }, { "epoch": 24.72, "learning_rate": 8.692255187886384e-05, "loss": 0.0386, "step": 103080 }, { "epoch": 24.73, "learning_rate": 8.692013131041698e-05, "loss": 0.043, "step": 103090 }, { "epoch": 24.73, "learning_rate": 8.691771055168344e-05, "loss": 0.0555, "step": 103100 }, { "epoch": 24.73, "learning_rate": 8.691528960267575e-05, "loss": 0.0321, "step": 103110 }, { "epoch": 24.73, "learning_rate": 8.691286846340634e-05, "loss": 0.0531, "step": 103120 }, { "epoch": 24.74, "learning_rate": 8.691044713388767e-05, "loss": 0.0707, "step": 103130 }, { "epoch": 24.74, "learning_rate": 8.690802561413228e-05, "loss": 0.0652, "step": 103140 }, { "epoch": 24.74, "learning_rate": 8.69056039041526e-05, "loss": 0.0435, "step": 103150 }, { "epoch": 24.74, "learning_rate": 8.690318200396113e-05, "loss": 0.0433, "step": 103160 }, { "epoch": 24.74, "learning_rate": 8.690075991357037e-05, "loss": 0.0442, "step": 103170 }, { "epoch": 24.75, "learning_rate": 8.689833763299275e-05, "loss": 0.0525, "step": 103180 }, { "epoch": 24.75, "learning_rate": 8.68959151622408e-05, "loss": 0.075, "step": 103190 }, { "epoch": 24.75, "learning_rate": 8.689349250132702e-05, "loss": 0.0388, "step": 103200 }, { "epoch": 24.75, "learning_rate": 8.689106965026386e-05, "loss": 0.0423, "step": 103210 }, { "epoch": 24.76, "learning_rate": 8.68886466090638e-05, "loss": 0.051, "step": 103220 }, { "epoch": 24.76, "learning_rate": 8.688622337773937e-05, "loss": 0.0422, "step": 103230 }, { "epoch": 24.76, "learning_rate": 8.688379995630302e-05, "loss": 0.0424, "step": 103240 }, { "epoch": 24.76, "learning_rate": 8.688137634476726e-05, "loss": 0.0627, "step": 103250 }, { "epoch": 24.77, "learning_rate": 8.687895254314457e-05, "loss": 0.0852, "step": 103260 }, { "epoch": 24.77, "learning_rate": 8.687652855144748e-05, "loss": 0.062, "step": 103270 }, { "epoch": 24.77, "learning_rate": 8.687410436968842e-05, "loss": 0.0758, "step": 103280 }, { "epoch": 24.77, "learning_rate": 8.687167999787995e-05, "loss": 0.0379, "step": 103290 }, { "epoch": 24.77, "learning_rate": 8.68692554360345e-05, "loss": 0.0512, "step": 103300 }, { "epoch": 24.78, "learning_rate": 8.686683068416462e-05, "loss": 0.0467, "step": 103310 }, { "epoch": 24.78, "learning_rate": 8.686440574228279e-05, "loss": 0.0348, "step": 103320 }, { "epoch": 24.78, "learning_rate": 8.68619806104015e-05, "loss": 0.0444, "step": 103330 }, { "epoch": 24.78, "learning_rate": 8.685955528853324e-05, "loss": 0.0426, "step": 103340 }, { "epoch": 24.79, "learning_rate": 8.685712977669053e-05, "loss": 0.0653, "step": 103350 }, { "epoch": 24.79, "learning_rate": 8.685470407488587e-05, "loss": 0.03, "step": 103360 }, { "epoch": 24.79, "learning_rate": 8.685227818313176e-05, "loss": 0.0417, "step": 103370 }, { "epoch": 24.79, "learning_rate": 8.68498521014407e-05, "loss": 0.0635, "step": 103380 }, { "epoch": 24.79, "learning_rate": 8.68474258298252e-05, "loss": 0.057, "step": 103390 }, { "epoch": 24.8, "learning_rate": 8.684499936829774e-05, "loss": 0.0772, "step": 103400 }, { "epoch": 24.8, "learning_rate": 8.684257271687086e-05, "loss": 0.0527, "step": 103410 }, { "epoch": 24.8, "learning_rate": 8.684014587555704e-05, "loss": 0.0401, "step": 103420 }, { "epoch": 24.8, "learning_rate": 8.68377188443688e-05, "loss": 0.0451, "step": 103430 }, { "epoch": 24.81, "learning_rate": 8.683529162331866e-05, "loss": 0.041, "step": 103440 }, { "epoch": 24.81, "learning_rate": 8.683286421241911e-05, "loss": 0.0359, "step": 103450 }, { "epoch": 24.81, "learning_rate": 8.683043661168269e-05, "loss": 0.0358, "step": 103460 }, { "epoch": 24.81, "learning_rate": 8.682800882112188e-05, "loss": 0.0428, "step": 103470 }, { "epoch": 24.82, "learning_rate": 8.682558084074919e-05, "loss": 0.0376, "step": 103480 }, { "epoch": 24.82, "learning_rate": 8.682315267057717e-05, "loss": 0.0297, "step": 103490 }, { "epoch": 24.82, "learning_rate": 8.68207243106183e-05, "loss": 0.0271, "step": 103500 }, { "epoch": 24.82, "learning_rate": 8.681829576088511e-05, "loss": 0.0499, "step": 103510 }, { "epoch": 24.82, "learning_rate": 8.681586702139012e-05, "loss": 0.0478, "step": 103520 }, { "epoch": 24.83, "learning_rate": 8.681343809214585e-05, "loss": 0.0407, "step": 103530 }, { "epoch": 24.83, "learning_rate": 8.681100897316481e-05, "loss": 0.0649, "step": 103540 }, { "epoch": 24.83, "learning_rate": 8.680857966445951e-05, "loss": 0.0346, "step": 103550 }, { "epoch": 24.83, "learning_rate": 8.680615016604249e-05, "loss": 0.0487, "step": 103560 }, { "epoch": 24.84, "learning_rate": 8.680372047792626e-05, "loss": 0.0439, "step": 103570 }, { "epoch": 24.84, "learning_rate": 8.680129060012336e-05, "loss": 0.0431, "step": 103580 }, { "epoch": 24.84, "learning_rate": 8.67988605326463e-05, "loss": 0.0486, "step": 103590 }, { "epoch": 24.84, "learning_rate": 8.67964302755076e-05, "loss": 0.0601, "step": 103600 }, { "epoch": 24.85, "learning_rate": 8.679399982871978e-05, "loss": 0.0475, "step": 103610 }, { "epoch": 24.85, "learning_rate": 8.679156919229539e-05, "loss": 0.0363, "step": 103620 }, { "epoch": 24.85, "learning_rate": 8.678913836624694e-05, "loss": 0.0649, "step": 103630 }, { "epoch": 24.85, "learning_rate": 8.678670735058696e-05, "loss": 0.0511, "step": 103640 }, { "epoch": 24.85, "learning_rate": 8.678427614532799e-05, "loss": 0.0689, "step": 103650 }, { "epoch": 24.86, "learning_rate": 8.678184475048255e-05, "loss": 0.0476, "step": 103660 }, { "epoch": 24.86, "learning_rate": 8.677941316606317e-05, "loss": 0.0512, "step": 103670 }, { "epoch": 24.86, "learning_rate": 8.677698139208238e-05, "loss": 0.0282, "step": 103680 }, { "epoch": 24.86, "learning_rate": 8.677454942855274e-05, "loss": 0.0315, "step": 103690 }, { "epoch": 24.87, "learning_rate": 8.677211727548675e-05, "loss": 0.0474, "step": 103700 }, { "epoch": 24.87, "learning_rate": 8.676968493289696e-05, "loss": 0.059, "step": 103710 }, { "epoch": 24.87, "learning_rate": 8.676725240079593e-05, "loss": 0.0386, "step": 103720 }, { "epoch": 24.87, "learning_rate": 8.676481967919617e-05, "loss": 0.0366, "step": 103730 }, { "epoch": 24.87, "learning_rate": 8.67623867681102e-05, "loss": 0.0255, "step": 103740 }, { "epoch": 24.88, "learning_rate": 8.675995366755058e-05, "loss": 0.046, "step": 103750 }, { "epoch": 24.88, "learning_rate": 8.675752037752987e-05, "loss": 0.0407, "step": 103760 }, { "epoch": 24.88, "learning_rate": 8.675508689806058e-05, "loss": 0.0331, "step": 103770 }, { "epoch": 24.88, "learning_rate": 8.675265322915527e-05, "loss": 0.051, "step": 103780 }, { "epoch": 24.89, "learning_rate": 8.675021937082648e-05, "loss": 0.0431, "step": 103790 }, { "epoch": 24.89, "learning_rate": 8.674778532308677e-05, "loss": 0.0505, "step": 103800 }, { "epoch": 24.89, "learning_rate": 8.674535108594864e-05, "loss": 0.0467, "step": 103810 }, { "epoch": 24.89, "learning_rate": 8.674291665942467e-05, "loss": 0.0391, "step": 103820 }, { "epoch": 24.9, "learning_rate": 8.674048204352741e-05, "loss": 0.0271, "step": 103830 }, { "epoch": 24.9, "learning_rate": 8.673804723826938e-05, "loss": 0.0587, "step": 103840 }, { "epoch": 24.9, "learning_rate": 8.673561224366316e-05, "loss": 0.0255, "step": 103850 }, { "epoch": 24.9, "learning_rate": 8.673317705972128e-05, "loss": 0.0325, "step": 103860 }, { "epoch": 24.9, "learning_rate": 8.67307416864563e-05, "loss": 0.03, "step": 103870 }, { "epoch": 24.91, "learning_rate": 8.672830612388076e-05, "loss": 0.0342, "step": 103880 }, { "epoch": 24.91, "learning_rate": 8.672587037200726e-05, "loss": 0.0624, "step": 103890 }, { "epoch": 24.91, "learning_rate": 8.67234344308483e-05, "loss": 0.0412, "step": 103900 }, { "epoch": 24.91, "learning_rate": 8.672099830041644e-05, "loss": 0.0382, "step": 103910 }, { "epoch": 24.92, "learning_rate": 8.671856198072425e-05, "loss": 0.0483, "step": 103920 }, { "epoch": 24.92, "learning_rate": 8.671612547178428e-05, "loss": 0.0619, "step": 103930 }, { "epoch": 24.92, "learning_rate": 8.67136887736091e-05, "loss": 0.0563, "step": 103940 }, { "epoch": 24.92, "learning_rate": 8.671125188621126e-05, "loss": 0.0582, "step": 103950 }, { "epoch": 24.93, "learning_rate": 8.670881480960333e-05, "loss": 0.0566, "step": 103960 }, { "epoch": 24.93, "learning_rate": 8.670637754379784e-05, "loss": 0.0547, "step": 103970 }, { "epoch": 24.93, "learning_rate": 8.67039400888074e-05, "loss": 0.0474, "step": 103980 }, { "epoch": 24.93, "learning_rate": 8.670150244464453e-05, "loss": 0.0709, "step": 103990 }, { "epoch": 24.93, "learning_rate": 8.669906461132182e-05, "loss": 0.0536, "step": 104000 }, { "epoch": 24.94, "learning_rate": 8.669662658885182e-05, "loss": 0.0375, "step": 104010 }, { "epoch": 24.94, "learning_rate": 8.669418837724709e-05, "loss": 0.087, "step": 104020 }, { "epoch": 24.94, "learning_rate": 8.66917499765202e-05, "loss": 0.0369, "step": 104030 }, { "epoch": 24.94, "learning_rate": 8.668931138668374e-05, "loss": 0.0519, "step": 104040 }, { "epoch": 24.95, "learning_rate": 8.668687260775028e-05, "loss": 0.0472, "step": 104050 }, { "epoch": 24.95, "learning_rate": 8.668443363973234e-05, "loss": 0.0565, "step": 104060 }, { "epoch": 24.95, "learning_rate": 8.668199448264254e-05, "loss": 0.0409, "step": 104070 }, { "epoch": 25.0, "learning_rate": 8.667955513649343e-05, "loss": 0.0413, "step": 104080 }, { "epoch": 25.0, "learning_rate": 8.667711560129759e-05, "loss": 0.0431, "step": 104090 }, { "epoch": 25.01, "learning_rate": 8.667467587706757e-05, "loss": 0.0395, "step": 104100 }, { "epoch": 25.01, "learning_rate": 8.667223596381598e-05, "loss": 0.0441, "step": 104110 }, { "epoch": 25.01, "learning_rate": 8.666979586155538e-05, "loss": 0.0416, "step": 104120 }, { "epoch": 25.01, "learning_rate": 8.666735557029835e-05, "loss": 0.0636, "step": 104130 }, { "epoch": 25.01, "learning_rate": 8.666491509005745e-05, "loss": 0.0462, "step": 104140 }, { "epoch": 25.02, "learning_rate": 8.666247442084528e-05, "loss": 0.0448, "step": 104150 }, { "epoch": 25.02, "learning_rate": 8.666003356267441e-05, "loss": 0.0248, "step": 104160 }, { "epoch": 25.02, "learning_rate": 8.66575925155574e-05, "loss": 0.0305, "step": 104170 }, { "epoch": 25.02, "learning_rate": 8.665515127950688e-05, "loss": 0.0536, "step": 104180 }, { "epoch": 25.03, "learning_rate": 8.665270985453539e-05, "loss": 0.0339, "step": 104190 }, { "epoch": 25.03, "learning_rate": 8.665026824065554e-05, "loss": 0.0414, "step": 104200 }, { "epoch": 25.03, "learning_rate": 8.664782643787988e-05, "loss": 0.0439, "step": 104210 }, { "epoch": 25.03, "learning_rate": 8.664538444622103e-05, "loss": 0.0472, "step": 104220 }, { "epoch": 25.04, "learning_rate": 8.664294226569157e-05, "loss": 0.0498, "step": 104230 }, { "epoch": 25.04, "learning_rate": 8.664049989630408e-05, "loss": 0.0464, "step": 104240 }, { "epoch": 25.04, "learning_rate": 8.663805733807113e-05, "loss": 0.0345, "step": 104250 }, { "epoch": 25.04, "learning_rate": 8.663561459100533e-05, "loss": 0.0444, "step": 104260 }, { "epoch": 25.04, "learning_rate": 8.663317165511926e-05, "loss": 0.0436, "step": 104270 }, { "epoch": 25.05, "learning_rate": 8.663072853042554e-05, "loss": 0.0362, "step": 104280 }, { "epoch": 25.05, "learning_rate": 8.662828521693672e-05, "loss": 0.04, "step": 104290 }, { "epoch": 25.05, "learning_rate": 8.66258417146654e-05, "loss": 0.0536, "step": 104300 }, { "epoch": 25.05, "learning_rate": 8.662339802362422e-05, "loss": 0.0596, "step": 104310 }, { "epoch": 25.06, "learning_rate": 8.662095414382571e-05, "loss": 0.05, "step": 104320 }, { "epoch": 25.06, "learning_rate": 8.661851007528252e-05, "loss": 0.0376, "step": 104330 }, { "epoch": 25.06, "learning_rate": 8.661606581800721e-05, "loss": 0.0342, "step": 104340 }, { "epoch": 25.06, "learning_rate": 8.66136213720124e-05, "loss": 0.0416, "step": 104350 }, { "epoch": 25.07, "learning_rate": 8.661117673731067e-05, "loss": 0.0572, "step": 104360 }, { "epoch": 25.07, "learning_rate": 8.660873191391463e-05, "loss": 0.0433, "step": 104370 }, { "epoch": 25.07, "learning_rate": 8.660628690183687e-05, "loss": 0.0585, "step": 104380 }, { "epoch": 25.07, "learning_rate": 8.660384170109002e-05, "loss": 0.0556, "step": 104390 }, { "epoch": 25.07, "learning_rate": 8.660139631168667e-05, "loss": 0.0423, "step": 104400 }, { "epoch": 25.08, "learning_rate": 8.65989507336394e-05, "loss": 0.0388, "step": 104410 }, { "epoch": 25.08, "learning_rate": 8.659650496696083e-05, "loss": 0.055, "step": 104420 }, { "epoch": 25.08, "learning_rate": 8.659405901166358e-05, "loss": 0.0752, "step": 104430 }, { "epoch": 25.08, "learning_rate": 8.659161286776023e-05, "loss": 0.0564, "step": 104440 }, { "epoch": 25.09, "learning_rate": 8.658916653526341e-05, "loss": 0.0583, "step": 104450 }, { "epoch": 25.09, "learning_rate": 8.658672001418571e-05, "loss": 0.0661, "step": 104460 }, { "epoch": 25.09, "learning_rate": 8.658427330453978e-05, "loss": 0.0503, "step": 104470 }, { "epoch": 25.09, "learning_rate": 8.658182640633817e-05, "loss": 0.0527, "step": 104480 }, { "epoch": 25.09, "learning_rate": 8.657937931959353e-05, "loss": 0.0663, "step": 104490 }, { "epoch": 25.1, "learning_rate": 8.657693204431845e-05, "loss": 0.0382, "step": 104500 }, { "epoch": 25.1, "learning_rate": 8.657448458052557e-05, "loss": 0.0336, "step": 104510 }, { "epoch": 25.1, "learning_rate": 8.65720369282275e-05, "loss": 0.0438, "step": 104520 }, { "epoch": 25.1, "learning_rate": 8.656958908743683e-05, "loss": 0.0432, "step": 104530 }, { "epoch": 25.11, "learning_rate": 8.656714105816619e-05, "loss": 0.0326, "step": 104540 }, { "epoch": 25.11, "learning_rate": 8.656469284042821e-05, "loss": 0.0293, "step": 104550 }, { "epoch": 25.11, "learning_rate": 8.65622444342355e-05, "loss": 0.0715, "step": 104560 }, { "epoch": 25.11, "learning_rate": 8.655979583960066e-05, "loss": 0.0539, "step": 104570 }, { "epoch": 25.12, "learning_rate": 8.655734705653635e-05, "loss": 0.033, "step": 104580 }, { "epoch": 25.12, "learning_rate": 8.655489808505515e-05, "loss": 0.0534, "step": 104590 }, { "epoch": 25.12, "learning_rate": 8.655244892516971e-05, "loss": 0.034, "step": 104600 }, { "epoch": 25.12, "learning_rate": 8.654999957689263e-05, "loss": 0.0398, "step": 104610 }, { "epoch": 25.12, "learning_rate": 8.654755004023655e-05, "loss": 0.0382, "step": 104620 }, { "epoch": 25.13, "learning_rate": 8.65451003152141e-05, "loss": 0.0239, "step": 104630 }, { "epoch": 25.13, "learning_rate": 8.654265040183788e-05, "loss": 0.0472, "step": 104640 }, { "epoch": 25.13, "learning_rate": 8.654020030012056e-05, "loss": 0.0325, "step": 104650 }, { "epoch": 25.13, "learning_rate": 8.653775001007473e-05, "loss": 0.0465, "step": 104660 }, { "epoch": 25.14, "learning_rate": 8.653529953171304e-05, "loss": 0.0481, "step": 104670 }, { "epoch": 25.14, "learning_rate": 8.653284886504808e-05, "loss": 0.0685, "step": 104680 }, { "epoch": 25.14, "learning_rate": 8.653039801009255e-05, "loss": 0.0688, "step": 104690 }, { "epoch": 25.14, "learning_rate": 8.652794696685902e-05, "loss": 0.0344, "step": 104700 }, { "epoch": 25.15, "learning_rate": 8.652549573536015e-05, "loss": 0.0484, "step": 104710 }, { "epoch": 25.15, "learning_rate": 8.652304431560858e-05, "loss": 0.0372, "step": 104720 }, { "epoch": 25.15, "learning_rate": 8.652059270761692e-05, "loss": 0.0488, "step": 104730 }, { "epoch": 25.15, "learning_rate": 8.651814091139783e-05, "loss": 0.0418, "step": 104740 }, { "epoch": 25.15, "learning_rate": 8.651568892696393e-05, "loss": 0.0652, "step": 104750 }, { "epoch": 25.16, "learning_rate": 8.651323675432787e-05, "loss": 0.0321, "step": 104760 }, { "epoch": 25.16, "learning_rate": 8.651078439350228e-05, "loss": 0.0429, "step": 104770 }, { "epoch": 25.16, "learning_rate": 8.65083318444998e-05, "loss": 0.0526, "step": 104780 }, { "epoch": 25.16, "learning_rate": 8.650587910733307e-05, "loss": 0.0401, "step": 104790 }, { "epoch": 25.17, "learning_rate": 8.650342618201475e-05, "loss": 0.0427, "step": 104800 }, { "epoch": 25.17, "learning_rate": 8.650097306855744e-05, "loss": 0.0603, "step": 104810 }, { "epoch": 25.17, "learning_rate": 8.649851976697383e-05, "loss": 0.0495, "step": 104820 }, { "epoch": 25.17, "learning_rate": 8.649606627727655e-05, "loss": 0.0727, "step": 104830 }, { "epoch": 25.17, "learning_rate": 8.649361259947821e-05, "loss": 0.0281, "step": 104840 }, { "epoch": 25.18, "learning_rate": 8.64911587335915e-05, "loss": 0.0592, "step": 104850 }, { "epoch": 25.18, "learning_rate": 8.648870467962908e-05, "loss": 0.0474, "step": 104860 }, { "epoch": 25.18, "learning_rate": 8.648625043760354e-05, "loss": 0.0472, "step": 104870 }, { "epoch": 25.18, "learning_rate": 8.648379600752756e-05, "loss": 0.0267, "step": 104880 }, { "epoch": 25.19, "learning_rate": 8.64813413894138e-05, "loss": 0.0481, "step": 104890 }, { "epoch": 25.19, "learning_rate": 8.64788865832749e-05, "loss": 0.0546, "step": 104900 }, { "epoch": 25.19, "learning_rate": 8.64764315891235e-05, "loss": 0.037, "step": 104910 }, { "epoch": 25.19, "learning_rate": 8.64739764069723e-05, "loss": 0.0476, "step": 104920 }, { "epoch": 25.2, "learning_rate": 8.64715210368339e-05, "loss": 0.0292, "step": 104930 }, { "epoch": 25.2, "learning_rate": 8.646906547872098e-05, "loss": 0.0502, "step": 104940 }, { "epoch": 25.2, "learning_rate": 8.646660973264618e-05, "loss": 0.0536, "step": 104950 }, { "epoch": 25.2, "learning_rate": 8.646415379862217e-05, "loss": 0.0558, "step": 104960 }, { "epoch": 25.2, "learning_rate": 8.646169767666161e-05, "loss": 0.0477, "step": 104970 }, { "epoch": 25.21, "learning_rate": 8.645924136677717e-05, "loss": 0.0373, "step": 104980 }, { "epoch": 25.21, "learning_rate": 8.645678486898148e-05, "loss": 0.0547, "step": 104990 }, { "epoch": 25.21, "learning_rate": 8.645432818328721e-05, "loss": 0.0589, "step": 105000 }, { "epoch": 25.21, "learning_rate": 8.645187130970705e-05, "loss": 0.0403, "step": 105010 }, { "epoch": 25.22, "learning_rate": 8.644941424825362e-05, "loss": 0.0621, "step": 105020 }, { "epoch": 25.22, "learning_rate": 8.644695699893961e-05, "loss": 0.0342, "step": 105030 }, { "epoch": 25.22, "learning_rate": 8.644449956177769e-05, "loss": 0.0716, "step": 105040 }, { "epoch": 25.22, "learning_rate": 8.64420419367805e-05, "loss": 0.0342, "step": 105050 }, { "epoch": 25.23, "learning_rate": 8.643958412396073e-05, "loss": 0.0552, "step": 105060 }, { "epoch": 25.23, "learning_rate": 8.643712612333103e-05, "loss": 0.0308, "step": 105070 }, { "epoch": 25.23, "learning_rate": 8.643466793490409e-05, "loss": 0.0347, "step": 105080 }, { "epoch": 25.23, "learning_rate": 8.643220955869256e-05, "loss": 0.0431, "step": 105090 }, { "epoch": 25.23, "learning_rate": 8.642975099470911e-05, "loss": 0.0559, "step": 105100 }, { "epoch": 25.24, "learning_rate": 8.642729224296644e-05, "loss": 0.0439, "step": 105110 }, { "epoch": 25.24, "learning_rate": 8.642483330347718e-05, "loss": 0.0253, "step": 105120 }, { "epoch": 25.24, "learning_rate": 8.642237417625403e-05, "loss": 0.0233, "step": 105130 }, { "epoch": 25.24, "learning_rate": 8.641991486130967e-05, "loss": 0.0498, "step": 105140 }, { "epoch": 25.25, "learning_rate": 8.641745535865676e-05, "loss": 0.0655, "step": 105150 }, { "epoch": 25.25, "learning_rate": 8.641499566830798e-05, "loss": 0.0665, "step": 105160 }, { "epoch": 25.25, "learning_rate": 8.6412535790276e-05, "loss": 0.0718, "step": 105170 }, { "epoch": 25.25, "learning_rate": 8.64100757245735e-05, "loss": 0.0306, "step": 105180 }, { "epoch": 25.25, "learning_rate": 8.64076154712132e-05, "loss": 0.053, "step": 105190 }, { "epoch": 25.26, "learning_rate": 8.640515503020769e-05, "loss": 0.0356, "step": 105200 }, { "epoch": 25.26, "learning_rate": 8.640269440156975e-05, "loss": 0.0289, "step": 105210 }, { "epoch": 25.26, "learning_rate": 8.640023358531201e-05, "loss": 0.0325, "step": 105220 }, { "epoch": 25.26, "learning_rate": 8.639777258144716e-05, "loss": 0.0545, "step": 105230 }, { "epoch": 25.27, "learning_rate": 8.63953113899879e-05, "loss": 0.0343, "step": 105240 }, { "epoch": 25.27, "learning_rate": 8.639285001094685e-05, "loss": 0.0399, "step": 105250 }, { "epoch": 25.27, "learning_rate": 8.63903884443368e-05, "loss": 0.0382, "step": 105260 }, { "epoch": 25.27, "learning_rate": 8.638792669017037e-05, "loss": 0.0258, "step": 105270 }, { "epoch": 25.28, "learning_rate": 8.638546474846025e-05, "loss": 0.047, "step": 105280 }, { "epoch": 25.28, "learning_rate": 8.638300261921915e-05, "loss": 0.0428, "step": 105290 }, { "epoch": 25.28, "learning_rate": 8.638054030245975e-05, "loss": 0.0195, "step": 105300 }, { "epoch": 25.28, "learning_rate": 8.637807779819473e-05, "loss": 0.0216, "step": 105310 }, { "epoch": 25.28, "learning_rate": 8.637561510643681e-05, "loss": 0.0494, "step": 105320 }, { "epoch": 25.29, "learning_rate": 8.637315222719866e-05, "loss": 0.0457, "step": 105330 }, { "epoch": 25.29, "learning_rate": 8.637068916049298e-05, "loss": 0.0602, "step": 105340 }, { "epoch": 25.29, "learning_rate": 8.636822590633247e-05, "loss": 0.033, "step": 105350 }, { "epoch": 25.29, "learning_rate": 8.63657624647298e-05, "loss": 0.0279, "step": 105360 }, { "epoch": 25.3, "learning_rate": 8.636329883569771e-05, "loss": 0.0402, "step": 105370 }, { "epoch": 25.3, "learning_rate": 8.636083501924885e-05, "loss": 0.028, "step": 105380 }, { "epoch": 25.3, "learning_rate": 8.635837101539595e-05, "loss": 0.0556, "step": 105390 }, { "epoch": 25.3, "learning_rate": 8.635590682415171e-05, "loss": 0.0449, "step": 105400 }, { "epoch": 25.31, "learning_rate": 8.635344244552883e-05, "loss": 0.05, "step": 105410 }, { "epoch": 25.31, "learning_rate": 8.635097787953998e-05, "loss": 0.0452, "step": 105420 }, { "epoch": 25.31, "learning_rate": 8.634851312619791e-05, "loss": 0.0637, "step": 105430 }, { "epoch": 25.31, "learning_rate": 8.634604818551529e-05, "loss": 0.0286, "step": 105440 }, { "epoch": 25.31, "learning_rate": 8.634358305750483e-05, "loss": 0.0554, "step": 105450 }, { "epoch": 25.32, "learning_rate": 8.634111774217924e-05, "loss": 0.0339, "step": 105460 }, { "epoch": 25.32, "learning_rate": 8.633865223955123e-05, "loss": 0.0405, "step": 105470 }, { "epoch": 25.32, "learning_rate": 8.63361865496335e-05, "loss": 0.028, "step": 105480 }, { "epoch": 25.32, "learning_rate": 8.633372067243875e-05, "loss": 0.0411, "step": 105490 }, { "epoch": 25.33, "learning_rate": 8.63312546079797e-05, "loss": 0.0211, "step": 105500 }, { "epoch": 25.33, "learning_rate": 8.632878835626908e-05, "loss": 0.0255, "step": 105510 }, { "epoch": 25.33, "learning_rate": 8.632632191731957e-05, "loss": 0.0383, "step": 105520 }, { "epoch": 25.33, "learning_rate": 8.632385529114389e-05, "loss": 0.0257, "step": 105530 }, { "epoch": 25.33, "learning_rate": 8.632138847775477e-05, "loss": 0.0382, "step": 105540 }, { "epoch": 25.34, "learning_rate": 8.63189214771649e-05, "loss": 0.0248, "step": 105550 }, { "epoch": 25.34, "learning_rate": 8.631645428938701e-05, "loss": 0.037, "step": 105560 }, { "epoch": 25.34, "learning_rate": 8.63139869144338e-05, "loss": 0.0345, "step": 105570 }, { "epoch": 25.34, "learning_rate": 8.631151935231801e-05, "loss": 0.0317, "step": 105580 }, { "epoch": 25.35, "learning_rate": 8.630905160305233e-05, "loss": 0.0445, "step": 105590 }, { "epoch": 25.35, "learning_rate": 8.630658366664951e-05, "loss": 0.0302, "step": 105600 }, { "epoch": 25.35, "learning_rate": 8.630411554312225e-05, "loss": 0.0306, "step": 105610 }, { "epoch": 25.35, "learning_rate": 8.630164723248328e-05, "loss": 0.0405, "step": 105620 }, { "epoch": 25.36, "learning_rate": 8.629917873474531e-05, "loss": 0.0329, "step": 105630 }, { "epoch": 25.36, "learning_rate": 8.629671004992106e-05, "loss": 0.0448, "step": 105640 }, { "epoch": 25.36, "learning_rate": 8.629424117802328e-05, "loss": 0.0385, "step": 105650 }, { "epoch": 25.36, "learning_rate": 8.629177211906468e-05, "loss": 0.0547, "step": 105660 }, { "epoch": 25.36, "learning_rate": 8.628930287305796e-05, "loss": 0.03, "step": 105670 }, { "epoch": 25.37, "learning_rate": 8.628683344001589e-05, "loss": 0.033, "step": 105680 }, { "epoch": 25.37, "learning_rate": 8.628436381995118e-05, "loss": 0.0356, "step": 105690 }, { "epoch": 25.37, "learning_rate": 8.628189401287654e-05, "loss": 0.0445, "step": 105700 }, { "epoch": 25.37, "learning_rate": 8.62794240188047e-05, "loss": 0.0348, "step": 105710 }, { "epoch": 25.38, "learning_rate": 8.627695383774845e-05, "loss": 0.0244, "step": 105720 }, { "epoch": 25.38, "learning_rate": 8.627448346972044e-05, "loss": 0.0425, "step": 105730 }, { "epoch": 25.38, "learning_rate": 8.627201291473345e-05, "loss": 0.0373, "step": 105740 }, { "epoch": 25.38, "learning_rate": 8.626954217280021e-05, "loss": 0.0419, "step": 105750 }, { "epoch": 25.39, "learning_rate": 8.626707124393345e-05, "loss": 0.0395, "step": 105760 }, { "epoch": 25.39, "learning_rate": 8.62646001281459e-05, "loss": 0.0206, "step": 105770 }, { "epoch": 25.39, "learning_rate": 8.626212882545029e-05, "loss": 0.0324, "step": 105780 }, { "epoch": 25.39, "learning_rate": 8.625965733585936e-05, "loss": 0.0454, "step": 105790 }, { "epoch": 25.39, "learning_rate": 8.625718565938585e-05, "loss": 0.0538, "step": 105800 }, { "epoch": 25.4, "learning_rate": 8.625471379604251e-05, "loss": 0.0547, "step": 105810 }, { "epoch": 25.4, "learning_rate": 8.625224174584208e-05, "loss": 0.0464, "step": 105820 }, { "epoch": 25.4, "learning_rate": 8.624976950879728e-05, "loss": 0.0477, "step": 105830 }, { "epoch": 25.4, "learning_rate": 8.624729708492088e-05, "loss": 0.03, "step": 105840 }, { "epoch": 25.41, "learning_rate": 8.62448244742256e-05, "loss": 0.0329, "step": 105850 }, { "epoch": 25.41, "learning_rate": 8.624235167672419e-05, "loss": 0.0352, "step": 105860 }, { "epoch": 25.41, "learning_rate": 8.62398786924294e-05, "loss": 0.029, "step": 105870 }, { "epoch": 25.41, "learning_rate": 8.623740552135396e-05, "loss": 0.0284, "step": 105880 }, { "epoch": 25.41, "learning_rate": 8.623493216351063e-05, "loss": 0.0471, "step": 105890 }, { "epoch": 25.42, "learning_rate": 8.623245861891217e-05, "loss": 0.0347, "step": 105900 }, { "epoch": 25.42, "learning_rate": 8.622998488757131e-05, "loss": 0.0394, "step": 105910 }, { "epoch": 25.42, "learning_rate": 8.622751096950081e-05, "loss": 0.0898, "step": 105920 }, { "epoch": 25.42, "learning_rate": 8.622503686471341e-05, "loss": 0.0412, "step": 105930 }, { "epoch": 25.43, "learning_rate": 8.622256257322188e-05, "loss": 0.0314, "step": 105940 }, { "epoch": 25.43, "learning_rate": 8.622008809503894e-05, "loss": 0.0361, "step": 105950 }, { "epoch": 25.43, "learning_rate": 8.621761343017737e-05, "loss": 0.0306, "step": 105960 }, { "epoch": 25.43, "learning_rate": 8.621513857864991e-05, "loss": 0.0546, "step": 105970 }, { "epoch": 25.44, "learning_rate": 8.621266354046934e-05, "loss": 0.0343, "step": 105980 }, { "epoch": 25.44, "learning_rate": 8.621018831564838e-05, "loss": 0.0311, "step": 105990 }, { "epoch": 25.44, "learning_rate": 8.620771290419982e-05, "loss": 0.0369, "step": 106000 }, { "epoch": 25.44, "learning_rate": 8.620523730613642e-05, "loss": 0.0457, "step": 106010 }, { "epoch": 25.44, "learning_rate": 8.62027615214709e-05, "loss": 0.0357, "step": 106020 }, { "epoch": 25.45, "learning_rate": 8.620028555021604e-05, "loss": 0.045, "step": 106030 }, { "epoch": 25.45, "learning_rate": 8.619780939238462e-05, "loss": 0.0417, "step": 106040 }, { "epoch": 25.45, "learning_rate": 8.619533304798938e-05, "loss": 0.0629, "step": 106050 }, { "epoch": 25.45, "learning_rate": 8.619285651704311e-05, "loss": 0.0301, "step": 106060 }, { "epoch": 25.46, "learning_rate": 8.619037979955853e-05, "loss": 0.0459, "step": 106070 }, { "epoch": 25.46, "learning_rate": 8.618790289554845e-05, "loss": 0.0629, "step": 106080 }, { "epoch": 25.46, "learning_rate": 8.618542580502561e-05, "loss": 0.0442, "step": 106090 }, { "epoch": 25.46, "learning_rate": 8.618294852800277e-05, "loss": 0.0296, "step": 106100 }, { "epoch": 25.47, "learning_rate": 8.618047106449273e-05, "loss": 0.0351, "step": 106110 }, { "epoch": 25.47, "learning_rate": 8.617799341450823e-05, "loss": 0.0496, "step": 106120 }, { "epoch": 25.47, "learning_rate": 8.617551557806205e-05, "loss": 0.0228, "step": 106130 }, { "epoch": 25.47, "learning_rate": 8.617303755516696e-05, "loss": 0.0447, "step": 106140 }, { "epoch": 25.47, "learning_rate": 8.617055934583573e-05, "loss": 0.0382, "step": 106150 }, { "epoch": 25.48, "learning_rate": 8.616808095008114e-05, "loss": 0.0353, "step": 106160 }, { "epoch": 25.48, "learning_rate": 8.616560236791595e-05, "loss": 0.049, "step": 106170 }, { "epoch": 25.48, "learning_rate": 8.616312359935296e-05, "loss": 0.0348, "step": 106180 }, { "epoch": 25.48, "learning_rate": 8.616064464440492e-05, "loss": 0.0302, "step": 106190 }, { "epoch": 25.49, "learning_rate": 8.61581655030846e-05, "loss": 0.0654, "step": 106200 }, { "epoch": 25.49, "learning_rate": 8.615568617540482e-05, "loss": 0.0512, "step": 106210 }, { "epoch": 25.49, "learning_rate": 8.61532066613783e-05, "loss": 0.0353, "step": 106220 }, { "epoch": 25.49, "learning_rate": 8.615072696101788e-05, "loss": 0.0457, "step": 106230 }, { "epoch": 25.49, "learning_rate": 8.61482470743363e-05, "loss": 0.0263, "step": 106240 }, { "epoch": 25.5, "learning_rate": 8.614576700134634e-05, "loss": 0.0364, "step": 106250 }, { "epoch": 25.5, "learning_rate": 8.614328674206082e-05, "loss": 0.035, "step": 106260 }, { "epoch": 25.5, "learning_rate": 8.614080629649249e-05, "loss": 0.032, "step": 106270 }, { "epoch": 25.5, "learning_rate": 8.613832566465412e-05, "loss": 0.0464, "step": 106280 }, { "epoch": 25.51, "learning_rate": 8.613584484655853e-05, "loss": 0.0245, "step": 106290 }, { "epoch": 25.51, "learning_rate": 8.61333638422185e-05, "loss": 0.0333, "step": 106300 }, { "epoch": 25.51, "learning_rate": 8.613088265164682e-05, "loss": 0.033, "step": 106310 }, { "epoch": 25.51, "learning_rate": 8.612840127485624e-05, "loss": 0.0254, "step": 106320 }, { "epoch": 25.52, "learning_rate": 8.61259197118596e-05, "loss": 0.0472, "step": 106330 }, { "epoch": 25.52, "learning_rate": 8.612343796266966e-05, "loss": 0.0277, "step": 106340 }, { "epoch": 25.52, "learning_rate": 8.612095602729923e-05, "loss": 0.0335, "step": 106350 }, { "epoch": 25.52, "learning_rate": 8.611847390576107e-05, "loss": 0.0337, "step": 106360 }, { "epoch": 25.52, "learning_rate": 8.611599159806802e-05, "loss": 0.0289, "step": 106370 }, { "epoch": 25.53, "learning_rate": 8.611350910423283e-05, "loss": 0.0408, "step": 106380 }, { "epoch": 25.53, "learning_rate": 8.611102642426832e-05, "loss": 0.0449, "step": 106390 }, { "epoch": 25.53, "learning_rate": 8.610854355818727e-05, "loss": 0.0469, "step": 106400 }, { "epoch": 25.53, "learning_rate": 8.610606050600249e-05, "loss": 0.0496, "step": 106410 }, { "epoch": 25.54, "learning_rate": 8.610357726772677e-05, "loss": 0.0519, "step": 106420 }, { "epoch": 25.54, "learning_rate": 8.61010938433729e-05, "loss": 0.0644, "step": 106430 }, { "epoch": 25.54, "learning_rate": 8.609861023295372e-05, "loss": 0.0405, "step": 106440 }, { "epoch": 25.54, "learning_rate": 8.609612643648197e-05, "loss": 0.0638, "step": 106450 }, { "epoch": 25.55, "learning_rate": 8.609364245397049e-05, "loss": 0.0747, "step": 106460 }, { "epoch": 25.55, "learning_rate": 8.609115828543208e-05, "loss": 0.0926, "step": 106470 }, { "epoch": 25.55, "learning_rate": 8.608867393087955e-05, "loss": 0.0652, "step": 106480 }, { "epoch": 25.55, "learning_rate": 8.608618939032568e-05, "loss": 0.0539, "step": 106490 }, { "epoch": 25.55, "learning_rate": 8.608370466378328e-05, "loss": 0.0364, "step": 106500 }, { "epoch": 25.56, "learning_rate": 8.608121975126518e-05, "loss": 0.0606, "step": 106510 }, { "epoch": 25.56, "learning_rate": 8.607873465278418e-05, "loss": 0.0391, "step": 106520 }, { "epoch": 25.56, "learning_rate": 8.607624936835305e-05, "loss": 0.0587, "step": 106530 }, { "epoch": 25.56, "learning_rate": 8.607376389798465e-05, "loss": 0.0507, "step": 106540 }, { "epoch": 25.57, "learning_rate": 8.607127824169177e-05, "loss": 0.0505, "step": 106550 }, { "epoch": 25.57, "learning_rate": 8.606879239948722e-05, "loss": 0.0328, "step": 106560 }, { "epoch": 25.57, "learning_rate": 8.60663063713838e-05, "loss": 0.0465, "step": 106570 }, { "epoch": 25.57, "learning_rate": 8.606382015739434e-05, "loss": 0.0676, "step": 106580 }, { "epoch": 25.57, "learning_rate": 8.606133375753166e-05, "loss": 0.0586, "step": 106590 }, { "epoch": 25.58, "learning_rate": 8.605884717180856e-05, "loss": 0.0811, "step": 106600 }, { "epoch": 25.58, "learning_rate": 8.605636040023786e-05, "loss": 0.0561, "step": 106610 }, { "epoch": 25.58, "learning_rate": 8.605387344283237e-05, "loss": 0.0668, "step": 106620 }, { "epoch": 25.58, "learning_rate": 8.605138629960491e-05, "loss": 0.0428, "step": 106630 }, { "epoch": 25.59, "learning_rate": 8.604889897056831e-05, "loss": 0.0461, "step": 106640 }, { "epoch": 25.59, "learning_rate": 8.60464114557354e-05, "loss": 0.0318, "step": 106650 }, { "epoch": 25.59, "learning_rate": 8.604392375511896e-05, "loss": 0.0709, "step": 106660 }, { "epoch": 25.59, "learning_rate": 8.604143586873185e-05, "loss": 0.0474, "step": 106670 }, { "epoch": 25.6, "learning_rate": 8.603894779658688e-05, "loss": 0.058, "step": 106680 }, { "epoch": 25.6, "learning_rate": 8.603645953869685e-05, "loss": 0.0571, "step": 106690 }, { "epoch": 25.6, "learning_rate": 8.603397109507464e-05, "loss": 0.0563, "step": 106700 }, { "epoch": 25.6, "learning_rate": 8.603148246573303e-05, "loss": 0.0387, "step": 106710 }, { "epoch": 25.6, "learning_rate": 8.602899365068484e-05, "loss": 0.0577, "step": 106720 }, { "epoch": 25.61, "learning_rate": 8.602650464994293e-05, "loss": 0.057, "step": 106730 }, { "epoch": 25.61, "learning_rate": 8.602401546352013e-05, "loss": 0.067, "step": 106740 }, { "epoch": 25.61, "learning_rate": 8.602152609142922e-05, "loss": 0.0582, "step": 106750 }, { "epoch": 25.61, "learning_rate": 8.601903653368308e-05, "loss": 0.0556, "step": 106760 }, { "epoch": 25.62, "learning_rate": 8.601654679029453e-05, "loss": 0.038, "step": 106770 }, { "epoch": 25.62, "learning_rate": 8.60140568612764e-05, "loss": 0.0728, "step": 106780 }, { "epoch": 25.62, "learning_rate": 8.60115667466415e-05, "loss": 0.0376, "step": 106790 }, { "epoch": 25.62, "learning_rate": 8.60090764464027e-05, "loss": 0.085, "step": 106800 }, { "epoch": 25.62, "learning_rate": 8.60065859605728e-05, "loss": 0.0427, "step": 106810 }, { "epoch": 25.63, "learning_rate": 8.600409528916466e-05, "loss": 0.0425, "step": 106820 }, { "epoch": 25.63, "learning_rate": 8.600160443219113e-05, "loss": 0.0552, "step": 106830 }, { "epoch": 25.63, "learning_rate": 8.599911338966502e-05, "loss": 0.069, "step": 106840 }, { "epoch": 25.63, "learning_rate": 8.599662216159918e-05, "loss": 0.0506, "step": 106850 }, { "epoch": 25.64, "learning_rate": 8.599413074800645e-05, "loss": 0.0535, "step": 106860 }, { "epoch": 25.64, "learning_rate": 8.599163914889967e-05, "loss": 0.0491, "step": 106870 }, { "epoch": 25.64, "learning_rate": 8.598914736429166e-05, "loss": 0.0391, "step": 106880 }, { "epoch": 25.64, "learning_rate": 8.598665539419531e-05, "loss": 0.0911, "step": 106890 }, { "epoch": 25.65, "learning_rate": 8.598416323862343e-05, "loss": 0.0731, "step": 106900 }, { "epoch": 25.65, "learning_rate": 8.598167089758887e-05, "loss": 0.0674, "step": 106910 }, { "epoch": 25.65, "learning_rate": 8.597917837110448e-05, "loss": 0.056, "step": 106920 }, { "epoch": 25.65, "learning_rate": 8.597668565918311e-05, "loss": 0.0425, "step": 106930 }, { "epoch": 25.65, "learning_rate": 8.597419276183758e-05, "loss": 0.0765, "step": 106940 }, { "epoch": 25.66, "learning_rate": 8.597169967908078e-05, "loss": 0.0357, "step": 106950 }, { "epoch": 25.66, "learning_rate": 8.596920641092553e-05, "loss": 0.0436, "step": 106960 }, { "epoch": 25.66, "learning_rate": 8.596671295738468e-05, "loss": 0.0425, "step": 106970 }, { "epoch": 25.66, "learning_rate": 8.596421931847112e-05, "loss": 0.0514, "step": 106980 }, { "epoch": 25.67, "learning_rate": 8.596172549419765e-05, "loss": 0.0474, "step": 106990 }, { "epoch": 25.67, "learning_rate": 8.595923148457715e-05, "loss": 0.0559, "step": 107000 }, { "epoch": 25.67, "learning_rate": 8.595673728962248e-05, "loss": 0.0347, "step": 107010 }, { "epoch": 25.67, "learning_rate": 8.595424290934647e-05, "loss": 0.0755, "step": 107020 }, { "epoch": 25.68, "learning_rate": 8.595174834376199e-05, "loss": 0.0392, "step": 107030 }, { "epoch": 25.68, "learning_rate": 8.594925359288191e-05, "loss": 0.0248, "step": 107040 }, { "epoch": 25.68, "learning_rate": 8.594675865671908e-05, "loss": 0.0362, "step": 107050 }, { "epoch": 25.68, "learning_rate": 8.594426353528636e-05, "loss": 0.0383, "step": 107060 }, { "epoch": 25.68, "learning_rate": 8.594176822859659e-05, "loss": 0.0497, "step": 107070 }, { "epoch": 25.69, "learning_rate": 8.593927273666265e-05, "loss": 0.0442, "step": 107080 }, { "epoch": 25.69, "learning_rate": 8.593677705949738e-05, "loss": 0.0605, "step": 107090 }, { "epoch": 25.69, "learning_rate": 8.593428119711368e-05, "loss": 0.0562, "step": 107100 }, { "epoch": 25.69, "learning_rate": 8.59317851495244e-05, "loss": 0.0367, "step": 107110 }, { "epoch": 25.7, "learning_rate": 8.592928891674239e-05, "loss": 0.0464, "step": 107120 }, { "epoch": 25.7, "learning_rate": 8.592679249878054e-05, "loss": 0.0407, "step": 107130 }, { "epoch": 25.7, "learning_rate": 8.592429589565169e-05, "loss": 0.0407, "step": 107140 }, { "epoch": 25.7, "learning_rate": 8.59217991073687e-05, "loss": 0.0347, "step": 107150 }, { "epoch": 25.7, "learning_rate": 8.591930213394449e-05, "loss": 0.0375, "step": 107160 }, { "epoch": 25.71, "learning_rate": 8.591680497539187e-05, "loss": 0.0568, "step": 107170 }, { "epoch": 25.71, "learning_rate": 8.591430763172374e-05, "loss": 0.0412, "step": 107180 }, { "epoch": 25.71, "learning_rate": 8.591181010295299e-05, "loss": 0.0513, "step": 107190 }, { "epoch": 25.71, "learning_rate": 8.590931238909245e-05, "loss": 0.0509, "step": 107200 }, { "epoch": 25.72, "learning_rate": 8.590681449015504e-05, "loss": 0.0382, "step": 107210 }, { "epoch": 25.72, "learning_rate": 8.590431640615358e-05, "loss": 0.043, "step": 107220 }, { "epoch": 25.72, "learning_rate": 8.590181813710098e-05, "loss": 0.0527, "step": 107230 }, { "epoch": 25.72, "learning_rate": 8.589931968301011e-05, "loss": 0.062, "step": 107240 }, { "epoch": 25.73, "learning_rate": 8.589682104389385e-05, "loss": 0.0355, "step": 107250 }, { "epoch": 25.73, "learning_rate": 8.589432221976506e-05, "loss": 0.0479, "step": 107260 }, { "epoch": 25.73, "learning_rate": 8.589182321063664e-05, "loss": 0.062, "step": 107270 }, { "epoch": 25.73, "learning_rate": 8.588932401652148e-05, "loss": 0.0315, "step": 107280 }, { "epoch": 25.73, "learning_rate": 8.588682463743243e-05, "loss": 0.0468, "step": 107290 }, { "epoch": 25.74, "learning_rate": 8.588432507338239e-05, "loss": 0.0221, "step": 107300 }, { "epoch": 25.74, "learning_rate": 8.588182532438423e-05, "loss": 0.0604, "step": 107310 }, { "epoch": 25.74, "learning_rate": 8.587932539045085e-05, "loss": 0.0395, "step": 107320 }, { "epoch": 25.74, "learning_rate": 8.587682527159512e-05, "loss": 0.0365, "step": 107330 }, { "epoch": 25.75, "learning_rate": 8.587432496782995e-05, "loss": 0.0503, "step": 107340 }, { "epoch": 25.75, "learning_rate": 8.58718244791682e-05, "loss": 0.0335, "step": 107350 }, { "epoch": 25.75, "learning_rate": 8.586932380562276e-05, "loss": 0.0306, "step": 107360 }, { "epoch": 25.75, "learning_rate": 8.586682294720652e-05, "loss": 0.0543, "step": 107370 }, { "epoch": 25.76, "learning_rate": 8.586432190393239e-05, "loss": 0.0182, "step": 107380 }, { "epoch": 25.76, "learning_rate": 8.586182067581325e-05, "loss": 0.0486, "step": 107390 }, { "epoch": 25.76, "learning_rate": 8.585931926286198e-05, "loss": 0.0678, "step": 107400 }, { "epoch": 25.76, "learning_rate": 8.585681766509146e-05, "loss": 0.0243, "step": 107410 }, { "epoch": 25.76, "learning_rate": 8.585431588251463e-05, "loss": 0.0649, "step": 107420 }, { "epoch": 25.77, "learning_rate": 8.585181391514434e-05, "loss": 0.0335, "step": 107430 }, { "epoch": 25.77, "learning_rate": 8.584931176299348e-05, "loss": 0.0359, "step": 107440 }, { "epoch": 25.77, "learning_rate": 8.584680942607501e-05, "loss": 0.052, "step": 107450 }, { "epoch": 25.77, "learning_rate": 8.584430690440177e-05, "loss": 0.0362, "step": 107460 }, { "epoch": 25.78, "learning_rate": 8.584180419798667e-05, "loss": 0.0387, "step": 107470 }, { "epoch": 25.78, "learning_rate": 8.58393013068426e-05, "loss": 0.0512, "step": 107480 }, { "epoch": 25.78, "learning_rate": 8.583679823098249e-05, "loss": 0.049, "step": 107490 }, { "epoch": 25.78, "learning_rate": 8.583429497041922e-05, "loss": 0.0647, "step": 107500 }, { "epoch": 25.78, "learning_rate": 8.583179152516567e-05, "loss": 0.0543, "step": 107510 }, { "epoch": 25.79, "learning_rate": 8.582928789523479e-05, "loss": 0.0381, "step": 107520 }, { "epoch": 25.79, "learning_rate": 8.582678408063946e-05, "loss": 0.0356, "step": 107530 }, { "epoch": 25.79, "learning_rate": 8.582428008139258e-05, "loss": 0.0363, "step": 107540 }, { "epoch": 25.79, "learning_rate": 8.582177589750707e-05, "loss": 0.0347, "step": 107550 }, { "epoch": 25.8, "learning_rate": 8.581927152899582e-05, "loss": 0.0668, "step": 107560 }, { "epoch": 25.8, "learning_rate": 8.581676697587174e-05, "loss": 0.0366, "step": 107570 }, { "epoch": 25.8, "learning_rate": 8.581426223814774e-05, "loss": 0.0543, "step": 107580 }, { "epoch": 25.8, "learning_rate": 8.581175731583675e-05, "loss": 0.0395, "step": 107590 }, { "epoch": 25.81, "learning_rate": 8.580925220895166e-05, "loss": 0.037, "step": 107600 }, { "epoch": 25.81, "learning_rate": 8.580674691750538e-05, "loss": 0.0583, "step": 107610 }, { "epoch": 25.81, "learning_rate": 8.580424144151082e-05, "loss": 0.0539, "step": 107620 }, { "epoch": 25.81, "learning_rate": 8.580173578098092e-05, "loss": 0.0386, "step": 107630 }, { "epoch": 25.81, "learning_rate": 8.579922993592854e-05, "loss": 0.0552, "step": 107640 }, { "epoch": 25.82, "learning_rate": 8.579672390636666e-05, "loss": 0.0378, "step": 107650 }, { "epoch": 25.82, "learning_rate": 8.579421769230816e-05, "loss": 0.0311, "step": 107660 }, { "epoch": 25.82, "learning_rate": 8.579171129376596e-05, "loss": 0.0414, "step": 107670 }, { "epoch": 25.82, "learning_rate": 8.578920471075298e-05, "loss": 0.0423, "step": 107680 }, { "epoch": 25.83, "learning_rate": 8.578669794328214e-05, "loss": 0.0327, "step": 107690 }, { "epoch": 25.83, "learning_rate": 8.578419099136636e-05, "loss": 0.0285, "step": 107700 }, { "epoch": 25.83, "learning_rate": 8.578168385501856e-05, "loss": 0.0354, "step": 107710 }, { "epoch": 25.83, "learning_rate": 8.577917653425167e-05, "loss": 0.038, "step": 107720 }, { "epoch": 25.84, "learning_rate": 8.57766690290786e-05, "loss": 0.0447, "step": 107730 }, { "epoch": 25.84, "learning_rate": 8.577416133951229e-05, "loss": 0.0527, "step": 107740 }, { "epoch": 25.84, "learning_rate": 8.577165346556564e-05, "loss": 0.0328, "step": 107750 }, { "epoch": 25.84, "learning_rate": 8.576914540725159e-05, "loss": 0.0527, "step": 107760 }, { "epoch": 25.84, "learning_rate": 8.576663716458306e-05, "loss": 0.0522, "step": 107770 }, { "epoch": 25.85, "learning_rate": 8.576412873757298e-05, "loss": 0.0272, "step": 107780 }, { "epoch": 25.85, "learning_rate": 8.576162012623429e-05, "loss": 0.0447, "step": 107790 }, { "epoch": 25.85, "learning_rate": 8.575911133057992e-05, "loss": 0.0496, "step": 107800 }, { "epoch": 25.85, "learning_rate": 8.575660235062277e-05, "loss": 0.0374, "step": 107810 }, { "epoch": 25.86, "learning_rate": 8.575409318637582e-05, "loss": 0.0572, "step": 107820 }, { "epoch": 25.86, "learning_rate": 8.575158383785195e-05, "loss": 0.0511, "step": 107830 }, { "epoch": 25.86, "learning_rate": 8.574907430506413e-05, "loss": 0.0322, "step": 107840 }, { "epoch": 25.86, "learning_rate": 8.574656458802529e-05, "loss": 0.0345, "step": 107850 }, { "epoch": 25.86, "learning_rate": 8.574405468674833e-05, "loss": 0.037, "step": 107860 }, { "epoch": 25.87, "learning_rate": 8.574154460124624e-05, "loss": 0.037, "step": 107870 }, { "epoch": 25.87, "learning_rate": 8.573903433153192e-05, "loss": 0.0614, "step": 107880 }, { "epoch": 25.87, "learning_rate": 8.573652387761832e-05, "loss": 0.0525, "step": 107890 }, { "epoch": 25.87, "learning_rate": 8.573401323951837e-05, "loss": 0.0336, "step": 107900 }, { "epoch": 25.88, "learning_rate": 8.573150241724504e-05, "loss": 0.0491, "step": 107910 }, { "epoch": 25.88, "learning_rate": 8.572899141081124e-05, "loss": 0.0568, "step": 107920 }, { "epoch": 25.88, "learning_rate": 8.572648022022989e-05, "loss": 0.044, "step": 107930 }, { "epoch": 25.88, "learning_rate": 8.5723968845514e-05, "loss": 0.0334, "step": 107940 }, { "epoch": 25.89, "learning_rate": 8.572145728667645e-05, "loss": 0.0547, "step": 107950 }, { "epoch": 25.89, "learning_rate": 8.571894554373021e-05, "loss": 0.0408, "step": 107960 }, { "epoch": 25.89, "learning_rate": 8.571643361668824e-05, "loss": 0.062, "step": 107970 }, { "epoch": 25.89, "learning_rate": 8.571392150556348e-05, "loss": 0.0398, "step": 107980 }, { "epoch": 25.89, "learning_rate": 8.571140921036886e-05, "loss": 0.0287, "step": 107990 }, { "epoch": 25.9, "learning_rate": 8.570889673111733e-05, "loss": 0.0492, "step": 108000 }, { "epoch": 25.9, "learning_rate": 8.570638406782185e-05, "loss": 0.024, "step": 108010 }, { "epoch": 25.9, "learning_rate": 8.570387122049538e-05, "loss": 0.0376, "step": 108020 }, { "epoch": 25.9, "learning_rate": 8.570135818915086e-05, "loss": 0.0361, "step": 108030 }, { "epoch": 25.91, "learning_rate": 8.569884497380123e-05, "loss": 0.029, "step": 108040 }, { "epoch": 25.91, "learning_rate": 8.569633157445946e-05, "loss": 0.0528, "step": 108050 }, { "epoch": 25.91, "learning_rate": 8.56938179911385e-05, "loss": 0.0512, "step": 108060 }, { "epoch": 25.91, "learning_rate": 8.56913042238513e-05, "loss": 0.0485, "step": 108070 }, { "epoch": 25.92, "learning_rate": 8.56887902726108e-05, "loss": 0.0325, "step": 108080 }, { "epoch": 25.92, "learning_rate": 8.568627613743001e-05, "loss": 0.0374, "step": 108090 }, { "epoch": 25.92, "learning_rate": 8.568376181832185e-05, "loss": 0.0347, "step": 108100 }, { "epoch": 25.92, "learning_rate": 8.568124731529927e-05, "loss": 0.0263, "step": 108110 }, { "epoch": 25.92, "learning_rate": 8.567873262837525e-05, "loss": 0.0441, "step": 108120 }, { "epoch": 25.93, "learning_rate": 8.567621775756274e-05, "loss": 0.0314, "step": 108130 }, { "epoch": 25.93, "learning_rate": 8.567370270287472e-05, "loss": 0.0431, "step": 108140 }, { "epoch": 25.93, "learning_rate": 8.567118746432411e-05, "loss": 0.0486, "step": 108150 }, { "epoch": 25.93, "learning_rate": 8.566867204192392e-05, "loss": 0.0561, "step": 108160 }, { "epoch": 25.94, "learning_rate": 8.566615643568709e-05, "loss": 0.0327, "step": 108170 }, { "epoch": 25.94, "learning_rate": 8.566364064562659e-05, "loss": 0.0511, "step": 108180 }, { "epoch": 25.94, "learning_rate": 8.56611246717554e-05, "loss": 0.0275, "step": 108190 }, { "epoch": 25.94, "learning_rate": 8.565860851408646e-05, "loss": 0.0624, "step": 108200 }, { "epoch": 25.94, "learning_rate": 8.565609217263277e-05, "loss": 0.0304, "step": 108210 }, { "epoch": 25.95, "learning_rate": 8.565357564740728e-05, "loss": 0.0222, "step": 108220 }, { "epoch": 25.95, "learning_rate": 8.565105893842296e-05, "loss": 0.0285, "step": 108230 }, { "epoch": 26.0, "learning_rate": 8.564854204569277e-05, "loss": 0.0251, "step": 108240 }, { "epoch": 26.0, "learning_rate": 8.564602496922971e-05, "loss": 0.0338, "step": 108250 }, { "epoch": 26.01, "learning_rate": 8.564350770904674e-05, "loss": 0.0477, "step": 108260 }, { "epoch": 26.01, "learning_rate": 8.564099026515684e-05, "loss": 0.0296, "step": 108270 }, { "epoch": 26.01, "learning_rate": 8.563847263757297e-05, "loss": 0.0306, "step": 108280 }, { "epoch": 26.01, "learning_rate": 8.563595482630811e-05, "loss": 0.035, "step": 108290 }, { "epoch": 26.01, "learning_rate": 8.563343683137523e-05, "loss": 0.0477, "step": 108300 }, { "epoch": 26.02, "learning_rate": 8.563091865278734e-05, "loss": 0.0516, "step": 108310 }, { "epoch": 26.02, "learning_rate": 8.562840029055739e-05, "loss": 0.0415, "step": 108320 }, { "epoch": 26.02, "learning_rate": 8.562588174469837e-05, "loss": 0.0468, "step": 108330 }, { "epoch": 26.02, "learning_rate": 8.562336301522326e-05, "loss": 0.0383, "step": 108340 }, { "epoch": 26.03, "learning_rate": 8.562084410214503e-05, "loss": 0.0516, "step": 108350 }, { "epoch": 26.03, "learning_rate": 8.561832500547668e-05, "loss": 0.0346, "step": 108360 }, { "epoch": 26.03, "learning_rate": 8.561580572523118e-05, "loss": 0.0718, "step": 108370 }, { "epoch": 26.03, "learning_rate": 8.561328626142152e-05, "loss": 0.0501, "step": 108380 }, { "epoch": 26.03, "learning_rate": 8.561076661406069e-05, "loss": 0.0505, "step": 108390 }, { "epoch": 26.04, "learning_rate": 8.560824678316167e-05, "loss": 0.0531, "step": 108400 }, { "epoch": 26.04, "learning_rate": 8.560572676873744e-05, "loss": 0.0389, "step": 108410 }, { "epoch": 26.04, "learning_rate": 8.5603206570801e-05, "loss": 0.0472, "step": 108420 }, { "epoch": 26.04, "learning_rate": 8.560068618936535e-05, "loss": 0.0392, "step": 108430 }, { "epoch": 26.05, "learning_rate": 8.559816562444344e-05, "loss": 0.0511, "step": 108440 }, { "epoch": 26.05, "learning_rate": 8.559564487604831e-05, "loss": 0.0297, "step": 108450 }, { "epoch": 26.05, "learning_rate": 8.559312394419293e-05, "loss": 0.046, "step": 108460 }, { "epoch": 26.05, "learning_rate": 8.559060282889027e-05, "loss": 0.0552, "step": 108470 }, { "epoch": 26.06, "learning_rate": 8.558808153015335e-05, "loss": 0.0515, "step": 108480 }, { "epoch": 26.06, "learning_rate": 8.558556004799518e-05, "loss": 0.0289, "step": 108490 }, { "epoch": 26.06, "learning_rate": 8.558303838242872e-05, "loss": 0.0533, "step": 108500 }, { "epoch": 26.06, "learning_rate": 8.558051653346698e-05, "loss": 0.0302, "step": 108510 }, { "epoch": 26.06, "learning_rate": 8.557799450112296e-05, "loss": 0.0402, "step": 108520 }, { "epoch": 26.07, "learning_rate": 8.557547228540968e-05, "loss": 0.0514, "step": 108530 }, { "epoch": 26.07, "learning_rate": 8.557294988634009e-05, "loss": 0.0435, "step": 108540 }, { "epoch": 26.07, "learning_rate": 8.557042730392724e-05, "loss": 0.0236, "step": 108550 }, { "epoch": 26.07, "learning_rate": 8.55679045381841e-05, "loss": 0.0326, "step": 108560 }, { "epoch": 26.08, "learning_rate": 8.556538158912369e-05, "loss": 0.0303, "step": 108570 }, { "epoch": 26.08, "learning_rate": 8.5562858456759e-05, "loss": 0.058, "step": 108580 }, { "epoch": 26.08, "learning_rate": 8.556033514110305e-05, "loss": 0.0611, "step": 108590 }, { "epoch": 26.08, "learning_rate": 8.555781164216883e-05, "loss": 0.0265, "step": 108600 }, { "epoch": 26.09, "learning_rate": 8.555528795996935e-05, "loss": 0.0393, "step": 108610 }, { "epoch": 26.09, "learning_rate": 8.55527640945176e-05, "loss": 0.0297, "step": 108620 }, { "epoch": 26.09, "learning_rate": 8.555024004582663e-05, "loss": 0.0314, "step": 108630 }, { "epoch": 26.09, "learning_rate": 8.554771581390942e-05, "loss": 0.043, "step": 108640 }, { "epoch": 26.09, "learning_rate": 8.5545191398779e-05, "loss": 0.0307, "step": 108650 }, { "epoch": 26.1, "learning_rate": 8.554266680044834e-05, "loss": 0.0418, "step": 108660 }, { "epoch": 26.1, "learning_rate": 8.55401420189305e-05, "loss": 0.0327, "step": 108670 }, { "epoch": 26.1, "learning_rate": 8.553761705423845e-05, "loss": 0.0269, "step": 108680 }, { "epoch": 26.1, "learning_rate": 8.553509190638524e-05, "loss": 0.0234, "step": 108690 }, { "epoch": 26.11, "learning_rate": 8.553256657538387e-05, "loss": 0.044, "step": 108700 }, { "epoch": 26.11, "learning_rate": 8.553004106124734e-05, "loss": 0.0368, "step": 108710 }, { "epoch": 26.11, "learning_rate": 8.552751536398869e-05, "loss": 0.0314, "step": 108720 }, { "epoch": 26.11, "learning_rate": 8.552498948362094e-05, "loss": 0.0425, "step": 108730 }, { "epoch": 26.11, "learning_rate": 8.552246342015708e-05, "loss": 0.0526, "step": 108740 }, { "epoch": 26.12, "learning_rate": 8.551993717361015e-05, "loss": 0.0369, "step": 108750 }, { "epoch": 26.12, "learning_rate": 8.551741074399318e-05, "loss": 0.034, "step": 108760 }, { "epoch": 26.12, "learning_rate": 8.551488413131916e-05, "loss": 0.0483, "step": 108770 }, { "epoch": 26.12, "learning_rate": 8.551235733560115e-05, "loss": 0.0502, "step": 108780 }, { "epoch": 26.13, "learning_rate": 8.550983035685214e-05, "loss": 0.0325, "step": 108790 }, { "epoch": 26.13, "learning_rate": 8.550730319508516e-05, "loss": 0.0528, "step": 108800 }, { "epoch": 26.13, "learning_rate": 8.550477585031326e-05, "loss": 0.066, "step": 108810 }, { "epoch": 26.13, "learning_rate": 8.550224832254945e-05, "loss": 0.0421, "step": 108820 }, { "epoch": 26.14, "learning_rate": 8.549972061180673e-05, "loss": 0.0271, "step": 108830 }, { "epoch": 26.14, "learning_rate": 8.549719271809818e-05, "loss": 0.0263, "step": 108840 }, { "epoch": 26.14, "learning_rate": 8.549466464143678e-05, "loss": 0.0305, "step": 108850 }, { "epoch": 26.14, "learning_rate": 8.54921363818356e-05, "loss": 0.0309, "step": 108860 }, { "epoch": 26.14, "learning_rate": 8.548960793930765e-05, "loss": 0.027, "step": 108870 }, { "epoch": 26.15, "learning_rate": 8.548707931386597e-05, "loss": 0.045, "step": 108880 }, { "epoch": 26.15, "learning_rate": 8.548455050552357e-05, "loss": 0.0455, "step": 108890 }, { "epoch": 26.15, "learning_rate": 8.548202151429351e-05, "loss": 0.0238, "step": 108900 }, { "epoch": 26.15, "learning_rate": 8.547949234018881e-05, "loss": 0.0284, "step": 108910 }, { "epoch": 26.16, "learning_rate": 8.547696298322251e-05, "loss": 0.045, "step": 108920 }, { "epoch": 26.16, "learning_rate": 8.547443344340765e-05, "loss": 0.0334, "step": 108930 }, { "epoch": 26.16, "learning_rate": 8.547190372075727e-05, "loss": 0.0613, "step": 108940 }, { "epoch": 26.16, "learning_rate": 8.546937381528438e-05, "loss": 0.0248, "step": 108950 }, { "epoch": 26.16, "learning_rate": 8.546684372700205e-05, "loss": 0.0195, "step": 108960 }, { "epoch": 26.17, "learning_rate": 8.546431345592332e-05, "loss": 0.0563, "step": 108970 }, { "epoch": 26.17, "learning_rate": 8.546178300206122e-05, "loss": 0.0489, "step": 108980 }, { "epoch": 26.17, "learning_rate": 8.545925236542879e-05, "loss": 0.0362, "step": 108990 }, { "epoch": 26.17, "learning_rate": 8.545672154603908e-05, "loss": 0.0494, "step": 109000 }, { "epoch": 26.18, "learning_rate": 8.545419054390512e-05, "loss": 0.0332, "step": 109010 }, { "epoch": 26.18, "learning_rate": 8.545165935903997e-05, "loss": 0.0455, "step": 109020 }, { "epoch": 26.18, "learning_rate": 8.544912799145668e-05, "loss": 0.0325, "step": 109030 }, { "epoch": 26.18, "learning_rate": 8.544659644116829e-05, "loss": 0.0401, "step": 109040 }, { "epoch": 26.19, "learning_rate": 8.544406470818784e-05, "loss": 0.0416, "step": 109050 }, { "epoch": 26.19, "learning_rate": 8.544153279252838e-05, "loss": 0.0358, "step": 109060 }, { "epoch": 26.19, "learning_rate": 8.543900069420296e-05, "loss": 0.0386, "step": 109070 }, { "epoch": 26.19, "learning_rate": 8.543646841322464e-05, "loss": 0.0366, "step": 109080 }, { "epoch": 26.19, "learning_rate": 8.543393594960647e-05, "loss": 0.0253, "step": 109090 }, { "epoch": 26.2, "learning_rate": 8.543140330336151e-05, "loss": 0.0319, "step": 109100 }, { "epoch": 26.2, "learning_rate": 8.542887047450278e-05, "loss": 0.0411, "step": 109110 }, { "epoch": 26.2, "learning_rate": 8.542633746304335e-05, "loss": 0.0264, "step": 109120 }, { "epoch": 26.2, "learning_rate": 8.54238042689963e-05, "loss": 0.0477, "step": 109130 }, { "epoch": 26.21, "learning_rate": 8.542127089237466e-05, "loss": 0.0463, "step": 109140 }, { "epoch": 26.21, "learning_rate": 8.541873733319149e-05, "loss": 0.033, "step": 109150 }, { "epoch": 26.21, "learning_rate": 8.541620359145985e-05, "loss": 0.0289, "step": 109160 }, { "epoch": 26.21, "learning_rate": 8.541366966719281e-05, "loss": 0.0347, "step": 109170 }, { "epoch": 26.22, "learning_rate": 8.541113556040341e-05, "loss": 0.0535, "step": 109180 }, { "epoch": 26.22, "learning_rate": 8.540860127110473e-05, "loss": 0.0429, "step": 109190 }, { "epoch": 26.22, "learning_rate": 8.540606679930982e-05, "loss": 0.0333, "step": 109200 }, { "epoch": 26.22, "learning_rate": 8.540353214503174e-05, "loss": 0.0604, "step": 109210 }, { "epoch": 26.22, "learning_rate": 8.540099730828357e-05, "loss": 0.0426, "step": 109220 }, { "epoch": 26.23, "learning_rate": 8.539846228907835e-05, "loss": 0.0302, "step": 109230 }, { "epoch": 26.23, "learning_rate": 8.539592708742918e-05, "loss": 0.0418, "step": 109240 }, { "epoch": 26.23, "learning_rate": 8.53933917033491e-05, "loss": 0.033, "step": 109250 }, { "epoch": 26.23, "learning_rate": 8.539085613685117e-05, "loss": 0.0381, "step": 109260 }, { "epoch": 26.24, "learning_rate": 8.538832038794849e-05, "loss": 0.0451, "step": 109270 }, { "epoch": 26.24, "learning_rate": 8.538578445665409e-05, "loss": 0.0411, "step": 109280 }, { "epoch": 26.24, "learning_rate": 8.538324834298107e-05, "loss": 0.0432, "step": 109290 }, { "epoch": 26.24, "learning_rate": 8.538071204694248e-05, "loss": 0.0475, "step": 109300 }, { "epoch": 26.24, "learning_rate": 8.537817556855143e-05, "loss": 0.0557, "step": 109310 }, { "epoch": 26.25, "learning_rate": 8.537563890782096e-05, "loss": 0.0414, "step": 109320 }, { "epoch": 26.25, "learning_rate": 8.537310206476415e-05, "loss": 0.025, "step": 109330 }, { "epoch": 26.25, "learning_rate": 8.537056503939406e-05, "loss": 0.0371, "step": 109340 }, { "epoch": 26.25, "learning_rate": 8.536802783172381e-05, "loss": 0.0178, "step": 109350 }, { "epoch": 26.26, "learning_rate": 8.536549044176643e-05, "loss": 0.0363, "step": 109360 }, { "epoch": 26.26, "learning_rate": 8.536295286953501e-05, "loss": 0.0482, "step": 109370 }, { "epoch": 26.26, "learning_rate": 8.536041511504265e-05, "loss": 0.031, "step": 109380 }, { "epoch": 26.26, "learning_rate": 8.535787717830241e-05, "loss": 0.0359, "step": 109390 }, { "epoch": 26.27, "learning_rate": 8.535533905932738e-05, "loss": 0.0417, "step": 109400 }, { "epoch": 26.27, "learning_rate": 8.535280075813064e-05, "loss": 0.0387, "step": 109410 }, { "epoch": 26.27, "learning_rate": 8.535026227472525e-05, "loss": 0.0311, "step": 109420 }, { "epoch": 26.27, "learning_rate": 8.534772360912433e-05, "loss": 0.0452, "step": 109430 }, { "epoch": 26.27, "learning_rate": 8.534518476134094e-05, "loss": 0.0389, "step": 109440 }, { "epoch": 26.28, "learning_rate": 8.534264573138818e-05, "loss": 0.0493, "step": 109450 }, { "epoch": 26.28, "learning_rate": 8.534010651927913e-05, "loss": 0.0363, "step": 109460 }, { "epoch": 26.28, "learning_rate": 8.533756712502686e-05, "loss": 0.0294, "step": 109470 }, { "epoch": 26.28, "learning_rate": 8.533502754864449e-05, "loss": 0.0401, "step": 109480 }, { "epoch": 26.29, "learning_rate": 8.533248779014508e-05, "loss": 0.0486, "step": 109490 }, { "epoch": 26.29, "learning_rate": 8.532994784954173e-05, "loss": 0.032, "step": 109500 }, { "epoch": 26.29, "learning_rate": 8.532740772684756e-05, "loss": 0.0397, "step": 109510 }, { "epoch": 26.29, "learning_rate": 8.532486742207561e-05, "loss": 0.0261, "step": 109520 }, { "epoch": 26.3, "learning_rate": 8.532232693523901e-05, "loss": 0.0264, "step": 109530 }, { "epoch": 26.3, "learning_rate": 8.531978626635082e-05, "loss": 0.018, "step": 109540 }, { "epoch": 26.3, "learning_rate": 8.531724541542419e-05, "loss": 0.0395, "step": 109550 }, { "epoch": 26.3, "learning_rate": 8.531470438247215e-05, "loss": 0.0324, "step": 109560 }, { "epoch": 26.3, "learning_rate": 8.531216316750785e-05, "loss": 0.0375, "step": 109570 }, { "epoch": 26.31, "learning_rate": 8.530962177054436e-05, "loss": 0.0415, "step": 109580 }, { "epoch": 26.31, "learning_rate": 8.53070801915948e-05, "loss": 0.0317, "step": 109590 }, { "epoch": 26.31, "learning_rate": 8.530453843067222e-05, "loss": 0.0492, "step": 109600 }, { "epoch": 26.31, "learning_rate": 8.530199648778977e-05, "loss": 0.0162, "step": 109610 }, { "epoch": 26.32, "learning_rate": 8.529945436296054e-05, "loss": 0.0212, "step": 109620 }, { "epoch": 26.32, "learning_rate": 8.52969120561976e-05, "loss": 0.0298, "step": 109630 }, { "epoch": 26.32, "learning_rate": 8.529436956751412e-05, "loss": 0.0461, "step": 109640 }, { "epoch": 26.32, "learning_rate": 8.529182689692315e-05, "loss": 0.0415, "step": 109650 }, { "epoch": 26.32, "learning_rate": 8.528928404443781e-05, "loss": 0.0465, "step": 109660 }, { "epoch": 26.33, "learning_rate": 8.52867410100712e-05, "loss": 0.024, "step": 109670 }, { "epoch": 26.33, "learning_rate": 8.528419779383642e-05, "loss": 0.0315, "step": 109680 }, { "epoch": 26.33, "learning_rate": 8.528165439574661e-05, "loss": 0.046, "step": 109690 }, { "epoch": 26.33, "learning_rate": 8.527911081581485e-05, "loss": 0.035, "step": 109700 }, { "epoch": 26.34, "learning_rate": 8.527656705405427e-05, "loss": 0.0391, "step": 109710 }, { "epoch": 26.34, "learning_rate": 8.527402311047794e-05, "loss": 0.0468, "step": 109720 }, { "epoch": 26.34, "learning_rate": 8.527147898509902e-05, "loss": 0.0343, "step": 109730 }, { "epoch": 26.34, "learning_rate": 8.526893467793062e-05, "loss": 0.0336, "step": 109740 }, { "epoch": 26.35, "learning_rate": 8.526639018898581e-05, "loss": 0.0286, "step": 109750 }, { "epoch": 26.35, "learning_rate": 8.526384551827773e-05, "loss": 0.0297, "step": 109760 }, { "epoch": 26.35, "learning_rate": 8.52613006658195e-05, "loss": 0.0308, "step": 109770 }, { "epoch": 26.35, "learning_rate": 8.525875563162424e-05, "loss": 0.0312, "step": 109780 }, { "epoch": 26.35, "learning_rate": 8.525621041570504e-05, "loss": 0.0327, "step": 109790 }, { "epoch": 26.36, "learning_rate": 8.525366501807506e-05, "loss": 0.0493, "step": 109800 }, { "epoch": 26.36, "learning_rate": 8.525111943874739e-05, "loss": 0.0587, "step": 109810 }, { "epoch": 26.36, "learning_rate": 8.524857367773514e-05, "loss": 0.0294, "step": 109820 }, { "epoch": 26.36, "learning_rate": 8.524602773505146e-05, "loss": 0.0262, "step": 109830 }, { "epoch": 26.37, "learning_rate": 8.524348161070945e-05, "loss": 0.0316, "step": 109840 }, { "epoch": 26.37, "learning_rate": 8.524093530472225e-05, "loss": 0.0471, "step": 109850 }, { "epoch": 26.37, "learning_rate": 8.523838881710297e-05, "loss": 0.0464, "step": 109860 }, { "epoch": 26.37, "learning_rate": 8.523584214786476e-05, "loss": 0.05, "step": 109870 }, { "epoch": 26.38, "learning_rate": 8.52332952970207e-05, "loss": 0.0395, "step": 109880 }, { "epoch": 26.38, "learning_rate": 8.523074826458394e-05, "loss": 0.0366, "step": 109890 }, { "epoch": 26.38, "learning_rate": 8.522820105056761e-05, "loss": 0.0492, "step": 109900 }, { "epoch": 26.38, "learning_rate": 8.522565365498485e-05, "loss": 0.0382, "step": 109910 }, { "epoch": 26.38, "learning_rate": 8.522310607784878e-05, "loss": 0.0456, "step": 109920 }, { "epoch": 26.39, "learning_rate": 8.522055831917251e-05, "loss": 0.0319, "step": 109930 }, { "epoch": 26.39, "learning_rate": 8.52180103789692e-05, "loss": 0.0303, "step": 109940 }, { "epoch": 26.39, "learning_rate": 8.521546225725197e-05, "loss": 0.0245, "step": 109950 }, { "epoch": 26.39, "learning_rate": 8.521291395403395e-05, "loss": 0.035, "step": 109960 }, { "epoch": 26.4, "learning_rate": 8.521036546932827e-05, "loss": 0.0327, "step": 109970 }, { "epoch": 26.4, "learning_rate": 8.520781680314808e-05, "loss": 0.036, "step": 109980 }, { "epoch": 26.4, "learning_rate": 8.520526795550649e-05, "loss": 0.0992, "step": 109990 }, { "epoch": 26.4, "learning_rate": 8.520271892641668e-05, "loss": 0.0219, "step": 110000 }, { "epoch": 26.4, "learning_rate": 8.520016971589176e-05, "loss": 0.0636, "step": 110010 }, { "epoch": 26.41, "learning_rate": 8.519762032394487e-05, "loss": 0.0592, "step": 110020 }, { "epoch": 26.41, "learning_rate": 8.519507075058914e-05, "loss": 0.056, "step": 110030 }, { "epoch": 26.41, "learning_rate": 8.519252099583772e-05, "loss": 0.0405, "step": 110040 }, { "epoch": 26.41, "learning_rate": 8.518997105970377e-05, "loss": 0.026, "step": 110050 }, { "epoch": 26.42, "learning_rate": 8.518742094220039e-05, "loss": 0.0433, "step": 110060 }, { "epoch": 26.42, "learning_rate": 8.518487064334076e-05, "loss": 0.0434, "step": 110070 }, { "epoch": 26.42, "learning_rate": 8.518232016313802e-05, "loss": 0.0335, "step": 110080 }, { "epoch": 26.42, "learning_rate": 8.517976950160532e-05, "loss": 0.038, "step": 110090 }, { "epoch": 26.43, "learning_rate": 8.517721865875576e-05, "loss": 0.0234, "step": 110100 }, { "epoch": 26.43, "learning_rate": 8.517466763460253e-05, "loss": 0.0199, "step": 110110 }, { "epoch": 26.43, "learning_rate": 8.517211642915878e-05, "loss": 0.0496, "step": 110120 }, { "epoch": 26.43, "learning_rate": 8.516956504243765e-05, "loss": 0.0373, "step": 110130 }, { "epoch": 26.43, "learning_rate": 8.516701347445229e-05, "loss": 0.0358, "step": 110140 }, { "epoch": 26.44, "learning_rate": 8.516446172521583e-05, "loss": 0.0387, "step": 110150 }, { "epoch": 26.44, "learning_rate": 8.516190979474146e-05, "loss": 0.0262, "step": 110160 }, { "epoch": 26.44, "learning_rate": 8.51593576830423e-05, "loss": 0.0267, "step": 110170 }, { "epoch": 26.44, "learning_rate": 8.515680539013151e-05, "loss": 0.032, "step": 110180 }, { "epoch": 26.45, "learning_rate": 8.515425291602226e-05, "loss": 0.0657, "step": 110190 }, { "epoch": 26.45, "learning_rate": 8.51517002607277e-05, "loss": 0.0246, "step": 110200 }, { "epoch": 26.45, "learning_rate": 8.514914742426098e-05, "loss": 0.0273, "step": 110210 }, { "epoch": 26.45, "learning_rate": 8.514659440663526e-05, "loss": 0.0202, "step": 110220 }, { "epoch": 26.46, "learning_rate": 8.514404120786371e-05, "loss": 0.0349, "step": 110230 }, { "epoch": 26.46, "learning_rate": 8.514148782795948e-05, "loss": 0.0381, "step": 110240 }, { "epoch": 26.46, "learning_rate": 8.513893426693572e-05, "loss": 0.032, "step": 110250 }, { "epoch": 26.46, "learning_rate": 8.513638052480559e-05, "loss": 0.0524, "step": 110260 }, { "epoch": 26.46, "learning_rate": 8.513382660158225e-05, "loss": 0.0645, "step": 110270 }, { "epoch": 26.47, "learning_rate": 8.513127249727889e-05, "loss": 0.045, "step": 110280 }, { "epoch": 26.47, "learning_rate": 8.512871821190866e-05, "loss": 0.057, "step": 110290 }, { "epoch": 26.47, "learning_rate": 8.512616374548473e-05, "loss": 0.0435, "step": 110300 }, { "epoch": 26.47, "learning_rate": 8.512360909802024e-05, "loss": 0.0247, "step": 110310 }, { "epoch": 26.48, "learning_rate": 8.512105426952839e-05, "loss": 0.0331, "step": 110320 }, { "epoch": 26.48, "learning_rate": 8.511849926002233e-05, "loss": 0.049, "step": 110330 }, { "epoch": 26.48, "learning_rate": 8.511594406951523e-05, "loss": 0.0607, "step": 110340 }, { "epoch": 26.48, "learning_rate": 8.511338869802026e-05, "loss": 0.036, "step": 110350 }, { "epoch": 26.48, "learning_rate": 8.511083314555059e-05, "loss": 0.0336, "step": 110360 }, { "epoch": 26.49, "learning_rate": 8.51082774121194e-05, "loss": 0.0492, "step": 110370 }, { "epoch": 26.49, "learning_rate": 8.510572149773983e-05, "loss": 0.0341, "step": 110380 }, { "epoch": 26.49, "learning_rate": 8.510316540242512e-05, "loss": 0.0331, "step": 110390 }, { "epoch": 26.49, "learning_rate": 8.510060912618835e-05, "loss": 0.062, "step": 110400 }, { "epoch": 26.5, "learning_rate": 8.509805266904278e-05, "loss": 0.0426, "step": 110410 }, { "epoch": 26.5, "learning_rate": 8.509549603100155e-05, "loss": 0.0395, "step": 110420 }, { "epoch": 26.5, "learning_rate": 8.509293921207784e-05, "loss": 0.0407, "step": 110430 }, { "epoch": 26.5, "learning_rate": 8.509038221228483e-05, "loss": 0.0354, "step": 110440 }, { "epoch": 26.51, "learning_rate": 8.50878250316357e-05, "loss": 0.0262, "step": 110450 }, { "epoch": 26.51, "learning_rate": 8.508526767014362e-05, "loss": 0.0559, "step": 110460 }, { "epoch": 26.51, "learning_rate": 8.508271012782176e-05, "loss": 0.0347, "step": 110470 }, { "epoch": 26.51, "learning_rate": 8.508015240468335e-05, "loss": 0.0499, "step": 110480 }, { "epoch": 26.51, "learning_rate": 8.507759450074152e-05, "loss": 0.0422, "step": 110490 }, { "epoch": 26.52, "learning_rate": 8.507503641600948e-05, "loss": 0.0382, "step": 110500 }, { "epoch": 26.52, "learning_rate": 8.507247815050041e-05, "loss": 0.0579, "step": 110510 }, { "epoch": 26.52, "learning_rate": 8.50699197042275e-05, "loss": 0.0548, "step": 110520 }, { "epoch": 26.52, "learning_rate": 8.506736107720392e-05, "loss": 0.0257, "step": 110530 }, { "epoch": 26.53, "learning_rate": 8.506480226944288e-05, "loss": 0.0659, "step": 110540 }, { "epoch": 26.53, "learning_rate": 8.506224328095756e-05, "loss": 0.0348, "step": 110550 }, { "epoch": 26.53, "learning_rate": 8.505968411176112e-05, "loss": 0.0442, "step": 110560 }, { "epoch": 26.53, "learning_rate": 8.50571247618668e-05, "loss": 0.022, "step": 110570 }, { "epoch": 26.54, "learning_rate": 8.505456523128775e-05, "loss": 0.0443, "step": 110580 }, { "epoch": 26.54, "learning_rate": 8.505200552003718e-05, "loss": 0.0343, "step": 110590 }, { "epoch": 26.54, "learning_rate": 8.504944562812829e-05, "loss": 0.0472, "step": 110600 }, { "epoch": 26.54, "learning_rate": 8.504688555557425e-05, "loss": 0.0698, "step": 110610 }, { "epoch": 26.54, "learning_rate": 8.504432530238828e-05, "loss": 0.0457, "step": 110620 }, { "epoch": 26.55, "learning_rate": 8.504176486858356e-05, "loss": 0.0593, "step": 110630 }, { "epoch": 26.55, "learning_rate": 8.503920425417329e-05, "loss": 0.0855, "step": 110640 }, { "epoch": 26.55, "learning_rate": 8.503664345917067e-05, "loss": 0.0612, "step": 110650 }, { "epoch": 26.55, "learning_rate": 8.50340824835889e-05, "loss": 0.0605, "step": 110660 }, { "epoch": 26.56, "learning_rate": 8.503152132744118e-05, "loss": 0.0782, "step": 110670 }, { "epoch": 26.56, "learning_rate": 8.50289599907407e-05, "loss": 0.0452, "step": 110680 }, { "epoch": 26.56, "learning_rate": 8.502639847350066e-05, "loss": 0.0774, "step": 110690 }, { "epoch": 26.56, "learning_rate": 8.502383677573428e-05, "loss": 0.0345, "step": 110700 }, { "epoch": 26.56, "learning_rate": 8.502127489745475e-05, "loss": 0.0264, "step": 110710 }, { "epoch": 26.57, "learning_rate": 8.501871283867527e-05, "loss": 0.0681, "step": 110720 }, { "epoch": 26.57, "learning_rate": 8.501615059940906e-05, "loss": 0.0698, "step": 110730 }, { "epoch": 26.57, "learning_rate": 8.501358817966931e-05, "loss": 0.0597, "step": 110740 }, { "epoch": 26.57, "learning_rate": 8.501102557946925e-05, "loss": 0.0584, "step": 110750 }, { "epoch": 26.58, "learning_rate": 8.500846279882205e-05, "loss": 0.0421, "step": 110760 }, { "epoch": 26.58, "learning_rate": 8.500589983774096e-05, "loss": 0.0806, "step": 110770 }, { "epoch": 26.58, "learning_rate": 8.500333669623915e-05, "loss": 0.0556, "step": 110780 }, { "epoch": 26.58, "learning_rate": 8.500077337432986e-05, "loss": 0.0353, "step": 110790 }, { "epoch": 26.59, "learning_rate": 8.49982098720263e-05, "loss": 0.0357, "step": 110800 }, { "epoch": 26.59, "learning_rate": 8.499564618934165e-05, "loss": 0.0348, "step": 110810 }, { "epoch": 26.59, "learning_rate": 8.499308232628917e-05, "loss": 0.0547, "step": 110820 }, { "epoch": 26.59, "learning_rate": 8.499051828288205e-05, "loss": 0.0532, "step": 110830 }, { "epoch": 26.59, "learning_rate": 8.498795405913349e-05, "loss": 0.0563, "step": 110840 }, { "epoch": 26.6, "learning_rate": 8.498538965505673e-05, "loss": 0.0339, "step": 110850 }, { "epoch": 26.6, "learning_rate": 8.498282507066498e-05, "loss": 0.0559, "step": 110860 }, { "epoch": 26.6, "learning_rate": 8.498026030597146e-05, "loss": 0.0335, "step": 110870 }, { "epoch": 26.6, "learning_rate": 8.497769536098938e-05, "loss": 0.0608, "step": 110880 }, { "epoch": 26.61, "learning_rate": 8.497513023573198e-05, "loss": 0.0389, "step": 110890 }, { "epoch": 26.61, "learning_rate": 8.497256493021246e-05, "loss": 0.0382, "step": 110900 }, { "epoch": 26.61, "learning_rate": 8.496999944444404e-05, "loss": 0.0553, "step": 110910 }, { "epoch": 26.61, "learning_rate": 8.496743377843995e-05, "loss": 0.0246, "step": 110920 }, { "epoch": 26.62, "learning_rate": 8.496486793221343e-05, "loss": 0.0462, "step": 110930 }, { "epoch": 26.62, "learning_rate": 8.496230190577766e-05, "loss": 0.0324, "step": 110940 }, { "epoch": 26.62, "learning_rate": 8.495973569914593e-05, "loss": 0.0513, "step": 110950 }, { "epoch": 26.62, "learning_rate": 8.49571693123314e-05, "loss": 0.0585, "step": 110960 }, { "epoch": 26.62, "learning_rate": 8.495460274534734e-05, "loss": 0.0569, "step": 110970 }, { "epoch": 26.63, "learning_rate": 8.495203599820696e-05, "loss": 0.0713, "step": 110980 }, { "epoch": 26.63, "learning_rate": 8.494946907092349e-05, "loss": 0.0678, "step": 110990 }, { "epoch": 26.63, "learning_rate": 8.494690196351018e-05, "loss": 0.0503, "step": 111000 }, { "epoch": 26.63, "learning_rate": 8.494433467598024e-05, "loss": 0.0644, "step": 111010 }, { "epoch": 26.64, "learning_rate": 8.49417672083469e-05, "loss": 0.037, "step": 111020 }, { "epoch": 26.64, "learning_rate": 8.49391995606234e-05, "loss": 0.054, "step": 111030 }, { "epoch": 26.64, "learning_rate": 8.493663173282298e-05, "loss": 0.0826, "step": 111040 }, { "epoch": 26.64, "learning_rate": 8.493406372495887e-05, "loss": 0.049, "step": 111050 }, { "epoch": 26.64, "learning_rate": 8.493149553704429e-05, "loss": 0.0269, "step": 111060 }, { "epoch": 26.65, "learning_rate": 8.49289271690925e-05, "loss": 0.0542, "step": 111070 }, { "epoch": 26.65, "learning_rate": 8.492635862111674e-05, "loss": 0.0509, "step": 111080 }, { "epoch": 26.65, "learning_rate": 8.49237898931302e-05, "loss": 0.0527, "step": 111090 }, { "epoch": 26.65, "learning_rate": 8.492122098514619e-05, "loss": 0.065, "step": 111100 }, { "epoch": 26.66, "learning_rate": 8.49186518971779e-05, "loss": 0.0364, "step": 111110 }, { "epoch": 26.66, "learning_rate": 8.491608262923859e-05, "loss": 0.0433, "step": 111120 }, { "epoch": 26.66, "learning_rate": 8.49135131813415e-05, "loss": 0.0395, "step": 111130 }, { "epoch": 26.66, "learning_rate": 8.491094355349987e-05, "loss": 0.0568, "step": 111140 }, { "epoch": 26.67, "learning_rate": 8.490837374572693e-05, "loss": 0.0589, "step": 111150 }, { "epoch": 26.67, "learning_rate": 8.490580375803596e-05, "loss": 0.0478, "step": 111160 }, { "epoch": 26.67, "learning_rate": 8.490323359044019e-05, "loss": 0.039, "step": 111170 }, { "epoch": 26.67, "learning_rate": 8.490066324295284e-05, "loss": 0.0397, "step": 111180 }, { "epoch": 26.67, "learning_rate": 8.48980927155872e-05, "loss": 0.0314, "step": 111190 }, { "epoch": 26.68, "learning_rate": 8.489552200835648e-05, "loss": 0.0371, "step": 111200 }, { "epoch": 26.68, "learning_rate": 8.489295112127396e-05, "loss": 0.0512, "step": 111210 }, { "epoch": 26.68, "learning_rate": 8.489038005435288e-05, "loss": 0.0311, "step": 111220 }, { "epoch": 26.68, "learning_rate": 8.488780880760648e-05, "loss": 0.0261, "step": 111230 }, { "epoch": 26.69, "learning_rate": 8.488523738104803e-05, "loss": 0.0388, "step": 111240 }, { "epoch": 26.69, "learning_rate": 8.488266577469077e-05, "loss": 0.0264, "step": 111250 }, { "epoch": 26.69, "learning_rate": 8.488009398854796e-05, "loss": 0.028, "step": 111260 }, { "epoch": 26.69, "learning_rate": 8.487752202263286e-05, "loss": 0.0525, "step": 111270 }, { "epoch": 26.7, "learning_rate": 8.48749498769587e-05, "loss": 0.0315, "step": 111280 }, { "epoch": 26.7, "learning_rate": 8.487237755153879e-05, "loss": 0.0378, "step": 111290 }, { "epoch": 26.7, "learning_rate": 8.486980504638633e-05, "loss": 0.069, "step": 111300 }, { "epoch": 26.7, "learning_rate": 8.486723236151462e-05, "loss": 0.0431, "step": 111310 }, { "epoch": 26.7, "learning_rate": 8.486465949693687e-05, "loss": 0.0369, "step": 111320 }, { "epoch": 26.71, "learning_rate": 8.48620864526664e-05, "loss": 0.0464, "step": 111330 }, { "epoch": 26.71, "learning_rate": 8.485951322871644e-05, "loss": 0.0619, "step": 111340 }, { "epoch": 26.71, "learning_rate": 8.485693982510026e-05, "loss": 0.044, "step": 111350 }, { "epoch": 26.71, "learning_rate": 8.485436624183112e-05, "loss": 0.0555, "step": 111360 }, { "epoch": 26.72, "learning_rate": 8.485179247892228e-05, "loss": 0.0439, "step": 111370 }, { "epoch": 26.72, "learning_rate": 8.484921853638703e-05, "loss": 0.052, "step": 111380 }, { "epoch": 26.72, "learning_rate": 8.48466444142386e-05, "loss": 0.0384, "step": 111390 }, { "epoch": 26.72, "learning_rate": 8.484407011249027e-05, "loss": 0.0326, "step": 111400 }, { "epoch": 26.72, "learning_rate": 8.484149563115531e-05, "loss": 0.06, "step": 111410 }, { "epoch": 26.73, "learning_rate": 8.4838920970247e-05, "loss": 0.0695, "step": 111420 }, { "epoch": 26.73, "learning_rate": 8.483634612977859e-05, "loss": 0.0393, "step": 111430 }, { "epoch": 26.73, "learning_rate": 8.483377110976336e-05, "loss": 0.0455, "step": 111440 }, { "epoch": 26.73, "learning_rate": 8.483119591021461e-05, "loss": 0.0295, "step": 111450 }, { "epoch": 26.74, "learning_rate": 8.482862053114555e-05, "loss": 0.0625, "step": 111460 }, { "epoch": 26.74, "learning_rate": 8.482604497256952e-05, "loss": 0.0298, "step": 111470 }, { "epoch": 26.74, "learning_rate": 8.482346923449974e-05, "loss": 0.0515, "step": 111480 }, { "epoch": 26.74, "learning_rate": 8.482089331694951e-05, "loss": 0.0434, "step": 111490 }, { "epoch": 26.75, "learning_rate": 8.481831721993211e-05, "loss": 0.0579, "step": 111500 }, { "epoch": 26.75, "learning_rate": 8.481574094346081e-05, "loss": 0.0312, "step": 111510 }, { "epoch": 26.75, "learning_rate": 8.48131644875489e-05, "loss": 0.0386, "step": 111520 }, { "epoch": 26.75, "learning_rate": 8.481058785220963e-05, "loss": 0.0386, "step": 111530 }, { "epoch": 26.75, "learning_rate": 8.480801103745633e-05, "loss": 0.0389, "step": 111540 }, { "epoch": 26.76, "learning_rate": 8.480543404330221e-05, "loss": 0.0311, "step": 111550 }, { "epoch": 26.76, "learning_rate": 8.480285686976062e-05, "loss": 0.057, "step": 111560 }, { "epoch": 26.76, "learning_rate": 8.48002795168448e-05, "loss": 0.0619, "step": 111570 }, { "epoch": 26.76, "learning_rate": 8.479770198456806e-05, "loss": 0.0325, "step": 111580 }, { "epoch": 26.77, "learning_rate": 8.479512427294366e-05, "loss": 0.036, "step": 111590 }, { "epoch": 26.77, "learning_rate": 8.479254638198493e-05, "loss": 0.035, "step": 111600 }, { "epoch": 26.77, "learning_rate": 8.478996831170509e-05, "loss": 0.0342, "step": 111610 }, { "epoch": 26.77, "learning_rate": 8.478739006211748e-05, "loss": 0.0286, "step": 111620 }, { "epoch": 26.78, "learning_rate": 8.478481163323536e-05, "loss": 0.0488, "step": 111630 }, { "epoch": 26.78, "learning_rate": 8.478223302507203e-05, "loss": 0.0396, "step": 111640 }, { "epoch": 26.78, "learning_rate": 8.477965423764078e-05, "loss": 0.0477, "step": 111650 }, { "epoch": 26.78, "learning_rate": 8.47770752709549e-05, "loss": 0.065, "step": 111660 }, { "epoch": 26.78, "learning_rate": 8.477449612502771e-05, "loss": 0.0393, "step": 111670 }, { "epoch": 26.79, "learning_rate": 8.477191679987246e-05, "loss": 0.0466, "step": 111680 }, { "epoch": 26.79, "learning_rate": 8.476933729550246e-05, "loss": 0.0263, "step": 111690 }, { "epoch": 26.79, "learning_rate": 8.4766757611931e-05, "loss": 0.0243, "step": 111700 }, { "epoch": 26.79, "learning_rate": 8.476417774917138e-05, "loss": 0.0684, "step": 111710 }, { "epoch": 26.8, "learning_rate": 8.47615977072369e-05, "loss": 0.0373, "step": 111720 }, { "epoch": 26.8, "learning_rate": 8.475901748614085e-05, "loss": 0.0439, "step": 111730 }, { "epoch": 26.8, "learning_rate": 8.475643708589656e-05, "loss": 0.0279, "step": 111740 }, { "epoch": 26.8, "learning_rate": 8.475385650651727e-05, "loss": 0.0418, "step": 111750 }, { "epoch": 26.8, "learning_rate": 8.475127574801633e-05, "loss": 0.0329, "step": 111760 }, { "epoch": 26.81, "learning_rate": 8.474869481040701e-05, "loss": 0.0257, "step": 111770 }, { "epoch": 26.81, "learning_rate": 8.474611369370265e-05, "loss": 0.0356, "step": 111780 }, { "epoch": 26.81, "learning_rate": 8.474353239791651e-05, "loss": 0.0355, "step": 111790 }, { "epoch": 26.81, "learning_rate": 8.474095092306191e-05, "loss": 0.0501, "step": 111800 }, { "epoch": 26.82, "learning_rate": 8.473836926915218e-05, "loss": 0.051, "step": 111810 }, { "epoch": 26.82, "learning_rate": 8.473578743620059e-05, "loss": 0.0388, "step": 111820 }, { "epoch": 26.82, "learning_rate": 8.473320542422046e-05, "loss": 0.0217, "step": 111830 }, { "epoch": 26.82, "learning_rate": 8.473062323322509e-05, "loss": 0.031, "step": 111840 }, { "epoch": 26.83, "learning_rate": 8.47280408632278e-05, "loss": 0.0463, "step": 111850 }, { "epoch": 26.83, "learning_rate": 8.472545831424192e-05, "loss": 0.0316, "step": 111860 }, { "epoch": 26.83, "learning_rate": 8.472287558628072e-05, "loss": 0.0461, "step": 111870 }, { "epoch": 26.83, "learning_rate": 8.472029267935753e-05, "loss": 0.0404, "step": 111880 }, { "epoch": 26.83, "learning_rate": 8.471770959348568e-05, "loss": 0.0366, "step": 111890 }, { "epoch": 26.84, "learning_rate": 8.471512632867844e-05, "loss": 0.0654, "step": 111900 }, { "epoch": 26.84, "learning_rate": 8.471254288494915e-05, "loss": 0.033, "step": 111910 }, { "epoch": 26.84, "learning_rate": 8.470995926231114e-05, "loss": 0.0359, "step": 111920 }, { "epoch": 26.84, "learning_rate": 8.470737546077769e-05, "loss": 0.0385, "step": 111930 }, { "epoch": 26.85, "learning_rate": 8.470479148036215e-05, "loss": 0.0315, "step": 111940 }, { "epoch": 26.85, "learning_rate": 8.470220732107783e-05, "loss": 0.0265, "step": 111950 }, { "epoch": 26.85, "learning_rate": 8.469962298293803e-05, "loss": 0.0241, "step": 111960 }, { "epoch": 26.85, "learning_rate": 8.46970384659561e-05, "loss": 0.0428, "step": 111970 }, { "epoch": 26.86, "learning_rate": 8.469445377014532e-05, "loss": 0.0325, "step": 111980 }, { "epoch": 26.86, "learning_rate": 8.469186889551906e-05, "loss": 0.0454, "step": 111990 }, { "epoch": 26.86, "learning_rate": 8.46892838420906e-05, "loss": 0.0327, "step": 112000 }, { "epoch": 26.86, "learning_rate": 8.468669860987329e-05, "loss": 0.0445, "step": 112010 }, { "epoch": 26.86, "learning_rate": 8.468411319888044e-05, "loss": 0.0397, "step": 112020 }, { "epoch": 26.87, "learning_rate": 8.468152760912537e-05, "loss": 0.0382, "step": 112030 }, { "epoch": 26.87, "learning_rate": 8.467894184062144e-05, "loss": 0.0358, "step": 112040 }, { "epoch": 26.87, "learning_rate": 8.467635589338194e-05, "loss": 0.039, "step": 112050 }, { "epoch": 26.87, "learning_rate": 8.467376976742022e-05, "loss": 0.0396, "step": 112060 }, { "epoch": 26.88, "learning_rate": 8.467118346274959e-05, "loss": 0.0359, "step": 112070 }, { "epoch": 26.88, "learning_rate": 8.466859697938339e-05, "loss": 0.0428, "step": 112080 }, { "epoch": 26.88, "learning_rate": 8.466601031733496e-05, "loss": 0.0432, "step": 112090 }, { "epoch": 26.88, "learning_rate": 8.466342347661764e-05, "loss": 0.0399, "step": 112100 }, { "epoch": 26.88, "learning_rate": 8.466083645724472e-05, "loss": 0.0435, "step": 112110 }, { "epoch": 26.89, "learning_rate": 8.465824925922956e-05, "loss": 0.0273, "step": 112120 }, { "epoch": 26.89, "learning_rate": 8.46556618825855e-05, "loss": 0.0241, "step": 112130 }, { "epoch": 26.89, "learning_rate": 8.465307432732587e-05, "loss": 0.0525, "step": 112140 }, { "epoch": 26.89, "learning_rate": 8.465048659346399e-05, "loss": 0.041, "step": 112150 }, { "epoch": 26.9, "learning_rate": 8.464789868101324e-05, "loss": 0.0479, "step": 112160 }, { "epoch": 26.9, "learning_rate": 8.464531058998693e-05, "loss": 0.0257, "step": 112170 }, { "epoch": 26.9, "learning_rate": 8.464272232039838e-05, "loss": 0.035, "step": 112180 }, { "epoch": 26.9, "learning_rate": 8.464013387226095e-05, "loss": 0.042, "step": 112190 }, { "epoch": 26.91, "learning_rate": 8.463754524558797e-05, "loss": 0.0338, "step": 112200 }, { "epoch": 26.91, "learning_rate": 8.463495644039283e-05, "loss": 0.0409, "step": 112210 }, { "epoch": 26.91, "learning_rate": 8.463236745668881e-05, "loss": 0.0262, "step": 112220 }, { "epoch": 26.91, "learning_rate": 8.462977829448929e-05, "loss": 0.0381, "step": 112230 }, { "epoch": 26.91, "learning_rate": 8.462718895380759e-05, "loss": 0.046, "step": 112240 }, { "epoch": 26.92, "learning_rate": 8.462459943465708e-05, "loss": 0.0229, "step": 112250 }, { "epoch": 26.92, "learning_rate": 8.462200973705108e-05, "loss": 0.0371, "step": 112260 }, { "epoch": 26.92, "learning_rate": 8.461941986100296e-05, "loss": 0.0308, "step": 112270 }, { "epoch": 26.92, "learning_rate": 8.461682980652607e-05, "loss": 0.053, "step": 112280 }, { "epoch": 26.93, "learning_rate": 8.461423957363374e-05, "loss": 0.0158, "step": 112290 }, { "epoch": 26.93, "learning_rate": 8.461164916233933e-05, "loss": 0.0271, "step": 112300 }, { "epoch": 26.93, "learning_rate": 8.46090585726562e-05, "loss": 0.0392, "step": 112310 }, { "epoch": 26.93, "learning_rate": 8.46064678045977e-05, "loss": 0.0427, "step": 112320 }, { "epoch": 26.94, "learning_rate": 8.460387685817715e-05, "loss": 0.0281, "step": 112330 }, { "epoch": 26.94, "learning_rate": 8.460128573340793e-05, "loss": 0.0335, "step": 112340 }, { "epoch": 26.94, "learning_rate": 8.459869443030341e-05, "loss": 0.0295, "step": 112350 }, { "epoch": 26.94, "learning_rate": 8.459610294887692e-05, "loss": 0.0296, "step": 112360 }, { "epoch": 26.94, "learning_rate": 8.459351128914184e-05, "loss": 0.0335, "step": 112370 }, { "epoch": 26.95, "learning_rate": 8.459091945111151e-05, "loss": 0.0229, "step": 112380 }, { "epoch": 26.95, "learning_rate": 8.458832743479927e-05, "loss": 0.0338, "step": 112390 }, { "epoch": 26.95, "learning_rate": 8.458573524021854e-05, "loss": 0.0372, "step": 112400 }, { "epoch": 27.0, "learning_rate": 8.45831428673826e-05, "loss": 0.0542, "step": 112410 }, { "epoch": 27.0, "learning_rate": 8.458055031630488e-05, "loss": 0.048, "step": 112420 }, { "epoch": 27.01, "learning_rate": 8.45779575869987e-05, "loss": 0.0278, "step": 112430 }, { "epoch": 27.01, "learning_rate": 8.457536467947745e-05, "loss": 0.0525, "step": 112440 }, { "epoch": 27.01, "learning_rate": 8.457277159375447e-05, "loss": 0.0706, "step": 112450 }, { "epoch": 27.01, "learning_rate": 8.457017832984315e-05, "loss": 0.0377, "step": 112460 }, { "epoch": 27.02, "learning_rate": 8.456758488775683e-05, "loss": 0.0336, "step": 112470 }, { "epoch": 27.02, "learning_rate": 8.45649912675089e-05, "loss": 0.0424, "step": 112480 }, { "epoch": 27.02, "learning_rate": 8.45623974691127e-05, "loss": 0.0229, "step": 112490 }, { "epoch": 27.02, "learning_rate": 8.455980349258162e-05, "loss": 0.0301, "step": 112500 }, { "epoch": 27.02, "learning_rate": 8.455720933792903e-05, "loss": 0.05, "step": 112510 }, { "epoch": 27.03, "learning_rate": 8.45546150051683e-05, "loss": 0.0336, "step": 112520 }, { "epoch": 27.03, "learning_rate": 8.455202049431279e-05, "loss": 0.0372, "step": 112530 }, { "epoch": 27.03, "learning_rate": 8.454942580537586e-05, "loss": 0.0348, "step": 112540 }, { "epoch": 27.03, "learning_rate": 8.454683093837093e-05, "loss": 0.0454, "step": 112550 }, { "epoch": 27.04, "learning_rate": 8.454423589331132e-05, "loss": 0.0347, "step": 112560 }, { "epoch": 27.04, "learning_rate": 8.454164067021045e-05, "loss": 0.0673, "step": 112570 }, { "epoch": 27.04, "learning_rate": 8.453904526908165e-05, "loss": 0.0375, "step": 112580 }, { "epoch": 27.04, "learning_rate": 8.453644968993834e-05, "loss": 0.038, "step": 112590 }, { "epoch": 27.05, "learning_rate": 8.453385393279387e-05, "loss": 0.056, "step": 112600 }, { "epoch": 27.05, "learning_rate": 8.453125799766164e-05, "loss": 0.0238, "step": 112610 }, { "epoch": 27.05, "learning_rate": 8.452866188455502e-05, "loss": 0.0287, "step": 112620 }, { "epoch": 27.05, "learning_rate": 8.452606559348737e-05, "loss": 0.0234, "step": 112630 }, { "epoch": 27.05, "learning_rate": 8.45234691244721e-05, "loss": 0.0294, "step": 112640 }, { "epoch": 27.06, "learning_rate": 8.452087247752259e-05, "loss": 0.0545, "step": 112650 }, { "epoch": 27.06, "learning_rate": 8.45182756526522e-05, "loss": 0.0551, "step": 112660 }, { "epoch": 27.06, "learning_rate": 8.451567864987433e-05, "loss": 0.0461, "step": 112670 }, { "epoch": 27.06, "learning_rate": 8.451308146920236e-05, "loss": 0.0453, "step": 112680 }, { "epoch": 27.07, "learning_rate": 8.45104841106497e-05, "loss": 0.035, "step": 112690 }, { "epoch": 27.07, "learning_rate": 8.45078865742297e-05, "loss": 0.0298, "step": 112700 }, { "epoch": 27.07, "learning_rate": 8.450528885995576e-05, "loss": 0.0277, "step": 112710 }, { "epoch": 27.07, "learning_rate": 8.450269096784129e-05, "loss": 0.0341, "step": 112720 }, { "epoch": 27.08, "learning_rate": 8.450009289789965e-05, "loss": 0.025, "step": 112730 }, { "epoch": 27.08, "learning_rate": 8.449749465014425e-05, "loss": 0.0312, "step": 112740 }, { "epoch": 27.08, "learning_rate": 8.449489622458847e-05, "loss": 0.0356, "step": 112750 }, { "epoch": 27.08, "learning_rate": 8.449229762124571e-05, "loss": 0.0493, "step": 112760 }, { "epoch": 27.08, "learning_rate": 8.448969884012934e-05, "loss": 0.0552, "step": 112770 }, { "epoch": 27.09, "learning_rate": 8.448709988125281e-05, "loss": 0.0459, "step": 112780 }, { "epoch": 27.09, "learning_rate": 8.448450074462945e-05, "loss": 0.0361, "step": 112790 }, { "epoch": 27.09, "learning_rate": 8.448190143027269e-05, "loss": 0.0531, "step": 112800 }, { "epoch": 27.09, "learning_rate": 8.447930193819594e-05, "loss": 0.0397, "step": 112810 }, { "epoch": 27.1, "learning_rate": 8.447670226841255e-05, "loss": 0.0163, "step": 112820 }, { "epoch": 27.1, "learning_rate": 8.447410242093597e-05, "loss": 0.0483, "step": 112830 }, { "epoch": 27.1, "learning_rate": 8.447150239577957e-05, "loss": 0.036, "step": 112840 }, { "epoch": 27.1, "learning_rate": 8.446890219295675e-05, "loss": 0.032, "step": 112850 }, { "epoch": 27.1, "learning_rate": 8.446630181248095e-05, "loss": 0.044, "step": 112860 }, { "epoch": 27.11, "learning_rate": 8.446370125436551e-05, "loss": 0.031, "step": 112870 }, { "epoch": 27.11, "learning_rate": 8.446110051862388e-05, "loss": 0.034, "step": 112880 }, { "epoch": 27.11, "learning_rate": 8.445849960526946e-05, "loss": 0.0412, "step": 112890 }, { "epoch": 27.11, "learning_rate": 8.445589851431563e-05, "loss": 0.0314, "step": 112900 }, { "epoch": 27.12, "learning_rate": 8.44532972457758e-05, "loss": 0.0485, "step": 112910 }, { "epoch": 27.12, "learning_rate": 8.44506957996634e-05, "loss": 0.0358, "step": 112920 }, { "epoch": 27.12, "learning_rate": 8.444809417599185e-05, "loss": 0.0453, "step": 112930 }, { "epoch": 27.12, "learning_rate": 8.44454923747745e-05, "loss": 0.0413, "step": 112940 }, { "epoch": 27.13, "learning_rate": 8.44428903960248e-05, "loss": 0.0204, "step": 112950 }, { "epoch": 27.13, "learning_rate": 8.444028823975618e-05, "loss": 0.0324, "step": 112960 }, { "epoch": 27.13, "learning_rate": 8.4437685905982e-05, "loss": 0.0464, "step": 112970 }, { "epoch": 27.13, "learning_rate": 8.443508339471571e-05, "loss": 0.0381, "step": 112980 }, { "epoch": 27.13, "learning_rate": 8.443248070597072e-05, "loss": 0.0202, "step": 112990 }, { "epoch": 27.14, "learning_rate": 8.442987783976042e-05, "loss": 0.0244, "step": 113000 }, { "epoch": 27.14, "learning_rate": 8.442727479609824e-05, "loss": 0.0367, "step": 113010 }, { "epoch": 27.14, "learning_rate": 8.44246715749976e-05, "loss": 0.0425, "step": 113020 }, { "epoch": 27.14, "learning_rate": 8.442206817647194e-05, "loss": 0.032, "step": 113030 }, { "epoch": 27.15, "learning_rate": 8.441946460053463e-05, "loss": 0.0255, "step": 113040 }, { "epoch": 27.15, "learning_rate": 8.441686084719912e-05, "loss": 0.0231, "step": 113050 }, { "epoch": 27.15, "learning_rate": 8.441425691647882e-05, "loss": 0.0325, "step": 113060 }, { "epoch": 27.15, "learning_rate": 8.441165280838714e-05, "loss": 0.0513, "step": 113070 }, { "epoch": 27.16, "learning_rate": 8.440904852293752e-05, "loss": 0.0328, "step": 113080 }, { "epoch": 27.16, "learning_rate": 8.440644406014338e-05, "loss": 0.0477, "step": 113090 }, { "epoch": 27.16, "learning_rate": 8.440383942001815e-05, "loss": 0.0228, "step": 113100 }, { "epoch": 27.16, "learning_rate": 8.440123460257523e-05, "loss": 0.033, "step": 113110 }, { "epoch": 27.16, "learning_rate": 8.439862960782807e-05, "loss": 0.0342, "step": 113120 }, { "epoch": 27.17, "learning_rate": 8.439602443579007e-05, "loss": 0.0435, "step": 113130 }, { "epoch": 27.17, "learning_rate": 8.439341908647469e-05, "loss": 0.0282, "step": 113140 }, { "epoch": 27.17, "learning_rate": 8.439081355989532e-05, "loss": 0.0298, "step": 113150 }, { "epoch": 27.17, "learning_rate": 8.438820785606543e-05, "loss": 0.0411, "step": 113160 }, { "epoch": 27.18, "learning_rate": 8.438560197499841e-05, "loss": 0.0383, "step": 113170 }, { "epoch": 27.18, "learning_rate": 8.438299591670772e-05, "loss": 0.0589, "step": 113180 }, { "epoch": 27.18, "learning_rate": 8.438038968120678e-05, "loss": 0.0398, "step": 113190 }, { "epoch": 27.18, "learning_rate": 8.437778326850903e-05, "loss": 0.043, "step": 113200 }, { "epoch": 27.18, "learning_rate": 8.43751766786279e-05, "loss": 0.0537, "step": 113210 }, { "epoch": 27.19, "learning_rate": 8.437256991157682e-05, "loss": 0.0225, "step": 113220 }, { "epoch": 27.19, "learning_rate": 8.43699629673692e-05, "loss": 0.038, "step": 113230 }, { "epoch": 27.19, "learning_rate": 8.436735584601853e-05, "loss": 0.0237, "step": 113240 }, { "epoch": 27.19, "learning_rate": 8.436474854753824e-05, "loss": 0.0345, "step": 113250 }, { "epoch": 27.2, "learning_rate": 8.436214107194172e-05, "loss": 0.0253, "step": 113260 }, { "epoch": 27.2, "learning_rate": 8.435953341924245e-05, "loss": 0.0447, "step": 113270 }, { "epoch": 27.2, "learning_rate": 8.435692558945385e-05, "loss": 0.0326, "step": 113280 }, { "epoch": 27.2, "learning_rate": 8.435431758258936e-05, "loss": 0.0646, "step": 113290 }, { "epoch": 27.21, "learning_rate": 8.435170939866243e-05, "loss": 0.0329, "step": 113300 }, { "epoch": 27.21, "learning_rate": 8.434910103768652e-05, "loss": 0.0335, "step": 113310 }, { "epoch": 27.21, "learning_rate": 8.434649249967506e-05, "loss": 0.0302, "step": 113320 }, { "epoch": 27.21, "learning_rate": 8.434388378464147e-05, "loss": 0.0345, "step": 113330 }, { "epoch": 27.21, "learning_rate": 8.434127489259923e-05, "loss": 0.0306, "step": 113340 }, { "epoch": 27.22, "learning_rate": 8.433866582356176e-05, "loss": 0.0529, "step": 113350 }, { "epoch": 27.22, "learning_rate": 8.433605657754254e-05, "loss": 0.0272, "step": 113360 }, { "epoch": 27.22, "learning_rate": 8.433344715455498e-05, "loss": 0.0216, "step": 113370 }, { "epoch": 27.22, "learning_rate": 8.433083755461255e-05, "loss": 0.0519, "step": 113380 }, { "epoch": 27.23, "learning_rate": 8.43282277777287e-05, "loss": 0.0356, "step": 113390 }, { "epoch": 27.23, "learning_rate": 8.432561782391687e-05, "loss": 0.0492, "step": 113400 }, { "epoch": 27.23, "learning_rate": 8.432300769319053e-05, "loss": 0.0396, "step": 113410 }, { "epoch": 27.23, "learning_rate": 8.43203973855631e-05, "loss": 0.0328, "step": 113420 }, { "epoch": 27.24, "learning_rate": 8.431778690104808e-05, "loss": 0.0245, "step": 113430 }, { "epoch": 27.24, "learning_rate": 8.431517623965888e-05, "loss": 0.0388, "step": 113440 }, { "epoch": 27.24, "learning_rate": 8.431256540140899e-05, "loss": 0.0506, "step": 113450 }, { "epoch": 27.24, "learning_rate": 8.430995438631184e-05, "loss": 0.0331, "step": 113460 }, { "epoch": 27.24, "learning_rate": 8.43073431943809e-05, "loss": 0.0322, "step": 113470 }, { "epoch": 27.25, "learning_rate": 8.430473182562964e-05, "loss": 0.0458, "step": 113480 }, { "epoch": 27.25, "learning_rate": 8.43021202800715e-05, "loss": 0.0395, "step": 113490 }, { "epoch": 27.25, "learning_rate": 8.429950855771993e-05, "loss": 0.0418, "step": 113500 }, { "epoch": 27.25, "learning_rate": 8.429689665858842e-05, "loss": 0.0344, "step": 113510 }, { "epoch": 27.26, "learning_rate": 8.429428458269041e-05, "loss": 0.0401, "step": 113520 }, { "epoch": 27.26, "learning_rate": 8.429167233003938e-05, "loss": 0.0607, "step": 113530 }, { "epoch": 27.26, "learning_rate": 8.428905990064876e-05, "loss": 0.0472, "step": 113540 }, { "epoch": 27.26, "learning_rate": 8.428644729453207e-05, "loss": 0.0314, "step": 113550 }, { "epoch": 27.26, "learning_rate": 8.428383451170273e-05, "loss": 0.0239, "step": 113560 }, { "epoch": 27.27, "learning_rate": 8.428122155217422e-05, "loss": 0.0327, "step": 113570 }, { "epoch": 27.27, "learning_rate": 8.427860841596001e-05, "loss": 0.044, "step": 113580 }, { "epoch": 27.27, "learning_rate": 8.427599510307357e-05, "loss": 0.0407, "step": 113590 }, { "epoch": 27.27, "learning_rate": 8.427338161352836e-05, "loss": 0.0288, "step": 113600 }, { "epoch": 27.28, "learning_rate": 8.427076794733786e-05, "loss": 0.0407, "step": 113610 }, { "epoch": 27.28, "learning_rate": 8.426815410451551e-05, "loss": 0.0322, "step": 113620 }, { "epoch": 27.28, "learning_rate": 8.426554008507483e-05, "loss": 0.0363, "step": 113630 }, { "epoch": 27.28, "learning_rate": 8.426292588902928e-05, "loss": 0.0263, "step": 113640 }, { "epoch": 27.29, "learning_rate": 8.426031151639231e-05, "loss": 0.0332, "step": 113650 }, { "epoch": 27.29, "learning_rate": 8.42576969671774e-05, "loss": 0.0359, "step": 113660 }, { "epoch": 27.29, "learning_rate": 8.425508224139804e-05, "loss": 0.0225, "step": 113670 }, { "epoch": 27.29, "learning_rate": 8.42524673390677e-05, "loss": 0.0388, "step": 113680 }, { "epoch": 27.29, "learning_rate": 8.424985226019988e-05, "loss": 0.0304, "step": 113690 }, { "epoch": 27.3, "learning_rate": 8.424723700480801e-05, "loss": 0.0334, "step": 113700 }, { "epoch": 27.3, "learning_rate": 8.42446215729056e-05, "loss": 0.0255, "step": 113710 }, { "epoch": 27.3, "learning_rate": 8.424200596450611e-05, "loss": 0.027, "step": 113720 }, { "epoch": 27.3, "learning_rate": 8.423939017962306e-05, "loss": 0.0258, "step": 113730 }, { "epoch": 27.31, "learning_rate": 8.423677421826988e-05, "loss": 0.0163, "step": 113740 }, { "epoch": 27.31, "learning_rate": 8.42341580804601e-05, "loss": 0.0196, "step": 113750 }, { "epoch": 27.31, "learning_rate": 8.423154176620717e-05, "loss": 0.0367, "step": 113760 }, { "epoch": 27.31, "learning_rate": 8.422892527552461e-05, "loss": 0.0326, "step": 113770 }, { "epoch": 27.32, "learning_rate": 8.422630860842586e-05, "loss": 0.0215, "step": 113780 }, { "epoch": 27.32, "learning_rate": 8.422369176492443e-05, "loss": 0.032, "step": 113790 }, { "epoch": 27.32, "learning_rate": 8.422107474503382e-05, "loss": 0.0224, "step": 113800 }, { "epoch": 27.32, "learning_rate": 8.421845754876751e-05, "loss": 0.0329, "step": 113810 }, { "epoch": 27.32, "learning_rate": 8.421584017613897e-05, "loss": 0.0229, "step": 113820 }, { "epoch": 27.33, "learning_rate": 8.42132226271617e-05, "loss": 0.0484, "step": 113830 }, { "epoch": 27.33, "learning_rate": 8.42106049018492e-05, "loss": 0.0261, "step": 113840 }, { "epoch": 27.33, "learning_rate": 8.420798700021496e-05, "loss": 0.0501, "step": 113850 }, { "epoch": 27.33, "learning_rate": 8.420536892227246e-05, "loss": 0.0346, "step": 113860 }, { "epoch": 27.34, "learning_rate": 8.420275066803521e-05, "loss": 0.0312, "step": 113870 }, { "epoch": 27.34, "learning_rate": 8.42001322375167e-05, "loss": 0.0268, "step": 113880 }, { "epoch": 27.34, "learning_rate": 8.419751363073043e-05, "loss": 0.0299, "step": 113890 }, { "epoch": 27.34, "learning_rate": 8.419489484768987e-05, "loss": 0.0356, "step": 113900 }, { "epoch": 27.34, "learning_rate": 8.419227588840855e-05, "loss": 0.0321, "step": 113910 }, { "epoch": 27.35, "learning_rate": 8.418965675289994e-05, "loss": 0.0196, "step": 113920 }, { "epoch": 27.35, "learning_rate": 8.418703744117756e-05, "loss": 0.0276, "step": 113930 }, { "epoch": 27.35, "learning_rate": 8.418441795325491e-05, "loss": 0.0383, "step": 113940 }, { "epoch": 27.35, "learning_rate": 8.418179828914548e-05, "loss": 0.027, "step": 113950 }, { "epoch": 27.36, "learning_rate": 8.417917844886278e-05, "loss": 0.0321, "step": 113960 }, { "epoch": 27.36, "learning_rate": 8.417655843242029e-05, "loss": 0.0442, "step": 113970 }, { "epoch": 27.36, "learning_rate": 8.417393823983155e-05, "loss": 0.0316, "step": 113980 }, { "epoch": 27.36, "learning_rate": 8.417131787111004e-05, "loss": 0.0383, "step": 113990 }, { "epoch": 27.37, "learning_rate": 8.416869732626928e-05, "loss": 0.0589, "step": 114000 }, { "epoch": 27.37, "learning_rate": 8.416607660532275e-05, "loss": 0.0293, "step": 114010 }, { "epoch": 27.37, "learning_rate": 8.416345570828399e-05, "loss": 0.0448, "step": 114020 }, { "epoch": 27.37, "learning_rate": 8.416083463516649e-05, "loss": 0.0332, "step": 114030 }, { "epoch": 27.37, "learning_rate": 8.415821338598377e-05, "loss": 0.0425, "step": 114040 }, { "epoch": 27.38, "learning_rate": 8.415559196074932e-05, "loss": 0.023, "step": 114050 }, { "epoch": 27.38, "learning_rate": 8.415297035947668e-05, "loss": 0.0291, "step": 114060 }, { "epoch": 27.38, "learning_rate": 8.415034858217934e-05, "loss": 0.0316, "step": 114070 }, { "epoch": 27.38, "learning_rate": 8.414772662887081e-05, "loss": 0.0282, "step": 114080 }, { "epoch": 27.39, "learning_rate": 8.41451044995646e-05, "loss": 0.0439, "step": 114090 }, { "epoch": 27.39, "learning_rate": 8.414248219427426e-05, "loss": 0.0234, "step": 114100 }, { "epoch": 27.39, "learning_rate": 8.413985971301328e-05, "loss": 0.0211, "step": 114110 }, { "epoch": 27.39, "learning_rate": 8.413723705579517e-05, "loss": 0.0406, "step": 114120 }, { "epoch": 27.4, "learning_rate": 8.413461422263344e-05, "loss": 0.0282, "step": 114130 }, { "epoch": 27.4, "learning_rate": 8.413199121354165e-05, "loss": 0.0367, "step": 114140 }, { "epoch": 27.4, "learning_rate": 8.412936802853329e-05, "loss": 0.0277, "step": 114150 }, { "epoch": 27.4, "learning_rate": 8.412674466762186e-05, "loss": 0.0288, "step": 114160 }, { "epoch": 27.4, "learning_rate": 8.41241211308209e-05, "loss": 0.0278, "step": 114170 }, { "epoch": 27.41, "learning_rate": 8.412149741814396e-05, "loss": 0.0402, "step": 114180 }, { "epoch": 27.41, "learning_rate": 8.411887352960454e-05, "loss": 0.0394, "step": 114190 }, { "epoch": 27.41, "learning_rate": 8.411624946521615e-05, "loss": 0.0203, "step": 114200 }, { "epoch": 27.41, "learning_rate": 8.411362522499232e-05, "loss": 0.0229, "step": 114210 }, { "epoch": 27.42, "learning_rate": 8.411100080894659e-05, "loss": 0.0385, "step": 114220 }, { "epoch": 27.42, "learning_rate": 8.410837621709246e-05, "loss": 0.0418, "step": 114230 }, { "epoch": 27.42, "learning_rate": 8.410575144944348e-05, "loss": 0.0275, "step": 114240 }, { "epoch": 27.42, "learning_rate": 8.410312650601318e-05, "loss": 0.0554, "step": 114250 }, { "epoch": 27.42, "learning_rate": 8.410050138681507e-05, "loss": 0.0458, "step": 114260 }, { "epoch": 27.43, "learning_rate": 8.40978760918627e-05, "loss": 0.0263, "step": 114270 }, { "epoch": 27.43, "learning_rate": 8.409525062116958e-05, "loss": 0.0246, "step": 114280 }, { "epoch": 27.43, "learning_rate": 8.409262497474927e-05, "loss": 0.0483, "step": 114290 }, { "epoch": 27.43, "learning_rate": 8.408999915261527e-05, "loss": 0.0424, "step": 114300 }, { "epoch": 27.44, "learning_rate": 8.408737315478115e-05, "loss": 0.0441, "step": 114310 }, { "epoch": 27.44, "learning_rate": 8.40847469812604e-05, "loss": 0.0372, "step": 114320 }, { "epoch": 27.44, "learning_rate": 8.408212063206659e-05, "loss": 0.0175, "step": 114330 }, { "epoch": 27.44, "learning_rate": 8.407949410721325e-05, "loss": 0.0368, "step": 114340 }, { "epoch": 27.45, "learning_rate": 8.40768674067139e-05, "loss": 0.0264, "step": 114350 }, { "epoch": 27.45, "learning_rate": 8.40742405305821e-05, "loss": 0.0237, "step": 114360 }, { "epoch": 27.45, "learning_rate": 8.407161347883139e-05, "loss": 0.0451, "step": 114370 }, { "epoch": 27.45, "learning_rate": 8.406898625147529e-05, "loss": 0.0351, "step": 114380 }, { "epoch": 27.45, "learning_rate": 8.406635884852734e-05, "loss": 0.0484, "step": 114390 }, { "epoch": 27.46, "learning_rate": 8.40637312700011e-05, "loss": 0.0342, "step": 114400 }, { "epoch": 27.46, "learning_rate": 8.40611035159101e-05, "loss": 0.0217, "step": 114410 }, { "epoch": 27.46, "learning_rate": 8.405847558626789e-05, "loss": 0.0282, "step": 114420 }, { "epoch": 27.46, "learning_rate": 8.405584748108801e-05, "loss": 0.0489, "step": 114430 }, { "epoch": 27.47, "learning_rate": 8.405321920038402e-05, "loss": 0.0328, "step": 114440 }, { "epoch": 27.47, "learning_rate": 8.405059074416944e-05, "loss": 0.0277, "step": 114450 }, { "epoch": 27.47, "learning_rate": 8.404796211245784e-05, "loss": 0.036, "step": 114460 }, { "epoch": 27.47, "learning_rate": 8.404533330526277e-05, "loss": 0.0267, "step": 114470 }, { "epoch": 27.48, "learning_rate": 8.404270432259773e-05, "loss": 0.0212, "step": 114480 }, { "epoch": 27.48, "learning_rate": 8.404007516447634e-05, "loss": 0.0275, "step": 114490 }, { "epoch": 27.48, "learning_rate": 8.40374458309121e-05, "loss": 0.0212, "step": 114500 }, { "epoch": 27.48, "learning_rate": 8.403481632191858e-05, "loss": 0.0441, "step": 114510 }, { "epoch": 27.48, "learning_rate": 8.403218663750933e-05, "loss": 0.0367, "step": 114520 }, { "epoch": 27.49, "learning_rate": 8.402955677769793e-05, "loss": 0.0469, "step": 114530 }, { "epoch": 27.49, "learning_rate": 8.40269267424979e-05, "loss": 0.0286, "step": 114540 }, { "epoch": 27.49, "learning_rate": 8.40242965319228e-05, "loss": 0.0243, "step": 114550 }, { "epoch": 27.49, "learning_rate": 8.402166614598619e-05, "loss": 0.036, "step": 114560 }, { "epoch": 27.5, "learning_rate": 8.401903558470162e-05, "loss": 0.0217, "step": 114570 }, { "epoch": 27.5, "learning_rate": 8.401640484808266e-05, "loss": 0.0174, "step": 114580 }, { "epoch": 27.5, "learning_rate": 8.401377393614287e-05, "loss": 0.0309, "step": 114590 }, { "epoch": 27.5, "learning_rate": 8.40111428488958e-05, "loss": 0.0364, "step": 114600 }, { "epoch": 27.5, "learning_rate": 8.400851158635504e-05, "loss": 0.0405, "step": 114610 }, { "epoch": 27.51, "learning_rate": 8.40058801485341e-05, "loss": 0.0283, "step": 114620 }, { "epoch": 27.51, "learning_rate": 8.400324853544659e-05, "loss": 0.0298, "step": 114630 }, { "epoch": 27.51, "learning_rate": 8.400061674710603e-05, "loss": 0.0182, "step": 114640 }, { "epoch": 27.51, "learning_rate": 8.399798478352602e-05, "loss": 0.0225, "step": 114650 }, { "epoch": 27.52, "learning_rate": 8.399535264472009e-05, "loss": 0.0375, "step": 114660 }, { "epoch": 27.52, "learning_rate": 8.399272033070186e-05, "loss": 0.0283, "step": 114670 }, { "epoch": 27.52, "learning_rate": 8.399008784148486e-05, "loss": 0.0518, "step": 114680 }, { "epoch": 27.52, "learning_rate": 8.398745517708265e-05, "loss": 0.0603, "step": 114690 }, { "epoch": 27.53, "learning_rate": 8.398482233750881e-05, "loss": 0.0441, "step": 114700 }, { "epoch": 27.53, "learning_rate": 8.398218932277692e-05, "loss": 0.048, "step": 114710 }, { "epoch": 27.53, "learning_rate": 8.397955613290054e-05, "loss": 0.0286, "step": 114720 }, { "epoch": 27.53, "learning_rate": 8.397692276789326e-05, "loss": 0.0619, "step": 114730 }, { "epoch": 27.53, "learning_rate": 8.397428922776861e-05, "loss": 0.0393, "step": 114740 }, { "epoch": 27.54, "learning_rate": 8.39716555125402e-05, "loss": 0.0432, "step": 114750 }, { "epoch": 27.54, "learning_rate": 8.39690216222216e-05, "loss": 0.0452, "step": 114760 }, { "epoch": 27.54, "learning_rate": 8.396638755682638e-05, "loss": 0.0444, "step": 114770 }, { "epoch": 27.54, "learning_rate": 8.39637533163681e-05, "loss": 0.0459, "step": 114780 }, { "epoch": 27.55, "learning_rate": 8.396111890086035e-05, "loss": 0.0506, "step": 114790 }, { "epoch": 27.55, "learning_rate": 8.395848431031672e-05, "loss": 0.0555, "step": 114800 }, { "epoch": 27.55, "learning_rate": 8.395584954475078e-05, "loss": 0.058, "step": 114810 }, { "epoch": 27.55, "learning_rate": 8.39532146041761e-05, "loss": 0.0561, "step": 114820 }, { "epoch": 27.56, "learning_rate": 8.395057948860628e-05, "loss": 0.0231, "step": 114830 }, { "epoch": 27.56, "learning_rate": 8.394794419805488e-05, "loss": 0.0428, "step": 114840 }, { "epoch": 27.56, "learning_rate": 8.39453087325355e-05, "loss": 0.0671, "step": 114850 }, { "epoch": 27.56, "learning_rate": 8.39426730920617e-05, "loss": 0.0629, "step": 114860 }, { "epoch": 27.56, "learning_rate": 8.39400372766471e-05, "loss": 0.0514, "step": 114870 }, { "epoch": 27.57, "learning_rate": 8.393740128630526e-05, "loss": 0.0709, "step": 114880 }, { "epoch": 27.57, "learning_rate": 8.393476512104974e-05, "loss": 0.0426, "step": 114890 }, { "epoch": 27.57, "learning_rate": 8.393212878089419e-05, "loss": 0.0406, "step": 114900 }, { "epoch": 27.57, "learning_rate": 8.392949226585215e-05, "loss": 0.0451, "step": 114910 }, { "epoch": 27.58, "learning_rate": 8.392685557593723e-05, "loss": 0.0334, "step": 114920 }, { "epoch": 27.58, "learning_rate": 8.392421871116301e-05, "loss": 0.0465, "step": 114930 }, { "epoch": 27.58, "learning_rate": 8.392158167154307e-05, "loss": 0.0365, "step": 114940 }, { "epoch": 27.58, "learning_rate": 8.391894445709103e-05, "loss": 0.0416, "step": 114950 }, { "epoch": 27.58, "learning_rate": 8.391630706782047e-05, "loss": 0.0594, "step": 114960 }, { "epoch": 27.59, "learning_rate": 8.391366950374497e-05, "loss": 0.0509, "step": 114970 }, { "epoch": 27.59, "learning_rate": 8.391103176487814e-05, "loss": 0.0549, "step": 114980 }, { "epoch": 27.59, "learning_rate": 8.390839385123357e-05, "loss": 0.0791, "step": 114990 }, { "epoch": 27.59, "learning_rate": 8.390575576282484e-05, "loss": 0.0557, "step": 115000 }, { "epoch": 27.6, "learning_rate": 8.390311749966557e-05, "loss": 0.0541, "step": 115010 }, { "epoch": 27.6, "learning_rate": 8.390047906176936e-05, "loss": 0.0386, "step": 115020 }, { "epoch": 27.6, "learning_rate": 8.38978404491498e-05, "loss": 0.0504, "step": 115030 }, { "epoch": 27.6, "learning_rate": 8.389520166182047e-05, "loss": 0.047, "step": 115040 }, { "epoch": 27.61, "learning_rate": 8.389256269979499e-05, "loss": 0.0273, "step": 115050 }, { "epoch": 27.61, "learning_rate": 8.388992356308695e-05, "loss": 0.0304, "step": 115060 }, { "epoch": 27.61, "learning_rate": 8.388728425170998e-05, "loss": 0.043, "step": 115070 }, { "epoch": 27.61, "learning_rate": 8.388464476567766e-05, "loss": 0.0317, "step": 115080 }, { "epoch": 27.61, "learning_rate": 8.388200510500359e-05, "loss": 0.0559, "step": 115090 }, { "epoch": 27.62, "learning_rate": 8.38793652697014e-05, "loss": 0.0547, "step": 115100 }, { "epoch": 27.62, "learning_rate": 8.387672525978466e-05, "loss": 0.0537, "step": 115110 }, { "epoch": 27.62, "learning_rate": 8.3874085075267e-05, "loss": 0.0416, "step": 115120 }, { "epoch": 27.62, "learning_rate": 8.387144471616202e-05, "loss": 0.0425, "step": 115130 }, { "epoch": 27.63, "learning_rate": 8.386880418248333e-05, "loss": 0.0457, "step": 115140 }, { "epoch": 27.63, "learning_rate": 8.386616347424454e-05, "loss": 0.0263, "step": 115150 }, { "epoch": 27.63, "learning_rate": 8.386352259145926e-05, "loss": 0.0406, "step": 115160 }, { "epoch": 27.63, "learning_rate": 8.386088153414111e-05, "loss": 0.0361, "step": 115170 }, { "epoch": 27.64, "learning_rate": 8.385824030230369e-05, "loss": 0.0474, "step": 115180 }, { "epoch": 27.64, "learning_rate": 8.385559889596062e-05, "loss": 0.0487, "step": 115190 }, { "epoch": 27.64, "learning_rate": 8.38529573151255e-05, "loss": 0.0475, "step": 115200 }, { "epoch": 27.64, "learning_rate": 8.385031555981197e-05, "loss": 0.0367, "step": 115210 }, { "epoch": 27.64, "learning_rate": 8.38476736300336e-05, "loss": 0.0462, "step": 115220 }, { "epoch": 27.65, "learning_rate": 8.384503152580407e-05, "loss": 0.0392, "step": 115230 }, { "epoch": 27.65, "learning_rate": 8.384238924713695e-05, "loss": 0.0914, "step": 115240 }, { "epoch": 27.65, "learning_rate": 8.383974679404587e-05, "loss": 0.0389, "step": 115250 }, { "epoch": 27.65, "learning_rate": 8.383710416654447e-05, "loss": 0.0433, "step": 115260 }, { "epoch": 27.66, "learning_rate": 8.383446136464634e-05, "loss": 0.0275, "step": 115270 }, { "epoch": 27.66, "learning_rate": 8.383181838836511e-05, "loss": 0.0604, "step": 115280 }, { "epoch": 27.66, "learning_rate": 8.382917523771441e-05, "loss": 0.0487, "step": 115290 }, { "epoch": 27.66, "learning_rate": 8.382653191270786e-05, "loss": 0.0426, "step": 115300 }, { "epoch": 27.66, "learning_rate": 8.382388841335907e-05, "loss": 0.0753, "step": 115310 }, { "epoch": 27.67, "learning_rate": 8.38212447396817e-05, "loss": 0.0456, "step": 115320 }, { "epoch": 27.67, "learning_rate": 8.381860089168933e-05, "loss": 0.0345, "step": 115330 }, { "epoch": 27.67, "learning_rate": 8.38159568693956e-05, "loss": 0.0515, "step": 115340 }, { "epoch": 27.67, "learning_rate": 8.381331267281417e-05, "loss": 0.0422, "step": 115350 }, { "epoch": 27.68, "learning_rate": 8.381066830195863e-05, "loss": 0.0596, "step": 115360 }, { "epoch": 27.68, "learning_rate": 8.380802375684264e-05, "loss": 0.0365, "step": 115370 }, { "epoch": 27.68, "learning_rate": 8.380537903747979e-05, "loss": 0.0669, "step": 115380 }, { "epoch": 27.68, "learning_rate": 8.380273414388375e-05, "loss": 0.041, "step": 115390 }, { "epoch": 27.69, "learning_rate": 8.380008907606813e-05, "loss": 0.0324, "step": 115400 }, { "epoch": 27.69, "learning_rate": 8.379744383404658e-05, "loss": 0.0337, "step": 115410 }, { "epoch": 27.69, "learning_rate": 8.37947984178327e-05, "loss": 0.0349, "step": 115420 }, { "epoch": 27.69, "learning_rate": 8.379215282744016e-05, "loss": 0.0438, "step": 115430 }, { "epoch": 27.69, "learning_rate": 8.378950706288257e-05, "loss": 0.0343, "step": 115440 }, { "epoch": 27.7, "learning_rate": 8.378686112417358e-05, "loss": 0.0785, "step": 115450 }, { "epoch": 27.7, "learning_rate": 8.378421501132684e-05, "loss": 0.0383, "step": 115460 }, { "epoch": 27.7, "learning_rate": 8.378156872435597e-05, "loss": 0.0469, "step": 115470 }, { "epoch": 27.7, "learning_rate": 8.37789222632746e-05, "loss": 0.0627, "step": 115480 }, { "epoch": 27.71, "learning_rate": 8.37762756280964e-05, "loss": 0.0286, "step": 115490 }, { "epoch": 27.71, "learning_rate": 8.377362881883497e-05, "loss": 0.0404, "step": 115500 }, { "epoch": 27.71, "learning_rate": 8.3770981835504e-05, "loss": 0.064, "step": 115510 }, { "epoch": 27.71, "learning_rate": 8.376833467811709e-05, "loss": 0.0526, "step": 115520 }, { "epoch": 27.72, "learning_rate": 8.37656873466879e-05, "loss": 0.0428, "step": 115530 }, { "epoch": 27.72, "learning_rate": 8.376303984123009e-05, "loss": 0.0535, "step": 115540 }, { "epoch": 27.72, "learning_rate": 8.376039216175729e-05, "loss": 0.0391, "step": 115550 }, { "epoch": 27.72, "learning_rate": 8.375774430828314e-05, "loss": 0.0423, "step": 115560 }, { "epoch": 27.72, "learning_rate": 8.375509628082127e-05, "loss": 0.0396, "step": 115570 }, { "epoch": 27.73, "learning_rate": 8.375244807938538e-05, "loss": 0.0443, "step": 115580 }, { "epoch": 27.73, "learning_rate": 8.374979970398908e-05, "loss": 0.0631, "step": 115590 }, { "epoch": 27.73, "learning_rate": 8.374715115464605e-05, "loss": 0.0564, "step": 115600 }, { "epoch": 27.73, "learning_rate": 8.374450243136991e-05, "loss": 0.0357, "step": 115610 }, { "epoch": 27.74, "learning_rate": 8.374185353417432e-05, "loss": 0.0369, "step": 115620 }, { "epoch": 27.74, "learning_rate": 8.373920446307293e-05, "loss": 0.0315, "step": 115630 }, { "epoch": 27.74, "learning_rate": 8.37365552180794e-05, "loss": 0.0334, "step": 115640 }, { "epoch": 27.74, "learning_rate": 8.373390579920737e-05, "loss": 0.0395, "step": 115650 }, { "epoch": 27.74, "learning_rate": 8.373125620647054e-05, "loss": 0.0658, "step": 115660 }, { "epoch": 27.75, "learning_rate": 8.372860643988249e-05, "loss": 0.0292, "step": 115670 }, { "epoch": 27.75, "learning_rate": 8.372595649945695e-05, "loss": 0.0375, "step": 115680 }, { "epoch": 27.75, "learning_rate": 8.372330638520755e-05, "loss": 0.0313, "step": 115690 }, { "epoch": 27.75, "learning_rate": 8.372065609714794e-05, "loss": 0.0332, "step": 115700 }, { "epoch": 27.76, "learning_rate": 8.371800563529178e-05, "loss": 0.0651, "step": 115710 }, { "epoch": 27.76, "learning_rate": 8.371535499965276e-05, "loss": 0.0248, "step": 115720 }, { "epoch": 27.76, "learning_rate": 8.371270419024449e-05, "loss": 0.0337, "step": 115730 }, { "epoch": 27.76, "learning_rate": 8.371005320708068e-05, "loss": 0.0415, "step": 115740 }, { "epoch": 27.77, "learning_rate": 8.370740205017495e-05, "loss": 0.037, "step": 115750 }, { "epoch": 27.77, "learning_rate": 8.370475071954103e-05, "loss": 0.037, "step": 115760 }, { "epoch": 27.77, "learning_rate": 8.37020992151925e-05, "loss": 0.0351, "step": 115770 }, { "epoch": 27.77, "learning_rate": 8.36994475371431e-05, "loss": 0.0409, "step": 115780 }, { "epoch": 27.77, "learning_rate": 8.369679568540644e-05, "loss": 0.0379, "step": 115790 }, { "epoch": 27.78, "learning_rate": 8.369414365999624e-05, "loss": 0.0247, "step": 115800 }, { "epoch": 27.78, "learning_rate": 8.369149146092612e-05, "loss": 0.0264, "step": 115810 }, { "epoch": 27.78, "learning_rate": 8.368883908820978e-05, "loss": 0.0407, "step": 115820 }, { "epoch": 27.78, "learning_rate": 8.36861865418609e-05, "loss": 0.0496, "step": 115830 }, { "epoch": 27.79, "learning_rate": 8.368353382189311e-05, "loss": 0.0356, "step": 115840 }, { "epoch": 27.79, "learning_rate": 8.368088092832009e-05, "loss": 0.0243, "step": 115850 }, { "epoch": 27.79, "learning_rate": 8.367822786115556e-05, "loss": 0.0303, "step": 115860 }, { "epoch": 27.79, "learning_rate": 8.367557462041314e-05, "loss": 0.0345, "step": 115870 }, { "epoch": 27.8, "learning_rate": 8.367292120610655e-05, "loss": 0.0398, "step": 115880 }, { "epoch": 27.8, "learning_rate": 8.367026761824941e-05, "loss": 0.0238, "step": 115890 }, { "epoch": 27.8, "learning_rate": 8.366761385685547e-05, "loss": 0.032, "step": 115900 }, { "epoch": 27.8, "learning_rate": 8.366495992193834e-05, "loss": 0.0193, "step": 115910 }, { "epoch": 27.8, "learning_rate": 8.366230581351173e-05, "loss": 0.0384, "step": 115920 }, { "epoch": 27.81, "learning_rate": 8.36596515315893e-05, "loss": 0.0338, "step": 115930 }, { "epoch": 27.81, "learning_rate": 8.365699707618477e-05, "loss": 0.0429, "step": 115940 }, { "epoch": 27.81, "learning_rate": 8.365434244731178e-05, "loss": 0.0602, "step": 115950 }, { "epoch": 27.81, "learning_rate": 8.365168764498403e-05, "loss": 0.0438, "step": 115960 }, { "epoch": 27.82, "learning_rate": 8.364903266921522e-05, "loss": 0.0381, "step": 115970 }, { "epoch": 27.82, "learning_rate": 8.3646377520019e-05, "loss": 0.0558, "step": 115980 }, { "epoch": 27.82, "learning_rate": 8.364372219740905e-05, "loss": 0.0419, "step": 115990 }, { "epoch": 27.82, "learning_rate": 8.36410667013991e-05, "loss": 0.0345, "step": 116000 }, { "epoch": 27.82, "learning_rate": 8.36384110320028e-05, "loss": 0.049, "step": 116010 }, { "epoch": 27.83, "learning_rate": 8.363575518923386e-05, "loss": 0.033, "step": 116020 }, { "epoch": 27.83, "learning_rate": 8.363309917310593e-05, "loss": 0.0277, "step": 116030 }, { "epoch": 27.83, "learning_rate": 8.363044298363275e-05, "loss": 0.0306, "step": 116040 }, { "epoch": 27.83, "learning_rate": 8.362778662082798e-05, "loss": 0.0288, "step": 116050 }, { "epoch": 27.84, "learning_rate": 8.362513008470532e-05, "loss": 0.0258, "step": 116060 }, { "epoch": 27.84, "learning_rate": 8.362247337527845e-05, "loss": 0.0373, "step": 116070 }, { "epoch": 27.84, "learning_rate": 8.361981649256108e-05, "loss": 0.0334, "step": 116080 }, { "epoch": 27.84, "learning_rate": 8.361715943656689e-05, "loss": 0.0186, "step": 116090 }, { "epoch": 27.85, "learning_rate": 8.361450220730958e-05, "loss": 0.0474, "step": 116100 }, { "epoch": 27.85, "learning_rate": 8.361184480480284e-05, "loss": 0.035, "step": 116110 }, { "epoch": 27.85, "learning_rate": 8.360918722906039e-05, "loss": 0.048, "step": 116120 }, { "epoch": 27.85, "learning_rate": 8.360652948009589e-05, "loss": 0.0272, "step": 116130 }, { "epoch": 27.85, "learning_rate": 8.360387155792305e-05, "loss": 0.0207, "step": 116140 }, { "epoch": 27.86, "learning_rate": 8.360121346255559e-05, "loss": 0.0209, "step": 116150 }, { "epoch": 27.86, "learning_rate": 8.359855519400719e-05, "loss": 0.0295, "step": 116160 }, { "epoch": 27.86, "learning_rate": 8.359589675229155e-05, "loss": 0.0404, "step": 116170 }, { "epoch": 27.86, "learning_rate": 8.359323813742238e-05, "loss": 0.0343, "step": 116180 }, { "epoch": 27.87, "learning_rate": 8.359057934941339e-05, "loss": 0.0354, "step": 116190 }, { "epoch": 27.87, "learning_rate": 8.358792038827826e-05, "loss": 0.0335, "step": 116200 }, { "epoch": 27.87, "learning_rate": 8.358526125403072e-05, "loss": 0.043, "step": 116210 }, { "epoch": 27.87, "learning_rate": 8.358260194668446e-05, "loss": 0.0443, "step": 116220 }, { "epoch": 27.88, "learning_rate": 8.357994246625319e-05, "loss": 0.0241, "step": 116230 }, { "epoch": 27.88, "learning_rate": 8.357728281275058e-05, "loss": 0.0401, "step": 116240 }, { "epoch": 27.88, "learning_rate": 8.357462298619042e-05, "loss": 0.0286, "step": 116250 }, { "epoch": 27.88, "learning_rate": 8.357196298658636e-05, "loss": 0.0242, "step": 116260 }, { "epoch": 27.88, "learning_rate": 8.356930281395212e-05, "loss": 0.0426, "step": 116270 }, { "epoch": 27.89, "learning_rate": 8.356664246830141e-05, "loss": 0.0418, "step": 116280 }, { "epoch": 27.89, "learning_rate": 8.356398194964794e-05, "loss": 0.0373, "step": 116290 }, { "epoch": 27.89, "learning_rate": 8.356132125800545e-05, "loss": 0.0194, "step": 116300 }, { "epoch": 27.89, "learning_rate": 8.35586603933876e-05, "loss": 0.033, "step": 116310 }, { "epoch": 27.9, "learning_rate": 8.355599935580813e-05, "loss": 0.048, "step": 116320 }, { "epoch": 27.9, "learning_rate": 8.35533381452808e-05, "loss": 0.0386, "step": 116330 }, { "epoch": 27.9, "learning_rate": 8.355067676181924e-05, "loss": 0.0422, "step": 116340 }, { "epoch": 27.9, "learning_rate": 8.354801520543724e-05, "loss": 0.0472, "step": 116350 }, { "epoch": 27.9, "learning_rate": 8.354535347614848e-05, "loss": 0.0327, "step": 116360 }, { "epoch": 27.91, "learning_rate": 8.354269157396668e-05, "loss": 0.0323, "step": 116370 }, { "epoch": 27.91, "learning_rate": 8.354002949890559e-05, "loss": 0.0337, "step": 116380 }, { "epoch": 27.91, "learning_rate": 8.353736725097888e-05, "loss": 0.0324, "step": 116390 }, { "epoch": 27.91, "learning_rate": 8.353470483020031e-05, "loss": 0.0355, "step": 116400 }, { "epoch": 27.92, "learning_rate": 8.35320422365836e-05, "loss": 0.0239, "step": 116410 }, { "epoch": 27.92, "learning_rate": 8.352937947014245e-05, "loss": 0.0278, "step": 116420 }, { "epoch": 27.92, "learning_rate": 8.352671653089061e-05, "loss": 0.0288, "step": 116430 }, { "epoch": 27.92, "learning_rate": 8.352405341884179e-05, "loss": 0.0302, "step": 116440 }, { "epoch": 27.93, "learning_rate": 8.352139013400971e-05, "loss": 0.0332, "step": 116450 }, { "epoch": 27.93, "learning_rate": 8.351872667640812e-05, "loss": 0.0464, "step": 116460 }, { "epoch": 27.93, "learning_rate": 8.351606304605071e-05, "loss": 0.0397, "step": 116470 }, { "epoch": 27.93, "learning_rate": 8.351339924295125e-05, "loss": 0.1094, "step": 116480 }, { "epoch": 27.93, "learning_rate": 8.351073526712345e-05, "loss": 0.0162, "step": 116490 }, { "epoch": 27.94, "learning_rate": 8.350807111858104e-05, "loss": 0.0267, "step": 116500 }, { "epoch": 27.94, "learning_rate": 8.350540679733774e-05, "loss": 0.0333, "step": 116510 }, { "epoch": 27.94, "learning_rate": 8.350274230340729e-05, "loss": 0.0306, "step": 116520 }, { "epoch": 27.94, "learning_rate": 8.350007763680344e-05, "loss": 0.0294, "step": 116530 }, { "epoch": 27.95, "learning_rate": 8.349741279753991e-05, "loss": 0.0231, "step": 116540 }, { "epoch": 27.95, "learning_rate": 8.349474778563042e-05, "loss": 0.0351, "step": 116550 }, { "epoch": 27.95, "learning_rate": 8.349208260108874e-05, "loss": 0.0437, "step": 116560 }, { "epoch": 28.0, "learning_rate": 8.348941724392858e-05, "loss": 0.0455, "step": 116570 }, { "epoch": 28.0, "learning_rate": 8.348675171416367e-05, "loss": 0.0484, "step": 116580 }, { "epoch": 28.01, "learning_rate": 8.348408601180777e-05, "loss": 0.0289, "step": 116590 }, { "epoch": 28.01, "learning_rate": 8.348142013687461e-05, "loss": 0.0427, "step": 116600 }, { "epoch": 28.01, "learning_rate": 8.347875408937793e-05, "loss": 0.0433, "step": 116610 }, { "epoch": 28.01, "learning_rate": 8.347608786933149e-05, "loss": 0.0374, "step": 116620 }, { "epoch": 28.02, "learning_rate": 8.347342147674899e-05, "loss": 0.0375, "step": 116630 }, { "epoch": 28.02, "learning_rate": 8.34707549116442e-05, "loss": 0.0339, "step": 116640 }, { "epoch": 28.02, "learning_rate": 8.346808817403087e-05, "loss": 0.0328, "step": 116650 }, { "epoch": 28.02, "learning_rate": 8.346542126392273e-05, "loss": 0.0358, "step": 116660 }, { "epoch": 28.02, "learning_rate": 8.346275418133351e-05, "loss": 0.0376, "step": 116670 }, { "epoch": 28.03, "learning_rate": 8.3460086926277e-05, "loss": 0.0211, "step": 116680 }, { "epoch": 28.03, "learning_rate": 8.345741949876692e-05, "loss": 0.0445, "step": 116690 }, { "epoch": 28.03, "learning_rate": 8.345475189881702e-05, "loss": 0.0429, "step": 116700 }, { "epoch": 28.03, "learning_rate": 8.345208412644103e-05, "loss": 0.0469, "step": 116710 }, { "epoch": 28.04, "learning_rate": 8.344941618165275e-05, "loss": 0.0441, "step": 116720 }, { "epoch": 28.04, "learning_rate": 8.344674806446587e-05, "loss": 0.0437, "step": 116730 }, { "epoch": 28.04, "learning_rate": 8.344407977489418e-05, "loss": 0.0325, "step": 116740 }, { "epoch": 28.04, "learning_rate": 8.344141131295142e-05, "loss": 0.0545, "step": 116750 }, { "epoch": 28.04, "learning_rate": 8.343874267865136e-05, "loss": 0.0383, "step": 116760 }, { "epoch": 28.05, "learning_rate": 8.343607387200773e-05, "loss": 0.0285, "step": 116770 }, { "epoch": 28.05, "learning_rate": 8.34334048930343e-05, "loss": 0.0429, "step": 116780 }, { "epoch": 28.05, "learning_rate": 8.343073574174482e-05, "loss": 0.0208, "step": 116790 }, { "epoch": 28.05, "learning_rate": 8.342806641815304e-05, "loss": 0.0274, "step": 116800 }, { "epoch": 28.06, "learning_rate": 8.342539692227274e-05, "loss": 0.0478, "step": 116810 }, { "epoch": 28.06, "learning_rate": 8.342272725411766e-05, "loss": 0.0145, "step": 116820 }, { "epoch": 28.06, "learning_rate": 8.342005741370157e-05, "loss": 0.0366, "step": 116830 }, { "epoch": 28.06, "learning_rate": 8.341738740103821e-05, "loss": 0.0353, "step": 116840 }, { "epoch": 28.07, "learning_rate": 8.341471721614137e-05, "loss": 0.0328, "step": 116850 }, { "epoch": 28.07, "learning_rate": 8.341204685902479e-05, "loss": 0.0246, "step": 116860 }, { "epoch": 28.07, "learning_rate": 8.340937632970225e-05, "loss": 0.0431, "step": 116870 }, { "epoch": 28.07, "learning_rate": 8.34067056281875e-05, "loss": 0.039, "step": 116880 }, { "epoch": 28.07, "learning_rate": 8.34040347544943e-05, "loss": 0.0348, "step": 116890 }, { "epoch": 28.08, "learning_rate": 8.340136370863643e-05, "loss": 0.0324, "step": 116900 }, { "epoch": 28.08, "learning_rate": 8.339869249062766e-05, "loss": 0.0278, "step": 116910 }, { "epoch": 28.08, "learning_rate": 8.339602110048175e-05, "loss": 0.0454, "step": 116920 }, { "epoch": 28.08, "learning_rate": 8.339334953821247e-05, "loss": 0.0199, "step": 116930 }, { "epoch": 28.09, "learning_rate": 8.339067780383358e-05, "loss": 0.0275, "step": 116940 }, { "epoch": 28.09, "learning_rate": 8.338800589735886e-05, "loss": 0.0257, "step": 116950 }, { "epoch": 28.09, "learning_rate": 8.338533381880208e-05, "loss": 0.0304, "step": 116960 }, { "epoch": 28.09, "learning_rate": 8.3382661568177e-05, "loss": 0.0289, "step": 116970 }, { "epoch": 28.1, "learning_rate": 8.337998914549743e-05, "loss": 0.0219, "step": 116980 }, { "epoch": 28.1, "learning_rate": 8.33773165507771e-05, "loss": 0.0401, "step": 116990 }, { "epoch": 28.1, "learning_rate": 8.33746437840298e-05, "loss": 0.0383, "step": 117000 }, { "epoch": 28.1, "learning_rate": 8.33719708452693e-05, "loss": 0.0457, "step": 117010 }, { "epoch": 28.1, "learning_rate": 8.336929773450939e-05, "loss": 0.0141, "step": 117020 }, { "epoch": 28.11, "learning_rate": 8.336662445176384e-05, "loss": 0.024, "step": 117030 }, { "epoch": 28.11, "learning_rate": 8.336395099704643e-05, "loss": 0.0243, "step": 117040 }, { "epoch": 28.11, "learning_rate": 8.336127737037094e-05, "loss": 0.0298, "step": 117050 }, { "epoch": 28.11, "learning_rate": 8.335860357175114e-05, "loss": 0.0381, "step": 117060 }, { "epoch": 28.12, "learning_rate": 8.335592960120082e-05, "loss": 0.0324, "step": 117070 }, { "epoch": 28.12, "learning_rate": 8.335325545873378e-05, "loss": 0.0304, "step": 117080 }, { "epoch": 28.12, "learning_rate": 8.335058114436376e-05, "loss": 0.0264, "step": 117090 }, { "epoch": 28.12, "learning_rate": 8.334790665810456e-05, "loss": 0.0312, "step": 117100 }, { "epoch": 28.12, "learning_rate": 8.334523199997e-05, "loss": 0.0353, "step": 117110 }, { "epoch": 28.13, "learning_rate": 8.334255716997382e-05, "loss": 0.0356, "step": 117120 }, { "epoch": 28.13, "learning_rate": 8.333988216812983e-05, "loss": 0.0252, "step": 117130 }, { "epoch": 28.13, "learning_rate": 8.333720699445178e-05, "loss": 0.0329, "step": 117140 }, { "epoch": 28.13, "learning_rate": 8.333453164895351e-05, "loss": 0.038, "step": 117150 }, { "epoch": 28.14, "learning_rate": 8.333185613164877e-05, "loss": 0.0427, "step": 117160 }, { "epoch": 28.14, "learning_rate": 8.332918044255138e-05, "loss": 0.0328, "step": 117170 }, { "epoch": 28.14, "learning_rate": 8.332650458167512e-05, "loss": 0.0257, "step": 117180 }, { "epoch": 28.14, "learning_rate": 8.332382854903377e-05, "loss": 0.0561, "step": 117190 }, { "epoch": 28.15, "learning_rate": 8.332115234464113e-05, "loss": 0.0455, "step": 117200 }, { "epoch": 28.15, "learning_rate": 8.331847596851097e-05, "loss": 0.0311, "step": 117210 }, { "epoch": 28.15, "learning_rate": 8.331579942065712e-05, "loss": 0.0335, "step": 117220 }, { "epoch": 28.15, "learning_rate": 8.331312270109337e-05, "loss": 0.0456, "step": 117230 }, { "epoch": 28.15, "learning_rate": 8.331044580983352e-05, "loss": 0.044, "step": 117240 }, { "epoch": 28.16, "learning_rate": 8.330776874689132e-05, "loss": 0.0353, "step": 117250 }, { "epoch": 28.16, "learning_rate": 8.330509151228063e-05, "loss": 0.0372, "step": 117260 }, { "epoch": 28.16, "learning_rate": 8.330241410601521e-05, "loss": 0.0416, "step": 117270 }, { "epoch": 28.16, "learning_rate": 8.329973652810888e-05, "loss": 0.0325, "step": 117280 }, { "epoch": 28.17, "learning_rate": 8.32970587785754e-05, "loss": 0.0379, "step": 117290 }, { "epoch": 28.17, "learning_rate": 8.329438085742862e-05, "loss": 0.0364, "step": 117300 }, { "epoch": 28.17, "learning_rate": 8.329170276468232e-05, "loss": 0.0232, "step": 117310 }, { "epoch": 28.17, "learning_rate": 8.32890245003503e-05, "loss": 0.0337, "step": 117320 }, { "epoch": 28.18, "learning_rate": 8.328634606444639e-05, "loss": 0.0471, "step": 117330 }, { "epoch": 28.18, "learning_rate": 8.328366745698436e-05, "loss": 0.0195, "step": 117340 }, { "epoch": 28.18, "learning_rate": 8.328098867797803e-05, "loss": 0.0321, "step": 117350 }, { "epoch": 28.18, "learning_rate": 8.32783097274412e-05, "loss": 0.0214, "step": 117360 }, { "epoch": 28.18, "learning_rate": 8.32756306053877e-05, "loss": 0.0264, "step": 117370 }, { "epoch": 28.19, "learning_rate": 8.327295131183131e-05, "loss": 0.0444, "step": 117380 }, { "epoch": 28.19, "learning_rate": 8.327027184678584e-05, "loss": 0.0332, "step": 117390 }, { "epoch": 28.19, "learning_rate": 8.326759221026512e-05, "loss": 0.0488, "step": 117400 }, { "epoch": 28.19, "learning_rate": 8.326491240228297e-05, "loss": 0.0391, "step": 117410 }, { "epoch": 28.2, "learning_rate": 8.326223242285317e-05, "loss": 0.0189, "step": 117420 }, { "epoch": 28.2, "learning_rate": 8.325955227198954e-05, "loss": 0.0245, "step": 117430 }, { "epoch": 28.2, "learning_rate": 8.325687194970591e-05, "loss": 0.0349, "step": 117440 }, { "epoch": 28.2, "learning_rate": 8.325419145601608e-05, "loss": 0.0367, "step": 117450 }, { "epoch": 28.2, "learning_rate": 8.325151079093385e-05, "loss": 0.0474, "step": 117460 }, { "epoch": 28.21, "learning_rate": 8.324882995447307e-05, "loss": 0.0462, "step": 117470 }, { "epoch": 28.21, "learning_rate": 8.324614894664756e-05, "loss": 0.0383, "step": 117480 }, { "epoch": 28.21, "learning_rate": 8.324346776747111e-05, "loss": 0.0277, "step": 117490 }, { "epoch": 28.21, "learning_rate": 8.324078641695754e-05, "loss": 0.0283, "step": 117500 }, { "epoch": 28.22, "learning_rate": 8.323810489512068e-05, "loss": 0.031, "step": 117510 }, { "epoch": 28.22, "learning_rate": 8.323542320197434e-05, "loss": 0.0352, "step": 117520 }, { "epoch": 28.22, "learning_rate": 8.323274133753238e-05, "loss": 0.0271, "step": 117530 }, { "epoch": 28.22, "learning_rate": 8.323005930180857e-05, "loss": 0.0311, "step": 117540 }, { "epoch": 28.23, "learning_rate": 8.322737709481678e-05, "loss": 0.0144, "step": 117550 }, { "epoch": 28.23, "learning_rate": 8.32246947165708e-05, "loss": 0.0205, "step": 117560 }, { "epoch": 28.23, "learning_rate": 8.322201216708445e-05, "loss": 0.0269, "step": 117570 }, { "epoch": 28.23, "learning_rate": 8.321932944637158e-05, "loss": 0.0238, "step": 117580 }, { "epoch": 28.23, "learning_rate": 8.3216646554446e-05, "loss": 0.034, "step": 117590 }, { "epoch": 28.24, "learning_rate": 8.321396349132156e-05, "loss": 0.048, "step": 117600 }, { "epoch": 28.24, "learning_rate": 8.321128025701208e-05, "loss": 0.0204, "step": 117610 }, { "epoch": 28.24, "learning_rate": 8.320859685153137e-05, "loss": 0.031, "step": 117620 }, { "epoch": 28.24, "learning_rate": 8.320591327489329e-05, "loss": 0.0364, "step": 117630 }, { "epoch": 28.25, "learning_rate": 8.320322952711164e-05, "loss": 0.028, "step": 117640 }, { "epoch": 28.25, "learning_rate": 8.320054560820028e-05, "loss": 0.0352, "step": 117650 }, { "epoch": 28.25, "learning_rate": 8.319786151817301e-05, "loss": 0.037, "step": 117660 }, { "epoch": 28.25, "learning_rate": 8.319517725704371e-05, "loss": 0.0198, "step": 117670 }, { "epoch": 28.26, "learning_rate": 8.319249282482617e-05, "loss": 0.0174, "step": 117680 }, { "epoch": 28.26, "learning_rate": 8.318980822153423e-05, "loss": 0.0437, "step": 117690 }, { "epoch": 28.26, "learning_rate": 8.318712344718179e-05, "loss": 0.0423, "step": 117700 }, { "epoch": 28.26, "learning_rate": 8.31844385017826e-05, "loss": 0.0283, "step": 117710 }, { "epoch": 28.26, "learning_rate": 8.318175338535055e-05, "loss": 0.0455, "step": 117720 }, { "epoch": 28.27, "learning_rate": 8.317906809789946e-05, "loss": 0.0496, "step": 117730 }, { "epoch": 28.27, "learning_rate": 8.317638263944318e-05, "loss": 0.0335, "step": 117740 }, { "epoch": 28.27, "learning_rate": 8.317369700999555e-05, "loss": 0.033, "step": 117750 }, { "epoch": 28.27, "learning_rate": 8.317101120957039e-05, "loss": 0.0407, "step": 117760 }, { "epoch": 28.28, "learning_rate": 8.316832523818159e-05, "loss": 0.0339, "step": 117770 }, { "epoch": 28.28, "learning_rate": 8.316563909584295e-05, "loss": 0.0364, "step": 117780 }, { "epoch": 28.28, "learning_rate": 8.316295278256831e-05, "loss": 0.0323, "step": 117790 }, { "epoch": 28.28, "learning_rate": 8.316026629837156e-05, "loss": 0.0319, "step": 117800 }, { "epoch": 28.28, "learning_rate": 8.315757964326651e-05, "loss": 0.0226, "step": 117810 }, { "epoch": 28.29, "learning_rate": 8.315489281726701e-05, "loss": 0.0301, "step": 117820 }, { "epoch": 28.29, "learning_rate": 8.315220582038693e-05, "loss": 0.0423, "step": 117830 }, { "epoch": 28.29, "learning_rate": 8.31495186526401e-05, "loss": 0.0462, "step": 117840 }, { "epoch": 28.29, "learning_rate": 8.314683131404037e-05, "loss": 0.0412, "step": 117850 }, { "epoch": 28.3, "learning_rate": 8.31441438046016e-05, "loss": 0.0409, "step": 117860 }, { "epoch": 28.3, "learning_rate": 8.314145612433764e-05, "loss": 0.0338, "step": 117870 }, { "epoch": 28.3, "learning_rate": 8.313876827326233e-05, "loss": 0.0292, "step": 117880 }, { "epoch": 28.3, "learning_rate": 8.313608025138953e-05, "loss": 0.0341, "step": 117890 }, { "epoch": 28.31, "learning_rate": 8.31333920587331e-05, "loss": 0.0239, "step": 117900 }, { "epoch": 28.31, "learning_rate": 8.313070369530687e-05, "loss": 0.0278, "step": 117910 }, { "epoch": 28.31, "learning_rate": 8.312801516112474e-05, "loss": 0.0429, "step": 117920 }, { "epoch": 28.31, "learning_rate": 8.312532645620053e-05, "loss": 0.0373, "step": 117930 }, { "epoch": 28.31, "learning_rate": 8.312263758054813e-05, "loss": 0.0239, "step": 117940 }, { "epoch": 28.32, "learning_rate": 8.311994853418136e-05, "loss": 0.0178, "step": 117950 }, { "epoch": 28.32, "learning_rate": 8.31172593171141e-05, "loss": 0.0218, "step": 117960 }, { "epoch": 28.32, "learning_rate": 8.311456992936022e-05, "loss": 0.0396, "step": 117970 }, { "epoch": 28.32, "learning_rate": 8.311188037093355e-05, "loss": 0.0492, "step": 117980 }, { "epoch": 28.33, "learning_rate": 8.3109190641848e-05, "loss": 0.0186, "step": 117990 }, { "epoch": 28.33, "learning_rate": 8.31065007421174e-05, "loss": 0.0328, "step": 118000 }, { "epoch": 28.33, "learning_rate": 8.310381067175559e-05, "loss": 0.0445, "step": 118010 }, { "epoch": 28.33, "learning_rate": 8.310112043077649e-05, "loss": 0.0206, "step": 118020 }, { "epoch": 28.34, "learning_rate": 8.309843001919393e-05, "loss": 0.0238, "step": 118030 }, { "epoch": 28.34, "learning_rate": 8.309573943702177e-05, "loss": 0.0273, "step": 118040 }, { "epoch": 28.34, "learning_rate": 8.309304868427392e-05, "loss": 0.0302, "step": 118050 }, { "epoch": 28.34, "learning_rate": 8.309035776096421e-05, "loss": 0.03, "step": 118060 }, { "epoch": 28.34, "learning_rate": 8.308766666710651e-05, "loss": 0.0159, "step": 118070 }, { "epoch": 28.35, "learning_rate": 8.308497540271471e-05, "loss": 0.0346, "step": 118080 }, { "epoch": 28.35, "learning_rate": 8.308228396780267e-05, "loss": 0.0476, "step": 118090 }, { "epoch": 28.35, "learning_rate": 8.307959236238425e-05, "loss": 0.0214, "step": 118100 }, { "epoch": 28.35, "learning_rate": 8.307690058647335e-05, "loss": 0.0327, "step": 118110 }, { "epoch": 28.36, "learning_rate": 8.307420864008382e-05, "loss": 0.0244, "step": 118120 }, { "epoch": 28.36, "learning_rate": 8.307151652322955e-05, "loss": 0.0274, "step": 118130 }, { "epoch": 28.36, "learning_rate": 8.30688242359244e-05, "loss": 0.0113, "step": 118140 }, { "epoch": 28.36, "learning_rate": 8.306613177818226e-05, "loss": 0.0354, "step": 118150 }, { "epoch": 28.36, "learning_rate": 8.306343915001697e-05, "loss": 0.0228, "step": 118160 }, { "epoch": 28.37, "learning_rate": 8.306074635144248e-05, "loss": 0.0184, "step": 118170 }, { "epoch": 28.37, "learning_rate": 8.30580533824726e-05, "loss": 0.0377, "step": 118180 }, { "epoch": 28.37, "learning_rate": 8.305536024312125e-05, "loss": 0.0235, "step": 118190 }, { "epoch": 28.37, "learning_rate": 8.305266693340231e-05, "loss": 0.0483, "step": 118200 }, { "epoch": 28.38, "learning_rate": 8.30499734533296e-05, "loss": 0.0331, "step": 118210 }, { "epoch": 28.38, "learning_rate": 8.30472798029171e-05, "loss": 0.029, "step": 118220 }, { "epoch": 28.38, "learning_rate": 8.304458598217862e-05, "loss": 0.0401, "step": 118230 }, { "epoch": 28.38, "learning_rate": 8.304189199112808e-05, "loss": 0.0214, "step": 118240 }, { "epoch": 28.39, "learning_rate": 8.303919782977933e-05, "loss": 0.0266, "step": 118250 }, { "epoch": 28.39, "learning_rate": 8.303650349814632e-05, "loss": 0.0172, "step": 118260 }, { "epoch": 28.39, "learning_rate": 8.303380899624286e-05, "loss": 0.036, "step": 118270 }, { "epoch": 28.39, "learning_rate": 8.303111432408289e-05, "loss": 0.0476, "step": 118280 }, { "epoch": 28.39, "learning_rate": 8.302841948168026e-05, "loss": 0.0357, "step": 118290 }, { "epoch": 28.4, "learning_rate": 8.302572446904888e-05, "loss": 0.0336, "step": 118300 }, { "epoch": 28.4, "learning_rate": 8.302302928620268e-05, "loss": 0.0316, "step": 118310 }, { "epoch": 28.4, "learning_rate": 8.302033393315548e-05, "loss": 0.0316, "step": 118320 }, { "epoch": 28.4, "learning_rate": 8.301763840992118e-05, "loss": 0.0367, "step": 118330 }, { "epoch": 28.41, "learning_rate": 8.301494271651373e-05, "loss": 0.0301, "step": 118340 }, { "epoch": 28.41, "learning_rate": 8.301224685294699e-05, "loss": 0.0208, "step": 118350 }, { "epoch": 28.41, "learning_rate": 8.300955081923483e-05, "loss": 0.0204, "step": 118360 }, { "epoch": 28.41, "learning_rate": 8.300685461539119e-05, "loss": 0.0378, "step": 118370 }, { "epoch": 28.41, "learning_rate": 8.300415824142994e-05, "loss": 0.0271, "step": 118380 }, { "epoch": 28.42, "learning_rate": 8.300146169736498e-05, "loss": 0.033, "step": 118390 }, { "epoch": 28.42, "learning_rate": 8.299876498321022e-05, "loss": 0.0161, "step": 118400 }, { "epoch": 28.42, "learning_rate": 8.299606809897954e-05, "loss": 0.023, "step": 118410 }, { "epoch": 28.42, "learning_rate": 8.299337104468685e-05, "loss": 0.0296, "step": 118420 }, { "epoch": 28.43, "learning_rate": 8.299067382034604e-05, "loss": 0.0424, "step": 118430 }, { "epoch": 28.43, "learning_rate": 8.298797642597105e-05, "loss": 0.0163, "step": 118440 }, { "epoch": 28.43, "learning_rate": 8.298527886157572e-05, "loss": 0.03, "step": 118450 }, { "epoch": 28.43, "learning_rate": 8.298258112717401e-05, "loss": 0.0325, "step": 118460 }, { "epoch": 28.44, "learning_rate": 8.297988322277979e-05, "loss": 0.019, "step": 118470 }, { "epoch": 28.44, "learning_rate": 8.297718514840698e-05, "loss": 0.0337, "step": 118480 }, { "epoch": 28.44, "learning_rate": 8.29744869040695e-05, "loss": 0.0252, "step": 118490 }, { "epoch": 28.44, "learning_rate": 8.297178848978121e-05, "loss": 0.0294, "step": 118500 }, { "epoch": 28.44, "learning_rate": 8.296908990555605e-05, "loss": 0.0211, "step": 118510 }, { "epoch": 28.45, "learning_rate": 8.296639115140794e-05, "loss": 0.0244, "step": 118520 }, { "epoch": 28.45, "learning_rate": 8.296369222735077e-05, "loss": 0.0242, "step": 118530 }, { "epoch": 28.45, "learning_rate": 8.296099313339844e-05, "loss": 0.0301, "step": 118540 }, { "epoch": 28.45, "learning_rate": 8.295829386956489e-05, "loss": 0.0342, "step": 118550 }, { "epoch": 28.46, "learning_rate": 8.295559443586402e-05, "loss": 0.0274, "step": 118560 }, { "epoch": 28.46, "learning_rate": 8.295289483230975e-05, "loss": 0.0242, "step": 118570 }, { "epoch": 28.46, "learning_rate": 8.295019505891596e-05, "loss": 0.0326, "step": 118580 }, { "epoch": 28.46, "learning_rate": 8.294749511569659e-05, "loss": 0.0446, "step": 118590 }, { "epoch": 28.47, "learning_rate": 8.294479500266557e-05, "loss": 0.0326, "step": 118600 }, { "epoch": 28.47, "learning_rate": 8.29420947198368e-05, "loss": 0.0431, "step": 118610 }, { "epoch": 28.47, "learning_rate": 8.293939426722419e-05, "loss": 0.0313, "step": 118620 }, { "epoch": 28.47, "learning_rate": 8.293669364484169e-05, "loss": 0.0396, "step": 118630 }, { "epoch": 28.47, "learning_rate": 8.293399285270317e-05, "loss": 0.0281, "step": 118640 }, { "epoch": 28.48, "learning_rate": 8.293129189082258e-05, "loss": 0.0276, "step": 118650 }, { "epoch": 28.48, "learning_rate": 8.292859075921385e-05, "loss": 0.0442, "step": 118660 }, { "epoch": 28.48, "learning_rate": 8.292588945789085e-05, "loss": 0.0307, "step": 118670 }, { "epoch": 28.48, "learning_rate": 8.292318798686757e-05, "loss": 0.031, "step": 118680 }, { "epoch": 28.49, "learning_rate": 8.292048634615791e-05, "loss": 0.0303, "step": 118690 }, { "epoch": 28.49, "learning_rate": 8.291778453577579e-05, "loss": 0.0488, "step": 118700 }, { "epoch": 28.49, "learning_rate": 8.291508255573512e-05, "loss": 0.0357, "step": 118710 }, { "epoch": 28.49, "learning_rate": 8.291238040604984e-05, "loss": 0.0239, "step": 118720 }, { "epoch": 28.49, "learning_rate": 8.290967808673387e-05, "loss": 0.0239, "step": 118730 }, { "epoch": 28.5, "learning_rate": 8.290697559780116e-05, "loss": 0.0152, "step": 118740 }, { "epoch": 28.5, "learning_rate": 8.290427293926562e-05, "loss": 0.0411, "step": 118750 }, { "epoch": 28.5, "learning_rate": 8.290157011114117e-05, "loss": 0.0498, "step": 118760 }, { "epoch": 28.5, "learning_rate": 8.289886711344176e-05, "loss": 0.0339, "step": 118770 }, { "epoch": 28.51, "learning_rate": 8.289616394618131e-05, "loss": 0.0376, "step": 118780 }, { "epoch": 28.51, "learning_rate": 8.289346060937377e-05, "loss": 0.0265, "step": 118790 }, { "epoch": 28.51, "learning_rate": 8.289075710303305e-05, "loss": 0.0222, "step": 118800 }, { "epoch": 28.51, "learning_rate": 8.288805342717308e-05, "loss": 0.0321, "step": 118810 }, { "epoch": 28.52, "learning_rate": 8.288534958180783e-05, "loss": 0.0366, "step": 118820 }, { "epoch": 28.52, "learning_rate": 8.28826455669512e-05, "loss": 0.0387, "step": 118830 }, { "epoch": 28.52, "learning_rate": 8.287994138261714e-05, "loss": 0.0383, "step": 118840 }, { "epoch": 28.52, "learning_rate": 8.28772370288196e-05, "loss": 0.0364, "step": 118850 }, { "epoch": 28.52, "learning_rate": 8.28745325055725e-05, "loss": 0.0429, "step": 118860 }, { "epoch": 28.53, "learning_rate": 8.287182781288978e-05, "loss": 0.0435, "step": 118870 }, { "epoch": 28.53, "learning_rate": 8.286912295078539e-05, "loss": 0.0421, "step": 118880 }, { "epoch": 28.53, "learning_rate": 8.286641791927326e-05, "loss": 0.0327, "step": 118890 }, { "epoch": 28.53, "learning_rate": 8.286371271836732e-05, "loss": 0.0381, "step": 118900 }, { "epoch": 28.54, "learning_rate": 8.286100734808155e-05, "loss": 0.0584, "step": 118910 }, { "epoch": 28.54, "learning_rate": 8.285830180842989e-05, "loss": 0.0457, "step": 118920 }, { "epoch": 28.54, "learning_rate": 8.285559609942624e-05, "loss": 0.0509, "step": 118930 }, { "epoch": 28.54, "learning_rate": 8.285289022108458e-05, "loss": 0.0332, "step": 118940 }, { "epoch": 28.55, "learning_rate": 8.285018417341886e-05, "loss": 0.0619, "step": 118950 }, { "epoch": 28.55, "learning_rate": 8.284747795644301e-05, "loss": 0.0358, "step": 118960 }, { "epoch": 28.55, "learning_rate": 8.284477157017096e-05, "loss": 0.037, "step": 118970 }, { "epoch": 28.55, "learning_rate": 8.284206501461671e-05, "loss": 0.0553, "step": 118980 }, { "epoch": 28.55, "learning_rate": 8.283935828979419e-05, "loss": 0.0455, "step": 118990 }, { "epoch": 28.56, "learning_rate": 8.283665139571732e-05, "loss": 0.0311, "step": 119000 }, { "epoch": 28.56, "learning_rate": 8.283394433240009e-05, "loss": 0.0409, "step": 119010 }, { "epoch": 28.56, "learning_rate": 8.283123709985642e-05, "loss": 0.0584, "step": 119020 }, { "epoch": 28.56, "learning_rate": 8.28285296981003e-05, "loss": 0.0514, "step": 119030 }, { "epoch": 28.57, "learning_rate": 8.282582212714565e-05, "loss": 0.0412, "step": 119040 }, { "epoch": 28.57, "learning_rate": 8.282311438700643e-05, "loss": 0.0421, "step": 119050 }, { "epoch": 28.57, "learning_rate": 8.282040647769665e-05, "loss": 0.0538, "step": 119060 }, { "epoch": 28.57, "learning_rate": 8.281769839923017e-05, "loss": 0.0391, "step": 119070 }, { "epoch": 28.57, "learning_rate": 8.281499015162102e-05, "loss": 0.0327, "step": 119080 }, { "epoch": 28.58, "learning_rate": 8.281228173488314e-05, "loss": 0.0271, "step": 119090 }, { "epoch": 28.58, "learning_rate": 8.280957314903046e-05, "loss": 0.0403, "step": 119100 }, { "epoch": 28.58, "learning_rate": 8.280686439407699e-05, "loss": 0.0214, "step": 119110 }, { "epoch": 28.58, "learning_rate": 8.280415547003665e-05, "loss": 0.0481, "step": 119120 }, { "epoch": 28.59, "learning_rate": 8.280144637692344e-05, "loss": 0.0296, "step": 119130 }, { "epoch": 28.59, "learning_rate": 8.279873711475128e-05, "loss": 0.037, "step": 119140 }, { "epoch": 28.59, "learning_rate": 8.279602768353417e-05, "loss": 0.0283, "step": 119150 }, { "epoch": 28.59, "learning_rate": 8.279331808328605e-05, "loss": 0.0333, "step": 119160 }, { "epoch": 28.6, "learning_rate": 8.27906083140209e-05, "loss": 0.0363, "step": 119170 }, { "epoch": 28.6, "learning_rate": 8.278789837575267e-05, "loss": 0.0433, "step": 119180 }, { "epoch": 28.6, "learning_rate": 8.278518826849534e-05, "loss": 0.036, "step": 119190 }, { "epoch": 28.6, "learning_rate": 8.278247799226291e-05, "loss": 0.0381, "step": 119200 }, { "epoch": 28.6, "learning_rate": 8.277976754706928e-05, "loss": 0.0453, "step": 119210 }, { "epoch": 28.61, "learning_rate": 8.277705693292845e-05, "loss": 0.0354, "step": 119220 }, { "epoch": 28.61, "learning_rate": 8.27743461498544e-05, "loss": 0.0481, "step": 119230 }, { "epoch": 28.61, "learning_rate": 8.27716351978611e-05, "loss": 0.0169, "step": 119240 }, { "epoch": 28.61, "learning_rate": 8.276892407696252e-05, "loss": 0.0466, "step": 119250 }, { "epoch": 28.62, "learning_rate": 8.276621278717263e-05, "loss": 0.0395, "step": 119260 }, { "epoch": 28.62, "learning_rate": 8.276350132850541e-05, "loss": 0.0441, "step": 119270 }, { "epoch": 28.62, "learning_rate": 8.276078970097483e-05, "loss": 0.0565, "step": 119280 }, { "epoch": 28.62, "learning_rate": 8.275807790459487e-05, "loss": 0.0362, "step": 119290 }, { "epoch": 28.63, "learning_rate": 8.27553659393795e-05, "loss": 0.0287, "step": 119300 }, { "epoch": 28.63, "learning_rate": 8.275265380534268e-05, "loss": 0.0418, "step": 119310 }, { "epoch": 28.63, "learning_rate": 8.274994150249843e-05, "loss": 0.0262, "step": 119320 }, { "epoch": 28.63, "learning_rate": 8.27472290308607e-05, "loss": 0.041, "step": 119330 }, { "epoch": 28.63, "learning_rate": 8.274451639044347e-05, "loss": 0.0596, "step": 119340 }, { "epoch": 28.64, "learning_rate": 8.274180358126076e-05, "loss": 0.052, "step": 119350 }, { "epoch": 28.64, "learning_rate": 8.273909060332649e-05, "loss": 0.029, "step": 119360 }, { "epoch": 28.64, "learning_rate": 8.273637745665468e-05, "loss": 0.0197, "step": 119370 }, { "epoch": 28.64, "learning_rate": 8.273366414125932e-05, "loss": 0.0452, "step": 119380 }, { "epoch": 28.65, "learning_rate": 8.273095065715435e-05, "loss": 0.047, "step": 119390 }, { "epoch": 28.65, "learning_rate": 8.272823700435382e-05, "loss": 0.0432, "step": 119400 }, { "epoch": 28.65, "learning_rate": 8.272552318287165e-05, "loss": 0.0191, "step": 119410 }, { "epoch": 28.65, "learning_rate": 8.27228091927219e-05, "loss": 0.0398, "step": 119420 }, { "epoch": 28.65, "learning_rate": 8.272009503391849e-05, "loss": 0.0272, "step": 119430 }, { "epoch": 28.66, "learning_rate": 8.271738070647546e-05, "loss": 0.036, "step": 119440 }, { "epoch": 28.66, "learning_rate": 8.271466621040675e-05, "loss": 0.0316, "step": 119450 }, { "epoch": 28.66, "learning_rate": 8.271195154572638e-05, "loss": 0.0377, "step": 119460 }, { "epoch": 28.66, "learning_rate": 8.270923671244835e-05, "loss": 0.0336, "step": 119470 }, { "epoch": 28.67, "learning_rate": 8.270652171058664e-05, "loss": 0.0469, "step": 119480 }, { "epoch": 28.67, "learning_rate": 8.270380654015524e-05, "loss": 0.0532, "step": 119490 }, { "epoch": 28.67, "learning_rate": 8.270109120116815e-05, "loss": 0.0328, "step": 119500 }, { "epoch": 28.67, "learning_rate": 8.269837569363937e-05, "loss": 0.0247, "step": 119510 }, { "epoch": 28.68, "learning_rate": 8.269566001758287e-05, "loss": 0.0411, "step": 119520 }, { "epoch": 28.68, "learning_rate": 8.269294417301268e-05, "loss": 0.03, "step": 119530 }, { "epoch": 28.68, "learning_rate": 8.269022815994276e-05, "loss": 0.0636, "step": 119540 }, { "epoch": 28.68, "learning_rate": 8.268751197838715e-05, "loss": 0.0375, "step": 119550 }, { "epoch": 28.68, "learning_rate": 8.268479562835984e-05, "loss": 0.0225, "step": 119560 }, { "epoch": 28.69, "learning_rate": 8.26820791098748e-05, "loss": 0.0237, "step": 119570 }, { "epoch": 28.69, "learning_rate": 8.267936242294606e-05, "loss": 0.0414, "step": 119580 }, { "epoch": 28.69, "learning_rate": 8.26766455675876e-05, "loss": 0.0328, "step": 119590 }, { "epoch": 28.69, "learning_rate": 8.267392854381347e-05, "loss": 0.0527, "step": 119600 }, { "epoch": 28.7, "learning_rate": 8.26712113516376e-05, "loss": 0.0285, "step": 119610 }, { "epoch": 28.7, "learning_rate": 8.266849399107405e-05, "loss": 0.0296, "step": 119620 }, { "epoch": 28.7, "learning_rate": 8.266577646213682e-05, "loss": 0.0401, "step": 119630 }, { "epoch": 28.7, "learning_rate": 8.266305876483988e-05, "loss": 0.0667, "step": 119640 }, { "epoch": 28.71, "learning_rate": 8.266034089919728e-05, "loss": 0.0351, "step": 119650 }, { "epoch": 28.71, "learning_rate": 8.2657622865223e-05, "loss": 0.0308, "step": 119660 }, { "epoch": 28.71, "learning_rate": 8.265490466293107e-05, "loss": 0.0493, "step": 119670 }, { "epoch": 28.71, "learning_rate": 8.265218629233549e-05, "loss": 0.0338, "step": 119680 }, { "epoch": 28.71, "learning_rate": 8.264946775345026e-05, "loss": 0.0435, "step": 119690 }, { "epoch": 28.72, "learning_rate": 8.26467490462894e-05, "loss": 0.0379, "step": 119700 }, { "epoch": 28.72, "learning_rate": 8.264403017086692e-05, "loss": 0.0417, "step": 119710 }, { "epoch": 28.72, "learning_rate": 8.264131112719685e-05, "loss": 0.0344, "step": 119720 }, { "epoch": 28.72, "learning_rate": 8.263859191529318e-05, "loss": 0.0682, "step": 119730 }, { "epoch": 28.73, "learning_rate": 8.263587253516993e-05, "loss": 0.0362, "step": 119740 }, { "epoch": 28.73, "learning_rate": 8.263315298684114e-05, "loss": 0.0494, "step": 119750 }, { "epoch": 28.73, "learning_rate": 8.263043327032078e-05, "loss": 0.0394, "step": 119760 }, { "epoch": 28.73, "learning_rate": 8.262771338562291e-05, "loss": 0.037, "step": 119770 }, { "epoch": 28.73, "learning_rate": 8.262499333276152e-05, "loss": 0.0355, "step": 119780 }, { "epoch": 28.74, "learning_rate": 8.262227311175066e-05, "loss": 0.0313, "step": 119790 }, { "epoch": 28.74, "learning_rate": 8.261955272260432e-05, "loss": 0.0526, "step": 119800 }, { "epoch": 28.74, "learning_rate": 8.261683216533653e-05, "loss": 0.0502, "step": 119810 }, { "epoch": 28.74, "learning_rate": 8.261411143996132e-05, "loss": 0.039, "step": 119820 }, { "epoch": 28.75, "learning_rate": 8.26113905464927e-05, "loss": 0.0326, "step": 119830 }, { "epoch": 28.75, "learning_rate": 8.260866948494472e-05, "loss": 0.0397, "step": 119840 }, { "epoch": 28.75, "learning_rate": 8.260594825533137e-05, "loss": 0.0459, "step": 119850 }, { "epoch": 28.75, "learning_rate": 8.260322685766668e-05, "loss": 0.0385, "step": 119860 }, { "epoch": 28.76, "learning_rate": 8.26005052919647e-05, "loss": 0.0317, "step": 119870 }, { "epoch": 28.76, "learning_rate": 8.259778355823943e-05, "loss": 0.0456, "step": 119880 }, { "epoch": 28.76, "learning_rate": 8.259506165650494e-05, "loss": 0.0331, "step": 119890 }, { "epoch": 28.76, "learning_rate": 8.259233958677522e-05, "loss": 0.0359, "step": 119900 }, { "epoch": 28.76, "learning_rate": 8.258961734906429e-05, "loss": 0.0258, "step": 119910 }, { "epoch": 28.77, "learning_rate": 8.258689494338622e-05, "loss": 0.0322, "step": 119920 }, { "epoch": 28.77, "learning_rate": 8.258417236975499e-05, "loss": 0.0275, "step": 119930 }, { "epoch": 28.77, "learning_rate": 8.25814496281847e-05, "loss": 0.0366, "step": 119940 }, { "epoch": 28.77, "learning_rate": 8.257872671868933e-05, "loss": 0.0278, "step": 119950 }, { "epoch": 28.78, "learning_rate": 8.257600364128293e-05, "loss": 0.0216, "step": 119960 }, { "epoch": 28.78, "learning_rate": 8.257328039597953e-05, "loss": 0.0211, "step": 119970 }, { "epoch": 28.78, "learning_rate": 8.257055698279318e-05, "loss": 0.0396, "step": 119980 }, { "epoch": 28.78, "learning_rate": 8.25678334017379e-05, "loss": 0.0284, "step": 119990 }, { "epoch": 28.79, "learning_rate": 8.256510965282776e-05, "loss": 0.0421, "step": 120000 }, { "epoch": 28.79, "learning_rate": 8.256238573607673e-05, "loss": 0.0418, "step": 120010 }, { "epoch": 28.79, "learning_rate": 8.255966165149892e-05, "loss": 0.0421, "step": 120020 }, { "epoch": 28.79, "learning_rate": 8.255693739910833e-05, "loss": 0.0515, "step": 120030 }, { "epoch": 28.79, "learning_rate": 8.255421297891902e-05, "loss": 0.0485, "step": 120040 }, { "epoch": 28.8, "learning_rate": 8.255148839094503e-05, "loss": 0.0386, "step": 120050 }, { "epoch": 28.8, "learning_rate": 8.254876363520037e-05, "loss": 0.0449, "step": 120060 }, { "epoch": 28.8, "learning_rate": 8.254603871169915e-05, "loss": 0.0376, "step": 120070 }, { "epoch": 28.8, "learning_rate": 8.254331362045534e-05, "loss": 0.0425, "step": 120080 }, { "epoch": 28.81, "learning_rate": 8.254058836148303e-05, "loss": 0.0221, "step": 120090 }, { "epoch": 28.81, "learning_rate": 8.253786293479626e-05, "loss": 0.0326, "step": 120100 }, { "epoch": 28.81, "learning_rate": 8.253513734040907e-05, "loss": 0.0267, "step": 120110 }, { "epoch": 28.81, "learning_rate": 8.253241157833552e-05, "loss": 0.0345, "step": 120120 }, { "epoch": 28.81, "learning_rate": 8.252968564858963e-05, "loss": 0.0288, "step": 120130 }, { "epoch": 28.82, "learning_rate": 8.252695955118547e-05, "loss": 0.0469, "step": 120140 }, { "epoch": 28.82, "learning_rate": 8.252423328613711e-05, "loss": 0.0209, "step": 120150 }, { "epoch": 28.82, "learning_rate": 8.252150685345857e-05, "loss": 0.0285, "step": 120160 }, { "epoch": 28.82, "learning_rate": 8.25187802531639e-05, "loss": 0.0428, "step": 120170 }, { "epoch": 28.83, "learning_rate": 8.251605348526717e-05, "loss": 0.0334, "step": 120180 }, { "epoch": 28.83, "learning_rate": 8.251332654978243e-05, "loss": 0.0397, "step": 120190 }, { "epoch": 28.83, "learning_rate": 8.251059944672373e-05, "loss": 0.0324, "step": 120200 }, { "epoch": 28.83, "learning_rate": 8.250787217610514e-05, "loss": 0.0517, "step": 120210 }, { "epoch": 28.84, "learning_rate": 8.250514473794069e-05, "loss": 0.0352, "step": 120220 }, { "epoch": 28.84, "learning_rate": 8.250241713224447e-05, "loss": 0.0255, "step": 120230 }, { "epoch": 28.84, "learning_rate": 8.249968935903051e-05, "loss": 0.0588, "step": 120240 }, { "epoch": 28.84, "learning_rate": 8.249696141831287e-05, "loss": 0.0279, "step": 120250 }, { "epoch": 28.84, "learning_rate": 8.249423331010564e-05, "loss": 0.0284, "step": 120260 }, { "epoch": 28.85, "learning_rate": 8.249150503442284e-05, "loss": 0.0436, "step": 120270 }, { "epoch": 28.85, "learning_rate": 8.248877659127858e-05, "loss": 0.0306, "step": 120280 }, { "epoch": 28.85, "learning_rate": 8.248604798068687e-05, "loss": 0.072, "step": 120290 }, { "epoch": 28.85, "learning_rate": 8.24833192026618e-05, "loss": 0.0244, "step": 120300 }, { "epoch": 28.86, "learning_rate": 8.248059025721742e-05, "loss": 0.0248, "step": 120310 }, { "epoch": 28.86, "learning_rate": 8.247786114436783e-05, "loss": 0.0258, "step": 120320 }, { "epoch": 28.86, "learning_rate": 8.247513186412705e-05, "loss": 0.0289, "step": 120330 }, { "epoch": 28.86, "learning_rate": 8.247240241650918e-05, "loss": 0.0305, "step": 120340 }, { "epoch": 28.87, "learning_rate": 8.246967280152829e-05, "loss": 0.0309, "step": 120350 }, { "epoch": 28.87, "learning_rate": 8.246694301919842e-05, "loss": 0.0323, "step": 120360 }, { "epoch": 28.87, "learning_rate": 8.246421306953366e-05, "loss": 0.0381, "step": 120370 }, { "epoch": 28.87, "learning_rate": 8.246148295254807e-05, "loss": 0.0266, "step": 120380 }, { "epoch": 28.87, "learning_rate": 8.245875266825573e-05, "loss": 0.038, "step": 120390 }, { "epoch": 28.88, "learning_rate": 8.24560222166707e-05, "loss": 0.0214, "step": 120400 }, { "epoch": 28.88, "learning_rate": 8.245329159780706e-05, "loss": 0.0214, "step": 120410 }, { "epoch": 28.88, "learning_rate": 8.245056081167889e-05, "loss": 0.0259, "step": 120420 }, { "epoch": 28.88, "learning_rate": 8.244782985830026e-05, "loss": 0.016, "step": 120430 }, { "epoch": 28.89, "learning_rate": 8.244509873768524e-05, "loss": 0.0624, "step": 120440 }, { "epoch": 28.89, "learning_rate": 8.24423674498479e-05, "loss": 0.0293, "step": 120450 }, { "epoch": 28.89, "learning_rate": 8.243963599480233e-05, "loss": 0.0382, "step": 120460 }, { "epoch": 28.89, "learning_rate": 8.243690437256262e-05, "loss": 0.0274, "step": 120470 }, { "epoch": 28.89, "learning_rate": 8.243417258314282e-05, "loss": 0.0444, "step": 120480 }, { "epoch": 28.9, "learning_rate": 8.243144062655703e-05, "loss": 0.0206, "step": 120490 }, { "epoch": 28.9, "learning_rate": 8.242870850281932e-05, "loss": 0.0231, "step": 120500 }, { "epoch": 28.9, "learning_rate": 8.242597621194379e-05, "loss": 0.0409, "step": 120510 }, { "epoch": 28.9, "learning_rate": 8.242324375394449e-05, "loss": 0.0359, "step": 120520 }, { "epoch": 28.91, "learning_rate": 8.242051112883553e-05, "loss": 0.032, "step": 120530 }, { "epoch": 28.91, "learning_rate": 8.241777833663098e-05, "loss": 0.038, "step": 120540 }, { "epoch": 28.91, "learning_rate": 8.241504537734492e-05, "loss": 0.0355, "step": 120550 }, { "epoch": 28.91, "learning_rate": 8.241231225099146e-05, "loss": 0.023, "step": 120560 }, { "epoch": 28.92, "learning_rate": 8.240957895758468e-05, "loss": 0.0356, "step": 120570 }, { "epoch": 28.92, "learning_rate": 8.240684549713863e-05, "loss": 0.0297, "step": 120580 }, { "epoch": 28.92, "learning_rate": 8.240411186966745e-05, "loss": 0.0504, "step": 120590 }, { "epoch": 28.92, "learning_rate": 8.24013780751852e-05, "loss": 0.0218, "step": 120600 }, { "epoch": 28.92, "learning_rate": 8.239864411370597e-05, "loss": 0.0735, "step": 120610 }, { "epoch": 28.93, "learning_rate": 8.239590998524387e-05, "loss": 0.0271, "step": 120620 }, { "epoch": 28.93, "learning_rate": 8.239317568981297e-05, "loss": 0.0326, "step": 120630 }, { "epoch": 28.93, "learning_rate": 8.239044122742739e-05, "loss": 0.0314, "step": 120640 }, { "epoch": 28.93, "learning_rate": 8.238770659810118e-05, "loss": 0.021, "step": 120650 }, { "epoch": 28.94, "learning_rate": 8.238497180184848e-05, "loss": 0.0297, "step": 120660 }, { "epoch": 28.94, "learning_rate": 8.238223683868335e-05, "loss": 0.0296, "step": 120670 }, { "epoch": 28.94, "learning_rate": 8.23795017086199e-05, "loss": 0.0311, "step": 120680 }, { "epoch": 28.94, "learning_rate": 8.237676641167223e-05, "loss": 0.0539, "step": 120690 }, { "epoch": 28.95, "learning_rate": 8.237403094785444e-05, "loss": 0.0354, "step": 120700 }, { "epoch": 28.95, "learning_rate": 8.237129531718062e-05, "loss": 0.0338, "step": 120710 }, { "epoch": 28.95, "learning_rate": 8.236855951966487e-05, "loss": 0.0404, "step": 120720 }, { "epoch": 29.0, "learning_rate": 8.236582355532131e-05, "loss": 0.0235, "step": 120730 }, { "epoch": 29.0, "learning_rate": 8.236308742416402e-05, "loss": 0.0293, "step": 120740 }, { "epoch": 29.01, "learning_rate": 8.23603511262071e-05, "loss": 0.0454, "step": 120750 }, { "epoch": 29.01, "learning_rate": 8.235761466146465e-05, "loss": 0.0364, "step": 120760 }, { "epoch": 29.01, "learning_rate": 8.23548780299508e-05, "loss": 0.0228, "step": 120770 }, { "epoch": 29.01, "learning_rate": 8.235214123167963e-05, "loss": 0.042, "step": 120780 }, { "epoch": 29.01, "learning_rate": 8.234940426666526e-05, "loss": 0.0342, "step": 120790 }, { "epoch": 29.02, "learning_rate": 8.234666713492178e-05, "loss": 0.0342, "step": 120800 }, { "epoch": 29.02, "learning_rate": 8.234392983646331e-05, "loss": 0.0244, "step": 120810 }, { "epoch": 29.02, "learning_rate": 8.234119237130395e-05, "loss": 0.0523, "step": 120820 }, { "epoch": 29.02, "learning_rate": 8.233845473945782e-05, "loss": 0.0221, "step": 120830 }, { "epoch": 29.03, "learning_rate": 8.233571694093905e-05, "loss": 0.0222, "step": 120840 }, { "epoch": 29.03, "learning_rate": 8.233297897576169e-05, "loss": 0.0439, "step": 120850 }, { "epoch": 29.03, "learning_rate": 8.23302408439399e-05, "loss": 0.0284, "step": 120860 }, { "epoch": 29.03, "learning_rate": 8.232750254548778e-05, "loss": 0.0375, "step": 120870 }, { "epoch": 29.03, "learning_rate": 8.232476408041943e-05, "loss": 0.0389, "step": 120880 }, { "epoch": 29.04, "learning_rate": 8.232202544874899e-05, "loss": 0.0249, "step": 120890 }, { "epoch": 29.04, "learning_rate": 8.231928665049056e-05, "loss": 0.0477, "step": 120900 }, { "epoch": 29.04, "learning_rate": 8.231654768565823e-05, "loss": 0.0416, "step": 120910 }, { "epoch": 29.04, "learning_rate": 8.231380855426617e-05, "loss": 0.0283, "step": 120920 }, { "epoch": 29.05, "learning_rate": 8.231106925632847e-05, "loss": 0.0323, "step": 120930 }, { "epoch": 29.05, "learning_rate": 8.230832979185924e-05, "loss": 0.0297, "step": 120940 }, { "epoch": 29.05, "learning_rate": 8.23055901608726e-05, "loss": 0.0123, "step": 120950 }, { "epoch": 29.05, "learning_rate": 8.23028503633827e-05, "loss": 0.0301, "step": 120960 }, { "epoch": 29.06, "learning_rate": 8.230011039940363e-05, "loss": 0.0644, "step": 120970 }, { "epoch": 29.06, "learning_rate": 8.229737026894952e-05, "loss": 0.0465, "step": 120980 }, { "epoch": 29.06, "learning_rate": 8.229462997203448e-05, "loss": 0.0355, "step": 120990 }, { "epoch": 29.06, "learning_rate": 8.229188950867268e-05, "loss": 0.0397, "step": 121000 }, { "epoch": 29.06, "learning_rate": 8.228914887887819e-05, "loss": 0.0338, "step": 121010 }, { "epoch": 29.07, "learning_rate": 8.228640808266514e-05, "loss": 0.0271, "step": 121020 }, { "epoch": 29.07, "learning_rate": 8.22836671200477e-05, "loss": 0.0302, "step": 121030 }, { "epoch": 29.07, "learning_rate": 8.228092599103995e-05, "loss": 0.0309, "step": 121040 }, { "epoch": 29.07, "learning_rate": 8.227818469565607e-05, "loss": 0.019, "step": 121050 }, { "epoch": 29.08, "learning_rate": 8.227544323391013e-05, "loss": 0.0259, "step": 121060 }, { "epoch": 29.08, "learning_rate": 8.227270160581629e-05, "loss": 0.0388, "step": 121070 }, { "epoch": 29.08, "learning_rate": 8.226995981138867e-05, "loss": 0.0308, "step": 121080 }, { "epoch": 29.08, "learning_rate": 8.226721785064142e-05, "loss": 0.0229, "step": 121090 }, { "epoch": 29.09, "learning_rate": 8.226447572358867e-05, "loss": 0.0356, "step": 121100 }, { "epoch": 29.09, "learning_rate": 8.226173343024452e-05, "loss": 0.0226, "step": 121110 }, { "epoch": 29.09, "learning_rate": 8.225899097062313e-05, "loss": 0.019, "step": 121120 }, { "epoch": 29.09, "learning_rate": 8.225624834473863e-05, "loss": 0.0199, "step": 121130 }, { "epoch": 29.09, "learning_rate": 8.225350555260516e-05, "loss": 0.0214, "step": 121140 }, { "epoch": 29.1, "learning_rate": 8.225076259423686e-05, "loss": 0.0194, "step": 121150 }, { "epoch": 29.1, "learning_rate": 8.224801946964785e-05, "loss": 0.0226, "step": 121160 }, { "epoch": 29.1, "learning_rate": 8.224527617885227e-05, "loss": 0.0279, "step": 121170 }, { "epoch": 29.1, "learning_rate": 8.224253272186429e-05, "loss": 0.0195, "step": 121180 }, { "epoch": 29.11, "learning_rate": 8.2239789098698e-05, "loss": 0.0149, "step": 121190 }, { "epoch": 29.11, "learning_rate": 8.22370453093676e-05, "loss": 0.0353, "step": 121200 }, { "epoch": 29.11, "learning_rate": 8.223430135388718e-05, "loss": 0.0206, "step": 121210 }, { "epoch": 29.11, "learning_rate": 8.22315572322709e-05, "loss": 0.0225, "step": 121220 }, { "epoch": 29.11, "learning_rate": 8.222881294453291e-05, "loss": 0.0206, "step": 121230 }, { "epoch": 29.12, "learning_rate": 8.222606849068735e-05, "loss": 0.026, "step": 121240 }, { "epoch": 29.12, "learning_rate": 8.222332387074836e-05, "loss": 0.0322, "step": 121250 }, { "epoch": 29.12, "learning_rate": 8.222057908473009e-05, "loss": 0.042, "step": 121260 }, { "epoch": 29.12, "learning_rate": 8.221783413264668e-05, "loss": 0.0387, "step": 121270 }, { "epoch": 29.13, "learning_rate": 8.221508901451228e-05, "loss": 0.0137, "step": 121280 }, { "epoch": 29.13, "learning_rate": 8.221234373034106e-05, "loss": 0.0581, "step": 121290 }, { "epoch": 29.13, "learning_rate": 8.220959828014714e-05, "loss": 0.0353, "step": 121300 }, { "epoch": 29.13, "learning_rate": 8.220685266394468e-05, "loss": 0.0229, "step": 121310 }, { "epoch": 29.14, "learning_rate": 8.220410688174784e-05, "loss": 0.0169, "step": 121320 }, { "epoch": 29.14, "learning_rate": 8.220136093357076e-05, "loss": 0.033, "step": 121330 }, { "epoch": 29.14, "learning_rate": 8.219861481942759e-05, "loss": 0.0209, "step": 121340 }, { "epoch": 29.14, "learning_rate": 8.21958685393325e-05, "loss": 0.0263, "step": 121350 }, { "epoch": 29.14, "learning_rate": 8.219312209329964e-05, "loss": 0.0184, "step": 121360 }, { "epoch": 29.15, "learning_rate": 8.219037548134315e-05, "loss": 0.0262, "step": 121370 }, { "epoch": 29.15, "learning_rate": 8.218762870347718e-05, "loss": 0.0265, "step": 121380 }, { "epoch": 29.15, "learning_rate": 8.218488175971593e-05, "loss": 0.0167, "step": 121390 }, { "epoch": 29.15, "learning_rate": 8.218213465007351e-05, "loss": 0.0222, "step": 121400 }, { "epoch": 29.16, "learning_rate": 8.21793873745641e-05, "loss": 0.0231, "step": 121410 }, { "epoch": 29.16, "learning_rate": 8.217663993320187e-05, "loss": 0.0256, "step": 121420 }, { "epoch": 29.16, "learning_rate": 8.217389232600097e-05, "loss": 0.0349, "step": 121430 }, { "epoch": 29.16, "learning_rate": 8.217114455297557e-05, "loss": 0.0205, "step": 121440 }, { "epoch": 29.17, "learning_rate": 8.21683966141398e-05, "loss": 0.0584, "step": 121450 }, { "epoch": 29.17, "learning_rate": 8.216564850950784e-05, "loss": 0.0237, "step": 121460 }, { "epoch": 29.17, "learning_rate": 8.216290023909387e-05, "loss": 0.0184, "step": 121470 }, { "epoch": 29.17, "learning_rate": 8.216015180291205e-05, "loss": 0.0191, "step": 121480 }, { "epoch": 29.17, "learning_rate": 8.215740320097653e-05, "loss": 0.0305, "step": 121490 }, { "epoch": 29.18, "learning_rate": 8.215465443330151e-05, "loss": 0.0431, "step": 121500 }, { "epoch": 29.18, "learning_rate": 8.215190549990109e-05, "loss": 0.0287, "step": 121510 }, { "epoch": 29.18, "learning_rate": 8.214915640078951e-05, "loss": 0.0324, "step": 121520 }, { "epoch": 29.18, "learning_rate": 8.214640713598089e-05, "loss": 0.0249, "step": 121530 }, { "epoch": 29.19, "learning_rate": 8.214365770548943e-05, "loss": 0.0311, "step": 121540 }, { "epoch": 29.19, "learning_rate": 8.214090810932928e-05, "loss": 0.0313, "step": 121550 }, { "epoch": 29.19, "learning_rate": 8.213815834751464e-05, "loss": 0.0157, "step": 121560 }, { "epoch": 29.19, "learning_rate": 8.213540842005965e-05, "loss": 0.0333, "step": 121570 }, { "epoch": 29.19, "learning_rate": 8.21326583269785e-05, "loss": 0.0406, "step": 121580 }, { "epoch": 29.2, "learning_rate": 8.212990806828536e-05, "loss": 0.0249, "step": 121590 }, { "epoch": 29.2, "learning_rate": 8.212715764399441e-05, "loss": 0.0312, "step": 121600 }, { "epoch": 29.2, "learning_rate": 8.212440705411981e-05, "loss": 0.014, "step": 121610 }, { "epoch": 29.2, "learning_rate": 8.212165629867575e-05, "loss": 0.0319, "step": 121620 }, { "epoch": 29.21, "learning_rate": 8.21189053776764e-05, "loss": 0.0242, "step": 121630 }, { "epoch": 29.21, "learning_rate": 8.211615429113598e-05, "loss": 0.0199, "step": 121640 }, { "epoch": 29.21, "learning_rate": 8.211340303906858e-05, "loss": 0.0175, "step": 121650 }, { "epoch": 29.21, "learning_rate": 8.211065162148846e-05, "loss": 0.0399, "step": 121660 }, { "epoch": 29.22, "learning_rate": 8.210790003840977e-05, "loss": 0.0221, "step": 121670 }, { "epoch": 29.22, "learning_rate": 8.210514828984668e-05, "loss": 0.0218, "step": 121680 }, { "epoch": 29.22, "learning_rate": 8.21023963758134e-05, "loss": 0.04, "step": 121690 }, { "epoch": 29.22, "learning_rate": 8.209964429632411e-05, "loss": 0.029, "step": 121700 }, { "epoch": 29.22, "learning_rate": 8.209689205139297e-05, "loss": 0.0247, "step": 121710 }, { "epoch": 29.23, "learning_rate": 8.209413964103421e-05, "loss": 0.0297, "step": 121720 }, { "epoch": 29.23, "learning_rate": 8.209138706526196e-05, "loss": 0.0211, "step": 121730 }, { "epoch": 29.23, "learning_rate": 8.208863432409042e-05, "loss": 0.0201, "step": 121740 }, { "epoch": 29.23, "learning_rate": 8.208588141753382e-05, "loss": 0.0124, "step": 121750 }, { "epoch": 29.24, "learning_rate": 8.20831283456063e-05, "loss": 0.0319, "step": 121760 }, { "epoch": 29.24, "learning_rate": 8.208037510832208e-05, "loss": 0.0335, "step": 121770 }, { "epoch": 29.24, "learning_rate": 8.207762170569531e-05, "loss": 0.0285, "step": 121780 }, { "epoch": 29.24, "learning_rate": 8.207486813774026e-05, "loss": 0.047, "step": 121790 }, { "epoch": 29.25, "learning_rate": 8.207211440447104e-05, "loss": 0.027, "step": 121800 }, { "epoch": 29.25, "learning_rate": 8.206936050590187e-05, "loss": 0.0363, "step": 121810 }, { "epoch": 29.25, "learning_rate": 8.206660644204695e-05, "loss": 0.0596, "step": 121820 }, { "epoch": 29.25, "learning_rate": 8.206385221292048e-05, "loss": 0.0214, "step": 121830 }, { "epoch": 29.25, "learning_rate": 8.206109781853664e-05, "loss": 0.0236, "step": 121840 }, { "epoch": 29.26, "learning_rate": 8.205834325890964e-05, "loss": 0.0447, "step": 121850 }, { "epoch": 29.26, "learning_rate": 8.205558853405369e-05, "loss": 0.0209, "step": 121860 }, { "epoch": 29.26, "learning_rate": 8.205283364398293e-05, "loss": 0.0265, "step": 121870 }, { "epoch": 29.26, "learning_rate": 8.205007858871162e-05, "loss": 0.0299, "step": 121880 }, { "epoch": 29.27, "learning_rate": 8.204732336825394e-05, "loss": 0.032, "step": 121890 }, { "epoch": 29.27, "learning_rate": 8.204456798262407e-05, "loss": 0.0194, "step": 121900 }, { "epoch": 29.27, "learning_rate": 8.204181243183624e-05, "loss": 0.0318, "step": 121910 }, { "epoch": 29.27, "learning_rate": 8.203905671590464e-05, "loss": 0.0311, "step": 121920 }, { "epoch": 29.27, "learning_rate": 8.203630083484349e-05, "loss": 0.033, "step": 121930 }, { "epoch": 29.28, "learning_rate": 8.203354478866696e-05, "loss": 0.0284, "step": 121940 }, { "epoch": 29.28, "learning_rate": 8.203078857738926e-05, "loss": 0.0265, "step": 121950 }, { "epoch": 29.28, "learning_rate": 8.202803220102462e-05, "loss": 0.0324, "step": 121960 }, { "epoch": 29.28, "learning_rate": 8.202527565958724e-05, "loss": 0.0221, "step": 121970 }, { "epoch": 29.29, "learning_rate": 8.202251895309132e-05, "loss": 0.0199, "step": 121980 }, { "epoch": 29.29, "learning_rate": 8.201976208155106e-05, "loss": 0.0175, "step": 121990 }, { "epoch": 29.29, "learning_rate": 8.20170050449807e-05, "loss": 0.0234, "step": 122000 }, { "epoch": 29.29, "learning_rate": 8.201424784339443e-05, "loss": 0.0214, "step": 122010 }, { "epoch": 29.3, "learning_rate": 8.201149047680643e-05, "loss": 0.0301, "step": 122020 }, { "epoch": 29.3, "learning_rate": 8.200873294523095e-05, "loss": 0.0232, "step": 122030 }, { "epoch": 29.3, "learning_rate": 8.20059752486822e-05, "loss": 0.0377, "step": 122040 }, { "epoch": 29.3, "learning_rate": 8.200321738717438e-05, "loss": 0.024, "step": 122050 }, { "epoch": 29.3, "learning_rate": 8.200045936072172e-05, "loss": 0.0276, "step": 122060 }, { "epoch": 29.31, "learning_rate": 8.199770116933842e-05, "loss": 0.03, "step": 122070 }, { "epoch": 29.31, "learning_rate": 8.19949428130387e-05, "loss": 0.0204, "step": 122080 }, { "epoch": 29.31, "learning_rate": 8.199218429183677e-05, "loss": 0.0319, "step": 122090 }, { "epoch": 29.31, "learning_rate": 8.198942560574686e-05, "loss": 0.0416, "step": 122100 }, { "epoch": 29.32, "learning_rate": 8.198666675478319e-05, "loss": 0.0223, "step": 122110 }, { "epoch": 29.32, "learning_rate": 8.198390773895996e-05, "loss": 0.0272, "step": 122120 }, { "epoch": 29.32, "learning_rate": 8.198114855829141e-05, "loss": 0.0219, "step": 122130 }, { "epoch": 29.32, "learning_rate": 8.197838921279175e-05, "loss": 0.0413, "step": 122140 }, { "epoch": 29.33, "learning_rate": 8.197562970247521e-05, "loss": 0.0219, "step": 122150 }, { "epoch": 29.33, "learning_rate": 8.197287002735601e-05, "loss": 0.0144, "step": 122160 }, { "epoch": 29.33, "learning_rate": 8.197011018744836e-05, "loss": 0.0356, "step": 122170 }, { "epoch": 29.33, "learning_rate": 8.196735018276649e-05, "loss": 0.0153, "step": 122180 }, { "epoch": 29.33, "learning_rate": 8.196459001332463e-05, "loss": 0.0199, "step": 122190 }, { "epoch": 29.34, "learning_rate": 8.196182967913702e-05, "loss": 0.0217, "step": 122200 }, { "epoch": 29.34, "learning_rate": 8.195906918021788e-05, "loss": 0.0297, "step": 122210 }, { "epoch": 29.34, "learning_rate": 8.195630851658141e-05, "loss": 0.0182, "step": 122220 }, { "epoch": 29.34, "learning_rate": 8.195354768824187e-05, "loss": 0.0274, "step": 122230 }, { "epoch": 29.35, "learning_rate": 8.195078669521348e-05, "loss": 0.0167, "step": 122240 }, { "epoch": 29.35, "learning_rate": 8.194802553751047e-05, "loss": 0.0273, "step": 122250 }, { "epoch": 29.35, "learning_rate": 8.194526421514705e-05, "loss": 0.0364, "step": 122260 }, { "epoch": 29.35, "learning_rate": 8.194250272813748e-05, "loss": 0.0252, "step": 122270 }, { "epoch": 29.35, "learning_rate": 8.193974107649599e-05, "loss": 0.0347, "step": 122280 }, { "epoch": 29.36, "learning_rate": 8.19369792602368e-05, "loss": 0.0268, "step": 122290 }, { "epoch": 29.36, "learning_rate": 8.193421727937416e-05, "loss": 0.0152, "step": 122300 }, { "epoch": 29.36, "learning_rate": 8.19314551339223e-05, "loss": 0.044, "step": 122310 }, { "epoch": 29.36, "learning_rate": 8.192869282389544e-05, "loss": 0.0434, "step": 122320 }, { "epoch": 29.37, "learning_rate": 8.192593034930785e-05, "loss": 0.0347, "step": 122330 }, { "epoch": 29.37, "learning_rate": 8.192316771017372e-05, "loss": 0.031, "step": 122340 }, { "epoch": 29.37, "learning_rate": 8.192040490650735e-05, "loss": 0.0215, "step": 122350 }, { "epoch": 29.37, "learning_rate": 8.191764193832291e-05, "loss": 0.0229, "step": 122360 }, { "epoch": 29.38, "learning_rate": 8.191487880563471e-05, "loss": 0.0241, "step": 122370 }, { "epoch": 29.38, "learning_rate": 8.191211550845695e-05, "loss": 0.0473, "step": 122380 }, { "epoch": 29.38, "learning_rate": 8.190935204680385e-05, "loss": 0.0199, "step": 122390 }, { "epoch": 29.38, "learning_rate": 8.190658842068972e-05, "loss": 0.0283, "step": 122400 }, { "epoch": 29.38, "learning_rate": 8.190382463012875e-05, "loss": 0.0133, "step": 122410 }, { "epoch": 29.39, "learning_rate": 8.19010606751352e-05, "loss": 0.0442, "step": 122420 }, { "epoch": 29.39, "learning_rate": 8.189829655572333e-05, "loss": 0.0375, "step": 122430 }, { "epoch": 29.39, "learning_rate": 8.189553227190736e-05, "loss": 0.041, "step": 122440 }, { "epoch": 29.39, "learning_rate": 8.189276782370156e-05, "loss": 0.0256, "step": 122450 }, { "epoch": 29.4, "learning_rate": 8.189000321112016e-05, "loss": 0.0204, "step": 122460 }, { "epoch": 29.4, "learning_rate": 8.188723843417741e-05, "loss": 0.0465, "step": 122470 }, { "epoch": 29.4, "learning_rate": 8.188447349288758e-05, "loss": 0.0189, "step": 122480 }, { "epoch": 29.4, "learning_rate": 8.18817083872649e-05, "loss": 0.026, "step": 122490 }, { "epoch": 29.41, "learning_rate": 8.187894311732362e-05, "loss": 0.0359, "step": 122500 }, { "epoch": 29.41, "learning_rate": 8.187617768307802e-05, "loss": 0.0303, "step": 122510 }, { "epoch": 29.41, "learning_rate": 8.187341208454233e-05, "loss": 0.0259, "step": 122520 }, { "epoch": 29.41, "learning_rate": 8.187064632173081e-05, "loss": 0.0345, "step": 122530 }, { "epoch": 29.41, "learning_rate": 8.18678803946577e-05, "loss": 0.0308, "step": 122540 }, { "epoch": 29.42, "learning_rate": 8.186511430333728e-05, "loss": 0.0356, "step": 122550 }, { "epoch": 29.42, "learning_rate": 8.186234804778377e-05, "loss": 0.0244, "step": 122560 }, { "epoch": 29.42, "learning_rate": 8.185958162801148e-05, "loss": 0.0475, "step": 122570 }, { "epoch": 29.42, "learning_rate": 8.185681504403463e-05, "loss": 0.0172, "step": 122580 }, { "epoch": 29.43, "learning_rate": 8.185404829586749e-05, "loss": 0.0262, "step": 122590 }, { "epoch": 29.43, "learning_rate": 8.185128138352431e-05, "loss": 0.0201, "step": 122600 }, { "epoch": 29.43, "learning_rate": 8.184851430701937e-05, "loss": 0.0274, "step": 122610 }, { "epoch": 29.43, "learning_rate": 8.184574706636691e-05, "loss": 0.0409, "step": 122620 }, { "epoch": 29.43, "learning_rate": 8.184297966158122e-05, "loss": 0.0307, "step": 122630 }, { "epoch": 29.44, "learning_rate": 8.184021209267654e-05, "loss": 0.0225, "step": 122640 }, { "epoch": 29.44, "learning_rate": 8.183744435966714e-05, "loss": 0.0367, "step": 122650 }, { "epoch": 29.44, "learning_rate": 8.183467646256728e-05, "loss": 0.0244, "step": 122660 }, { "epoch": 29.44, "learning_rate": 8.183190840139123e-05, "loss": 0.0221, "step": 122670 }, { "epoch": 29.45, "learning_rate": 8.182914017615327e-05, "loss": 0.0179, "step": 122680 }, { "epoch": 29.45, "learning_rate": 8.182637178686765e-05, "loss": 0.0322, "step": 122690 }, { "epoch": 29.45, "learning_rate": 8.182360323354865e-05, "loss": 0.0199, "step": 122700 }, { "epoch": 29.45, "learning_rate": 8.182083451621052e-05, "loss": 0.0342, "step": 122710 }, { "epoch": 29.46, "learning_rate": 8.181806563486756e-05, "loss": 0.022, "step": 122720 }, { "epoch": 29.46, "learning_rate": 8.181529658953401e-05, "loss": 0.0152, "step": 122730 }, { "epoch": 29.46, "learning_rate": 8.181252738022416e-05, "loss": 0.0289, "step": 122740 }, { "epoch": 29.46, "learning_rate": 8.180975800695228e-05, "loss": 0.016, "step": 122750 }, { "epoch": 29.46, "learning_rate": 8.180698846973263e-05, "loss": 0.0279, "step": 122760 }, { "epoch": 29.47, "learning_rate": 8.18042187685795e-05, "loss": 0.0217, "step": 122770 }, { "epoch": 29.47, "learning_rate": 8.180144890350717e-05, "loss": 0.0303, "step": 122780 }, { "epoch": 29.47, "learning_rate": 8.179867887452989e-05, "loss": 0.0207, "step": 122790 }, { "epoch": 29.47, "learning_rate": 8.179590868166196e-05, "loss": 0.0219, "step": 122800 }, { "epoch": 29.48, "learning_rate": 8.179313832491766e-05, "loss": 0.0308, "step": 122810 }, { "epoch": 29.48, "learning_rate": 8.179036780431126e-05, "loss": 0.0284, "step": 122820 }, { "epoch": 29.48, "learning_rate": 8.178759711985703e-05, "loss": 0.0216, "step": 122830 }, { "epoch": 29.48, "learning_rate": 8.178482627156926e-05, "loss": 0.0479, "step": 122840 }, { "epoch": 29.49, "learning_rate": 8.178205525946223e-05, "loss": 0.0412, "step": 122850 }, { "epoch": 29.49, "learning_rate": 8.177928408355024e-05, "loss": 0.0215, "step": 122860 }, { "epoch": 29.49, "learning_rate": 8.177651274384753e-05, "loss": 0.0219, "step": 122870 }, { "epoch": 29.49, "learning_rate": 8.17737412403684e-05, "loss": 0.03, "step": 122880 }, { "epoch": 29.49, "learning_rate": 8.177096957312716e-05, "loss": 0.0262, "step": 122890 }, { "epoch": 29.5, "learning_rate": 8.176819774213807e-05, "loss": 0.0287, "step": 122900 }, { "epoch": 29.5, "learning_rate": 8.176542574741543e-05, "loss": 0.0367, "step": 122910 }, { "epoch": 29.5, "learning_rate": 8.176265358897353e-05, "loss": 0.0266, "step": 122920 }, { "epoch": 29.5, "learning_rate": 8.175988126682663e-05, "loss": 0.0382, "step": 122930 }, { "epoch": 29.51, "learning_rate": 8.175710878098904e-05, "loss": 0.0142, "step": 122940 }, { "epoch": 29.51, "learning_rate": 8.175433613147505e-05, "loss": 0.0244, "step": 122950 }, { "epoch": 29.51, "learning_rate": 8.175156331829895e-05, "loss": 0.0216, "step": 122960 }, { "epoch": 29.51, "learning_rate": 8.174879034147501e-05, "loss": 0.0229, "step": 122970 }, { "epoch": 29.51, "learning_rate": 8.174601720101756e-05, "loss": 0.0638, "step": 122980 }, { "epoch": 29.52, "learning_rate": 8.174324389694086e-05, "loss": 0.0314, "step": 122990 }, { "epoch": 29.52, "learning_rate": 8.174047042925921e-05, "loss": 0.0225, "step": 123000 }, { "epoch": 29.52, "learning_rate": 8.173769679798692e-05, "loss": 0.0353, "step": 123010 }, { "epoch": 29.52, "learning_rate": 8.173492300313828e-05, "loss": 0.0301, "step": 123020 }, { "epoch": 29.53, "learning_rate": 8.173214904472757e-05, "loss": 0.044, "step": 123030 }, { "epoch": 29.53, "learning_rate": 8.17293749227691e-05, "loss": 0.0359, "step": 123040 }, { "epoch": 29.53, "learning_rate": 8.172660063727718e-05, "loss": 0.0408, "step": 123050 }, { "epoch": 29.53, "learning_rate": 8.172382618826608e-05, "loss": 0.0762, "step": 123060 }, { "epoch": 29.54, "learning_rate": 8.172105157575011e-05, "loss": 0.0788, "step": 123070 }, { "epoch": 29.54, "learning_rate": 8.17182767997436e-05, "loss": 0.0435, "step": 123080 }, { "epoch": 29.54, "learning_rate": 8.17155018602608e-05, "loss": 0.034, "step": 123090 }, { "epoch": 29.54, "learning_rate": 8.171272675731605e-05, "loss": 0.0397, "step": 123100 }, { "epoch": 29.54, "learning_rate": 8.170995149092365e-05, "loss": 0.0462, "step": 123110 }, { "epoch": 29.55, "learning_rate": 8.170717606109788e-05, "loss": 0.0404, "step": 123120 }, { "epoch": 29.55, "learning_rate": 8.170440046785305e-05, "loss": 0.0515, "step": 123130 }, { "epoch": 29.55, "learning_rate": 8.17016247112035e-05, "loss": 0.0377, "step": 123140 }, { "epoch": 29.55, "learning_rate": 8.169884879116351e-05, "loss": 0.0403, "step": 123150 }, { "epoch": 29.56, "learning_rate": 8.169607270774737e-05, "loss": 0.0468, "step": 123160 }, { "epoch": 29.56, "learning_rate": 8.169329646096941e-05, "loss": 0.0479, "step": 123170 }, { "epoch": 29.56, "learning_rate": 8.169052005084394e-05, "loss": 0.0389, "step": 123180 }, { "epoch": 29.56, "learning_rate": 8.168774347738528e-05, "loss": 0.0537, "step": 123190 }, { "epoch": 29.57, "learning_rate": 8.16849667406077e-05, "loss": 0.0408, "step": 123200 }, { "epoch": 29.57, "learning_rate": 8.168218984052555e-05, "loss": 0.0502, "step": 123210 }, { "epoch": 29.57, "learning_rate": 8.167941277715314e-05, "loss": 0.0388, "step": 123220 }, { "epoch": 29.57, "learning_rate": 8.167663555050476e-05, "loss": 0.0273, "step": 123230 }, { "epoch": 29.57, "learning_rate": 8.167385816059471e-05, "loss": 0.0474, "step": 123240 }, { "epoch": 29.58, "learning_rate": 8.167108060743736e-05, "loss": 0.039, "step": 123250 }, { "epoch": 29.58, "learning_rate": 8.1668302891047e-05, "loss": 0.0621, "step": 123260 }, { "epoch": 29.58, "learning_rate": 8.166552501143793e-05, "loss": 0.0426, "step": 123270 }, { "epoch": 29.58, "learning_rate": 8.166274696862448e-05, "loss": 0.0328, "step": 123280 }, { "epoch": 29.59, "learning_rate": 8.165996876262097e-05, "loss": 0.0415, "step": 123290 }, { "epoch": 29.59, "learning_rate": 8.165719039344172e-05, "loss": 0.0378, "step": 123300 }, { "epoch": 29.59, "learning_rate": 8.165441186110104e-05, "loss": 0.0372, "step": 123310 }, { "epoch": 29.59, "learning_rate": 8.165163316561326e-05, "loss": 0.0484, "step": 123320 }, { "epoch": 29.59, "learning_rate": 8.164885430699269e-05, "loss": 0.0359, "step": 123330 }, { "epoch": 29.6, "learning_rate": 8.164607528525367e-05, "loss": 0.0299, "step": 123340 }, { "epoch": 29.6, "learning_rate": 8.16432961004105e-05, "loss": 0.0328, "step": 123350 }, { "epoch": 29.6, "learning_rate": 8.164051675247753e-05, "loss": 0.0502, "step": 123360 }, { "epoch": 29.6, "learning_rate": 8.163773724146908e-05, "loss": 0.0392, "step": 123370 }, { "epoch": 29.61, "learning_rate": 8.163495756739945e-05, "loss": 0.0345, "step": 123380 }, { "epoch": 29.61, "learning_rate": 8.1632177730283e-05, "loss": 0.0584, "step": 123390 }, { "epoch": 29.61, "learning_rate": 8.162939773013402e-05, "loss": 0.0394, "step": 123400 }, { "epoch": 29.61, "learning_rate": 8.162661756696688e-05, "loss": 0.0358, "step": 123410 }, { "epoch": 29.62, "learning_rate": 8.162383724079587e-05, "loss": 0.0433, "step": 123420 }, { "epoch": 29.62, "learning_rate": 8.162105675163534e-05, "loss": 0.0564, "step": 123430 }, { "epoch": 29.62, "learning_rate": 8.161827609949966e-05, "loss": 0.0468, "step": 123440 }, { "epoch": 29.62, "learning_rate": 8.161549528440307e-05, "loss": 0.0528, "step": 123450 }, { "epoch": 29.62, "learning_rate": 8.161271430635998e-05, "loss": 0.0401, "step": 123460 }, { "epoch": 29.63, "learning_rate": 8.160993316538468e-05, "loss": 0.0302, "step": 123470 }, { "epoch": 29.63, "learning_rate": 8.160715186149154e-05, "loss": 0.0574, "step": 123480 }, { "epoch": 29.63, "learning_rate": 8.160437039469487e-05, "loss": 0.0542, "step": 123490 }, { "epoch": 29.63, "learning_rate": 8.1601588765009e-05, "loss": 0.0566, "step": 123500 }, { "epoch": 29.64, "learning_rate": 8.159880697244828e-05, "loss": 0.0439, "step": 123510 }, { "epoch": 29.64, "learning_rate": 8.159602501702706e-05, "loss": 0.0371, "step": 123520 }, { "epoch": 29.64, "learning_rate": 8.159324289875965e-05, "loss": 0.031, "step": 123530 }, { "epoch": 29.64, "learning_rate": 8.15904606176604e-05, "loss": 0.0346, "step": 123540 }, { "epoch": 29.65, "learning_rate": 8.158767817374365e-05, "loss": 0.0371, "step": 123550 }, { "epoch": 29.65, "learning_rate": 8.158489556702375e-05, "loss": 0.0875, "step": 123560 }, { "epoch": 29.65, "learning_rate": 8.158211279751501e-05, "loss": 0.044, "step": 123570 }, { "epoch": 29.65, "learning_rate": 8.157932986523184e-05, "loss": 0.0324, "step": 123580 }, { "epoch": 29.65, "learning_rate": 8.157654677018851e-05, "loss": 0.0435, "step": 123590 }, { "epoch": 29.66, "learning_rate": 8.157376351239941e-05, "loss": 0.0569, "step": 123600 }, { "epoch": 29.66, "learning_rate": 8.157098009187885e-05, "loss": 0.0516, "step": 123610 }, { "epoch": 29.66, "learning_rate": 8.15681965086412e-05, "loss": 0.0282, "step": 123620 }, { "epoch": 29.66, "learning_rate": 8.156541276270082e-05, "loss": 0.0255, "step": 123630 }, { "epoch": 29.67, "learning_rate": 8.156262885407202e-05, "loss": 0.0363, "step": 123640 }, { "epoch": 29.67, "learning_rate": 8.155984478276917e-05, "loss": 0.0323, "step": 123650 }, { "epoch": 29.67, "learning_rate": 8.155706054880663e-05, "loss": 0.0385, "step": 123660 }, { "epoch": 29.67, "learning_rate": 8.155427615219872e-05, "loss": 0.0321, "step": 123670 }, { "epoch": 29.67, "learning_rate": 8.15514915929598e-05, "loss": 0.0222, "step": 123680 }, { "epoch": 29.68, "learning_rate": 8.154870687110425e-05, "loss": 0.0545, "step": 123690 }, { "epoch": 29.68, "learning_rate": 8.154592198664639e-05, "loss": 0.0341, "step": 123700 }, { "epoch": 29.68, "learning_rate": 8.154313693960058e-05, "loss": 0.0452, "step": 123710 }, { "epoch": 29.68, "learning_rate": 8.15403517299812e-05, "loss": 0.0285, "step": 123720 }, { "epoch": 29.69, "learning_rate": 8.153756635780256e-05, "loss": 0.0373, "step": 123730 }, { "epoch": 29.69, "learning_rate": 8.153478082307905e-05, "loss": 0.0178, "step": 123740 }, { "epoch": 29.69, "learning_rate": 8.153199512582501e-05, "loss": 0.0314, "step": 123750 }, { "epoch": 29.69, "learning_rate": 8.15292092660548e-05, "loss": 0.025, "step": 123760 }, { "epoch": 29.7, "learning_rate": 8.152642324378279e-05, "loss": 0.0287, "step": 123770 }, { "epoch": 29.7, "learning_rate": 8.152363705902333e-05, "loss": 0.0348, "step": 123780 }, { "epoch": 29.7, "learning_rate": 8.152085071179079e-05, "loss": 0.0342, "step": 123790 }, { "epoch": 29.7, "learning_rate": 8.15180642020995e-05, "loss": 0.029, "step": 123800 }, { "epoch": 29.7, "learning_rate": 8.151527752996386e-05, "loss": 0.0366, "step": 123810 }, { "epoch": 29.71, "learning_rate": 8.151249069539822e-05, "loss": 0.0473, "step": 123820 }, { "epoch": 29.71, "learning_rate": 8.150970369841693e-05, "loss": 0.0323, "step": 123830 }, { "epoch": 29.71, "learning_rate": 8.150691653903437e-05, "loss": 0.0169, "step": 123840 }, { "epoch": 29.71, "learning_rate": 8.15041292172649e-05, "loss": 0.0407, "step": 123850 }, { "epoch": 29.72, "learning_rate": 8.150134173312287e-05, "loss": 0.0465, "step": 123860 }, { "epoch": 29.72, "learning_rate": 8.149855408662268e-05, "loss": 0.0398, "step": 123870 }, { "epoch": 29.72, "learning_rate": 8.149576627777866e-05, "loss": 0.0418, "step": 123880 }, { "epoch": 29.72, "learning_rate": 8.149297830660521e-05, "loss": 0.0366, "step": 123890 }, { "epoch": 29.73, "learning_rate": 8.149019017311668e-05, "loss": 0.0407, "step": 123900 }, { "epoch": 29.73, "learning_rate": 8.148740187732746e-05, "loss": 0.0355, "step": 123910 }, { "epoch": 29.73, "learning_rate": 8.148461341925188e-05, "loss": 0.0386, "step": 123920 }, { "epoch": 29.73, "learning_rate": 8.148182479890437e-05, "loss": 0.0299, "step": 123930 }, { "epoch": 29.73, "learning_rate": 8.147903601629927e-05, "loss": 0.0338, "step": 123940 }, { "epoch": 29.74, "learning_rate": 8.147624707145094e-05, "loss": 0.0625, "step": 123950 }, { "epoch": 29.74, "learning_rate": 8.147345796437378e-05, "loss": 0.0187, "step": 123960 }, { "epoch": 29.74, "learning_rate": 8.147066869508214e-05, "loss": 0.0194, "step": 123970 }, { "epoch": 29.74, "learning_rate": 8.146787926359041e-05, "loss": 0.0404, "step": 123980 }, { "epoch": 29.75, "learning_rate": 8.146508966991298e-05, "loss": 0.0393, "step": 123990 }, { "epoch": 29.75, "learning_rate": 8.146229991406422e-05, "loss": 0.0446, "step": 124000 }, { "epoch": 29.75, "learning_rate": 8.14595099960585e-05, "loss": 0.0391, "step": 124010 }, { "epoch": 29.75, "learning_rate": 8.14567199159102e-05, "loss": 0.0303, "step": 124020 }, { "epoch": 29.75, "learning_rate": 8.145392967363368e-05, "loss": 0.0294, "step": 124030 }, { "epoch": 29.76, "learning_rate": 8.145113926924337e-05, "loss": 0.0352, "step": 124040 }, { "epoch": 29.76, "learning_rate": 8.144834870275361e-05, "loss": 0.0469, "step": 124050 }, { "epoch": 29.76, "learning_rate": 8.144555797417881e-05, "loss": 0.031, "step": 124060 }, { "epoch": 29.76, "learning_rate": 8.144276708353333e-05, "loss": 0.0271, "step": 124070 }, { "epoch": 29.77, "learning_rate": 8.143997603083159e-05, "loss": 0.0309, "step": 124080 }, { "epoch": 29.77, "learning_rate": 8.143718481608793e-05, "loss": 0.0147, "step": 124090 }, { "epoch": 29.77, "learning_rate": 8.143439343931676e-05, "loss": 0.0697, "step": 124100 }, { "epoch": 29.77, "learning_rate": 8.143160190053247e-05, "loss": 0.0123, "step": 124110 }, { "epoch": 29.78, "learning_rate": 8.142881019974943e-05, "loss": 0.0373, "step": 124120 }, { "epoch": 29.78, "learning_rate": 8.142601833698204e-05, "loss": 0.0327, "step": 124130 }, { "epoch": 29.78, "learning_rate": 8.142322631224471e-05, "loss": 0.0331, "step": 124140 }, { "epoch": 29.78, "learning_rate": 8.142043412555178e-05, "loss": 0.0412, "step": 124150 }, { "epoch": 29.78, "learning_rate": 8.141764177691768e-05, "loss": 0.0295, "step": 124160 }, { "epoch": 29.79, "learning_rate": 8.14148492663568e-05, "loss": 0.024, "step": 124170 }, { "epoch": 29.79, "learning_rate": 8.141205659388351e-05, "loss": 0.0665, "step": 124180 }, { "epoch": 29.79, "learning_rate": 8.140926375951223e-05, "loss": 0.0324, "step": 124190 }, { "epoch": 29.79, "learning_rate": 8.140647076325734e-05, "loss": 0.0333, "step": 124200 }, { "epoch": 29.8, "learning_rate": 8.140367760513324e-05, "loss": 0.0297, "step": 124210 }, { "epoch": 29.8, "learning_rate": 8.140088428515431e-05, "loss": 0.021, "step": 124220 }, { "epoch": 29.8, "learning_rate": 8.139809080333498e-05, "loss": 0.025, "step": 124230 }, { "epoch": 29.8, "learning_rate": 8.139529715968961e-05, "loss": 0.0333, "step": 124240 }, { "epoch": 29.81, "learning_rate": 8.139250335423261e-05, "loss": 0.0404, "step": 124250 }, { "epoch": 29.81, "learning_rate": 8.13897093869784e-05, "loss": 0.0356, "step": 124260 }, { "epoch": 29.81, "learning_rate": 8.138691525794137e-05, "loss": 0.033, "step": 124270 }, { "epoch": 29.81, "learning_rate": 8.13841209671359e-05, "loss": 0.03, "step": 124280 }, { "epoch": 29.81, "learning_rate": 8.138132651457642e-05, "loss": 0.0331, "step": 124290 }, { "epoch": 29.82, "learning_rate": 8.137853190027733e-05, "loss": 0.0769, "step": 124300 }, { "epoch": 29.82, "learning_rate": 8.137573712425302e-05, "loss": 0.0255, "step": 124310 }, { "epoch": 29.82, "learning_rate": 8.137294218651787e-05, "loss": 0.0514, "step": 124320 }, { "epoch": 29.82, "learning_rate": 8.137014708708634e-05, "loss": 0.0251, "step": 124330 }, { "epoch": 29.83, "learning_rate": 8.136735182597281e-05, "loss": 0.0416, "step": 124340 }, { "epoch": 29.83, "learning_rate": 8.136455640319167e-05, "loss": 0.0334, "step": 124350 }, { "epoch": 29.83, "learning_rate": 8.136176081875736e-05, "loss": 0.032, "step": 124360 }, { "epoch": 29.83, "learning_rate": 8.135896507268427e-05, "loss": 0.0217, "step": 124370 }, { "epoch": 29.83, "learning_rate": 8.135616916498681e-05, "loss": 0.0274, "step": 124380 }, { "epoch": 29.84, "learning_rate": 8.13533730956794e-05, "loss": 0.0293, "step": 124390 }, { "epoch": 29.84, "learning_rate": 8.135057686477643e-05, "loss": 0.0209, "step": 124400 }, { "epoch": 29.84, "learning_rate": 8.134778047229232e-05, "loss": 0.039, "step": 124410 }, { "epoch": 29.84, "learning_rate": 8.13449839182415e-05, "loss": 0.0262, "step": 124420 }, { "epoch": 29.85, "learning_rate": 8.134218720263838e-05, "loss": 0.0244, "step": 124430 }, { "epoch": 29.85, "learning_rate": 8.133939032549736e-05, "loss": 0.0333, "step": 124440 }, { "epoch": 29.85, "learning_rate": 8.133659328683284e-05, "loss": 0.0375, "step": 124450 }, { "epoch": 29.85, "learning_rate": 8.133379608665927e-05, "loss": 0.0345, "step": 124460 }, { "epoch": 29.86, "learning_rate": 8.133099872499106e-05, "loss": 0.0392, "step": 124470 }, { "epoch": 29.86, "learning_rate": 8.13282012018426e-05, "loss": 0.0319, "step": 124480 }, { "epoch": 29.86, "learning_rate": 8.132540351722835e-05, "loss": 0.0334, "step": 124490 }, { "epoch": 29.86, "learning_rate": 8.13226056711627e-05, "loss": 0.0401, "step": 124500 }, { "epoch": 29.86, "learning_rate": 8.131980766366007e-05, "loss": 0.0334, "step": 124510 }, { "epoch": 29.87, "learning_rate": 8.131700949473491e-05, "loss": 0.0187, "step": 124520 }, { "epoch": 29.87, "learning_rate": 8.131421116440161e-05, "loss": 0.0214, "step": 124530 }, { "epoch": 29.87, "learning_rate": 8.13114126726746e-05, "loss": 0.0278, "step": 124540 }, { "epoch": 29.87, "learning_rate": 8.13086140195683e-05, "loss": 0.0243, "step": 124550 }, { "epoch": 29.88, "learning_rate": 8.130581520509717e-05, "loss": 0.0218, "step": 124560 }, { "epoch": 29.88, "learning_rate": 8.130301622927559e-05, "loss": 0.039, "step": 124570 }, { "epoch": 29.88, "learning_rate": 8.130021709211799e-05, "loss": 0.0262, "step": 124580 }, { "epoch": 29.88, "learning_rate": 8.129741779363883e-05, "loss": 0.0303, "step": 124590 }, { "epoch": 29.89, "learning_rate": 8.129461833385252e-05, "loss": 0.0185, "step": 124600 }, { "epoch": 29.89, "learning_rate": 8.129181871277347e-05, "loss": 0.0237, "step": 124610 }, { "epoch": 29.89, "learning_rate": 8.128901893041611e-05, "loss": 0.0231, "step": 124620 }, { "epoch": 29.89, "learning_rate": 8.128621898679492e-05, "loss": 0.0498, "step": 124630 }, { "epoch": 29.89, "learning_rate": 8.128341888192428e-05, "loss": 0.0276, "step": 124640 }, { "epoch": 29.9, "learning_rate": 8.128061861581863e-05, "loss": 0.0249, "step": 124650 }, { "epoch": 29.9, "learning_rate": 8.127781818849242e-05, "loss": 0.0274, "step": 124660 }, { "epoch": 29.9, "learning_rate": 8.127501759996007e-05, "loss": 0.0322, "step": 124670 }, { "epoch": 29.9, "learning_rate": 8.127221685023603e-05, "loss": 0.0217, "step": 124680 }, { "epoch": 29.91, "learning_rate": 8.12694159393347e-05, "loss": 0.0239, "step": 124690 }, { "epoch": 29.91, "learning_rate": 8.126661486727056e-05, "loss": 0.0423, "step": 124700 }, { "epoch": 29.91, "learning_rate": 8.126381363405802e-05, "loss": 0.0408, "step": 124710 }, { "epoch": 29.91, "learning_rate": 8.12610122397115e-05, "loss": 0.0309, "step": 124720 }, { "epoch": 29.91, "learning_rate": 8.125821068424551e-05, "loss": 0.0343, "step": 124730 }, { "epoch": 29.92, "learning_rate": 8.12554089676744e-05, "loss": 0.0381, "step": 124740 }, { "epoch": 29.92, "learning_rate": 8.125260709001266e-05, "loss": 0.03, "step": 124750 }, { "epoch": 29.92, "learning_rate": 8.124980505127473e-05, "loss": 0.0349, "step": 124760 }, { "epoch": 29.92, "learning_rate": 8.124700285147504e-05, "loss": 0.0399, "step": 124770 }, { "epoch": 29.93, "learning_rate": 8.124420049062803e-05, "loss": 0.0353, "step": 124780 }, { "epoch": 29.93, "learning_rate": 8.124139796874814e-05, "loss": 0.0171, "step": 124790 }, { "epoch": 29.93, "learning_rate": 8.123859528584985e-05, "loss": 0.0282, "step": 124800 }, { "epoch": 29.93, "learning_rate": 8.123579244194757e-05, "loss": 0.0357, "step": 124810 }, { "epoch": 29.94, "learning_rate": 8.123298943705575e-05, "loss": 0.0226, "step": 124820 }, { "epoch": 29.94, "learning_rate": 8.123018627118884e-05, "loss": 0.0344, "step": 124830 }, { "epoch": 29.94, "learning_rate": 8.12273829443613e-05, "loss": 0.055, "step": 124840 }, { "epoch": 29.94, "learning_rate": 8.122457945658755e-05, "loss": 0.0467, "step": 124850 }, { "epoch": 29.94, "learning_rate": 8.122177580788208e-05, "loss": 0.0325, "step": 124860 }, { "epoch": 29.95, "learning_rate": 8.12189719982593e-05, "loss": 0.0258, "step": 124870 }, { "epoch": 29.95, "learning_rate": 8.121616802773367e-05, "loss": 0.0303, "step": 124880 }, { "epoch": 29.95, "learning_rate": 8.121336389631966e-05, "loss": 0.0371, "step": 124890 }, { "epoch": 30.0, "learning_rate": 8.121055960403171e-05, "loss": 0.0337, "step": 124900 }, { "epoch": 30.0, "learning_rate": 8.120775515088429e-05, "loss": 0.0392, "step": 124910 }, { "epoch": 30.01, "learning_rate": 8.120495053689181e-05, "loss": 0.0297, "step": 124920 }, { "epoch": 30.01, "learning_rate": 8.120214576206877e-05, "loss": 0.0328, "step": 124930 }, { "epoch": 30.01, "learning_rate": 8.11993408264296e-05, "loss": 0.0487, "step": 124940 }, { "epoch": 30.01, "learning_rate": 8.119653572998877e-05, "loss": 0.0268, "step": 124950 }, { "epoch": 30.02, "learning_rate": 8.119373047276075e-05, "loss": 0.0271, "step": 124960 }, { "epoch": 30.02, "learning_rate": 8.119092505475998e-05, "loss": 0.0287, "step": 124970 }, { "epoch": 30.02, "learning_rate": 8.11881194760009e-05, "loss": 0.0171, "step": 124980 }, { "epoch": 30.02, "learning_rate": 8.1185313736498e-05, "loss": 0.0324, "step": 124990 }, { "epoch": 30.03, "learning_rate": 8.118250783626575e-05, "loss": 0.0418, "step": 125000 }, { "epoch": 30.03, "learning_rate": 8.117970177531858e-05, "loss": 0.03, "step": 125010 }, { "epoch": 30.03, "learning_rate": 8.117689555367096e-05, "loss": 0.0263, "step": 125020 }, { "epoch": 30.03, "learning_rate": 8.117408917133738e-05, "loss": 0.0315, "step": 125030 }, { "epoch": 30.03, "learning_rate": 8.117128262833226e-05, "loss": 0.0339, "step": 125040 }, { "epoch": 30.04, "learning_rate": 8.11684759246701e-05, "loss": 0.0322, "step": 125050 }, { "epoch": 30.04, "learning_rate": 8.116566906036535e-05, "loss": 0.0234, "step": 125060 }, { "epoch": 30.04, "learning_rate": 8.116286203543249e-05, "loss": 0.0248, "step": 125070 }, { "epoch": 30.04, "learning_rate": 8.116005484988597e-05, "loss": 0.0308, "step": 125080 }, { "epoch": 30.05, "learning_rate": 8.115724750374028e-05, "loss": 0.0309, "step": 125090 }, { "epoch": 30.05, "learning_rate": 8.115443999700987e-05, "loss": 0.0328, "step": 125100 }, { "epoch": 30.05, "learning_rate": 8.11516323297092e-05, "loss": 0.0501, "step": 125110 }, { "epoch": 30.05, "learning_rate": 8.114882450185277e-05, "loss": 0.0352, "step": 125120 }, { "epoch": 30.05, "learning_rate": 8.114601651345503e-05, "loss": 0.0234, "step": 125130 }, { "epoch": 30.06, "learning_rate": 8.114320836453048e-05, "loss": 0.0401, "step": 125140 }, { "epoch": 30.06, "learning_rate": 8.114040005509356e-05, "loss": 0.0277, "step": 125150 }, { "epoch": 30.06, "learning_rate": 8.113759158515877e-05, "loss": 0.0209, "step": 125160 }, { "epoch": 30.06, "learning_rate": 8.113478295474055e-05, "loss": 0.0212, "step": 125170 }, { "epoch": 30.07, "learning_rate": 8.11319741638534e-05, "loss": 0.0429, "step": 125180 }, { "epoch": 30.07, "learning_rate": 8.112916521251182e-05, "loss": 0.0211, "step": 125190 }, { "epoch": 30.07, "learning_rate": 8.112635610073025e-05, "loss": 0.0331, "step": 125200 }, { "epoch": 30.07, "learning_rate": 8.112354682852317e-05, "loss": 0.0275, "step": 125210 }, { "epoch": 30.08, "learning_rate": 8.112073739590508e-05, "loss": 0.0206, "step": 125220 }, { "epoch": 30.08, "learning_rate": 8.111792780289045e-05, "loss": 0.0296, "step": 125230 }, { "epoch": 30.08, "learning_rate": 8.111511804949375e-05, "loss": 0.0251, "step": 125240 }, { "epoch": 30.08, "learning_rate": 8.111230813572948e-05, "loss": 0.0288, "step": 125250 }, { "epoch": 30.08, "learning_rate": 8.110949806161212e-05, "loss": 0.0309, "step": 125260 }, { "epoch": 30.09, "learning_rate": 8.110668782715613e-05, "loss": 0.0262, "step": 125270 }, { "epoch": 30.09, "learning_rate": 8.110387743237602e-05, "loss": 0.0202, "step": 125280 }, { "epoch": 30.09, "learning_rate": 8.110106687728627e-05, "loss": 0.0364, "step": 125290 }, { "epoch": 30.09, "learning_rate": 8.109825616190136e-05, "loss": 0.0492, "step": 125300 }, { "epoch": 30.1, "learning_rate": 8.109544528623578e-05, "loss": 0.0397, "step": 125310 }, { "epoch": 30.1, "learning_rate": 8.1092634250304e-05, "loss": 0.0336, "step": 125320 }, { "epoch": 30.1, "learning_rate": 8.108982305412054e-05, "loss": 0.0183, "step": 125330 }, { "epoch": 30.1, "learning_rate": 8.108701169769986e-05, "loss": 0.0409, "step": 125340 }, { "epoch": 30.11, "learning_rate": 8.108420018105646e-05, "loss": 0.0287, "step": 125350 }, { "epoch": 30.11, "learning_rate": 8.108138850420483e-05, "loss": 0.0285, "step": 125360 }, { "epoch": 30.11, "learning_rate": 8.107857666715948e-05, "loss": 0.0323, "step": 125370 }, { "epoch": 30.11, "learning_rate": 8.10757646699349e-05, "loss": 0.0299, "step": 125380 }, { "epoch": 30.11, "learning_rate": 8.107295251254553e-05, "loss": 0.0381, "step": 125390 }, { "epoch": 30.12, "learning_rate": 8.107014019500592e-05, "loss": 0.0356, "step": 125400 }, { "epoch": 30.12, "learning_rate": 8.106732771733057e-05, "loss": 0.0362, "step": 125410 }, { "epoch": 30.12, "learning_rate": 8.106451507953392e-05, "loss": 0.0282, "step": 125420 }, { "epoch": 30.12, "learning_rate": 8.106170228163052e-05, "loss": 0.0226, "step": 125430 }, { "epoch": 30.13, "learning_rate": 8.105888932363483e-05, "loss": 0.0308, "step": 125440 }, { "epoch": 30.13, "learning_rate": 8.105607620556137e-05, "loss": 0.0425, "step": 125450 }, { "epoch": 30.13, "learning_rate": 8.105326292742465e-05, "loss": 0.0266, "step": 125460 }, { "epoch": 30.13, "learning_rate": 8.105044948923913e-05, "loss": 0.0225, "step": 125470 }, { "epoch": 30.13, "learning_rate": 8.104763589101935e-05, "loss": 0.0351, "step": 125480 }, { "epoch": 30.14, "learning_rate": 8.104482213277979e-05, "loss": 0.024, "step": 125490 }, { "epoch": 30.14, "learning_rate": 8.104200821453496e-05, "loss": 0.0355, "step": 125500 }, { "epoch": 30.14, "learning_rate": 8.103919413629934e-05, "loss": 0.0285, "step": 125510 }, { "epoch": 30.14, "learning_rate": 8.103637989808748e-05, "loss": 0.0274, "step": 125520 }, { "epoch": 30.15, "learning_rate": 8.103356549991386e-05, "loss": 0.0257, "step": 125530 }, { "epoch": 30.15, "learning_rate": 8.103075094179296e-05, "loss": 0.0433, "step": 125540 }, { "epoch": 30.15, "learning_rate": 8.102793622373933e-05, "loss": 0.0259, "step": 125550 }, { "epoch": 30.15, "learning_rate": 8.102512134576745e-05, "loss": 0.0248, "step": 125560 }, { "epoch": 30.16, "learning_rate": 8.102230630789184e-05, "loss": 0.0278, "step": 125570 }, { "epoch": 30.16, "learning_rate": 8.1019491110127e-05, "loss": 0.0464, "step": 125580 }, { "epoch": 30.16, "learning_rate": 8.101667575248745e-05, "loss": 0.0262, "step": 125590 }, { "epoch": 30.16, "learning_rate": 8.101386023498769e-05, "loss": 0.0197, "step": 125600 }, { "epoch": 30.16, "learning_rate": 8.101104455764222e-05, "loss": 0.0223, "step": 125610 }, { "epoch": 30.17, "learning_rate": 8.100822872046559e-05, "loss": 0.0361, "step": 125620 }, { "epoch": 30.17, "learning_rate": 8.100541272347228e-05, "loss": 0.0363, "step": 125630 }, { "epoch": 30.17, "learning_rate": 8.100259656667682e-05, "loss": 0.022, "step": 125640 }, { "epoch": 30.17, "learning_rate": 8.099978025009369e-05, "loss": 0.0325, "step": 125650 }, { "epoch": 30.18, "learning_rate": 8.099696377373746e-05, "loss": 0.0484, "step": 125660 }, { "epoch": 30.18, "learning_rate": 8.099414713762263e-05, "loss": 0.0283, "step": 125670 }, { "epoch": 30.18, "learning_rate": 8.099133034176368e-05, "loss": 0.0216, "step": 125680 }, { "epoch": 30.18, "learning_rate": 8.098851338617517e-05, "loss": 0.0232, "step": 125690 }, { "epoch": 30.19, "learning_rate": 8.09856962708716e-05, "loss": 0.0259, "step": 125700 }, { "epoch": 30.19, "learning_rate": 8.09828789958675e-05, "loss": 0.0281, "step": 125710 }, { "epoch": 30.19, "learning_rate": 8.098006156117737e-05, "loss": 0.0243, "step": 125720 }, { "epoch": 30.19, "learning_rate": 8.097724396681574e-05, "loss": 0.0486, "step": 125730 }, { "epoch": 30.19, "learning_rate": 8.097442621279715e-05, "loss": 0.0279, "step": 125740 }, { "epoch": 30.2, "learning_rate": 8.09716082991361e-05, "loss": 0.0337, "step": 125750 }, { "epoch": 30.2, "learning_rate": 8.096879022584712e-05, "loss": 0.0294, "step": 125760 }, { "epoch": 30.2, "learning_rate": 8.096597199294474e-05, "loss": 0.0387, "step": 125770 }, { "epoch": 30.2, "learning_rate": 8.096315360044348e-05, "loss": 0.0233, "step": 125780 }, { "epoch": 30.21, "learning_rate": 8.096033504835787e-05, "loss": 0.0228, "step": 125790 }, { "epoch": 30.21, "learning_rate": 8.095751633670243e-05, "loss": 0.0238, "step": 125800 }, { "epoch": 30.21, "learning_rate": 8.095469746549172e-05, "loss": 0.0235, "step": 125810 }, { "epoch": 30.21, "learning_rate": 8.095187843474021e-05, "loss": 0.0269, "step": 125820 }, { "epoch": 30.21, "learning_rate": 8.094905924446246e-05, "loss": 0.0287, "step": 125830 }, { "epoch": 30.22, "learning_rate": 8.094623989467301e-05, "loss": 0.0366, "step": 125840 }, { "epoch": 30.22, "learning_rate": 8.094342038538636e-05, "loss": 0.0341, "step": 125850 }, { "epoch": 30.22, "learning_rate": 8.094060071661708e-05, "loss": 0.055, "step": 125860 }, { "epoch": 30.22, "learning_rate": 8.093778088837969e-05, "loss": 0.0467, "step": 125870 }, { "epoch": 30.23, "learning_rate": 8.093496090068872e-05, "loss": 0.0184, "step": 125880 }, { "epoch": 30.23, "learning_rate": 8.09321407535587e-05, "loss": 0.0227, "step": 125890 }, { "epoch": 30.23, "learning_rate": 8.092932044700416e-05, "loss": 0.0221, "step": 125900 }, { "epoch": 30.23, "learning_rate": 8.092649998103965e-05, "loss": 0.0223, "step": 125910 }, { "epoch": 30.24, "learning_rate": 8.092367935567969e-05, "loss": 0.0377, "step": 125920 }, { "epoch": 30.24, "learning_rate": 8.092085857093884e-05, "loss": 0.0353, "step": 125930 }, { "epoch": 30.24, "learning_rate": 8.091803762683162e-05, "loss": 0.0301, "step": 125940 }, { "epoch": 30.24, "learning_rate": 8.091521652337259e-05, "loss": 0.0152, "step": 125950 }, { "epoch": 30.24, "learning_rate": 8.091239526057626e-05, "loss": 0.0234, "step": 125960 }, { "epoch": 30.25, "learning_rate": 8.09095738384572e-05, "loss": 0.0388, "step": 125970 }, { "epoch": 30.25, "learning_rate": 8.090675225702993e-05, "loss": 0.0301, "step": 125980 }, { "epoch": 30.25, "learning_rate": 8.090393051630899e-05, "loss": 0.0263, "step": 125990 }, { "epoch": 30.25, "learning_rate": 8.090110861630894e-05, "loss": 0.0359, "step": 126000 }, { "epoch": 30.26, "learning_rate": 8.089828655704433e-05, "loss": 0.0211, "step": 126010 }, { "epoch": 30.26, "learning_rate": 8.089546433852968e-05, "loss": 0.0375, "step": 126020 }, { "epoch": 30.26, "learning_rate": 8.089264196077956e-05, "loss": 0.0267, "step": 126030 }, { "epoch": 30.26, "learning_rate": 8.088981942380849e-05, "loss": 0.0288, "step": 126040 }, { "epoch": 30.27, "learning_rate": 8.088699672763105e-05, "loss": 0.0226, "step": 126050 }, { "epoch": 30.27, "learning_rate": 8.088417387226176e-05, "loss": 0.0121, "step": 126060 }, { "epoch": 30.27, "learning_rate": 8.088135085771518e-05, "loss": 0.0396, "step": 126070 }, { "epoch": 30.27, "learning_rate": 8.087852768400586e-05, "loss": 0.0253, "step": 126080 }, { "epoch": 30.27, "learning_rate": 8.087570435114836e-05, "loss": 0.0258, "step": 126090 }, { "epoch": 30.28, "learning_rate": 8.08728808591572e-05, "loss": 0.017, "step": 126100 }, { "epoch": 30.28, "learning_rate": 8.087005720804696e-05, "loss": 0.0301, "step": 126110 }, { "epoch": 30.28, "learning_rate": 8.08672333978322e-05, "loss": 0.0204, "step": 126120 }, { "epoch": 30.28, "learning_rate": 8.086440942852745e-05, "loss": 0.0174, "step": 126130 }, { "epoch": 30.29, "learning_rate": 8.08615853001473e-05, "loss": 0.0298, "step": 126140 }, { "epoch": 30.29, "learning_rate": 8.085876101270624e-05, "loss": 0.0233, "step": 126150 }, { "epoch": 30.29, "learning_rate": 8.085593656621889e-05, "loss": 0.0209, "step": 126160 }, { "epoch": 30.29, "learning_rate": 8.08531119606998e-05, "loss": 0.0141, "step": 126170 }, { "epoch": 30.29, "learning_rate": 8.08502871961635e-05, "loss": 0.0431, "step": 126180 }, { "epoch": 30.3, "learning_rate": 8.084746227262455e-05, "loss": 0.0325, "step": 126190 }, { "epoch": 30.3, "learning_rate": 8.084463719009753e-05, "loss": 0.0181, "step": 126200 }, { "epoch": 30.3, "learning_rate": 8.084181194859699e-05, "loss": 0.0374, "step": 126210 }, { "epoch": 30.3, "learning_rate": 8.083898654813751e-05, "loss": 0.0258, "step": 126220 }, { "epoch": 30.31, "learning_rate": 8.083616098873361e-05, "loss": 0.0306, "step": 126230 }, { "epoch": 30.31, "learning_rate": 8.083333527039989e-05, "loss": 0.0268, "step": 126240 }, { "epoch": 30.31, "learning_rate": 8.083050939315091e-05, "loss": 0.0251, "step": 126250 }, { "epoch": 30.31, "learning_rate": 8.082768335700121e-05, "loss": 0.0275, "step": 126260 }, { "epoch": 30.32, "learning_rate": 8.08248571619654e-05, "loss": 0.0197, "step": 126270 }, { "epoch": 30.32, "learning_rate": 8.082203080805799e-05, "loss": 0.0321, "step": 126280 }, { "epoch": 30.32, "learning_rate": 8.08192042952936e-05, "loss": 0.0211, "step": 126290 }, { "epoch": 30.32, "learning_rate": 8.081637762368675e-05, "loss": 0.0439, "step": 126300 }, { "epoch": 30.32, "learning_rate": 8.081355079325203e-05, "loss": 0.0339, "step": 126310 }, { "epoch": 30.33, "learning_rate": 8.081072380400403e-05, "loss": 0.0402, "step": 126320 }, { "epoch": 30.33, "learning_rate": 8.080789665595729e-05, "loss": 0.0339, "step": 126330 }, { "epoch": 30.33, "learning_rate": 8.08050693491264e-05, "loss": 0.0244, "step": 126340 }, { "epoch": 30.33, "learning_rate": 8.080224188352593e-05, "loss": 0.029, "step": 126350 }, { "epoch": 30.34, "learning_rate": 8.079941425917043e-05, "loss": 0.0318, "step": 126360 }, { "epoch": 30.34, "learning_rate": 8.079658647607451e-05, "loss": 0.0227, "step": 126370 }, { "epoch": 30.34, "learning_rate": 8.079375853425273e-05, "loss": 0.0396, "step": 126380 }, { "epoch": 30.34, "learning_rate": 8.079093043371964e-05, "loss": 0.0274, "step": 126390 }, { "epoch": 30.35, "learning_rate": 8.078810217448986e-05, "loss": 0.0193, "step": 126400 }, { "epoch": 30.35, "learning_rate": 8.078527375657792e-05, "loss": 0.0275, "step": 126410 }, { "epoch": 30.35, "learning_rate": 8.078244517999843e-05, "loss": 0.0179, "step": 126420 }, { "epoch": 30.35, "learning_rate": 8.077961644476597e-05, "loss": 0.0338, "step": 126430 }, { "epoch": 30.35, "learning_rate": 8.07767875508951e-05, "loss": 0.0297, "step": 126440 }, { "epoch": 30.36, "learning_rate": 8.077395849840042e-05, "loss": 0.0165, "step": 126450 }, { "epoch": 30.36, "learning_rate": 8.077112928729649e-05, "loss": 0.0264, "step": 126460 }, { "epoch": 30.36, "learning_rate": 8.076829991759791e-05, "loss": 0.0174, "step": 126470 }, { "epoch": 30.36, "learning_rate": 8.076547038931924e-05, "loss": 0.0257, "step": 126480 }, { "epoch": 30.37, "learning_rate": 8.076264070247511e-05, "loss": 0.0258, "step": 126490 }, { "epoch": 30.37, "learning_rate": 8.075981085708004e-05, "loss": 0.0128, "step": 126500 }, { "epoch": 30.37, "learning_rate": 8.075698085314866e-05, "loss": 0.0277, "step": 126510 }, { "epoch": 30.37, "learning_rate": 8.075415069069554e-05, "loss": 0.0301, "step": 126520 }, { "epoch": 30.37, "learning_rate": 8.075132036973527e-05, "loss": 0.0194, "step": 126530 }, { "epoch": 30.38, "learning_rate": 8.074848989028244e-05, "loss": 0.0315, "step": 126540 }, { "epoch": 30.38, "learning_rate": 8.074565925235164e-05, "loss": 0.0246, "step": 126550 }, { "epoch": 30.38, "learning_rate": 8.074282845595745e-05, "loss": 0.0159, "step": 126560 }, { "epoch": 30.38, "learning_rate": 8.073999750111448e-05, "loss": 0.0336, "step": 126570 }, { "epoch": 30.39, "learning_rate": 8.073716638783729e-05, "loss": 0.0186, "step": 126580 }, { "epoch": 30.39, "learning_rate": 8.073433511614047e-05, "loss": 0.0301, "step": 126590 }, { "epoch": 30.39, "learning_rate": 8.073150368603866e-05, "loss": 0.0247, "step": 126600 }, { "epoch": 30.39, "learning_rate": 8.072867209754642e-05, "loss": 0.0532, "step": 126610 }, { "epoch": 30.4, "learning_rate": 8.072584035067834e-05, "loss": 0.0412, "step": 126620 }, { "epoch": 30.4, "learning_rate": 8.072300844544902e-05, "loss": 0.0286, "step": 126630 }, { "epoch": 30.4, "learning_rate": 8.072017638187306e-05, "loss": 0.0267, "step": 126640 }, { "epoch": 30.4, "learning_rate": 8.071734415996506e-05, "loss": 0.0228, "step": 126650 }, { "epoch": 30.4, "learning_rate": 8.071451177973961e-05, "loss": 0.0178, "step": 126660 }, { "epoch": 30.41, "learning_rate": 8.07116792412113e-05, "loss": 0.0304, "step": 126670 }, { "epoch": 30.41, "learning_rate": 8.070884654439475e-05, "loss": 0.0213, "step": 126680 }, { "epoch": 30.41, "learning_rate": 8.070601368930456e-05, "loss": 0.0211, "step": 126690 }, { "epoch": 30.41, "learning_rate": 8.070318067595528e-05, "loss": 0.0277, "step": 126700 }, { "epoch": 30.42, "learning_rate": 8.070034750436157e-05, "loss": 0.0227, "step": 126710 }, { "epoch": 30.42, "learning_rate": 8.069751417453802e-05, "loss": 0.03, "step": 126720 }, { "epoch": 30.42, "learning_rate": 8.069468068649921e-05, "loss": 0.0347, "step": 126730 }, { "epoch": 30.42, "learning_rate": 8.069184704025978e-05, "loss": 0.0265, "step": 126740 }, { "epoch": 30.43, "learning_rate": 8.068901323583432e-05, "loss": 0.0291, "step": 126750 }, { "epoch": 30.43, "learning_rate": 8.068617927323739e-05, "loss": 0.0614, "step": 126760 }, { "epoch": 30.43, "learning_rate": 8.068334515248366e-05, "loss": 0.014, "step": 126770 }, { "epoch": 30.43, "learning_rate": 8.068051087358772e-05, "loss": 0.041, "step": 126780 }, { "epoch": 30.43, "learning_rate": 8.067767643656414e-05, "loss": 0.0219, "step": 126790 }, { "epoch": 30.44, "learning_rate": 8.067484184142759e-05, "loss": 0.0204, "step": 126800 }, { "epoch": 30.44, "learning_rate": 8.067200708819265e-05, "loss": 0.0338, "step": 126810 }, { "epoch": 30.44, "learning_rate": 8.066917217687391e-05, "loss": 0.024, "step": 126820 }, { "epoch": 30.44, "learning_rate": 8.066633710748601e-05, "loss": 0.0244, "step": 126830 }, { "epoch": 30.45, "learning_rate": 8.066350188004354e-05, "loss": 0.0203, "step": 126840 }, { "epoch": 30.45, "learning_rate": 8.066066649456114e-05, "loss": 0.0372, "step": 126850 }, { "epoch": 30.45, "learning_rate": 8.065783095105339e-05, "loss": 0.0207, "step": 126860 }, { "epoch": 30.45, "learning_rate": 8.065499524953494e-05, "loss": 0.0334, "step": 126870 }, { "epoch": 30.45, "learning_rate": 8.06521593900204e-05, "loss": 0.0248, "step": 126880 }, { "epoch": 30.46, "learning_rate": 8.064932337252435e-05, "loss": 0.0179, "step": 126890 }, { "epoch": 30.46, "learning_rate": 8.064648719706145e-05, "loss": 0.0324, "step": 126900 }, { "epoch": 30.46, "learning_rate": 8.064365086364628e-05, "loss": 0.0288, "step": 126910 }, { "epoch": 30.46, "learning_rate": 8.064081437229349e-05, "loss": 0.0432, "step": 126920 }, { "epoch": 30.47, "learning_rate": 8.063797772301768e-05, "loss": 0.0281, "step": 126930 }, { "epoch": 30.47, "learning_rate": 8.063514091583349e-05, "loss": 0.0188, "step": 126940 }, { "epoch": 30.47, "learning_rate": 8.063230395075551e-05, "loss": 0.023, "step": 126950 }, { "epoch": 30.47, "learning_rate": 8.062946682779839e-05, "loss": 0.0317, "step": 126960 }, { "epoch": 30.48, "learning_rate": 8.062662954697673e-05, "loss": 0.0298, "step": 126970 }, { "epoch": 30.48, "learning_rate": 8.062379210830518e-05, "loss": 0.0151, "step": 126980 }, { "epoch": 30.48, "learning_rate": 8.062095451179835e-05, "loss": 0.0281, "step": 126990 }, { "epoch": 30.48, "learning_rate": 8.061811675747084e-05, "loss": 0.015, "step": 127000 }, { "epoch": 30.48, "learning_rate": 8.061527884533732e-05, "loss": 0.0236, "step": 127010 }, { "epoch": 30.49, "learning_rate": 8.06124407754124e-05, "loss": 0.0445, "step": 127020 }, { "epoch": 30.49, "learning_rate": 8.06096025477107e-05, "loss": 0.0509, "step": 127030 }, { "epoch": 30.49, "learning_rate": 8.060676416224686e-05, "loss": 0.0233, "step": 127040 }, { "epoch": 30.49, "learning_rate": 8.06039256190355e-05, "loss": 0.0302, "step": 127050 }, { "epoch": 30.5, "learning_rate": 8.060108691809122e-05, "loss": 0.0285, "step": 127060 }, { "epoch": 30.5, "learning_rate": 8.059824805942873e-05, "loss": 0.0375, "step": 127070 }, { "epoch": 30.5, "learning_rate": 8.059540904306257e-05, "loss": 0.0248, "step": 127080 }, { "epoch": 30.5, "learning_rate": 8.059256986900746e-05, "loss": 0.0232, "step": 127090 }, { "epoch": 30.51, "learning_rate": 8.058973053727797e-05, "loss": 0.021, "step": 127100 }, { "epoch": 30.51, "learning_rate": 8.058689104788873e-05, "loss": 0.0307, "step": 127110 }, { "epoch": 30.51, "learning_rate": 8.058405140085442e-05, "loss": 0.0346, "step": 127120 }, { "epoch": 30.51, "learning_rate": 8.058121159618966e-05, "loss": 0.0216, "step": 127130 }, { "epoch": 30.51, "learning_rate": 8.057837163390907e-05, "loss": 0.023, "step": 127140 }, { "epoch": 30.52, "learning_rate": 8.05755315140273e-05, "loss": 0.0252, "step": 127150 }, { "epoch": 30.52, "learning_rate": 8.057269123655897e-05, "loss": 0.0453, "step": 127160 }, { "epoch": 30.52, "learning_rate": 8.056985080151875e-05, "loss": 0.0363, "step": 127170 }, { "epoch": 30.52, "learning_rate": 8.056701020892126e-05, "loss": 0.0247, "step": 127180 }, { "epoch": 30.53, "learning_rate": 8.056416945878115e-05, "loss": 0.0162, "step": 127190 }, { "epoch": 30.53, "learning_rate": 8.056132855111305e-05, "loss": 0.0194, "step": 127200 }, { "epoch": 30.53, "learning_rate": 8.05584874859316e-05, "loss": 0.0319, "step": 127210 }, { "epoch": 30.53, "learning_rate": 8.055564626325145e-05, "loss": 0.0365, "step": 127220 }, { "epoch": 30.53, "learning_rate": 8.055280488308725e-05, "loss": 0.0474, "step": 127230 }, { "epoch": 30.54, "learning_rate": 8.054996334545366e-05, "loss": 0.0475, "step": 127240 }, { "epoch": 30.54, "learning_rate": 8.054712165036528e-05, "loss": 0.027, "step": 127250 }, { "epoch": 30.54, "learning_rate": 8.054427979783678e-05, "loss": 0.0266, "step": 127260 }, { "epoch": 30.54, "learning_rate": 8.05414377878828e-05, "loss": 0.053, "step": 127270 }, { "epoch": 30.55, "learning_rate": 8.0538595620518e-05, "loss": 0.0524, "step": 127280 }, { "epoch": 30.55, "learning_rate": 8.053575329575702e-05, "loss": 0.0315, "step": 127290 }, { "epoch": 30.55, "learning_rate": 8.053291081361452e-05, "loss": 0.0468, "step": 127300 }, { "epoch": 30.55, "learning_rate": 8.053006817410514e-05, "loss": 0.0698, "step": 127310 }, { "epoch": 30.56, "learning_rate": 8.052722537724354e-05, "loss": 0.0463, "step": 127320 }, { "epoch": 30.56, "learning_rate": 8.052438242304437e-05, "loss": 0.0327, "step": 127330 }, { "epoch": 30.56, "learning_rate": 8.052153931152226e-05, "loss": 0.0402, "step": 127340 }, { "epoch": 30.56, "learning_rate": 8.051869604269188e-05, "loss": 0.0402, "step": 127350 }, { "epoch": 30.56, "learning_rate": 8.05158526165679e-05, "loss": 0.0346, "step": 127360 }, { "epoch": 30.57, "learning_rate": 8.051300903316494e-05, "loss": 0.0412, "step": 127370 }, { "epoch": 30.57, "learning_rate": 8.051016529249769e-05, "loss": 0.0245, "step": 127380 }, { "epoch": 30.57, "learning_rate": 8.050732139458081e-05, "loss": 0.0201, "step": 127390 }, { "epoch": 30.57, "learning_rate": 8.050447733942892e-05, "loss": 0.0299, "step": 127400 }, { "epoch": 30.58, "learning_rate": 8.05016331270567e-05, "loss": 0.0233, "step": 127410 }, { "epoch": 30.58, "learning_rate": 8.049878875747882e-05, "loss": 0.0423, "step": 127420 }, { "epoch": 30.58, "learning_rate": 8.04959442307099e-05, "loss": 0.0402, "step": 127430 }, { "epoch": 30.58, "learning_rate": 8.049309954676465e-05, "loss": 0.0302, "step": 127440 }, { "epoch": 30.59, "learning_rate": 8.049025470565773e-05, "loss": 0.0412, "step": 127450 }, { "epoch": 30.59, "learning_rate": 8.048740970740375e-05, "loss": 0.0292, "step": 127460 }, { "epoch": 30.59, "learning_rate": 8.048456455201742e-05, "loss": 0.0547, "step": 127470 }, { "epoch": 30.59, "learning_rate": 8.048171923951337e-05, "loss": 0.0701, "step": 127480 }, { "epoch": 30.59, "learning_rate": 8.047887376990631e-05, "loss": 0.0282, "step": 127490 }, { "epoch": 30.6, "learning_rate": 8.047602814321086e-05, "loss": 0.0238, "step": 127500 }, { "epoch": 30.6, "learning_rate": 8.047318235944172e-05, "loss": 0.0292, "step": 127510 }, { "epoch": 30.6, "learning_rate": 8.047033641861353e-05, "loss": 0.0393, "step": 127520 }, { "epoch": 30.6, "learning_rate": 8.046749032074099e-05, "loss": 0.0351, "step": 127530 }, { "epoch": 30.61, "learning_rate": 8.046464406583873e-05, "loss": 0.0316, "step": 127540 }, { "epoch": 30.61, "learning_rate": 8.046179765392146e-05, "loss": 0.0387, "step": 127550 }, { "epoch": 30.61, "learning_rate": 8.045895108500382e-05, "loss": 0.023, "step": 127560 }, { "epoch": 30.61, "learning_rate": 8.04561043591005e-05, "loss": 0.0203, "step": 127570 }, { "epoch": 30.61, "learning_rate": 8.045325747622614e-05, "loss": 0.0364, "step": 127580 }, { "epoch": 30.62, "learning_rate": 8.045041043639545e-05, "loss": 0.0403, "step": 127590 }, { "epoch": 30.62, "learning_rate": 8.04475632396231e-05, "loss": 0.0427, "step": 127600 }, { "epoch": 30.62, "learning_rate": 8.044471588592375e-05, "loss": 0.0349, "step": 127610 }, { "epoch": 30.62, "learning_rate": 8.044186837531207e-05, "loss": 0.0304, "step": 127620 }, { "epoch": 30.63, "learning_rate": 8.043902070780276e-05, "loss": 0.0208, "step": 127630 }, { "epoch": 30.63, "learning_rate": 8.043617288341047e-05, "loss": 0.0293, "step": 127640 }, { "epoch": 30.63, "learning_rate": 8.04333249021499e-05, "loss": 0.0333, "step": 127650 }, { "epoch": 30.63, "learning_rate": 8.04304767640357e-05, "loss": 0.0441, "step": 127660 }, { "epoch": 30.64, "learning_rate": 8.042762846908258e-05, "loss": 0.0283, "step": 127670 }, { "epoch": 30.64, "learning_rate": 8.042478001730522e-05, "loss": 0.0409, "step": 127680 }, { "epoch": 30.64, "learning_rate": 8.042193140871828e-05, "loss": 0.0299, "step": 127690 }, { "epoch": 30.64, "learning_rate": 8.041908264333645e-05, "loss": 0.0179, "step": 127700 }, { "epoch": 30.64, "learning_rate": 8.041623372117441e-05, "loss": 0.0427, "step": 127710 }, { "epoch": 30.65, "learning_rate": 8.041338464224686e-05, "loss": 0.0363, "step": 127720 }, { "epoch": 30.65, "learning_rate": 8.041053540656847e-05, "loss": 0.0266, "step": 127730 }, { "epoch": 30.65, "learning_rate": 8.040768601415392e-05, "loss": 0.0614, "step": 127740 }, { "epoch": 30.65, "learning_rate": 8.040483646501791e-05, "loss": 0.0357, "step": 127750 }, { "epoch": 30.66, "learning_rate": 8.04019867591751e-05, "loss": 0.0251, "step": 127760 }, { "epoch": 30.66, "learning_rate": 8.039913689664021e-05, "loss": 0.0767, "step": 127770 }, { "epoch": 30.66, "learning_rate": 8.039628687742791e-05, "loss": 0.0267, "step": 127780 }, { "epoch": 30.66, "learning_rate": 8.039343670155289e-05, "loss": 0.0287, "step": 127790 }, { "epoch": 30.66, "learning_rate": 8.039058636902985e-05, "loss": 0.0137, "step": 127800 }, { "epoch": 30.67, "learning_rate": 8.038773587987348e-05, "loss": 0.0253, "step": 127810 }, { "epoch": 30.67, "learning_rate": 8.038488523409846e-05, "loss": 0.0193, "step": 127820 }, { "epoch": 30.67, "learning_rate": 8.038203443171948e-05, "loss": 0.0234, "step": 127830 }, { "epoch": 30.67, "learning_rate": 8.037918347275124e-05, "loss": 0.022, "step": 127840 }, { "epoch": 30.68, "learning_rate": 8.037633235720845e-05, "loss": 0.0276, "step": 127850 }, { "epoch": 30.68, "learning_rate": 8.037348108510578e-05, "loss": 0.0339, "step": 127860 }, { "epoch": 30.68, "learning_rate": 8.037062965645792e-05, "loss": 0.0546, "step": 127870 }, { "epoch": 30.68, "learning_rate": 8.03677780712796e-05, "loss": 0.0292, "step": 127880 }, { "epoch": 30.69, "learning_rate": 8.03649263295855e-05, "loss": 0.0347, "step": 127890 }, { "epoch": 30.69, "learning_rate": 8.03620744313903e-05, "loss": 0.0403, "step": 127900 }, { "epoch": 30.69, "learning_rate": 8.035922237670872e-05, "loss": 0.0407, "step": 127910 }, { "epoch": 30.69, "learning_rate": 8.035637016555546e-05, "loss": 0.026, "step": 127920 }, { "epoch": 30.69, "learning_rate": 8.035351779794522e-05, "loss": 0.0231, "step": 127930 }, { "epoch": 30.7, "learning_rate": 8.035066527389267e-05, "loss": 0.044, "step": 127940 }, { "epoch": 30.7, "learning_rate": 8.034781259341257e-05, "loss": 0.0323, "step": 127950 }, { "epoch": 30.7, "learning_rate": 8.034495975651957e-05, "loss": 0.0251, "step": 127960 }, { "epoch": 30.7, "learning_rate": 8.03421067632284e-05, "loss": 0.0408, "step": 127970 }, { "epoch": 30.71, "learning_rate": 8.033925361355376e-05, "loss": 0.0245, "step": 127980 }, { "epoch": 30.71, "learning_rate": 8.033640030751035e-05, "loss": 0.0302, "step": 127990 }, { "epoch": 30.71, "learning_rate": 8.033354684511287e-05, "loss": 0.0267, "step": 128000 }, { "epoch": 30.71, "learning_rate": 8.033069322637605e-05, "loss": 0.0306, "step": 128010 }, { "epoch": 30.72, "learning_rate": 8.032783945131458e-05, "loss": 0.032, "step": 128020 }, { "epoch": 30.72, "learning_rate": 8.032498551994317e-05, "loss": 0.0218, "step": 128030 }, { "epoch": 30.72, "learning_rate": 8.032213143227654e-05, "loss": 0.0389, "step": 128040 }, { "epoch": 30.72, "learning_rate": 8.031927718832938e-05, "loss": 0.0358, "step": 128050 }, { "epoch": 30.72, "learning_rate": 8.031642278811641e-05, "loss": 0.0211, "step": 128060 }, { "epoch": 30.73, "learning_rate": 8.031356823165235e-05, "loss": 0.0214, "step": 128070 }, { "epoch": 30.73, "learning_rate": 8.031071351895191e-05, "loss": 0.0235, "step": 128080 }, { "epoch": 30.73, "learning_rate": 8.030785865002978e-05, "loss": 0.0179, "step": 128090 }, { "epoch": 30.73, "learning_rate": 8.030500362490072e-05, "loss": 0.0593, "step": 128100 }, { "epoch": 30.74, "learning_rate": 8.03021484435794e-05, "loss": 0.0298, "step": 128110 }, { "epoch": 30.74, "learning_rate": 8.029929310608057e-05, "loss": 0.0407, "step": 128120 }, { "epoch": 30.74, "learning_rate": 8.029643761241892e-05, "loss": 0.0355, "step": 128130 }, { "epoch": 30.74, "learning_rate": 8.029358196260916e-05, "loss": 0.036, "step": 128140 }, { "epoch": 30.74, "learning_rate": 8.029072615666604e-05, "loss": 0.0324, "step": 128150 }, { "epoch": 30.75, "learning_rate": 8.028787019460427e-05, "loss": 0.0642, "step": 128160 }, { "epoch": 30.75, "learning_rate": 8.028501407643856e-05, "loss": 0.0326, "step": 128170 }, { "epoch": 30.75, "learning_rate": 8.028215780218365e-05, "loss": 0.0463, "step": 128180 }, { "epoch": 30.75, "learning_rate": 8.027930137185422e-05, "loss": 0.0224, "step": 128190 }, { "epoch": 30.76, "learning_rate": 8.027644478546503e-05, "loss": 0.042, "step": 128200 }, { "epoch": 30.76, "learning_rate": 8.027358804303078e-05, "loss": 0.0226, "step": 128210 }, { "epoch": 30.76, "learning_rate": 8.02707311445662e-05, "loss": 0.0358, "step": 128220 }, { "epoch": 30.76, "learning_rate": 8.026787409008603e-05, "loss": 0.0185, "step": 128230 }, { "epoch": 30.77, "learning_rate": 8.026501687960499e-05, "loss": 0.0269, "step": 128240 }, { "epoch": 30.77, "learning_rate": 8.02621595131378e-05, "loss": 0.0301, "step": 128250 }, { "epoch": 30.77, "learning_rate": 8.025930199069918e-05, "loss": 0.0242, "step": 128260 }, { "epoch": 30.77, "learning_rate": 8.025644431230387e-05, "loss": 0.0256, "step": 128270 }, { "epoch": 30.77, "learning_rate": 8.025358647796659e-05, "loss": 0.0308, "step": 128280 }, { "epoch": 30.78, "learning_rate": 8.025072848770206e-05, "loss": 0.0404, "step": 128290 }, { "epoch": 30.78, "learning_rate": 8.024787034152504e-05, "loss": 0.0144, "step": 128300 }, { "epoch": 30.78, "learning_rate": 8.024501203945024e-05, "loss": 0.0395, "step": 128310 }, { "epoch": 30.78, "learning_rate": 8.024215358149238e-05, "loss": 0.0221, "step": 128320 }, { "epoch": 30.79, "learning_rate": 8.023929496766622e-05, "loss": 0.0186, "step": 128330 }, { "epoch": 30.79, "learning_rate": 8.023643619798649e-05, "loss": 0.0153, "step": 128340 }, { "epoch": 30.79, "learning_rate": 8.023357727246791e-05, "loss": 0.0351, "step": 128350 }, { "epoch": 30.79, "learning_rate": 8.023071819112522e-05, "loss": 0.0233, "step": 128360 }, { "epoch": 30.8, "learning_rate": 8.022785895397315e-05, "loss": 0.0316, "step": 128370 }, { "epoch": 30.8, "learning_rate": 8.022499956102643e-05, "loss": 0.0295, "step": 128380 }, { "epoch": 30.8, "learning_rate": 8.022214001229984e-05, "loss": 0.0285, "step": 128390 }, { "epoch": 30.8, "learning_rate": 8.021928030780806e-05, "loss": 0.0384, "step": 128400 }, { "epoch": 30.8, "learning_rate": 8.021642044756587e-05, "loss": 0.0378, "step": 128410 }, { "epoch": 30.81, "learning_rate": 8.021356043158799e-05, "loss": 0.021, "step": 128420 }, { "epoch": 30.81, "learning_rate": 8.021070025988917e-05, "loss": 0.0232, "step": 128430 }, { "epoch": 30.81, "learning_rate": 8.020783993248415e-05, "loss": 0.0301, "step": 128440 }, { "epoch": 30.81, "learning_rate": 8.020497944938768e-05, "loss": 0.0279, "step": 128450 }, { "epoch": 30.82, "learning_rate": 8.020211881061449e-05, "loss": 0.0238, "step": 128460 }, { "epoch": 30.82, "learning_rate": 8.019925801617931e-05, "loss": 0.031, "step": 128470 }, { "epoch": 30.82, "learning_rate": 8.019639706609692e-05, "loss": 0.0244, "step": 128480 }, { "epoch": 30.82, "learning_rate": 8.019353596038204e-05, "loss": 0.0323, "step": 128490 }, { "epoch": 30.82, "learning_rate": 8.019067469904941e-05, "loss": 0.0539, "step": 128500 }, { "epoch": 30.83, "learning_rate": 8.018781328211381e-05, "loss": 0.0396, "step": 128510 }, { "epoch": 30.83, "learning_rate": 8.018495170958996e-05, "loss": 0.0331, "step": 128520 }, { "epoch": 30.83, "learning_rate": 8.018208998149262e-05, "loss": 0.0285, "step": 128530 }, { "epoch": 30.83, "learning_rate": 8.017922809783655e-05, "loss": 0.0377, "step": 128540 }, { "epoch": 30.84, "learning_rate": 8.017636605863646e-05, "loss": 0.0371, "step": 128550 }, { "epoch": 30.84, "learning_rate": 8.017350386390713e-05, "loss": 0.0293, "step": 128560 }, { "epoch": 30.84, "learning_rate": 8.017064151366332e-05, "loss": 0.0249, "step": 128570 }, { "epoch": 30.84, "learning_rate": 8.016777900791977e-05, "loss": 0.0271, "step": 128580 }, { "epoch": 30.85, "learning_rate": 8.016491634669124e-05, "loss": 0.0232, "step": 128590 }, { "epoch": 30.85, "learning_rate": 8.016205352999246e-05, "loss": 0.0144, "step": 128600 }, { "epoch": 30.85, "learning_rate": 8.015919055783823e-05, "loss": 0.0456, "step": 128610 }, { "epoch": 30.85, "learning_rate": 8.015632743024326e-05, "loss": 0.0232, "step": 128620 }, { "epoch": 30.85, "learning_rate": 8.015346414722233e-05, "loss": 0.0179, "step": 128630 }, { "epoch": 30.86, "learning_rate": 8.015060070879019e-05, "loss": 0.0277, "step": 128640 }, { "epoch": 30.86, "learning_rate": 8.01477371149616e-05, "loss": 0.0161, "step": 128650 }, { "epoch": 30.86, "learning_rate": 8.014487336575134e-05, "loss": 0.044, "step": 128660 }, { "epoch": 30.86, "learning_rate": 8.014200946117413e-05, "loss": 0.0374, "step": 128670 }, { "epoch": 30.87, "learning_rate": 8.013914540124477e-05, "loss": 0.0372, "step": 128680 }, { "epoch": 30.87, "learning_rate": 8.013628118597799e-05, "loss": 0.0282, "step": 128690 }, { "epoch": 30.87, "learning_rate": 8.013341681538857e-05, "loss": 0.0278, "step": 128700 }, { "epoch": 30.87, "learning_rate": 8.013055228949127e-05, "loss": 0.0196, "step": 128710 }, { "epoch": 30.88, "learning_rate": 8.012768760830084e-05, "loss": 0.0313, "step": 128720 }, { "epoch": 30.88, "learning_rate": 8.012482277183206e-05, "loss": 0.0262, "step": 128730 }, { "epoch": 30.88, "learning_rate": 8.01219577800997e-05, "loss": 0.0175, "step": 128740 }, { "epoch": 30.88, "learning_rate": 8.011909263311853e-05, "loss": 0.0307, "step": 128750 }, { "epoch": 30.88, "learning_rate": 8.011622733090326e-05, "loss": 0.0239, "step": 128760 }, { "epoch": 30.89, "learning_rate": 8.011336187346874e-05, "loss": 0.0372, "step": 128770 }, { "epoch": 30.89, "learning_rate": 8.011049626082969e-05, "loss": 0.0337, "step": 128780 }, { "epoch": 30.89, "learning_rate": 8.010763049300089e-05, "loss": 0.0192, "step": 128790 }, { "epoch": 30.89, "learning_rate": 8.010476456999712e-05, "loss": 0.0224, "step": 128800 }, { "epoch": 30.9, "learning_rate": 8.010189849183312e-05, "loss": 0.0198, "step": 128810 }, { "epoch": 30.9, "learning_rate": 8.009903225852371e-05, "loss": 0.03, "step": 128820 }, { "epoch": 30.9, "learning_rate": 8.009616587008363e-05, "loss": 0.0255, "step": 128830 }, { "epoch": 30.9, "learning_rate": 8.009329932652766e-05, "loss": 0.0297, "step": 128840 }, { "epoch": 30.9, "learning_rate": 8.009043262787055e-05, "loss": 0.0177, "step": 128850 }, { "epoch": 30.91, "learning_rate": 8.008756577412711e-05, "loss": 0.0142, "step": 128860 }, { "epoch": 30.91, "learning_rate": 8.008469876531212e-05, "loss": 0.0326, "step": 128870 }, { "epoch": 30.91, "learning_rate": 8.008183160144033e-05, "loss": 0.0286, "step": 128880 }, { "epoch": 30.91, "learning_rate": 8.007896428252654e-05, "loss": 0.0414, "step": 128890 }, { "epoch": 30.92, "learning_rate": 8.00760968085855e-05, "loss": 0.0288, "step": 128900 }, { "epoch": 30.92, "learning_rate": 8.007322917963201e-05, "loss": 0.0373, "step": 128910 }, { "epoch": 30.92, "learning_rate": 8.007036139568085e-05, "loss": 0.0245, "step": 128920 }, { "epoch": 30.92, "learning_rate": 8.00674934567468e-05, "loss": 0.0298, "step": 128930 }, { "epoch": 30.93, "learning_rate": 8.006462536284462e-05, "loss": 0.0212, "step": 128940 }, { "epoch": 30.93, "learning_rate": 8.006175711398912e-05, "loss": 0.0164, "step": 128950 }, { "epoch": 30.93, "learning_rate": 8.005888871019507e-05, "loss": 0.0328, "step": 128960 }, { "epoch": 30.93, "learning_rate": 8.005602015147727e-05, "loss": 0.022, "step": 128970 }, { "epoch": 30.93, "learning_rate": 8.005315143785049e-05, "loss": 0.0274, "step": 128980 }, { "epoch": 30.94, "learning_rate": 8.00502825693295e-05, "loss": 0.0301, "step": 128990 }, { "epoch": 30.94, "learning_rate": 8.004741354592911e-05, "loss": 0.026, "step": 129000 }, { "epoch": 30.94, "learning_rate": 8.00445443676641e-05, "loss": 0.0274, "step": 129010 }, { "epoch": 30.94, "learning_rate": 8.004167503454924e-05, "loss": 0.0241, "step": 129020 }, { "epoch": 30.95, "learning_rate": 8.003880554659936e-05, "loss": 0.0304, "step": 129030 }, { "epoch": 30.95, "learning_rate": 8.003593590382922e-05, "loss": 0.0219, "step": 129040 }, { "epoch": 30.95, "learning_rate": 8.003306610625362e-05, "loss": 0.0193, "step": 129050 }, { "epoch": 31.0, "learning_rate": 8.003019615388734e-05, "loss": 0.0237, "step": 129060 }, { "epoch": 31.0, "learning_rate": 8.002732604674517e-05, "loss": 0.0315, "step": 129070 }, { "epoch": 31.01, "learning_rate": 8.002445578484192e-05, "loss": 0.0257, "step": 129080 }, { "epoch": 31.01, "learning_rate": 8.002158536819238e-05, "loss": 0.0187, "step": 129090 }, { "epoch": 31.01, "learning_rate": 8.00187147968113e-05, "loss": 0.0265, "step": 129100 }, { "epoch": 31.01, "learning_rate": 8.001584407071356e-05, "loss": 0.0305, "step": 129110 }, { "epoch": 31.02, "learning_rate": 8.00129731899139e-05, "loss": 0.0465, "step": 129120 }, { "epoch": 31.02, "learning_rate": 8.001010215442712e-05, "loss": 0.0389, "step": 129130 }, { "epoch": 31.02, "learning_rate": 8.000723096426801e-05, "loss": 0.0301, "step": 129140 }, { "epoch": 31.02, "learning_rate": 8.000435961945138e-05, "loss": 0.0168, "step": 129150 }, { "epoch": 31.02, "learning_rate": 8.000148811999204e-05, "loss": 0.0274, "step": 129160 }, { "epoch": 31.03, "learning_rate": 7.999861646590479e-05, "loss": 0.0192, "step": 129170 }, { "epoch": 31.03, "learning_rate": 7.999574465720441e-05, "loss": 0.0189, "step": 129180 }, { "epoch": 31.03, "learning_rate": 7.999287269390571e-05, "loss": 0.0233, "step": 129190 }, { "epoch": 31.03, "learning_rate": 7.99900005760235e-05, "loss": 0.0201, "step": 129200 }, { "epoch": 31.04, "learning_rate": 7.998712830357255e-05, "loss": 0.0273, "step": 129210 }, { "epoch": 31.04, "learning_rate": 7.998425587656772e-05, "loss": 0.0385, "step": 129220 }, { "epoch": 31.04, "learning_rate": 7.998138329502378e-05, "loss": 0.022, "step": 129230 }, { "epoch": 31.04, "learning_rate": 7.997851055895553e-05, "loss": 0.0422, "step": 129240 }, { "epoch": 31.05, "learning_rate": 7.997563766837778e-05, "loss": 0.0206, "step": 129250 }, { "epoch": 31.05, "learning_rate": 7.997276462330536e-05, "loss": 0.0261, "step": 129260 }, { "epoch": 31.05, "learning_rate": 7.996989142375306e-05, "loss": 0.0214, "step": 129270 }, { "epoch": 31.05, "learning_rate": 7.996701806973568e-05, "loss": 0.0254, "step": 129280 }, { "epoch": 31.05, "learning_rate": 7.996414456126804e-05, "loss": 0.0271, "step": 129290 }, { "epoch": 31.06, "learning_rate": 7.996127089836495e-05, "loss": 0.0253, "step": 129300 }, { "epoch": 31.06, "learning_rate": 7.995839708104122e-05, "loss": 0.0387, "step": 129310 }, { "epoch": 31.06, "learning_rate": 7.995552310931168e-05, "loss": 0.0275, "step": 129320 }, { "epoch": 31.06, "learning_rate": 7.995264898319109e-05, "loss": 0.0224, "step": 129330 }, { "epoch": 31.07, "learning_rate": 7.994977470269432e-05, "loss": 0.0243, "step": 129340 }, { "epoch": 31.07, "learning_rate": 7.994690026783613e-05, "loss": 0.0255, "step": 129350 }, { "epoch": 31.07, "learning_rate": 7.99440256786314e-05, "loss": 0.0261, "step": 129360 }, { "epoch": 31.07, "learning_rate": 7.994115093509489e-05, "loss": 0.0479, "step": 129370 }, { "epoch": 31.07, "learning_rate": 7.993827603724144e-05, "loss": 0.0233, "step": 129380 }, { "epoch": 31.08, "learning_rate": 7.993540098508589e-05, "loss": 0.0275, "step": 129390 }, { "epoch": 31.08, "learning_rate": 7.9932525778643e-05, "loss": 0.0411, "step": 129400 }, { "epoch": 31.08, "learning_rate": 7.992965041792765e-05, "loss": 0.0474, "step": 129410 }, { "epoch": 31.08, "learning_rate": 7.992677490295461e-05, "loss": 0.0268, "step": 129420 }, { "epoch": 31.09, "learning_rate": 7.992389923373873e-05, "loss": 0.0333, "step": 129430 }, { "epoch": 31.09, "learning_rate": 7.992102341029483e-05, "loss": 0.0369, "step": 129440 }, { "epoch": 31.09, "learning_rate": 7.991814743263772e-05, "loss": 0.0193, "step": 129450 }, { "epoch": 31.09, "learning_rate": 7.991527130078222e-05, "loss": 0.0202, "step": 129460 }, { "epoch": 31.1, "learning_rate": 7.991239501474317e-05, "loss": 0.0186, "step": 129470 }, { "epoch": 31.1, "learning_rate": 7.990951857453539e-05, "loss": 0.0411, "step": 129480 }, { "epoch": 31.1, "learning_rate": 7.99066419801737e-05, "loss": 0.0217, "step": 129490 }, { "epoch": 31.1, "learning_rate": 7.99037652316729e-05, "loss": 0.0249, "step": 129500 }, { "epoch": 31.1, "learning_rate": 7.990088832904787e-05, "loss": 0.0277, "step": 129510 }, { "epoch": 31.11, "learning_rate": 7.989801127231342e-05, "loss": 0.0358, "step": 129520 }, { "epoch": 31.11, "learning_rate": 7.989513406148436e-05, "loss": 0.0253, "step": 129530 }, { "epoch": 31.11, "learning_rate": 7.989225669657552e-05, "loss": 0.0174, "step": 129540 }, { "epoch": 31.11, "learning_rate": 7.988937917760176e-05, "loss": 0.0162, "step": 129550 }, { "epoch": 31.12, "learning_rate": 7.988650150457787e-05, "loss": 0.02, "step": 129560 }, { "epoch": 31.12, "learning_rate": 7.988362367751871e-05, "loss": 0.0339, "step": 129570 }, { "epoch": 31.12, "learning_rate": 7.98807456964391e-05, "loss": 0.0157, "step": 129580 }, { "epoch": 31.12, "learning_rate": 7.987786756135387e-05, "loss": 0.0152, "step": 129590 }, { "epoch": 31.12, "learning_rate": 7.987498927227788e-05, "loss": 0.0245, "step": 129600 }, { "epoch": 31.13, "learning_rate": 7.987211082922593e-05, "loss": 0.0215, "step": 129610 }, { "epoch": 31.13, "learning_rate": 7.986923223221287e-05, "loss": 0.0203, "step": 129620 }, { "epoch": 31.13, "learning_rate": 7.986635348125356e-05, "loss": 0.0351, "step": 129630 }, { "epoch": 31.13, "learning_rate": 7.986347457636279e-05, "loss": 0.0174, "step": 129640 }, { "epoch": 31.14, "learning_rate": 7.986059551755543e-05, "loss": 0.0406, "step": 129650 }, { "epoch": 31.14, "learning_rate": 7.985771630484631e-05, "loss": 0.0198, "step": 129660 }, { "epoch": 31.14, "learning_rate": 7.985483693825027e-05, "loss": 0.0251, "step": 129670 }, { "epoch": 31.14, "learning_rate": 7.985195741778216e-05, "loss": 0.0151, "step": 129680 }, { "epoch": 31.15, "learning_rate": 7.98490777434568e-05, "loss": 0.0181, "step": 129690 }, { "epoch": 31.15, "learning_rate": 7.984619791528905e-05, "loss": 0.028, "step": 129700 }, { "epoch": 31.15, "learning_rate": 7.984331793329375e-05, "loss": 0.0245, "step": 129710 }, { "epoch": 31.15, "learning_rate": 7.984043779748573e-05, "loss": 0.0258, "step": 129720 }, { "epoch": 31.15, "learning_rate": 7.983755750787984e-05, "loss": 0.0302, "step": 129730 }, { "epoch": 31.16, "learning_rate": 7.983467706449095e-05, "loss": 0.0185, "step": 129740 }, { "epoch": 31.16, "learning_rate": 7.983179646733387e-05, "loss": 0.0343, "step": 129750 }, { "epoch": 31.16, "learning_rate": 7.982891571642347e-05, "loss": 0.038, "step": 129760 }, { "epoch": 31.16, "learning_rate": 7.982603481177459e-05, "loss": 0.0143, "step": 129770 }, { "epoch": 31.17, "learning_rate": 7.982315375340206e-05, "loss": 0.0156, "step": 129780 }, { "epoch": 31.17, "learning_rate": 7.982027254132076e-05, "loss": 0.0303, "step": 129790 }, { "epoch": 31.17, "learning_rate": 7.981739117554551e-05, "loss": 0.0158, "step": 129800 }, { "epoch": 31.17, "learning_rate": 7.98145096560912e-05, "loss": 0.0389, "step": 129810 }, { "epoch": 31.18, "learning_rate": 7.981162798297266e-05, "loss": 0.0311, "step": 129820 }, { "epoch": 31.18, "learning_rate": 7.980874615620473e-05, "loss": 0.0293, "step": 129830 }, { "epoch": 31.18, "learning_rate": 7.980586417580227e-05, "loss": 0.012, "step": 129840 }, { "epoch": 31.18, "learning_rate": 7.980298204178014e-05, "loss": 0.055, "step": 129850 }, { "epoch": 31.18, "learning_rate": 7.98000997541532e-05, "loss": 0.0119, "step": 129860 }, { "epoch": 31.19, "learning_rate": 7.979721731293628e-05, "loss": 0.0225, "step": 129870 }, { "epoch": 31.19, "learning_rate": 7.979433471814426e-05, "loss": 0.031, "step": 129880 }, { "epoch": 31.19, "learning_rate": 7.979145196979199e-05, "loss": 0.0301, "step": 129890 }, { "epoch": 31.19, "learning_rate": 7.978856906789433e-05, "loss": 0.0324, "step": 129900 }, { "epoch": 31.2, "learning_rate": 7.978568601246612e-05, "loss": 0.0224, "step": 129910 }, { "epoch": 31.2, "learning_rate": 7.978280280352226e-05, "loss": 0.0254, "step": 129920 }, { "epoch": 31.2, "learning_rate": 7.977991944107756e-05, "loss": 0.0217, "step": 129930 }, { "epoch": 31.2, "learning_rate": 7.977703592514692e-05, "loss": 0.0193, "step": 129940 }, { "epoch": 31.2, "learning_rate": 7.977415225574519e-05, "loss": 0.0224, "step": 129950 }, { "epoch": 31.21, "learning_rate": 7.977126843288724e-05, "loss": 0.0176, "step": 129960 }, { "epoch": 31.21, "learning_rate": 7.976838445658792e-05, "loss": 0.0159, "step": 129970 }, { "epoch": 31.21, "learning_rate": 7.976550032686207e-05, "loss": 0.0173, "step": 129980 }, { "epoch": 31.21, "learning_rate": 7.976261604372462e-05, "loss": 0.0299, "step": 129990 }, { "epoch": 31.22, "learning_rate": 7.975973160719036e-05, "loss": 0.0205, "step": 130000 }, { "epoch": 31.22, "learning_rate": 7.975684701727423e-05, "loss": 0.0239, "step": 130010 }, { "epoch": 31.22, "learning_rate": 7.975396227399105e-05, "loss": 0.0167, "step": 130020 }, { "epoch": 31.22, "learning_rate": 7.975107737735569e-05, "loss": 0.0365, "step": 130030 }, { "epoch": 31.23, "learning_rate": 7.974819232738305e-05, "loss": 0.036, "step": 130040 }, { "epoch": 31.23, "learning_rate": 7.974530712408795e-05, "loss": 0.0251, "step": 130050 }, { "epoch": 31.23, "learning_rate": 7.97424217674853e-05, "loss": 0.0243, "step": 130060 }, { "epoch": 31.23, "learning_rate": 7.973953625758996e-05, "loss": 0.0187, "step": 130070 }, { "epoch": 31.23, "learning_rate": 7.973665059441681e-05, "loss": 0.0368, "step": 130080 }, { "epoch": 31.24, "learning_rate": 7.973376477798071e-05, "loss": 0.0174, "step": 130090 }, { "epoch": 31.24, "learning_rate": 7.973087880829653e-05, "loss": 0.0282, "step": 130100 }, { "epoch": 31.24, "learning_rate": 7.972799268537916e-05, "loss": 0.0393, "step": 130110 }, { "epoch": 31.24, "learning_rate": 7.972510640924346e-05, "loss": 0.0201, "step": 130120 }, { "epoch": 31.25, "learning_rate": 7.972221997990432e-05, "loss": 0.021, "step": 130130 }, { "epoch": 31.25, "learning_rate": 7.97193333973766e-05, "loss": 0.0311, "step": 130140 }, { "epoch": 31.25, "learning_rate": 7.97164466616752e-05, "loss": 0.0231, "step": 130150 }, { "epoch": 31.25, "learning_rate": 7.971355977281499e-05, "loss": 0.0464, "step": 130160 }, { "epoch": 31.26, "learning_rate": 7.971067273081082e-05, "loss": 0.0207, "step": 130170 }, { "epoch": 31.26, "learning_rate": 7.970778553567762e-05, "loss": 0.0096, "step": 130180 }, { "epoch": 31.26, "learning_rate": 7.970489818743023e-05, "loss": 0.0379, "step": 130190 }, { "epoch": 31.26, "learning_rate": 7.970201068608355e-05, "loss": 0.0142, "step": 130200 }, { "epoch": 31.26, "learning_rate": 7.969912303165246e-05, "loss": 0.0246, "step": 130210 }, { "epoch": 31.27, "learning_rate": 7.969623522415183e-05, "loss": 0.0254, "step": 130220 }, { "epoch": 31.27, "learning_rate": 7.969334726359658e-05, "loss": 0.0164, "step": 130230 }, { "epoch": 31.27, "learning_rate": 7.969045915000155e-05, "loss": 0.0208, "step": 130240 }, { "epoch": 31.27, "learning_rate": 7.968757088338166e-05, "loss": 0.0323, "step": 130250 }, { "epoch": 31.28, "learning_rate": 7.968468246375178e-05, "loss": 0.0268, "step": 130260 }, { "epoch": 31.28, "learning_rate": 7.968179389112677e-05, "loss": 0.0378, "step": 130270 }, { "epoch": 31.28, "learning_rate": 7.967890516552158e-05, "loss": 0.0174, "step": 130280 }, { "epoch": 31.28, "learning_rate": 7.967601628695105e-05, "loss": 0.0302, "step": 130290 }, { "epoch": 31.28, "learning_rate": 7.967312725543008e-05, "loss": 0.0113, "step": 130300 }, { "epoch": 31.29, "learning_rate": 7.967023807097358e-05, "loss": 0.0169, "step": 130310 }, { "epoch": 31.29, "learning_rate": 7.96673487335964e-05, "loss": 0.0278, "step": 130320 }, { "epoch": 31.29, "learning_rate": 7.966445924331349e-05, "loss": 0.0189, "step": 130330 }, { "epoch": 31.29, "learning_rate": 7.966156960013969e-05, "loss": 0.025, "step": 130340 }, { "epoch": 31.3, "learning_rate": 7.965867980408991e-05, "loss": 0.0203, "step": 130350 }, { "epoch": 31.3, "learning_rate": 7.965578985517905e-05, "loss": 0.019, "step": 130360 }, { "epoch": 31.3, "learning_rate": 7.9652899753422e-05, "loss": 0.0242, "step": 130370 }, { "epoch": 31.3, "learning_rate": 7.965000949883366e-05, "loss": 0.0297, "step": 130380 }, { "epoch": 31.31, "learning_rate": 7.964711909142892e-05, "loss": 0.0216, "step": 130390 }, { "epoch": 31.31, "learning_rate": 7.964422853122268e-05, "loss": 0.0213, "step": 130400 }, { "epoch": 31.31, "learning_rate": 7.964133781822984e-05, "loss": 0.0117, "step": 130410 }, { "epoch": 31.31, "learning_rate": 7.96384469524653e-05, "loss": 0.0182, "step": 130420 }, { "epoch": 31.31, "learning_rate": 7.963555593394395e-05, "loss": 0.031, "step": 130430 }, { "epoch": 31.32, "learning_rate": 7.963266476268069e-05, "loss": 0.0235, "step": 130440 }, { "epoch": 31.32, "learning_rate": 7.962977343869045e-05, "loss": 0.0164, "step": 130450 }, { "epoch": 31.32, "learning_rate": 7.96268819619881e-05, "loss": 0.0296, "step": 130460 }, { "epoch": 31.32, "learning_rate": 7.962399033258857e-05, "loss": 0.0218, "step": 130470 }, { "epoch": 31.33, "learning_rate": 7.96210985505067e-05, "loss": 0.0104, "step": 130480 }, { "epoch": 31.33, "learning_rate": 7.961820661575747e-05, "loss": 0.0653, "step": 130490 }, { "epoch": 31.33, "learning_rate": 7.961531452835576e-05, "loss": 0.0241, "step": 130500 }, { "epoch": 31.33, "learning_rate": 7.961242228831647e-05, "loss": 0.0533, "step": 130510 }, { "epoch": 31.34, "learning_rate": 7.96095298956545e-05, "loss": 0.0213, "step": 130520 }, { "epoch": 31.34, "learning_rate": 7.960663735038476e-05, "loss": 0.0269, "step": 130530 }, { "epoch": 31.34, "learning_rate": 7.960374465252218e-05, "loss": 0.0275, "step": 130540 }, { "epoch": 31.34, "learning_rate": 7.960085180208165e-05, "loss": 0.0163, "step": 130550 }, { "epoch": 31.34, "learning_rate": 7.959795879907807e-05, "loss": 0.019, "step": 130560 }, { "epoch": 31.35, "learning_rate": 7.959506564352637e-05, "loss": 0.0316, "step": 130570 }, { "epoch": 31.35, "learning_rate": 7.959217233544146e-05, "loss": 0.0131, "step": 130580 }, { "epoch": 31.35, "learning_rate": 7.958927887483825e-05, "loss": 0.0331, "step": 130590 }, { "epoch": 31.35, "learning_rate": 7.958638526173164e-05, "loss": 0.0261, "step": 130600 }, { "epoch": 31.36, "learning_rate": 7.958349149613653e-05, "loss": 0.038, "step": 130610 }, { "epoch": 31.36, "learning_rate": 7.95805975780679e-05, "loss": 0.0181, "step": 130620 }, { "epoch": 31.36, "learning_rate": 7.957770350754061e-05, "loss": 0.023, "step": 130630 }, { "epoch": 31.36, "learning_rate": 7.957480928456957e-05, "loss": 0.0195, "step": 130640 }, { "epoch": 31.36, "learning_rate": 7.957191490916973e-05, "loss": 0.0236, "step": 130650 }, { "epoch": 31.37, "learning_rate": 7.956902038135598e-05, "loss": 0.0207, "step": 130660 }, { "epoch": 31.37, "learning_rate": 7.956612570114328e-05, "loss": 0.0163, "step": 130670 }, { "epoch": 31.37, "learning_rate": 7.956323086854649e-05, "loss": 0.0177, "step": 130680 }, { "epoch": 31.37, "learning_rate": 7.956033588358058e-05, "loss": 0.0206, "step": 130690 }, { "epoch": 31.38, "learning_rate": 7.955744074626046e-05, "loss": 0.0205, "step": 130700 }, { "epoch": 31.38, "learning_rate": 7.955454545660102e-05, "loss": 0.0227, "step": 130710 }, { "epoch": 31.38, "learning_rate": 7.955165001461722e-05, "loss": 0.0162, "step": 130720 }, { "epoch": 31.38, "learning_rate": 7.954875442032397e-05, "loss": 0.0229, "step": 130730 }, { "epoch": 31.39, "learning_rate": 7.954585867373618e-05, "loss": 0.016, "step": 130740 }, { "epoch": 31.39, "learning_rate": 7.954296277486879e-05, "loss": 0.0243, "step": 130750 }, { "epoch": 31.39, "learning_rate": 7.954006672373674e-05, "loss": 0.036, "step": 130760 }, { "epoch": 31.39, "learning_rate": 7.953717052035492e-05, "loss": 0.0298, "step": 130770 }, { "epoch": 31.39, "learning_rate": 7.953427416473829e-05, "loss": 0.0149, "step": 130780 }, { "epoch": 31.4, "learning_rate": 7.953137765690174e-05, "loss": 0.0147, "step": 130790 }, { "epoch": 31.4, "learning_rate": 7.952848099686025e-05, "loss": 0.0175, "step": 130800 }, { "epoch": 31.4, "learning_rate": 7.952558418462873e-05, "loss": 0.028, "step": 130810 }, { "epoch": 31.4, "learning_rate": 7.952268722022207e-05, "loss": 0.0367, "step": 130820 }, { "epoch": 31.41, "learning_rate": 7.951979010365524e-05, "loss": 0.0177, "step": 130830 }, { "epoch": 31.41, "learning_rate": 7.951689283494319e-05, "loss": 0.0256, "step": 130840 }, { "epoch": 31.41, "learning_rate": 7.95139954141008e-05, "loss": 0.0287, "step": 130850 }, { "epoch": 31.41, "learning_rate": 7.951109784114304e-05, "loss": 0.0193, "step": 130860 }, { "epoch": 31.42, "learning_rate": 7.950820011608485e-05, "loss": 0.0168, "step": 130870 }, { "epoch": 31.42, "learning_rate": 7.950530223894113e-05, "loss": 0.0232, "step": 130880 }, { "epoch": 31.42, "learning_rate": 7.950240420972683e-05, "loss": 0.0296, "step": 130890 }, { "epoch": 31.42, "learning_rate": 7.949950602845692e-05, "loss": 0.0259, "step": 130900 }, { "epoch": 31.42, "learning_rate": 7.949660769514629e-05, "loss": 0.0411, "step": 130910 }, { "epoch": 31.43, "learning_rate": 7.949370920980989e-05, "loss": 0.0193, "step": 130920 }, { "epoch": 31.43, "learning_rate": 7.949081057246268e-05, "loss": 0.0226, "step": 130930 }, { "epoch": 31.43, "learning_rate": 7.948791178311958e-05, "loss": 0.0368, "step": 130940 }, { "epoch": 31.43, "learning_rate": 7.948501284179554e-05, "loss": 0.024, "step": 130950 }, { "epoch": 31.44, "learning_rate": 7.948211374850551e-05, "loss": 0.0169, "step": 130960 }, { "epoch": 31.44, "learning_rate": 7.94792145032644e-05, "loss": 0.0235, "step": 130970 }, { "epoch": 31.44, "learning_rate": 7.947631510608719e-05, "loss": 0.0127, "step": 130980 }, { "epoch": 31.44, "learning_rate": 7.947341555698878e-05, "loss": 0.0305, "step": 130990 }, { "epoch": 31.44, "learning_rate": 7.947051585598415e-05, "loss": 0.0173, "step": 131000 }, { "epoch": 31.45, "learning_rate": 7.946761600308825e-05, "loss": 0.016, "step": 131010 }, { "epoch": 31.45, "learning_rate": 7.9464715998316e-05, "loss": 0.0254, "step": 131020 }, { "epoch": 31.45, "learning_rate": 7.946181584168236e-05, "loss": 0.0394, "step": 131030 }, { "epoch": 31.45, "learning_rate": 7.945891553320227e-05, "loss": 0.0275, "step": 131040 }, { "epoch": 31.46, "learning_rate": 7.945601507289068e-05, "loss": 0.027, "step": 131050 }, { "epoch": 31.46, "learning_rate": 7.945311446076255e-05, "loss": 0.0323, "step": 131060 }, { "epoch": 31.46, "learning_rate": 7.94502136968328e-05, "loss": 0.072, "step": 131070 }, { "epoch": 31.46, "learning_rate": 7.944731278111644e-05, "loss": 0.0386, "step": 131080 }, { "epoch": 31.47, "learning_rate": 7.944441171362835e-05, "loss": 0.0224, "step": 131090 }, { "epoch": 31.47, "learning_rate": 7.944151049438354e-05, "loss": 0.0235, "step": 131100 }, { "epoch": 31.47, "learning_rate": 7.943860912339694e-05, "loss": 0.0244, "step": 131110 }, { "epoch": 31.47, "learning_rate": 7.943570760068348e-05, "loss": 0.0351, "step": 131120 }, { "epoch": 31.47, "learning_rate": 7.943280592625815e-05, "loss": 0.0242, "step": 131130 }, { "epoch": 31.48, "learning_rate": 7.942990410013589e-05, "loss": 0.0247, "step": 131140 }, { "epoch": 31.48, "learning_rate": 7.942700212233166e-05, "loss": 0.0208, "step": 131150 }, { "epoch": 31.48, "learning_rate": 7.942409999286042e-05, "loss": 0.0162, "step": 131160 }, { "epoch": 31.48, "learning_rate": 7.942119771173712e-05, "loss": 0.0175, "step": 131170 }, { "epoch": 31.49, "learning_rate": 7.94182952789767e-05, "loss": 0.0287, "step": 131180 }, { "epoch": 31.49, "learning_rate": 7.941539269459417e-05, "loss": 0.0213, "step": 131190 }, { "epoch": 31.49, "learning_rate": 7.941248995860445e-05, "loss": 0.0358, "step": 131200 }, { "epoch": 31.49, "learning_rate": 7.94095870710225e-05, "loss": 0.0247, "step": 131210 }, { "epoch": 31.5, "learning_rate": 7.940668403186332e-05, "loss": 0.028, "step": 131220 }, { "epoch": 31.5, "learning_rate": 7.940378084114181e-05, "loss": 0.0212, "step": 131230 }, { "epoch": 31.5, "learning_rate": 7.9400877498873e-05, "loss": 0.0223, "step": 131240 }, { "epoch": 31.5, "learning_rate": 7.939797400507181e-05, "loss": 0.0301, "step": 131250 }, { "epoch": 31.5, "learning_rate": 7.93950703597532e-05, "loss": 0.0283, "step": 131260 }, { "epoch": 31.51, "learning_rate": 7.939216656293216e-05, "loss": 0.0398, "step": 131270 }, { "epoch": 31.51, "learning_rate": 7.938926261462366e-05, "loss": 0.0432, "step": 131280 }, { "epoch": 31.51, "learning_rate": 7.938635851484264e-05, "loss": 0.0255, "step": 131290 }, { "epoch": 31.51, "learning_rate": 7.938345426360409e-05, "loss": 0.0317, "step": 131300 }, { "epoch": 31.52, "learning_rate": 7.938054986092298e-05, "loss": 0.0208, "step": 131310 }, { "epoch": 31.52, "learning_rate": 7.937764530681426e-05, "loss": 0.0329, "step": 131320 }, { "epoch": 31.52, "learning_rate": 7.93747406012929e-05, "loss": 0.0296, "step": 131330 }, { "epoch": 31.52, "learning_rate": 7.93718357443739e-05, "loss": 0.0359, "step": 131340 }, { "epoch": 31.52, "learning_rate": 7.936893073607221e-05, "loss": 0.0267, "step": 131350 }, { "epoch": 31.53, "learning_rate": 7.93660255764028e-05, "loss": 0.0333, "step": 131360 }, { "epoch": 31.53, "learning_rate": 7.936312026538065e-05, "loss": 0.0379, "step": 131370 }, { "epoch": 31.53, "learning_rate": 7.936021480302073e-05, "loss": 0.04, "step": 131380 }, { "epoch": 31.53, "learning_rate": 7.935730918933802e-05, "loss": 0.0543, "step": 131390 }, { "epoch": 31.54, "learning_rate": 7.93544034243475e-05, "loss": 0.0239, "step": 131400 }, { "epoch": 31.54, "learning_rate": 7.935149750806414e-05, "loss": 0.0276, "step": 131410 }, { "epoch": 31.54, "learning_rate": 7.934859144050291e-05, "loss": 0.0247, "step": 131420 }, { "epoch": 31.54, "learning_rate": 7.934568522167878e-05, "loss": 0.0281, "step": 131430 }, { "epoch": 31.55, "learning_rate": 7.934277885160676e-05, "loss": 0.0597, "step": 131440 }, { "epoch": 31.55, "learning_rate": 7.93398723303018e-05, "loss": 0.0339, "step": 131450 }, { "epoch": 31.55, "learning_rate": 7.93369656577789e-05, "loss": 0.0564, "step": 131460 }, { "epoch": 31.55, "learning_rate": 7.933405883405305e-05, "loss": 0.0199, "step": 131470 }, { "epoch": 31.55, "learning_rate": 7.933115185913921e-05, "loss": 0.0285, "step": 131480 }, { "epoch": 31.56, "learning_rate": 7.932824473305236e-05, "loss": 0.0358, "step": 131490 }, { "epoch": 31.56, "learning_rate": 7.932533745580748e-05, "loss": 0.0379, "step": 131500 }, { "epoch": 31.56, "learning_rate": 7.932243002741957e-05, "loss": 0.05, "step": 131510 }, { "epoch": 31.56, "learning_rate": 7.931952244790361e-05, "loss": 0.0264, "step": 131520 }, { "epoch": 31.57, "learning_rate": 7.931661471727461e-05, "loss": 0.0283, "step": 131530 }, { "epoch": 31.57, "learning_rate": 7.931370683554751e-05, "loss": 0.0365, "step": 131540 }, { "epoch": 31.57, "learning_rate": 7.931079880273733e-05, "loss": 0.0319, "step": 131550 }, { "epoch": 31.57, "learning_rate": 7.930789061885905e-05, "loss": 0.0384, "step": 131560 }, { "epoch": 31.58, "learning_rate": 7.930498228392764e-05, "loss": 0.0385, "step": 131570 }, { "epoch": 31.58, "learning_rate": 7.930207379795812e-05, "loss": 0.0285, "step": 131580 }, { "epoch": 31.58, "learning_rate": 7.929916516096547e-05, "loss": 0.0134, "step": 131590 }, { "epoch": 31.58, "learning_rate": 7.929625637296467e-05, "loss": 0.0237, "step": 131600 }, { "epoch": 31.58, "learning_rate": 7.929334743397073e-05, "loss": 0.0485, "step": 131610 }, { "epoch": 31.59, "learning_rate": 7.929043834399861e-05, "loss": 0.0327, "step": 131620 }, { "epoch": 31.59, "learning_rate": 7.928752910306335e-05, "loss": 0.0286, "step": 131630 }, { "epoch": 31.59, "learning_rate": 7.928461971117991e-05, "loss": 0.0291, "step": 131640 }, { "epoch": 31.59, "learning_rate": 7.928171016836329e-05, "loss": 0.0229, "step": 131650 }, { "epoch": 31.6, "learning_rate": 7.92788004746285e-05, "loss": 0.0436, "step": 131660 }, { "epoch": 31.6, "learning_rate": 7.927589062999052e-05, "loss": 0.0286, "step": 131670 }, { "epoch": 31.6, "learning_rate": 7.927298063446436e-05, "loss": 0.0261, "step": 131680 }, { "epoch": 31.6, "learning_rate": 7.927007048806502e-05, "loss": 0.0251, "step": 131690 }, { "epoch": 31.6, "learning_rate": 7.926716019080749e-05, "loss": 0.0335, "step": 131700 }, { "epoch": 31.61, "learning_rate": 7.926424974270676e-05, "loss": 0.0285, "step": 131710 }, { "epoch": 31.61, "learning_rate": 7.926133914377785e-05, "loss": 0.0285, "step": 131720 }, { "epoch": 31.61, "learning_rate": 7.925842839403575e-05, "loss": 0.0249, "step": 131730 }, { "epoch": 31.61, "learning_rate": 7.925551749349546e-05, "loss": 0.0332, "step": 131740 }, { "epoch": 31.62, "learning_rate": 7.9252606442172e-05, "loss": 0.0355, "step": 131750 }, { "epoch": 31.62, "learning_rate": 7.924969524008035e-05, "loss": 0.0359, "step": 131760 }, { "epoch": 31.62, "learning_rate": 7.924678388723554e-05, "loss": 0.0359, "step": 131770 }, { "epoch": 31.62, "learning_rate": 7.924387238365257e-05, "loss": 0.0374, "step": 131780 }, { "epoch": 31.63, "learning_rate": 7.924096072934641e-05, "loss": 0.0333, "step": 131790 }, { "epoch": 31.63, "learning_rate": 7.92380489243321e-05, "loss": 0.0381, "step": 131800 }, { "epoch": 31.63, "learning_rate": 7.923513696862464e-05, "loss": 0.0332, "step": 131810 }, { "epoch": 31.63, "learning_rate": 7.923222486223905e-05, "loss": 0.0255, "step": 131820 }, { "epoch": 31.63, "learning_rate": 7.922931260519033e-05, "loss": 0.0195, "step": 131830 }, { "epoch": 31.64, "learning_rate": 7.922640019749349e-05, "loss": 0.0334, "step": 131840 }, { "epoch": 31.64, "learning_rate": 7.922348763916354e-05, "loss": 0.0468, "step": 131850 }, { "epoch": 31.64, "learning_rate": 7.922057493021549e-05, "loss": 0.0296, "step": 131860 }, { "epoch": 31.64, "learning_rate": 7.921766207066434e-05, "loss": 0.0319, "step": 131870 }, { "epoch": 31.65, "learning_rate": 7.921474906052512e-05, "loss": 0.0499, "step": 131880 }, { "epoch": 31.65, "learning_rate": 7.921183589981283e-05, "loss": 0.0258, "step": 131890 }, { "epoch": 31.65, "learning_rate": 7.920892258854251e-05, "loss": 0.0613, "step": 131900 }, { "epoch": 31.65, "learning_rate": 7.920600912672916e-05, "loss": 0.031, "step": 131910 }, { "epoch": 31.66, "learning_rate": 7.920309551438779e-05, "loss": 0.029, "step": 131920 }, { "epoch": 31.66, "learning_rate": 7.920018175153341e-05, "loss": 0.0343, "step": 131930 }, { "epoch": 31.66, "learning_rate": 7.919726783818107e-05, "loss": 0.0189, "step": 131940 }, { "epoch": 31.66, "learning_rate": 7.919435377434576e-05, "loss": 0.0308, "step": 131950 }, { "epoch": 31.66, "learning_rate": 7.919143956004249e-05, "loss": 0.0342, "step": 131960 }, { "epoch": 31.67, "learning_rate": 7.91885251952863e-05, "loss": 0.028, "step": 131970 }, { "epoch": 31.67, "learning_rate": 7.918561068009224e-05, "loss": 0.0241, "step": 131980 }, { "epoch": 31.67, "learning_rate": 7.918269601447528e-05, "loss": 0.0187, "step": 131990 }, { "epoch": 31.67, "learning_rate": 7.917978119845045e-05, "loss": 0.0332, "step": 132000 }, { "epoch": 31.68, "learning_rate": 7.917686623203279e-05, "loss": 0.0326, "step": 132010 }, { "epoch": 31.68, "learning_rate": 7.91739511152373e-05, "loss": 0.0369, "step": 132020 }, { "epoch": 31.68, "learning_rate": 7.917103584807905e-05, "loss": 0.0273, "step": 132030 }, { "epoch": 31.68, "learning_rate": 7.916812043057302e-05, "loss": 0.0383, "step": 132040 }, { "epoch": 31.68, "learning_rate": 7.916520486273427e-05, "loss": 0.0336, "step": 132050 }, { "epoch": 31.69, "learning_rate": 7.91622891445778e-05, "loss": 0.02, "step": 132060 }, { "epoch": 31.69, "learning_rate": 7.915937327611865e-05, "loss": 0.0172, "step": 132070 }, { "epoch": 31.69, "learning_rate": 7.915645725737184e-05, "loss": 0.0266, "step": 132080 }, { "epoch": 31.69, "learning_rate": 7.915354108835242e-05, "loss": 0.0382, "step": 132090 }, { "epoch": 31.7, "learning_rate": 7.91506247690754e-05, "loss": 0.0348, "step": 132100 }, { "epoch": 31.7, "learning_rate": 7.91477082995558e-05, "loss": 0.0194, "step": 132110 }, { "epoch": 31.7, "learning_rate": 7.914479167980869e-05, "loss": 0.0285, "step": 132120 }, { "epoch": 31.7, "learning_rate": 7.914187490984908e-05, "loss": 0.0275, "step": 132130 }, { "epoch": 31.71, "learning_rate": 7.913895798969198e-05, "loss": 0.0269, "step": 132140 }, { "epoch": 31.71, "learning_rate": 7.913604091935247e-05, "loss": 0.0223, "step": 132150 }, { "epoch": 31.71, "learning_rate": 7.913312369884555e-05, "loss": 0.0375, "step": 132160 }, { "epoch": 31.71, "learning_rate": 7.913020632818626e-05, "loss": 0.0251, "step": 132170 }, { "epoch": 31.71, "learning_rate": 7.912728880738967e-05, "loss": 0.0197, "step": 132180 }, { "epoch": 31.72, "learning_rate": 7.912437113647076e-05, "loss": 0.0222, "step": 132190 }, { "epoch": 31.72, "learning_rate": 7.912145331544462e-05, "loss": 0.0319, "step": 132200 }, { "epoch": 31.72, "learning_rate": 7.911853534432625e-05, "loss": 0.0257, "step": 132210 }, { "epoch": 31.72, "learning_rate": 7.911561722313071e-05, "loss": 0.0428, "step": 132220 }, { "epoch": 31.73, "learning_rate": 7.911269895187303e-05, "loss": 0.0241, "step": 132230 }, { "epoch": 31.73, "learning_rate": 7.910978053056828e-05, "loss": 0.0188, "step": 132240 }, { "epoch": 31.73, "learning_rate": 7.910686195923145e-05, "loss": 0.0178, "step": 132250 }, { "epoch": 31.73, "learning_rate": 7.910394323787762e-05, "loss": 0.0277, "step": 132260 }, { "epoch": 31.74, "learning_rate": 7.910102436652182e-05, "loss": 0.0349, "step": 132270 }, { "epoch": 31.74, "learning_rate": 7.909810534517912e-05, "loss": 0.0262, "step": 132280 }, { "epoch": 31.74, "learning_rate": 7.90951861738645e-05, "loss": 0.0398, "step": 132290 }, { "epoch": 31.74, "learning_rate": 7.909226685259309e-05, "loss": 0.0297, "step": 132300 }, { "epoch": 31.74, "learning_rate": 7.908934738137987e-05, "loss": 0.0214, "step": 132310 }, { "epoch": 31.75, "learning_rate": 7.908642776023992e-05, "loss": 0.0207, "step": 132320 }, { "epoch": 31.75, "learning_rate": 7.908350798918826e-05, "loss": 0.03, "step": 132330 }, { "epoch": 31.75, "learning_rate": 7.908058806823999e-05, "loss": 0.0182, "step": 132340 }, { "epoch": 31.75, "learning_rate": 7.90776679974101e-05, "loss": 0.0249, "step": 132350 }, { "epoch": 31.76, "learning_rate": 7.907474777671366e-05, "loss": 0.0191, "step": 132360 }, { "epoch": 31.76, "learning_rate": 7.907182740616575e-05, "loss": 0.0634, "step": 132370 }, { "epoch": 31.76, "learning_rate": 7.906890688578139e-05, "loss": 0.0299, "step": 132380 }, { "epoch": 31.76, "learning_rate": 7.906598621557564e-05, "loss": 0.024, "step": 132390 }, { "epoch": 31.76, "learning_rate": 7.906306539556354e-05, "loss": 0.0337, "step": 132400 }, { "epoch": 31.77, "learning_rate": 7.906014442576018e-05, "loss": 0.0373, "step": 132410 }, { "epoch": 31.77, "learning_rate": 7.905722330618058e-05, "loss": 0.0224, "step": 132420 }, { "epoch": 31.77, "learning_rate": 7.905430203683981e-05, "loss": 0.0457, "step": 132430 }, { "epoch": 31.77, "learning_rate": 7.905138061775292e-05, "loss": 0.0136, "step": 132440 }, { "epoch": 31.78, "learning_rate": 7.904845904893499e-05, "loss": 0.0318, "step": 132450 }, { "epoch": 31.78, "learning_rate": 7.904553733040104e-05, "loss": 0.0267, "step": 132460 }, { "epoch": 31.78, "learning_rate": 7.904261546216616e-05, "loss": 0.0244, "step": 132470 }, { "epoch": 31.78, "learning_rate": 7.90396934442454e-05, "loss": 0.0396, "step": 132480 }, { "epoch": 31.79, "learning_rate": 7.903677127665381e-05, "loss": 0.0197, "step": 132490 }, { "epoch": 31.79, "learning_rate": 7.903384895940644e-05, "loss": 0.0283, "step": 132500 }, { "epoch": 31.79, "learning_rate": 7.90309264925184e-05, "loss": 0.0286, "step": 132510 }, { "epoch": 31.79, "learning_rate": 7.90280038760047e-05, "loss": 0.0294, "step": 132520 }, { "epoch": 31.79, "learning_rate": 7.902508110988043e-05, "loss": 0.0253, "step": 132530 }, { "epoch": 31.8, "learning_rate": 7.902215819416066e-05, "loss": 0.0438, "step": 132540 }, { "epoch": 31.8, "learning_rate": 7.901923512886043e-05, "loss": 0.0189, "step": 132550 }, { "epoch": 31.8, "learning_rate": 7.901631191399484e-05, "loss": 0.02, "step": 132560 }, { "epoch": 31.8, "learning_rate": 7.901338854957892e-05, "loss": 0.0338, "step": 132570 }, { "epoch": 31.81, "learning_rate": 7.901046503562775e-05, "loss": 0.0156, "step": 132580 }, { "epoch": 31.81, "learning_rate": 7.900754137215641e-05, "loss": 0.0341, "step": 132590 }, { "epoch": 31.81, "learning_rate": 7.900461755917996e-05, "loss": 0.0157, "step": 132600 }, { "epoch": 31.81, "learning_rate": 7.900169359671345e-05, "loss": 0.0172, "step": 132610 }, { "epoch": 31.82, "learning_rate": 7.8998769484772e-05, "loss": 0.0324, "step": 132620 }, { "epoch": 31.82, "learning_rate": 7.899584522337063e-05, "loss": 0.0256, "step": 132630 }, { "epoch": 31.82, "learning_rate": 7.899292081252443e-05, "loss": 0.0214, "step": 132640 }, { "epoch": 31.82, "learning_rate": 7.898999625224849e-05, "loss": 0.0188, "step": 132650 }, { "epoch": 31.82, "learning_rate": 7.898707154255784e-05, "loss": 0.0204, "step": 132660 }, { "epoch": 31.83, "learning_rate": 7.89841466834676e-05, "loss": 0.0215, "step": 132670 }, { "epoch": 31.83, "learning_rate": 7.898122167499282e-05, "loss": 0.0257, "step": 132680 }, { "epoch": 31.83, "learning_rate": 7.897829651714859e-05, "loss": 0.0349, "step": 132690 }, { "epoch": 31.83, "learning_rate": 7.897537120994998e-05, "loss": 0.0174, "step": 132700 }, { "epoch": 31.84, "learning_rate": 7.897244575341205e-05, "loss": 0.0206, "step": 132710 }, { "epoch": 31.84, "learning_rate": 7.89695201475499e-05, "loss": 0.0199, "step": 132720 }, { "epoch": 31.84, "learning_rate": 7.89665943923786e-05, "loss": 0.059, "step": 132730 }, { "epoch": 31.84, "learning_rate": 7.896366848791323e-05, "loss": 0.0281, "step": 132740 }, { "epoch": 31.84, "learning_rate": 7.896074243416886e-05, "loss": 0.0156, "step": 132750 }, { "epoch": 31.85, "learning_rate": 7.895781623116059e-05, "loss": 0.0245, "step": 132760 }, { "epoch": 31.85, "learning_rate": 7.89548898789035e-05, "loss": 0.0341, "step": 132770 }, { "epoch": 31.85, "learning_rate": 7.895196337741266e-05, "loss": 0.0259, "step": 132780 }, { "epoch": 31.85, "learning_rate": 7.894903672670316e-05, "loss": 0.0232, "step": 132790 }, { "epoch": 31.86, "learning_rate": 7.894610992679008e-05, "loss": 0.0236, "step": 132800 }, { "epoch": 31.86, "learning_rate": 7.894318297768851e-05, "loss": 0.0233, "step": 132810 }, { "epoch": 31.86, "learning_rate": 7.894025587941354e-05, "loss": 0.0296, "step": 132820 }, { "epoch": 31.86, "learning_rate": 7.893732863198024e-05, "loss": 0.0248, "step": 132830 }, { "epoch": 31.87, "learning_rate": 7.893440123540371e-05, "loss": 0.0235, "step": 132840 }, { "epoch": 31.87, "learning_rate": 7.893147368969902e-05, "loss": 0.0258, "step": 132850 }, { "epoch": 31.87, "learning_rate": 7.892854599488129e-05, "loss": 0.039, "step": 132860 }, { "epoch": 31.87, "learning_rate": 7.892561815096559e-05, "loss": 0.0308, "step": 132870 }, { "epoch": 31.87, "learning_rate": 7.8922690157967e-05, "loss": 0.0279, "step": 132880 }, { "epoch": 31.88, "learning_rate": 7.891976201590064e-05, "loss": 0.0229, "step": 132890 }, { "epoch": 31.88, "learning_rate": 7.891683372478157e-05, "loss": 0.0296, "step": 132900 }, { "epoch": 31.88, "learning_rate": 7.891390528462491e-05, "loss": 0.0158, "step": 132910 }, { "epoch": 31.88, "learning_rate": 7.891097669544574e-05, "loss": 0.031, "step": 132920 }, { "epoch": 31.89, "learning_rate": 7.890804795725915e-05, "loss": 0.0274, "step": 132930 }, { "epoch": 31.89, "learning_rate": 7.890511907008023e-05, "loss": 0.0316, "step": 132940 }, { "epoch": 31.89, "learning_rate": 7.89021900339241e-05, "loss": 0.0264, "step": 132950 }, { "epoch": 31.89, "learning_rate": 7.889926084880582e-05, "loss": 0.0323, "step": 132960 }, { "epoch": 31.9, "learning_rate": 7.889633151474052e-05, "loss": 0.025, "step": 132970 }, { "epoch": 31.9, "learning_rate": 7.88934020317433e-05, "loss": 0.0248, "step": 132980 }, { "epoch": 31.9, "learning_rate": 7.889047239982923e-05, "loss": 0.0196, "step": 132990 }, { "epoch": 31.9, "learning_rate": 7.888754261901343e-05, "loss": 0.0229, "step": 133000 }, { "epoch": 31.9, "learning_rate": 7.888461268931097e-05, "loss": 0.0206, "step": 133010 }, { "epoch": 31.91, "learning_rate": 7.888168261073701e-05, "loss": 0.0391, "step": 133020 }, { "epoch": 31.91, "learning_rate": 7.88787523833066e-05, "loss": 0.0239, "step": 133030 }, { "epoch": 31.91, "learning_rate": 7.887582200703486e-05, "loss": 0.0344, "step": 133040 }, { "epoch": 31.91, "learning_rate": 7.887289148193688e-05, "loss": 0.0202, "step": 133050 }, { "epoch": 31.92, "learning_rate": 7.88699608080278e-05, "loss": 0.056, "step": 133060 }, { "epoch": 31.92, "learning_rate": 7.88670299853227e-05, "loss": 0.029, "step": 133070 }, { "epoch": 31.92, "learning_rate": 7.886409901383666e-05, "loss": 0.0228, "step": 133080 }, { "epoch": 31.92, "learning_rate": 7.886116789358483e-05, "loss": 0.0241, "step": 133090 }, { "epoch": 31.92, "learning_rate": 7.88582366245823e-05, "loss": 0.0224, "step": 133100 }, { "epoch": 31.93, "learning_rate": 7.885530520684416e-05, "loss": 0.0143, "step": 133110 }, { "epoch": 31.93, "learning_rate": 7.885237364038556e-05, "loss": 0.0184, "step": 133120 }, { "epoch": 31.93, "learning_rate": 7.884944192522157e-05, "loss": 0.0277, "step": 133130 }, { "epoch": 31.93, "learning_rate": 7.884651006136733e-05, "loss": 0.0326, "step": 133140 }, { "epoch": 31.94, "learning_rate": 7.884357804883793e-05, "loss": 0.0268, "step": 133150 }, { "epoch": 31.94, "learning_rate": 7.884064588764848e-05, "loss": 0.0232, "step": 133160 }, { "epoch": 31.94, "learning_rate": 7.88377135778141e-05, "loss": 0.0504, "step": 133170 }, { "epoch": 31.94, "learning_rate": 7.88347811193499e-05, "loss": 0.0165, "step": 133180 }, { "epoch": 31.95, "learning_rate": 7.883184851227102e-05, "loss": 0.0358, "step": 133190 }, { "epoch": 31.95, "learning_rate": 7.882891575659253e-05, "loss": 0.0117, "step": 133200 }, { "epoch": 31.95, "learning_rate": 7.882598285232957e-05, "loss": 0.0238, "step": 133210 }, { "epoch": 32.0, "learning_rate": 7.882304979949726e-05, "loss": 0.0181, "step": 133220 }, { "epoch": 32.0, "learning_rate": 7.88201165981107e-05, "loss": 0.0297, "step": 133230 }, { "epoch": 32.01, "learning_rate": 7.881718324818503e-05, "loss": 0.0209, "step": 133240 }, { "epoch": 32.01, "learning_rate": 7.881424974973535e-05, "loss": 0.0245, "step": 133250 }, { "epoch": 32.01, "learning_rate": 7.88113161027768e-05, "loss": 0.0278, "step": 133260 }, { "epoch": 32.01, "learning_rate": 7.880838230732445e-05, "loss": 0.0549, "step": 133270 }, { "epoch": 32.01, "learning_rate": 7.880544836339349e-05, "loss": 0.0356, "step": 133280 }, { "epoch": 32.02, "learning_rate": 7.8802514270999e-05, "loss": 0.0227, "step": 133290 }, { "epoch": 32.02, "learning_rate": 7.879958003015611e-05, "loss": 0.0398, "step": 133300 }, { "epoch": 32.02, "learning_rate": 7.879664564087993e-05, "loss": 0.0316, "step": 133310 }, { "epoch": 32.02, "learning_rate": 7.879371110318562e-05, "loss": 0.0344, "step": 133320 }, { "epoch": 32.03, "learning_rate": 7.879077641708828e-05, "loss": 0.027, "step": 133330 }, { "epoch": 32.03, "learning_rate": 7.878784158260302e-05, "loss": 0.0492, "step": 133340 }, { "epoch": 32.03, "learning_rate": 7.878490659974501e-05, "loss": 0.0279, "step": 133350 }, { "epoch": 32.03, "learning_rate": 7.878197146852932e-05, "loss": 0.026, "step": 133360 }, { "epoch": 32.04, "learning_rate": 7.877903618897113e-05, "loss": 0.0206, "step": 133370 }, { "epoch": 32.04, "learning_rate": 7.877610076108554e-05, "loss": 0.0365, "step": 133380 }, { "epoch": 32.04, "learning_rate": 7.877316518488769e-05, "loss": 0.0361, "step": 133390 }, { "epoch": 32.04, "learning_rate": 7.87702294603927e-05, "loss": 0.0204, "step": 133400 }, { "epoch": 32.04, "learning_rate": 7.87672935876157e-05, "loss": 0.0172, "step": 133410 }, { "epoch": 32.05, "learning_rate": 7.876435756657186e-05, "loss": 0.0175, "step": 133420 }, { "epoch": 32.05, "learning_rate": 7.876142139727625e-05, "loss": 0.0195, "step": 133430 }, { "epoch": 32.05, "learning_rate": 7.875848507974404e-05, "loss": 0.0369, "step": 133440 }, { "epoch": 32.05, "learning_rate": 7.875554861399036e-05, "loss": 0.0179, "step": 133450 }, { "epoch": 32.06, "learning_rate": 7.875261200003035e-05, "loss": 0.0331, "step": 133460 }, { "epoch": 32.06, "learning_rate": 7.874967523787912e-05, "loss": 0.0345, "step": 133470 }, { "epoch": 32.06, "learning_rate": 7.874673832755183e-05, "loss": 0.0332, "step": 133480 }, { "epoch": 32.06, "learning_rate": 7.874380126906362e-05, "loss": 0.0262, "step": 133490 }, { "epoch": 32.06, "learning_rate": 7.87408640624296e-05, "loss": 0.031, "step": 133500 }, { "epoch": 32.07, "learning_rate": 7.873792670766495e-05, "loss": 0.0189, "step": 133510 }, { "epoch": 32.07, "learning_rate": 7.873498920478477e-05, "loss": 0.0472, "step": 133520 }, { "epoch": 32.07, "learning_rate": 7.873205155380423e-05, "loss": 0.0178, "step": 133530 }, { "epoch": 32.07, "learning_rate": 7.872911375473844e-05, "loss": 0.0259, "step": 133540 }, { "epoch": 32.08, "learning_rate": 7.872617580760256e-05, "loss": 0.0193, "step": 133550 }, { "epoch": 32.08, "learning_rate": 7.872323771241172e-05, "loss": 0.0328, "step": 133560 }, { "epoch": 32.08, "learning_rate": 7.87202994691811e-05, "loss": 0.0287, "step": 133570 }, { "epoch": 32.08, "learning_rate": 7.87173610779258e-05, "loss": 0.0313, "step": 133580 }, { "epoch": 32.09, "learning_rate": 7.871442253866098e-05, "loss": 0.0196, "step": 133590 }, { "epoch": 32.09, "learning_rate": 7.871148385140179e-05, "loss": 0.0196, "step": 133600 }, { "epoch": 32.09, "learning_rate": 7.870854501616336e-05, "loss": 0.0187, "step": 133610 }, { "epoch": 32.09, "learning_rate": 7.870560603296086e-05, "loss": 0.016, "step": 133620 }, { "epoch": 32.09, "learning_rate": 7.870266690180943e-05, "loss": 0.025, "step": 133630 }, { "epoch": 32.1, "learning_rate": 7.869972762272421e-05, "loss": 0.0271, "step": 133640 }, { "epoch": 32.1, "learning_rate": 7.869678819572035e-05, "loss": 0.0178, "step": 133650 }, { "epoch": 32.1, "learning_rate": 7.869384862081301e-05, "loss": 0.0207, "step": 133660 }, { "epoch": 32.1, "learning_rate": 7.869090889801735e-05, "loss": 0.0191, "step": 133670 }, { "epoch": 32.11, "learning_rate": 7.868796902734849e-05, "loss": 0.0265, "step": 133680 }, { "epoch": 32.11, "learning_rate": 7.868502900882159e-05, "loss": 0.0334, "step": 133690 }, { "epoch": 32.11, "learning_rate": 7.868208884245182e-05, "loss": 0.0182, "step": 133700 }, { "epoch": 32.11, "learning_rate": 7.867914852825432e-05, "loss": 0.0212, "step": 133710 }, { "epoch": 32.12, "learning_rate": 7.867620806624425e-05, "loss": 0.0305, "step": 133720 }, { "epoch": 32.12, "learning_rate": 7.867326745643677e-05, "loss": 0.0226, "step": 133730 }, { "epoch": 32.12, "learning_rate": 7.867032669884702e-05, "loss": 0.0215, "step": 133740 }, { "epoch": 32.12, "learning_rate": 7.866738579349018e-05, "loss": 0.0142, "step": 133750 }, { "epoch": 32.12, "learning_rate": 7.866444474038137e-05, "loss": 0.0383, "step": 133760 }, { "epoch": 32.13, "learning_rate": 7.866150353953579e-05, "loss": 0.0231, "step": 133770 }, { "epoch": 32.13, "learning_rate": 7.865856219096859e-05, "loss": 0.0126, "step": 133780 }, { "epoch": 32.13, "learning_rate": 7.86556206946949e-05, "loss": 0.0268, "step": 133790 }, { "epoch": 32.13, "learning_rate": 7.865267905072992e-05, "loss": 0.0336, "step": 133800 }, { "epoch": 32.14, "learning_rate": 7.864973725908878e-05, "loss": 0.0243, "step": 133810 }, { "epoch": 32.14, "learning_rate": 7.864679531978665e-05, "loss": 0.0344, "step": 133820 }, { "epoch": 32.14, "learning_rate": 7.864385323283871e-05, "loss": 0.0245, "step": 133830 }, { "epoch": 32.14, "learning_rate": 7.864091099826011e-05, "loss": 0.0205, "step": 133840 }, { "epoch": 32.14, "learning_rate": 7.8637968616066e-05, "loss": 0.0302, "step": 133850 }, { "epoch": 32.15, "learning_rate": 7.863502608627158e-05, "loss": 0.0238, "step": 133860 }, { "epoch": 32.15, "learning_rate": 7.863208340889199e-05, "loss": 0.014, "step": 133870 }, { "epoch": 32.15, "learning_rate": 7.862914058394239e-05, "loss": 0.0268, "step": 133880 }, { "epoch": 32.15, "learning_rate": 7.862619761143798e-05, "loss": 0.0262, "step": 133890 }, { "epoch": 32.16, "learning_rate": 7.862325449139391e-05, "loss": 0.0197, "step": 133900 }, { "epoch": 32.16, "learning_rate": 7.862031122382533e-05, "loss": 0.0269, "step": 133910 }, { "epoch": 32.16, "learning_rate": 7.861736780874744e-05, "loss": 0.0218, "step": 133920 }, { "epoch": 32.16, "learning_rate": 7.861442424617538e-05, "loss": 0.0356, "step": 133930 }, { "epoch": 32.17, "learning_rate": 7.861148053612434e-05, "loss": 0.0201, "step": 133940 }, { "epoch": 32.17, "learning_rate": 7.860853667860952e-05, "loss": 0.0192, "step": 133950 }, { "epoch": 32.17, "learning_rate": 7.860559267364604e-05, "loss": 0.017, "step": 133960 }, { "epoch": 32.17, "learning_rate": 7.86026485212491e-05, "loss": 0.0166, "step": 133970 }, { "epoch": 32.17, "learning_rate": 7.859970422143385e-05, "loss": 0.0182, "step": 133980 }, { "epoch": 32.18, "learning_rate": 7.859675977421552e-05, "loss": 0.0263, "step": 133990 }, { "epoch": 32.18, "learning_rate": 7.859381517960924e-05, "loss": 0.0293, "step": 134000 }, { "epoch": 32.18, "learning_rate": 7.859087043763018e-05, "loss": 0.0135, "step": 134010 }, { "epoch": 32.18, "learning_rate": 7.858792554829355e-05, "loss": 0.0263, "step": 134020 }, { "epoch": 32.19, "learning_rate": 7.858498051161452e-05, "loss": 0.0244, "step": 134030 }, { "epoch": 32.19, "learning_rate": 7.858203532760824e-05, "loss": 0.0288, "step": 134040 }, { "epoch": 32.19, "learning_rate": 7.857908999628993e-05, "loss": 0.0375, "step": 134050 }, { "epoch": 32.19, "learning_rate": 7.857614451767474e-05, "loss": 0.0345, "step": 134060 }, { "epoch": 32.2, "learning_rate": 7.857319889177788e-05, "loss": 0.016, "step": 134070 }, { "epoch": 32.2, "learning_rate": 7.857025311861449e-05, "loss": 0.0261, "step": 134080 }, { "epoch": 32.2, "learning_rate": 7.856730719819978e-05, "loss": 0.0293, "step": 134090 }, { "epoch": 32.2, "learning_rate": 7.856436113054894e-05, "loss": 0.0295, "step": 134100 }, { "epoch": 32.2, "learning_rate": 7.856141491567714e-05, "loss": 0.0199, "step": 134110 }, { "epoch": 32.21, "learning_rate": 7.855846855359957e-05, "loss": 0.0237, "step": 134120 }, { "epoch": 32.21, "learning_rate": 7.855552204433142e-05, "loss": 0.0185, "step": 134130 }, { "epoch": 32.21, "learning_rate": 7.855257538788786e-05, "loss": 0.0274, "step": 134140 }, { "epoch": 32.21, "learning_rate": 7.85496285842841e-05, "loss": 0.0236, "step": 134150 }, { "epoch": 32.22, "learning_rate": 7.85466816335353e-05, "loss": 0.0212, "step": 134160 }, { "epoch": 32.22, "learning_rate": 7.854373453565667e-05, "loss": 0.0169, "step": 134170 }, { "epoch": 32.22, "learning_rate": 7.85407872906634e-05, "loss": 0.0195, "step": 134180 }, { "epoch": 32.22, "learning_rate": 7.853783989857067e-05, "loss": 0.0348, "step": 134190 }, { "epoch": 32.22, "learning_rate": 7.853489235939367e-05, "loss": 0.0211, "step": 134200 }, { "epoch": 32.23, "learning_rate": 7.85319446731476e-05, "loss": 0.0162, "step": 134210 }, { "epoch": 32.23, "learning_rate": 7.852899683984766e-05, "loss": 0.0229, "step": 134220 }, { "epoch": 32.23, "learning_rate": 7.852604885950902e-05, "loss": 0.0199, "step": 134230 }, { "epoch": 32.23, "learning_rate": 7.852310073214689e-05, "loss": 0.0217, "step": 134240 }, { "epoch": 32.24, "learning_rate": 7.852015245777645e-05, "loss": 0.0268, "step": 134250 }, { "epoch": 32.24, "learning_rate": 7.851720403641292e-05, "loss": 0.0163, "step": 134260 }, { "epoch": 32.24, "learning_rate": 7.851425546807148e-05, "loss": 0.0143, "step": 134270 }, { "epoch": 32.24, "learning_rate": 7.851130675276732e-05, "loss": 0.0167, "step": 134280 }, { "epoch": 32.25, "learning_rate": 7.850835789051565e-05, "loss": 0.0497, "step": 134290 }, { "epoch": 32.25, "learning_rate": 7.850540888133166e-05, "loss": 0.046, "step": 134300 }, { "epoch": 32.25, "learning_rate": 7.850245972523056e-05, "loss": 0.0211, "step": 134310 }, { "epoch": 32.25, "learning_rate": 7.849951042222754e-05, "loss": 0.0161, "step": 134320 }, { "epoch": 32.25, "learning_rate": 7.849656097233782e-05, "loss": 0.0263, "step": 134330 }, { "epoch": 32.26, "learning_rate": 7.849361137557657e-05, "loss": 0.0277, "step": 134340 }, { "epoch": 32.26, "learning_rate": 7.849066163195902e-05, "loss": 0.0369, "step": 134350 }, { "epoch": 32.26, "learning_rate": 7.848771174150035e-05, "loss": 0.0198, "step": 134360 }, { "epoch": 32.26, "learning_rate": 7.848476170421579e-05, "loss": 0.0285, "step": 134370 }, { "epoch": 32.27, "learning_rate": 7.848181152012052e-05, "loss": 0.0259, "step": 134380 }, { "epoch": 32.27, "learning_rate": 7.847886118922975e-05, "loss": 0.0491, "step": 134390 }, { "epoch": 32.27, "learning_rate": 7.847591071155871e-05, "loss": 0.016, "step": 134400 }, { "epoch": 32.27, "learning_rate": 7.847296008712257e-05, "loss": 0.0297, "step": 134410 }, { "epoch": 32.28, "learning_rate": 7.847000931593657e-05, "loss": 0.0331, "step": 134420 }, { "epoch": 32.28, "learning_rate": 7.84670583980159e-05, "loss": 0.0216, "step": 134430 }, { "epoch": 32.28, "learning_rate": 7.846410733337578e-05, "loss": 0.0206, "step": 134440 }, { "epoch": 32.28, "learning_rate": 7.846115612203139e-05, "loss": 0.024, "step": 134450 }, { "epoch": 32.28, "learning_rate": 7.845820476399797e-05, "loss": 0.0366, "step": 134460 }, { "epoch": 32.29, "learning_rate": 7.845525325929073e-05, "loss": 0.0282, "step": 134470 }, { "epoch": 32.29, "learning_rate": 7.845230160792489e-05, "loss": 0.0191, "step": 134480 }, { "epoch": 32.29, "learning_rate": 7.844934980991563e-05, "loss": 0.0198, "step": 134490 }, { "epoch": 32.29, "learning_rate": 7.84463978652782e-05, "loss": 0.0209, "step": 134500 }, { "epoch": 32.3, "learning_rate": 7.844344577402778e-05, "loss": 0.0368, "step": 134510 }, { "epoch": 32.3, "learning_rate": 7.844049353617962e-05, "loss": 0.0163, "step": 134520 }, { "epoch": 32.3, "learning_rate": 7.843754115174891e-05, "loss": 0.0154, "step": 134530 }, { "epoch": 32.3, "learning_rate": 7.843458862075086e-05, "loss": 0.0295, "step": 134540 }, { "epoch": 32.3, "learning_rate": 7.843163594320074e-05, "loss": 0.0168, "step": 134550 }, { "epoch": 32.31, "learning_rate": 7.842868311911369e-05, "loss": 0.0209, "step": 134560 }, { "epoch": 32.31, "learning_rate": 7.842573014850501e-05, "loss": 0.0374, "step": 134570 }, { "epoch": 32.31, "learning_rate": 7.842277703138985e-05, "loss": 0.0193, "step": 134580 }, { "epoch": 32.31, "learning_rate": 7.841982376778346e-05, "loss": 0.0158, "step": 134590 }, { "epoch": 32.32, "learning_rate": 7.841687035770106e-05, "loss": 0.0334, "step": 134600 }, { "epoch": 32.32, "learning_rate": 7.841391680115788e-05, "loss": 0.0172, "step": 134610 }, { "epoch": 32.32, "learning_rate": 7.841096309816913e-05, "loss": 0.0278, "step": 134620 }, { "epoch": 32.32, "learning_rate": 7.840800924875005e-05, "loss": 0.0159, "step": 134630 }, { "epoch": 32.33, "learning_rate": 7.840505525291586e-05, "loss": 0.0249, "step": 134640 }, { "epoch": 32.33, "learning_rate": 7.840210111068176e-05, "loss": 0.0147, "step": 134650 }, { "epoch": 32.33, "learning_rate": 7.839914682206299e-05, "loss": 0.0271, "step": 134660 }, { "epoch": 32.33, "learning_rate": 7.839619238707479e-05, "loss": 0.0256, "step": 134670 }, { "epoch": 32.33, "learning_rate": 7.839323780573237e-05, "loss": 0.0258, "step": 134680 }, { "epoch": 32.34, "learning_rate": 7.839028307805099e-05, "loss": 0.0283, "step": 134690 }, { "epoch": 32.34, "learning_rate": 7.838732820404582e-05, "loss": 0.0187, "step": 134700 }, { "epoch": 32.34, "learning_rate": 7.838437318373215e-05, "loss": 0.0137, "step": 134710 }, { "epoch": 32.34, "learning_rate": 7.838141801712518e-05, "loss": 0.0285, "step": 134720 }, { "epoch": 32.35, "learning_rate": 7.837846270424012e-05, "loss": 0.0132, "step": 134730 }, { "epoch": 32.35, "learning_rate": 7.837550724509224e-05, "loss": 0.0267, "step": 134740 }, { "epoch": 32.35, "learning_rate": 7.837255163969677e-05, "loss": 0.0228, "step": 134750 }, { "epoch": 32.35, "learning_rate": 7.836959588806892e-05, "loss": 0.0267, "step": 134760 }, { "epoch": 32.36, "learning_rate": 7.836663999022392e-05, "loss": 0.0129, "step": 134770 }, { "epoch": 32.36, "learning_rate": 7.836368394617706e-05, "loss": 0.0298, "step": 134780 }, { "epoch": 32.36, "learning_rate": 7.83607277559435e-05, "loss": 0.0317, "step": 134790 }, { "epoch": 32.36, "learning_rate": 7.835777141953853e-05, "loss": 0.016, "step": 134800 }, { "epoch": 32.36, "learning_rate": 7.835481493697736e-05, "loss": 0.0141, "step": 134810 }, { "epoch": 32.37, "learning_rate": 7.835185830827524e-05, "loss": 0.0265, "step": 134820 }, { "epoch": 32.37, "learning_rate": 7.83489015334474e-05, "loss": 0.0251, "step": 134830 }, { "epoch": 32.37, "learning_rate": 7.834594461250909e-05, "loss": 0.0316, "step": 134840 }, { "epoch": 32.37, "learning_rate": 7.834298754547556e-05, "loss": 0.0189, "step": 134850 }, { "epoch": 32.38, "learning_rate": 7.834003033236201e-05, "loss": 0.0275, "step": 134860 }, { "epoch": 32.38, "learning_rate": 7.833707297318372e-05, "loss": 0.0428, "step": 134870 }, { "epoch": 32.38, "learning_rate": 7.833411546795593e-05, "loss": 0.0207, "step": 134880 }, { "epoch": 32.38, "learning_rate": 7.833115781669384e-05, "loss": 0.0251, "step": 134890 }, { "epoch": 32.38, "learning_rate": 7.832820001941275e-05, "loss": 0.0309, "step": 134900 }, { "epoch": 32.39, "learning_rate": 7.832524207612788e-05, "loss": 0.0217, "step": 134910 }, { "epoch": 32.39, "learning_rate": 7.832228398685446e-05, "loss": 0.0177, "step": 134920 }, { "epoch": 32.39, "learning_rate": 7.831932575160777e-05, "loss": 0.031, "step": 134930 }, { "epoch": 32.39, "learning_rate": 7.831636737040303e-05, "loss": 0.0208, "step": 134940 }, { "epoch": 32.4, "learning_rate": 7.83134088432555e-05, "loss": 0.0158, "step": 134950 }, { "epoch": 32.4, "learning_rate": 7.831045017018042e-05, "loss": 0.0215, "step": 134960 }, { "epoch": 32.4, "learning_rate": 7.830749135119304e-05, "loss": 0.0186, "step": 134970 }, { "epoch": 32.4, "learning_rate": 7.830453238630861e-05, "loss": 0.0325, "step": 134980 }, { "epoch": 32.41, "learning_rate": 7.830157327554239e-05, "loss": 0.0174, "step": 134990 }, { "epoch": 32.41, "learning_rate": 7.829861401890964e-05, "loss": 0.0268, "step": 135000 }, { "epoch": 32.41, "learning_rate": 7.829565461642557e-05, "loss": 0.0192, "step": 135010 }, { "epoch": 32.41, "learning_rate": 7.829269506810548e-05, "loss": 0.0214, "step": 135020 }, { "epoch": 32.41, "learning_rate": 7.828973537396458e-05, "loss": 0.0267, "step": 135030 }, { "epoch": 32.42, "learning_rate": 7.828677553401818e-05, "loss": 0.0238, "step": 135040 }, { "epoch": 32.42, "learning_rate": 7.828381554828146e-05, "loss": 0.0312, "step": 135050 }, { "epoch": 32.42, "learning_rate": 7.828085541676976e-05, "loss": 0.0203, "step": 135060 }, { "epoch": 32.42, "learning_rate": 7.827789513949827e-05, "loss": 0.0338, "step": 135070 }, { "epoch": 32.43, "learning_rate": 7.827493471648228e-05, "loss": 0.0309, "step": 135080 }, { "epoch": 32.43, "learning_rate": 7.827197414773704e-05, "loss": 0.0194, "step": 135090 }, { "epoch": 32.43, "learning_rate": 7.826901343327781e-05, "loss": 0.0204, "step": 135100 }, { "epoch": 32.43, "learning_rate": 7.826605257311985e-05, "loss": 0.0176, "step": 135110 }, { "epoch": 32.44, "learning_rate": 7.82630915672784e-05, "loss": 0.0259, "step": 135120 }, { "epoch": 32.44, "learning_rate": 7.826013041576876e-05, "loss": 0.0328, "step": 135130 }, { "epoch": 32.44, "learning_rate": 7.825716911860618e-05, "loss": 0.0225, "step": 135140 }, { "epoch": 32.44, "learning_rate": 7.825420767580589e-05, "loss": 0.0167, "step": 135150 }, { "epoch": 32.44, "learning_rate": 7.825124608738318e-05, "loss": 0.025, "step": 135160 }, { "epoch": 32.45, "learning_rate": 7.824828435335334e-05, "loss": 0.02, "step": 135170 }, { "epoch": 32.45, "learning_rate": 7.824532247373158e-05, "loss": 0.013, "step": 135180 }, { "epoch": 32.45, "learning_rate": 7.824236044853319e-05, "loss": 0.0155, "step": 135190 }, { "epoch": 32.45, "learning_rate": 7.823939827777344e-05, "loss": 0.0203, "step": 135200 }, { "epoch": 32.46, "learning_rate": 7.823643596146761e-05, "loss": 0.0187, "step": 135210 }, { "epoch": 32.46, "learning_rate": 7.823347349963095e-05, "loss": 0.0192, "step": 135220 }, { "epoch": 32.46, "learning_rate": 7.823051089227873e-05, "loss": 0.0107, "step": 135230 }, { "epoch": 32.46, "learning_rate": 7.82275481394262e-05, "loss": 0.0187, "step": 135240 }, { "epoch": 32.46, "learning_rate": 7.822458524108869e-05, "loss": 0.0129, "step": 135250 }, { "epoch": 32.47, "learning_rate": 7.822162219728139e-05, "loss": 0.0307, "step": 135260 }, { "epoch": 32.47, "learning_rate": 7.821865900801965e-05, "loss": 0.0395, "step": 135270 }, { "epoch": 32.47, "learning_rate": 7.821569567331868e-05, "loss": 0.0182, "step": 135280 }, { "epoch": 32.47, "learning_rate": 7.82127321931938e-05, "loss": 0.0273, "step": 135290 }, { "epoch": 32.48, "learning_rate": 7.820976856766025e-05, "loss": 0.0207, "step": 135300 }, { "epoch": 32.48, "learning_rate": 7.82068047967333e-05, "loss": 0.0197, "step": 135310 }, { "epoch": 32.48, "learning_rate": 7.820384088042827e-05, "loss": 0.024, "step": 135320 }, { "epoch": 32.48, "learning_rate": 7.82008768187604e-05, "loss": 0.0182, "step": 135330 }, { "epoch": 32.49, "learning_rate": 7.819791261174496e-05, "loss": 0.0195, "step": 135340 }, { "epoch": 32.49, "learning_rate": 7.819494825939726e-05, "loss": 0.0125, "step": 135350 }, { "epoch": 32.49, "learning_rate": 7.819198376173255e-05, "loss": 0.0293, "step": 135360 }, { "epoch": 32.49, "learning_rate": 7.818901911876613e-05, "loss": 0.0208, "step": 135370 }, { "epoch": 32.49, "learning_rate": 7.818605433051327e-05, "loss": 0.0599, "step": 135380 }, { "epoch": 32.5, "learning_rate": 7.818308939698925e-05, "loss": 0.0201, "step": 135390 }, { "epoch": 32.5, "learning_rate": 7.818012431820935e-05, "loss": 0.0315, "step": 135400 }, { "epoch": 32.5, "learning_rate": 7.817715909418884e-05, "loss": 0.0103, "step": 135410 }, { "epoch": 32.5, "learning_rate": 7.817419372494303e-05, "loss": 0.0289, "step": 135420 }, { "epoch": 32.51, "learning_rate": 7.817122821048719e-05, "loss": 0.0271, "step": 135430 }, { "epoch": 32.51, "learning_rate": 7.816826255083661e-05, "loss": 0.0149, "step": 135440 }, { "epoch": 32.51, "learning_rate": 7.816529674600657e-05, "loss": 0.0402, "step": 135450 }, { "epoch": 32.51, "learning_rate": 7.816233079601234e-05, "loss": 0.039, "step": 135460 }, { "epoch": 32.52, "learning_rate": 7.815936470086922e-05, "loss": 0.0228, "step": 135470 }, { "epoch": 32.52, "learning_rate": 7.815639846059251e-05, "loss": 0.0232, "step": 135480 }, { "epoch": 32.52, "learning_rate": 7.81534320751975e-05, "loss": 0.0291, "step": 135490 }, { "epoch": 32.52, "learning_rate": 7.815046554469945e-05, "loss": 0.0284, "step": 135500 }, { "epoch": 32.52, "learning_rate": 7.814749886911366e-05, "loss": 0.0311, "step": 135510 }, { "epoch": 32.53, "learning_rate": 7.814453204845543e-05, "loss": 0.0222, "step": 135520 }, { "epoch": 32.53, "learning_rate": 7.814156508274004e-05, "loss": 0.0295, "step": 135530 }, { "epoch": 32.53, "learning_rate": 7.813859797198279e-05, "loss": 0.0402, "step": 135540 }, { "epoch": 32.53, "learning_rate": 7.813563071619898e-05, "loss": 0.0342, "step": 135550 }, { "epoch": 32.54, "learning_rate": 7.81326633154039e-05, "loss": 0.0452, "step": 135560 }, { "epoch": 32.54, "learning_rate": 7.812969576961285e-05, "loss": 0.0393, "step": 135570 }, { "epoch": 32.54, "learning_rate": 7.812672807884108e-05, "loss": 0.0309, "step": 135580 }, { "epoch": 32.54, "learning_rate": 7.812376024310393e-05, "loss": 0.0211, "step": 135590 }, { "epoch": 32.54, "learning_rate": 7.812079226241669e-05, "loss": 0.0208, "step": 135600 }, { "epoch": 32.55, "learning_rate": 7.811782413679464e-05, "loss": 0.0454, "step": 135610 }, { "epoch": 32.55, "learning_rate": 7.811485586625309e-05, "loss": 0.0576, "step": 135620 }, { "epoch": 32.55, "learning_rate": 7.811188745080735e-05, "loss": 0.027, "step": 135630 }, { "epoch": 32.55, "learning_rate": 7.810891889047271e-05, "loss": 0.0207, "step": 135640 }, { "epoch": 32.56, "learning_rate": 7.810595018526445e-05, "loss": 0.0275, "step": 135650 }, { "epoch": 32.56, "learning_rate": 7.81029813351979e-05, "loss": 0.0195, "step": 135660 }, { "epoch": 32.56, "learning_rate": 7.810001234028834e-05, "loss": 0.0197, "step": 135670 }, { "epoch": 32.56, "learning_rate": 7.80970432005511e-05, "loss": 0.0347, "step": 135680 }, { "epoch": 32.57, "learning_rate": 7.809407391600143e-05, "loss": 0.033, "step": 135690 }, { "epoch": 32.57, "learning_rate": 7.80911044866547e-05, "loss": 0.0218, "step": 135700 }, { "epoch": 32.57, "learning_rate": 7.808813491252618e-05, "loss": 0.0319, "step": 135710 }, { "epoch": 32.57, "learning_rate": 7.808516519363116e-05, "loss": 0.0296, "step": 135720 }, { "epoch": 32.57, "learning_rate": 7.808219532998498e-05, "loss": 0.0228, "step": 135730 }, { "epoch": 32.58, "learning_rate": 7.807922532160292e-05, "loss": 0.0422, "step": 135740 }, { "epoch": 32.58, "learning_rate": 7.80762551685003e-05, "loss": 0.0365, "step": 135750 }, { "epoch": 32.58, "learning_rate": 7.807328487069243e-05, "loss": 0.0263, "step": 135760 }, { "epoch": 32.58, "learning_rate": 7.807031442819461e-05, "loss": 0.0236, "step": 135770 }, { "epoch": 32.59, "learning_rate": 7.806734384102217e-05, "loss": 0.0154, "step": 135780 }, { "epoch": 32.59, "learning_rate": 7.80643731091904e-05, "loss": 0.0305, "step": 135790 }, { "epoch": 32.59, "learning_rate": 7.806140223271461e-05, "loss": 0.036, "step": 135800 }, { "epoch": 32.59, "learning_rate": 7.805843121161011e-05, "loss": 0.015, "step": 135810 }, { "epoch": 32.6, "learning_rate": 7.805546004589223e-05, "loss": 0.0248, "step": 135820 }, { "epoch": 32.6, "learning_rate": 7.805248873557626e-05, "loss": 0.0375, "step": 135830 }, { "epoch": 32.6, "learning_rate": 7.804951728067756e-05, "loss": 0.0418, "step": 135840 }, { "epoch": 32.6, "learning_rate": 7.804654568121139e-05, "loss": 0.028, "step": 135850 }, { "epoch": 32.6, "learning_rate": 7.80435739371931e-05, "loss": 0.0407, "step": 135860 }, { "epoch": 32.61, "learning_rate": 7.804060204863799e-05, "loss": 0.0337, "step": 135870 }, { "epoch": 32.61, "learning_rate": 7.803763001556139e-05, "loss": 0.0202, "step": 135880 }, { "epoch": 32.61, "learning_rate": 7.80346578379786e-05, "loss": 0.0351, "step": 135890 }, { "epoch": 32.61, "learning_rate": 7.803168551590495e-05, "loss": 0.0226, "step": 135900 }, { "epoch": 32.62, "learning_rate": 7.802871304935576e-05, "loss": 0.03, "step": 135910 }, { "epoch": 32.62, "learning_rate": 7.802574043834635e-05, "loss": 0.0354, "step": 135920 }, { "epoch": 32.62, "learning_rate": 7.802276768289205e-05, "loss": 0.0253, "step": 135930 }, { "epoch": 32.62, "learning_rate": 7.801979478300816e-05, "loss": 0.0492, "step": 135940 }, { "epoch": 32.62, "learning_rate": 7.801682173871002e-05, "loss": 0.0406, "step": 135950 }, { "epoch": 32.63, "learning_rate": 7.801384855001293e-05, "loss": 0.0214, "step": 135960 }, { "epoch": 32.63, "learning_rate": 7.801087521693225e-05, "loss": 0.0383, "step": 135970 }, { "epoch": 32.63, "learning_rate": 7.800790173948327e-05, "loss": 0.0192, "step": 135980 }, { "epoch": 32.63, "learning_rate": 7.800492811768134e-05, "loss": 0.0175, "step": 135990 }, { "epoch": 32.64, "learning_rate": 7.800195435154178e-05, "loss": 0.0332, "step": 136000 }, { "epoch": 32.64, "learning_rate": 7.79989804410799e-05, "loss": 0.0209, "step": 136010 }, { "epoch": 32.64, "learning_rate": 7.799600638631105e-05, "loss": 0.039, "step": 136020 }, { "epoch": 32.64, "learning_rate": 7.799303218725054e-05, "loss": 0.0314, "step": 136030 }, { "epoch": 32.65, "learning_rate": 7.799005784391372e-05, "loss": 0.0318, "step": 136040 }, { "epoch": 32.65, "learning_rate": 7.798708335631589e-05, "loss": 0.0119, "step": 136050 }, { "epoch": 32.65, "learning_rate": 7.798410872447241e-05, "loss": 0.0255, "step": 136060 }, { "epoch": 32.65, "learning_rate": 7.798113394839861e-05, "loss": 0.0191, "step": 136070 }, { "epoch": 32.65, "learning_rate": 7.79781590281098e-05, "loss": 0.0187, "step": 136080 }, { "epoch": 32.66, "learning_rate": 7.797518396362134e-05, "loss": 0.0253, "step": 136090 }, { "epoch": 32.66, "learning_rate": 7.797220875494853e-05, "loss": 0.0115, "step": 136100 }, { "epoch": 32.66, "learning_rate": 7.796923340210672e-05, "loss": 0.0434, "step": 136110 }, { "epoch": 32.66, "learning_rate": 7.796625790511125e-05, "loss": 0.0265, "step": 136120 }, { "epoch": 32.67, "learning_rate": 7.796328226397746e-05, "loss": 0.0327, "step": 136130 }, { "epoch": 32.67, "learning_rate": 7.796030647872068e-05, "loss": 0.0173, "step": 136140 }, { "epoch": 32.67, "learning_rate": 7.795733054935625e-05, "loss": 0.0371, "step": 136150 }, { "epoch": 32.67, "learning_rate": 7.79543544758995e-05, "loss": 0.0175, "step": 136160 }, { "epoch": 32.68, "learning_rate": 7.795137825836576e-05, "loss": 0.0295, "step": 136170 }, { "epoch": 32.68, "learning_rate": 7.79484018967704e-05, "loss": 0.0264, "step": 136180 }, { "epoch": 32.68, "learning_rate": 7.794542539112873e-05, "loss": 0.0303, "step": 136190 }, { "epoch": 32.68, "learning_rate": 7.794244874145611e-05, "loss": 0.0368, "step": 136200 }, { "epoch": 32.68, "learning_rate": 7.793947194776787e-05, "loss": 0.0325, "step": 136210 }, { "epoch": 32.69, "learning_rate": 7.793649501007937e-05, "loss": 0.0227, "step": 136220 }, { "epoch": 32.69, "learning_rate": 7.793351792840595e-05, "loss": 0.0096, "step": 136230 }, { "epoch": 32.69, "learning_rate": 7.793054070276294e-05, "loss": 0.0256, "step": 136240 }, { "epoch": 32.69, "learning_rate": 7.792756333316567e-05, "loss": 0.0273, "step": 136250 }, { "epoch": 32.7, "learning_rate": 7.792458581962951e-05, "loss": 0.0203, "step": 136260 }, { "epoch": 32.7, "learning_rate": 7.79216081621698e-05, "loss": 0.0191, "step": 136270 }, { "epoch": 32.7, "learning_rate": 7.791863036080191e-05, "loss": 0.0246, "step": 136280 }, { "epoch": 32.7, "learning_rate": 7.791565241554115e-05, "loss": 0.0238, "step": 136290 }, { "epoch": 32.7, "learning_rate": 7.791267432640288e-05, "loss": 0.0199, "step": 136300 }, { "epoch": 32.71, "learning_rate": 7.790969609340246e-05, "loss": 0.031, "step": 136310 }, { "epoch": 32.71, "learning_rate": 7.790671771655525e-05, "loss": 0.0179, "step": 136320 }, { "epoch": 32.71, "learning_rate": 7.790373919587655e-05, "loss": 0.0255, "step": 136330 }, { "epoch": 32.71, "learning_rate": 7.790076053138175e-05, "loss": 0.0306, "step": 136340 }, { "epoch": 32.72, "learning_rate": 7.789778172308622e-05, "loss": 0.0296, "step": 136350 }, { "epoch": 32.72, "learning_rate": 7.789480277100527e-05, "loss": 0.0319, "step": 136360 }, { "epoch": 32.72, "learning_rate": 7.789182367515429e-05, "loss": 0.0177, "step": 136370 }, { "epoch": 32.72, "learning_rate": 7.78888444355486e-05, "loss": 0.0323, "step": 136380 }, { "epoch": 32.73, "learning_rate": 7.788586505220359e-05, "loss": 0.0182, "step": 136390 }, { "epoch": 32.73, "learning_rate": 7.788288552513458e-05, "loss": 0.024, "step": 136400 }, { "epoch": 32.73, "learning_rate": 7.787990585435696e-05, "loss": 0.0169, "step": 136410 }, { "epoch": 32.73, "learning_rate": 7.787692603988606e-05, "loss": 0.0244, "step": 136420 }, { "epoch": 32.73, "learning_rate": 7.787394608173726e-05, "loss": 0.0222, "step": 136430 }, { "epoch": 32.74, "learning_rate": 7.787096597992592e-05, "loss": 0.0383, "step": 136440 }, { "epoch": 32.74, "learning_rate": 7.786798573446736e-05, "loss": 0.0412, "step": 136450 }, { "epoch": 32.74, "learning_rate": 7.786500534537699e-05, "loss": 0.0566, "step": 136460 }, { "epoch": 32.74, "learning_rate": 7.786202481267013e-05, "loss": 0.0188, "step": 136470 }, { "epoch": 32.75, "learning_rate": 7.785904413636218e-05, "loss": 0.0362, "step": 136480 }, { "epoch": 32.75, "learning_rate": 7.785606331646848e-05, "loss": 0.0211, "step": 136490 }, { "epoch": 32.75, "learning_rate": 7.78530823530044e-05, "loss": 0.0235, "step": 136500 }, { "epoch": 32.75, "learning_rate": 7.785010124598529e-05, "loss": 0.0313, "step": 136510 }, { "epoch": 32.76, "learning_rate": 7.784711999542653e-05, "loss": 0.0302, "step": 136520 }, { "epoch": 32.76, "learning_rate": 7.784413860134348e-05, "loss": 0.0314, "step": 136530 }, { "epoch": 32.76, "learning_rate": 7.78411570637515e-05, "loss": 0.0229, "step": 136540 }, { "epoch": 32.76, "learning_rate": 7.783817538266597e-05, "loss": 0.0343, "step": 136550 }, { "epoch": 32.76, "learning_rate": 7.783519355810225e-05, "loss": 0.0221, "step": 136560 }, { "epoch": 32.77, "learning_rate": 7.783221159007572e-05, "loss": 0.0172, "step": 136570 }, { "epoch": 32.77, "learning_rate": 7.782922947860173e-05, "loss": 0.0545, "step": 136580 }, { "epoch": 32.77, "learning_rate": 7.782624722369565e-05, "loss": 0.0351, "step": 136590 }, { "epoch": 32.77, "learning_rate": 7.782326482537287e-05, "loss": 0.0226, "step": 136600 }, { "epoch": 32.78, "learning_rate": 7.782028228364876e-05, "loss": 0.0404, "step": 136610 }, { "epoch": 32.78, "learning_rate": 7.781729959853868e-05, "loss": 0.0277, "step": 136620 }, { "epoch": 32.78, "learning_rate": 7.781431677005799e-05, "loss": 0.0264, "step": 136630 }, { "epoch": 32.78, "learning_rate": 7.781133379822207e-05, "loss": 0.0273, "step": 136640 }, { "epoch": 32.78, "learning_rate": 7.780835068304633e-05, "loss": 0.0161, "step": 136650 }, { "epoch": 32.79, "learning_rate": 7.780536742454612e-05, "loss": 0.0206, "step": 136660 }, { "epoch": 32.79, "learning_rate": 7.780238402273679e-05, "loss": 0.033, "step": 136670 }, { "epoch": 32.79, "learning_rate": 7.779940047763375e-05, "loss": 0.0254, "step": 136680 }, { "epoch": 32.79, "learning_rate": 7.779641678925237e-05, "loss": 0.0143, "step": 136690 }, { "epoch": 32.8, "learning_rate": 7.779343295760803e-05, "loss": 0.0319, "step": 136700 }, { "epoch": 32.8, "learning_rate": 7.77904489827161e-05, "loss": 0.0238, "step": 136710 }, { "epoch": 32.8, "learning_rate": 7.778746486459196e-05, "loss": 0.0294, "step": 136720 }, { "epoch": 32.8, "learning_rate": 7.7784480603251e-05, "loss": 0.0324, "step": 136730 }, { "epoch": 32.81, "learning_rate": 7.778149619870859e-05, "loss": 0.0352, "step": 136740 }, { "epoch": 32.81, "learning_rate": 7.777851165098012e-05, "loss": 0.0358, "step": 136750 }, { "epoch": 32.81, "learning_rate": 7.777552696008097e-05, "loss": 0.0158, "step": 136760 }, { "epoch": 32.81, "learning_rate": 7.777254212602651e-05, "loss": 0.0227, "step": 136770 }, { "epoch": 32.81, "learning_rate": 7.776955714883214e-05, "loss": 0.0199, "step": 136780 }, { "epoch": 32.82, "learning_rate": 7.776657202851325e-05, "loss": 0.0341, "step": 136790 }, { "epoch": 32.82, "learning_rate": 7.776358676508522e-05, "loss": 0.0139, "step": 136800 }, { "epoch": 32.82, "learning_rate": 7.776060135856341e-05, "loss": 0.0202, "step": 136810 }, { "epoch": 32.82, "learning_rate": 7.775761580896324e-05, "loss": 0.0363, "step": 136820 }, { "epoch": 32.83, "learning_rate": 7.775463011630008e-05, "loss": 0.0336, "step": 136830 }, { "epoch": 32.83, "learning_rate": 7.775164428058934e-05, "loss": 0.0211, "step": 136840 }, { "epoch": 32.83, "learning_rate": 7.774865830184639e-05, "loss": 0.0206, "step": 136850 }, { "epoch": 32.83, "learning_rate": 7.774567218008661e-05, "loss": 0.021, "step": 136860 }, { "epoch": 32.84, "learning_rate": 7.774268591532541e-05, "loss": 0.0226, "step": 136870 }, { "epoch": 32.84, "learning_rate": 7.773969950757817e-05, "loss": 0.0272, "step": 136880 }, { "epoch": 32.84, "learning_rate": 7.77367129568603e-05, "loss": 0.0213, "step": 136890 }, { "epoch": 32.84, "learning_rate": 7.773372626318717e-05, "loss": 0.0372, "step": 136900 }, { "epoch": 32.84, "learning_rate": 7.773073942657419e-05, "loss": 0.0245, "step": 136910 }, { "epoch": 32.85, "learning_rate": 7.772775244703674e-05, "loss": 0.0218, "step": 136920 }, { "epoch": 32.85, "learning_rate": 7.772476532459023e-05, "loss": 0.015, "step": 136930 }, { "epoch": 32.85, "learning_rate": 7.772177805925005e-05, "loss": 0.0315, "step": 136940 }, { "epoch": 32.85, "learning_rate": 7.771879065103157e-05, "loss": 0.0252, "step": 136950 }, { "epoch": 32.86, "learning_rate": 7.771580309995024e-05, "loss": 0.0163, "step": 136960 }, { "epoch": 32.86, "learning_rate": 7.771281540602141e-05, "loss": 0.0113, "step": 136970 }, { "epoch": 32.86, "learning_rate": 7.770982756926051e-05, "loss": 0.0238, "step": 136980 }, { "epoch": 32.86, "learning_rate": 7.770683958968292e-05, "loss": 0.0213, "step": 136990 }, { "epoch": 32.86, "learning_rate": 7.770385146730405e-05, "loss": 0.013, "step": 137000 }, { "epoch": 32.87, "learning_rate": 7.77008632021393e-05, "loss": 0.0441, "step": 137010 }, { "epoch": 32.87, "learning_rate": 7.769787479420406e-05, "loss": 0.0339, "step": 137020 }, { "epoch": 32.87, "learning_rate": 7.769488624351375e-05, "loss": 0.0343, "step": 137030 }, { "epoch": 32.87, "learning_rate": 7.769189755008377e-05, "loss": 0.0259, "step": 137040 }, { "epoch": 32.88, "learning_rate": 7.768890871392951e-05, "loss": 0.0177, "step": 137050 }, { "epoch": 32.88, "learning_rate": 7.768591973506639e-05, "loss": 0.0119, "step": 137060 }, { "epoch": 32.88, "learning_rate": 7.76829306135098e-05, "loss": 0.0233, "step": 137070 }, { "epoch": 32.88, "learning_rate": 7.767994134927515e-05, "loss": 0.013, "step": 137080 }, { "epoch": 32.89, "learning_rate": 7.767695194237786e-05, "loss": 0.0165, "step": 137090 }, { "epoch": 32.89, "learning_rate": 7.767396239283333e-05, "loss": 0.0231, "step": 137100 }, { "epoch": 32.89, "learning_rate": 7.767097270065695e-05, "loss": 0.0268, "step": 137110 }, { "epoch": 32.89, "learning_rate": 7.766798286586416e-05, "loss": 0.0246, "step": 137120 }, { "epoch": 32.89, "learning_rate": 7.766499288847036e-05, "loss": 0.0277, "step": 137130 }, { "epoch": 32.9, "learning_rate": 7.766200276849095e-05, "loss": 0.0173, "step": 137140 }, { "epoch": 32.9, "learning_rate": 7.765901250594135e-05, "loss": 0.0219, "step": 137150 }, { "epoch": 32.9, "learning_rate": 7.765602210083695e-05, "loss": 0.0136, "step": 137160 }, { "epoch": 32.9, "learning_rate": 7.765303155319321e-05, "loss": 0.0175, "step": 137170 }, { "epoch": 32.91, "learning_rate": 7.765004086302549e-05, "loss": 0.0226, "step": 137180 }, { "epoch": 32.91, "learning_rate": 7.764705003034925e-05, "loss": 0.0246, "step": 137190 }, { "epoch": 32.91, "learning_rate": 7.764405905517986e-05, "loss": 0.026, "step": 137200 }, { "epoch": 32.91, "learning_rate": 7.764106793753277e-05, "loss": 0.0272, "step": 137210 }, { "epoch": 32.91, "learning_rate": 7.76380766774234e-05, "loss": 0.0167, "step": 137220 }, { "epoch": 32.92, "learning_rate": 7.763508527486712e-05, "loss": 0.0219, "step": 137230 }, { "epoch": 32.92, "learning_rate": 7.76320937298794e-05, "loss": 0.0143, "step": 137240 }, { "epoch": 32.92, "learning_rate": 7.762910204247562e-05, "loss": 0.0252, "step": 137250 }, { "epoch": 32.92, "learning_rate": 7.762611021267123e-05, "loss": 0.0184, "step": 137260 }, { "epoch": 32.93, "learning_rate": 7.762311824048165e-05, "loss": 0.0357, "step": 137270 }, { "epoch": 32.93, "learning_rate": 7.762012612592227e-05, "loss": 0.0178, "step": 137280 }, { "epoch": 32.93, "learning_rate": 7.761713386900854e-05, "loss": 0.0199, "step": 137290 }, { "epoch": 32.93, "learning_rate": 7.761414146975586e-05, "loss": 0.017, "step": 137300 }, { "epoch": 32.94, "learning_rate": 7.761114892817967e-05, "loss": 0.0154, "step": 137310 }, { "epoch": 32.94, "learning_rate": 7.760815624429538e-05, "loss": 0.0346, "step": 137320 }, { "epoch": 32.94, "learning_rate": 7.760516341811843e-05, "loss": 0.0203, "step": 137330 }, { "epoch": 32.94, "learning_rate": 7.760217044966425e-05, "loss": 0.0216, "step": 137340 }, { "epoch": 32.94, "learning_rate": 7.759917733894823e-05, "loss": 0.0218, "step": 137350 }, { "epoch": 32.95, "learning_rate": 7.759618408598583e-05, "loss": 0.0245, "step": 137360 }, { "epoch": 32.95, "learning_rate": 7.759319069079248e-05, "loss": 0.025, "step": 137370 }, { "epoch": 33.0, "learning_rate": 7.759019715338357e-05, "loss": 0.017, "step": 137380 }, { "epoch": 33.0, "learning_rate": 7.758720347377455e-05, "loss": 0.0378, "step": 137390 }, { "epoch": 33.0, "learning_rate": 7.758420965198087e-05, "loss": 0.0241, "step": 137400 }, { "epoch": 33.01, "learning_rate": 7.758121568801793e-05, "loss": 0.0145, "step": 137410 }, { "epoch": 33.01, "learning_rate": 7.757822158190118e-05, "loss": 0.0684, "step": 137420 }, { "epoch": 33.01, "learning_rate": 7.757522733364605e-05, "loss": 0.0279, "step": 137430 }, { "epoch": 33.01, "learning_rate": 7.757223294326797e-05, "loss": 0.0223, "step": 137440 }, { "epoch": 33.02, "learning_rate": 7.756923841078237e-05, "loss": 0.0301, "step": 137450 }, { "epoch": 33.02, "learning_rate": 7.756624373620468e-05, "loss": 0.0399, "step": 137460 }, { "epoch": 33.02, "learning_rate": 7.756324891955034e-05, "loss": 0.0156, "step": 137470 }, { "epoch": 33.02, "learning_rate": 7.756025396083477e-05, "loss": 0.0183, "step": 137480 }, { "epoch": 33.03, "learning_rate": 7.755725886007343e-05, "loss": 0.0248, "step": 137490 }, { "epoch": 33.03, "learning_rate": 7.755426361728177e-05, "loss": 0.0264, "step": 137500 }, { "epoch": 33.03, "learning_rate": 7.755126823247519e-05, "loss": 0.0171, "step": 137510 }, { "epoch": 33.03, "learning_rate": 7.754827270566913e-05, "loss": 0.0364, "step": 137520 }, { "epoch": 33.03, "learning_rate": 7.754527703687906e-05, "loss": 0.0288, "step": 137530 }, { "epoch": 33.04, "learning_rate": 7.754228122612039e-05, "loss": 0.0345, "step": 137540 }, { "epoch": 33.04, "learning_rate": 7.753928527340858e-05, "loss": 0.0314, "step": 137550 }, { "epoch": 33.04, "learning_rate": 7.753628917875906e-05, "loss": 0.0343, "step": 137560 }, { "epoch": 33.04, "learning_rate": 7.753329294218728e-05, "loss": 0.0145, "step": 137570 }, { "epoch": 33.05, "learning_rate": 7.753029656370869e-05, "loss": 0.0218, "step": 137580 }, { "epoch": 33.05, "learning_rate": 7.75273000433387e-05, "loss": 0.0162, "step": 137590 }, { "epoch": 33.05, "learning_rate": 7.752430338109277e-05, "loss": 0.03, "step": 137600 }, { "epoch": 33.05, "learning_rate": 7.752130657698636e-05, "loss": 0.0289, "step": 137610 }, { "epoch": 33.06, "learning_rate": 7.751830963103491e-05, "loss": 0.0195, "step": 137620 }, { "epoch": 33.06, "learning_rate": 7.751531254325386e-05, "loss": 0.0206, "step": 137630 }, { "epoch": 33.06, "learning_rate": 7.751231531365866e-05, "loss": 0.0235, "step": 137640 }, { "epoch": 33.06, "learning_rate": 7.750931794226475e-05, "loss": 0.0231, "step": 137650 }, { "epoch": 33.06, "learning_rate": 7.75063204290876e-05, "loss": 0.0273, "step": 137660 }, { "epoch": 33.07, "learning_rate": 7.750332277414263e-05, "loss": 0.0443, "step": 137670 }, { "epoch": 33.07, "learning_rate": 7.750032497744532e-05, "loss": 0.0307, "step": 137680 }, { "epoch": 33.07, "learning_rate": 7.749732703901109e-05, "loss": 0.015, "step": 137690 }, { "epoch": 33.07, "learning_rate": 7.749432895885541e-05, "loss": 0.0222, "step": 137700 }, { "epoch": 33.08, "learning_rate": 7.749133073699372e-05, "loss": 0.0316, "step": 137710 }, { "epoch": 33.08, "learning_rate": 7.748833237344151e-05, "loss": 0.024, "step": 137720 }, { "epoch": 33.08, "learning_rate": 7.748533386821418e-05, "loss": 0.0178, "step": 137730 }, { "epoch": 33.08, "learning_rate": 7.748233522132722e-05, "loss": 0.0239, "step": 137740 }, { "epoch": 33.08, "learning_rate": 7.747933643279607e-05, "loss": 0.0355, "step": 137750 }, { "epoch": 33.09, "learning_rate": 7.747633750263619e-05, "loss": 0.0284, "step": 137760 }, { "epoch": 33.09, "learning_rate": 7.747333843086304e-05, "loss": 0.0214, "step": 137770 }, { "epoch": 33.09, "learning_rate": 7.747033921749207e-05, "loss": 0.017, "step": 137780 }, { "epoch": 33.09, "learning_rate": 7.746733986253873e-05, "loss": 0.0334, "step": 137790 }, { "epoch": 33.1, "learning_rate": 7.746434036601853e-05, "loss": 0.0296, "step": 137800 }, { "epoch": 33.1, "learning_rate": 7.746134072794686e-05, "loss": 0.0216, "step": 137810 }, { "epoch": 33.1, "learning_rate": 7.745834094833921e-05, "loss": 0.0313, "step": 137820 }, { "epoch": 33.1, "learning_rate": 7.745534102721106e-05, "loss": 0.0273, "step": 137830 }, { "epoch": 33.11, "learning_rate": 7.745234096457782e-05, "loss": 0.0228, "step": 137840 }, { "epoch": 33.11, "learning_rate": 7.744934076045502e-05, "loss": 0.0394, "step": 137850 }, { "epoch": 33.11, "learning_rate": 7.744634041485808e-05, "loss": 0.0314, "step": 137860 }, { "epoch": 33.11, "learning_rate": 7.744333992780246e-05, "loss": 0.0257, "step": 137870 }, { "epoch": 33.11, "learning_rate": 7.744033929930365e-05, "loss": 0.0307, "step": 137880 }, { "epoch": 33.12, "learning_rate": 7.74373385293771e-05, "loss": 0.0256, "step": 137890 }, { "epoch": 33.12, "learning_rate": 7.743433761803825e-05, "loss": 0.0261, "step": 137900 }, { "epoch": 33.12, "learning_rate": 7.743133656530263e-05, "loss": 0.0121, "step": 137910 }, { "epoch": 33.12, "learning_rate": 7.742833537118566e-05, "loss": 0.0262, "step": 137920 }, { "epoch": 33.13, "learning_rate": 7.742533403570281e-05, "loss": 0.0222, "step": 137930 }, { "epoch": 33.13, "learning_rate": 7.742233255886957e-05, "loss": 0.0137, "step": 137940 }, { "epoch": 33.13, "learning_rate": 7.74193309407014e-05, "loss": 0.0434, "step": 137950 }, { "epoch": 33.13, "learning_rate": 7.741632918121376e-05, "loss": 0.0358, "step": 137960 }, { "epoch": 33.14, "learning_rate": 7.741332728042215e-05, "loss": 0.0196, "step": 137970 }, { "epoch": 33.14, "learning_rate": 7.7410325238342e-05, "loss": 0.0248, "step": 137980 }, { "epoch": 33.14, "learning_rate": 7.74073230549888e-05, "loss": 0.0297, "step": 137990 }, { "epoch": 33.14, "learning_rate": 7.740432073037804e-05, "loss": 0.0174, "step": 138000 }, { "epoch": 33.14, "learning_rate": 7.74013182645252e-05, "loss": 0.0097, "step": 138010 }, { "epoch": 33.15, "learning_rate": 7.73983156574457e-05, "loss": 0.0275, "step": 138020 }, { "epoch": 33.15, "learning_rate": 7.739531290915509e-05, "loss": 0.0155, "step": 138030 }, { "epoch": 33.15, "learning_rate": 7.739231001966878e-05, "loss": 0.0224, "step": 138040 }, { "epoch": 33.15, "learning_rate": 7.738930698900228e-05, "loss": 0.0188, "step": 138050 }, { "epoch": 33.16, "learning_rate": 7.738630381717108e-05, "loss": 0.0242, "step": 138060 }, { "epoch": 33.16, "learning_rate": 7.738330050419062e-05, "loss": 0.0285, "step": 138070 }, { "epoch": 33.16, "learning_rate": 7.738029705007641e-05, "loss": 0.014, "step": 138080 }, { "epoch": 33.16, "learning_rate": 7.737729345484392e-05, "loss": 0.0158, "step": 138090 }, { "epoch": 33.16, "learning_rate": 7.737428971850865e-05, "loss": 0.0183, "step": 138100 }, { "epoch": 33.17, "learning_rate": 7.737128584108603e-05, "loss": 0.0189, "step": 138110 }, { "epoch": 33.17, "learning_rate": 7.736828182259159e-05, "loss": 0.0205, "step": 138120 }, { "epoch": 33.17, "learning_rate": 7.736527766304078e-05, "loss": 0.0157, "step": 138130 }, { "epoch": 33.17, "learning_rate": 7.736227336244913e-05, "loss": 0.0347, "step": 138140 }, { "epoch": 33.18, "learning_rate": 7.735926892083207e-05, "loss": 0.0223, "step": 138150 }, { "epoch": 33.18, "learning_rate": 7.73562643382051e-05, "loss": 0.0381, "step": 138160 }, { "epoch": 33.18, "learning_rate": 7.735325961458375e-05, "loss": 0.0178, "step": 138170 }, { "epoch": 33.18, "learning_rate": 7.735025474998345e-05, "loss": 0.0402, "step": 138180 }, { "epoch": 33.19, "learning_rate": 7.734724974441971e-05, "loss": 0.0463, "step": 138190 }, { "epoch": 33.19, "learning_rate": 7.7344244597908e-05, "loss": 0.0178, "step": 138200 }, { "epoch": 33.19, "learning_rate": 7.734123931046386e-05, "loss": 0.0427, "step": 138210 }, { "epoch": 33.19, "learning_rate": 7.733823388210273e-05, "loss": 0.0227, "step": 138220 }, { "epoch": 33.19, "learning_rate": 7.73352283128401e-05, "loss": 0.0222, "step": 138230 }, { "epoch": 33.2, "learning_rate": 7.73322226026915e-05, "loss": 0.0267, "step": 138240 }, { "epoch": 33.2, "learning_rate": 7.732921675167237e-05, "loss": 0.0115, "step": 138250 }, { "epoch": 33.2, "learning_rate": 7.732621075979824e-05, "loss": 0.0232, "step": 138260 }, { "epoch": 33.2, "learning_rate": 7.73232046270846e-05, "loss": 0.0207, "step": 138270 }, { "epoch": 33.21, "learning_rate": 7.732019835354691e-05, "loss": 0.0217, "step": 138280 }, { "epoch": 33.21, "learning_rate": 7.731719193920072e-05, "loss": 0.0123, "step": 138290 }, { "epoch": 33.21, "learning_rate": 7.731418538406148e-05, "loss": 0.0178, "step": 138300 }, { "epoch": 33.21, "learning_rate": 7.73111786881447e-05, "loss": 0.0281, "step": 138310 }, { "epoch": 33.22, "learning_rate": 7.730817185146588e-05, "loss": 0.0166, "step": 138320 }, { "epoch": 33.22, "learning_rate": 7.73051648740405e-05, "loss": 0.0207, "step": 138330 }, { "epoch": 33.22, "learning_rate": 7.730215775588408e-05, "loss": 0.0289, "step": 138340 }, { "epoch": 33.22, "learning_rate": 7.729915049701212e-05, "loss": 0.019, "step": 138350 }, { "epoch": 33.22, "learning_rate": 7.72961430974401e-05, "loss": 0.0452, "step": 138360 }, { "epoch": 33.23, "learning_rate": 7.729313555718354e-05, "loss": 0.0149, "step": 138370 }, { "epoch": 33.23, "learning_rate": 7.729012787625794e-05, "loss": 0.0269, "step": 138380 }, { "epoch": 33.23, "learning_rate": 7.728712005467876e-05, "loss": 0.0318, "step": 138390 }, { "epoch": 33.23, "learning_rate": 7.728411209246156e-05, "loss": 0.0248, "step": 138400 }, { "epoch": 33.24, "learning_rate": 7.728110398962181e-05, "loss": 0.0193, "step": 138410 }, { "epoch": 33.24, "learning_rate": 7.727809574617501e-05, "loss": 0.0249, "step": 138420 }, { "epoch": 33.24, "learning_rate": 7.72750873621367e-05, "loss": 0.0132, "step": 138430 }, { "epoch": 33.24, "learning_rate": 7.727207883752235e-05, "loss": 0.0198, "step": 138440 }, { "epoch": 33.24, "learning_rate": 7.726907017234747e-05, "loss": 0.0159, "step": 138450 }, { "epoch": 33.25, "learning_rate": 7.72660613666276e-05, "loss": 0.0165, "step": 138460 }, { "epoch": 33.25, "learning_rate": 7.72630524203782e-05, "loss": 0.0202, "step": 138470 }, { "epoch": 33.25, "learning_rate": 7.72600433336148e-05, "loss": 0.0297, "step": 138480 }, { "epoch": 33.25, "learning_rate": 7.725703410635292e-05, "loss": 0.0354, "step": 138490 }, { "epoch": 33.26, "learning_rate": 7.725402473860806e-05, "loss": 0.0172, "step": 138500 }, { "epoch": 33.26, "learning_rate": 7.725101523039572e-05, "loss": 0.018, "step": 138510 }, { "epoch": 33.26, "learning_rate": 7.724800558173142e-05, "loss": 0.0163, "step": 138520 }, { "epoch": 33.26, "learning_rate": 7.724499579263067e-05, "loss": 0.0183, "step": 138530 }, { "epoch": 33.27, "learning_rate": 7.724198586310899e-05, "loss": 0.0143, "step": 138540 }, { "epoch": 33.27, "learning_rate": 7.723897579318187e-05, "loss": 0.0123, "step": 138550 }, { "epoch": 33.27, "learning_rate": 7.723596558286486e-05, "loss": 0.035, "step": 138560 }, { "epoch": 33.27, "learning_rate": 7.723295523217345e-05, "loss": 0.0188, "step": 138570 }, { "epoch": 33.27, "learning_rate": 7.722994474112317e-05, "loss": 0.0265, "step": 138580 }, { "epoch": 33.28, "learning_rate": 7.722693410972952e-05, "loss": 0.0181, "step": 138590 }, { "epoch": 33.28, "learning_rate": 7.722392333800802e-05, "loss": 0.0157, "step": 138600 }, { "epoch": 33.28, "learning_rate": 7.72209124259742e-05, "loss": 0.0103, "step": 138610 }, { "epoch": 33.28, "learning_rate": 7.721790137364355e-05, "loss": 0.0289, "step": 138620 }, { "epoch": 33.29, "learning_rate": 7.721489018103163e-05, "loss": 0.0154, "step": 138630 }, { "epoch": 33.29, "learning_rate": 7.721187884815392e-05, "loss": 0.0297, "step": 138640 }, { "epoch": 33.29, "learning_rate": 7.720886737502598e-05, "loss": 0.0189, "step": 138650 }, { "epoch": 33.29, "learning_rate": 7.72058557616633e-05, "loss": 0.0255, "step": 138660 }, { "epoch": 33.3, "learning_rate": 7.720284400808143e-05, "loss": 0.0194, "step": 138670 }, { "epoch": 33.3, "learning_rate": 7.719983211429585e-05, "loss": 0.016, "step": 138680 }, { "epoch": 33.3, "learning_rate": 7.71968200803221e-05, "loss": 0.0306, "step": 138690 }, { "epoch": 33.3, "learning_rate": 7.719380790617575e-05, "loss": 0.0153, "step": 138700 }, { "epoch": 33.3, "learning_rate": 7.719079559187226e-05, "loss": 0.0231, "step": 138710 }, { "epoch": 33.31, "learning_rate": 7.718778313742719e-05, "loss": 0.0143, "step": 138720 }, { "epoch": 33.31, "learning_rate": 7.718477054285604e-05, "loss": 0.0309, "step": 138730 }, { "epoch": 33.31, "learning_rate": 7.718175780817439e-05, "loss": 0.0207, "step": 138740 }, { "epoch": 33.31, "learning_rate": 7.71787449333977e-05, "loss": 0.0259, "step": 138750 }, { "epoch": 33.32, "learning_rate": 7.717573191854154e-05, "loss": 0.0229, "step": 138760 }, { "epoch": 33.32, "learning_rate": 7.717271876362143e-05, "loss": 0.0145, "step": 138770 }, { "epoch": 33.32, "learning_rate": 7.71697054686529e-05, "loss": 0.0136, "step": 138780 }, { "epoch": 33.32, "learning_rate": 7.716669203365149e-05, "loss": 0.0167, "step": 138790 }, { "epoch": 33.32, "learning_rate": 7.716367845863273e-05, "loss": 0.016, "step": 138800 }, { "epoch": 33.33, "learning_rate": 7.716066474361214e-05, "loss": 0.018, "step": 138810 }, { "epoch": 33.33, "learning_rate": 7.715765088860525e-05, "loss": 0.0124, "step": 138820 }, { "epoch": 33.33, "learning_rate": 7.715463689362759e-05, "loss": 0.0221, "step": 138830 }, { "epoch": 33.33, "learning_rate": 7.71516227586947e-05, "loss": 0.0252, "step": 138840 }, { "epoch": 33.34, "learning_rate": 7.714860848382215e-05, "loss": 0.0408, "step": 138850 }, { "epoch": 33.34, "learning_rate": 7.714559406902541e-05, "loss": 0.0206, "step": 138860 }, { "epoch": 33.34, "learning_rate": 7.714257951432009e-05, "loss": 0.0304, "step": 138870 }, { "epoch": 33.34, "learning_rate": 7.713956481972167e-05, "loss": 0.0174, "step": 138880 }, { "epoch": 33.35, "learning_rate": 7.713654998524572e-05, "loss": 0.0277, "step": 138890 }, { "epoch": 33.35, "learning_rate": 7.713353501090774e-05, "loss": 0.0206, "step": 138900 }, { "epoch": 33.35, "learning_rate": 7.713051989672329e-05, "loss": 0.0422, "step": 138910 }, { "epoch": 33.35, "learning_rate": 7.712750464270792e-05, "loss": 0.0197, "step": 138920 }, { "epoch": 33.35, "learning_rate": 7.712448924887717e-05, "loss": 0.024, "step": 138930 }, { "epoch": 33.36, "learning_rate": 7.712147371524659e-05, "loss": 0.0198, "step": 138940 }, { "epoch": 33.36, "learning_rate": 7.71184580418317e-05, "loss": 0.034, "step": 138950 }, { "epoch": 33.36, "learning_rate": 7.711544222864804e-05, "loss": 0.0258, "step": 138960 }, { "epoch": 33.36, "learning_rate": 7.711242627571116e-05, "loss": 0.0108, "step": 138970 }, { "epoch": 33.37, "learning_rate": 7.710941018303661e-05, "loss": 0.0234, "step": 138980 }, { "epoch": 33.37, "learning_rate": 7.710639395063995e-05, "loss": 0.0311, "step": 138990 }, { "epoch": 33.37, "learning_rate": 7.71033775785367e-05, "loss": 0.0209, "step": 139000 }, { "epoch": 33.37, "learning_rate": 7.710036106674241e-05, "loss": 0.0225, "step": 139010 }, { "epoch": 33.38, "learning_rate": 7.709734441527264e-05, "loss": 0.0285, "step": 139020 }, { "epoch": 33.38, "learning_rate": 7.709432762414292e-05, "loss": 0.0284, "step": 139030 }, { "epoch": 33.38, "learning_rate": 7.709131069336883e-05, "loss": 0.0232, "step": 139040 }, { "epoch": 33.38, "learning_rate": 7.708829362296588e-05, "loss": 0.0268, "step": 139050 }, { "epoch": 33.38, "learning_rate": 7.708527641294964e-05, "loss": 0.02, "step": 139060 }, { "epoch": 33.39, "learning_rate": 7.708225906333566e-05, "loss": 0.0193, "step": 139070 }, { "epoch": 33.39, "learning_rate": 7.707924157413949e-05, "loss": 0.0101, "step": 139080 }, { "epoch": 33.39, "learning_rate": 7.70762239453767e-05, "loss": 0.0165, "step": 139090 }, { "epoch": 33.39, "learning_rate": 7.707320617706281e-05, "loss": 0.0272, "step": 139100 }, { "epoch": 33.4, "learning_rate": 7.707018826921339e-05, "loss": 0.0216, "step": 139110 }, { "epoch": 33.4, "learning_rate": 7.706717022184398e-05, "loss": 0.0589, "step": 139120 }, { "epoch": 33.4, "learning_rate": 7.706415203497018e-05, "loss": 0.0186, "step": 139130 }, { "epoch": 33.4, "learning_rate": 7.706113370860749e-05, "loss": 0.0307, "step": 139140 }, { "epoch": 33.4, "learning_rate": 7.70581152427715e-05, "loss": 0.0169, "step": 139150 }, { "epoch": 33.41, "learning_rate": 7.705509663747774e-05, "loss": 0.051, "step": 139160 }, { "epoch": 33.41, "learning_rate": 7.70520778927418e-05, "loss": 0.0115, "step": 139170 }, { "epoch": 33.41, "learning_rate": 7.704905900857923e-05, "loss": 0.02, "step": 139180 }, { "epoch": 33.41, "learning_rate": 7.704603998500558e-05, "loss": 0.0138, "step": 139190 }, { "epoch": 33.42, "learning_rate": 7.704302082203641e-05, "loss": 0.0237, "step": 139200 }, { "epoch": 33.42, "learning_rate": 7.704000151968728e-05, "loss": 0.0232, "step": 139210 }, { "epoch": 33.42, "learning_rate": 7.703698207797377e-05, "loss": 0.0184, "step": 139220 }, { "epoch": 33.42, "learning_rate": 7.703396249691142e-05, "loss": 0.0228, "step": 139230 }, { "epoch": 33.43, "learning_rate": 7.70309427765158e-05, "loss": 0.02, "step": 139240 }, { "epoch": 33.43, "learning_rate": 7.702792291680248e-05, "loss": 0.0412, "step": 139250 }, { "epoch": 33.43, "learning_rate": 7.7024902917787e-05, "loss": 0.0122, "step": 139260 }, { "epoch": 33.43, "learning_rate": 7.702188277948498e-05, "loss": 0.0417, "step": 139270 }, { "epoch": 33.43, "learning_rate": 7.701886250191193e-05, "loss": 0.0191, "step": 139280 }, { "epoch": 33.44, "learning_rate": 7.701584208508343e-05, "loss": 0.0159, "step": 139290 }, { "epoch": 33.44, "learning_rate": 7.701282152901508e-05, "loss": 0.021, "step": 139300 }, { "epoch": 33.44, "learning_rate": 7.70098008337224e-05, "loss": 0.017, "step": 139310 }, { "epoch": 33.44, "learning_rate": 7.700677999922097e-05, "loss": 0.011, "step": 139320 }, { "epoch": 33.45, "learning_rate": 7.700375902552639e-05, "loss": 0.0292, "step": 139330 }, { "epoch": 33.45, "learning_rate": 7.700073791265421e-05, "loss": 0.0415, "step": 139340 }, { "epoch": 33.45, "learning_rate": 7.699771666061999e-05, "loss": 0.0222, "step": 139350 }, { "epoch": 33.45, "learning_rate": 7.699469526943933e-05, "loss": 0.0192, "step": 139360 }, { "epoch": 33.45, "learning_rate": 7.699167373912777e-05, "loss": 0.0258, "step": 139370 }, { "epoch": 33.46, "learning_rate": 7.698865206970092e-05, "loss": 0.0158, "step": 139380 }, { "epoch": 33.46, "learning_rate": 7.698563026117429e-05, "loss": 0.0218, "step": 139390 }, { "epoch": 33.46, "learning_rate": 7.698260831356352e-05, "loss": 0.0264, "step": 139400 }, { "epoch": 33.46, "learning_rate": 7.697958622688417e-05, "loss": 0.0183, "step": 139410 }, { "epoch": 33.47, "learning_rate": 7.697656400115179e-05, "loss": 0.0123, "step": 139420 }, { "epoch": 33.47, "learning_rate": 7.697354163638198e-05, "loss": 0.0231, "step": 139430 }, { "epoch": 33.47, "learning_rate": 7.697051913259033e-05, "loss": 0.0215, "step": 139440 }, { "epoch": 33.47, "learning_rate": 7.696749648979238e-05, "loss": 0.0234, "step": 139450 }, { "epoch": 33.48, "learning_rate": 7.696447370800372e-05, "loss": 0.021, "step": 139460 }, { "epoch": 33.48, "learning_rate": 7.696145078723996e-05, "loss": 0.0179, "step": 139470 }, { "epoch": 33.48, "learning_rate": 7.695842772751663e-05, "loss": 0.0245, "step": 139480 }, { "epoch": 33.48, "learning_rate": 7.695540452884935e-05, "loss": 0.0096, "step": 139490 }, { "epoch": 33.48, "learning_rate": 7.69523811912537e-05, "loss": 0.013, "step": 139500 }, { "epoch": 33.49, "learning_rate": 7.694935771474525e-05, "loss": 0.0133, "step": 139510 }, { "epoch": 33.49, "learning_rate": 7.694633409933958e-05, "loss": 0.019, "step": 139520 }, { "epoch": 33.49, "learning_rate": 7.694331034505228e-05, "loss": 0.0337, "step": 139530 }, { "epoch": 33.49, "learning_rate": 7.694028645189892e-05, "loss": 0.0181, "step": 139540 }, { "epoch": 33.5, "learning_rate": 7.693726241989511e-05, "loss": 0.0231, "step": 139550 }, { "epoch": 33.5, "learning_rate": 7.693423824905641e-05, "loss": 0.0183, "step": 139560 }, { "epoch": 33.5, "learning_rate": 7.693121393939844e-05, "loss": 0.0141, "step": 139570 }, { "epoch": 33.5, "learning_rate": 7.692818949093677e-05, "loss": 0.017, "step": 139580 }, { "epoch": 33.51, "learning_rate": 7.692516490368698e-05, "loss": 0.0211, "step": 139590 }, { "epoch": 33.51, "learning_rate": 7.692214017766466e-05, "loss": 0.0239, "step": 139600 }, { "epoch": 33.51, "learning_rate": 7.691911531288542e-05, "loss": 0.0252, "step": 139610 }, { "epoch": 33.51, "learning_rate": 7.691609030936482e-05, "loss": 0.0227, "step": 139620 }, { "epoch": 33.51, "learning_rate": 7.691306516711847e-05, "loss": 0.0166, "step": 139630 }, { "epoch": 33.52, "learning_rate": 7.691003988616194e-05, "loss": 0.0189, "step": 139640 }, { "epoch": 33.52, "learning_rate": 7.690701446651088e-05, "loss": 0.0123, "step": 139650 }, { "epoch": 33.52, "learning_rate": 7.690398890818081e-05, "loss": 0.0313, "step": 139660 }, { "epoch": 33.52, "learning_rate": 7.690096321118736e-05, "loss": 0.0366, "step": 139670 }, { "epoch": 33.53, "learning_rate": 7.689793737554614e-05, "loss": 0.0212, "step": 139680 }, { "epoch": 33.53, "learning_rate": 7.68949114012727e-05, "loss": 0.0239, "step": 139690 }, { "epoch": 33.53, "learning_rate": 7.689188528838267e-05, "loss": 0.0202, "step": 139700 }, { "epoch": 33.53, "learning_rate": 7.688885903689164e-05, "loss": 0.0192, "step": 139710 }, { "epoch": 33.53, "learning_rate": 7.68858326468152e-05, "loss": 0.0245, "step": 139720 }, { "epoch": 33.54, "learning_rate": 7.688280611816898e-05, "loss": 0.0322, "step": 139730 }, { "epoch": 33.54, "learning_rate": 7.687977945096852e-05, "loss": 0.0533, "step": 139740 }, { "epoch": 33.54, "learning_rate": 7.687675264522947e-05, "loss": 0.0223, "step": 139750 }, { "epoch": 33.54, "learning_rate": 7.68737257009674e-05, "loss": 0.0226, "step": 139760 }, { "epoch": 33.55, "learning_rate": 7.687069861819793e-05, "loss": 0.0291, "step": 139770 }, { "epoch": 33.55, "learning_rate": 7.686767139693667e-05, "loss": 0.0288, "step": 139780 }, { "epoch": 33.55, "learning_rate": 7.686464403719918e-05, "loss": 0.0227, "step": 139790 }, { "epoch": 33.55, "learning_rate": 7.686161653900111e-05, "loss": 0.0275, "step": 139800 }, { "epoch": 33.56, "learning_rate": 7.685858890235805e-05, "loss": 0.0201, "step": 139810 }, { "epoch": 33.56, "learning_rate": 7.685556112728558e-05, "loss": 0.0206, "step": 139820 }, { "epoch": 33.56, "learning_rate": 7.685253321379933e-05, "loss": 0.0265, "step": 139830 }, { "epoch": 33.56, "learning_rate": 7.68495051619149e-05, "loss": 0.029, "step": 139840 }, { "epoch": 33.56, "learning_rate": 7.684647697164789e-05, "loss": 0.0266, "step": 139850 }, { "epoch": 33.57, "learning_rate": 7.684344864301389e-05, "loss": 0.0406, "step": 139860 }, { "epoch": 33.57, "learning_rate": 7.684042017602858e-05, "loss": 0.0224, "step": 139870 }, { "epoch": 33.57, "learning_rate": 7.68373915707075e-05, "loss": 0.0265, "step": 139880 }, { "epoch": 33.57, "learning_rate": 7.683436282706627e-05, "loss": 0.0344, "step": 139890 }, { "epoch": 33.58, "learning_rate": 7.683133394512052e-05, "loss": 0.0185, "step": 139900 }, { "epoch": 33.58, "learning_rate": 7.682830492488584e-05, "loss": 0.0383, "step": 139910 }, { "epoch": 33.58, "learning_rate": 7.682527576637787e-05, "loss": 0.0225, "step": 139920 }, { "epoch": 33.58, "learning_rate": 7.68222464696122e-05, "loss": 0.0306, "step": 139930 }, { "epoch": 33.59, "learning_rate": 7.681921703460444e-05, "loss": 0.0203, "step": 139940 }, { "epoch": 33.59, "learning_rate": 7.681618746137022e-05, "loss": 0.0455, "step": 139950 }, { "epoch": 33.59, "learning_rate": 7.681315774992514e-05, "loss": 0.0352, "step": 139960 }, { "epoch": 33.59, "learning_rate": 7.681012790028481e-05, "loss": 0.0238, "step": 139970 }, { "epoch": 33.59, "learning_rate": 7.680709791246488e-05, "loss": 0.0411, "step": 139980 }, { "epoch": 33.6, "learning_rate": 7.680406778648093e-05, "loss": 0.0243, "step": 139990 }, { "epoch": 33.6, "learning_rate": 7.680103752234858e-05, "loss": 0.0325, "step": 140000 }, { "epoch": 33.6, "learning_rate": 7.679800712008347e-05, "loss": 0.0294, "step": 140010 }, { "epoch": 33.6, "learning_rate": 7.67949765797012e-05, "loss": 0.0172, "step": 140020 }, { "epoch": 33.61, "learning_rate": 7.679194590121741e-05, "loss": 0.0227, "step": 140030 }, { "epoch": 33.61, "learning_rate": 7.678891508464769e-05, "loss": 0.0239, "step": 140040 }, { "epoch": 33.61, "learning_rate": 7.67858841300077e-05, "loss": 0.0253, "step": 140050 }, { "epoch": 33.61, "learning_rate": 7.678285303731301e-05, "loss": 0.0243, "step": 140060 }, { "epoch": 33.61, "learning_rate": 7.67798218065793e-05, "loss": 0.0228, "step": 140070 }, { "epoch": 33.62, "learning_rate": 7.677679043782215e-05, "loss": 0.0233, "step": 140080 }, { "epoch": 33.62, "learning_rate": 7.67737589310572e-05, "loss": 0.0214, "step": 140090 }, { "epoch": 33.62, "learning_rate": 7.677072728630008e-05, "loss": 0.0236, "step": 140100 }, { "epoch": 33.62, "learning_rate": 7.67676955035664e-05, "loss": 0.0346, "step": 140110 }, { "epoch": 33.63, "learning_rate": 7.67646635828718e-05, "loss": 0.0286, "step": 140120 }, { "epoch": 33.63, "learning_rate": 7.67616315242319e-05, "loss": 0.0285, "step": 140130 }, { "epoch": 33.63, "learning_rate": 7.675859932766231e-05, "loss": 0.0202, "step": 140140 }, { "epoch": 33.63, "learning_rate": 7.675556699317869e-05, "loss": 0.0306, "step": 140150 }, { "epoch": 33.64, "learning_rate": 7.675253452079664e-05, "loss": 0.0137, "step": 140160 }, { "epoch": 33.64, "learning_rate": 7.674950191053183e-05, "loss": 0.025, "step": 140170 }, { "epoch": 33.64, "learning_rate": 7.674646916239985e-05, "loss": 0.0232, "step": 140180 }, { "epoch": 33.64, "learning_rate": 7.674343627641634e-05, "loss": 0.033, "step": 140190 }, { "epoch": 33.64, "learning_rate": 7.674040325259695e-05, "loss": 0.0239, "step": 140200 }, { "epoch": 33.65, "learning_rate": 7.673737009095728e-05, "loss": 0.0241, "step": 140210 }, { "epoch": 33.65, "learning_rate": 7.673433679151299e-05, "loss": 0.0357, "step": 140220 }, { "epoch": 33.65, "learning_rate": 7.67313033542797e-05, "loss": 0.0137, "step": 140230 }, { "epoch": 33.65, "learning_rate": 7.672826977927306e-05, "loss": 0.034, "step": 140240 }, { "epoch": 33.66, "learning_rate": 7.67252360665087e-05, "loss": 0.0311, "step": 140250 }, { "epoch": 33.66, "learning_rate": 7.672220221600223e-05, "loss": 0.0168, "step": 140260 }, { "epoch": 33.66, "learning_rate": 7.671916822776932e-05, "loss": 0.0213, "step": 140270 }, { "epoch": 33.66, "learning_rate": 7.671613410182558e-05, "loss": 0.0206, "step": 140280 }, { "epoch": 33.67, "learning_rate": 7.671309983818666e-05, "loss": 0.019, "step": 140290 }, { "epoch": 33.67, "learning_rate": 7.671006543686821e-05, "loss": 0.0263, "step": 140300 }, { "epoch": 33.67, "learning_rate": 7.670703089788586e-05, "loss": 0.024, "step": 140310 }, { "epoch": 33.67, "learning_rate": 7.670399622125524e-05, "loss": 0.0385, "step": 140320 }, { "epoch": 33.67, "learning_rate": 7.670096140699202e-05, "loss": 0.0291, "step": 140330 }, { "epoch": 33.68, "learning_rate": 7.66979264551118e-05, "loss": 0.0166, "step": 140340 }, { "epoch": 33.68, "learning_rate": 7.669489136563027e-05, "loss": 0.0216, "step": 140350 }, { "epoch": 33.68, "learning_rate": 7.669185613856303e-05, "loss": 0.0357, "step": 140360 }, { "epoch": 33.68, "learning_rate": 7.668882077392572e-05, "loss": 0.0161, "step": 140370 }, { "epoch": 33.69, "learning_rate": 7.668578527173405e-05, "loss": 0.0314, "step": 140380 }, { "epoch": 33.69, "learning_rate": 7.668274963200359e-05, "loss": 0.0337, "step": 140390 }, { "epoch": 33.69, "learning_rate": 7.667971385475001e-05, "loss": 0.0147, "step": 140400 }, { "epoch": 33.69, "learning_rate": 7.667667793998899e-05, "loss": 0.0174, "step": 140410 }, { "epoch": 33.69, "learning_rate": 7.667364188773611e-05, "loss": 0.0269, "step": 140420 }, { "epoch": 33.7, "learning_rate": 7.667060569800709e-05, "loss": 0.0164, "step": 140430 }, { "epoch": 33.7, "learning_rate": 7.666756937081753e-05, "loss": 0.0326, "step": 140440 }, { "epoch": 33.7, "learning_rate": 7.66645329061831e-05, "loss": 0.0414, "step": 140450 }, { "epoch": 33.7, "learning_rate": 7.666149630411943e-05, "loss": 0.0262, "step": 140460 }, { "epoch": 33.71, "learning_rate": 7.66584595646422e-05, "loss": 0.0257, "step": 140470 }, { "epoch": 33.71, "learning_rate": 7.665542268776705e-05, "loss": 0.022, "step": 140480 }, { "epoch": 33.71, "learning_rate": 7.665238567350962e-05, "loss": 0.0223, "step": 140490 }, { "epoch": 33.71, "learning_rate": 7.664934852188556e-05, "loss": 0.0277, "step": 140500 }, { "epoch": 33.72, "learning_rate": 7.664631123291055e-05, "loss": 0.0218, "step": 140510 }, { "epoch": 33.72, "learning_rate": 7.664327380660024e-05, "loss": 0.0403, "step": 140520 }, { "epoch": 33.72, "learning_rate": 7.664023624297027e-05, "loss": 0.0266, "step": 140530 }, { "epoch": 33.72, "learning_rate": 7.663719854203628e-05, "loss": 0.0271, "step": 140540 }, { "epoch": 33.72, "learning_rate": 7.663416070381397e-05, "loss": 0.0231, "step": 140550 }, { "epoch": 33.73, "learning_rate": 7.663112272831895e-05, "loss": 0.0233, "step": 140560 }, { "epoch": 33.73, "learning_rate": 7.662808461556693e-05, "loss": 0.02, "step": 140570 }, { "epoch": 33.73, "learning_rate": 7.662504636557351e-05, "loss": 0.0176, "step": 140580 }, { "epoch": 33.73, "learning_rate": 7.66220079783544e-05, "loss": 0.0227, "step": 140590 }, { "epoch": 33.74, "learning_rate": 7.661896945392522e-05, "loss": 0.0275, "step": 140600 }, { "epoch": 33.74, "learning_rate": 7.661593079230164e-05, "loss": 0.0147, "step": 140610 }, { "epoch": 33.74, "learning_rate": 7.661289199349936e-05, "loss": 0.0182, "step": 140620 }, { "epoch": 33.74, "learning_rate": 7.660985305753399e-05, "loss": 0.0199, "step": 140630 }, { "epoch": 33.75, "learning_rate": 7.660681398442124e-05, "loss": 0.0129, "step": 140640 }, { "epoch": 33.75, "learning_rate": 7.660377477417673e-05, "loss": 0.0291, "step": 140650 }, { "epoch": 33.75, "learning_rate": 7.660073542681614e-05, "loss": 0.0171, "step": 140660 }, { "epoch": 33.75, "learning_rate": 7.659769594235515e-05, "loss": 0.0164, "step": 140670 }, { "epoch": 33.75, "learning_rate": 7.65946563208094e-05, "loss": 0.0219, "step": 140680 }, { "epoch": 33.76, "learning_rate": 7.659161656219458e-05, "loss": 0.0139, "step": 140690 }, { "epoch": 33.76, "learning_rate": 7.658857666652633e-05, "loss": 0.0302, "step": 140700 }, { "epoch": 33.76, "learning_rate": 7.658553663382036e-05, "loss": 0.0213, "step": 140710 }, { "epoch": 33.76, "learning_rate": 7.658249646409228e-05, "loss": 0.0254, "step": 140720 }, { "epoch": 33.77, "learning_rate": 7.65794561573578e-05, "loss": 0.0325, "step": 140730 }, { "epoch": 33.77, "learning_rate": 7.65764157136326e-05, "loss": 0.0168, "step": 140740 }, { "epoch": 33.77, "learning_rate": 7.657337513293233e-05, "loss": 0.0268, "step": 140750 }, { "epoch": 33.77, "learning_rate": 7.657033441527263e-05, "loss": 0.015, "step": 140760 }, { "epoch": 33.77, "learning_rate": 7.656729356066922e-05, "loss": 0.0417, "step": 140770 }, { "epoch": 33.78, "learning_rate": 7.656425256913777e-05, "loss": 0.0216, "step": 140780 }, { "epoch": 33.78, "learning_rate": 7.656121144069393e-05, "loss": 0.0354, "step": 140790 }, { "epoch": 33.78, "learning_rate": 7.655817017535339e-05, "loss": 0.0152, "step": 140800 }, { "epoch": 33.78, "learning_rate": 7.655512877313182e-05, "loss": 0.0157, "step": 140810 }, { "epoch": 33.79, "learning_rate": 7.65520872340449e-05, "loss": 0.03, "step": 140820 }, { "epoch": 33.79, "learning_rate": 7.654904555810829e-05, "loss": 0.0232, "step": 140830 }, { "epoch": 33.79, "learning_rate": 7.654600374533767e-05, "loss": 0.025, "step": 140840 }, { "epoch": 33.79, "learning_rate": 7.654296179574873e-05, "loss": 0.026, "step": 140850 }, { "epoch": 33.8, "learning_rate": 7.653991970935715e-05, "loss": 0.0335, "step": 140860 }, { "epoch": 33.8, "learning_rate": 7.65368774861786e-05, "loss": 0.0164, "step": 140870 }, { "epoch": 33.8, "learning_rate": 7.653383512622877e-05, "loss": 0.0224, "step": 140880 }, { "epoch": 33.8, "learning_rate": 7.653079262952332e-05, "loss": 0.0209, "step": 140890 }, { "epoch": 33.8, "learning_rate": 7.652774999607793e-05, "loss": 0.0158, "step": 140900 }, { "epoch": 33.81, "learning_rate": 7.652470722590832e-05, "loss": 0.0141, "step": 140910 }, { "epoch": 33.81, "learning_rate": 7.652166431903013e-05, "loss": 0.0175, "step": 140920 }, { "epoch": 33.81, "learning_rate": 7.651862127545906e-05, "loss": 0.0087, "step": 140930 }, { "epoch": 33.81, "learning_rate": 7.65155780952108e-05, "loss": 0.0129, "step": 140940 }, { "epoch": 33.82, "learning_rate": 7.651253477830104e-05, "loss": 0.0255, "step": 140950 }, { "epoch": 33.82, "learning_rate": 7.650949132474545e-05, "loss": 0.0198, "step": 140960 }, { "epoch": 33.82, "learning_rate": 7.65064477345597e-05, "loss": 0.0299, "step": 140970 }, { "epoch": 33.82, "learning_rate": 7.650340400775952e-05, "loss": 0.0225, "step": 140980 }, { "epoch": 33.83, "learning_rate": 7.650036014436057e-05, "loss": 0.0267, "step": 140990 }, { "epoch": 33.83, "learning_rate": 7.649731614437854e-05, "loss": 0.0233, "step": 141000 }, { "epoch": 33.83, "learning_rate": 7.64942720078291e-05, "loss": 0.0283, "step": 141010 }, { "epoch": 33.83, "learning_rate": 7.649122773472799e-05, "loss": 0.0239, "step": 141020 }, { "epoch": 33.83, "learning_rate": 7.648818332509087e-05, "loss": 0.0294, "step": 141030 }, { "epoch": 33.84, "learning_rate": 7.648513877893342e-05, "loss": 0.0154, "step": 141040 }, { "epoch": 33.84, "learning_rate": 7.648209409627133e-05, "loss": 0.024, "step": 141050 }, { "epoch": 33.84, "learning_rate": 7.647904927712033e-05, "loss": 0.0156, "step": 141060 }, { "epoch": 33.84, "learning_rate": 7.647600432149607e-05, "loss": 0.0281, "step": 141070 }, { "epoch": 33.85, "learning_rate": 7.647295922941428e-05, "loss": 0.0121, "step": 141080 }, { "epoch": 33.85, "learning_rate": 7.646991400089063e-05, "loss": 0.0262, "step": 141090 }, { "epoch": 33.85, "learning_rate": 7.646686863594083e-05, "loss": 0.0479, "step": 141100 }, { "epoch": 33.85, "learning_rate": 7.646382313458056e-05, "loss": 0.0234, "step": 141110 }, { "epoch": 33.85, "learning_rate": 7.646077749682552e-05, "loss": 0.0188, "step": 141120 }, { "epoch": 33.86, "learning_rate": 7.645773172269142e-05, "loss": 0.0234, "step": 141130 }, { "epoch": 33.86, "learning_rate": 7.645468581219392e-05, "loss": 0.0108, "step": 141140 }, { "epoch": 33.86, "learning_rate": 7.645163976534879e-05, "loss": 0.0128, "step": 141150 }, { "epoch": 33.86, "learning_rate": 7.644859358217167e-05, "loss": 0.0342, "step": 141160 }, { "epoch": 33.87, "learning_rate": 7.644554726267828e-05, "loss": 0.0221, "step": 141170 }, { "epoch": 33.87, "learning_rate": 7.644250080688431e-05, "loss": 0.0202, "step": 141180 }, { "epoch": 33.87, "learning_rate": 7.643945421480549e-05, "loss": 0.0171, "step": 141190 }, { "epoch": 33.87, "learning_rate": 7.643640748645748e-05, "loss": 0.0186, "step": 141200 }, { "epoch": 33.88, "learning_rate": 7.6433360621856e-05, "loss": 0.0196, "step": 141210 }, { "epoch": 33.88, "learning_rate": 7.643031362101677e-05, "loss": 0.0158, "step": 141220 }, { "epoch": 33.88, "learning_rate": 7.642726648395549e-05, "loss": 0.0106, "step": 141230 }, { "epoch": 33.88, "learning_rate": 7.642421921068785e-05, "loss": 0.0244, "step": 141240 }, { "epoch": 33.88, "learning_rate": 7.642117180122957e-05, "loss": 0.0105, "step": 141250 }, { "epoch": 33.89, "learning_rate": 7.641812425559633e-05, "loss": 0.0289, "step": 141260 }, { "epoch": 33.89, "learning_rate": 7.641507657380389e-05, "loss": 0.0237, "step": 141270 }, { "epoch": 33.89, "learning_rate": 7.64120287558679e-05, "loss": 0.0233, "step": 141280 }, { "epoch": 33.89, "learning_rate": 7.64089808018041e-05, "loss": 0.0274, "step": 141290 }, { "epoch": 33.9, "learning_rate": 7.640593271162819e-05, "loss": 0.0226, "step": 141300 }, { "epoch": 33.9, "learning_rate": 7.640288448535589e-05, "loss": 0.0329, "step": 141310 }, { "epoch": 33.9, "learning_rate": 7.63998361230029e-05, "loss": 0.0195, "step": 141320 }, { "epoch": 33.9, "learning_rate": 7.639678762458492e-05, "loss": 0.015, "step": 141330 }, { "epoch": 33.91, "learning_rate": 7.639373899011769e-05, "loss": 0.0254, "step": 141340 }, { "epoch": 33.91, "learning_rate": 7.63906902196169e-05, "loss": 0.0221, "step": 141350 }, { "epoch": 33.91, "learning_rate": 7.638764131309827e-05, "loss": 0.0185, "step": 141360 }, { "epoch": 33.91, "learning_rate": 7.638459227057753e-05, "loss": 0.0216, "step": 141370 }, { "epoch": 33.91, "learning_rate": 7.638154309207037e-05, "loss": 0.0223, "step": 141380 }, { "epoch": 33.92, "learning_rate": 7.637849377759252e-05, "loss": 0.0168, "step": 141390 }, { "epoch": 33.92, "learning_rate": 7.637544432715969e-05, "loss": 0.0174, "step": 141400 }, { "epoch": 33.92, "learning_rate": 7.63723947407876e-05, "loss": 0.0321, "step": 141410 }, { "epoch": 33.92, "learning_rate": 7.636934501849197e-05, "loss": 0.0168, "step": 141420 }, { "epoch": 33.93, "learning_rate": 7.636629516028851e-05, "loss": 0.053, "step": 141430 }, { "epoch": 33.93, "learning_rate": 7.636324516619296e-05, "loss": 0.0135, "step": 141440 }, { "epoch": 33.93, "learning_rate": 7.6360195036221e-05, "loss": 0.0339, "step": 141450 }, { "epoch": 33.93, "learning_rate": 7.63571447703884e-05, "loss": 0.0215, "step": 141460 }, { "epoch": 33.93, "learning_rate": 7.635409436871084e-05, "loss": 0.0154, "step": 141470 }, { "epoch": 33.94, "learning_rate": 7.635104383120406e-05, "loss": 0.0198, "step": 141480 }, { "epoch": 33.94, "learning_rate": 7.634799315788378e-05, "loss": 0.0193, "step": 141490 }, { "epoch": 33.94, "learning_rate": 7.634494234876572e-05, "loss": 0.0202, "step": 141500 }, { "epoch": 33.94, "learning_rate": 7.63418914038656e-05, "loss": 0.0256, "step": 141510 }, { "epoch": 33.95, "learning_rate": 7.633884032319917e-05, "loss": 0.0157, "step": 141520 }, { "epoch": 33.95, "learning_rate": 7.633578910678212e-05, "loss": 0.0162, "step": 141530 }, { "epoch": 33.95, "learning_rate": 7.633273775463021e-05, "loss": 0.0181, "step": 141540 }, { "epoch": 34.0, "learning_rate": 7.632968626675914e-05, "loss": 0.023, "step": 141550 }, { "epoch": 34.0, "learning_rate": 7.632663464318463e-05, "loss": 0.0179, "step": 141560 }, { "epoch": 34.01, "learning_rate": 7.632358288392245e-05, "loss": 0.0176, "step": 141570 }, { "epoch": 34.01, "learning_rate": 7.632053098898831e-05, "loss": 0.0197, "step": 141580 }, { "epoch": 34.01, "learning_rate": 7.631747895839792e-05, "loss": 0.0183, "step": 141590 }, { "epoch": 34.01, "learning_rate": 7.631442679216703e-05, "loss": 0.021, "step": 141600 }, { "epoch": 34.02, "learning_rate": 7.631137449031134e-05, "loss": 0.0226, "step": 141610 }, { "epoch": 34.02, "learning_rate": 7.630832205284663e-05, "loss": 0.0251, "step": 141620 }, { "epoch": 34.02, "learning_rate": 7.63052694797886e-05, "loss": 0.0291, "step": 141630 }, { "epoch": 34.02, "learning_rate": 7.630221677115299e-05, "loss": 0.0232, "step": 141640 }, { "epoch": 34.02, "learning_rate": 7.629916392695553e-05, "loss": 0.0247, "step": 141650 }, { "epoch": 34.03, "learning_rate": 7.629611094721198e-05, "loss": 0.0166, "step": 141660 }, { "epoch": 34.03, "learning_rate": 7.629305783193803e-05, "loss": 0.0277, "step": 141670 }, { "epoch": 34.03, "learning_rate": 7.629000458114945e-05, "loss": 0.0279, "step": 141680 }, { "epoch": 34.03, "learning_rate": 7.628695119486198e-05, "loss": 0.0262, "step": 141690 }, { "epoch": 34.04, "learning_rate": 7.628389767309132e-05, "loss": 0.02, "step": 141700 }, { "epoch": 34.04, "learning_rate": 7.628084401585324e-05, "loss": 0.0129, "step": 141710 }, { "epoch": 34.04, "learning_rate": 7.627779022316348e-05, "loss": 0.0168, "step": 141720 }, { "epoch": 34.04, "learning_rate": 7.627473629503777e-05, "loss": 0.0222, "step": 141730 }, { "epoch": 34.05, "learning_rate": 7.627168223149184e-05, "loss": 0.0193, "step": 141740 }, { "epoch": 34.05, "learning_rate": 7.626862803254144e-05, "loss": 0.0154, "step": 141750 }, { "epoch": 34.05, "learning_rate": 7.626557369820231e-05, "loss": 0.0301, "step": 141760 }, { "epoch": 34.05, "learning_rate": 7.626251922849021e-05, "loss": 0.0113, "step": 141770 }, { "epoch": 34.05, "learning_rate": 7.625946462342084e-05, "loss": 0.0224, "step": 141780 }, { "epoch": 34.06, "learning_rate": 7.625640988300999e-05, "loss": 0.0275, "step": 141790 }, { "epoch": 34.06, "learning_rate": 7.625335500727338e-05, "loss": 0.0245, "step": 141800 }, { "epoch": 34.06, "learning_rate": 7.625029999622675e-05, "loss": 0.0218, "step": 141810 }, { "epoch": 34.06, "learning_rate": 7.624724484988585e-05, "loss": 0.0231, "step": 141820 }, { "epoch": 34.07, "learning_rate": 7.624418956826645e-05, "loss": 0.0413, "step": 141830 }, { "epoch": 34.07, "learning_rate": 7.624113415138427e-05, "loss": 0.0173, "step": 141840 }, { "epoch": 34.07, "learning_rate": 7.623807859925507e-05, "loss": 0.0128, "step": 141850 }, { "epoch": 34.07, "learning_rate": 7.62350229118946e-05, "loss": 0.0433, "step": 141860 }, { "epoch": 34.07, "learning_rate": 7.623196708931857e-05, "loss": 0.0238, "step": 141870 }, { "epoch": 34.08, "learning_rate": 7.622891113154279e-05, "loss": 0.0212, "step": 141880 }, { "epoch": 34.08, "learning_rate": 7.622585503858298e-05, "loss": 0.0179, "step": 141890 }, { "epoch": 34.08, "learning_rate": 7.622279881045489e-05, "loss": 0.0172, "step": 141900 }, { "epoch": 34.08, "learning_rate": 7.621974244717428e-05, "loss": 0.0225, "step": 141910 }, { "epoch": 34.09, "learning_rate": 7.621668594875689e-05, "loss": 0.014, "step": 141920 }, { "epoch": 34.09, "learning_rate": 7.621362931521849e-05, "loss": 0.0205, "step": 141930 }, { "epoch": 34.09, "learning_rate": 7.621057254657482e-05, "loss": 0.0229, "step": 141940 }, { "epoch": 34.09, "learning_rate": 7.620751564284163e-05, "loss": 0.012, "step": 141950 }, { "epoch": 34.1, "learning_rate": 7.620445860403472e-05, "loss": 0.0161, "step": 141960 }, { "epoch": 34.1, "learning_rate": 7.620140143016977e-05, "loss": 0.0274, "step": 141970 }, { "epoch": 34.1, "learning_rate": 7.61983441212626e-05, "loss": 0.0265, "step": 141980 }, { "epoch": 34.1, "learning_rate": 7.619528667732894e-05, "loss": 0.02, "step": 141990 }, { "epoch": 34.1, "learning_rate": 7.619222909838456e-05, "loss": 0.0193, "step": 142000 }, { "epoch": 34.11, "learning_rate": 7.61891713844452e-05, "loss": 0.0197, "step": 142010 }, { "epoch": 34.11, "learning_rate": 7.618611353552663e-05, "loss": 0.0183, "step": 142020 }, { "epoch": 34.11, "learning_rate": 7.618305555164464e-05, "loss": 0.0158, "step": 142030 }, { "epoch": 34.11, "learning_rate": 7.617999743281495e-05, "loss": 0.0127, "step": 142040 }, { "epoch": 34.12, "learning_rate": 7.61769391790533e-05, "loss": 0.0161, "step": 142050 }, { "epoch": 34.12, "learning_rate": 7.617388079037553e-05, "loss": 0.0276, "step": 142060 }, { "epoch": 34.12, "learning_rate": 7.617082226679735e-05, "loss": 0.0201, "step": 142070 }, { "epoch": 34.12, "learning_rate": 7.616776360833451e-05, "loss": 0.0131, "step": 142080 }, { "epoch": 34.13, "learning_rate": 7.616470481500281e-05, "loss": 0.034, "step": 142090 }, { "epoch": 34.13, "learning_rate": 7.616164588681802e-05, "loss": 0.0214, "step": 142100 }, { "epoch": 34.13, "learning_rate": 7.615858682379588e-05, "loss": 0.0167, "step": 142110 }, { "epoch": 34.13, "learning_rate": 7.615552762595214e-05, "loss": 0.024, "step": 142120 }, { "epoch": 34.13, "learning_rate": 7.615246829330263e-05, "loss": 0.0245, "step": 142130 }, { "epoch": 34.14, "learning_rate": 7.614940882586306e-05, "loss": 0.0281, "step": 142140 }, { "epoch": 34.14, "learning_rate": 7.614634922364922e-05, "loss": 0.0182, "step": 142150 }, { "epoch": 34.14, "learning_rate": 7.614328948667688e-05, "loss": 0.0212, "step": 142160 }, { "epoch": 34.14, "learning_rate": 7.614022961496181e-05, "loss": 0.0257, "step": 142170 }, { "epoch": 34.15, "learning_rate": 7.613716960851978e-05, "loss": 0.0249, "step": 142180 }, { "epoch": 34.15, "learning_rate": 7.613410946736654e-05, "loss": 0.0109, "step": 142190 }, { "epoch": 34.15, "learning_rate": 7.61310491915179e-05, "loss": 0.0248, "step": 142200 }, { "epoch": 34.15, "learning_rate": 7.61279887809896e-05, "loss": 0.0222, "step": 142210 }, { "epoch": 34.15, "learning_rate": 7.612492823579745e-05, "loss": 0.0103, "step": 142220 }, { "epoch": 34.16, "learning_rate": 7.612186755595718e-05, "loss": 0.0068, "step": 142230 }, { "epoch": 34.16, "learning_rate": 7.611880674148459e-05, "loss": 0.0274, "step": 142240 }, { "epoch": 34.16, "learning_rate": 7.611574579239548e-05, "loss": 0.0206, "step": 142250 }, { "epoch": 34.16, "learning_rate": 7.611268470870557e-05, "loss": 0.0272, "step": 142260 }, { "epoch": 34.17, "learning_rate": 7.610962349043064e-05, "loss": 0.0249, "step": 142270 }, { "epoch": 34.17, "learning_rate": 7.610656213758654e-05, "loss": 0.0191, "step": 142280 }, { "epoch": 34.17, "learning_rate": 7.610350065018898e-05, "loss": 0.0112, "step": 142290 }, { "epoch": 34.17, "learning_rate": 7.610043902825375e-05, "loss": 0.0194, "step": 142300 }, { "epoch": 34.18, "learning_rate": 7.609737727179665e-05, "loss": 0.014, "step": 142310 }, { "epoch": 34.18, "learning_rate": 7.609431538083348e-05, "loss": 0.011, "step": 142320 }, { "epoch": 34.18, "learning_rate": 7.609125335537994e-05, "loss": 0.0094, "step": 142330 }, { "epoch": 34.18, "learning_rate": 7.608819119545188e-05, "loss": 0.0389, "step": 142340 }, { "epoch": 34.18, "learning_rate": 7.608512890106507e-05, "loss": 0.0151, "step": 142350 }, { "epoch": 34.19, "learning_rate": 7.608206647223528e-05, "loss": 0.0191, "step": 142360 }, { "epoch": 34.19, "learning_rate": 7.607900390897831e-05, "loss": 0.0247, "step": 142370 }, { "epoch": 34.19, "learning_rate": 7.607594121130993e-05, "loss": 0.0212, "step": 142380 }, { "epoch": 34.19, "learning_rate": 7.607287837924594e-05, "loss": 0.0312, "step": 142390 }, { "epoch": 34.2, "learning_rate": 7.606981541280212e-05, "loss": 0.0174, "step": 142400 }, { "epoch": 34.2, "learning_rate": 7.606675231199422e-05, "loss": 0.0237, "step": 142410 }, { "epoch": 34.2, "learning_rate": 7.606368907683809e-05, "loss": 0.0274, "step": 142420 }, { "epoch": 34.2, "learning_rate": 7.606062570734947e-05, "loss": 0.0181, "step": 142430 }, { "epoch": 34.21, "learning_rate": 7.605756220354418e-05, "loss": 0.012, "step": 142440 }, { "epoch": 34.21, "learning_rate": 7.6054498565438e-05, "loss": 0.0232, "step": 142450 }, { "epoch": 34.21, "learning_rate": 7.605143479304672e-05, "loss": 0.0136, "step": 142460 }, { "epoch": 34.21, "learning_rate": 7.604837088638612e-05, "loss": 0.0099, "step": 142470 }, { "epoch": 34.21, "learning_rate": 7.6045306845472e-05, "loss": 0.0209, "step": 142480 }, { "epoch": 34.22, "learning_rate": 7.604224267032015e-05, "loss": 0.0149, "step": 142490 }, { "epoch": 34.22, "learning_rate": 7.603917836094635e-05, "loss": 0.0221, "step": 142500 }, { "epoch": 34.22, "learning_rate": 7.603611391736643e-05, "loss": 0.011, "step": 142510 }, { "epoch": 34.22, "learning_rate": 7.603304933959614e-05, "loss": 0.0231, "step": 142520 }, { "epoch": 34.23, "learning_rate": 7.602998462765132e-05, "loss": 0.0173, "step": 142530 }, { "epoch": 34.23, "learning_rate": 7.602691978154773e-05, "loss": 0.0206, "step": 142540 }, { "epoch": 34.23, "learning_rate": 7.602385480130118e-05, "loss": 0.0291, "step": 142550 }, { "epoch": 34.23, "learning_rate": 7.602078968692746e-05, "loss": 0.039, "step": 142560 }, { "epoch": 34.23, "learning_rate": 7.601772443844237e-05, "loss": 0.0132, "step": 142570 }, { "epoch": 34.24, "learning_rate": 7.601465905586172e-05, "loss": 0.0146, "step": 142580 }, { "epoch": 34.24, "learning_rate": 7.601159353920128e-05, "loss": 0.0249, "step": 142590 }, { "epoch": 34.24, "learning_rate": 7.600852788847688e-05, "loss": 0.026, "step": 142600 }, { "epoch": 34.24, "learning_rate": 7.600546210370433e-05, "loss": 0.0416, "step": 142610 }, { "epoch": 34.25, "learning_rate": 7.600239618489939e-05, "loss": 0.0225, "step": 142620 }, { "epoch": 34.25, "learning_rate": 7.59993301320779e-05, "loss": 0.0195, "step": 142630 }, { "epoch": 34.25, "learning_rate": 7.599626394525562e-05, "loss": 0.0292, "step": 142640 }, { "epoch": 34.25, "learning_rate": 7.599319762444838e-05, "loss": 0.0322, "step": 142650 }, { "epoch": 34.26, "learning_rate": 7.5990131169672e-05, "loss": 0.0134, "step": 142660 }, { "epoch": 34.26, "learning_rate": 7.598706458094227e-05, "loss": 0.0164, "step": 142670 }, { "epoch": 34.26, "learning_rate": 7.5983997858275e-05, "loss": 0.0159, "step": 142680 }, { "epoch": 34.26, "learning_rate": 7.598093100168596e-05, "loss": 0.0202, "step": 142690 }, { "epoch": 34.26, "learning_rate": 7.597786401119098e-05, "loss": 0.0139, "step": 142700 }, { "epoch": 34.27, "learning_rate": 7.597479688680589e-05, "loss": 0.013, "step": 142710 }, { "epoch": 34.27, "learning_rate": 7.597172962854649e-05, "loss": 0.0213, "step": 142720 }, { "epoch": 34.27, "learning_rate": 7.596866223642854e-05, "loss": 0.0168, "step": 142730 }, { "epoch": 34.27, "learning_rate": 7.596559471046792e-05, "loss": 0.0218, "step": 142740 }, { "epoch": 34.28, "learning_rate": 7.59625270506804e-05, "loss": 0.0172, "step": 142750 }, { "epoch": 34.28, "learning_rate": 7.59594592570818e-05, "loss": 0.0253, "step": 142760 }, { "epoch": 34.28, "learning_rate": 7.595639132968792e-05, "loss": 0.0212, "step": 142770 }, { "epoch": 34.28, "learning_rate": 7.59533232685146e-05, "loss": 0.012, "step": 142780 }, { "epoch": 34.29, "learning_rate": 7.595025507357762e-05, "loss": 0.0214, "step": 142790 }, { "epoch": 34.29, "learning_rate": 7.594718674489281e-05, "loss": 0.0209, "step": 142800 }, { "epoch": 34.29, "learning_rate": 7.594411828247598e-05, "loss": 0.0257, "step": 142810 }, { "epoch": 34.29, "learning_rate": 7.594104968634297e-05, "loss": 0.015, "step": 142820 }, { "epoch": 34.29, "learning_rate": 7.593798095650956e-05, "loss": 0.0251, "step": 142830 }, { "epoch": 34.3, "learning_rate": 7.593491209299157e-05, "loss": 0.0265, "step": 142840 }, { "epoch": 34.3, "learning_rate": 7.593184309580483e-05, "loss": 0.0207, "step": 142850 }, { "epoch": 34.3, "learning_rate": 7.592877396496516e-05, "loss": 0.0225, "step": 142860 }, { "epoch": 34.3, "learning_rate": 7.592570470048837e-05, "loss": 0.0195, "step": 142870 }, { "epoch": 34.31, "learning_rate": 7.592263530239028e-05, "loss": 0.0172, "step": 142880 }, { "epoch": 34.31, "learning_rate": 7.59195657706867e-05, "loss": 0.0206, "step": 142890 }, { "epoch": 34.31, "learning_rate": 7.591649610539348e-05, "loss": 0.0144, "step": 142900 }, { "epoch": 34.31, "learning_rate": 7.591342630652642e-05, "loss": 0.0143, "step": 142910 }, { "epoch": 34.31, "learning_rate": 7.591035637410133e-05, "loss": 0.0252, "step": 142920 }, { "epoch": 34.32, "learning_rate": 7.590728630813406e-05, "loss": 0.0234, "step": 142930 }, { "epoch": 34.32, "learning_rate": 7.590421610864042e-05, "loss": 0.0212, "step": 142940 }, { "epoch": 34.32, "learning_rate": 7.590114577563622e-05, "loss": 0.0249, "step": 142950 }, { "epoch": 34.32, "learning_rate": 7.589807530913731e-05, "loss": 0.0162, "step": 142960 }, { "epoch": 34.33, "learning_rate": 7.589500470915951e-05, "loss": 0.0169, "step": 142970 }, { "epoch": 34.33, "learning_rate": 7.589193397571863e-05, "loss": 0.0199, "step": 142980 }, { "epoch": 34.33, "learning_rate": 7.58888631088305e-05, "loss": 0.0185, "step": 142990 }, { "epoch": 34.33, "learning_rate": 7.588579210851097e-05, "loss": 0.0149, "step": 143000 }, { "epoch": 34.34, "learning_rate": 7.588272097477583e-05, "loss": 0.0309, "step": 143010 }, { "epoch": 34.34, "learning_rate": 7.587964970764094e-05, "loss": 0.0273, "step": 143020 }, { "epoch": 34.34, "learning_rate": 7.587657830712211e-05, "loss": 0.0144, "step": 143030 }, { "epoch": 34.34, "learning_rate": 7.587350677323519e-05, "loss": 0.0222, "step": 143040 }, { "epoch": 34.34, "learning_rate": 7.587043510599601e-05, "loss": 0.0194, "step": 143050 }, { "epoch": 34.35, "learning_rate": 7.586736330542037e-05, "loss": 0.0163, "step": 143060 }, { "epoch": 34.35, "learning_rate": 7.586429137152413e-05, "loss": 0.012, "step": 143070 }, { "epoch": 34.35, "learning_rate": 7.586121930432313e-05, "loss": 0.0191, "step": 143080 }, { "epoch": 34.35, "learning_rate": 7.585814710383316e-05, "loss": 0.0161, "step": 143090 }, { "epoch": 34.36, "learning_rate": 7.585507477007011e-05, "loss": 0.0167, "step": 143100 }, { "epoch": 34.36, "learning_rate": 7.585200230304979e-05, "loss": 0.0149, "step": 143110 }, { "epoch": 34.36, "learning_rate": 7.584892970278803e-05, "loss": 0.0244, "step": 143120 }, { "epoch": 34.36, "learning_rate": 7.584585696930066e-05, "loss": 0.0117, "step": 143130 }, { "epoch": 34.37, "learning_rate": 7.584278410260352e-05, "loss": 0.0169, "step": 143140 }, { "epoch": 34.37, "learning_rate": 7.583971110271247e-05, "loss": 0.0184, "step": 143150 }, { "epoch": 34.37, "learning_rate": 7.583663796964334e-05, "loss": 0.0205, "step": 143160 }, { "epoch": 34.37, "learning_rate": 7.583356470341194e-05, "loss": 0.0153, "step": 143170 }, { "epoch": 34.37, "learning_rate": 7.583049130403414e-05, "loss": 0.0197, "step": 143180 }, { "epoch": 34.38, "learning_rate": 7.582741777152578e-05, "loss": 0.0105, "step": 143190 }, { "epoch": 34.38, "learning_rate": 7.582434410590269e-05, "loss": 0.0176, "step": 143200 }, { "epoch": 34.38, "learning_rate": 7.582127030718071e-05, "loss": 0.0254, "step": 143210 }, { "epoch": 34.38, "learning_rate": 7.581819637537569e-05, "loss": 0.0222, "step": 143220 }, { "epoch": 34.39, "learning_rate": 7.581512231050347e-05, "loss": 0.0217, "step": 143230 }, { "epoch": 34.39, "learning_rate": 7.581204811257989e-05, "loss": 0.0252, "step": 143240 }, { "epoch": 34.39, "learning_rate": 7.580897378162081e-05, "loss": 0.0239, "step": 143250 }, { "epoch": 34.39, "learning_rate": 7.580589931764205e-05, "loss": 0.0125, "step": 143260 }, { "epoch": 34.39, "learning_rate": 7.580282472065947e-05, "loss": 0.0132, "step": 143270 }, { "epoch": 34.4, "learning_rate": 7.579974999068893e-05, "loss": 0.0289, "step": 143280 }, { "epoch": 34.4, "learning_rate": 7.579667512774625e-05, "loss": 0.0299, "step": 143290 }, { "epoch": 34.4, "learning_rate": 7.579360013184729e-05, "loss": 0.0258, "step": 143300 }, { "epoch": 34.4, "learning_rate": 7.57905250030079e-05, "loss": 0.0315, "step": 143310 }, { "epoch": 34.41, "learning_rate": 7.578744974124393e-05, "loss": 0.0245, "step": 143320 }, { "epoch": 34.41, "learning_rate": 7.578437434657124e-05, "loss": 0.0206, "step": 143330 }, { "epoch": 34.41, "learning_rate": 7.578129881900566e-05, "loss": 0.0206, "step": 143340 }, { "epoch": 34.41, "learning_rate": 7.577822315856304e-05, "loss": 0.0169, "step": 143350 }, { "epoch": 34.42, "learning_rate": 7.577514736525926e-05, "loss": 0.0185, "step": 143360 }, { "epoch": 34.42, "learning_rate": 7.577207143911014e-05, "loss": 0.0257, "step": 143370 }, { "epoch": 34.42, "learning_rate": 7.576899538013156e-05, "loss": 0.0234, "step": 143380 }, { "epoch": 34.42, "learning_rate": 7.576591918833935e-05, "loss": 0.0236, "step": 143390 }, { "epoch": 34.42, "learning_rate": 7.57628428637494e-05, "loss": 0.0166, "step": 143400 }, { "epoch": 34.43, "learning_rate": 7.575976640637752e-05, "loss": 0.0159, "step": 143410 }, { "epoch": 34.43, "learning_rate": 7.57566898162396e-05, "loss": 0.0213, "step": 143420 }, { "epoch": 34.43, "learning_rate": 7.575361309335147e-05, "loss": 0.0232, "step": 143430 }, { "epoch": 34.43, "learning_rate": 7.575053623772902e-05, "loss": 0.0151, "step": 143440 }, { "epoch": 34.44, "learning_rate": 7.574745924938809e-05, "loss": 0.0214, "step": 143450 }, { "epoch": 34.44, "learning_rate": 7.574438212834452e-05, "loss": 0.0123, "step": 143460 }, { "epoch": 34.44, "learning_rate": 7.574130487461422e-05, "loss": 0.0178, "step": 143470 }, { "epoch": 34.44, "learning_rate": 7.5738227488213e-05, "loss": 0.037, "step": 143480 }, { "epoch": 34.45, "learning_rate": 7.573514996915674e-05, "loss": 0.0149, "step": 143490 }, { "epoch": 34.45, "learning_rate": 7.57320723174613e-05, "loss": 0.0199, "step": 143500 }, { "epoch": 34.45, "learning_rate": 7.572899453314254e-05, "loss": 0.0266, "step": 143510 }, { "epoch": 34.45, "learning_rate": 7.572591661621636e-05, "loss": 0.0125, "step": 143520 }, { "epoch": 34.45, "learning_rate": 7.572283856669855e-05, "loss": 0.015, "step": 143530 }, { "epoch": 34.46, "learning_rate": 7.571976038460504e-05, "loss": 0.029, "step": 143540 }, { "epoch": 34.46, "learning_rate": 7.571668206995167e-05, "loss": 0.0228, "step": 143550 }, { "epoch": 34.46, "learning_rate": 7.57136036227543e-05, "loss": 0.0123, "step": 143560 }, { "epoch": 34.46, "learning_rate": 7.571052504302881e-05, "loss": 0.0091, "step": 143570 }, { "epoch": 34.47, "learning_rate": 7.570744633079104e-05, "loss": 0.0136, "step": 143580 }, { "epoch": 34.47, "learning_rate": 7.570436748605688e-05, "loss": 0.0188, "step": 143590 }, { "epoch": 34.47, "learning_rate": 7.570128850884221e-05, "loss": 0.0288, "step": 143600 }, { "epoch": 34.47, "learning_rate": 7.569820939916288e-05, "loss": 0.0223, "step": 143610 }, { "epoch": 34.47, "learning_rate": 7.569513015703475e-05, "loss": 0.0285, "step": 143620 }, { "epoch": 34.48, "learning_rate": 7.56920507824737e-05, "loss": 0.025, "step": 143630 }, { "epoch": 34.48, "learning_rate": 7.568897127549563e-05, "loss": 0.0137, "step": 143640 }, { "epoch": 34.48, "learning_rate": 7.568589163611639e-05, "loss": 0.0218, "step": 143650 }, { "epoch": 34.48, "learning_rate": 7.568281186435183e-05, "loss": 0.0372, "step": 143660 }, { "epoch": 34.49, "learning_rate": 7.567973196021785e-05, "loss": 0.0253, "step": 143670 }, { "epoch": 34.49, "learning_rate": 7.567665192373033e-05, "loss": 0.0185, "step": 143680 }, { "epoch": 34.49, "learning_rate": 7.56735717549051e-05, "loss": 0.037, "step": 143690 }, { "epoch": 34.49, "learning_rate": 7.567049145375809e-05, "loss": 0.0146, "step": 143700 }, { "epoch": 34.5, "learning_rate": 7.566741102030515e-05, "loss": 0.0132, "step": 143710 }, { "epoch": 34.5, "learning_rate": 7.566433045456216e-05, "loss": 0.0263, "step": 143720 }, { "epoch": 34.5, "learning_rate": 7.566124975654499e-05, "loss": 0.016, "step": 143730 }, { "epoch": 34.5, "learning_rate": 7.565816892626951e-05, "loss": 0.021, "step": 143740 }, { "epoch": 34.5, "learning_rate": 7.565508796375165e-05, "loss": 0.0266, "step": 143750 }, { "epoch": 34.51, "learning_rate": 7.565200686900723e-05, "loss": 0.0356, "step": 143760 }, { "epoch": 34.51, "learning_rate": 7.564892564205215e-05, "loss": 0.0195, "step": 143770 }, { "epoch": 34.51, "learning_rate": 7.56458442829023e-05, "loss": 0.015, "step": 143780 }, { "epoch": 34.51, "learning_rate": 7.564276279157354e-05, "loss": 0.0161, "step": 143790 }, { "epoch": 34.52, "learning_rate": 7.563968116808178e-05, "loss": 0.0226, "step": 143800 }, { "epoch": 34.52, "learning_rate": 7.563659941244288e-05, "loss": 0.0374, "step": 143810 }, { "epoch": 34.52, "learning_rate": 7.563351752467273e-05, "loss": 0.0282, "step": 143820 }, { "epoch": 34.52, "learning_rate": 7.563043550478724e-05, "loss": 0.0375, "step": 143830 }, { "epoch": 34.53, "learning_rate": 7.562735335280227e-05, "loss": 0.0234, "step": 143840 }, { "epoch": 34.53, "learning_rate": 7.562427106873368e-05, "loss": 0.0331, "step": 143850 }, { "epoch": 34.53, "learning_rate": 7.56211886525974e-05, "loss": 0.0273, "step": 143860 }, { "epoch": 34.53, "learning_rate": 7.56181061044093e-05, "loss": 0.024, "step": 143870 }, { "epoch": 34.53, "learning_rate": 7.561502342418525e-05, "loss": 0.0427, "step": 143880 }, { "epoch": 34.54, "learning_rate": 7.561194061194116e-05, "loss": 0.0293, "step": 143890 }, { "epoch": 34.54, "learning_rate": 7.560885766769294e-05, "loss": 0.0288, "step": 143900 }, { "epoch": 34.54, "learning_rate": 7.560577459145644e-05, "loss": 0.0383, "step": 143910 }, { "epoch": 34.54, "learning_rate": 7.560269138324755e-05, "loss": 0.0114, "step": 143920 }, { "epoch": 34.55, "learning_rate": 7.559960804308217e-05, "loss": 0.0217, "step": 143930 }, { "epoch": 34.55, "learning_rate": 7.559652457097622e-05, "loss": 0.0309, "step": 143940 }, { "epoch": 34.55, "learning_rate": 7.559344096694554e-05, "loss": 0.0287, "step": 143950 }, { "epoch": 34.55, "learning_rate": 7.559035723100607e-05, "loss": 0.0209, "step": 143960 }, { "epoch": 34.55, "learning_rate": 7.558727336317371e-05, "loss": 0.0301, "step": 143970 }, { "epoch": 34.56, "learning_rate": 7.55841893634643e-05, "loss": 0.0256, "step": 143980 }, { "epoch": 34.56, "learning_rate": 7.558110523189376e-05, "loss": 0.0191, "step": 143990 }, { "epoch": 34.56, "learning_rate": 7.557802096847799e-05, "loss": 0.0383, "step": 144000 }, { "epoch": 34.56, "learning_rate": 7.557493657323289e-05, "loss": 0.0369, "step": 144010 }, { "epoch": 34.57, "learning_rate": 7.557185204617436e-05, "loss": 0.0282, "step": 144020 }, { "epoch": 34.57, "learning_rate": 7.556876738731829e-05, "loss": 0.0285, "step": 144030 }, { "epoch": 34.57, "learning_rate": 7.556568259668058e-05, "loss": 0.0166, "step": 144040 }, { "epoch": 34.57, "learning_rate": 7.556259767427713e-05, "loss": 0.0314, "step": 144050 }, { "epoch": 34.58, "learning_rate": 7.555951262012383e-05, "loss": 0.0242, "step": 144060 }, { "epoch": 34.58, "learning_rate": 7.555642743423658e-05, "loss": 0.0228, "step": 144070 }, { "epoch": 34.58, "learning_rate": 7.55533421166313e-05, "loss": 0.0247, "step": 144080 }, { "epoch": 34.58, "learning_rate": 7.555025666732388e-05, "loss": 0.0217, "step": 144090 }, { "epoch": 34.58, "learning_rate": 7.554717108633023e-05, "loss": 0.0526, "step": 144100 }, { "epoch": 34.59, "learning_rate": 7.554408537366625e-05, "loss": 0.0211, "step": 144110 }, { "epoch": 34.59, "learning_rate": 7.554099952934782e-05, "loss": 0.0309, "step": 144120 }, { "epoch": 34.59, "learning_rate": 7.553791355339089e-05, "loss": 0.0314, "step": 144130 }, { "epoch": 34.59, "learning_rate": 7.55348274458113e-05, "loss": 0.0203, "step": 144140 }, { "epoch": 34.6, "learning_rate": 7.553174120662504e-05, "loss": 0.0207, "step": 144150 }, { "epoch": 34.6, "learning_rate": 7.552865483584794e-05, "loss": 0.0208, "step": 144160 }, { "epoch": 34.6, "learning_rate": 7.552556833349597e-05, "loss": 0.0206, "step": 144170 }, { "epoch": 34.6, "learning_rate": 7.5522481699585e-05, "loss": 0.0302, "step": 144180 }, { "epoch": 34.61, "learning_rate": 7.551939493413094e-05, "loss": 0.0335, "step": 144190 }, { "epoch": 34.61, "learning_rate": 7.55163080371497e-05, "loss": 0.0162, "step": 144200 }, { "epoch": 34.61, "learning_rate": 7.55132210086572e-05, "loss": 0.0203, "step": 144210 }, { "epoch": 34.61, "learning_rate": 7.551013384866934e-05, "loss": 0.0255, "step": 144220 }, { "epoch": 34.61, "learning_rate": 7.550704655720204e-05, "loss": 0.03, "step": 144230 }, { "epoch": 34.62, "learning_rate": 7.55039591342712e-05, "loss": 0.0277, "step": 144240 }, { "epoch": 34.62, "learning_rate": 7.550087157989275e-05, "loss": 0.0265, "step": 144250 }, { "epoch": 34.62, "learning_rate": 7.549778389408259e-05, "loss": 0.0256, "step": 144260 }, { "epoch": 34.62, "learning_rate": 7.549469607685667e-05, "loss": 0.0239, "step": 144270 }, { "epoch": 34.63, "learning_rate": 7.549160812823084e-05, "loss": 0.0194, "step": 144280 }, { "epoch": 34.63, "learning_rate": 7.548852004822105e-05, "loss": 0.0243, "step": 144290 }, { "epoch": 34.63, "learning_rate": 7.548543183684322e-05, "loss": 0.0136, "step": 144300 }, { "epoch": 34.63, "learning_rate": 7.548234349411327e-05, "loss": 0.0231, "step": 144310 }, { "epoch": 34.63, "learning_rate": 7.547925502004709e-05, "loss": 0.0201, "step": 144320 }, { "epoch": 34.64, "learning_rate": 7.547616641466064e-05, "loss": 0.0435, "step": 144330 }, { "epoch": 34.64, "learning_rate": 7.547307767796981e-05, "loss": 0.0195, "step": 144340 }, { "epoch": 34.64, "learning_rate": 7.546998880999052e-05, "loss": 0.0249, "step": 144350 }, { "epoch": 34.64, "learning_rate": 7.54668998107387e-05, "loss": 0.0167, "step": 144360 }, { "epoch": 34.65, "learning_rate": 7.546381068023024e-05, "loss": 0.0303, "step": 144370 }, { "epoch": 34.65, "learning_rate": 7.54607214184811e-05, "loss": 0.0265, "step": 144380 }, { "epoch": 34.65, "learning_rate": 7.54576320255072e-05, "loss": 0.0262, "step": 144390 }, { "epoch": 34.65, "learning_rate": 7.545454250132445e-05, "loss": 0.0242, "step": 144400 }, { "epoch": 34.66, "learning_rate": 7.545145284594876e-05, "loss": 0.0164, "step": 144410 }, { "epoch": 34.66, "learning_rate": 7.544836305939609e-05, "loss": 0.0251, "step": 144420 }, { "epoch": 34.66, "learning_rate": 7.544527314168232e-05, "loss": 0.0286, "step": 144430 }, { "epoch": 34.66, "learning_rate": 7.544218309282343e-05, "loss": 0.0151, "step": 144440 }, { "epoch": 34.66, "learning_rate": 7.543909291283528e-05, "loss": 0.0227, "step": 144450 }, { "epoch": 34.67, "learning_rate": 7.543600260173387e-05, "loss": 0.0278, "step": 144460 }, { "epoch": 34.67, "learning_rate": 7.543291215953507e-05, "loss": 0.0143, "step": 144470 }, { "epoch": 34.67, "learning_rate": 7.542982158625484e-05, "loss": 0.0184, "step": 144480 }, { "epoch": 34.67, "learning_rate": 7.542673088190908e-05, "loss": 0.0165, "step": 144490 }, { "epoch": 34.68, "learning_rate": 7.542364004651374e-05, "loss": 0.02, "step": 144500 }, { "epoch": 34.68, "learning_rate": 7.542054908008475e-05, "loss": 0.0182, "step": 144510 }, { "epoch": 34.68, "learning_rate": 7.541745798263805e-05, "loss": 0.0201, "step": 144520 }, { "epoch": 34.68, "learning_rate": 7.541436675418954e-05, "loss": 0.03, "step": 144530 }, { "epoch": 34.69, "learning_rate": 7.541127539475516e-05, "loss": 0.0154, "step": 144540 }, { "epoch": 34.69, "learning_rate": 7.540818390435089e-05, "loss": 0.0288, "step": 144550 }, { "epoch": 34.69, "learning_rate": 7.540509228299261e-05, "loss": 0.0316, "step": 144560 }, { "epoch": 34.69, "learning_rate": 7.540200053069626e-05, "loss": 0.0235, "step": 144570 }, { "epoch": 34.69, "learning_rate": 7.53989086474778e-05, "loss": 0.0166, "step": 144580 }, { "epoch": 34.7, "learning_rate": 7.539581663335315e-05, "loss": 0.0232, "step": 144590 }, { "epoch": 34.7, "learning_rate": 7.539272448833824e-05, "loss": 0.0265, "step": 144600 }, { "epoch": 34.7, "learning_rate": 7.538963221244904e-05, "loss": 0.017, "step": 144610 }, { "epoch": 34.7, "learning_rate": 7.538653980570147e-05, "loss": 0.0331, "step": 144620 }, { "epoch": 34.71, "learning_rate": 7.538344726811144e-05, "loss": 0.0172, "step": 144630 }, { "epoch": 34.71, "learning_rate": 7.53803545996949e-05, "loss": 0.037, "step": 144640 }, { "epoch": 34.71, "learning_rate": 7.537726180046781e-05, "loss": 0.0337, "step": 144650 }, { "epoch": 34.71, "learning_rate": 7.537416887044611e-05, "loss": 0.0124, "step": 144660 }, { "epoch": 34.71, "learning_rate": 7.537107580964572e-05, "loss": 0.028, "step": 144670 }, { "epoch": 34.72, "learning_rate": 7.53679826180826e-05, "loss": 0.0241, "step": 144680 }, { "epoch": 34.72, "learning_rate": 7.536488929577267e-05, "loss": 0.0225, "step": 144690 }, { "epoch": 34.72, "learning_rate": 7.536179584273191e-05, "loss": 0.019, "step": 144700 }, { "epoch": 34.72, "learning_rate": 7.535870225897624e-05, "loss": 0.0212, "step": 144710 }, { "epoch": 34.73, "learning_rate": 7.535560854452159e-05, "loss": 0.0206, "step": 144720 }, { "epoch": 34.73, "learning_rate": 7.535251469938394e-05, "loss": 0.015, "step": 144730 }, { "epoch": 34.73, "learning_rate": 7.53494207235792e-05, "loss": 0.0182, "step": 144740 }, { "epoch": 34.73, "learning_rate": 7.534632661712336e-05, "loss": 0.0322, "step": 144750 }, { "epoch": 34.74, "learning_rate": 7.534323238003232e-05, "loss": 0.0243, "step": 144760 }, { "epoch": 34.74, "learning_rate": 7.534013801232205e-05, "loss": 0.0183, "step": 144770 }, { "epoch": 34.74, "learning_rate": 7.53370435140085e-05, "loss": 0.0141, "step": 144780 }, { "epoch": 34.74, "learning_rate": 7.53339488851076e-05, "loss": 0.0155, "step": 144790 }, { "epoch": 34.74, "learning_rate": 7.533085412563534e-05, "loss": 0.0288, "step": 144800 }, { "epoch": 34.75, "learning_rate": 7.532775923560764e-05, "loss": 0.0241, "step": 144810 }, { "epoch": 34.75, "learning_rate": 7.532466421504046e-05, "loss": 0.017, "step": 144820 }, { "epoch": 34.75, "learning_rate": 7.532156906394974e-05, "loss": 0.0612, "step": 144830 }, { "epoch": 34.75, "learning_rate": 7.531847378235144e-05, "loss": 0.025, "step": 144840 }, { "epoch": 34.76, "learning_rate": 7.531537837026152e-05, "loss": 0.0197, "step": 144850 }, { "epoch": 34.76, "learning_rate": 7.531228282769593e-05, "loss": 0.0279, "step": 144860 }, { "epoch": 34.76, "learning_rate": 7.53091871546706e-05, "loss": 0.023, "step": 144870 }, { "epoch": 34.76, "learning_rate": 7.530609135120155e-05, "loss": 0.0184, "step": 144880 }, { "epoch": 34.77, "learning_rate": 7.530299541730466e-05, "loss": 0.0331, "step": 144890 }, { "epoch": 34.77, "learning_rate": 7.529989935299595e-05, "loss": 0.0257, "step": 144900 }, { "epoch": 34.77, "learning_rate": 7.529680315829133e-05, "loss": 0.0208, "step": 144910 }, { "epoch": 34.77, "learning_rate": 7.529370683320675e-05, "loss": 0.0192, "step": 144920 }, { "epoch": 34.77, "learning_rate": 7.529061037775823e-05, "loss": 0.0222, "step": 144930 }, { "epoch": 34.78, "learning_rate": 7.528751379196168e-05, "loss": 0.0213, "step": 144940 }, { "epoch": 34.78, "learning_rate": 7.528441707583306e-05, "loss": 0.0139, "step": 144950 }, { "epoch": 34.78, "learning_rate": 7.528132022938836e-05, "loss": 0.011, "step": 144960 }, { "epoch": 34.78, "learning_rate": 7.527822325264354e-05, "loss": 0.0229, "step": 144970 }, { "epoch": 34.79, "learning_rate": 7.527512614561452e-05, "loss": 0.0106, "step": 144980 }, { "epoch": 34.79, "learning_rate": 7.527202890831729e-05, "loss": 0.0165, "step": 144990 }, { "epoch": 34.79, "learning_rate": 7.526893154076782e-05, "loss": 0.0174, "step": 145000 }, { "epoch": 34.79, "learning_rate": 7.526583404298205e-05, "loss": 0.0294, "step": 145010 }, { "epoch": 34.79, "learning_rate": 7.526273641497598e-05, "loss": 0.0164, "step": 145020 }, { "epoch": 34.8, "learning_rate": 7.525963865676554e-05, "loss": 0.0303, "step": 145030 }, { "epoch": 34.8, "learning_rate": 7.525654076836672e-05, "loss": 0.0216, "step": 145040 }, { "epoch": 34.8, "learning_rate": 7.525344274979549e-05, "loss": 0.032, "step": 145050 }, { "epoch": 34.8, "learning_rate": 7.525034460106779e-05, "loss": 0.0201, "step": 145060 }, { "epoch": 34.81, "learning_rate": 7.52472463221996e-05, "loss": 0.0152, "step": 145070 }, { "epoch": 34.81, "learning_rate": 7.52441479132069e-05, "loss": 0.0156, "step": 145080 }, { "epoch": 34.81, "learning_rate": 7.524104937410564e-05, "loss": 0.012, "step": 145090 }, { "epoch": 34.81, "learning_rate": 7.52379507049118e-05, "loss": 0.0199, "step": 145100 }, { "epoch": 34.82, "learning_rate": 7.523485190564137e-05, "loss": 0.0112, "step": 145110 }, { "epoch": 34.82, "learning_rate": 7.523175297631029e-05, "loss": 0.0162, "step": 145120 }, { "epoch": 34.82, "learning_rate": 7.522865391693455e-05, "loss": 0.0297, "step": 145130 }, { "epoch": 34.82, "learning_rate": 7.52255547275301e-05, "loss": 0.0318, "step": 145140 }, { "epoch": 34.82, "learning_rate": 7.522245540811295e-05, "loss": 0.032, "step": 145150 }, { "epoch": 34.83, "learning_rate": 7.521935595869904e-05, "loss": 0.0127, "step": 145160 }, { "epoch": 34.83, "learning_rate": 7.521625637930436e-05, "loss": 0.0187, "step": 145170 }, { "epoch": 34.83, "learning_rate": 7.521315666994488e-05, "loss": 0.019, "step": 145180 }, { "epoch": 34.83, "learning_rate": 7.52100568306366e-05, "loss": 0.0165, "step": 145190 }, { "epoch": 34.84, "learning_rate": 7.520695686139547e-05, "loss": 0.0228, "step": 145200 }, { "epoch": 34.84, "learning_rate": 7.520385676223747e-05, "loss": 0.0404, "step": 145210 }, { "epoch": 34.84, "learning_rate": 7.520075653317858e-05, "loss": 0.0137, "step": 145220 }, { "epoch": 34.84, "learning_rate": 7.519765617423477e-05, "loss": 0.0239, "step": 145230 }, { "epoch": 34.85, "learning_rate": 7.519455568542205e-05, "loss": 0.0174, "step": 145240 }, { "epoch": 34.85, "learning_rate": 7.519145506675635e-05, "loss": 0.0207, "step": 145250 }, { "epoch": 34.85, "learning_rate": 7.518835431825372e-05, "loss": 0.0182, "step": 145260 }, { "epoch": 34.85, "learning_rate": 7.518525343993009e-05, "loss": 0.0178, "step": 145270 }, { "epoch": 34.85, "learning_rate": 7.518215243180142e-05, "loss": 0.0251, "step": 145280 }, { "epoch": 34.86, "learning_rate": 7.517905129388374e-05, "loss": 0.0192, "step": 145290 }, { "epoch": 34.86, "learning_rate": 7.517595002619303e-05, "loss": 0.0152, "step": 145300 }, { "epoch": 34.86, "learning_rate": 7.517284862874526e-05, "loss": 0.0167, "step": 145310 }, { "epoch": 34.86, "learning_rate": 7.516974710155643e-05, "loss": 0.0206, "step": 145320 }, { "epoch": 34.87, "learning_rate": 7.516664544464251e-05, "loss": 0.04, "step": 145330 }, { "epoch": 34.87, "learning_rate": 7.516354365801948e-05, "loss": 0.0221, "step": 145340 }, { "epoch": 34.87, "learning_rate": 7.516044174170333e-05, "loss": 0.0106, "step": 145350 }, { "epoch": 34.87, "learning_rate": 7.515733969571006e-05, "loss": 0.0236, "step": 145360 }, { "epoch": 34.87, "learning_rate": 7.515423752005565e-05, "loss": 0.033, "step": 145370 }, { "epoch": 34.88, "learning_rate": 7.515113521475608e-05, "loss": 0.0205, "step": 145380 }, { "epoch": 34.88, "learning_rate": 7.514803277982736e-05, "loss": 0.0179, "step": 145390 }, { "epoch": 34.88, "learning_rate": 7.514493021528548e-05, "loss": 0.016, "step": 145400 }, { "epoch": 34.88, "learning_rate": 7.51418275211464e-05, "loss": 0.0145, "step": 145410 }, { "epoch": 34.89, "learning_rate": 7.513872469742616e-05, "loss": 0.0171, "step": 145420 }, { "epoch": 34.89, "learning_rate": 7.513562174414069e-05, "loss": 0.0235, "step": 145430 }, { "epoch": 34.89, "learning_rate": 7.513251866130601e-05, "loss": 0.0194, "step": 145440 }, { "epoch": 34.89, "learning_rate": 7.512941544893814e-05, "loss": 0.0558, "step": 145450 }, { "epoch": 34.9, "learning_rate": 7.512631210705304e-05, "loss": 0.0174, "step": 145460 }, { "epoch": 34.9, "learning_rate": 7.512320863566673e-05, "loss": 0.0161, "step": 145470 }, { "epoch": 34.9, "learning_rate": 7.512010503479519e-05, "loss": 0.0208, "step": 145480 }, { "epoch": 34.9, "learning_rate": 7.511700130445442e-05, "loss": 0.0237, "step": 145490 }, { "epoch": 34.9, "learning_rate": 7.511389744466041e-05, "loss": 0.025, "step": 145500 }, { "epoch": 34.91, "learning_rate": 7.511079345542917e-05, "loss": 0.0166, "step": 145510 }, { "epoch": 34.91, "learning_rate": 7.510768933677668e-05, "loss": 0.0175, "step": 145520 }, { "epoch": 34.91, "learning_rate": 7.510458508871896e-05, "loss": 0.019, "step": 145530 }, { "epoch": 34.91, "learning_rate": 7.510148071127199e-05, "loss": 0.0192, "step": 145540 }, { "epoch": 34.92, "learning_rate": 7.509837620445179e-05, "loss": 0.0166, "step": 145550 }, { "epoch": 34.92, "learning_rate": 7.509527156827434e-05, "loss": 0.0265, "step": 145560 }, { "epoch": 34.92, "learning_rate": 7.509216680275565e-05, "loss": 0.0468, "step": 145570 }, { "epoch": 34.92, "learning_rate": 7.508906190791171e-05, "loss": 0.0174, "step": 145580 }, { "epoch": 34.93, "learning_rate": 7.508595688375857e-05, "loss": 0.0195, "step": 145590 }, { "epoch": 34.93, "learning_rate": 7.508285173031216e-05, "loss": 0.018, "step": 145600 }, { "epoch": 34.93, "learning_rate": 7.507974644758854e-05, "loss": 0.016, "step": 145610 }, { "epoch": 34.93, "learning_rate": 7.50766410356037e-05, "loss": 0.0187, "step": 145620 }, { "epoch": 34.93, "learning_rate": 7.507353549437363e-05, "loss": 0.0566, "step": 145630 }, { "epoch": 34.94, "learning_rate": 7.507042982391437e-05, "loss": 0.0163, "step": 145640 }, { "epoch": 34.94, "learning_rate": 7.50673240242419e-05, "loss": 0.0218, "step": 145650 }, { "epoch": 34.94, "learning_rate": 7.506421809537222e-05, "loss": 0.0248, "step": 145660 }, { "epoch": 34.94, "learning_rate": 7.506111203732136e-05, "loss": 0.0187, "step": 145670 }, { "epoch": 34.95, "learning_rate": 7.505800585010531e-05, "loss": 0.0241, "step": 145680 }, { "epoch": 34.95, "learning_rate": 7.50548995337401e-05, "loss": 0.0152, "step": 145690 }, { "epoch": 34.95, "learning_rate": 7.505179308824172e-05, "loss": 0.0262, "step": 145700 }, { "epoch": 35.0, "learning_rate": 7.50486865136262e-05, "loss": 0.017, "step": 145710 }, { "epoch": 35.0, "learning_rate": 7.504557980990953e-05, "loss": 0.0116, "step": 145720 }, { "epoch": 35.01, "learning_rate": 7.504247297710773e-05, "loss": 0.029, "step": 145730 }, { "epoch": 35.01, "learning_rate": 7.503936601523682e-05, "loss": 0.0155, "step": 145740 }, { "epoch": 35.01, "learning_rate": 7.503625892431281e-05, "loss": 0.0201, "step": 145750 }, { "epoch": 35.01, "learning_rate": 7.50331517043517e-05, "loss": 0.0172, "step": 145760 }, { "epoch": 35.01, "learning_rate": 7.503004435536953e-05, "loss": 0.0413, "step": 145770 }, { "epoch": 35.02, "learning_rate": 7.50269368773823e-05, "loss": 0.0211, "step": 145780 }, { "epoch": 35.02, "learning_rate": 7.502382927040604e-05, "loss": 0.0244, "step": 145790 }, { "epoch": 35.02, "learning_rate": 7.502072153445672e-05, "loss": 0.0136, "step": 145800 }, { "epoch": 35.02, "learning_rate": 7.501761366955043e-05, "loss": 0.0177, "step": 145810 }, { "epoch": 35.03, "learning_rate": 7.501450567570312e-05, "loss": 0.0191, "step": 145820 }, { "epoch": 35.03, "learning_rate": 7.501139755293085e-05, "loss": 0.0271, "step": 145830 }, { "epoch": 35.03, "learning_rate": 7.500828930124963e-05, "loss": 0.022, "step": 145840 }, { "epoch": 35.03, "learning_rate": 7.500518092067549e-05, "loss": 0.0227, "step": 145850 }, { "epoch": 35.04, "learning_rate": 7.500207241122442e-05, "loss": 0.0243, "step": 145860 }, { "epoch": 35.04, "learning_rate": 7.499896377291247e-05, "loss": 0.0159, "step": 145870 }, { "epoch": 35.04, "learning_rate": 7.499585500575564e-05, "loss": 0.018, "step": 145880 }, { "epoch": 35.04, "learning_rate": 7.499274610976998e-05, "loss": 0.0131, "step": 145890 }, { "epoch": 35.04, "learning_rate": 7.498963708497148e-05, "loss": 0.0156, "step": 145900 }, { "epoch": 35.05, "learning_rate": 7.498652793137619e-05, "loss": 0.0114, "step": 145910 }, { "epoch": 35.05, "learning_rate": 7.498341864900013e-05, "loss": 0.0193, "step": 145920 }, { "epoch": 35.05, "learning_rate": 7.498030923785932e-05, "loss": 0.0258, "step": 145930 }, { "epoch": 35.05, "learning_rate": 7.497719969796979e-05, "loss": 0.0308, "step": 145940 }, { "epoch": 35.06, "learning_rate": 7.497409002934756e-05, "loss": 0.0171, "step": 145950 }, { "epoch": 35.06, "learning_rate": 7.497098023200866e-05, "loss": 0.0241, "step": 145960 }, { "epoch": 35.06, "learning_rate": 7.496787030596913e-05, "loss": 0.0214, "step": 145970 }, { "epoch": 35.06, "learning_rate": 7.496476025124498e-05, "loss": 0.02, "step": 145980 }, { "epoch": 35.07, "learning_rate": 7.496165006785225e-05, "loss": 0.0147, "step": 145990 }, { "epoch": 35.07, "learning_rate": 7.495853975580695e-05, "loss": 0.0157, "step": 146000 }, { "epoch": 35.07, "learning_rate": 7.495542931512515e-05, "loss": 0.0333, "step": 146010 }, { "epoch": 35.07, "learning_rate": 7.495231874582285e-05, "loss": 0.0167, "step": 146020 }, { "epoch": 35.07, "learning_rate": 7.494920804791608e-05, "loss": 0.0204, "step": 146030 }, { "epoch": 35.08, "learning_rate": 7.494609722142089e-05, "loss": 0.02, "step": 146040 }, { "epoch": 35.08, "learning_rate": 7.494298626635332e-05, "loss": 0.0132, "step": 146050 }, { "epoch": 35.08, "learning_rate": 7.493987518272938e-05, "loss": 0.0172, "step": 146060 }, { "epoch": 35.08, "learning_rate": 7.49367639705651e-05, "loss": 0.0179, "step": 146070 }, { "epoch": 35.09, "learning_rate": 7.493365262987656e-05, "loss": 0.022, "step": 146080 }, { "epoch": 35.09, "learning_rate": 7.493054116067975e-05, "loss": 0.0213, "step": 146090 }, { "epoch": 35.09, "learning_rate": 7.492742956299071e-05, "loss": 0.0286, "step": 146100 }, { "epoch": 35.09, "learning_rate": 7.492431783682549e-05, "loss": 0.0137, "step": 146110 }, { "epoch": 35.09, "learning_rate": 7.492120598220017e-05, "loss": 0.0319, "step": 146120 }, { "epoch": 35.1, "learning_rate": 7.491809399913071e-05, "loss": 0.0191, "step": 146130 }, { "epoch": 35.1, "learning_rate": 7.491498188763319e-05, "loss": 0.0209, "step": 146140 }, { "epoch": 35.1, "learning_rate": 7.491186964772364e-05, "loss": 0.0209, "step": 146150 }, { "epoch": 35.1, "learning_rate": 7.490875727941812e-05, "loss": 0.0135, "step": 146160 }, { "epoch": 35.11, "learning_rate": 7.490564478273265e-05, "loss": 0.0353, "step": 146170 }, { "epoch": 35.11, "learning_rate": 7.490253215768327e-05, "loss": 0.0286, "step": 146180 }, { "epoch": 35.11, "learning_rate": 7.489941940428604e-05, "loss": 0.015, "step": 146190 }, { "epoch": 35.11, "learning_rate": 7.489630652255699e-05, "loss": 0.0282, "step": 146200 }, { "epoch": 35.12, "learning_rate": 7.489319351251217e-05, "loss": 0.0201, "step": 146210 }, { "epoch": 35.12, "learning_rate": 7.489008037416763e-05, "loss": 0.0193, "step": 146220 }, { "epoch": 35.12, "learning_rate": 7.48869671075394e-05, "loss": 0.0154, "step": 146230 }, { "epoch": 35.12, "learning_rate": 7.488385371264353e-05, "loss": 0.0288, "step": 146240 }, { "epoch": 35.12, "learning_rate": 7.488074018949607e-05, "loss": 0.0116, "step": 146250 }, { "epoch": 35.13, "learning_rate": 7.487762653811308e-05, "loss": 0.0177, "step": 146260 }, { "epoch": 35.13, "learning_rate": 7.487451275851058e-05, "loss": 0.0338, "step": 146270 }, { "epoch": 35.13, "learning_rate": 7.487139885070464e-05, "loss": 0.0151, "step": 146280 }, { "epoch": 35.13, "learning_rate": 7.486828481471131e-05, "loss": 0.0347, "step": 146290 }, { "epoch": 35.14, "learning_rate": 7.486517065054663e-05, "loss": 0.0194, "step": 146300 }, { "epoch": 35.14, "learning_rate": 7.486205635822664e-05, "loss": 0.0161, "step": 146310 }, { "epoch": 35.14, "learning_rate": 7.485894193776742e-05, "loss": 0.021, "step": 146320 }, { "epoch": 35.14, "learning_rate": 7.485582738918498e-05, "loss": 0.0155, "step": 146330 }, { "epoch": 35.15, "learning_rate": 7.48527127124954e-05, "loss": 0.0102, "step": 146340 }, { "epoch": 35.15, "learning_rate": 7.484959790771477e-05, "loss": 0.0156, "step": 146350 }, { "epoch": 35.15, "learning_rate": 7.484648297485906e-05, "loss": 0.0122, "step": 146360 }, { "epoch": 35.15, "learning_rate": 7.48433679139444e-05, "loss": 0.0351, "step": 146370 }, { "epoch": 35.15, "learning_rate": 7.484025272498681e-05, "loss": 0.0209, "step": 146380 }, { "epoch": 35.16, "learning_rate": 7.483713740800234e-05, "loss": 0.0181, "step": 146390 }, { "epoch": 35.16, "learning_rate": 7.483402196300705e-05, "loss": 0.0136, "step": 146400 }, { "epoch": 35.16, "learning_rate": 7.483090639001702e-05, "loss": 0.0205, "step": 146410 }, { "epoch": 35.16, "learning_rate": 7.482779068904829e-05, "loss": 0.0147, "step": 146420 }, { "epoch": 35.17, "learning_rate": 7.48246748601169e-05, "loss": 0.019, "step": 146430 }, { "epoch": 35.17, "learning_rate": 7.482155890323894e-05, "loss": 0.0127, "step": 146440 }, { "epoch": 35.17, "learning_rate": 7.481844281843047e-05, "loss": 0.0364, "step": 146450 }, { "epoch": 35.17, "learning_rate": 7.481532660570752e-05, "loss": 0.0126, "step": 146460 }, { "epoch": 35.17, "learning_rate": 7.481221026508617e-05, "loss": 0.0261, "step": 146470 }, { "epoch": 35.18, "learning_rate": 7.48090937965825e-05, "loss": 0.015, "step": 146480 }, { "epoch": 35.18, "learning_rate": 7.480597720021253e-05, "loss": 0.013, "step": 146490 }, { "epoch": 35.18, "learning_rate": 7.480286047599236e-05, "loss": 0.0268, "step": 146500 }, { "epoch": 35.18, "learning_rate": 7.479974362393803e-05, "loss": 0.0275, "step": 146510 }, { "epoch": 35.19, "learning_rate": 7.479662664406561e-05, "loss": 0.0161, "step": 146520 }, { "epoch": 35.19, "learning_rate": 7.479350953639119e-05, "loss": 0.0332, "step": 146530 }, { "epoch": 35.19, "learning_rate": 7.47903923009308e-05, "loss": 0.0293, "step": 146540 }, { "epoch": 35.19, "learning_rate": 7.478727493770054e-05, "loss": 0.0238, "step": 146550 }, { "epoch": 35.2, "learning_rate": 7.478415744671644e-05, "loss": 0.0171, "step": 146560 }, { "epoch": 35.2, "learning_rate": 7.478103982799458e-05, "loss": 0.0183, "step": 146570 }, { "epoch": 35.2, "learning_rate": 7.477792208155104e-05, "loss": 0.0231, "step": 146580 }, { "epoch": 35.2, "learning_rate": 7.477480420740188e-05, "loss": 0.0443, "step": 146590 }, { "epoch": 35.2, "learning_rate": 7.477168620556319e-05, "loss": 0.0212, "step": 146600 }, { "epoch": 35.21, "learning_rate": 7.4768568076051e-05, "loss": 0.0258, "step": 146610 }, { "epoch": 35.21, "learning_rate": 7.476544981888141e-05, "loss": 0.0238, "step": 146620 }, { "epoch": 35.21, "learning_rate": 7.47623314340705e-05, "loss": 0.0136, "step": 146630 }, { "epoch": 35.21, "learning_rate": 7.47592129216343e-05, "loss": 0.0106, "step": 146640 }, { "epoch": 35.22, "learning_rate": 7.475609428158891e-05, "loss": 0.0153, "step": 146650 }, { "epoch": 35.22, "learning_rate": 7.475297551395041e-05, "loss": 0.0195, "step": 146660 }, { "epoch": 35.22, "learning_rate": 7.474985661873489e-05, "loss": 0.0128, "step": 146670 }, { "epoch": 35.22, "learning_rate": 7.474673759595838e-05, "loss": 0.0173, "step": 146680 }, { "epoch": 35.23, "learning_rate": 7.474361844563697e-05, "loss": 0.0209, "step": 146690 }, { "epoch": 35.23, "learning_rate": 7.474049916778678e-05, "loss": 0.0196, "step": 146700 }, { "epoch": 35.23, "learning_rate": 7.473737976242382e-05, "loss": 0.0307, "step": 146710 }, { "epoch": 35.23, "learning_rate": 7.47342602295642e-05, "loss": 0.0192, "step": 146720 }, { "epoch": 35.23, "learning_rate": 7.473114056922401e-05, "loss": 0.0151, "step": 146730 }, { "epoch": 35.24, "learning_rate": 7.472802078141929e-05, "loss": 0.0136, "step": 146740 }, { "epoch": 35.24, "learning_rate": 7.472490086616617e-05, "loss": 0.0106, "step": 146750 }, { "epoch": 35.24, "learning_rate": 7.47217808234807e-05, "loss": 0.0234, "step": 146760 }, { "epoch": 35.24, "learning_rate": 7.471866065337895e-05, "loss": 0.0255, "step": 146770 }, { "epoch": 35.25, "learning_rate": 7.471554035587703e-05, "loss": 0.0169, "step": 146780 }, { "epoch": 35.25, "learning_rate": 7.471241993099101e-05, "loss": 0.0149, "step": 146790 }, { "epoch": 35.25, "learning_rate": 7.470929937873695e-05, "loss": 0.0092, "step": 146800 }, { "epoch": 35.25, "learning_rate": 7.470617869913097e-05, "loss": 0.0207, "step": 146810 }, { "epoch": 35.25, "learning_rate": 7.470305789218915e-05, "loss": 0.0201, "step": 146820 }, { "epoch": 35.26, "learning_rate": 7.469993695792754e-05, "loss": 0.0216, "step": 146830 }, { "epoch": 35.26, "learning_rate": 7.469681589636226e-05, "loss": 0.0203, "step": 146840 }, { "epoch": 35.26, "learning_rate": 7.469369470750939e-05, "loss": 0.0119, "step": 146850 }, { "epoch": 35.26, "learning_rate": 7.4690573391385e-05, "loss": 0.0328, "step": 146860 }, { "epoch": 35.27, "learning_rate": 7.46874519480052e-05, "loss": 0.0249, "step": 146870 }, { "epoch": 35.27, "learning_rate": 7.468433037738606e-05, "loss": 0.0195, "step": 146880 }, { "epoch": 35.27, "learning_rate": 7.468120867954367e-05, "loss": 0.0251, "step": 146890 }, { "epoch": 35.27, "learning_rate": 7.467808685449413e-05, "loss": 0.0286, "step": 146900 }, { "epoch": 35.28, "learning_rate": 7.467496490225353e-05, "loss": 0.0239, "step": 146910 }, { "epoch": 35.28, "learning_rate": 7.467184282283795e-05, "loss": 0.0115, "step": 146920 }, { "epoch": 35.28, "learning_rate": 7.466872061626348e-05, "loss": 0.0181, "step": 146930 }, { "epoch": 35.28, "learning_rate": 7.466559828254622e-05, "loss": 0.019, "step": 146940 }, { "epoch": 35.28, "learning_rate": 7.466247582170225e-05, "loss": 0.0095, "step": 146950 }, { "epoch": 35.29, "learning_rate": 7.465935323374769e-05, "loss": 0.0202, "step": 146960 }, { "epoch": 35.29, "learning_rate": 7.46562305186986e-05, "loss": 0.0261, "step": 146970 }, { "epoch": 35.29, "learning_rate": 7.465310767657112e-05, "loss": 0.0155, "step": 146980 }, { "epoch": 35.29, "learning_rate": 7.464998470738129e-05, "loss": 0.0197, "step": 146990 }, { "epoch": 35.3, "learning_rate": 7.464686161114524e-05, "loss": 0.0155, "step": 147000 }, { "epoch": 35.3, "learning_rate": 7.464373838787908e-05, "loss": 0.0196, "step": 147010 }, { "epoch": 35.3, "learning_rate": 7.464061503759886e-05, "loss": 0.0172, "step": 147020 }, { "epoch": 35.3, "learning_rate": 7.463749156032071e-05, "loss": 0.0107, "step": 147030 }, { "epoch": 35.31, "learning_rate": 7.463436795606073e-05, "loss": 0.0251, "step": 147040 }, { "epoch": 35.31, "learning_rate": 7.4631244224835e-05, "loss": 0.0161, "step": 147050 }, { "epoch": 35.31, "learning_rate": 7.462812036665965e-05, "loss": 0.0102, "step": 147060 }, { "epoch": 35.31, "learning_rate": 7.462499638155075e-05, "loss": 0.0297, "step": 147070 }, { "epoch": 35.31, "learning_rate": 7.462187226952442e-05, "loss": 0.0116, "step": 147080 }, { "epoch": 35.32, "learning_rate": 7.461874803059674e-05, "loss": 0.0152, "step": 147090 }, { "epoch": 35.32, "learning_rate": 7.461562366478383e-05, "loss": 0.0214, "step": 147100 }, { "epoch": 35.32, "learning_rate": 7.46124991721018e-05, "loss": 0.0201, "step": 147110 }, { "epoch": 35.32, "learning_rate": 7.460937455256673e-05, "loss": 0.0167, "step": 147120 }, { "epoch": 35.33, "learning_rate": 7.460624980619476e-05, "loss": 0.0124, "step": 147130 }, { "epoch": 35.33, "learning_rate": 7.460312493300195e-05, "loss": 0.015, "step": 147140 }, { "epoch": 35.33, "learning_rate": 7.459999993300443e-05, "loss": 0.015, "step": 147150 }, { "epoch": 35.33, "learning_rate": 7.459687480621831e-05, "loss": 0.0098, "step": 147160 }, { "epoch": 35.33, "learning_rate": 7.45937495526597e-05, "loss": 0.0195, "step": 147170 }, { "epoch": 35.34, "learning_rate": 7.459062417234469e-05, "loss": 0.0171, "step": 147180 }, { "epoch": 35.34, "learning_rate": 7.45874986652894e-05, "loss": 0.0123, "step": 147190 }, { "epoch": 35.34, "learning_rate": 7.458437303150994e-05, "loss": 0.0116, "step": 147200 }, { "epoch": 35.34, "learning_rate": 7.458124727102242e-05, "loss": 0.0074, "step": 147210 }, { "epoch": 35.35, "learning_rate": 7.457812138384294e-05, "loss": 0.0249, "step": 147220 }, { "epoch": 35.35, "learning_rate": 7.457499536998761e-05, "loss": 0.0158, "step": 147230 }, { "epoch": 35.35, "learning_rate": 7.457186922947254e-05, "loss": 0.0154, "step": 147240 }, { "epoch": 35.35, "learning_rate": 7.456874296231387e-05, "loss": 0.0306, "step": 147250 }, { "epoch": 35.36, "learning_rate": 7.45656165685277e-05, "loss": 0.0111, "step": 147260 }, { "epoch": 35.36, "learning_rate": 7.456249004813012e-05, "loss": 0.0331, "step": 147270 }, { "epoch": 35.36, "learning_rate": 7.455936340113726e-05, "loss": 0.0189, "step": 147280 }, { "epoch": 35.36, "learning_rate": 7.455623662756525e-05, "loss": 0.0168, "step": 147290 }, { "epoch": 35.36, "learning_rate": 7.455310972743017e-05, "loss": 0.0218, "step": 147300 }, { "epoch": 35.37, "learning_rate": 7.454998270074818e-05, "loss": 0.0102, "step": 147310 }, { "epoch": 35.37, "learning_rate": 7.454685554753535e-05, "loss": 0.025, "step": 147320 }, { "epoch": 35.37, "learning_rate": 7.454372826780784e-05, "loss": 0.0187, "step": 147330 }, { "epoch": 35.37, "learning_rate": 7.454060086158175e-05, "loss": 0.016, "step": 147340 }, { "epoch": 35.38, "learning_rate": 7.45374733288732e-05, "loss": 0.0123, "step": 147350 }, { "epoch": 35.38, "learning_rate": 7.45343456696983e-05, "loss": 0.0179, "step": 147360 }, { "epoch": 35.38, "learning_rate": 7.453121788407318e-05, "loss": 0.0167, "step": 147370 }, { "epoch": 35.38, "learning_rate": 7.452808997201394e-05, "loss": 0.022, "step": 147380 }, { "epoch": 35.39, "learning_rate": 7.452496193353674e-05, "loss": 0.015, "step": 147390 }, { "epoch": 35.39, "learning_rate": 7.452183376865767e-05, "loss": 0.0166, "step": 147400 }, { "epoch": 35.39, "learning_rate": 7.451870547739287e-05, "loss": 0.0096, "step": 147410 }, { "epoch": 35.39, "learning_rate": 7.451557705975847e-05, "loss": 0.0104, "step": 147420 }, { "epoch": 35.39, "learning_rate": 7.451244851577057e-05, "loss": 0.018, "step": 147430 }, { "epoch": 35.4, "learning_rate": 7.45093198454453e-05, "loss": 0.0153, "step": 147440 }, { "epoch": 35.4, "learning_rate": 7.450619104879879e-05, "loss": 0.0196, "step": 147450 }, { "epoch": 35.4, "learning_rate": 7.450306212584717e-05, "loss": 0.022, "step": 147460 }, { "epoch": 35.4, "learning_rate": 7.449993307660656e-05, "loss": 0.0127, "step": 147470 }, { "epoch": 35.41, "learning_rate": 7.449680390109309e-05, "loss": 0.0112, "step": 147480 }, { "epoch": 35.41, "learning_rate": 7.44936745993229e-05, "loss": 0.0274, "step": 147490 }, { "epoch": 35.41, "learning_rate": 7.449054517131209e-05, "loss": 0.0414, "step": 147500 }, { "epoch": 35.41, "learning_rate": 7.448741561707681e-05, "loss": 0.0099, "step": 147510 }, { "epoch": 35.41, "learning_rate": 7.448428593663319e-05, "loss": 0.0281, "step": 147520 }, { "epoch": 35.42, "learning_rate": 7.448115612999737e-05, "loss": 0.0161, "step": 147530 }, { "epoch": 35.42, "learning_rate": 7.447802619718544e-05, "loss": 0.0144, "step": 147540 }, { "epoch": 35.42, "learning_rate": 7.447489613821357e-05, "loss": 0.0357, "step": 147550 }, { "epoch": 35.42, "learning_rate": 7.447176595309789e-05, "loss": 0.0131, "step": 147560 }, { "epoch": 35.43, "learning_rate": 7.44686356418545e-05, "loss": 0.0161, "step": 147570 }, { "epoch": 35.43, "learning_rate": 7.446550520449957e-05, "loss": 0.0255, "step": 147580 }, { "epoch": 35.43, "learning_rate": 7.446237464104923e-05, "loss": 0.0098, "step": 147590 }, { "epoch": 35.43, "learning_rate": 7.44592439515196e-05, "loss": 0.0173, "step": 147600 }, { "epoch": 35.44, "learning_rate": 7.445611313592681e-05, "loss": 0.0118, "step": 147610 }, { "epoch": 35.44, "learning_rate": 7.445298219428703e-05, "loss": 0.0245, "step": 147620 }, { "epoch": 35.44, "learning_rate": 7.444985112661636e-05, "loss": 0.0085, "step": 147630 }, { "epoch": 35.44, "learning_rate": 7.444671993293096e-05, "loss": 0.0108, "step": 147640 }, { "epoch": 35.44, "learning_rate": 7.444358861324696e-05, "loss": 0.0192, "step": 147650 }, { "epoch": 35.45, "learning_rate": 7.44404571675805e-05, "loss": 0.0162, "step": 147660 }, { "epoch": 35.45, "learning_rate": 7.443732559594771e-05, "loss": 0.0119, "step": 147670 }, { "epoch": 35.45, "learning_rate": 7.443419389836476e-05, "loss": 0.0164, "step": 147680 }, { "epoch": 35.45, "learning_rate": 7.443106207484776e-05, "loss": 0.0093, "step": 147690 }, { "epoch": 35.46, "learning_rate": 7.442793012541284e-05, "loss": 0.0185, "step": 147700 }, { "epoch": 35.46, "learning_rate": 7.44247980500762e-05, "loss": 0.0183, "step": 147710 }, { "epoch": 35.46, "learning_rate": 7.442166584885393e-05, "loss": 0.0192, "step": 147720 }, { "epoch": 35.46, "learning_rate": 7.441853352176219e-05, "loss": 0.0137, "step": 147730 }, { "epoch": 35.47, "learning_rate": 7.441540106881713e-05, "loss": 0.0207, "step": 147740 }, { "epoch": 35.47, "learning_rate": 7.441226849003487e-05, "loss": 0.0282, "step": 147750 }, { "epoch": 35.47, "learning_rate": 7.440913578543159e-05, "loss": 0.0136, "step": 147760 }, { "epoch": 35.47, "learning_rate": 7.440600295502342e-05, "loss": 0.0389, "step": 147770 }, { "epoch": 35.47, "learning_rate": 7.440286999882652e-05, "loss": 0.0219, "step": 147780 }, { "epoch": 35.48, "learning_rate": 7.4399736916857e-05, "loss": 0.0214, "step": 147790 }, { "epoch": 35.48, "learning_rate": 7.439660370913104e-05, "loss": 0.0292, "step": 147800 }, { "epoch": 35.48, "learning_rate": 7.439347037566479e-05, "loss": 0.0112, "step": 147810 }, { "epoch": 35.48, "learning_rate": 7.439033691647439e-05, "loss": 0.0094, "step": 147820 }, { "epoch": 35.49, "learning_rate": 7.438720333157596e-05, "loss": 0.0209, "step": 147830 }, { "epoch": 35.49, "learning_rate": 7.43840696209857e-05, "loss": 0.0074, "step": 147840 }, { "epoch": 35.49, "learning_rate": 7.438093578471975e-05, "loss": 0.014, "step": 147850 }, { "epoch": 35.49, "learning_rate": 7.437780182279425e-05, "loss": 0.0075, "step": 147860 }, { "epoch": 35.49, "learning_rate": 7.437466773522535e-05, "loss": 0.0233, "step": 147870 }, { "epoch": 35.5, "learning_rate": 7.43715335220292e-05, "loss": 0.0128, "step": 147880 }, { "epoch": 35.5, "learning_rate": 7.436839918322198e-05, "loss": 0.0213, "step": 147890 }, { "epoch": 35.5, "learning_rate": 7.436526471881982e-05, "loss": 0.013, "step": 147900 }, { "epoch": 35.5, "learning_rate": 7.436213012883887e-05, "loss": 0.0141, "step": 147910 }, { "epoch": 35.51, "learning_rate": 7.435899541329532e-05, "loss": 0.0147, "step": 147920 }, { "epoch": 35.51, "learning_rate": 7.43558605722053e-05, "loss": 0.0089, "step": 147930 }, { "epoch": 35.51, "learning_rate": 7.435272560558496e-05, "loss": 0.0307, "step": 147940 }, { "epoch": 35.51, "learning_rate": 7.434959051345048e-05, "loss": 0.0164, "step": 147950 }, { "epoch": 35.52, "learning_rate": 7.4346455295818e-05, "loss": 0.01, "step": 147960 }, { "epoch": 35.52, "learning_rate": 7.434331995270368e-05, "loss": 0.0138, "step": 147970 }, { "epoch": 35.52, "learning_rate": 7.43401844841237e-05, "loss": 0.0237, "step": 147980 }, { "epoch": 35.52, "learning_rate": 7.433704889009419e-05, "loss": 0.0204, "step": 147990 }, { "epoch": 35.52, "learning_rate": 7.433391317063134e-05, "loss": 0.0279, "step": 148000 }, { "epoch": 35.53, "learning_rate": 7.43307773257513e-05, "loss": 0.0177, "step": 148010 }, { "epoch": 35.53, "learning_rate": 7.43276413554702e-05, "loss": 0.0375, "step": 148020 }, { "epoch": 35.53, "learning_rate": 7.432450525980425e-05, "loss": 0.0485, "step": 148030 }, { "epoch": 35.53, "learning_rate": 7.43213690387696e-05, "loss": 0.0184, "step": 148040 }, { "epoch": 35.54, "learning_rate": 7.431823269238241e-05, "loss": 0.0158, "step": 148050 }, { "epoch": 35.54, "learning_rate": 7.431509622065886e-05, "loss": 0.0345, "step": 148060 }, { "epoch": 35.54, "learning_rate": 7.43119596236151e-05, "loss": 0.022, "step": 148070 }, { "epoch": 35.54, "learning_rate": 7.430882290126728e-05, "loss": 0.0315, "step": 148080 }, { "epoch": 35.55, "learning_rate": 7.430568605363159e-05, "loss": 0.0251, "step": 148090 }, { "epoch": 35.55, "learning_rate": 7.430254908072419e-05, "loss": 0.0146, "step": 148100 }, { "epoch": 35.55, "learning_rate": 7.429941198256125e-05, "loss": 0.0283, "step": 148110 }, { "epoch": 35.55, "learning_rate": 7.429627475915893e-05, "loss": 0.0251, "step": 148120 }, { "epoch": 35.55, "learning_rate": 7.429313741053343e-05, "loss": 0.0244, "step": 148130 }, { "epoch": 35.56, "learning_rate": 7.428999993670087e-05, "loss": 0.0255, "step": 148140 }, { "epoch": 35.56, "learning_rate": 7.428686233767746e-05, "loss": 0.0268, "step": 148150 }, { "epoch": 35.56, "learning_rate": 7.428372461347935e-05, "loss": 0.0358, "step": 148160 }, { "epoch": 35.56, "learning_rate": 7.428058676412272e-05, "loss": 0.0124, "step": 148170 }, { "epoch": 35.57, "learning_rate": 7.427744878962374e-05, "loss": 0.0609, "step": 148180 }, { "epoch": 35.57, "learning_rate": 7.42743106899986e-05, "loss": 0.0318, "step": 148190 }, { "epoch": 35.57, "learning_rate": 7.427117246526347e-05, "loss": 0.0253, "step": 148200 }, { "epoch": 35.57, "learning_rate": 7.42680341154345e-05, "loss": 0.0274, "step": 148210 }, { "epoch": 35.57, "learning_rate": 7.426489564052788e-05, "loss": 0.0155, "step": 148220 }, { "epoch": 35.58, "learning_rate": 7.426175704055977e-05, "loss": 0.0166, "step": 148230 }, { "epoch": 35.58, "learning_rate": 7.42586183155464e-05, "loss": 0.011, "step": 148240 }, { "epoch": 35.58, "learning_rate": 7.425547946550387e-05, "loss": 0.0375, "step": 148250 }, { "epoch": 35.58, "learning_rate": 7.42523404904484e-05, "loss": 0.0241, "step": 148260 }, { "epoch": 35.59, "learning_rate": 7.424920139039617e-05, "loss": 0.0495, "step": 148270 }, { "epoch": 35.59, "learning_rate": 7.424606216536337e-05, "loss": 0.02, "step": 148280 }, { "epoch": 35.59, "learning_rate": 7.424292281536615e-05, "loss": 0.0182, "step": 148290 }, { "epoch": 35.59, "learning_rate": 7.42397833404207e-05, "loss": 0.0219, "step": 148300 }, { "epoch": 35.6, "learning_rate": 7.423664374054321e-05, "loss": 0.0836, "step": 148310 }, { "epoch": 35.6, "learning_rate": 7.423350401574985e-05, "loss": 0.0263, "step": 148320 }, { "epoch": 35.6, "learning_rate": 7.42303641660568e-05, "loss": 0.0235, "step": 148330 }, { "epoch": 35.6, "learning_rate": 7.422722419148027e-05, "loss": 0.0334, "step": 148340 }, { "epoch": 35.6, "learning_rate": 7.422408409203643e-05, "loss": 0.0178, "step": 148350 }, { "epoch": 35.61, "learning_rate": 7.422094386774143e-05, "loss": 0.028, "step": 148360 }, { "epoch": 35.61, "learning_rate": 7.42178035186115e-05, "loss": 0.0213, "step": 148370 }, { "epoch": 35.61, "learning_rate": 7.42146630446628e-05, "loss": 0.0188, "step": 148380 }, { "epoch": 35.61, "learning_rate": 7.421152244591154e-05, "loss": 0.0305, "step": 148390 }, { "epoch": 35.62, "learning_rate": 7.420838172237388e-05, "loss": 0.0223, "step": 148400 }, { "epoch": 35.62, "learning_rate": 7.420524087406601e-05, "loss": 0.0224, "step": 148410 }, { "epoch": 35.62, "learning_rate": 7.420209990100414e-05, "loss": 0.024, "step": 148420 }, { "epoch": 35.62, "learning_rate": 7.419895880320444e-05, "loss": 0.0241, "step": 148430 }, { "epoch": 35.62, "learning_rate": 7.41958175806831e-05, "loss": 0.0403, "step": 148440 }, { "epoch": 35.63, "learning_rate": 7.419267623345631e-05, "loss": 0.0253, "step": 148450 }, { "epoch": 35.63, "learning_rate": 7.418953476154028e-05, "loss": 0.018, "step": 148460 }, { "epoch": 35.63, "learning_rate": 7.418639316495117e-05, "loss": 0.0288, "step": 148470 }, { "epoch": 35.63, "learning_rate": 7.418325144370519e-05, "loss": 0.0348, "step": 148480 }, { "epoch": 35.64, "learning_rate": 7.418010959781853e-05, "loss": 0.0151, "step": 148490 }, { "epoch": 35.64, "learning_rate": 7.41769676273074e-05, "loss": 0.0248, "step": 148500 }, { "epoch": 35.64, "learning_rate": 7.417382553218797e-05, "loss": 0.0247, "step": 148510 }, { "epoch": 35.64, "learning_rate": 7.417068331247643e-05, "loss": 0.0181, "step": 148520 }, { "epoch": 35.65, "learning_rate": 7.416754096818898e-05, "loss": 0.0235, "step": 148530 }, { "epoch": 35.65, "learning_rate": 7.416439849934185e-05, "loss": 0.0277, "step": 148540 }, { "epoch": 35.65, "learning_rate": 7.416125590595117e-05, "loss": 0.0341, "step": 148550 }, { "epoch": 35.65, "learning_rate": 7.415811318803322e-05, "loss": 0.0228, "step": 148560 }, { "epoch": 35.65, "learning_rate": 7.415497034560413e-05, "loss": 0.0154, "step": 148570 }, { "epoch": 35.66, "learning_rate": 7.415182737868011e-05, "loss": 0.0168, "step": 148580 }, { "epoch": 35.66, "learning_rate": 7.414868428727739e-05, "loss": 0.0256, "step": 148590 }, { "epoch": 35.66, "learning_rate": 7.414554107141214e-05, "loss": 0.0223, "step": 148600 }, { "epoch": 35.66, "learning_rate": 7.414239773110056e-05, "loss": 0.0227, "step": 148610 }, { "epoch": 35.67, "learning_rate": 7.413925426635887e-05, "loss": 0.0149, "step": 148620 }, { "epoch": 35.67, "learning_rate": 7.413611067720325e-05, "loss": 0.0235, "step": 148630 }, { "epoch": 35.67, "learning_rate": 7.413296696364993e-05, "loss": 0.0221, "step": 148640 }, { "epoch": 35.67, "learning_rate": 7.41298231257151e-05, "loss": 0.0218, "step": 148650 }, { "epoch": 35.68, "learning_rate": 7.412667916341495e-05, "loss": 0.0197, "step": 148660 }, { "epoch": 35.68, "learning_rate": 7.41235350767657e-05, "loss": 0.0165, "step": 148670 }, { "epoch": 35.68, "learning_rate": 7.412039086578353e-05, "loss": 0.0226, "step": 148680 }, { "epoch": 35.68, "learning_rate": 7.411724653048469e-05, "loss": 0.0309, "step": 148690 }, { "epoch": 35.68, "learning_rate": 7.411410207088534e-05, "loss": 0.0202, "step": 148700 }, { "epoch": 35.69, "learning_rate": 7.411095748700172e-05, "loss": 0.0353, "step": 148710 }, { "epoch": 35.69, "learning_rate": 7.410781277885002e-05, "loss": 0.0127, "step": 148720 }, { "epoch": 35.69, "learning_rate": 7.410466794644645e-05, "loss": 0.0271, "step": 148730 }, { "epoch": 35.69, "learning_rate": 7.410152298980721e-05, "loss": 0.0194, "step": 148740 }, { "epoch": 35.7, "learning_rate": 7.409837790894854e-05, "loss": 0.0253, "step": 148750 }, { "epoch": 35.7, "learning_rate": 7.409523270388661e-05, "loss": 0.0226, "step": 148760 }, { "epoch": 35.7, "learning_rate": 7.409208737463766e-05, "loss": 0.0216, "step": 148770 }, { "epoch": 35.7, "learning_rate": 7.408894192121788e-05, "loss": 0.0158, "step": 148780 }, { "epoch": 35.7, "learning_rate": 7.40857963436435e-05, "loss": 0.0201, "step": 148790 }, { "epoch": 35.71, "learning_rate": 7.408265064193071e-05, "loss": 0.024, "step": 148800 }, { "epoch": 35.71, "learning_rate": 7.407950481609575e-05, "loss": 0.0071, "step": 148810 }, { "epoch": 35.71, "learning_rate": 7.407635886615482e-05, "loss": 0.0109, "step": 148820 }, { "epoch": 35.71, "learning_rate": 7.407321279212414e-05, "loss": 0.0203, "step": 148830 }, { "epoch": 35.72, "learning_rate": 7.407006659401992e-05, "loss": 0.0313, "step": 148840 }, { "epoch": 35.72, "learning_rate": 7.406692027185837e-05, "loss": 0.0324, "step": 148850 }, { "epoch": 35.72, "learning_rate": 7.406377382565572e-05, "loss": 0.0197, "step": 148860 }, { "epoch": 35.72, "learning_rate": 7.406062725542817e-05, "loss": 0.0154, "step": 148870 }, { "epoch": 35.73, "learning_rate": 7.405748056119195e-05, "loss": 0.0252, "step": 148880 }, { "epoch": 35.73, "learning_rate": 7.405433374296327e-05, "loss": 0.0231, "step": 148890 }, { "epoch": 35.73, "learning_rate": 7.405118680075836e-05, "loss": 0.0126, "step": 148900 }, { "epoch": 35.73, "learning_rate": 7.404803973459342e-05, "loss": 0.0164, "step": 148910 }, { "epoch": 35.73, "learning_rate": 7.404489254448468e-05, "loss": 0.019, "step": 148920 }, { "epoch": 35.74, "learning_rate": 7.404174523044837e-05, "loss": 0.02, "step": 148930 }, { "epoch": 35.74, "learning_rate": 7.40385977925007e-05, "loss": 0.0243, "step": 148940 }, { "epoch": 35.74, "learning_rate": 7.403545023065791e-05, "loss": 0.0203, "step": 148950 }, { "epoch": 35.74, "learning_rate": 7.40323025449362e-05, "loss": 0.015, "step": 148960 }, { "epoch": 35.75, "learning_rate": 7.40291547353518e-05, "loss": 0.0172, "step": 148970 }, { "epoch": 35.75, "learning_rate": 7.402600680192095e-05, "loss": 0.0144, "step": 148980 }, { "epoch": 35.75, "learning_rate": 7.402285874465984e-05, "loss": 0.0203, "step": 148990 }, { "epoch": 35.75, "learning_rate": 7.401971056358473e-05, "loss": 0.0228, "step": 149000 }, { "epoch": 35.76, "learning_rate": 7.401656225871183e-05, "loss": 0.0195, "step": 149010 }, { "epoch": 35.76, "learning_rate": 7.401341383005735e-05, "loss": 0.0377, "step": 149020 }, { "epoch": 35.76, "learning_rate": 7.401026527763755e-05, "loss": 0.0215, "step": 149030 }, { "epoch": 35.76, "learning_rate": 7.400711660146865e-05, "loss": 0.025, "step": 149040 }, { "epoch": 35.76, "learning_rate": 7.400396780156685e-05, "loss": 0.0257, "step": 149050 }, { "epoch": 35.77, "learning_rate": 7.400081887794841e-05, "loss": 0.0116, "step": 149060 }, { "epoch": 35.77, "learning_rate": 7.399766983062955e-05, "loss": 0.0246, "step": 149070 }, { "epoch": 35.77, "learning_rate": 7.39945206596265e-05, "loss": 0.0296, "step": 149080 }, { "epoch": 35.77, "learning_rate": 7.399137136495547e-05, "loss": 0.0254, "step": 149090 }, { "epoch": 35.78, "learning_rate": 7.398822194663273e-05, "loss": 0.0284, "step": 149100 }, { "epoch": 35.78, "learning_rate": 7.398507240467449e-05, "loss": 0.0218, "step": 149110 }, { "epoch": 35.78, "learning_rate": 7.398192273909699e-05, "loss": 0.0212, "step": 149120 }, { "epoch": 35.78, "learning_rate": 7.397877294991645e-05, "loss": 0.0185, "step": 149130 }, { "epoch": 35.78, "learning_rate": 7.397562303714913e-05, "loss": 0.0152, "step": 149140 }, { "epoch": 35.79, "learning_rate": 7.397247300081124e-05, "loss": 0.0329, "step": 149150 }, { "epoch": 35.79, "learning_rate": 7.396932284091902e-05, "loss": 0.0241, "step": 149160 }, { "epoch": 35.79, "learning_rate": 7.396617255748871e-05, "loss": 0.0169, "step": 149170 }, { "epoch": 35.79, "learning_rate": 7.396302215053656e-05, "loss": 0.0083, "step": 149180 }, { "epoch": 35.8, "learning_rate": 7.395987162007878e-05, "loss": 0.0178, "step": 149190 }, { "epoch": 35.8, "learning_rate": 7.395672096613163e-05, "loss": 0.0156, "step": 149200 }, { "epoch": 35.8, "learning_rate": 7.395357018871132e-05, "loss": 0.0174, "step": 149210 }, { "epoch": 35.8, "learning_rate": 7.395041928783413e-05, "loss": 0.0289, "step": 149220 }, { "epoch": 35.81, "learning_rate": 7.394726826351626e-05, "loss": 0.0112, "step": 149230 }, { "epoch": 35.81, "learning_rate": 7.394411711577398e-05, "loss": 0.0162, "step": 149240 }, { "epoch": 35.81, "learning_rate": 7.394096584462352e-05, "loss": 0.0157, "step": 149250 }, { "epoch": 35.81, "learning_rate": 7.393781445008113e-05, "loss": 0.0115, "step": 149260 }, { "epoch": 35.81, "learning_rate": 7.393466293216304e-05, "loss": 0.0282, "step": 149270 }, { "epoch": 35.82, "learning_rate": 7.393151129088549e-05, "loss": 0.0198, "step": 149280 }, { "epoch": 35.82, "learning_rate": 7.392835952626473e-05, "loss": 0.0191, "step": 149290 }, { "epoch": 35.82, "learning_rate": 7.392520763831702e-05, "loss": 0.015, "step": 149300 }, { "epoch": 35.82, "learning_rate": 7.392205562705858e-05, "loss": 0.0312, "step": 149310 }, { "epoch": 35.83, "learning_rate": 7.391890349250567e-05, "loss": 0.0183, "step": 149320 }, { "epoch": 35.83, "learning_rate": 7.391575123467451e-05, "loss": 0.0246, "step": 149330 }, { "epoch": 35.83, "learning_rate": 7.39125988535814e-05, "loss": 0.0193, "step": 149340 }, { "epoch": 35.83, "learning_rate": 7.390944634924255e-05, "loss": 0.028, "step": 149350 }, { "epoch": 35.84, "learning_rate": 7.390629372167419e-05, "loss": 0.0401, "step": 149360 }, { "epoch": 35.84, "learning_rate": 7.39031409708926e-05, "loss": 0.0182, "step": 149370 }, { "epoch": 35.84, "learning_rate": 7.389998809691403e-05, "loss": 0.0166, "step": 149380 }, { "epoch": 35.84, "learning_rate": 7.389683509975473e-05, "loss": 0.0178, "step": 149390 }, { "epoch": 35.84, "learning_rate": 7.389368197943091e-05, "loss": 0.009, "step": 149400 }, { "epoch": 35.85, "learning_rate": 7.389052873595889e-05, "loss": 0.0196, "step": 149410 }, { "epoch": 35.85, "learning_rate": 7.388737536935485e-05, "loss": 0.0152, "step": 149420 }, { "epoch": 35.85, "learning_rate": 7.388422187963513e-05, "loss": 0.0227, "step": 149430 }, { "epoch": 35.85, "learning_rate": 7.388106826681589e-05, "loss": 0.0255, "step": 149440 }, { "epoch": 35.86, "learning_rate": 7.387791453091344e-05, "loss": 0.0186, "step": 149450 }, { "epoch": 35.86, "learning_rate": 7.3874760671944e-05, "loss": 0.0201, "step": 149460 }, { "epoch": 35.86, "learning_rate": 7.387160668992387e-05, "loss": 0.0205, "step": 149470 }, { "epoch": 35.86, "learning_rate": 7.386845258486926e-05, "loss": 0.0253, "step": 149480 }, { "epoch": 35.86, "learning_rate": 7.386529835679645e-05, "loss": 0.0402, "step": 149490 }, { "epoch": 35.87, "learning_rate": 7.38621440057217e-05, "loss": 0.0216, "step": 149500 }, { "epoch": 35.87, "learning_rate": 7.385898953166126e-05, "loss": 0.0155, "step": 149510 }, { "epoch": 35.87, "learning_rate": 7.385583493463138e-05, "loss": 0.0177, "step": 149520 }, { "epoch": 35.87, "learning_rate": 7.385268021464832e-05, "loss": 0.0129, "step": 149530 }, { "epoch": 35.88, "learning_rate": 7.384952537172836e-05, "loss": 0.0147, "step": 149540 }, { "epoch": 35.88, "learning_rate": 7.384637040588775e-05, "loss": 0.0238, "step": 149550 }, { "epoch": 35.88, "learning_rate": 7.384321531714273e-05, "loss": 0.0199, "step": 149560 }, { "epoch": 35.88, "learning_rate": 7.38400601055096e-05, "loss": 0.0137, "step": 149570 }, { "epoch": 35.89, "learning_rate": 7.383690477100461e-05, "loss": 0.0188, "step": 149580 }, { "epoch": 35.89, "learning_rate": 7.383374931364398e-05, "loss": 0.019, "step": 149590 }, { "epoch": 35.89, "learning_rate": 7.383059373344402e-05, "loss": 0.0147, "step": 149600 }, { "epoch": 35.89, "learning_rate": 7.382743803042099e-05, "loss": 0.0218, "step": 149610 }, { "epoch": 35.89, "learning_rate": 7.382428220459113e-05, "loss": 0.029, "step": 149620 }, { "epoch": 35.9, "learning_rate": 7.382112625597074e-05, "loss": 0.0124, "step": 149630 }, { "epoch": 35.9, "learning_rate": 7.381797018457606e-05, "loss": 0.0168, "step": 149640 }, { "epoch": 35.9, "learning_rate": 7.381481399042335e-05, "loss": 0.0416, "step": 149650 }, { "epoch": 35.9, "learning_rate": 7.38116576735289e-05, "loss": 0.0249, "step": 149660 }, { "epoch": 35.91, "learning_rate": 7.380850123390896e-05, "loss": 0.0102, "step": 149670 }, { "epoch": 35.91, "learning_rate": 7.38053446715798e-05, "loss": 0.0178, "step": 149680 }, { "epoch": 35.91, "learning_rate": 7.38021879865577e-05, "loss": 0.0112, "step": 149690 }, { "epoch": 35.91, "learning_rate": 7.379903117885894e-05, "loss": 0.0156, "step": 149700 }, { "epoch": 35.92, "learning_rate": 7.379587424849976e-05, "loss": 0.0146, "step": 149710 }, { "epoch": 35.92, "learning_rate": 7.379271719549645e-05, "loss": 0.0191, "step": 149720 }, { "epoch": 35.92, "learning_rate": 7.378956001986527e-05, "loss": 0.0153, "step": 149730 }, { "epoch": 35.92, "learning_rate": 7.378640272162252e-05, "loss": 0.0178, "step": 149740 }, { "epoch": 35.92, "learning_rate": 7.378324530078443e-05, "loss": 0.0177, "step": 149750 }, { "epoch": 35.93, "learning_rate": 7.378008775736729e-05, "loss": 0.0176, "step": 149760 }, { "epoch": 35.93, "learning_rate": 7.377693009138739e-05, "loss": 0.0117, "step": 149770 }, { "epoch": 35.93, "learning_rate": 7.3773772302861e-05, "loss": 0.0236, "step": 149780 }, { "epoch": 35.93, "learning_rate": 7.37706143918044e-05, "loss": 0.0155, "step": 149790 }, { "epoch": 35.94, "learning_rate": 7.376745635823382e-05, "loss": 0.0183, "step": 149800 }, { "epoch": 35.94, "learning_rate": 7.376429820216559e-05, "loss": 0.0115, "step": 149810 }, { "epoch": 35.94, "learning_rate": 7.376113992361596e-05, "loss": 0.0166, "step": 149820 }, { "epoch": 35.94, "learning_rate": 7.375798152260121e-05, "loss": 0.012, "step": 149830 }, { "epoch": 35.94, "learning_rate": 7.375482299913764e-05, "loss": 0.0139, "step": 149840 }, { "epoch": 35.95, "learning_rate": 7.37516643532415e-05, "loss": 0.0136, "step": 149850 }, { "epoch": 35.95, "learning_rate": 7.374850558492912e-05, "loss": 0.012, "step": 149860 }, { "epoch": 36.0, "learning_rate": 7.374534669421672e-05, "loss": 0.0257, "step": 149870 }, { "epoch": 36.0, "learning_rate": 7.37421876811206e-05, "loss": 0.0219, "step": 149880 }, { "epoch": 36.01, "learning_rate": 7.373902854565704e-05, "loss": 0.0437, "step": 149890 }, { "epoch": 36.01, "learning_rate": 7.373586928784234e-05, "loss": 0.0126, "step": 149900 }, { "epoch": 36.01, "learning_rate": 7.373270990769276e-05, "loss": 0.0159, "step": 149910 }, { "epoch": 36.01, "learning_rate": 7.372955040522461e-05, "loss": 0.0133, "step": 149920 }, { "epoch": 36.01, "learning_rate": 7.372639078045416e-05, "loss": 0.0122, "step": 149930 }, { "epoch": 36.02, "learning_rate": 7.372323103339769e-05, "loss": 0.0221, "step": 149940 }, { "epoch": 36.02, "learning_rate": 7.372007116407148e-05, "loss": 0.0257, "step": 149950 }, { "epoch": 36.02, "learning_rate": 7.371691117249184e-05, "loss": 0.0129, "step": 149960 }, { "epoch": 36.02, "learning_rate": 7.371375105867501e-05, "loss": 0.0157, "step": 149970 }, { "epoch": 36.03, "learning_rate": 7.371059082263734e-05, "loss": 0.0158, "step": 149980 }, { "epoch": 36.03, "learning_rate": 7.370743046439506e-05, "loss": 0.0199, "step": 149990 }, { "epoch": 36.03, "learning_rate": 7.370426998396452e-05, "loss": 0.0138, "step": 150000 }, { "epoch": 36.03, "learning_rate": 7.370110938136195e-05, "loss": 0.0139, "step": 150010 }, { "epoch": 36.03, "learning_rate": 7.369794865660367e-05, "loss": 0.0249, "step": 150020 }, { "epoch": 36.04, "learning_rate": 7.369478780970597e-05, "loss": 0.0204, "step": 150030 }, { "epoch": 36.04, "learning_rate": 7.369162684068512e-05, "loss": 0.0244, "step": 150040 }, { "epoch": 36.04, "learning_rate": 7.368846574955744e-05, "loss": 0.022, "step": 150050 }, { "epoch": 36.04, "learning_rate": 7.36853045363392e-05, "loss": 0.0151, "step": 150060 }, { "epoch": 36.05, "learning_rate": 7.368214320104673e-05, "loss": 0.0291, "step": 150070 }, { "epoch": 36.05, "learning_rate": 7.367898174369627e-05, "loss": 0.0149, "step": 150080 }, { "epoch": 36.05, "learning_rate": 7.367582016430415e-05, "loss": 0.012, "step": 150090 }, { "epoch": 36.05, "learning_rate": 7.367265846288664e-05, "loss": 0.0257, "step": 150100 }, { "epoch": 36.06, "learning_rate": 7.366949663946007e-05, "loss": 0.0245, "step": 150110 }, { "epoch": 36.06, "learning_rate": 7.366633469404071e-05, "loss": 0.0213, "step": 150120 }, { "epoch": 36.06, "learning_rate": 7.366317262664486e-05, "loss": 0.0349, "step": 150130 }, { "epoch": 36.06, "learning_rate": 7.366001043728882e-05, "loss": 0.0123, "step": 150140 }, { "epoch": 36.06, "learning_rate": 7.365684812598889e-05, "loss": 0.0165, "step": 150150 }, { "epoch": 36.07, "learning_rate": 7.365368569276137e-05, "loss": 0.0179, "step": 150160 }, { "epoch": 36.07, "learning_rate": 7.365052313762255e-05, "loss": 0.026, "step": 150170 }, { "epoch": 36.07, "learning_rate": 7.364736046058873e-05, "loss": 0.0174, "step": 150180 }, { "epoch": 36.07, "learning_rate": 7.364419766167623e-05, "loss": 0.0197, "step": 150190 }, { "epoch": 36.08, "learning_rate": 7.364103474090133e-05, "loss": 0.0281, "step": 150200 }, { "epoch": 36.08, "learning_rate": 7.363787169828036e-05, "loss": 0.0132, "step": 150210 }, { "epoch": 36.08, "learning_rate": 7.363470853382958e-05, "loss": 0.0128, "step": 150220 }, { "epoch": 36.08, "learning_rate": 7.363154524756532e-05, "loss": 0.0216, "step": 150230 }, { "epoch": 36.09, "learning_rate": 7.362838183950387e-05, "loss": 0.021, "step": 150240 }, { "epoch": 36.09, "learning_rate": 7.362521830966155e-05, "loss": 0.017, "step": 150250 }, { "epoch": 36.09, "learning_rate": 7.362205465805465e-05, "loss": 0.0176, "step": 150260 }, { "epoch": 36.09, "learning_rate": 7.361889088469949e-05, "loss": 0.0195, "step": 150270 }, { "epoch": 36.09, "learning_rate": 7.361572698961238e-05, "loss": 0.0284, "step": 150280 }, { "epoch": 36.1, "learning_rate": 7.361256297280959e-05, "loss": 0.0272, "step": 150290 }, { "epoch": 36.1, "learning_rate": 7.360939883430748e-05, "loss": 0.0182, "step": 150300 }, { "epoch": 36.1, "learning_rate": 7.36062345741223e-05, "loss": 0.0161, "step": 150310 }, { "epoch": 36.1, "learning_rate": 7.360307019227042e-05, "loss": 0.021, "step": 150320 }, { "epoch": 36.11, "learning_rate": 7.359990568876811e-05, "loss": 0.0157, "step": 150330 }, { "epoch": 36.11, "learning_rate": 7.359674106363167e-05, "loss": 0.0068, "step": 150340 }, { "epoch": 36.11, "learning_rate": 7.359357631687745e-05, "loss": 0.0152, "step": 150350 }, { "epoch": 36.11, "learning_rate": 7.359041144852174e-05, "loss": 0.0093, "step": 150360 }, { "epoch": 36.11, "learning_rate": 7.358724645858086e-05, "loss": 0.0326, "step": 150370 }, { "epoch": 36.12, "learning_rate": 7.35840813470711e-05, "loss": 0.009, "step": 150380 }, { "epoch": 36.12, "learning_rate": 7.358091611400879e-05, "loss": 0.0199, "step": 150390 }, { "epoch": 36.12, "learning_rate": 7.357775075941025e-05, "loss": 0.0113, "step": 150400 }, { "epoch": 36.12, "learning_rate": 7.357458528329176e-05, "loss": 0.0239, "step": 150410 }, { "epoch": 36.13, "learning_rate": 7.357141968566968e-05, "loss": 0.0195, "step": 150420 }, { "epoch": 36.13, "learning_rate": 7.35682539665603e-05, "loss": 0.0206, "step": 150430 }, { "epoch": 36.13, "learning_rate": 7.356508812597995e-05, "loss": 0.0179, "step": 150440 }, { "epoch": 36.13, "learning_rate": 7.356192216394493e-05, "loss": 0.0176, "step": 150450 }, { "epoch": 36.14, "learning_rate": 7.355875608047158e-05, "loss": 0.0224, "step": 150460 }, { "epoch": 36.14, "learning_rate": 7.35555898755762e-05, "loss": 0.0138, "step": 150470 }, { "epoch": 36.14, "learning_rate": 7.35524235492751e-05, "loss": 0.0215, "step": 150480 }, { "epoch": 36.14, "learning_rate": 7.354925710158461e-05, "loss": 0.0112, "step": 150490 }, { "epoch": 36.14, "learning_rate": 7.354609053252107e-05, "loss": 0.0177, "step": 150500 }, { "epoch": 36.15, "learning_rate": 7.354292384210077e-05, "loss": 0.016, "step": 150510 }, { "epoch": 36.15, "learning_rate": 7.353975703034006e-05, "loss": 0.0079, "step": 150520 }, { "epoch": 36.15, "learning_rate": 7.353659009725523e-05, "loss": 0.0156, "step": 150530 }, { "epoch": 36.15, "learning_rate": 7.353342304286261e-05, "loss": 0.0272, "step": 150540 }, { "epoch": 36.16, "learning_rate": 7.353025586717856e-05, "loss": 0.0094, "step": 150550 }, { "epoch": 36.16, "learning_rate": 7.352708857021934e-05, "loss": 0.0169, "step": 150560 }, { "epoch": 36.16, "learning_rate": 7.352392115200132e-05, "loss": 0.0146, "step": 150570 }, { "epoch": 36.16, "learning_rate": 7.352075361254082e-05, "loss": 0.0136, "step": 150580 }, { "epoch": 36.16, "learning_rate": 7.351758595185417e-05, "loss": 0.022, "step": 150590 }, { "epoch": 36.17, "learning_rate": 7.351441816995767e-05, "loss": 0.017, "step": 150600 }, { "epoch": 36.17, "learning_rate": 7.351125026686768e-05, "loss": 0.0114, "step": 150610 }, { "epoch": 36.17, "learning_rate": 7.350808224260048e-05, "loss": 0.0152, "step": 150620 }, { "epoch": 36.17, "learning_rate": 7.350491409717245e-05, "loss": 0.0207, "step": 150630 }, { "epoch": 36.18, "learning_rate": 7.350174583059989e-05, "loss": 0.0106, "step": 150640 }, { "epoch": 36.18, "learning_rate": 7.349857744289914e-05, "loss": 0.0155, "step": 150650 }, { "epoch": 36.18, "learning_rate": 7.349540893408653e-05, "loss": 0.016, "step": 150660 }, { "epoch": 36.18, "learning_rate": 7.349224030417838e-05, "loss": 0.0157, "step": 150670 }, { "epoch": 36.19, "learning_rate": 7.348907155319101e-05, "loss": 0.0112, "step": 150680 }, { "epoch": 36.19, "learning_rate": 7.348590268114078e-05, "loss": 0.0167, "step": 150690 }, { "epoch": 36.19, "learning_rate": 7.348273368804402e-05, "loss": 0.017, "step": 150700 }, { "epoch": 36.19, "learning_rate": 7.347956457391704e-05, "loss": 0.0253, "step": 150710 }, { "epoch": 36.19, "learning_rate": 7.34763953387762e-05, "loss": 0.0122, "step": 150720 }, { "epoch": 36.2, "learning_rate": 7.347322598263781e-05, "loss": 0.0124, "step": 150730 }, { "epoch": 36.2, "learning_rate": 7.347005650551824e-05, "loss": 0.0112, "step": 150740 }, { "epoch": 36.2, "learning_rate": 7.346688690743378e-05, "loss": 0.0142, "step": 150750 }, { "epoch": 36.2, "learning_rate": 7.346371718840079e-05, "loss": 0.0299, "step": 150760 }, { "epoch": 36.21, "learning_rate": 7.346054734843561e-05, "loss": 0.0102, "step": 150770 }, { "epoch": 36.21, "learning_rate": 7.345737738755458e-05, "loss": 0.0145, "step": 150780 }, { "epoch": 36.21, "learning_rate": 7.345420730577403e-05, "loss": 0.0198, "step": 150790 }, { "epoch": 36.21, "learning_rate": 7.345103710311031e-05, "loss": 0.0139, "step": 150800 }, { "epoch": 36.22, "learning_rate": 7.344786677957973e-05, "loss": 0.0196, "step": 150810 }, { "epoch": 36.22, "learning_rate": 7.344469633519865e-05, "loss": 0.0243, "step": 150820 }, { "epoch": 36.22, "learning_rate": 7.344152576998341e-05, "loss": 0.0153, "step": 150830 }, { "epoch": 36.22, "learning_rate": 7.343835508395036e-05, "loss": 0.0127, "step": 150840 }, { "epoch": 36.22, "learning_rate": 7.343518427711581e-05, "loss": 0.0179, "step": 150850 }, { "epoch": 36.23, "learning_rate": 7.343201334949615e-05, "loss": 0.0117, "step": 150860 }, { "epoch": 36.23, "learning_rate": 7.342884230110768e-05, "loss": 0.0126, "step": 150870 }, { "epoch": 36.23, "learning_rate": 7.342567113196677e-05, "loss": 0.0144, "step": 150880 }, { "epoch": 36.23, "learning_rate": 7.342249984208976e-05, "loss": 0.0171, "step": 150890 }, { "epoch": 36.24, "learning_rate": 7.341932843149298e-05, "loss": 0.0184, "step": 150900 }, { "epoch": 36.24, "learning_rate": 7.341615690019278e-05, "loss": 0.0162, "step": 150910 }, { "epoch": 36.24, "learning_rate": 7.341298524820552e-05, "loss": 0.0151, "step": 150920 }, { "epoch": 36.24, "learning_rate": 7.340981347554754e-05, "loss": 0.016, "step": 150930 }, { "epoch": 36.24, "learning_rate": 7.34066415822352e-05, "loss": 0.0196, "step": 150940 }, { "epoch": 36.25, "learning_rate": 7.340346956828481e-05, "loss": 0.0179, "step": 150950 }, { "epoch": 36.25, "learning_rate": 7.340029743371275e-05, "loss": 0.0259, "step": 150960 }, { "epoch": 36.25, "learning_rate": 7.339712517853536e-05, "loss": 0.0171, "step": 150970 }, { "epoch": 36.25, "learning_rate": 7.339395280276898e-05, "loss": 0.0098, "step": 150980 }, { "epoch": 36.26, "learning_rate": 7.339078030642999e-05, "loss": 0.0169, "step": 150990 }, { "epoch": 36.26, "learning_rate": 7.338760768953473e-05, "loss": 0.0188, "step": 151000 }, { "epoch": 36.26, "learning_rate": 7.338443495209953e-05, "loss": 0.0144, "step": 151010 }, { "epoch": 36.26, "learning_rate": 7.338126209414075e-05, "loss": 0.0162, "step": 151020 }, { "epoch": 36.27, "learning_rate": 7.337808911567475e-05, "loss": 0.0102, "step": 151030 }, { "epoch": 36.27, "learning_rate": 7.337491601671789e-05, "loss": 0.0137, "step": 151040 }, { "epoch": 36.27, "learning_rate": 7.337174279728652e-05, "loss": 0.0151, "step": 151050 }, { "epoch": 36.27, "learning_rate": 7.336856945739699e-05, "loss": 0.0209, "step": 151060 }, { "epoch": 36.27, "learning_rate": 7.336539599706565e-05, "loss": 0.0225, "step": 151070 }, { "epoch": 36.28, "learning_rate": 7.336222241630887e-05, "loss": 0.017, "step": 151080 }, { "epoch": 36.28, "learning_rate": 7.3359048715143e-05, "loss": 0.0145, "step": 151090 }, { "epoch": 36.28, "learning_rate": 7.335587489358442e-05, "loss": 0.0115, "step": 151100 }, { "epoch": 36.28, "learning_rate": 7.335270095164944e-05, "loss": 0.0122, "step": 151110 }, { "epoch": 36.29, "learning_rate": 7.334952688935444e-05, "loss": 0.0162, "step": 151120 }, { "epoch": 36.29, "learning_rate": 7.334635270671579e-05, "loss": 0.0062, "step": 151130 }, { "epoch": 36.29, "learning_rate": 7.334317840374985e-05, "loss": 0.0143, "step": 151140 }, { "epoch": 36.29, "learning_rate": 7.334000398047299e-05, "loss": 0.0198, "step": 151150 }, { "epoch": 36.3, "learning_rate": 7.333682943690152e-05, "loss": 0.0161, "step": 151160 }, { "epoch": 36.3, "learning_rate": 7.333365477305186e-05, "loss": 0.0225, "step": 151170 }, { "epoch": 36.3, "learning_rate": 7.333047998894034e-05, "loss": 0.0374, "step": 151180 }, { "epoch": 36.3, "learning_rate": 7.332730508458331e-05, "loss": 0.0177, "step": 151190 }, { "epoch": 36.3, "learning_rate": 7.332413005999717e-05, "loss": 0.0169, "step": 151200 }, { "epoch": 36.31, "learning_rate": 7.332095491519828e-05, "loss": 0.0268, "step": 151210 }, { "epoch": 36.31, "learning_rate": 7.331777965020299e-05, "loss": 0.0128, "step": 151220 }, { "epoch": 36.31, "learning_rate": 7.331460426502766e-05, "loss": 0.0131, "step": 151230 }, { "epoch": 36.31, "learning_rate": 7.331142875968867e-05, "loss": 0.0156, "step": 151240 }, { "epoch": 36.32, "learning_rate": 7.330825313420237e-05, "loss": 0.0164, "step": 151250 }, { "epoch": 36.32, "learning_rate": 7.330507738858517e-05, "loss": 0.019, "step": 151260 }, { "epoch": 36.32, "learning_rate": 7.330190152285338e-05, "loss": 0.0086, "step": 151270 }, { "epoch": 36.32, "learning_rate": 7.329872553702339e-05, "loss": 0.0229, "step": 151280 }, { "epoch": 36.32, "learning_rate": 7.32955494311116e-05, "loss": 0.0172, "step": 151290 }, { "epoch": 36.33, "learning_rate": 7.329237320513433e-05, "loss": 0.019, "step": 151300 }, { "epoch": 36.33, "learning_rate": 7.328919685910799e-05, "loss": 0.0131, "step": 151310 }, { "epoch": 36.33, "learning_rate": 7.328602039304893e-05, "loss": 0.0225, "step": 151320 }, { "epoch": 36.33, "learning_rate": 7.32828438069735e-05, "loss": 0.035, "step": 151330 }, { "epoch": 36.34, "learning_rate": 7.327966710089812e-05, "loss": 0.0137, "step": 151340 }, { "epoch": 36.34, "learning_rate": 7.327649027483914e-05, "loss": 0.0255, "step": 151350 }, { "epoch": 36.34, "learning_rate": 7.327331332881296e-05, "loss": 0.0115, "step": 151360 }, { "epoch": 36.34, "learning_rate": 7.32701362628359e-05, "loss": 0.0142, "step": 151370 }, { "epoch": 36.35, "learning_rate": 7.326695907692436e-05, "loss": 0.015, "step": 151380 }, { "epoch": 36.35, "learning_rate": 7.326378177109473e-05, "loss": 0.0118, "step": 151390 }, { "epoch": 36.35, "learning_rate": 7.326060434536337e-05, "loss": 0.0211, "step": 151400 }, { "epoch": 36.35, "learning_rate": 7.325742679974665e-05, "loss": 0.017, "step": 151410 }, { "epoch": 36.35, "learning_rate": 7.325424913426098e-05, "loss": 0.0118, "step": 151420 }, { "epoch": 36.36, "learning_rate": 7.325107134892271e-05, "loss": 0.0119, "step": 151430 }, { "epoch": 36.36, "learning_rate": 7.324789344374822e-05, "loss": 0.0176, "step": 151440 }, { "epoch": 36.36, "learning_rate": 7.32447154187539e-05, "loss": 0.0258, "step": 151450 }, { "epoch": 36.36, "learning_rate": 7.32415372739561e-05, "loss": 0.0404, "step": 151460 }, { "epoch": 36.37, "learning_rate": 7.323835900937124e-05, "loss": 0.0301, "step": 151470 }, { "epoch": 36.37, "learning_rate": 7.323518062501569e-05, "loss": 0.0146, "step": 151480 }, { "epoch": 36.37, "learning_rate": 7.32320021209058e-05, "loss": 0.0176, "step": 151490 }, { "epoch": 36.37, "learning_rate": 7.322882349705799e-05, "loss": 0.0109, "step": 151500 }, { "epoch": 36.38, "learning_rate": 7.322564475348864e-05, "loss": 0.014, "step": 151510 }, { "epoch": 36.38, "learning_rate": 7.322246589021411e-05, "loss": 0.0206, "step": 151520 }, { "epoch": 36.38, "learning_rate": 7.321928690725081e-05, "loss": 0.0166, "step": 151530 }, { "epoch": 36.38, "learning_rate": 7.32161078046151e-05, "loss": 0.011, "step": 151540 }, { "epoch": 36.38, "learning_rate": 7.321292858232337e-05, "loss": 0.0125, "step": 151550 }, { "epoch": 36.39, "learning_rate": 7.320974924039203e-05, "loss": 0.0189, "step": 151560 }, { "epoch": 36.39, "learning_rate": 7.320656977883744e-05, "loss": 0.0206, "step": 151570 }, { "epoch": 36.39, "learning_rate": 7.320339019767599e-05, "loss": 0.01, "step": 151580 }, { "epoch": 36.39, "learning_rate": 7.320021049692408e-05, "loss": 0.0335, "step": 151590 }, { "epoch": 36.4, "learning_rate": 7.319703067659809e-05, "loss": 0.0206, "step": 151600 }, { "epoch": 36.4, "learning_rate": 7.319385073671441e-05, "loss": 0.0107, "step": 151610 }, { "epoch": 36.4, "learning_rate": 7.319067067728943e-05, "loss": 0.0118, "step": 151620 }, { "epoch": 36.4, "learning_rate": 7.318749049833952e-05, "loss": 0.0265, "step": 151630 }, { "epoch": 36.4, "learning_rate": 7.318431019988112e-05, "loss": 0.0294, "step": 151640 }, { "epoch": 36.41, "learning_rate": 7.318112978193058e-05, "loss": 0.0251, "step": 151650 }, { "epoch": 36.41, "learning_rate": 7.31779492445043e-05, "loss": 0.0149, "step": 151660 }, { "epoch": 36.41, "learning_rate": 7.317476858761868e-05, "loss": 0.0253, "step": 151670 }, { "epoch": 36.41, "learning_rate": 7.31715878112901e-05, "loss": 0.0161, "step": 151680 }, { "epoch": 36.42, "learning_rate": 7.316840691553497e-05, "loss": 0.0106, "step": 151690 }, { "epoch": 36.42, "learning_rate": 7.316522590036968e-05, "loss": 0.0219, "step": 151700 }, { "epoch": 36.42, "learning_rate": 7.316204476581062e-05, "loss": 0.0331, "step": 151710 }, { "epoch": 36.42, "learning_rate": 7.31588635118742e-05, "loss": 0.0245, "step": 151720 }, { "epoch": 36.43, "learning_rate": 7.315568213857678e-05, "loss": 0.0147, "step": 151730 }, { "epoch": 36.43, "learning_rate": 7.315250064593479e-05, "loss": 0.0298, "step": 151740 }, { "epoch": 36.43, "learning_rate": 7.314931903396463e-05, "loss": 0.0092, "step": 151750 }, { "epoch": 36.43, "learning_rate": 7.314613730268267e-05, "loss": 0.0093, "step": 151760 }, { "epoch": 36.43, "learning_rate": 7.314295545210533e-05, "loss": 0.0162, "step": 151770 }, { "epoch": 36.44, "learning_rate": 7.313977348224901e-05, "loss": 0.018, "step": 151780 }, { "epoch": 36.44, "learning_rate": 7.313659139313009e-05, "loss": 0.0104, "step": 151790 }, { "epoch": 36.44, "learning_rate": 7.3133409184765e-05, "loss": 0.0098, "step": 151800 }, { "epoch": 36.44, "learning_rate": 7.313022685717012e-05, "loss": 0.0163, "step": 151810 }, { "epoch": 36.45, "learning_rate": 7.312704441036186e-05, "loss": 0.0242, "step": 151820 }, { "epoch": 36.45, "learning_rate": 7.312386184435661e-05, "loss": 0.0255, "step": 151830 }, { "epoch": 36.45, "learning_rate": 7.312067915917077e-05, "loss": 0.0114, "step": 151840 }, { "epoch": 36.45, "learning_rate": 7.31174963548208e-05, "loss": 0.0116, "step": 151850 }, { "epoch": 36.46, "learning_rate": 7.311431343132303e-05, "loss": 0.018, "step": 151860 }, { "epoch": 36.46, "learning_rate": 7.31111303886939e-05, "loss": 0.0159, "step": 151870 }, { "epoch": 36.46, "learning_rate": 7.310794722694982e-05, "loss": 0.0112, "step": 151880 }, { "epoch": 36.46, "learning_rate": 7.310476394610718e-05, "loss": 0.0152, "step": 151890 }, { "epoch": 36.46, "learning_rate": 7.310158054618239e-05, "loss": 0.0265, "step": 151900 }, { "epoch": 36.47, "learning_rate": 7.309839702719185e-05, "loss": 0.0214, "step": 151910 }, { "epoch": 36.47, "learning_rate": 7.3095213389152e-05, "loss": 0.0196, "step": 151920 }, { "epoch": 36.47, "learning_rate": 7.309202963207922e-05, "loss": 0.0121, "step": 151930 }, { "epoch": 36.47, "learning_rate": 7.308884575598993e-05, "loss": 0.0152, "step": 151940 }, { "epoch": 36.48, "learning_rate": 7.308566176090052e-05, "loss": 0.0284, "step": 151950 }, { "epoch": 36.48, "learning_rate": 7.308247764682743e-05, "loss": 0.0119, "step": 151960 }, { "epoch": 36.48, "learning_rate": 7.307929341378705e-05, "loss": 0.0243, "step": 151970 }, { "epoch": 36.48, "learning_rate": 7.307610906179581e-05, "loss": 0.0113, "step": 151980 }, { "epoch": 36.48, "learning_rate": 7.30729245908701e-05, "loss": 0.0177, "step": 151990 }, { "epoch": 36.49, "learning_rate": 7.306974000102636e-05, "loss": 0.0265, "step": 152000 }, { "epoch": 36.49, "learning_rate": 7.306655529228098e-05, "loss": 0.0145, "step": 152010 }, { "epoch": 36.49, "learning_rate": 7.306337046465037e-05, "loss": 0.0243, "step": 152020 }, { "epoch": 36.49, "learning_rate": 7.306018551815097e-05, "loss": 0.0111, "step": 152030 }, { "epoch": 36.5, "learning_rate": 7.305700045279918e-05, "loss": 0.0126, "step": 152040 }, { "epoch": 36.5, "learning_rate": 7.30538152686114e-05, "loss": 0.0255, "step": 152050 }, { "epoch": 36.5, "learning_rate": 7.305062996560408e-05, "loss": 0.0239, "step": 152060 }, { "epoch": 36.5, "learning_rate": 7.30474445437936e-05, "loss": 0.0142, "step": 152070 }, { "epoch": 36.51, "learning_rate": 7.304425900319643e-05, "loss": 0.0232, "step": 152080 }, { "epoch": 36.51, "learning_rate": 7.304107334382893e-05, "loss": 0.0186, "step": 152090 }, { "epoch": 36.51, "learning_rate": 7.303788756570755e-05, "loss": 0.0173, "step": 152100 }, { "epoch": 36.51, "learning_rate": 7.303470166884872e-05, "loss": 0.0238, "step": 152110 }, { "epoch": 36.51, "learning_rate": 7.303151565326882e-05, "loss": 0.0237, "step": 152120 }, { "epoch": 36.52, "learning_rate": 7.302832951898432e-05, "loss": 0.0109, "step": 152130 }, { "epoch": 36.52, "learning_rate": 7.30251432660116e-05, "loss": 0.0157, "step": 152140 }, { "epoch": 36.52, "learning_rate": 7.302195689436713e-05, "loss": 0.0193, "step": 152150 }, { "epoch": 36.52, "learning_rate": 7.301877040406727e-05, "loss": 0.0199, "step": 152160 }, { "epoch": 36.53, "learning_rate": 7.301558379512848e-05, "loss": 0.0175, "step": 152170 }, { "epoch": 36.53, "learning_rate": 7.301239706756718e-05, "loss": 0.014, "step": 152180 }, { "epoch": 36.53, "learning_rate": 7.300921022139981e-05, "loss": 0.0144, "step": 152190 }, { "epoch": 36.53, "learning_rate": 7.300602325664276e-05, "loss": 0.0221, "step": 152200 }, { "epoch": 36.54, "learning_rate": 7.300283617331248e-05, "loss": 0.0205, "step": 152210 }, { "epoch": 36.54, "learning_rate": 7.29996489714254e-05, "loss": 0.0219, "step": 152220 }, { "epoch": 36.54, "learning_rate": 7.299646165099791e-05, "loss": 0.025, "step": 152230 }, { "epoch": 36.54, "learning_rate": 7.299327421204647e-05, "loss": 0.0286, "step": 152240 }, { "epoch": 36.54, "learning_rate": 7.299008665458751e-05, "loss": 0.0201, "step": 152250 }, { "epoch": 36.55, "learning_rate": 7.298689897863746e-05, "loss": 0.0116, "step": 152260 }, { "epoch": 36.55, "learning_rate": 7.298371118421272e-05, "loss": 0.0174, "step": 152270 }, { "epoch": 36.55, "learning_rate": 7.298052327132976e-05, "loss": 0.0139, "step": 152280 }, { "epoch": 36.55, "learning_rate": 7.297733524000499e-05, "loss": 0.0304, "step": 152290 }, { "epoch": 36.56, "learning_rate": 7.297414709025484e-05, "loss": 0.0296, "step": 152300 }, { "epoch": 36.56, "learning_rate": 7.297095882209574e-05, "loss": 0.0155, "step": 152310 }, { "epoch": 36.56, "learning_rate": 7.296777043554412e-05, "loss": 0.0187, "step": 152320 }, { "epoch": 36.56, "learning_rate": 7.296458193061642e-05, "loss": 0.033, "step": 152330 }, { "epoch": 36.56, "learning_rate": 7.296139330732908e-05, "loss": 0.0115, "step": 152340 }, { "epoch": 36.57, "learning_rate": 7.295820456569853e-05, "loss": 0.0315, "step": 152350 }, { "epoch": 36.57, "learning_rate": 7.29550157057412e-05, "loss": 0.0303, "step": 152360 }, { "epoch": 36.57, "learning_rate": 7.295182672747353e-05, "loss": 0.0219, "step": 152370 }, { "epoch": 36.57, "learning_rate": 7.294863763091196e-05, "loss": 0.0092, "step": 152380 }, { "epoch": 36.58, "learning_rate": 7.29454484160729e-05, "loss": 0.0208, "step": 152390 }, { "epoch": 36.58, "learning_rate": 7.29422590829728e-05, "loss": 0.0259, "step": 152400 }, { "epoch": 36.58, "learning_rate": 7.293906963162811e-05, "loss": 0.0187, "step": 152410 }, { "epoch": 36.58, "learning_rate": 7.293588006205529e-05, "loss": 0.0246, "step": 152420 }, { "epoch": 36.59, "learning_rate": 7.293269037427073e-05, "loss": 0.0163, "step": 152430 }, { "epoch": 36.59, "learning_rate": 7.292950056829091e-05, "loss": 0.0221, "step": 152440 }, { "epoch": 36.59, "learning_rate": 7.292631064413223e-05, "loss": 0.0413, "step": 152450 }, { "epoch": 36.59, "learning_rate": 7.292312060181116e-05, "loss": 0.0275, "step": 152460 }, { "epoch": 36.59, "learning_rate": 7.291993044134415e-05, "loss": 0.0193, "step": 152470 }, { "epoch": 36.6, "learning_rate": 7.291674016274761e-05, "loss": 0.0188, "step": 152480 }, { "epoch": 36.6, "learning_rate": 7.2913549766038e-05, "loss": 0.0153, "step": 152490 }, { "epoch": 36.6, "learning_rate": 7.291035925123177e-05, "loss": 0.0143, "step": 152500 }, { "epoch": 36.6, "learning_rate": 7.290716861834537e-05, "loss": 0.0314, "step": 152510 }, { "epoch": 36.61, "learning_rate": 7.290397786739522e-05, "loss": 0.0272, "step": 152520 }, { "epoch": 36.61, "learning_rate": 7.290078699839776e-05, "loss": 0.0243, "step": 152530 }, { "epoch": 36.61, "learning_rate": 7.289759601136947e-05, "loss": 0.0175, "step": 152540 }, { "epoch": 36.61, "learning_rate": 7.289440490632677e-05, "loss": 0.0202, "step": 152550 }, { "epoch": 36.62, "learning_rate": 7.28912136832861e-05, "loss": 0.0166, "step": 152560 }, { "epoch": 36.62, "learning_rate": 7.288802234226395e-05, "loss": 0.0334, "step": 152570 }, { "epoch": 36.62, "learning_rate": 7.288483088327675e-05, "loss": 0.0151, "step": 152580 }, { "epoch": 36.62, "learning_rate": 7.288163930634092e-05, "loss": 0.0204, "step": 152590 }, { "epoch": 36.62, "learning_rate": 7.287844761147293e-05, "loss": 0.0229, "step": 152600 }, { "epoch": 36.63, "learning_rate": 7.287525579868923e-05, "loss": 0.0197, "step": 152610 }, { "epoch": 36.63, "learning_rate": 7.287206386800629e-05, "loss": 0.0331, "step": 152620 }, { "epoch": 36.63, "learning_rate": 7.286887181944053e-05, "loss": 0.016, "step": 152630 }, { "epoch": 36.63, "learning_rate": 7.28656796530084e-05, "loss": 0.0134, "step": 152640 }, { "epoch": 36.64, "learning_rate": 7.286248736872637e-05, "loss": 0.0217, "step": 152650 }, { "epoch": 36.64, "learning_rate": 7.28592949666109e-05, "loss": 0.016, "step": 152660 }, { "epoch": 36.64, "learning_rate": 7.285610244667844e-05, "loss": 0.0164, "step": 152670 }, { "epoch": 36.64, "learning_rate": 7.285290980894541e-05, "loss": 0.02, "step": 152680 }, { "epoch": 36.64, "learning_rate": 7.284971705342832e-05, "loss": 0.0212, "step": 152690 }, { "epoch": 36.65, "learning_rate": 7.284652418014357e-05, "loss": 0.0164, "step": 152700 }, { "epoch": 36.65, "learning_rate": 7.284333118910765e-05, "loss": 0.0263, "step": 152710 }, { "epoch": 36.65, "learning_rate": 7.284013808033703e-05, "loss": 0.0217, "step": 152720 }, { "epoch": 36.65, "learning_rate": 7.283694485384813e-05, "loss": 0.014, "step": 152730 }, { "epoch": 36.66, "learning_rate": 7.283375150965743e-05, "loss": 0.0158, "step": 152740 }, { "epoch": 36.66, "learning_rate": 7.283055804778138e-05, "loss": 0.0268, "step": 152750 }, { "epoch": 36.66, "learning_rate": 7.282736446823646e-05, "loss": 0.0212, "step": 152760 }, { "epoch": 36.66, "learning_rate": 7.28241707710391e-05, "loss": 0.0499, "step": 152770 }, { "epoch": 36.67, "learning_rate": 7.282097695620576e-05, "loss": 0.0234, "step": 152780 }, { "epoch": 36.67, "learning_rate": 7.281778302375292e-05, "loss": 0.0308, "step": 152790 }, { "epoch": 36.67, "learning_rate": 7.281458897369707e-05, "loss": 0.0216, "step": 152800 }, { "epoch": 36.67, "learning_rate": 7.281139480605461e-05, "loss": 0.0335, "step": 152810 }, { "epoch": 36.67, "learning_rate": 7.280820052084202e-05, "loss": 0.0174, "step": 152820 }, { "epoch": 36.68, "learning_rate": 7.280500611807579e-05, "loss": 0.0263, "step": 152830 }, { "epoch": 36.68, "learning_rate": 7.280181159777236e-05, "loss": 0.0092, "step": 152840 }, { "epoch": 36.68, "learning_rate": 7.279861695994821e-05, "loss": 0.0186, "step": 152850 }, { "epoch": 36.68, "learning_rate": 7.279542220461977e-05, "loss": 0.0238, "step": 152860 }, { "epoch": 36.69, "learning_rate": 7.279222733180356e-05, "loss": 0.0188, "step": 152870 }, { "epoch": 36.69, "learning_rate": 7.278903234151602e-05, "loss": 0.0225, "step": 152880 }, { "epoch": 36.69, "learning_rate": 7.278583723377362e-05, "loss": 0.0317, "step": 152890 }, { "epoch": 36.69, "learning_rate": 7.278264200859281e-05, "loss": 0.0124, "step": 152900 }, { "epoch": 36.7, "learning_rate": 7.277944666599009e-05, "loss": 0.0178, "step": 152910 }, { "epoch": 36.7, "learning_rate": 7.277625120598189e-05, "loss": 0.0249, "step": 152920 }, { "epoch": 36.7, "learning_rate": 7.277305562858471e-05, "loss": 0.0155, "step": 152930 }, { "epoch": 36.7, "learning_rate": 7.276985993381503e-05, "loss": 0.0248, "step": 152940 }, { "epoch": 36.7, "learning_rate": 7.276666412168927e-05, "loss": 0.0112, "step": 152950 }, { "epoch": 36.71, "learning_rate": 7.276346819222394e-05, "loss": 0.0122, "step": 152960 }, { "epoch": 36.71, "learning_rate": 7.276027214543553e-05, "loss": 0.0244, "step": 152970 }, { "epoch": 36.71, "learning_rate": 7.275707598134046e-05, "loss": 0.0241, "step": 152980 }, { "epoch": 36.71, "learning_rate": 7.275387969995524e-05, "loss": 0.0177, "step": 152990 }, { "epoch": 36.72, "learning_rate": 7.275068330129633e-05, "loss": 0.0292, "step": 153000 }, { "epoch": 36.72, "learning_rate": 7.274748678538022e-05, "loss": 0.017, "step": 153010 }, { "epoch": 36.72, "learning_rate": 7.274429015222335e-05, "loss": 0.0268, "step": 153020 }, { "epoch": 36.72, "learning_rate": 7.274109340184224e-05, "loss": 0.0319, "step": 153030 }, { "epoch": 36.72, "learning_rate": 7.273789653425334e-05, "loss": 0.0223, "step": 153040 }, { "epoch": 36.73, "learning_rate": 7.273469954947312e-05, "loss": 0.0309, "step": 153050 }, { "epoch": 36.73, "learning_rate": 7.273150244751807e-05, "loss": 0.011, "step": 153060 }, { "epoch": 36.73, "learning_rate": 7.272830522840468e-05, "loss": 0.0244, "step": 153070 }, { "epoch": 36.73, "learning_rate": 7.27251078921494e-05, "loss": 0.0217, "step": 153080 }, { "epoch": 36.74, "learning_rate": 7.272191043876875e-05, "loss": 0.0093, "step": 153090 }, { "epoch": 36.74, "learning_rate": 7.271871286827915e-05, "loss": 0.0213, "step": 153100 }, { "epoch": 36.74, "learning_rate": 7.271551518069713e-05, "loss": 0.0211, "step": 153110 }, { "epoch": 36.74, "learning_rate": 7.271231737603916e-05, "loss": 0.014, "step": 153120 }, { "epoch": 36.75, "learning_rate": 7.27091194543217e-05, "loss": 0.0118, "step": 153130 }, { "epoch": 36.75, "learning_rate": 7.270592141556127e-05, "loss": 0.027, "step": 153140 }, { "epoch": 36.75, "learning_rate": 7.270272325977432e-05, "loss": 0.0196, "step": 153150 }, { "epoch": 36.75, "learning_rate": 7.269952498697734e-05, "loss": 0.0201, "step": 153160 }, { "epoch": 36.75, "learning_rate": 7.269632659718683e-05, "loss": 0.0154, "step": 153170 }, { "epoch": 36.76, "learning_rate": 7.269312809041926e-05, "loss": 0.0148, "step": 153180 }, { "epoch": 36.76, "learning_rate": 7.268992946669111e-05, "loss": 0.014, "step": 153190 }, { "epoch": 36.76, "learning_rate": 7.268673072601888e-05, "loss": 0.0254, "step": 153200 }, { "epoch": 36.76, "learning_rate": 7.268353186841904e-05, "loss": 0.0332, "step": 153210 }, { "epoch": 36.77, "learning_rate": 7.268033289390809e-05, "loss": 0.0091, "step": 153220 }, { "epoch": 36.77, "learning_rate": 7.267713380250253e-05, "loss": 0.0281, "step": 153230 }, { "epoch": 36.77, "learning_rate": 7.267393459421883e-05, "loss": 0.0201, "step": 153240 }, { "epoch": 36.77, "learning_rate": 7.267073526907347e-05, "loss": 0.0201, "step": 153250 }, { "epoch": 36.78, "learning_rate": 7.266753582708297e-05, "loss": 0.0137, "step": 153260 }, { "epoch": 36.78, "learning_rate": 7.266433626826377e-05, "loss": 0.0194, "step": 153270 }, { "epoch": 36.78, "learning_rate": 7.266113659263242e-05, "loss": 0.0129, "step": 153280 }, { "epoch": 36.78, "learning_rate": 7.265793680020537e-05, "loss": 0.0209, "step": 153290 }, { "epoch": 36.78, "learning_rate": 7.265473689099912e-05, "loss": 0.026, "step": 153300 }, { "epoch": 36.79, "learning_rate": 7.265153686503017e-05, "loss": 0.0209, "step": 153310 }, { "epoch": 36.79, "learning_rate": 7.264833672231502e-05, "loss": 0.0129, "step": 153320 }, { "epoch": 36.79, "learning_rate": 7.264513646287013e-05, "loss": 0.0174, "step": 153330 }, { "epoch": 36.79, "learning_rate": 7.264193608671204e-05, "loss": 0.0268, "step": 153340 }, { "epoch": 36.8, "learning_rate": 7.263873559385721e-05, "loss": 0.0144, "step": 153350 }, { "epoch": 36.8, "learning_rate": 7.263553498432215e-05, "loss": 0.0173, "step": 153360 }, { "epoch": 36.8, "learning_rate": 7.263233425812337e-05, "loss": 0.0159, "step": 153370 }, { "epoch": 36.8, "learning_rate": 7.262913341527733e-05, "loss": 0.015, "step": 153380 }, { "epoch": 36.8, "learning_rate": 7.262593245580055e-05, "loss": 0.0151, "step": 153390 }, { "epoch": 36.81, "learning_rate": 7.262273137970953e-05, "loss": 0.0303, "step": 153400 }, { "epoch": 36.81, "learning_rate": 7.261953018702076e-05, "loss": 0.0134, "step": 153410 }, { "epoch": 36.81, "learning_rate": 7.261632887775074e-05, "loss": 0.0159, "step": 153420 }, { "epoch": 36.81, "learning_rate": 7.261312745191597e-05, "loss": 0.0241, "step": 153430 }, { "epoch": 36.82, "learning_rate": 7.260992590953296e-05, "loss": 0.0114, "step": 153440 }, { "epoch": 36.82, "learning_rate": 7.26067242506182e-05, "loss": 0.0211, "step": 153450 }, { "epoch": 36.82, "learning_rate": 7.260352247518819e-05, "loss": 0.0129, "step": 153460 }, { "epoch": 36.82, "learning_rate": 7.260032058325945e-05, "loss": 0.0225, "step": 153470 }, { "epoch": 36.83, "learning_rate": 7.259711857484845e-05, "loss": 0.009, "step": 153480 }, { "epoch": 36.83, "learning_rate": 7.259391644997173e-05, "loss": 0.0171, "step": 153490 }, { "epoch": 36.83, "learning_rate": 7.259071420864576e-05, "loss": 0.0144, "step": 153500 }, { "epoch": 36.83, "learning_rate": 7.258751185088708e-05, "loss": 0.0162, "step": 153510 }, { "epoch": 36.83, "learning_rate": 7.258430937671215e-05, "loss": 0.0146, "step": 153520 }, { "epoch": 36.84, "learning_rate": 7.258110678613752e-05, "loss": 0.018, "step": 153530 }, { "epoch": 36.84, "learning_rate": 7.257790407917968e-05, "loss": 0.0299, "step": 153540 }, { "epoch": 36.84, "learning_rate": 7.257470125585512e-05, "loss": 0.0237, "step": 153550 }, { "epoch": 36.84, "learning_rate": 7.257149831618036e-05, "loss": 0.011, "step": 153560 }, { "epoch": 36.85, "learning_rate": 7.25682952601719e-05, "loss": 0.0145, "step": 153570 }, { "epoch": 36.85, "learning_rate": 7.256509208784628e-05, "loss": 0.0209, "step": 153580 }, { "epoch": 36.85, "learning_rate": 7.256188879921998e-05, "loss": 0.013, "step": 153590 }, { "epoch": 36.85, "learning_rate": 7.255868539430951e-05, "loss": 0.0267, "step": 153600 }, { "epoch": 36.86, "learning_rate": 7.255548187313139e-05, "loss": 0.0124, "step": 153610 }, { "epoch": 36.86, "learning_rate": 7.255227823570213e-05, "loss": 0.0169, "step": 153620 }, { "epoch": 36.86, "learning_rate": 7.254907448203824e-05, "loss": 0.0255, "step": 153630 }, { "epoch": 36.86, "learning_rate": 7.254587061215622e-05, "loss": 0.0068, "step": 153640 }, { "epoch": 36.86, "learning_rate": 7.25426666260726e-05, "loss": 0.0085, "step": 153650 }, { "epoch": 36.87, "learning_rate": 7.253946252380392e-05, "loss": 0.0098, "step": 153660 }, { "epoch": 36.87, "learning_rate": 7.253625830536664e-05, "loss": 0.0167, "step": 153670 }, { "epoch": 36.87, "learning_rate": 7.253305397077727e-05, "loss": 0.0221, "step": 153680 }, { "epoch": 36.87, "learning_rate": 7.252984952005238e-05, "loss": 0.0134, "step": 153690 }, { "epoch": 36.88, "learning_rate": 7.252664495320845e-05, "loss": 0.0212, "step": 153700 }, { "epoch": 36.88, "learning_rate": 7.2523440270262e-05, "loss": 0.0249, "step": 153710 }, { "epoch": 36.88, "learning_rate": 7.252023547122954e-05, "loss": 0.0157, "step": 153720 }, { "epoch": 36.88, "learning_rate": 7.251703055612764e-05, "loss": 0.0127, "step": 153730 }, { "epoch": 36.88, "learning_rate": 7.251382552497274e-05, "loss": 0.0153, "step": 153740 }, { "epoch": 36.89, "learning_rate": 7.25106203777814e-05, "loss": 0.0198, "step": 153750 }, { "epoch": 36.89, "learning_rate": 7.250741511457013e-05, "loss": 0.0157, "step": 153760 }, { "epoch": 36.89, "learning_rate": 7.250420973535546e-05, "loss": 0.0107, "step": 153770 }, { "epoch": 36.89, "learning_rate": 7.250100424015391e-05, "loss": 0.0254, "step": 153780 }, { "epoch": 36.9, "learning_rate": 7.249779862898199e-05, "loss": 0.0167, "step": 153790 }, { "epoch": 36.9, "learning_rate": 7.249459290185623e-05, "loss": 0.0106, "step": 153800 }, { "epoch": 36.9, "learning_rate": 7.249138705879316e-05, "loss": 0.0267, "step": 153810 }, { "epoch": 36.9, "learning_rate": 7.248818109980928e-05, "loss": 0.017, "step": 153820 }, { "epoch": 36.91, "learning_rate": 7.248497502492113e-05, "loss": 0.0147, "step": 153830 }, { "epoch": 36.91, "learning_rate": 7.248176883414523e-05, "loss": 0.009, "step": 153840 }, { "epoch": 36.91, "learning_rate": 7.247856252749811e-05, "loss": 0.0245, "step": 153850 }, { "epoch": 36.91, "learning_rate": 7.24753561049963e-05, "loss": 0.0169, "step": 153860 }, { "epoch": 36.91, "learning_rate": 7.24721495666563e-05, "loss": 0.0232, "step": 153870 }, { "epoch": 36.92, "learning_rate": 7.246894291249466e-05, "loss": 0.0229, "step": 153880 }, { "epoch": 36.92, "learning_rate": 7.24657361425279e-05, "loss": 0.0207, "step": 153890 }, { "epoch": 36.92, "learning_rate": 7.246252925677252e-05, "loss": 0.0215, "step": 153900 }, { "epoch": 36.92, "learning_rate": 7.245932225524512e-05, "loss": 0.0269, "step": 153910 }, { "epoch": 36.93, "learning_rate": 7.245611513796217e-05, "loss": 0.0303, "step": 153920 }, { "epoch": 36.93, "learning_rate": 7.245290790494021e-05, "loss": 0.02, "step": 153930 }, { "epoch": 36.93, "learning_rate": 7.244970055619577e-05, "loss": 0.0136, "step": 153940 }, { "epoch": 36.93, "learning_rate": 7.24464930917454e-05, "loss": 0.0149, "step": 153950 }, { "epoch": 36.94, "learning_rate": 7.244328551160562e-05, "loss": 0.0296, "step": 153960 }, { "epoch": 36.94, "learning_rate": 7.244007781579294e-05, "loss": 0.0223, "step": 153970 }, { "epoch": 36.94, "learning_rate": 7.243687000432392e-05, "loss": 0.02, "step": 153980 }, { "epoch": 36.94, "learning_rate": 7.243366207721509e-05, "loss": 0.0097, "step": 153990 }, { "epoch": 36.94, "learning_rate": 7.243045403448298e-05, "loss": 0.0246, "step": 154000 }, { "epoch": 36.95, "learning_rate": 7.242724587614411e-05, "loss": 0.0091, "step": 154010 }, { "epoch": 36.95, "learning_rate": 7.242403760221504e-05, "loss": 0.0146, "step": 154020 }, { "epoch": 36.95, "learning_rate": 7.242082921271228e-05, "loss": 0.0159, "step": 154030 }, { "epoch": 37.0, "learning_rate": 7.241762070765239e-05, "loss": 0.0147, "step": 154040 }, { "epoch": 37.0, "learning_rate": 7.241441208705189e-05, "loss": 0.01, "step": 154050 }, { "epoch": 37.01, "learning_rate": 7.241120335092732e-05, "loss": 0.0163, "step": 154060 }, { "epoch": 37.01, "learning_rate": 7.240799449929521e-05, "loss": 0.025, "step": 154070 }, { "epoch": 37.01, "learning_rate": 7.240478553217213e-05, "loss": 0.0103, "step": 154080 }, { "epoch": 37.01, "learning_rate": 7.24015764495746e-05, "loss": 0.0136, "step": 154090 }, { "epoch": 37.02, "learning_rate": 7.239836725151913e-05, "loss": 0.0125, "step": 154100 }, { "epoch": 37.02, "learning_rate": 7.239515793802232e-05, "loss": 0.0241, "step": 154110 }, { "epoch": 37.02, "learning_rate": 7.239194850910065e-05, "loss": 0.0144, "step": 154120 }, { "epoch": 37.02, "learning_rate": 7.238873896477072e-05, "loss": 0.0173, "step": 154130 }, { "epoch": 37.02, "learning_rate": 7.238552930504903e-05, "loss": 0.0072, "step": 154140 }, { "epoch": 37.03, "learning_rate": 7.238231952995213e-05, "loss": 0.0101, "step": 154150 }, { "epoch": 37.03, "learning_rate": 7.237910963949658e-05, "loss": 0.0154, "step": 154160 }, { "epoch": 37.03, "learning_rate": 7.23758996336989e-05, "loss": 0.0104, "step": 154170 }, { "epoch": 37.03, "learning_rate": 7.237268951257565e-05, "loss": 0.0248, "step": 154180 }, { "epoch": 37.04, "learning_rate": 7.236947927614337e-05, "loss": 0.0118, "step": 154190 }, { "epoch": 37.04, "learning_rate": 7.23662689244186e-05, "loss": 0.0161, "step": 154200 }, { "epoch": 37.04, "learning_rate": 7.236305845741789e-05, "loss": 0.014, "step": 154210 }, { "epoch": 37.04, "learning_rate": 7.235984787515781e-05, "loss": 0.0144, "step": 154220 }, { "epoch": 37.05, "learning_rate": 7.235663717765487e-05, "loss": 0.0142, "step": 154230 }, { "epoch": 37.05, "learning_rate": 7.235342636492564e-05, "loss": 0.0145, "step": 154240 }, { "epoch": 37.05, "learning_rate": 7.235021543698667e-05, "loss": 0.0312, "step": 154250 }, { "epoch": 37.05, "learning_rate": 7.23470043938545e-05, "loss": 0.03, "step": 154260 }, { "epoch": 37.05, "learning_rate": 7.234379323554567e-05, "loss": 0.0165, "step": 154270 }, { "epoch": 37.06, "learning_rate": 7.234058196207676e-05, "loss": 0.0186, "step": 154280 }, { "epoch": 37.06, "learning_rate": 7.23373705734643e-05, "loss": 0.0144, "step": 154290 }, { "epoch": 37.06, "learning_rate": 7.233415906972486e-05, "loss": 0.0173, "step": 154300 }, { "epoch": 37.06, "learning_rate": 7.233094745087495e-05, "loss": 0.0242, "step": 154310 }, { "epoch": 37.07, "learning_rate": 7.232773571693117e-05, "loss": 0.0077, "step": 154320 }, { "epoch": 37.07, "learning_rate": 7.232452386791004e-05, "loss": 0.0326, "step": 154330 }, { "epoch": 37.07, "learning_rate": 7.232131190382812e-05, "loss": 0.0445, "step": 154340 }, { "epoch": 37.07, "learning_rate": 7.231809982470199e-05, "loss": 0.0162, "step": 154350 }, { "epoch": 37.08, "learning_rate": 7.231488763054818e-05, "loss": 0.0133, "step": 154360 }, { "epoch": 37.08, "learning_rate": 7.231167532138324e-05, "loss": 0.0231, "step": 154370 }, { "epoch": 37.08, "learning_rate": 7.230846289722377e-05, "loss": 0.0239, "step": 154380 }, { "epoch": 37.08, "learning_rate": 7.230525035808628e-05, "loss": 0.0197, "step": 154390 }, { "epoch": 37.08, "learning_rate": 7.230203770398734e-05, "loss": 0.0186, "step": 154400 }, { "epoch": 37.09, "learning_rate": 7.22988249349435e-05, "loss": 0.0145, "step": 154410 }, { "epoch": 37.09, "learning_rate": 7.229561205097134e-05, "loss": 0.0135, "step": 154420 }, { "epoch": 37.09, "learning_rate": 7.229239905208741e-05, "loss": 0.02, "step": 154430 }, { "epoch": 37.09, "learning_rate": 7.228918593830827e-05, "loss": 0.0133, "step": 154440 }, { "epoch": 37.1, "learning_rate": 7.22859727096505e-05, "loss": 0.0108, "step": 154450 }, { "epoch": 37.1, "learning_rate": 7.22827593661306e-05, "loss": 0.0231, "step": 154460 }, { "epoch": 37.1, "learning_rate": 7.22795459077652e-05, "loss": 0.0252, "step": 154470 }, { "epoch": 37.1, "learning_rate": 7.227633233457083e-05, "loss": 0.019, "step": 154480 }, { "epoch": 37.1, "learning_rate": 7.227311864656405e-05, "loss": 0.0123, "step": 154490 }, { "epoch": 37.11, "learning_rate": 7.226990484376144e-05, "loss": 0.0158, "step": 154500 }, { "epoch": 37.11, "learning_rate": 7.226669092617954e-05, "loss": 0.0173, "step": 154510 }, { "epoch": 37.11, "learning_rate": 7.226347689383494e-05, "loss": 0.0172, "step": 154520 }, { "epoch": 37.11, "learning_rate": 7.226026274674418e-05, "loss": 0.0105, "step": 154530 }, { "epoch": 37.12, "learning_rate": 7.225704848492385e-05, "loss": 0.0169, "step": 154540 }, { "epoch": 37.12, "learning_rate": 7.225383410839051e-05, "loss": 0.0223, "step": 154550 }, { "epoch": 37.12, "learning_rate": 7.225061961716072e-05, "loss": 0.019, "step": 154560 }, { "epoch": 37.12, "learning_rate": 7.224740501125105e-05, "loss": 0.017, "step": 154570 }, { "epoch": 37.13, "learning_rate": 7.224419029067807e-05, "loss": 0.0195, "step": 154580 }, { "epoch": 37.13, "learning_rate": 7.224097545545835e-05, "loss": 0.0243, "step": 154590 }, { "epoch": 37.13, "learning_rate": 7.223776050560845e-05, "loss": 0.0243, "step": 154600 }, { "epoch": 37.13, "learning_rate": 7.223454544114494e-05, "loss": 0.0095, "step": 154610 }, { "epoch": 37.13, "learning_rate": 7.223133026208442e-05, "loss": 0.0165, "step": 154620 }, { "epoch": 37.14, "learning_rate": 7.222811496844342e-05, "loss": 0.0215, "step": 154630 }, { "epoch": 37.14, "learning_rate": 7.222489956023852e-05, "loss": 0.0277, "step": 154640 }, { "epoch": 37.14, "learning_rate": 7.222168403748632e-05, "loss": 0.012, "step": 154650 }, { "epoch": 37.14, "learning_rate": 7.221846840020337e-05, "loss": 0.015, "step": 154660 }, { "epoch": 37.15, "learning_rate": 7.221525264840625e-05, "loss": 0.018, "step": 154670 }, { "epoch": 37.15, "learning_rate": 7.221203678211153e-05, "loss": 0.0079, "step": 154680 }, { "epoch": 37.15, "learning_rate": 7.220882080133579e-05, "loss": 0.0136, "step": 154690 }, { "epoch": 37.15, "learning_rate": 7.220560470609559e-05, "loss": 0.0238, "step": 154700 }, { "epoch": 37.16, "learning_rate": 7.220238849640753e-05, "loss": 0.0165, "step": 154710 }, { "epoch": 37.16, "learning_rate": 7.219917217228816e-05, "loss": 0.0171, "step": 154720 }, { "epoch": 37.16, "learning_rate": 7.219595573375408e-05, "loss": 0.0092, "step": 154730 }, { "epoch": 37.16, "learning_rate": 7.219273918082187e-05, "loss": 0.0109, "step": 154740 }, { "epoch": 37.16, "learning_rate": 7.21895225135081e-05, "loss": 0.0165, "step": 154750 }, { "epoch": 37.17, "learning_rate": 7.218630573182933e-05, "loss": 0.0121, "step": 154760 }, { "epoch": 37.17, "learning_rate": 7.218308883580215e-05, "loss": 0.0146, "step": 154770 }, { "epoch": 37.17, "learning_rate": 7.217987182544315e-05, "loss": 0.0161, "step": 154780 }, { "epoch": 37.17, "learning_rate": 7.217665470076891e-05, "loss": 0.0189, "step": 154790 }, { "epoch": 37.18, "learning_rate": 7.217343746179601e-05, "loss": 0.0168, "step": 154800 }, { "epoch": 37.18, "learning_rate": 7.217022010854102e-05, "loss": 0.0082, "step": 154810 }, { "epoch": 37.18, "learning_rate": 7.216700264102052e-05, "loss": 0.0149, "step": 154820 }, { "epoch": 37.18, "learning_rate": 7.216378505925112e-05, "loss": 0.0117, "step": 154830 }, { "epoch": 37.18, "learning_rate": 7.216056736324939e-05, "loss": 0.0138, "step": 154840 }, { "epoch": 37.19, "learning_rate": 7.21573495530319e-05, "loss": 0.0201, "step": 154850 }, { "epoch": 37.19, "learning_rate": 7.215413162861523e-05, "loss": 0.0098, "step": 154860 }, { "epoch": 37.19, "learning_rate": 7.2150913590016e-05, "loss": 0.0134, "step": 154870 }, { "epoch": 37.19, "learning_rate": 7.21476954372508e-05, "loss": 0.022, "step": 154880 }, { "epoch": 37.2, "learning_rate": 7.214447717033615e-05, "loss": 0.0169, "step": 154890 }, { "epoch": 37.2, "learning_rate": 7.21412587892887e-05, "loss": 0.0169, "step": 154900 }, { "epoch": 37.2, "learning_rate": 7.2138040294125e-05, "loss": 0.0251, "step": 154910 }, { "epoch": 37.2, "learning_rate": 7.213482168486167e-05, "loss": 0.02, "step": 154920 }, { "epoch": 37.21, "learning_rate": 7.213160296151529e-05, "loss": 0.0259, "step": 154930 }, { "epoch": 37.21, "learning_rate": 7.212838412410244e-05, "loss": 0.0198, "step": 154940 }, { "epoch": 37.21, "learning_rate": 7.21251651726397e-05, "loss": 0.0109, "step": 154950 }, { "epoch": 37.21, "learning_rate": 7.212194610714369e-05, "loss": 0.0146, "step": 154960 }, { "epoch": 37.21, "learning_rate": 7.211872692763098e-05, "loss": 0.0121, "step": 154970 }, { "epoch": 37.22, "learning_rate": 7.211550763411817e-05, "loss": 0.0256, "step": 154980 }, { "epoch": 37.22, "learning_rate": 7.211228822662184e-05, "loss": 0.0155, "step": 154990 }, { "epoch": 37.22, "learning_rate": 7.210906870515858e-05, "loss": 0.0167, "step": 155000 }, { "epoch": 37.22, "learning_rate": 7.210584906974502e-05, "loss": 0.0143, "step": 155010 }, { "epoch": 37.23, "learning_rate": 7.210262932039774e-05, "loss": 0.0156, "step": 155020 }, { "epoch": 37.23, "learning_rate": 7.209940945713328e-05, "loss": 0.0212, "step": 155030 }, { "epoch": 37.23, "learning_rate": 7.20961894799683e-05, "loss": 0.023, "step": 155040 }, { "epoch": 37.23, "learning_rate": 7.209296938891938e-05, "loss": 0.0124, "step": 155050 }, { "epoch": 37.24, "learning_rate": 7.20897491840031e-05, "loss": 0.0173, "step": 155060 }, { "epoch": 37.24, "learning_rate": 7.208652886523608e-05, "loss": 0.0211, "step": 155070 }, { "epoch": 37.24, "learning_rate": 7.208330843263491e-05, "loss": 0.0161, "step": 155080 }, { "epoch": 37.24, "learning_rate": 7.208008788621617e-05, "loss": 0.0109, "step": 155090 }, { "epoch": 37.24, "learning_rate": 7.207686722599647e-05, "loss": 0.0139, "step": 155100 }, { "epoch": 37.25, "learning_rate": 7.207364645199243e-05, "loss": 0.0123, "step": 155110 }, { "epoch": 37.25, "learning_rate": 7.207042556422062e-05, "loss": 0.0143, "step": 155120 }, { "epoch": 37.25, "learning_rate": 7.206720456269765e-05, "loss": 0.0185, "step": 155130 }, { "epoch": 37.25, "learning_rate": 7.206398344744012e-05, "loss": 0.0117, "step": 155140 }, { "epoch": 37.26, "learning_rate": 7.206076221846464e-05, "loss": 0.0123, "step": 155150 }, { "epoch": 37.26, "learning_rate": 7.205754087578781e-05, "loss": 0.0196, "step": 155160 }, { "epoch": 37.26, "learning_rate": 7.205431941942624e-05, "loss": 0.0201, "step": 155170 }, { "epoch": 37.26, "learning_rate": 7.20510978493965e-05, "loss": 0.0108, "step": 155180 }, { "epoch": 37.26, "learning_rate": 7.204787616571524e-05, "loss": 0.0162, "step": 155190 }, { "epoch": 37.27, "learning_rate": 7.204465436839903e-05, "loss": 0.0227, "step": 155200 }, { "epoch": 37.27, "learning_rate": 7.204143245746449e-05, "loss": 0.0086, "step": 155210 }, { "epoch": 37.27, "learning_rate": 7.203821043292821e-05, "loss": 0.039, "step": 155220 }, { "epoch": 37.27, "learning_rate": 7.203498829480681e-05, "loss": 0.0077, "step": 155230 }, { "epoch": 37.28, "learning_rate": 7.203176604311692e-05, "loss": 0.0074, "step": 155240 }, { "epoch": 37.28, "learning_rate": 7.202854367787512e-05, "loss": 0.0199, "step": 155250 }, { "epoch": 37.28, "learning_rate": 7.202532119909799e-05, "loss": 0.0211, "step": 155260 }, { "epoch": 37.28, "learning_rate": 7.20220986068022e-05, "loss": 0.0421, "step": 155270 }, { "epoch": 37.29, "learning_rate": 7.201887590100433e-05, "loss": 0.0143, "step": 155280 }, { "epoch": 37.29, "learning_rate": 7.201565308172097e-05, "loss": 0.0189, "step": 155290 }, { "epoch": 37.29, "learning_rate": 7.201243014896876e-05, "loss": 0.0153, "step": 155300 }, { "epoch": 37.29, "learning_rate": 7.200920710276431e-05, "loss": 0.01, "step": 155310 }, { "epoch": 37.29, "learning_rate": 7.200598394312422e-05, "loss": 0.0606, "step": 155320 }, { "epoch": 37.3, "learning_rate": 7.20027606700651e-05, "loss": 0.0131, "step": 155330 }, { "epoch": 37.3, "learning_rate": 7.199953728360355e-05, "loss": 0.0212, "step": 155340 }, { "epoch": 37.3, "learning_rate": 7.199631378375623e-05, "loss": 0.0183, "step": 155350 }, { "epoch": 37.3, "learning_rate": 7.199309017053971e-05, "loss": 0.0075, "step": 155360 }, { "epoch": 37.31, "learning_rate": 7.198986644397063e-05, "loss": 0.0146, "step": 155370 }, { "epoch": 37.31, "learning_rate": 7.198664260406559e-05, "loss": 0.0119, "step": 155380 }, { "epoch": 37.31, "learning_rate": 7.19834186508412e-05, "loss": 0.0084, "step": 155390 }, { "epoch": 37.31, "learning_rate": 7.19801945843141e-05, "loss": 0.0164, "step": 155400 }, { "epoch": 37.32, "learning_rate": 7.197697040450087e-05, "loss": 0.0264, "step": 155410 }, { "epoch": 37.32, "learning_rate": 7.197374611141817e-05, "loss": 0.0106, "step": 155420 }, { "epoch": 37.32, "learning_rate": 7.197052170508261e-05, "loss": 0.0146, "step": 155430 }, { "epoch": 37.32, "learning_rate": 7.196729718551078e-05, "loss": 0.0111, "step": 155440 }, { "epoch": 37.32, "learning_rate": 7.196407255271933e-05, "loss": 0.0177, "step": 155450 }, { "epoch": 37.33, "learning_rate": 7.196084780672486e-05, "loss": 0.0156, "step": 155460 }, { "epoch": 37.33, "learning_rate": 7.195762294754397e-05, "loss": 0.0233, "step": 155470 }, { "epoch": 37.33, "learning_rate": 7.195439797519335e-05, "loss": 0.0107, "step": 155480 }, { "epoch": 37.33, "learning_rate": 7.195117288968956e-05, "loss": 0.0132, "step": 155490 }, { "epoch": 37.34, "learning_rate": 7.194794769104925e-05, "loss": 0.0122, "step": 155500 }, { "epoch": 37.34, "learning_rate": 7.194472237928902e-05, "loss": 0.028, "step": 155510 }, { "epoch": 37.34, "learning_rate": 7.194149695442551e-05, "loss": 0.009, "step": 155520 }, { "epoch": 37.34, "learning_rate": 7.193827141647536e-05, "loss": 0.0204, "step": 155530 }, { "epoch": 37.34, "learning_rate": 7.193504576545515e-05, "loss": 0.0162, "step": 155540 }, { "epoch": 37.35, "learning_rate": 7.193182000138155e-05, "loss": 0.0127, "step": 155550 }, { "epoch": 37.35, "learning_rate": 7.192859412427115e-05, "loss": 0.0149, "step": 155560 }, { "epoch": 37.35, "learning_rate": 7.192536813414059e-05, "loss": 0.009, "step": 155570 }, { "epoch": 37.35, "learning_rate": 7.192214203100651e-05, "loss": 0.0143, "step": 155580 }, { "epoch": 37.36, "learning_rate": 7.191891581488554e-05, "loss": 0.0157, "step": 155590 }, { "epoch": 37.36, "learning_rate": 7.191568948579428e-05, "loss": 0.0311, "step": 155600 }, { "epoch": 37.36, "learning_rate": 7.191246304374938e-05, "loss": 0.0256, "step": 155610 }, { "epoch": 37.36, "learning_rate": 7.190923648876746e-05, "loss": 0.0137, "step": 155620 }, { "epoch": 37.37, "learning_rate": 7.190600982086515e-05, "loss": 0.0158, "step": 155630 }, { "epoch": 37.37, "learning_rate": 7.190278304005908e-05, "loss": 0.0264, "step": 155640 }, { "epoch": 37.37, "learning_rate": 7.189955614636588e-05, "loss": 0.0119, "step": 155650 }, { "epoch": 37.37, "learning_rate": 7.189632913980218e-05, "loss": 0.0187, "step": 155660 }, { "epoch": 37.37, "learning_rate": 7.189310202038464e-05, "loss": 0.0085, "step": 155670 }, { "epoch": 37.38, "learning_rate": 7.188987478812986e-05, "loss": 0.0117, "step": 155680 }, { "epoch": 37.38, "learning_rate": 7.188664744305447e-05, "loss": 0.0104, "step": 155690 }, { "epoch": 37.38, "learning_rate": 7.188341998517513e-05, "loss": 0.0286, "step": 155700 }, { "epoch": 37.38, "learning_rate": 7.188019241450845e-05, "loss": 0.0069, "step": 155710 }, { "epoch": 37.39, "learning_rate": 7.187696473107109e-05, "loss": 0.0143, "step": 155720 }, { "epoch": 37.39, "learning_rate": 7.187373693487964e-05, "loss": 0.0075, "step": 155730 }, { "epoch": 37.39, "learning_rate": 7.18705090259508e-05, "loss": 0.0096, "step": 155740 }, { "epoch": 37.39, "learning_rate": 7.186728100430116e-05, "loss": 0.0095, "step": 155750 }, { "epoch": 37.4, "learning_rate": 7.186405286994737e-05, "loss": 0.0188, "step": 155760 }, { "epoch": 37.4, "learning_rate": 7.186082462290607e-05, "loss": 0.0135, "step": 155770 }, { "epoch": 37.4, "learning_rate": 7.18575962631939e-05, "loss": 0.0171, "step": 155780 }, { "epoch": 37.4, "learning_rate": 7.185436779082749e-05, "loss": 0.0073, "step": 155790 }, { "epoch": 37.4, "learning_rate": 7.185113920582349e-05, "loss": 0.0106, "step": 155800 }, { "epoch": 37.41, "learning_rate": 7.184791050819855e-05, "loss": 0.0208, "step": 155810 }, { "epoch": 37.41, "learning_rate": 7.184468169796929e-05, "loss": 0.0215, "step": 155820 }, { "epoch": 37.41, "learning_rate": 7.184145277515234e-05, "loss": 0.0083, "step": 155830 }, { "epoch": 37.41, "learning_rate": 7.183822373976437e-05, "loss": 0.0231, "step": 155840 }, { "epoch": 37.42, "learning_rate": 7.183499459182202e-05, "loss": 0.0134, "step": 155850 }, { "epoch": 37.42, "learning_rate": 7.18317653313419e-05, "loss": 0.0118, "step": 155860 }, { "epoch": 37.42, "learning_rate": 7.18285359583407e-05, "loss": 0.0157, "step": 155870 }, { "epoch": 37.42, "learning_rate": 7.182530647283505e-05, "loss": 0.0107, "step": 155880 }, { "epoch": 37.42, "learning_rate": 7.182207687484157e-05, "loss": 0.0157, "step": 155890 }, { "epoch": 37.43, "learning_rate": 7.181884716437693e-05, "loss": 0.0164, "step": 155900 }, { "epoch": 37.43, "learning_rate": 7.181561734145777e-05, "loss": 0.0091, "step": 155910 }, { "epoch": 37.43, "learning_rate": 7.181238740610074e-05, "loss": 0.0224, "step": 155920 }, { "epoch": 37.43, "learning_rate": 7.180915735832247e-05, "loss": 0.0192, "step": 155930 }, { "epoch": 37.44, "learning_rate": 7.180592719813963e-05, "loss": 0.0228, "step": 155940 }, { "epoch": 37.44, "learning_rate": 7.180269692556886e-05, "loss": 0.0125, "step": 155950 }, { "epoch": 37.44, "learning_rate": 7.179946654062683e-05, "loss": 0.0134, "step": 155960 }, { "epoch": 37.44, "learning_rate": 7.179623604333015e-05, "loss": 0.0136, "step": 155970 }, { "epoch": 37.45, "learning_rate": 7.179300543369547e-05, "loss": 0.017, "step": 155980 }, { "epoch": 37.45, "learning_rate": 7.178977471173946e-05, "loss": 0.0097, "step": 155990 }, { "epoch": 37.45, "learning_rate": 7.178654387747879e-05, "loss": 0.0166, "step": 156000 }, { "epoch": 37.45, "learning_rate": 7.178331293093008e-05, "loss": 0.0138, "step": 156010 }, { "epoch": 37.45, "learning_rate": 7.178008187210998e-05, "loss": 0.0224, "step": 156020 }, { "epoch": 37.46, "learning_rate": 7.177685070103517e-05, "loss": 0.0243, "step": 156030 }, { "epoch": 37.46, "learning_rate": 7.177361941772229e-05, "loss": 0.0111, "step": 156040 }, { "epoch": 37.46, "learning_rate": 7.1770388022188e-05, "loss": 0.0128, "step": 156050 }, { "epoch": 37.46, "learning_rate": 7.176715651444894e-05, "loss": 0.0208, "step": 156060 }, { "epoch": 37.47, "learning_rate": 7.176392489452177e-05, "loss": 0.0128, "step": 156070 }, { "epoch": 37.47, "learning_rate": 7.176069316242315e-05, "loss": 0.0118, "step": 156080 }, { "epoch": 37.47, "learning_rate": 7.175746131816972e-05, "loss": 0.0099, "step": 156090 }, { "epoch": 37.47, "learning_rate": 7.175422936177819e-05, "loss": 0.0144, "step": 156100 }, { "epoch": 37.48, "learning_rate": 7.175099729326515e-05, "loss": 0.0054, "step": 156110 }, { "epoch": 37.48, "learning_rate": 7.174776511264731e-05, "loss": 0.0209, "step": 156120 }, { "epoch": 37.48, "learning_rate": 7.17445328199413e-05, "loss": 0.0134, "step": 156130 }, { "epoch": 37.48, "learning_rate": 7.174130041516376e-05, "loss": 0.0104, "step": 156140 }, { "epoch": 37.48, "learning_rate": 7.17380678983314e-05, "loss": 0.0148, "step": 156150 }, { "epoch": 37.49, "learning_rate": 7.173483526946087e-05, "loss": 0.0126, "step": 156160 }, { "epoch": 37.49, "learning_rate": 7.173160252856878e-05, "loss": 0.0208, "step": 156170 }, { "epoch": 37.49, "learning_rate": 7.172836967567186e-05, "loss": 0.0166, "step": 156180 }, { "epoch": 37.49, "learning_rate": 7.172513671078673e-05, "loss": 0.0074, "step": 156190 }, { "epoch": 37.5, "learning_rate": 7.172190363393007e-05, "loss": 0.0202, "step": 156200 }, { "epoch": 37.5, "learning_rate": 7.171867044511852e-05, "loss": 0.0165, "step": 156210 }, { "epoch": 37.5, "learning_rate": 7.171543714436879e-05, "loss": 0.0153, "step": 156220 }, { "epoch": 37.5, "learning_rate": 7.17122037316975e-05, "loss": 0.0127, "step": 156230 }, { "epoch": 37.5, "learning_rate": 7.170897020712133e-05, "loss": 0.0168, "step": 156240 }, { "epoch": 37.51, "learning_rate": 7.170573657065693e-05, "loss": 0.0188, "step": 156250 }, { "epoch": 37.51, "learning_rate": 7.170250282232101e-05, "loss": 0.014, "step": 156260 }, { "epoch": 37.51, "learning_rate": 7.169926896213019e-05, "loss": 0.0083, "step": 156270 }, { "epoch": 37.51, "learning_rate": 7.169603499010116e-05, "loss": 0.0446, "step": 156280 }, { "epoch": 37.52, "learning_rate": 7.169280090625058e-05, "loss": 0.0212, "step": 156290 }, { "epoch": 37.52, "learning_rate": 7.168956671059513e-05, "loss": 0.0185, "step": 156300 }, { "epoch": 37.52, "learning_rate": 7.168633240315148e-05, "loss": 0.0158, "step": 156310 }, { "epoch": 37.52, "learning_rate": 7.168309798393627e-05, "loss": 0.0094, "step": 156320 }, { "epoch": 37.53, "learning_rate": 7.16798634529662e-05, "loss": 0.0272, "step": 156330 }, { "epoch": 37.53, "learning_rate": 7.167662881025796e-05, "loss": 0.0196, "step": 156340 }, { "epoch": 37.53, "learning_rate": 7.167339405582816e-05, "loss": 0.0214, "step": 156350 }, { "epoch": 37.53, "learning_rate": 7.167015918969351e-05, "loss": 0.0234, "step": 156360 }, { "epoch": 37.53, "learning_rate": 7.166692421187069e-05, "loss": 0.0283, "step": 156370 }, { "epoch": 37.54, "learning_rate": 7.166368912237636e-05, "loss": 0.0458, "step": 156380 }, { "epoch": 37.54, "learning_rate": 7.16604539212272e-05, "loss": 0.0276, "step": 156390 }, { "epoch": 37.54, "learning_rate": 7.165721860843987e-05, "loss": 0.021, "step": 156400 }, { "epoch": 37.54, "learning_rate": 7.165398318403106e-05, "loss": 0.0413, "step": 156410 }, { "epoch": 37.55, "learning_rate": 7.165074764801742e-05, "loss": 0.0283, "step": 156420 }, { "epoch": 37.55, "learning_rate": 7.164751200041567e-05, "loss": 0.0336, "step": 156430 }, { "epoch": 37.55, "learning_rate": 7.164427624124245e-05, "loss": 0.0424, "step": 156440 }, { "epoch": 37.55, "learning_rate": 7.164104037051445e-05, "loss": 0.023, "step": 156450 }, { "epoch": 37.56, "learning_rate": 7.163780438824836e-05, "loss": 0.0229, "step": 156460 }, { "epoch": 37.56, "learning_rate": 7.163456829446082e-05, "loss": 0.0159, "step": 156470 }, { "epoch": 37.56, "learning_rate": 7.163133208916856e-05, "loss": 0.0366, "step": 156480 }, { "epoch": 37.56, "learning_rate": 7.162809577238823e-05, "loss": 0.0191, "step": 156490 }, { "epoch": 37.56, "learning_rate": 7.162485934413649e-05, "loss": 0.0216, "step": 156500 }, { "epoch": 37.57, "learning_rate": 7.162162280443007e-05, "loss": 0.0147, "step": 156510 }, { "epoch": 37.57, "learning_rate": 7.161838615328561e-05, "loss": 0.015, "step": 156520 }, { "epoch": 37.57, "learning_rate": 7.161514939071983e-05, "loss": 0.0116, "step": 156530 }, { "epoch": 37.57, "learning_rate": 7.161191251674937e-05, "loss": 0.0224, "step": 156540 }, { "epoch": 37.58, "learning_rate": 7.160867553139093e-05, "loss": 0.0247, "step": 156550 }, { "epoch": 37.58, "learning_rate": 7.160543843466119e-05, "loss": 0.0217, "step": 156560 }, { "epoch": 37.58, "learning_rate": 7.160220122657686e-05, "loss": 0.0288, "step": 156570 }, { "epoch": 37.58, "learning_rate": 7.159896390715459e-05, "loss": 0.0256, "step": 156580 }, { "epoch": 37.58, "learning_rate": 7.159572647641109e-05, "loss": 0.0192, "step": 156590 }, { "epoch": 37.59, "learning_rate": 7.159248893436304e-05, "loss": 0.0215, "step": 156600 }, { "epoch": 37.59, "learning_rate": 7.15892512810271e-05, "loss": 0.0225, "step": 156610 }, { "epoch": 37.59, "learning_rate": 7.158601351641999e-05, "loss": 0.0189, "step": 156620 }, { "epoch": 37.59, "learning_rate": 7.158277564055838e-05, "loss": 0.0187, "step": 156630 }, { "epoch": 37.6, "learning_rate": 7.157953765345896e-05, "loss": 0.0162, "step": 156640 }, { "epoch": 37.6, "learning_rate": 7.157629955513843e-05, "loss": 0.0322, "step": 156650 }, { "epoch": 37.6, "learning_rate": 7.157306134561349e-05, "loss": 0.0149, "step": 156660 }, { "epoch": 37.6, "learning_rate": 7.156982302490079e-05, "loss": 0.022, "step": 156670 }, { "epoch": 37.61, "learning_rate": 7.156658459301705e-05, "loss": 0.0253, "step": 156680 }, { "epoch": 37.61, "learning_rate": 7.156334604997895e-05, "loss": 0.014, "step": 156690 }, { "epoch": 37.61, "learning_rate": 7.156010739580317e-05, "loss": 0.0138, "step": 156700 }, { "epoch": 37.61, "learning_rate": 7.155686863050644e-05, "loss": 0.0175, "step": 156710 }, { "epoch": 37.61, "learning_rate": 7.155362975410541e-05, "loss": 0.024, "step": 156720 }, { "epoch": 37.62, "learning_rate": 7.155039076661681e-05, "loss": 0.0255, "step": 156730 }, { "epoch": 37.62, "learning_rate": 7.15471516680573e-05, "loss": 0.011, "step": 156740 }, { "epoch": 37.62, "learning_rate": 7.15439124584436e-05, "loss": 0.0135, "step": 156750 }, { "epoch": 37.62, "learning_rate": 7.15406731377924e-05, "loss": 0.0153, "step": 156760 }, { "epoch": 37.63, "learning_rate": 7.153743370612038e-05, "loss": 0.0164, "step": 156770 }, { "epoch": 37.63, "learning_rate": 7.153419416344423e-05, "loss": 0.0227, "step": 156780 }, { "epoch": 37.63, "learning_rate": 7.153095450978069e-05, "loss": 0.0199, "step": 156790 }, { "epoch": 37.63, "learning_rate": 7.152771474514642e-05, "loss": 0.0235, "step": 156800 }, { "epoch": 37.64, "learning_rate": 7.152447486955813e-05, "loss": 0.0177, "step": 156810 }, { "epoch": 37.64, "learning_rate": 7.152123488303253e-05, "loss": 0.0269, "step": 156820 }, { "epoch": 37.64, "learning_rate": 7.151799478558629e-05, "loss": 0.0176, "step": 156830 }, { "epoch": 37.64, "learning_rate": 7.151475457723614e-05, "loss": 0.0272, "step": 156840 }, { "epoch": 37.64, "learning_rate": 7.151151425799875e-05, "loss": 0.0211, "step": 156850 }, { "epoch": 37.65, "learning_rate": 7.150827382789083e-05, "loss": 0.0205, "step": 156860 }, { "epoch": 37.65, "learning_rate": 7.150503328692911e-05, "loss": 0.0236, "step": 156870 }, { "epoch": 37.65, "learning_rate": 7.150179263513024e-05, "loss": 0.0169, "step": 156880 }, { "epoch": 37.65, "learning_rate": 7.149855187251097e-05, "loss": 0.0184, "step": 156890 }, { "epoch": 37.66, "learning_rate": 7.149531099908798e-05, "loss": 0.0309, "step": 156900 }, { "epoch": 37.66, "learning_rate": 7.149207001487798e-05, "loss": 0.0236, "step": 156910 }, { "epoch": 37.66, "learning_rate": 7.148882891989766e-05, "loss": 0.0194, "step": 156920 }, { "epoch": 37.66, "learning_rate": 7.148558771416374e-05, "loss": 0.0245, "step": 156930 }, { "epoch": 37.66, "learning_rate": 7.148234639769294e-05, "loss": 0.0134, "step": 156940 }, { "epoch": 37.67, "learning_rate": 7.147910497050192e-05, "loss": 0.0085, "step": 156950 }, { "epoch": 37.67, "learning_rate": 7.147586343260744e-05, "loss": 0.0139, "step": 156960 }, { "epoch": 37.67, "learning_rate": 7.147262178402616e-05, "loss": 0.0222, "step": 156970 }, { "epoch": 37.67, "learning_rate": 7.146938002477481e-05, "loss": 0.016, "step": 156980 }, { "epoch": 37.68, "learning_rate": 7.146613815487011e-05, "loss": 0.0224, "step": 156990 }, { "epoch": 37.68, "learning_rate": 7.146289617432874e-05, "loss": 0.0112, "step": 157000 }, { "epoch": 37.68, "learning_rate": 7.145965408316742e-05, "loss": 0.0161, "step": 157010 }, { "epoch": 37.68, "learning_rate": 7.145641188140289e-05, "loss": 0.0142, "step": 157020 }, { "epoch": 37.69, "learning_rate": 7.145316956905182e-05, "loss": 0.0195, "step": 157030 }, { "epoch": 37.69, "learning_rate": 7.144992714613092e-05, "loss": 0.0107, "step": 157040 }, { "epoch": 37.69, "learning_rate": 7.144668461265694e-05, "loss": 0.023, "step": 157050 }, { "epoch": 37.69, "learning_rate": 7.144344196864654e-05, "loss": 0.0217, "step": 157060 }, { "epoch": 37.69, "learning_rate": 7.144019921411648e-05, "loss": 0.0137, "step": 157070 }, { "epoch": 37.7, "learning_rate": 7.143695634908345e-05, "loss": 0.0197, "step": 157080 }, { "epoch": 37.7, "learning_rate": 7.143371337356416e-05, "loss": 0.0146, "step": 157090 }, { "epoch": 37.7, "learning_rate": 7.143047028757533e-05, "loss": 0.0144, "step": 157100 }, { "epoch": 37.7, "learning_rate": 7.14272270911337e-05, "loss": 0.0197, "step": 157110 }, { "epoch": 37.71, "learning_rate": 7.142398378425596e-05, "loss": 0.0277, "step": 157120 }, { "epoch": 37.71, "learning_rate": 7.142074036695881e-05, "loss": 0.0288, "step": 157130 }, { "epoch": 37.71, "learning_rate": 7.1417496839259e-05, "loss": 0.0252, "step": 157140 }, { "epoch": 37.71, "learning_rate": 7.141425320117322e-05, "loss": 0.0119, "step": 157150 }, { "epoch": 37.72, "learning_rate": 7.14110094527182e-05, "loss": 0.0342, "step": 157160 }, { "epoch": 37.72, "learning_rate": 7.140776559391067e-05, "loss": 0.0143, "step": 157170 }, { "epoch": 37.72, "learning_rate": 7.140452162476734e-05, "loss": 0.0282, "step": 157180 }, { "epoch": 37.72, "learning_rate": 7.140127754530491e-05, "loss": 0.0215, "step": 157190 }, { "epoch": 37.72, "learning_rate": 7.139803335554013e-05, "loss": 0.0217, "step": 157200 }, { "epoch": 37.73, "learning_rate": 7.139478905548969e-05, "loss": 0.0257, "step": 157210 }, { "epoch": 37.73, "learning_rate": 7.139154464517035e-05, "loss": 0.0523, "step": 157220 }, { "epoch": 37.73, "learning_rate": 7.13883001245988e-05, "loss": 0.0272, "step": 157230 }, { "epoch": 37.73, "learning_rate": 7.138505549379175e-05, "loss": 0.0112, "step": 157240 }, { "epoch": 37.74, "learning_rate": 7.138181075276599e-05, "loss": 0.018, "step": 157250 }, { "epoch": 37.74, "learning_rate": 7.137856590153817e-05, "loss": 0.021, "step": 157260 }, { "epoch": 37.74, "learning_rate": 7.137532094012505e-05, "loss": 0.0329, "step": 157270 }, { "epoch": 37.74, "learning_rate": 7.137207586854335e-05, "loss": 0.0441, "step": 157280 }, { "epoch": 37.74, "learning_rate": 7.136883068680978e-05, "loss": 0.0152, "step": 157290 }, { "epoch": 37.75, "learning_rate": 7.136558539494109e-05, "loss": 0.0209, "step": 157300 }, { "epoch": 37.75, "learning_rate": 7.136233999295398e-05, "loss": 0.0245, "step": 157310 }, { "epoch": 37.75, "learning_rate": 7.135909448086522e-05, "loss": 0.0121, "step": 157320 }, { "epoch": 37.75, "learning_rate": 7.135584885869149e-05, "loss": 0.0088, "step": 157330 }, { "epoch": 37.76, "learning_rate": 7.135260312644953e-05, "loss": 0.0263, "step": 157340 }, { "epoch": 37.76, "learning_rate": 7.134935728415609e-05, "loss": 0.0192, "step": 157350 }, { "epoch": 37.76, "learning_rate": 7.134611133182788e-05, "loss": 0.0193, "step": 157360 }, { "epoch": 37.76, "learning_rate": 7.134286526948162e-05, "loss": 0.0186, "step": 157370 }, { "epoch": 37.77, "learning_rate": 7.133961909713407e-05, "loss": 0.0146, "step": 157380 }, { "epoch": 37.77, "learning_rate": 7.133637281480193e-05, "loss": 0.0234, "step": 157390 }, { "epoch": 37.77, "learning_rate": 7.133312642250196e-05, "loss": 0.0136, "step": 157400 }, { "epoch": 37.77, "learning_rate": 7.132987992025086e-05, "loss": 0.0209, "step": 157410 }, { "epoch": 37.77, "learning_rate": 7.132663330806539e-05, "loss": 0.0203, "step": 157420 }, { "epoch": 37.78, "learning_rate": 7.132338658596229e-05, "loss": 0.0136, "step": 157430 }, { "epoch": 37.78, "learning_rate": 7.132013975395826e-05, "loss": 0.0127, "step": 157440 }, { "epoch": 37.78, "learning_rate": 7.131689281207006e-05, "loss": 0.0186, "step": 157450 }, { "epoch": 37.78, "learning_rate": 7.131364576031442e-05, "loss": 0.013, "step": 157460 }, { "epoch": 37.79, "learning_rate": 7.131039859870806e-05, "loss": 0.0115, "step": 157470 }, { "epoch": 37.79, "learning_rate": 7.130715132726773e-05, "loss": 0.0167, "step": 157480 }, { "epoch": 37.79, "learning_rate": 7.130390394601016e-05, "loss": 0.0175, "step": 157490 }, { "epoch": 37.79, "learning_rate": 7.13006564549521e-05, "loss": 0.0195, "step": 157500 }, { "epoch": 37.8, "learning_rate": 7.129740885411027e-05, "loss": 0.0245, "step": 157510 }, { "epoch": 37.8, "learning_rate": 7.129416114350143e-05, "loss": 0.0169, "step": 157520 }, { "epoch": 37.8, "learning_rate": 7.12909133231423e-05, "loss": 0.0188, "step": 157530 }, { "epoch": 37.8, "learning_rate": 7.12876653930496e-05, "loss": 0.0103, "step": 157540 }, { "epoch": 37.8, "learning_rate": 7.128441735324013e-05, "loss": 0.0145, "step": 157550 }, { "epoch": 37.81, "learning_rate": 7.128116920373059e-05, "loss": 0.0277, "step": 157560 }, { "epoch": 37.81, "learning_rate": 7.12779209445377e-05, "loss": 0.0221, "step": 157570 }, { "epoch": 37.81, "learning_rate": 7.127467257567825e-05, "loss": 0.0245, "step": 157580 }, { "epoch": 37.81, "learning_rate": 7.127142409716897e-05, "loss": 0.0206, "step": 157590 }, { "epoch": 37.82, "learning_rate": 7.126817550902655e-05, "loss": 0.0125, "step": 157600 }, { "epoch": 37.82, "learning_rate": 7.126492681126782e-05, "loss": 0.011, "step": 157610 }, { "epoch": 37.82, "learning_rate": 7.126167800390947e-05, "loss": 0.0268, "step": 157620 }, { "epoch": 37.82, "learning_rate": 7.125842908696824e-05, "loss": 0.0186, "step": 157630 }, { "epoch": 37.82, "learning_rate": 7.12551800604609e-05, "loss": 0.0147, "step": 157640 }, { "epoch": 37.83, "learning_rate": 7.125193092440417e-05, "loss": 0.0187, "step": 157650 }, { "epoch": 37.83, "learning_rate": 7.124868167881482e-05, "loss": 0.0232, "step": 157660 }, { "epoch": 37.83, "learning_rate": 7.124543232370959e-05, "loss": 0.0215, "step": 157670 }, { "epoch": 37.83, "learning_rate": 7.124218285910522e-05, "loss": 0.0164, "step": 157680 }, { "epoch": 37.84, "learning_rate": 7.123893328501847e-05, "loss": 0.0178, "step": 157690 }, { "epoch": 37.84, "learning_rate": 7.123568360146606e-05, "loss": 0.0309, "step": 157700 }, { "epoch": 37.84, "learning_rate": 7.123243380846478e-05, "loss": 0.0078, "step": 157710 }, { "epoch": 37.84, "learning_rate": 7.122918390603135e-05, "loss": 0.0171, "step": 157720 }, { "epoch": 37.85, "learning_rate": 7.122593389418252e-05, "loss": 0.0154, "step": 157730 }, { "epoch": 37.85, "learning_rate": 7.122268377293506e-05, "loss": 0.0213, "step": 157740 }, { "epoch": 37.85, "learning_rate": 7.121943354230572e-05, "loss": 0.0119, "step": 157750 }, { "epoch": 37.85, "learning_rate": 7.121618320231122e-05, "loss": 0.0177, "step": 157760 }, { "epoch": 37.85, "learning_rate": 7.121293275296835e-05, "loss": 0.0147, "step": 157770 }, { "epoch": 37.86, "learning_rate": 7.120968219429384e-05, "loss": 0.0168, "step": 157780 }, { "epoch": 37.86, "learning_rate": 7.120643152630446e-05, "loss": 0.0118, "step": 157790 }, { "epoch": 37.86, "learning_rate": 7.120318074901695e-05, "loss": 0.0168, "step": 157800 }, { "epoch": 37.86, "learning_rate": 7.119992986244806e-05, "loss": 0.0185, "step": 157810 }, { "epoch": 37.87, "learning_rate": 7.119667886661456e-05, "loss": 0.0165, "step": 157820 }, { "epoch": 37.87, "learning_rate": 7.119342776153322e-05, "loss": 0.0098, "step": 157830 }, { "epoch": 37.87, "learning_rate": 7.119017654722075e-05, "loss": 0.0128, "step": 157840 }, { "epoch": 37.87, "learning_rate": 7.118692522369393e-05, "loss": 0.0246, "step": 157850 }, { "epoch": 37.88, "learning_rate": 7.118367379096954e-05, "loss": 0.016, "step": 157860 }, { "epoch": 37.88, "learning_rate": 7.11804222490643e-05, "loss": 0.0093, "step": 157870 }, { "epoch": 37.88, "learning_rate": 7.1177170597995e-05, "loss": 0.0157, "step": 157880 }, { "epoch": 37.88, "learning_rate": 7.117391883777838e-05, "loss": 0.015, "step": 157890 }, { "epoch": 37.88, "learning_rate": 7.117066696843122e-05, "loss": 0.0146, "step": 157900 }, { "epoch": 37.89, "learning_rate": 7.116741498997025e-05, "loss": 0.0197, "step": 157910 }, { "epoch": 37.89, "learning_rate": 7.116416290241226e-05, "loss": 0.0166, "step": 157920 }, { "epoch": 37.89, "learning_rate": 7.116091070577398e-05, "loss": 0.0142, "step": 157930 }, { "epoch": 37.89, "learning_rate": 7.11576584000722e-05, "loss": 0.0153, "step": 157940 }, { "epoch": 37.9, "learning_rate": 7.115440598532366e-05, "loss": 0.0142, "step": 157950 }, { "epoch": 37.9, "learning_rate": 7.115115346154514e-05, "loss": 0.0116, "step": 157960 }, { "epoch": 37.9, "learning_rate": 7.11479008287534e-05, "loss": 0.0183, "step": 157970 }, { "epoch": 37.9, "learning_rate": 7.11446480869652e-05, "loss": 0.0119, "step": 157980 }, { "epoch": 37.9, "learning_rate": 7.114139523619732e-05, "loss": 0.0246, "step": 157990 }, { "epoch": 37.91, "learning_rate": 7.11381422764665e-05, "loss": 0.0266, "step": 158000 }, { "epoch": 37.91, "learning_rate": 7.113488920778951e-05, "loss": 0.0288, "step": 158010 }, { "epoch": 37.91, "learning_rate": 7.113163603018313e-05, "loss": 0.0195, "step": 158020 }, { "epoch": 37.91, "learning_rate": 7.112838274366413e-05, "loss": 0.0104, "step": 158030 }, { "epoch": 37.92, "learning_rate": 7.112512934824927e-05, "loss": 0.0402, "step": 158040 }, { "epoch": 37.92, "learning_rate": 7.112187584395532e-05, "loss": 0.0162, "step": 158050 }, { "epoch": 37.92, "learning_rate": 7.111862223079904e-05, "loss": 0.013, "step": 158060 }, { "epoch": 37.92, "learning_rate": 7.11153685087972e-05, "loss": 0.0216, "step": 158070 }, { "epoch": 37.93, "learning_rate": 7.111211467796656e-05, "loss": 0.0079, "step": 158080 }, { "epoch": 37.93, "learning_rate": 7.110886073832393e-05, "loss": 0.0156, "step": 158090 }, { "epoch": 37.93, "learning_rate": 7.110560668988604e-05, "loss": 0.0196, "step": 158100 }, { "epoch": 37.93, "learning_rate": 7.11023525326697e-05, "loss": 0.0188, "step": 158110 }, { "epoch": 37.93, "learning_rate": 7.109909826669164e-05, "loss": 0.022, "step": 158120 }, { "epoch": 37.94, "learning_rate": 7.109584389196864e-05, "loss": 0.0137, "step": 158130 }, { "epoch": 37.94, "learning_rate": 7.109258940851748e-05, "loss": 0.0132, "step": 158140 }, { "epoch": 37.94, "learning_rate": 7.108933481635496e-05, "loss": 0.0191, "step": 158150 }, { "epoch": 37.94, "learning_rate": 7.108608011549783e-05, "loss": 0.0148, "step": 158160 }, { "epoch": 37.95, "learning_rate": 7.108282530596286e-05, "loss": 0.0172, "step": 158170 }, { "epoch": 37.95, "learning_rate": 7.107957038776685e-05, "loss": 0.0141, "step": 158180 }, { "epoch": 37.95, "learning_rate": 7.107631536092654e-05, "loss": 0.015, "step": 158190 }, { "epoch": 38.0, "learning_rate": 7.107306022545872e-05, "loss": 0.0125, "step": 158200 }, { "epoch": 38.0, "learning_rate": 7.106980498138019e-05, "loss": 0.0185, "step": 158210 }, { "epoch": 38.01, "learning_rate": 7.106654962870769e-05, "loss": 0.029, "step": 158220 }, { "epoch": 38.01, "learning_rate": 7.106329416745803e-05, "loss": 0.0133, "step": 158230 }, { "epoch": 38.01, "learning_rate": 7.106003859764796e-05, "loss": 0.0154, "step": 158240 }, { "epoch": 38.01, "learning_rate": 7.10567829192943e-05, "loss": 0.018, "step": 158250 }, { "epoch": 38.02, "learning_rate": 7.10535271324138e-05, "loss": 0.0176, "step": 158260 }, { "epoch": 38.02, "learning_rate": 7.105027123702323e-05, "loss": 0.0156, "step": 158270 }, { "epoch": 38.02, "learning_rate": 7.104701523313939e-05, "loss": 0.0141, "step": 158280 }, { "epoch": 38.02, "learning_rate": 7.104375912077906e-05, "loss": 0.0119, "step": 158290 }, { "epoch": 38.02, "learning_rate": 7.1040502899959e-05, "loss": 0.021, "step": 158300 }, { "epoch": 38.03, "learning_rate": 7.103724657069603e-05, "loss": 0.0098, "step": 158310 }, { "epoch": 38.03, "learning_rate": 7.103399013300692e-05, "loss": 0.0109, "step": 158320 }, { "epoch": 38.03, "learning_rate": 7.103073358690847e-05, "loss": 0.0267, "step": 158330 }, { "epoch": 38.03, "learning_rate": 7.10274769324174e-05, "loss": 0.0154, "step": 158340 }, { "epoch": 38.04, "learning_rate": 7.102422016955056e-05, "loss": 0.0147, "step": 158350 }, { "epoch": 38.04, "learning_rate": 7.10209632983247e-05, "loss": 0.0191, "step": 158360 }, { "epoch": 38.04, "learning_rate": 7.101770631875664e-05, "loss": 0.0091, "step": 158370 }, { "epoch": 38.04, "learning_rate": 7.101444923086313e-05, "loss": 0.0113, "step": 158380 }, { "epoch": 38.04, "learning_rate": 7.101119203466097e-05, "loss": 0.0234, "step": 158390 }, { "epoch": 38.05, "learning_rate": 7.100793473016699e-05, "loss": 0.0106, "step": 158400 }, { "epoch": 38.05, "learning_rate": 7.10046773173979e-05, "loss": 0.0148, "step": 158410 }, { "epoch": 38.05, "learning_rate": 7.100141979637054e-05, "loss": 0.0079, "step": 158420 }, { "epoch": 38.05, "learning_rate": 7.099816216710167e-05, "loss": 0.0152, "step": 158430 }, { "epoch": 38.06, "learning_rate": 7.099490442960812e-05, "loss": 0.0136, "step": 158440 }, { "epoch": 38.06, "learning_rate": 7.099164658390664e-05, "loss": 0.0118, "step": 158450 }, { "epoch": 38.06, "learning_rate": 7.098838863001404e-05, "loss": 0.0139, "step": 158460 }, { "epoch": 38.06, "learning_rate": 7.098513056794712e-05, "loss": 0.0135, "step": 158470 }, { "epoch": 38.07, "learning_rate": 7.098187239772266e-05, "loss": 0.0099, "step": 158480 }, { "epoch": 38.07, "learning_rate": 7.097861411935744e-05, "loss": 0.0151, "step": 158490 }, { "epoch": 38.07, "learning_rate": 7.097535573286828e-05, "loss": 0.0069, "step": 158500 }, { "epoch": 38.07, "learning_rate": 7.097209723827196e-05, "loss": 0.0162, "step": 158510 }, { "epoch": 38.07, "learning_rate": 7.096883863558528e-05, "loss": 0.0226, "step": 158520 }, { "epoch": 38.08, "learning_rate": 7.096557992482502e-05, "loss": 0.0142, "step": 158530 }, { "epoch": 38.08, "learning_rate": 7.0962321106008e-05, "loss": 0.0116, "step": 158540 }, { "epoch": 38.08, "learning_rate": 7.0959062179151e-05, "loss": 0.0149, "step": 158550 }, { "epoch": 38.08, "learning_rate": 7.095580314427079e-05, "loss": 0.0161, "step": 158560 }, { "epoch": 38.09, "learning_rate": 7.095254400138423e-05, "loss": 0.0086, "step": 158570 }, { "epoch": 38.09, "learning_rate": 7.094928475050806e-05, "loss": 0.0113, "step": 158580 }, { "epoch": 38.09, "learning_rate": 7.094602539165911e-05, "loss": 0.0207, "step": 158590 }, { "epoch": 38.09, "learning_rate": 7.094276592485417e-05, "loss": 0.0177, "step": 158600 }, { "epoch": 38.1, "learning_rate": 7.093950635011004e-05, "loss": 0.0126, "step": 158610 }, { "epoch": 38.1, "learning_rate": 7.093624666744352e-05, "loss": 0.0213, "step": 158620 }, { "epoch": 38.1, "learning_rate": 7.09329868768714e-05, "loss": 0.0158, "step": 158630 }, { "epoch": 38.1, "learning_rate": 7.09297269784105e-05, "loss": 0.0119, "step": 158640 }, { "epoch": 38.1, "learning_rate": 7.092646697207762e-05, "loss": 0.0207, "step": 158650 }, { "epoch": 38.11, "learning_rate": 7.092320685788954e-05, "loss": 0.03, "step": 158660 }, { "epoch": 38.11, "learning_rate": 7.091994663586308e-05, "loss": 0.0123, "step": 158670 }, { "epoch": 38.11, "learning_rate": 7.091668630601504e-05, "loss": 0.0169, "step": 158680 }, { "epoch": 38.11, "learning_rate": 7.091342586836225e-05, "loss": 0.0078, "step": 158690 }, { "epoch": 38.12, "learning_rate": 7.091016532292146e-05, "loss": 0.0401, "step": 158700 }, { "epoch": 38.12, "learning_rate": 7.090690466970951e-05, "loss": 0.011, "step": 158710 }, { "epoch": 38.12, "learning_rate": 7.09036439087432e-05, "loss": 0.0252, "step": 158720 }, { "epoch": 38.12, "learning_rate": 7.090038304003932e-05, "loss": 0.0198, "step": 158730 }, { "epoch": 38.12, "learning_rate": 7.08971220636147e-05, "loss": 0.01, "step": 158740 }, { "epoch": 38.13, "learning_rate": 7.089386097948615e-05, "loss": 0.0213, "step": 158750 }, { "epoch": 38.13, "learning_rate": 7.089059978767045e-05, "loss": 0.0142, "step": 158760 }, { "epoch": 38.13, "learning_rate": 7.088733848818444e-05, "loss": 0.0099, "step": 158770 }, { "epoch": 38.13, "learning_rate": 7.08840770810449e-05, "loss": 0.0308, "step": 158780 }, { "epoch": 38.14, "learning_rate": 7.088081556626865e-05, "loss": 0.0082, "step": 158790 }, { "epoch": 38.14, "learning_rate": 7.087755394387251e-05, "loss": 0.0181, "step": 158800 }, { "epoch": 38.14, "learning_rate": 7.087429221387328e-05, "loss": 0.014, "step": 158810 }, { "epoch": 38.14, "learning_rate": 7.087103037628777e-05, "loss": 0.0165, "step": 158820 }, { "epoch": 38.15, "learning_rate": 7.086776843113281e-05, "loss": 0.0193, "step": 158830 }, { "epoch": 38.15, "learning_rate": 7.086450637842518e-05, "loss": 0.0119, "step": 158840 }, { "epoch": 38.15, "learning_rate": 7.086124421818173e-05, "loss": 0.0087, "step": 158850 }, { "epoch": 38.15, "learning_rate": 7.085798195041923e-05, "loss": 0.0183, "step": 158860 }, { "epoch": 38.15, "learning_rate": 7.085471957515453e-05, "loss": 0.0161, "step": 158870 }, { "epoch": 38.16, "learning_rate": 7.085145709240442e-05, "loss": 0.0143, "step": 158880 }, { "epoch": 38.16, "learning_rate": 7.084819450218573e-05, "loss": 0.0112, "step": 158890 }, { "epoch": 38.16, "learning_rate": 7.084493180451528e-05, "loss": 0.0098, "step": 158900 }, { "epoch": 38.16, "learning_rate": 7.084166899940986e-05, "loss": 0.024, "step": 158910 }, { "epoch": 38.17, "learning_rate": 7.083840608688633e-05, "loss": 0.0128, "step": 158920 }, { "epoch": 38.17, "learning_rate": 7.083514306696146e-05, "loss": 0.0183, "step": 158930 }, { "epoch": 38.17, "learning_rate": 7.083187993965208e-05, "loss": 0.0104, "step": 158940 }, { "epoch": 38.17, "learning_rate": 7.082861670497503e-05, "loss": 0.0092, "step": 158950 }, { "epoch": 38.18, "learning_rate": 7.082535336294713e-05, "loss": 0.0132, "step": 158960 }, { "epoch": 38.18, "learning_rate": 7.082208991358517e-05, "loss": 0.0095, "step": 158970 }, { "epoch": 38.18, "learning_rate": 7.081882635690598e-05, "loss": 0.0247, "step": 158980 }, { "epoch": 38.18, "learning_rate": 7.08155626929264e-05, "loss": 0.0189, "step": 158990 }, { "epoch": 38.18, "learning_rate": 7.08122989216632e-05, "loss": 0.0142, "step": 159000 }, { "epoch": 38.19, "learning_rate": 7.080903504313328e-05, "loss": 0.0198, "step": 159010 }, { "epoch": 38.19, "learning_rate": 7.08057710573534e-05, "loss": 0.0086, "step": 159020 }, { "epoch": 38.19, "learning_rate": 7.080250696434041e-05, "loss": 0.0217, "step": 159030 }, { "epoch": 38.19, "learning_rate": 7.079924276411111e-05, "loss": 0.0259, "step": 159040 }, { "epoch": 38.2, "learning_rate": 7.079597845668235e-05, "loss": 0.0145, "step": 159050 }, { "epoch": 38.2, "learning_rate": 7.079271404207095e-05, "loss": 0.0099, "step": 159060 }, { "epoch": 38.2, "learning_rate": 7.078944952029371e-05, "loss": 0.0122, "step": 159070 }, { "epoch": 38.2, "learning_rate": 7.078618489136748e-05, "loss": 0.0096, "step": 159080 }, { "epoch": 38.2, "learning_rate": 7.07829201553091e-05, "loss": 0.0085, "step": 159090 }, { "epoch": 38.21, "learning_rate": 7.077965531213535e-05, "loss": 0.0201, "step": 159100 }, { "epoch": 38.21, "learning_rate": 7.077639036186309e-05, "loss": 0.0228, "step": 159110 }, { "epoch": 38.21, "learning_rate": 7.077312530450914e-05, "loss": 0.01, "step": 159120 }, { "epoch": 38.21, "learning_rate": 7.076986014009034e-05, "loss": 0.0193, "step": 159130 }, { "epoch": 38.22, "learning_rate": 7.07665948686235e-05, "loss": 0.0184, "step": 159140 }, { "epoch": 38.22, "learning_rate": 7.076332949012545e-05, "loss": 0.0162, "step": 159150 }, { "epoch": 38.22, "learning_rate": 7.076006400461303e-05, "loss": 0.0217, "step": 159160 }, { "epoch": 38.22, "learning_rate": 7.075679841210306e-05, "loss": 0.0115, "step": 159170 }, { "epoch": 38.23, "learning_rate": 7.075353271261239e-05, "loss": 0.0195, "step": 159180 }, { "epoch": 38.23, "learning_rate": 7.075026690615783e-05, "loss": 0.0209, "step": 159190 }, { "epoch": 38.23, "learning_rate": 7.074700099275623e-05, "loss": 0.019, "step": 159200 }, { "epoch": 38.23, "learning_rate": 7.07437349724244e-05, "loss": 0.0174, "step": 159210 }, { "epoch": 38.23, "learning_rate": 7.07404688451792e-05, "loss": 0.0166, "step": 159220 }, { "epoch": 38.24, "learning_rate": 7.073720261103744e-05, "loss": 0.0148, "step": 159230 }, { "epoch": 38.24, "learning_rate": 7.073393627001596e-05, "loss": 0.0223, "step": 159240 }, { "epoch": 38.24, "learning_rate": 7.073066982213161e-05, "loss": 0.011, "step": 159250 }, { "epoch": 38.24, "learning_rate": 7.072740326740123e-05, "loss": 0.0161, "step": 159260 }, { "epoch": 38.25, "learning_rate": 7.072413660584161e-05, "loss": 0.0121, "step": 159270 }, { "epoch": 38.25, "learning_rate": 7.072086983746964e-05, "loss": 0.0177, "step": 159280 }, { "epoch": 38.25, "learning_rate": 7.071760296230212e-05, "loss": 0.0113, "step": 159290 }, { "epoch": 38.25, "learning_rate": 7.071433598035591e-05, "loss": 0.0178, "step": 159300 }, { "epoch": 38.26, "learning_rate": 7.071106889164782e-05, "loss": 0.0183, "step": 159310 }, { "epoch": 38.26, "learning_rate": 7.070780169619473e-05, "loss": 0.0115, "step": 159320 }, { "epoch": 38.26, "learning_rate": 7.070453439401345e-05, "loss": 0.0222, "step": 159330 }, { "epoch": 38.26, "learning_rate": 7.070126698512083e-05, "loss": 0.0108, "step": 159340 }, { "epoch": 38.26, "learning_rate": 7.06979994695337e-05, "loss": 0.0155, "step": 159350 }, { "epoch": 38.27, "learning_rate": 7.06947318472689e-05, "loss": 0.0184, "step": 159360 }, { "epoch": 38.27, "learning_rate": 7.069146411834329e-05, "loss": 0.0114, "step": 159370 }, { "epoch": 38.27, "learning_rate": 7.06881962827737e-05, "loss": 0.0083, "step": 159380 }, { "epoch": 38.27, "learning_rate": 7.068492834057697e-05, "loss": 0.0103, "step": 159390 }, { "epoch": 38.28, "learning_rate": 7.068166029176996e-05, "loss": 0.0185, "step": 159400 }, { "epoch": 38.28, "learning_rate": 7.067839213636948e-05, "loss": 0.0072, "step": 159410 }, { "epoch": 38.28, "learning_rate": 7.067512387439242e-05, "loss": 0.0169, "step": 159420 }, { "epoch": 38.28, "learning_rate": 7.067185550585557e-05, "loss": 0.0112, "step": 159430 }, { "epoch": 38.28, "learning_rate": 7.066858703077582e-05, "loss": 0.0151, "step": 159440 }, { "epoch": 38.29, "learning_rate": 7.066531844916999e-05, "loss": 0.0169, "step": 159450 }, { "epoch": 38.29, "learning_rate": 7.066204976105495e-05, "loss": 0.0115, "step": 159460 }, { "epoch": 38.29, "learning_rate": 7.065878096644753e-05, "loss": 0.0125, "step": 159470 }, { "epoch": 38.29, "learning_rate": 7.065551206536456e-05, "loss": 0.0153, "step": 159480 }, { "epoch": 38.3, "learning_rate": 7.065224305782293e-05, "loss": 0.0137, "step": 159490 }, { "epoch": 38.3, "learning_rate": 7.064897394383946e-05, "loss": 0.0148, "step": 159500 }, { "epoch": 38.3, "learning_rate": 7.0645704723431e-05, "loss": 0.0105, "step": 159510 }, { "epoch": 38.3, "learning_rate": 7.064243539661441e-05, "loss": 0.0136, "step": 159520 }, { "epoch": 38.31, "learning_rate": 7.063916596340654e-05, "loss": 0.0132, "step": 159530 }, { "epoch": 38.31, "learning_rate": 7.063589642382423e-05, "loss": 0.0067, "step": 159540 }, { "epoch": 38.31, "learning_rate": 7.063262677788435e-05, "loss": 0.0163, "step": 159550 }, { "epoch": 38.31, "learning_rate": 7.062935702560372e-05, "loss": 0.0184, "step": 159560 }, { "epoch": 38.31, "learning_rate": 7.062608716699923e-05, "loss": 0.027, "step": 159570 }, { "epoch": 38.32, "learning_rate": 7.06228172020877e-05, "loss": 0.017, "step": 159580 }, { "epoch": 38.32, "learning_rate": 7.0619547130886e-05, "loss": 0.0204, "step": 159590 }, { "epoch": 38.32, "learning_rate": 7.061627695341099e-05, "loss": 0.0208, "step": 159600 }, { "epoch": 38.32, "learning_rate": 7.061300666967951e-05, "loss": 0.0264, "step": 159610 }, { "epoch": 38.33, "learning_rate": 7.060973627970843e-05, "loss": 0.0099, "step": 159620 }, { "epoch": 38.33, "learning_rate": 7.060646578351459e-05, "loss": 0.0155, "step": 159630 }, { "epoch": 38.33, "learning_rate": 7.060319518111483e-05, "loss": 0.0205, "step": 159640 }, { "epoch": 38.33, "learning_rate": 7.059992447252606e-05, "loss": 0.0156, "step": 159650 }, { "epoch": 38.34, "learning_rate": 7.05966536577651e-05, "loss": 0.0133, "step": 159660 }, { "epoch": 38.34, "learning_rate": 7.059338273684881e-05, "loss": 0.0109, "step": 159670 }, { "epoch": 38.34, "learning_rate": 7.059011170979404e-05, "loss": 0.0151, "step": 159680 }, { "epoch": 38.34, "learning_rate": 7.05868405766177e-05, "loss": 0.0093, "step": 159690 }, { "epoch": 38.34, "learning_rate": 7.058356933733659e-05, "loss": 0.0182, "step": 159700 }, { "epoch": 38.35, "learning_rate": 7.058029799196759e-05, "loss": 0.0286, "step": 159710 }, { "epoch": 38.35, "learning_rate": 7.057702654052757e-05, "loss": 0.016, "step": 159720 }, { "epoch": 38.35, "learning_rate": 7.057375498303337e-05, "loss": 0.0153, "step": 159730 }, { "epoch": 38.35, "learning_rate": 7.057048331950186e-05, "loss": 0.0203, "step": 159740 }, { "epoch": 38.36, "learning_rate": 7.056721154994992e-05, "loss": 0.0199, "step": 159750 }, { "epoch": 38.36, "learning_rate": 7.056393967439442e-05, "loss": 0.0264, "step": 159760 }, { "epoch": 38.36, "learning_rate": 7.05606676928522e-05, "loss": 0.0058, "step": 159770 }, { "epoch": 38.36, "learning_rate": 7.05573956053401e-05, "loss": 0.009, "step": 159780 }, { "epoch": 38.36, "learning_rate": 7.0554123411875e-05, "loss": 0.0138, "step": 159790 }, { "epoch": 38.37, "learning_rate": 7.055085111247379e-05, "loss": 0.0255, "step": 159800 }, { "epoch": 38.37, "learning_rate": 7.054757870715334e-05, "loss": 0.0121, "step": 159810 }, { "epoch": 38.37, "learning_rate": 7.054430619593048e-05, "loss": 0.0203, "step": 159820 }, { "epoch": 38.37, "learning_rate": 7.054103357882211e-05, "loss": 0.0185, "step": 159830 }, { "epoch": 38.38, "learning_rate": 7.053776085584508e-05, "loss": 0.0084, "step": 159840 }, { "epoch": 38.38, "learning_rate": 7.053448802701623e-05, "loss": 0.0168, "step": 159850 }, { "epoch": 38.38, "learning_rate": 7.053121509235248e-05, "loss": 0.0104, "step": 159860 }, { "epoch": 38.38, "learning_rate": 7.052794205187067e-05, "loss": 0.0205, "step": 159870 }, { "epoch": 38.39, "learning_rate": 7.052466890558769e-05, "loss": 0.0078, "step": 159880 }, { "epoch": 38.39, "learning_rate": 7.052139565352037e-05, "loss": 0.018, "step": 159890 }, { "epoch": 38.39, "learning_rate": 7.051812229568561e-05, "loss": 0.0122, "step": 159900 }, { "epoch": 38.39, "learning_rate": 7.05148488321003e-05, "loss": 0.0093, "step": 159910 }, { "epoch": 38.39, "learning_rate": 7.051157526278127e-05, "loss": 0.011, "step": 159920 }, { "epoch": 38.4, "learning_rate": 7.050830158774541e-05, "loss": 0.0218, "step": 159930 }, { "epoch": 38.4, "learning_rate": 7.050502780700959e-05, "loss": 0.02, "step": 159940 }, { "epoch": 38.4, "learning_rate": 7.050175392059069e-05, "loss": 0.0161, "step": 159950 }, { "epoch": 38.4, "learning_rate": 7.049847992850558e-05, "loss": 0.0189, "step": 159960 }, { "epoch": 38.41, "learning_rate": 7.049520583077111e-05, "loss": 0.013, "step": 159970 }, { "epoch": 38.41, "learning_rate": 7.049193162740422e-05, "loss": 0.0139, "step": 159980 }, { "epoch": 38.41, "learning_rate": 7.048865731842172e-05, "loss": 0.0136, "step": 159990 }, { "epoch": 38.41, "learning_rate": 7.048538290384051e-05, "loss": 0.01, "step": 160000 }, { "epoch": 38.41, "learning_rate": 7.048210838367747e-05, "loss": 0.0158, "step": 160010 }, { "epoch": 38.42, "learning_rate": 7.047883375794945e-05, "loss": 0.0167, "step": 160020 }, { "epoch": 38.42, "learning_rate": 7.047555902667337e-05, "loss": 0.014, "step": 160030 }, { "epoch": 38.42, "learning_rate": 7.04722841898661e-05, "loss": 0.0143, "step": 160040 }, { "epoch": 38.42, "learning_rate": 7.04690092475445e-05, "loss": 0.0178, "step": 160050 }, { "epoch": 38.43, "learning_rate": 7.046573419972544e-05, "loss": 0.0109, "step": 160060 }, { "epoch": 38.43, "learning_rate": 7.046245904642582e-05, "loss": 0.0149, "step": 160070 }, { "epoch": 38.43, "learning_rate": 7.045918378766252e-05, "loss": 0.0156, "step": 160080 }, { "epoch": 38.43, "learning_rate": 7.045590842345242e-05, "loss": 0.0187, "step": 160090 }, { "epoch": 38.44, "learning_rate": 7.045263295381238e-05, "loss": 0.0213, "step": 160100 }, { "epoch": 38.44, "learning_rate": 7.044935737875929e-05, "loss": 0.0198, "step": 160110 }, { "epoch": 38.44, "learning_rate": 7.044608169831007e-05, "loss": 0.0092, "step": 160120 }, { "epoch": 38.44, "learning_rate": 7.044280591248157e-05, "loss": 0.0186, "step": 160130 }, { "epoch": 38.44, "learning_rate": 7.043953002129067e-05, "loss": 0.0143, "step": 160140 }, { "epoch": 38.45, "learning_rate": 7.043625402475426e-05, "loss": 0.0134, "step": 160150 }, { "epoch": 38.45, "learning_rate": 7.043297792288923e-05, "loss": 0.0275, "step": 160160 }, { "epoch": 38.45, "learning_rate": 7.042970171571246e-05, "loss": 0.0162, "step": 160170 }, { "epoch": 38.45, "learning_rate": 7.042642540324084e-05, "loss": 0.0135, "step": 160180 }, { "epoch": 38.46, "learning_rate": 7.042314898549125e-05, "loss": 0.0136, "step": 160190 }, { "epoch": 38.46, "learning_rate": 7.041987246248058e-05, "loss": 0.0145, "step": 160200 }, { "epoch": 38.46, "learning_rate": 7.04165958342257e-05, "loss": 0.014, "step": 160210 }, { "epoch": 38.46, "learning_rate": 7.041331910074354e-05, "loss": 0.0116, "step": 160220 }, { "epoch": 38.47, "learning_rate": 7.041004226205094e-05, "loss": 0.018, "step": 160230 }, { "epoch": 38.47, "learning_rate": 7.040676531816484e-05, "loss": 0.0102, "step": 160240 }, { "epoch": 38.47, "learning_rate": 7.040348826910208e-05, "loss": 0.007, "step": 160250 }, { "epoch": 38.47, "learning_rate": 7.040021111487958e-05, "loss": 0.0067, "step": 160260 }, { "epoch": 38.47, "learning_rate": 7.039693385551421e-05, "loss": 0.02, "step": 160270 }, { "epoch": 38.48, "learning_rate": 7.039365649102287e-05, "loss": 0.0109, "step": 160280 }, { "epoch": 38.48, "learning_rate": 7.039037902142246e-05, "loss": 0.0139, "step": 160290 }, { "epoch": 38.48, "learning_rate": 7.038710144672987e-05, "loss": 0.0129, "step": 160300 }, { "epoch": 38.48, "learning_rate": 7.0383823766962e-05, "loss": 0.0164, "step": 160310 }, { "epoch": 38.49, "learning_rate": 7.038054598213571e-05, "loss": 0.0259, "step": 160320 }, { "epoch": 38.49, "learning_rate": 7.037726809226793e-05, "loss": 0.0129, "step": 160330 }, { "epoch": 38.49, "learning_rate": 7.037399009737554e-05, "loss": 0.0181, "step": 160340 }, { "epoch": 38.49, "learning_rate": 7.037071199747544e-05, "loss": 0.0152, "step": 160350 }, { "epoch": 38.49, "learning_rate": 7.036743379258451e-05, "loss": 0.0187, "step": 160360 }, { "epoch": 38.5, "learning_rate": 7.036415548271964e-05, "loss": 0.0143, "step": 160370 }, { "epoch": 38.5, "learning_rate": 7.036087706789777e-05, "loss": 0.0119, "step": 160380 }, { "epoch": 38.5, "learning_rate": 7.035759854813576e-05, "loss": 0.0132, "step": 160390 }, { "epoch": 38.5, "learning_rate": 7.035431992345051e-05, "loss": 0.0197, "step": 160400 }, { "epoch": 38.51, "learning_rate": 7.035104119385893e-05, "loss": 0.013, "step": 160410 }, { "epoch": 38.51, "learning_rate": 7.03477623593779e-05, "loss": 0.0155, "step": 160420 }, { "epoch": 38.51, "learning_rate": 7.034448342002435e-05, "loss": 0.0121, "step": 160430 }, { "epoch": 38.51, "learning_rate": 7.034120437581516e-05, "loss": 0.0172, "step": 160440 }, { "epoch": 38.52, "learning_rate": 7.033792522676723e-05, "loss": 0.0178, "step": 160450 }, { "epoch": 38.52, "learning_rate": 7.033464597289747e-05, "loss": 0.015, "step": 160460 }, { "epoch": 38.52, "learning_rate": 7.033136661422276e-05, "loss": 0.0112, "step": 160470 }, { "epoch": 38.52, "learning_rate": 7.032808715076003e-05, "loss": 0.0332, "step": 160480 }, { "epoch": 38.52, "learning_rate": 7.032480758252617e-05, "loss": 0.0174, "step": 160490 }, { "epoch": 38.53, "learning_rate": 7.032152790953807e-05, "loss": 0.0129, "step": 160500 }, { "epoch": 38.53, "learning_rate": 7.031824813181266e-05, "loss": 0.0188, "step": 160510 }, { "epoch": 38.53, "learning_rate": 7.031496824936682e-05, "loss": 0.0175, "step": 160520 }, { "epoch": 38.53, "learning_rate": 7.031168826221747e-05, "loss": 0.0157, "step": 160530 }, { "epoch": 38.54, "learning_rate": 7.03084081703815e-05, "loss": 0.0219, "step": 160540 }, { "epoch": 38.54, "learning_rate": 7.030512797387583e-05, "loss": 0.0098, "step": 160550 }, { "epoch": 38.54, "learning_rate": 7.030184767271735e-05, "loss": 0.0317, "step": 160560 }, { "epoch": 38.54, "learning_rate": 7.0298567266923e-05, "loss": 0.0105, "step": 160570 }, { "epoch": 38.55, "learning_rate": 7.029528675650964e-05, "loss": 0.021, "step": 160580 }, { "epoch": 38.55, "learning_rate": 7.029200614149421e-05, "loss": 0.0226, "step": 160590 }, { "epoch": 38.55, "learning_rate": 7.028872542189362e-05, "loss": 0.0151, "step": 160600 }, { "epoch": 38.55, "learning_rate": 7.028544459772476e-05, "loss": 0.0154, "step": 160610 }, { "epoch": 38.55, "learning_rate": 7.028216366900457e-05, "loss": 0.0115, "step": 160620 }, { "epoch": 38.56, "learning_rate": 7.027888263574991e-05, "loss": 0.0225, "step": 160630 }, { "epoch": 38.56, "learning_rate": 7.027560149797774e-05, "loss": 0.0259, "step": 160640 }, { "epoch": 38.56, "learning_rate": 7.027232025570494e-05, "loss": 0.0131, "step": 160650 }, { "epoch": 38.56, "learning_rate": 7.026903890894842e-05, "loss": 0.0198, "step": 160660 }, { "epoch": 38.57, "learning_rate": 7.026575745772513e-05, "loss": 0.0132, "step": 160670 }, { "epoch": 38.57, "learning_rate": 7.026247590205194e-05, "loss": 0.0174, "step": 160680 }, { "epoch": 38.57, "learning_rate": 7.025919424194578e-05, "loss": 0.0133, "step": 160690 }, { "epoch": 38.57, "learning_rate": 7.025591247742357e-05, "loss": 0.0095, "step": 160700 }, { "epoch": 38.57, "learning_rate": 7.025263060850222e-05, "loss": 0.0203, "step": 160710 }, { "epoch": 38.58, "learning_rate": 7.024934863519863e-05, "loss": 0.0144, "step": 160720 }, { "epoch": 38.58, "learning_rate": 7.024606655752973e-05, "loss": 0.0081, "step": 160730 }, { "epoch": 38.58, "learning_rate": 7.024278437551244e-05, "loss": 0.0156, "step": 160740 }, { "epoch": 38.58, "learning_rate": 7.023950208916368e-05, "loss": 0.0269, "step": 160750 }, { "epoch": 38.59, "learning_rate": 7.023621969850034e-05, "loss": 0.0233, "step": 160760 }, { "epoch": 38.59, "learning_rate": 7.023293720353937e-05, "loss": 0.0261, "step": 160770 }, { "epoch": 38.59, "learning_rate": 7.022965460429767e-05, "loss": 0.0165, "step": 160780 }, { "epoch": 38.59, "learning_rate": 7.022637190079215e-05, "loss": 0.0252, "step": 160790 }, { "epoch": 38.6, "learning_rate": 7.022308909303974e-05, "loss": 0.026, "step": 160800 }, { "epoch": 38.6, "learning_rate": 7.021980618105736e-05, "loss": 0.0148, "step": 160810 }, { "epoch": 38.6, "learning_rate": 7.021652316486193e-05, "loss": 0.0143, "step": 160820 }, { "epoch": 38.6, "learning_rate": 7.021324004447039e-05, "loss": 0.0115, "step": 160830 }, { "epoch": 38.6, "learning_rate": 7.020995681989962e-05, "loss": 0.0212, "step": 160840 }, { "epoch": 38.61, "learning_rate": 7.020667349116656e-05, "loss": 0.0178, "step": 160850 }, { "epoch": 38.61, "learning_rate": 7.020339005828815e-05, "loss": 0.0141, "step": 160860 }, { "epoch": 38.61, "learning_rate": 7.020010652128131e-05, "loss": 0.0268, "step": 160870 }, { "epoch": 38.61, "learning_rate": 7.019682288016293e-05, "loss": 0.0203, "step": 160880 }, { "epoch": 38.62, "learning_rate": 7.019353913494996e-05, "loss": 0.0131, "step": 160890 }, { "epoch": 38.62, "learning_rate": 7.019025528565933e-05, "loss": 0.0176, "step": 160900 }, { "epoch": 38.62, "learning_rate": 7.018697133230794e-05, "loss": 0.0132, "step": 160910 }, { "epoch": 38.62, "learning_rate": 7.018368727491275e-05, "loss": 0.0213, "step": 160920 }, { "epoch": 38.63, "learning_rate": 7.018040311349065e-05, "loss": 0.021, "step": 160930 }, { "epoch": 38.63, "learning_rate": 7.01771188480586e-05, "loss": 0.0156, "step": 160940 }, { "epoch": 38.63, "learning_rate": 7.01738344786335e-05, "loss": 0.016, "step": 160950 }, { "epoch": 38.63, "learning_rate": 7.017055000523229e-05, "loss": 0.0222, "step": 160960 }, { "epoch": 38.63, "learning_rate": 7.01672654278719e-05, "loss": 0.0211, "step": 160970 }, { "epoch": 38.64, "learning_rate": 7.016398074656926e-05, "loss": 0.0108, "step": 160980 }, { "epoch": 38.64, "learning_rate": 7.01606959613413e-05, "loss": 0.0175, "step": 160990 }, { "epoch": 38.64, "learning_rate": 7.015741107220491e-05, "loss": 0.0287, "step": 161000 }, { "epoch": 38.64, "learning_rate": 7.015412607917708e-05, "loss": 0.0116, "step": 161010 }, { "epoch": 38.65, "learning_rate": 7.015084098227472e-05, "loss": 0.0137, "step": 161020 }, { "epoch": 38.65, "learning_rate": 7.014755578151473e-05, "loss": 0.0101, "step": 161030 }, { "epoch": 38.65, "learning_rate": 7.01442704769141e-05, "loss": 0.0139, "step": 161040 }, { "epoch": 38.65, "learning_rate": 7.014098506848971e-05, "loss": 0.0213, "step": 161050 }, { "epoch": 38.65, "learning_rate": 7.013769955625854e-05, "loss": 0.0128, "step": 161060 }, { "epoch": 38.66, "learning_rate": 7.013441394023748e-05, "loss": 0.0112, "step": 161070 }, { "epoch": 38.66, "learning_rate": 7.013112822044348e-05, "loss": 0.0107, "step": 161080 }, { "epoch": 38.66, "learning_rate": 7.012784239689348e-05, "loss": 0.0133, "step": 161090 }, { "epoch": 38.66, "learning_rate": 7.012455646960441e-05, "loss": 0.0221, "step": 161100 }, { "epoch": 38.67, "learning_rate": 7.012127043859322e-05, "loss": 0.0285, "step": 161110 }, { "epoch": 38.67, "learning_rate": 7.011798430387683e-05, "loss": 0.0113, "step": 161120 }, { "epoch": 38.67, "learning_rate": 7.011469806547218e-05, "loss": 0.0088, "step": 161130 }, { "epoch": 38.67, "learning_rate": 7.01114117233962e-05, "loss": 0.0172, "step": 161140 }, { "epoch": 38.68, "learning_rate": 7.010812527766585e-05, "loss": 0.0221, "step": 161150 }, { "epoch": 38.68, "learning_rate": 7.010483872829803e-05, "loss": 0.034, "step": 161160 }, { "epoch": 38.68, "learning_rate": 7.010155207530971e-05, "loss": 0.0146, "step": 161170 }, { "epoch": 38.68, "learning_rate": 7.009826531871783e-05, "loss": 0.0113, "step": 161180 }, { "epoch": 38.68, "learning_rate": 7.009497845853933e-05, "loss": 0.0192, "step": 161190 }, { "epoch": 38.69, "learning_rate": 7.009169149479115e-05, "loss": 0.0358, "step": 161200 }, { "epoch": 38.69, "learning_rate": 7.00884044274902e-05, "loss": 0.0086, "step": 161210 }, { "epoch": 38.69, "learning_rate": 7.008511725665346e-05, "loss": 0.0098, "step": 161220 }, { "epoch": 38.69, "learning_rate": 7.008182998229785e-05, "loss": 0.0133, "step": 161230 }, { "epoch": 38.7, "learning_rate": 7.007854260444033e-05, "loss": 0.0482, "step": 161240 }, { "epoch": 38.7, "learning_rate": 7.007525512309783e-05, "loss": 0.0116, "step": 161250 }, { "epoch": 38.7, "learning_rate": 7.007196753828728e-05, "loss": 0.0119, "step": 161260 }, { "epoch": 38.7, "learning_rate": 7.006867985002568e-05, "loss": 0.021, "step": 161270 }, { "epoch": 38.71, "learning_rate": 7.006539205832991e-05, "loss": 0.0129, "step": 161280 }, { "epoch": 38.71, "learning_rate": 7.006210416321695e-05, "loss": 0.0107, "step": 161290 }, { "epoch": 38.71, "learning_rate": 7.005881616470372e-05, "loss": 0.017, "step": 161300 }, { "epoch": 38.71, "learning_rate": 7.005552806280719e-05, "loss": 0.0162, "step": 161310 }, { "epoch": 38.71, "learning_rate": 7.00522398575443e-05, "loss": 0.0108, "step": 161320 }, { "epoch": 38.72, "learning_rate": 7.0048951548932e-05, "loss": 0.0126, "step": 161330 }, { "epoch": 38.72, "learning_rate": 7.004566313698726e-05, "loss": 0.013, "step": 161340 }, { "epoch": 38.72, "learning_rate": 7.004237462172698e-05, "loss": 0.0153, "step": 161350 }, { "epoch": 38.72, "learning_rate": 7.003908600316814e-05, "loss": 0.0167, "step": 161360 }, { "epoch": 38.73, "learning_rate": 7.003579728132767e-05, "loss": 0.0235, "step": 161370 }, { "epoch": 38.73, "learning_rate": 7.003250845622256e-05, "loss": 0.0154, "step": 161380 }, { "epoch": 38.73, "learning_rate": 7.002921952786972e-05, "loss": 0.02, "step": 161390 }, { "epoch": 38.73, "learning_rate": 7.002593049628611e-05, "loss": 0.0128, "step": 161400 }, { "epoch": 38.73, "learning_rate": 7.00226413614887e-05, "loss": 0.0226, "step": 161410 }, { "epoch": 38.74, "learning_rate": 7.001935212349442e-05, "loss": 0.01, "step": 161420 }, { "epoch": 38.74, "learning_rate": 7.001606278232024e-05, "loss": 0.0148, "step": 161430 }, { "epoch": 38.74, "learning_rate": 7.001277333798308e-05, "loss": 0.0113, "step": 161440 }, { "epoch": 38.74, "learning_rate": 7.000948379049994e-05, "loss": 0.0141, "step": 161450 }, { "epoch": 38.75, "learning_rate": 7.000619413988775e-05, "loss": 0.0179, "step": 161460 }, { "epoch": 38.75, "learning_rate": 7.000290438616346e-05, "loss": 0.022, "step": 161470 }, { "epoch": 38.75, "learning_rate": 6.999961452934404e-05, "loss": 0.0257, "step": 161480 }, { "epoch": 38.75, "learning_rate": 6.999632456944645e-05, "loss": 0.0141, "step": 161490 }, { "epoch": 38.76, "learning_rate": 6.999303450648763e-05, "loss": 0.0122, "step": 161500 }, { "epoch": 38.76, "learning_rate": 6.998974434048454e-05, "loss": 0.0145, "step": 161510 }, { "epoch": 38.76, "learning_rate": 6.998645407145415e-05, "loss": 0.0115, "step": 161520 }, { "epoch": 38.76, "learning_rate": 6.998316369941338e-05, "loss": 0.0235, "step": 161530 }, { "epoch": 38.76, "learning_rate": 6.997987322437924e-05, "loss": 0.0093, "step": 161540 }, { "epoch": 38.77, "learning_rate": 6.997658264636866e-05, "loss": 0.0254, "step": 161550 }, { "epoch": 38.77, "learning_rate": 6.997329196539862e-05, "loss": 0.0176, "step": 161560 }, { "epoch": 38.77, "learning_rate": 6.997000118148606e-05, "loss": 0.024, "step": 161570 }, { "epoch": 38.77, "learning_rate": 6.996671029464794e-05, "loss": 0.0121, "step": 161580 }, { "epoch": 38.78, "learning_rate": 6.996341930490123e-05, "loss": 0.0142, "step": 161590 }, { "epoch": 38.78, "learning_rate": 6.996012821226288e-05, "loss": 0.0137, "step": 161600 }, { "epoch": 38.78, "learning_rate": 6.995683701674989e-05, "loss": 0.0177, "step": 161610 }, { "epoch": 38.78, "learning_rate": 6.995354571837918e-05, "loss": 0.0257, "step": 161620 }, { "epoch": 38.79, "learning_rate": 6.995025431716771e-05, "loss": 0.0089, "step": 161630 }, { "epoch": 38.79, "learning_rate": 6.994696281313248e-05, "loss": 0.0085, "step": 161640 }, { "epoch": 38.79, "learning_rate": 6.994367120629044e-05, "loss": 0.0192, "step": 161650 }, { "epoch": 38.79, "learning_rate": 6.994037949665854e-05, "loss": 0.047, "step": 161660 }, { "epoch": 38.79, "learning_rate": 6.993708768425378e-05, "loss": 0.0178, "step": 161670 }, { "epoch": 38.8, "learning_rate": 6.993379576909309e-05, "loss": 0.0146, "step": 161680 }, { "epoch": 38.8, "learning_rate": 6.993050375119344e-05, "loss": 0.0175, "step": 161690 }, { "epoch": 38.8, "learning_rate": 6.992721163057183e-05, "loss": 0.0098, "step": 161700 }, { "epoch": 38.8, "learning_rate": 6.992391940724519e-05, "loss": 0.0153, "step": 161710 }, { "epoch": 38.81, "learning_rate": 6.99206270812305e-05, "loss": 0.0167, "step": 161720 }, { "epoch": 38.81, "learning_rate": 6.991733465254473e-05, "loss": 0.0298, "step": 161730 }, { "epoch": 38.81, "learning_rate": 6.991404212120486e-05, "loss": 0.012, "step": 161740 }, { "epoch": 38.81, "learning_rate": 6.991074948722784e-05, "loss": 0.0202, "step": 161750 }, { "epoch": 38.81, "learning_rate": 6.990745675063066e-05, "loss": 0.0143, "step": 161760 }, { "epoch": 38.82, "learning_rate": 6.990416391143027e-05, "loss": 0.0138, "step": 161770 }, { "epoch": 38.82, "learning_rate": 6.990087096964366e-05, "loss": 0.0193, "step": 161780 }, { "epoch": 38.82, "learning_rate": 6.989757792528781e-05, "loss": 0.0217, "step": 161790 }, { "epoch": 38.82, "learning_rate": 6.989428477837965e-05, "loss": 0.0217, "step": 161800 }, { "epoch": 38.83, "learning_rate": 6.98909915289362e-05, "loss": 0.0139, "step": 161810 }, { "epoch": 38.83, "learning_rate": 6.988769817697441e-05, "loss": 0.0123, "step": 161820 }, { "epoch": 38.83, "learning_rate": 6.988440472251124e-05, "loss": 0.0185, "step": 161830 }, { "epoch": 38.83, "learning_rate": 6.988111116556371e-05, "loss": 0.0144, "step": 161840 }, { "epoch": 38.84, "learning_rate": 6.987781750614875e-05, "loss": 0.0091, "step": 161850 }, { "epoch": 38.84, "learning_rate": 6.987452374428336e-05, "loss": 0.0173, "step": 161860 }, { "epoch": 38.84, "learning_rate": 6.98712298799845e-05, "loss": 0.0135, "step": 161870 }, { "epoch": 38.84, "learning_rate": 6.986793591326915e-05, "loss": 0.0118, "step": 161880 }, { "epoch": 38.84, "learning_rate": 6.986464184415432e-05, "loss": 0.0144, "step": 161890 }, { "epoch": 38.85, "learning_rate": 6.986134767265693e-05, "loss": 0.0094, "step": 161900 }, { "epoch": 38.85, "learning_rate": 6.9858053398794e-05, "loss": 0.012, "step": 161910 }, { "epoch": 38.85, "learning_rate": 6.98547590225825e-05, "loss": 0.0194, "step": 161920 }, { "epoch": 38.85, "learning_rate": 6.985146454403939e-05, "loss": 0.017, "step": 161930 }, { "epoch": 38.86, "learning_rate": 6.984816996318167e-05, "loss": 0.0082, "step": 161940 }, { "epoch": 38.86, "learning_rate": 6.984487528002632e-05, "loss": 0.0108, "step": 161950 }, { "epoch": 38.86, "learning_rate": 6.984158049459033e-05, "loss": 0.012, "step": 161960 }, { "epoch": 38.86, "learning_rate": 6.983828560689065e-05, "loss": 0.0064, "step": 161970 }, { "epoch": 38.87, "learning_rate": 6.983499061694429e-05, "loss": 0.0061, "step": 161980 }, { "epoch": 38.87, "learning_rate": 6.983169552476823e-05, "loss": 0.0116, "step": 161990 }, { "epoch": 38.87, "learning_rate": 6.982840033037944e-05, "loss": 0.0563, "step": 162000 }, { "epoch": 38.87, "learning_rate": 6.982510503379491e-05, "loss": 0.015, "step": 162010 }, { "epoch": 38.87, "learning_rate": 6.982180963503162e-05, "loss": 0.0205, "step": 162020 }, { "epoch": 38.88, "learning_rate": 6.981851413410655e-05, "loss": 0.0143, "step": 162030 }, { "epoch": 38.88, "learning_rate": 6.98152185310367e-05, "loss": 0.0134, "step": 162040 }, { "epoch": 38.88, "learning_rate": 6.981192282583903e-05, "loss": 0.0242, "step": 162050 }, { "epoch": 38.88, "learning_rate": 6.980862701853057e-05, "loss": 0.0111, "step": 162060 }, { "epoch": 38.89, "learning_rate": 6.980533110912827e-05, "loss": 0.019, "step": 162070 }, { "epoch": 38.89, "learning_rate": 6.980203509764913e-05, "loss": 0.0145, "step": 162080 }, { "epoch": 38.89, "learning_rate": 6.979873898411014e-05, "loss": 0.0094, "step": 162090 }, { "epoch": 38.89, "learning_rate": 6.979544276852827e-05, "loss": 0.0175, "step": 162100 }, { "epoch": 38.89, "learning_rate": 6.979214645092054e-05, "loss": 0.0217, "step": 162110 }, { "epoch": 38.9, "learning_rate": 6.978885003130391e-05, "loss": 0.0087, "step": 162120 }, { "epoch": 38.9, "learning_rate": 6.97855535096954e-05, "loss": 0.0161, "step": 162130 }, { "epoch": 38.9, "learning_rate": 6.978225688611197e-05, "loss": 0.0083, "step": 162140 }, { "epoch": 38.9, "learning_rate": 6.977896016057061e-05, "loss": 0.0167, "step": 162150 }, { "epoch": 38.91, "learning_rate": 6.977566333308834e-05, "loss": 0.0086, "step": 162160 }, { "epoch": 38.91, "learning_rate": 6.977236640368212e-05, "loss": 0.0056, "step": 162170 }, { "epoch": 38.91, "learning_rate": 6.976906937236896e-05, "loss": 0.0057, "step": 162180 }, { "epoch": 38.91, "learning_rate": 6.976577223916586e-05, "loss": 0.0417, "step": 162190 }, { "epoch": 38.92, "learning_rate": 6.976247500408981e-05, "loss": 0.0146, "step": 162200 }, { "epoch": 38.92, "learning_rate": 6.975917766715778e-05, "loss": 0.0115, "step": 162210 }, { "epoch": 38.92, "learning_rate": 6.97558802283868e-05, "loss": 0.0111, "step": 162220 }, { "epoch": 38.92, "learning_rate": 6.975258268779384e-05, "loss": 0.0168, "step": 162230 }, { "epoch": 38.92, "learning_rate": 6.974928504539591e-05, "loss": 0.0145, "step": 162240 }, { "epoch": 38.93, "learning_rate": 6.974598730121e-05, "loss": 0.0062, "step": 162250 }, { "epoch": 38.93, "learning_rate": 6.97426894552531e-05, "loss": 0.0095, "step": 162260 }, { "epoch": 38.93, "learning_rate": 6.973939150754222e-05, "loss": 0.0108, "step": 162270 }, { "epoch": 38.93, "learning_rate": 6.973609345809436e-05, "loss": 0.0138, "step": 162280 }, { "epoch": 38.94, "learning_rate": 6.973279530692649e-05, "loss": 0.0149, "step": 162290 }, { "epoch": 38.94, "learning_rate": 6.972949705405564e-05, "loss": 0.0122, "step": 162300 }, { "epoch": 38.94, "learning_rate": 6.972619869949879e-05, "loss": 0.0157, "step": 162310 }, { "epoch": 38.94, "learning_rate": 6.972290024327295e-05, "loss": 0.0108, "step": 162320 }, { "epoch": 38.95, "learning_rate": 6.971960168539511e-05, "loss": 0.018, "step": 162330 }, { "epoch": 38.95, "learning_rate": 6.971630302588228e-05, "loss": 0.0105, "step": 162340 }, { "epoch": 38.95, "learning_rate": 6.971300426475148e-05, "loss": 0.0172, "step": 162350 }, { "epoch": 39.0, "learning_rate": 6.970970540201967e-05, "loss": 0.0211, "step": 162360 }, { "epoch": 39.0, "learning_rate": 6.970640643770387e-05, "loss": 0.027, "step": 162370 }, { "epoch": 39.01, "learning_rate": 6.97031073718211e-05, "loss": 0.0088, "step": 162380 }, { "epoch": 39.01, "learning_rate": 6.969980820438834e-05, "loss": 0.01, "step": 162390 }, { "epoch": 39.01, "learning_rate": 6.96965089354226e-05, "loss": 0.0218, "step": 162400 }, { "epoch": 39.01, "learning_rate": 6.96932095649409e-05, "loss": 0.0183, "step": 162410 }, { "epoch": 39.01, "learning_rate": 6.968991009296024e-05, "loss": 0.0156, "step": 162420 }, { "epoch": 39.02, "learning_rate": 6.968661051949762e-05, "loss": 0.0211, "step": 162430 }, { "epoch": 39.02, "learning_rate": 6.968331084457003e-05, "loss": 0.0119, "step": 162440 }, { "epoch": 39.02, "learning_rate": 6.96800110681945e-05, "loss": 0.0203, "step": 162450 }, { "epoch": 39.02, "learning_rate": 6.967671119038802e-05, "loss": 0.0123, "step": 162460 }, { "epoch": 39.03, "learning_rate": 6.967341121116761e-05, "loss": 0.0109, "step": 162470 }, { "epoch": 39.03, "learning_rate": 6.967011113055028e-05, "loss": 0.0157, "step": 162480 }, { "epoch": 39.03, "learning_rate": 6.966681094855303e-05, "loss": 0.013, "step": 162490 }, { "epoch": 39.03, "learning_rate": 6.966351066519287e-05, "loss": 0.023, "step": 162500 }, { "epoch": 39.03, "learning_rate": 6.96602102804868e-05, "loss": 0.0227, "step": 162510 }, { "epoch": 39.04, "learning_rate": 6.965690979445185e-05, "loss": 0.019, "step": 162520 }, { "epoch": 39.04, "learning_rate": 6.965360920710503e-05, "loss": 0.0177, "step": 162530 }, { "epoch": 39.04, "learning_rate": 6.965030851846334e-05, "loss": 0.0141, "step": 162540 }, { "epoch": 39.04, "learning_rate": 6.964700772854379e-05, "loss": 0.015, "step": 162550 }, { "epoch": 39.05, "learning_rate": 6.96437068373634e-05, "loss": 0.0161, "step": 162560 }, { "epoch": 39.05, "learning_rate": 6.964040584493919e-05, "loss": 0.0067, "step": 162570 }, { "epoch": 39.05, "learning_rate": 6.963710475128817e-05, "loss": 0.0113, "step": 162580 }, { "epoch": 39.05, "learning_rate": 6.963380355642732e-05, "loss": 0.025, "step": 162590 }, { "epoch": 39.06, "learning_rate": 6.963050226037371e-05, "loss": 0.016, "step": 162600 }, { "epoch": 39.06, "learning_rate": 6.962720086314432e-05, "loss": 0.0116, "step": 162610 }, { "epoch": 39.06, "learning_rate": 6.962389936475616e-05, "loss": 0.0105, "step": 162620 }, { "epoch": 39.06, "learning_rate": 6.962059776522628e-05, "loss": 0.0096, "step": 162630 }, { "epoch": 39.06, "learning_rate": 6.961729606457166e-05, "loss": 0.0177, "step": 162640 }, { "epoch": 39.07, "learning_rate": 6.961399426280932e-05, "loss": 0.0146, "step": 162650 }, { "epoch": 39.07, "learning_rate": 6.96106923599563e-05, "loss": 0.0103, "step": 162660 }, { "epoch": 39.07, "learning_rate": 6.960739035602962e-05, "loss": 0.0114, "step": 162670 }, { "epoch": 39.07, "learning_rate": 6.960408825104627e-05, "loss": 0.0113, "step": 162680 }, { "epoch": 39.08, "learning_rate": 6.960078604502329e-05, "loss": 0.0226, "step": 162690 }, { "epoch": 39.08, "learning_rate": 6.95974837379777e-05, "loss": 0.0155, "step": 162700 }, { "epoch": 39.08, "learning_rate": 6.959418132992652e-05, "loss": 0.0163, "step": 162710 }, { "epoch": 39.08, "learning_rate": 6.959087882088677e-05, "loss": 0.0126, "step": 162720 }, { "epoch": 39.09, "learning_rate": 6.958757621087544e-05, "loss": 0.0084, "step": 162730 }, { "epoch": 39.09, "learning_rate": 6.958427349990959e-05, "loss": 0.0089, "step": 162740 }, { "epoch": 39.09, "learning_rate": 6.958097068800625e-05, "loss": 0.014, "step": 162750 }, { "epoch": 39.09, "learning_rate": 6.95776677751824e-05, "loss": 0.0083, "step": 162760 }, { "epoch": 39.09, "learning_rate": 6.957436476145508e-05, "loss": 0.0126, "step": 162770 }, { "epoch": 39.1, "learning_rate": 6.957106164684135e-05, "loss": 0.0211, "step": 162780 }, { "epoch": 39.1, "learning_rate": 6.956775843135818e-05, "loss": 0.0132, "step": 162790 }, { "epoch": 39.1, "learning_rate": 6.956445511502264e-05, "loss": 0.0173, "step": 162800 }, { "epoch": 39.1, "learning_rate": 6.956115169785173e-05, "loss": 0.0191, "step": 162810 }, { "epoch": 39.11, "learning_rate": 6.955784817986247e-05, "loss": 0.0091, "step": 162820 }, { "epoch": 39.11, "learning_rate": 6.955454456107189e-05, "loss": 0.015, "step": 162830 }, { "epoch": 39.11, "learning_rate": 6.955124084149704e-05, "loss": 0.0129, "step": 162840 }, { "epoch": 39.11, "learning_rate": 6.954793702115493e-05, "loss": 0.0237, "step": 162850 }, { "epoch": 39.11, "learning_rate": 6.954463310006258e-05, "loss": 0.0142, "step": 162860 }, { "epoch": 39.12, "learning_rate": 6.954132907823704e-05, "loss": 0.0159, "step": 162870 }, { "epoch": 39.12, "learning_rate": 6.953802495569533e-05, "loss": 0.0287, "step": 162880 }, { "epoch": 39.12, "learning_rate": 6.953472073245445e-05, "loss": 0.0149, "step": 162890 }, { "epoch": 39.12, "learning_rate": 6.953141640853147e-05, "loss": 0.0119, "step": 162900 }, { "epoch": 39.13, "learning_rate": 6.952811198394342e-05, "loss": 0.021, "step": 162910 }, { "epoch": 39.13, "learning_rate": 6.952480745870731e-05, "loss": 0.018, "step": 162920 }, { "epoch": 39.13, "learning_rate": 6.952150283284019e-05, "loss": 0.0111, "step": 162930 }, { "epoch": 39.13, "learning_rate": 6.951819810635904e-05, "loss": 0.0135, "step": 162940 }, { "epoch": 39.14, "learning_rate": 6.951489327928097e-05, "loss": 0.0108, "step": 162950 }, { "epoch": 39.14, "learning_rate": 6.951158835162297e-05, "loss": 0.0171, "step": 162960 }, { "epoch": 39.14, "learning_rate": 6.950828332340207e-05, "loss": 0.0089, "step": 162970 }, { "epoch": 39.14, "learning_rate": 6.950497819463532e-05, "loss": 0.0149, "step": 162980 }, { "epoch": 39.14, "learning_rate": 6.950167296533976e-05, "loss": 0.0096, "step": 162990 }, { "epoch": 39.15, "learning_rate": 6.94983676355324e-05, "loss": 0.0083, "step": 163000 }, { "epoch": 39.15, "learning_rate": 6.94950622052303e-05, "loss": 0.0102, "step": 163010 }, { "epoch": 39.15, "learning_rate": 6.949175667445048e-05, "loss": 0.0205, "step": 163020 }, { "epoch": 39.15, "learning_rate": 6.948845104320999e-05, "loss": 0.0118, "step": 163030 }, { "epoch": 39.16, "learning_rate": 6.948514531152586e-05, "loss": 0.0147, "step": 163040 }, { "epoch": 39.16, "learning_rate": 6.948183947941511e-05, "loss": 0.0151, "step": 163050 }, { "epoch": 39.16, "learning_rate": 6.947853354689483e-05, "loss": 0.0199, "step": 163060 }, { "epoch": 39.16, "learning_rate": 6.947522751398201e-05, "loss": 0.0288, "step": 163070 }, { "epoch": 39.17, "learning_rate": 6.947192138069369e-05, "loss": 0.0148, "step": 163080 }, { "epoch": 39.17, "learning_rate": 6.946861514704694e-05, "loss": 0.031, "step": 163090 }, { "epoch": 39.17, "learning_rate": 6.946530881305878e-05, "loss": 0.0254, "step": 163100 }, { "epoch": 39.17, "learning_rate": 6.946200237874625e-05, "loss": 0.0119, "step": 163110 }, { "epoch": 39.17, "learning_rate": 6.94586958441264e-05, "loss": 0.0213, "step": 163120 }, { "epoch": 39.18, "learning_rate": 6.945538920921628e-05, "loss": 0.0286, "step": 163130 }, { "epoch": 39.18, "learning_rate": 6.94520824740329e-05, "loss": 0.0139, "step": 163140 }, { "epoch": 39.18, "learning_rate": 6.944877563859335e-05, "loss": 0.0108, "step": 163150 }, { "epoch": 39.18, "learning_rate": 6.944546870291464e-05, "loss": 0.0149, "step": 163160 }, { "epoch": 39.19, "learning_rate": 6.94421616670138e-05, "loss": 0.012, "step": 163170 }, { "epoch": 39.19, "learning_rate": 6.943885453090793e-05, "loss": 0.0134, "step": 163180 }, { "epoch": 39.19, "learning_rate": 6.943554729461402e-05, "loss": 0.014, "step": 163190 }, { "epoch": 39.19, "learning_rate": 6.943223995814913e-05, "loss": 0.0121, "step": 163200 }, { "epoch": 39.19, "learning_rate": 6.942893252153035e-05, "loss": 0.0146, "step": 163210 }, { "epoch": 39.2, "learning_rate": 6.942562498477466e-05, "loss": 0.0121, "step": 163220 }, { "epoch": 39.2, "learning_rate": 6.942231734789914e-05, "loss": 0.01, "step": 163230 }, { "epoch": 39.2, "learning_rate": 6.941900961092083e-05, "loss": 0.0162, "step": 163240 }, { "epoch": 39.2, "learning_rate": 6.941570177385678e-05, "loss": 0.0097, "step": 163250 }, { "epoch": 39.21, "learning_rate": 6.941239383672405e-05, "loss": 0.0086, "step": 163260 }, { "epoch": 39.21, "learning_rate": 6.940908579953969e-05, "loss": 0.0099, "step": 163270 }, { "epoch": 39.21, "learning_rate": 6.940577766232072e-05, "loss": 0.0115, "step": 163280 }, { "epoch": 39.21, "learning_rate": 6.940246942508421e-05, "loss": 0.0112, "step": 163290 }, { "epoch": 39.22, "learning_rate": 6.939916108784722e-05, "loss": 0.0128, "step": 163300 }, { "epoch": 39.22, "learning_rate": 6.939585265062679e-05, "loss": 0.0165, "step": 163310 }, { "epoch": 39.22, "learning_rate": 6.939254411343998e-05, "loss": 0.0083, "step": 163320 }, { "epoch": 39.22, "learning_rate": 6.938923547630382e-05, "loss": 0.0119, "step": 163330 }, { "epoch": 39.22, "learning_rate": 6.938592673923539e-05, "loss": 0.0136, "step": 163340 }, { "epoch": 39.23, "learning_rate": 6.938261790225174e-05, "loss": 0.0227, "step": 163350 }, { "epoch": 39.23, "learning_rate": 6.937930896536989e-05, "loss": 0.0153, "step": 163360 }, { "epoch": 39.23, "learning_rate": 6.937599992860692e-05, "loss": 0.0181, "step": 163370 }, { "epoch": 39.23, "learning_rate": 6.93726907919799e-05, "loss": 0.0089, "step": 163380 }, { "epoch": 39.24, "learning_rate": 6.936938155550588e-05, "loss": 0.0217, "step": 163390 }, { "epoch": 39.24, "learning_rate": 6.936607221920188e-05, "loss": 0.0126, "step": 163400 }, { "epoch": 39.24, "learning_rate": 6.9362762783085e-05, "loss": 0.0067, "step": 163410 }, { "epoch": 39.24, "learning_rate": 6.935945324717227e-05, "loss": 0.0092, "step": 163420 }, { "epoch": 39.25, "learning_rate": 6.935614361148076e-05, "loss": 0.012, "step": 163430 }, { "epoch": 39.25, "learning_rate": 6.935283387602752e-05, "loss": 0.0126, "step": 163440 }, { "epoch": 39.25, "learning_rate": 6.934952404082961e-05, "loss": 0.0099, "step": 163450 }, { "epoch": 39.25, "learning_rate": 6.934621410590409e-05, "loss": 0.0167, "step": 163460 }, { "epoch": 39.25, "learning_rate": 6.934290407126805e-05, "loss": 0.0168, "step": 163470 }, { "epoch": 39.26, "learning_rate": 6.933959393693848e-05, "loss": 0.0124, "step": 163480 }, { "epoch": 39.26, "learning_rate": 6.933628370293251e-05, "loss": 0.0281, "step": 163490 }, { "epoch": 39.26, "learning_rate": 6.933297336926717e-05, "loss": 0.0119, "step": 163500 }, { "epoch": 39.26, "learning_rate": 6.93296629359595e-05, "loss": 0.0097, "step": 163510 }, { "epoch": 39.27, "learning_rate": 6.932635240302661e-05, "loss": 0.0185, "step": 163520 }, { "epoch": 39.27, "learning_rate": 6.932304177048554e-05, "loss": 0.0167, "step": 163530 }, { "epoch": 39.27, "learning_rate": 6.931973103835332e-05, "loss": 0.0108, "step": 163540 }, { "epoch": 39.27, "learning_rate": 6.931642020664706e-05, "loss": 0.0191, "step": 163550 }, { "epoch": 39.27, "learning_rate": 6.931310927538383e-05, "loss": 0.0091, "step": 163560 }, { "epoch": 39.28, "learning_rate": 6.930979824458065e-05, "loss": 0.0079, "step": 163570 }, { "epoch": 39.28, "learning_rate": 6.930648711425462e-05, "loss": 0.0195, "step": 163580 }, { "epoch": 39.28, "learning_rate": 6.930317588442279e-05, "loss": 0.006, "step": 163590 }, { "epoch": 39.28, "learning_rate": 6.929986455510222e-05, "loss": 0.0074, "step": 163600 }, { "epoch": 39.29, "learning_rate": 6.929655312631001e-05, "loss": 0.0166, "step": 163610 }, { "epoch": 39.29, "learning_rate": 6.929324159806319e-05, "loss": 0.0163, "step": 163620 }, { "epoch": 39.29, "learning_rate": 6.928992997037883e-05, "loss": 0.0129, "step": 163630 }, { "epoch": 39.29, "learning_rate": 6.928661824327403e-05, "loss": 0.0231, "step": 163640 }, { "epoch": 39.3, "learning_rate": 6.928330641676584e-05, "loss": 0.0147, "step": 163650 }, { "epoch": 39.3, "learning_rate": 6.92799944908713e-05, "loss": 0.0099, "step": 163660 }, { "epoch": 39.3, "learning_rate": 6.927668246560754e-05, "loss": 0.0255, "step": 163670 }, { "epoch": 39.3, "learning_rate": 6.927337034099157e-05, "loss": 0.0061, "step": 163680 }, { "epoch": 39.3, "learning_rate": 6.927005811704051e-05, "loss": 0.0218, "step": 163690 }, { "epoch": 39.31, "learning_rate": 6.92667457937714e-05, "loss": 0.0073, "step": 163700 }, { "epoch": 39.31, "learning_rate": 6.926343337120132e-05, "loss": 0.0116, "step": 163710 }, { "epoch": 39.31, "learning_rate": 6.926012084934735e-05, "loss": 0.0085, "step": 163720 }, { "epoch": 39.31, "learning_rate": 6.925680822822654e-05, "loss": 0.0139, "step": 163730 }, { "epoch": 39.32, "learning_rate": 6.925349550785597e-05, "loss": 0.0237, "step": 163740 }, { "epoch": 39.32, "learning_rate": 6.925018268825277e-05, "loss": 0.012, "step": 163750 }, { "epoch": 39.32, "learning_rate": 6.924686976943393e-05, "loss": 0.0138, "step": 163760 }, { "epoch": 39.32, "learning_rate": 6.924355675141658e-05, "loss": 0.0121, "step": 163770 }, { "epoch": 39.33, "learning_rate": 6.924024363421778e-05, "loss": 0.021, "step": 163780 }, { "epoch": 39.33, "learning_rate": 6.923693041785459e-05, "loss": 0.0128, "step": 163790 }, { "epoch": 39.33, "learning_rate": 6.92336171023441e-05, "loss": 0.0156, "step": 163800 }, { "epoch": 39.33, "learning_rate": 6.923030368770339e-05, "loss": 0.013, "step": 163810 }, { "epoch": 39.33, "learning_rate": 6.922699017394954e-05, "loss": 0.0155, "step": 163820 }, { "epoch": 39.34, "learning_rate": 6.922367656109961e-05, "loss": 0.016, "step": 163830 }, { "epoch": 39.34, "learning_rate": 6.922036284917069e-05, "loss": 0.0089, "step": 163840 }, { "epoch": 39.34, "learning_rate": 6.921704903817989e-05, "loss": 0.0062, "step": 163850 }, { "epoch": 39.34, "learning_rate": 6.921373512814422e-05, "loss": 0.0116, "step": 163860 }, { "epoch": 39.35, "learning_rate": 6.92104211190808e-05, "loss": 0.0112, "step": 163870 }, { "epoch": 39.35, "learning_rate": 6.920710701100672e-05, "loss": 0.0145, "step": 163880 }, { "epoch": 39.35, "learning_rate": 6.920379280393906e-05, "loss": 0.0166, "step": 163890 }, { "epoch": 39.35, "learning_rate": 6.920047849789489e-05, "loss": 0.0203, "step": 163900 }, { "epoch": 39.35, "learning_rate": 6.919716409289127e-05, "loss": 0.0092, "step": 163910 }, { "epoch": 39.36, "learning_rate": 6.919384958894532e-05, "loss": 0.0171, "step": 163920 }, { "epoch": 39.36, "learning_rate": 6.919053498607412e-05, "loss": 0.0148, "step": 163930 }, { "epoch": 39.36, "learning_rate": 6.918722028429474e-05, "loss": 0.0111, "step": 163940 }, { "epoch": 39.36, "learning_rate": 6.918390548362426e-05, "loss": 0.0148, "step": 163950 }, { "epoch": 39.37, "learning_rate": 6.918059058407978e-05, "loss": 0.0236, "step": 163960 }, { "epoch": 39.37, "learning_rate": 6.917727558567836e-05, "loss": 0.0189, "step": 163970 }, { "epoch": 39.37, "learning_rate": 6.91739604884371e-05, "loss": 0.0098, "step": 163980 }, { "epoch": 39.37, "learning_rate": 6.917064529237309e-05, "loss": 0.0089, "step": 163990 }, { "epoch": 39.38, "learning_rate": 6.916732999750344e-05, "loss": 0.0112, "step": 164000 }, { "epoch": 39.38, "learning_rate": 6.916401460384518e-05, "loss": 0.0247, "step": 164010 }, { "epoch": 39.38, "learning_rate": 6.916069911141546e-05, "loss": 0.0131, "step": 164020 }, { "epoch": 39.38, "learning_rate": 6.91573835202313e-05, "loss": 0.0138, "step": 164030 }, { "epoch": 39.38, "learning_rate": 6.915406783030983e-05, "loss": 0.0135, "step": 164040 }, { "epoch": 39.39, "learning_rate": 6.915075204166814e-05, "loss": 0.009, "step": 164050 }, { "epoch": 39.39, "learning_rate": 6.914743615432332e-05, "loss": 0.0078, "step": 164060 }, { "epoch": 39.39, "learning_rate": 6.914412016829246e-05, "loss": 0.0084, "step": 164070 }, { "epoch": 39.39, "learning_rate": 6.914080408359264e-05, "loss": 0.0068, "step": 164080 }, { "epoch": 39.4, "learning_rate": 6.913748790024095e-05, "loss": 0.0285, "step": 164090 }, { "epoch": 39.4, "learning_rate": 6.91341716182545e-05, "loss": 0.0112, "step": 164100 }, { "epoch": 39.4, "learning_rate": 6.913085523765035e-05, "loss": 0.0126, "step": 164110 }, { "epoch": 39.4, "learning_rate": 6.912753875844562e-05, "loss": 0.0118, "step": 164120 }, { "epoch": 39.41, "learning_rate": 6.91242221806574e-05, "loss": 0.0164, "step": 164130 }, { "epoch": 39.41, "learning_rate": 6.91209055043028e-05, "loss": 0.014, "step": 164140 }, { "epoch": 39.41, "learning_rate": 6.911758872939886e-05, "loss": 0.0125, "step": 164150 }, { "epoch": 39.41, "learning_rate": 6.911427185596271e-05, "loss": 0.0266, "step": 164160 }, { "epoch": 39.41, "learning_rate": 6.911095488401146e-05, "loss": 0.013, "step": 164170 }, { "epoch": 39.42, "learning_rate": 6.910763781356217e-05, "loss": 0.0145, "step": 164180 }, { "epoch": 39.42, "learning_rate": 6.910432064463196e-05, "loss": 0.022, "step": 164190 }, { "epoch": 39.42, "learning_rate": 6.910100337723793e-05, "loss": 0.0105, "step": 164200 }, { "epoch": 39.42, "learning_rate": 6.909768601139716e-05, "loss": 0.0053, "step": 164210 }, { "epoch": 39.43, "learning_rate": 6.909436854712676e-05, "loss": 0.0184, "step": 164220 }, { "epoch": 39.43, "learning_rate": 6.909105098444383e-05, "loss": 0.0164, "step": 164230 }, { "epoch": 39.43, "learning_rate": 6.908773332336546e-05, "loss": 0.0201, "step": 164240 }, { "epoch": 39.43, "learning_rate": 6.908441556390876e-05, "loss": 0.0148, "step": 164250 }, { "epoch": 39.43, "learning_rate": 6.908109770609082e-05, "loss": 0.0306, "step": 164260 }, { "epoch": 39.44, "learning_rate": 6.907777974992873e-05, "loss": 0.0186, "step": 164270 }, { "epoch": 39.44, "learning_rate": 6.907446169543963e-05, "loss": 0.0112, "step": 164280 }, { "epoch": 39.44, "learning_rate": 6.907114354264057e-05, "loss": 0.0091, "step": 164290 }, { "epoch": 39.44, "learning_rate": 6.906782529154868e-05, "loss": 0.0182, "step": 164300 }, { "epoch": 39.45, "learning_rate": 6.906450694218108e-05, "loss": 0.0119, "step": 164310 }, { "epoch": 39.45, "learning_rate": 6.906118849455481e-05, "loss": 0.0071, "step": 164320 }, { "epoch": 39.45, "learning_rate": 6.905786994868705e-05, "loss": 0.0126, "step": 164330 }, { "epoch": 39.45, "learning_rate": 6.905455130459485e-05, "loss": 0.0085, "step": 164340 }, { "epoch": 39.46, "learning_rate": 6.905123256229535e-05, "loss": 0.0071, "step": 164350 }, { "epoch": 39.46, "learning_rate": 6.904791372180563e-05, "loss": 0.0148, "step": 164360 }, { "epoch": 39.46, "learning_rate": 6.904459478314281e-05, "loss": 0.0196, "step": 164370 }, { "epoch": 39.46, "learning_rate": 6.904127574632397e-05, "loss": 0.0107, "step": 164380 }, { "epoch": 39.46, "learning_rate": 6.903795661136626e-05, "loss": 0.0116, "step": 164390 }, { "epoch": 39.47, "learning_rate": 6.903463737828675e-05, "loss": 0.0192, "step": 164400 }, { "epoch": 39.47, "learning_rate": 6.903131804710257e-05, "loss": 0.0147, "step": 164410 }, { "epoch": 39.47, "learning_rate": 6.90279986178308e-05, "loss": 0.0103, "step": 164420 }, { "epoch": 39.47, "learning_rate": 6.902467909048859e-05, "loss": 0.0069, "step": 164430 }, { "epoch": 39.48, "learning_rate": 6.9021359465093e-05, "loss": 0.0063, "step": 164440 }, { "epoch": 39.48, "learning_rate": 6.901803974166118e-05, "loss": 0.0056, "step": 164450 }, { "epoch": 39.48, "learning_rate": 6.901471992021021e-05, "loss": 0.012, "step": 164460 }, { "epoch": 39.48, "learning_rate": 6.901140000075723e-05, "loss": 0.0143, "step": 164470 }, { "epoch": 39.49, "learning_rate": 6.900807998331933e-05, "loss": 0.0108, "step": 164480 }, { "epoch": 39.49, "learning_rate": 6.900475986791363e-05, "loss": 0.0178, "step": 164490 }, { "epoch": 39.49, "learning_rate": 6.900143965455723e-05, "loss": 0.0125, "step": 164500 }, { "epoch": 39.49, "learning_rate": 6.899811934326725e-05, "loss": 0.016, "step": 164510 }, { "epoch": 39.49, "learning_rate": 6.89947989340608e-05, "loss": 0.015, "step": 164520 }, { "epoch": 39.5, "learning_rate": 6.899147842695501e-05, "loss": 0.0117, "step": 164530 }, { "epoch": 39.5, "learning_rate": 6.898815782196699e-05, "loss": 0.0172, "step": 164540 }, { "epoch": 39.5, "learning_rate": 6.898483711911383e-05, "loss": 0.0119, "step": 164550 }, { "epoch": 39.5, "learning_rate": 6.898151631841266e-05, "loss": 0.0099, "step": 164560 }, { "epoch": 39.51, "learning_rate": 6.897819541988062e-05, "loss": 0.0226, "step": 164570 }, { "epoch": 39.51, "learning_rate": 6.897487442353478e-05, "loss": 0.0074, "step": 164580 }, { "epoch": 39.51, "learning_rate": 6.897155332939228e-05, "loss": 0.0069, "step": 164590 }, { "epoch": 39.51, "learning_rate": 6.896823213747024e-05, "loss": 0.0124, "step": 164600 }, { "epoch": 39.51, "learning_rate": 6.896491084778577e-05, "loss": 0.0047, "step": 164610 }, { "epoch": 39.52, "learning_rate": 6.8961589460356e-05, "loss": 0.01, "step": 164620 }, { "epoch": 39.52, "learning_rate": 6.895826797519802e-05, "loss": 0.0088, "step": 164630 }, { "epoch": 39.52, "learning_rate": 6.895494639232898e-05, "loss": 0.024, "step": 164640 }, { "epoch": 39.52, "learning_rate": 6.8951624711766e-05, "loss": 0.0126, "step": 164650 }, { "epoch": 39.53, "learning_rate": 6.894830293352617e-05, "loss": 0.0142, "step": 164660 }, { "epoch": 39.53, "learning_rate": 6.894498105762664e-05, "loss": 0.0101, "step": 164670 }, { "epoch": 39.53, "learning_rate": 6.89416590840845e-05, "loss": 0.0158, "step": 164680 }, { "epoch": 39.53, "learning_rate": 6.893833701291689e-05, "loss": 0.0166, "step": 164690 }, { "epoch": 39.54, "learning_rate": 6.893501484414096e-05, "loss": 0.014, "step": 164700 }, { "epoch": 39.54, "learning_rate": 6.893169257777378e-05, "loss": 0.0211, "step": 164710 }, { "epoch": 39.54, "learning_rate": 6.892837021383253e-05, "loss": 0.0219, "step": 164720 }, { "epoch": 39.54, "learning_rate": 6.892504775233428e-05, "loss": 0.0172, "step": 164730 }, { "epoch": 39.54, "learning_rate": 6.892172519329619e-05, "loss": 0.0244, "step": 164740 }, { "epoch": 39.55, "learning_rate": 6.891840253673536e-05, "loss": 0.0504, "step": 164750 }, { "epoch": 39.55, "learning_rate": 6.891507978266892e-05, "loss": 0.014, "step": 164760 }, { "epoch": 39.55, "learning_rate": 6.8911756931114e-05, "loss": 0.0155, "step": 164770 }, { "epoch": 39.55, "learning_rate": 6.890843398208772e-05, "loss": 0.0277, "step": 164780 }, { "epoch": 39.56, "learning_rate": 6.890511093560722e-05, "loss": 0.0262, "step": 164790 }, { "epoch": 39.56, "learning_rate": 6.890178779168963e-05, "loss": 0.0159, "step": 164800 }, { "epoch": 39.56, "learning_rate": 6.889846455035206e-05, "loss": 0.0173, "step": 164810 }, { "epoch": 39.56, "learning_rate": 6.889514121161164e-05, "loss": 0.0145, "step": 164820 }, { "epoch": 39.57, "learning_rate": 6.889181777548551e-05, "loss": 0.0165, "step": 164830 }, { "epoch": 39.57, "learning_rate": 6.88884942419908e-05, "loss": 0.0125, "step": 164840 }, { "epoch": 39.57, "learning_rate": 6.888517061114463e-05, "loss": 0.0238, "step": 164850 }, { "epoch": 39.57, "learning_rate": 6.888184688296413e-05, "loss": 0.0169, "step": 164860 }, { "epoch": 39.57, "learning_rate": 6.887852305746644e-05, "loss": 0.0187, "step": 164870 }, { "epoch": 39.58, "learning_rate": 6.887519913466868e-05, "loss": 0.0089, "step": 164880 }, { "epoch": 39.58, "learning_rate": 6.887187511458798e-05, "loss": 0.0164, "step": 164890 }, { "epoch": 39.58, "learning_rate": 6.886855099724148e-05, "loss": 0.0184, "step": 164900 }, { "epoch": 39.58, "learning_rate": 6.88652267826463e-05, "loss": 0.0086, "step": 164910 }, { "epoch": 39.59, "learning_rate": 6.886190247081961e-05, "loss": 0.0049, "step": 164920 }, { "epoch": 39.59, "learning_rate": 6.88585780617785e-05, "loss": 0.0211, "step": 164930 }, { "epoch": 39.59, "learning_rate": 6.885525355554012e-05, "loss": 0.0303, "step": 164940 }, { "epoch": 39.59, "learning_rate": 6.885192895212162e-05, "loss": 0.0177, "step": 164950 }, { "epoch": 39.59, "learning_rate": 6.88486042515401e-05, "loss": 0.0148, "step": 164960 }, { "epoch": 39.6, "learning_rate": 6.884527945381273e-05, "loss": 0.0182, "step": 164970 }, { "epoch": 39.6, "learning_rate": 6.884195455895662e-05, "loss": 0.0201, "step": 164980 }, { "epoch": 39.6, "learning_rate": 6.883862956698893e-05, "loss": 0.0337, "step": 164990 }, { "epoch": 39.6, "learning_rate": 6.883530447792679e-05, "loss": 0.0178, "step": 165000 }, { "epoch": 39.61, "learning_rate": 6.883197929178733e-05, "loss": 0.0106, "step": 165010 }, { "epoch": 39.61, "learning_rate": 6.88286540085877e-05, "loss": 0.0132, "step": 165020 }, { "epoch": 39.61, "learning_rate": 6.8825328628345e-05, "loss": 0.0121, "step": 165030 }, { "epoch": 39.61, "learning_rate": 6.882200315107642e-05, "loss": 0.0266, "step": 165040 }, { "epoch": 39.62, "learning_rate": 6.881867757679908e-05, "loss": 0.0087, "step": 165050 }, { "epoch": 39.62, "learning_rate": 6.88153519055301e-05, "loss": 0.0217, "step": 165060 }, { "epoch": 39.62, "learning_rate": 6.881202613728666e-05, "loss": 0.0184, "step": 165070 }, { "epoch": 39.62, "learning_rate": 6.880870027208587e-05, "loss": 0.0201, "step": 165080 }, { "epoch": 39.62, "learning_rate": 6.880537430994489e-05, "loss": 0.0188, "step": 165090 }, { "epoch": 39.63, "learning_rate": 6.880204825088084e-05, "loss": 0.0245, "step": 165100 }, { "epoch": 39.63, "learning_rate": 6.879872209491087e-05, "loss": 0.0238, "step": 165110 }, { "epoch": 39.63, "learning_rate": 6.879539584205215e-05, "loss": 0.0089, "step": 165120 }, { "epoch": 39.63, "learning_rate": 6.87920694923218e-05, "loss": 0.0187, "step": 165130 }, { "epoch": 39.64, "learning_rate": 6.878874304573695e-05, "loss": 0.0152, "step": 165140 }, { "epoch": 39.64, "learning_rate": 6.878541650231479e-05, "loss": 0.0204, "step": 165150 }, { "epoch": 39.64, "learning_rate": 6.878208986207242e-05, "loss": 0.0224, "step": 165160 }, { "epoch": 39.64, "learning_rate": 6.877876312502701e-05, "loss": 0.0179, "step": 165170 }, { "epoch": 39.65, "learning_rate": 6.877543629119567e-05, "loss": 0.016, "step": 165180 }, { "epoch": 39.65, "learning_rate": 6.87721093605956e-05, "loss": 0.0154, "step": 165190 }, { "epoch": 39.65, "learning_rate": 6.876878233324391e-05, "loss": 0.0179, "step": 165200 }, { "epoch": 39.65, "learning_rate": 6.876545520915777e-05, "loss": 0.0133, "step": 165210 }, { "epoch": 39.65, "learning_rate": 6.876212798835432e-05, "loss": 0.0175, "step": 165220 }, { "epoch": 39.66, "learning_rate": 6.875880067085069e-05, "loss": 0.013, "step": 165230 }, { "epoch": 39.66, "learning_rate": 6.875547325666404e-05, "loss": 0.0115, "step": 165240 }, { "epoch": 39.66, "learning_rate": 6.875214574581155e-05, "loss": 0.0202, "step": 165250 }, { "epoch": 39.66, "learning_rate": 6.874881813831033e-05, "loss": 0.0143, "step": 165260 }, { "epoch": 39.67, "learning_rate": 6.874549043417753e-05, "loss": 0.0129, "step": 165270 }, { "epoch": 39.67, "learning_rate": 6.874216263343032e-05, "loss": 0.0167, "step": 165280 }, { "epoch": 39.67, "learning_rate": 6.873883473608588e-05, "loss": 0.0118, "step": 165290 }, { "epoch": 39.67, "learning_rate": 6.87355067421613e-05, "loss": 0.0167, "step": 165300 }, { "epoch": 39.67, "learning_rate": 6.873217865167377e-05, "loss": 0.0227, "step": 165310 }, { "epoch": 39.68, "learning_rate": 6.872885046464044e-05, "loss": 0.0069, "step": 165320 }, { "epoch": 39.68, "learning_rate": 6.872552218107844e-05, "loss": 0.0207, "step": 165330 }, { "epoch": 39.68, "learning_rate": 6.872219380100496e-05, "loss": 0.0156, "step": 165340 }, { "epoch": 39.68, "learning_rate": 6.871886532443712e-05, "loss": 0.0214, "step": 165350 }, { "epoch": 39.69, "learning_rate": 6.871553675139211e-05, "loss": 0.0206, "step": 165360 }, { "epoch": 39.69, "learning_rate": 6.871220808188706e-05, "loss": 0.0129, "step": 165370 }, { "epoch": 39.69, "learning_rate": 6.870887931593912e-05, "loss": 0.0146, "step": 165380 }, { "epoch": 39.69, "learning_rate": 6.870555045356547e-05, "loss": 0.012, "step": 165390 }, { "epoch": 39.7, "learning_rate": 6.870222149478326e-05, "loss": 0.0195, "step": 165400 }, { "epoch": 39.7, "learning_rate": 6.869889243960964e-05, "loss": 0.0139, "step": 165410 }, { "epoch": 39.7, "learning_rate": 6.869556328806178e-05, "loss": 0.0122, "step": 165420 }, { "epoch": 39.7, "learning_rate": 6.869223404015683e-05, "loss": 0.0142, "step": 165430 }, { "epoch": 39.7, "learning_rate": 6.868890469591194e-05, "loss": 0.0148, "step": 165440 }, { "epoch": 39.71, "learning_rate": 6.868557525534428e-05, "loss": 0.0147, "step": 165450 }, { "epoch": 39.71, "learning_rate": 6.868224571847102e-05, "loss": 0.0063, "step": 165460 }, { "epoch": 39.71, "learning_rate": 6.867891608530929e-05, "loss": 0.0154, "step": 165470 }, { "epoch": 39.71, "learning_rate": 6.867558635587628e-05, "loss": 0.0216, "step": 165480 }, { "epoch": 39.72, "learning_rate": 6.867225653018914e-05, "loss": 0.0305, "step": 165490 }, { "epoch": 39.72, "learning_rate": 6.866892660826505e-05, "loss": 0.0114, "step": 165500 }, { "epoch": 39.72, "learning_rate": 6.866559659012114e-05, "loss": 0.0135, "step": 165510 }, { "epoch": 39.72, "learning_rate": 6.86622664757746e-05, "loss": 0.0146, "step": 165520 }, { "epoch": 39.73, "learning_rate": 6.865893626524257e-05, "loss": 0.0173, "step": 165530 }, { "epoch": 39.73, "learning_rate": 6.865560595854221e-05, "loss": 0.0125, "step": 165540 }, { "epoch": 39.73, "learning_rate": 6.865227555569073e-05, "loss": 0.0149, "step": 165550 }, { "epoch": 39.73, "learning_rate": 6.864894505670527e-05, "loss": 0.0174, "step": 165560 }, { "epoch": 39.73, "learning_rate": 6.864561446160297e-05, "loss": 0.0161, "step": 165570 }, { "epoch": 39.74, "learning_rate": 6.864228377040103e-05, "loss": 0.0153, "step": 165580 }, { "epoch": 39.74, "learning_rate": 6.86389529831166e-05, "loss": 0.0235, "step": 165590 }, { "epoch": 39.74, "learning_rate": 6.863562209976685e-05, "loss": 0.0116, "step": 165600 }, { "epoch": 39.74, "learning_rate": 6.863229112036896e-05, "loss": 0.0173, "step": 165610 }, { "epoch": 39.75, "learning_rate": 6.862896004494007e-05, "loss": 0.0071, "step": 165620 }, { "epoch": 39.75, "learning_rate": 6.862562887349736e-05, "loss": 0.0233, "step": 165630 }, { "epoch": 39.75, "learning_rate": 6.862229760605802e-05, "loss": 0.02, "step": 165640 }, { "epoch": 39.75, "learning_rate": 6.861896624263919e-05, "loss": 0.0294, "step": 165650 }, { "epoch": 39.75, "learning_rate": 6.861563478325807e-05, "loss": 0.0328, "step": 165660 }, { "epoch": 39.76, "learning_rate": 6.861230322793179e-05, "loss": 0.0159, "step": 165670 }, { "epoch": 39.76, "learning_rate": 6.860897157667755e-05, "loss": 0.0225, "step": 165680 }, { "epoch": 39.76, "learning_rate": 6.860563982951253e-05, "loss": 0.0083, "step": 165690 }, { "epoch": 39.76, "learning_rate": 6.860230798645386e-05, "loss": 0.0228, "step": 165700 }, { "epoch": 39.77, "learning_rate": 6.859897604751875e-05, "loss": 0.0186, "step": 165710 }, { "epoch": 39.77, "learning_rate": 6.859564401272438e-05, "loss": 0.0098, "step": 165720 }, { "epoch": 39.77, "learning_rate": 6.859231188208787e-05, "loss": 0.0128, "step": 165730 }, { "epoch": 39.77, "learning_rate": 6.858897965562647e-05, "loss": 0.0279, "step": 165740 }, { "epoch": 39.78, "learning_rate": 6.858564733335728e-05, "loss": 0.0161, "step": 165750 }, { "epoch": 39.78, "learning_rate": 6.858231491529754e-05, "loss": 0.0129, "step": 165760 }, { "epoch": 39.78, "learning_rate": 6.857898240146437e-05, "loss": 0.0207, "step": 165770 }, { "epoch": 39.78, "learning_rate": 6.857564979187496e-05, "loss": 0.0184, "step": 165780 }, { "epoch": 39.78, "learning_rate": 6.857231708654653e-05, "loss": 0.0098, "step": 165790 }, { "epoch": 39.79, "learning_rate": 6.85689842854962e-05, "loss": 0.0176, "step": 165800 }, { "epoch": 39.79, "learning_rate": 6.856565138874118e-05, "loss": 0.0193, "step": 165810 }, { "epoch": 39.79, "learning_rate": 6.856231839629864e-05, "loss": 0.0161, "step": 165820 }, { "epoch": 39.79, "learning_rate": 6.855898530818573e-05, "loss": 0.0172, "step": 165830 }, { "epoch": 39.8, "learning_rate": 6.855565212441967e-05, "loss": 0.0147, "step": 165840 }, { "epoch": 39.8, "learning_rate": 6.855231884501761e-05, "loss": 0.0117, "step": 165850 }, { "epoch": 39.8, "learning_rate": 6.854898546999678e-05, "loss": 0.0137, "step": 165860 }, { "epoch": 39.8, "learning_rate": 6.854565199937429e-05, "loss": 0.0134, "step": 165870 }, { "epoch": 39.81, "learning_rate": 6.854231843316738e-05, "loss": 0.0126, "step": 165880 }, { "epoch": 39.81, "learning_rate": 6.853898477139317e-05, "loss": 0.0107, "step": 165890 }, { "epoch": 39.81, "learning_rate": 6.853565101406891e-05, "loss": 0.0169, "step": 165900 }, { "epoch": 39.81, "learning_rate": 6.853231716121175e-05, "loss": 0.0136, "step": 165910 }, { "epoch": 39.81, "learning_rate": 6.852898321283886e-05, "loss": 0.0117, "step": 165920 }, { "epoch": 39.82, "learning_rate": 6.852564916896743e-05, "loss": 0.0115, "step": 165930 }, { "epoch": 39.82, "learning_rate": 6.852231502961466e-05, "loss": 0.0098, "step": 165940 }, { "epoch": 39.82, "learning_rate": 6.851898079479772e-05, "loss": 0.0093, "step": 165950 }, { "epoch": 39.82, "learning_rate": 6.851564646453382e-05, "loss": 0.0202, "step": 165960 }, { "epoch": 39.83, "learning_rate": 6.851231203884009e-05, "loss": 0.0105, "step": 165970 }, { "epoch": 39.83, "learning_rate": 6.850897751773377e-05, "loss": 0.0137, "step": 165980 }, { "epoch": 39.83, "learning_rate": 6.8505642901232e-05, "loss": 0.0147, "step": 165990 }, { "epoch": 39.83, "learning_rate": 6.850230818935201e-05, "loss": 0.0154, "step": 166000 }, { "epoch": 39.83, "learning_rate": 6.849897338211098e-05, "loss": 0.0163, "step": 166010 }, { "epoch": 39.84, "learning_rate": 6.849563847952607e-05, "loss": 0.0074, "step": 166020 }, { "epoch": 39.84, "learning_rate": 6.849230348161448e-05, "loss": 0.0056, "step": 166030 }, { "epoch": 39.84, "learning_rate": 6.848896838839341e-05, "loss": 0.0186, "step": 166040 }, { "epoch": 39.84, "learning_rate": 6.848563319988005e-05, "loss": 0.0104, "step": 166050 }, { "epoch": 39.85, "learning_rate": 6.848229791609158e-05, "loss": 0.0081, "step": 166060 }, { "epoch": 39.85, "learning_rate": 6.847896253704518e-05, "loss": 0.0123, "step": 166070 }, { "epoch": 39.85, "learning_rate": 6.847562706275808e-05, "loss": 0.017, "step": 166080 }, { "epoch": 39.85, "learning_rate": 6.84722914932474e-05, "loss": 0.016, "step": 166090 }, { "epoch": 39.86, "learning_rate": 6.846895582853042e-05, "loss": 0.008, "step": 166100 }, { "epoch": 39.86, "learning_rate": 6.846562006862426e-05, "loss": 0.0114, "step": 166110 }, { "epoch": 39.86, "learning_rate": 6.846228421354614e-05, "loss": 0.0101, "step": 166120 }, { "epoch": 39.86, "learning_rate": 6.845894826331328e-05, "loss": 0.0085, "step": 166130 }, { "epoch": 39.86, "learning_rate": 6.845561221794281e-05, "loss": 0.0086, "step": 166140 }, { "epoch": 39.87, "learning_rate": 6.845227607745198e-05, "loss": 0.0051, "step": 166150 }, { "epoch": 39.87, "learning_rate": 6.844893984185796e-05, "loss": 0.0211, "step": 166160 }, { "epoch": 39.87, "learning_rate": 6.844560351117795e-05, "loss": 0.0075, "step": 166170 }, { "epoch": 39.87, "learning_rate": 6.844226708542915e-05, "loss": 0.0151, "step": 166180 }, { "epoch": 39.88, "learning_rate": 6.843893056462874e-05, "loss": 0.01, "step": 166190 }, { "epoch": 39.88, "learning_rate": 6.843559394879395e-05, "loss": 0.0297, "step": 166200 }, { "epoch": 39.88, "learning_rate": 6.843225723794194e-05, "loss": 0.0158, "step": 166210 }, { "epoch": 39.88, "learning_rate": 6.842892043208991e-05, "loss": 0.013, "step": 166220 }, { "epoch": 39.89, "learning_rate": 6.842558353125509e-05, "loss": 0.0198, "step": 166230 }, { "epoch": 39.89, "learning_rate": 6.842224653545465e-05, "loss": 0.006, "step": 166240 }, { "epoch": 39.89, "learning_rate": 6.84189094447058e-05, "loss": 0.0181, "step": 166250 }, { "epoch": 39.89, "learning_rate": 6.841557225902573e-05, "loss": 0.0111, "step": 166260 }, { "epoch": 39.89, "learning_rate": 6.841223497843166e-05, "loss": 0.0154, "step": 166270 }, { "epoch": 39.9, "learning_rate": 6.840889760294076e-05, "loss": 0.0129, "step": 166280 }, { "epoch": 39.9, "learning_rate": 6.840556013257026e-05, "loss": 0.0075, "step": 166290 }, { "epoch": 39.9, "learning_rate": 6.840222256733735e-05, "loss": 0.0113, "step": 166300 }, { "epoch": 39.9, "learning_rate": 6.839888490725922e-05, "loss": 0.017, "step": 166310 }, { "epoch": 39.91, "learning_rate": 6.839554715235309e-05, "loss": 0.0356, "step": 166320 }, { "epoch": 39.91, "learning_rate": 6.839220930263615e-05, "loss": 0.0161, "step": 166330 }, { "epoch": 39.91, "learning_rate": 6.838887135812561e-05, "loss": 0.0135, "step": 166340 }, { "epoch": 39.91, "learning_rate": 6.83855333188387e-05, "loss": 0.0108, "step": 166350 }, { "epoch": 39.91, "learning_rate": 6.838219518479256e-05, "loss": 0.0159, "step": 166360 }, { "epoch": 39.92, "learning_rate": 6.837885695600446e-05, "loss": 0.0256, "step": 166370 }, { "epoch": 39.92, "learning_rate": 6.837551863249158e-05, "loss": 0.03, "step": 166380 }, { "epoch": 39.92, "learning_rate": 6.83721802142711e-05, "loss": 0.0114, "step": 166390 }, { "epoch": 39.92, "learning_rate": 6.836884170136027e-05, "loss": 0.0123, "step": 166400 }, { "epoch": 39.93, "learning_rate": 6.836550309377625e-05, "loss": 0.0268, "step": 166410 }, { "epoch": 39.93, "learning_rate": 6.836216439153629e-05, "loss": 0.015, "step": 166420 }, { "epoch": 39.93, "learning_rate": 6.835882559465758e-05, "loss": 0.0098, "step": 166430 }, { "epoch": 39.93, "learning_rate": 6.835548670315733e-05, "loss": 0.0163, "step": 166440 }, { "epoch": 39.94, "learning_rate": 6.835214771705275e-05, "loss": 0.0169, "step": 166450 }, { "epoch": 39.94, "learning_rate": 6.834880863636105e-05, "loss": 0.0153, "step": 166460 }, { "epoch": 39.94, "learning_rate": 6.834546946109943e-05, "loss": 0.0054, "step": 166470 }, { "epoch": 39.94, "learning_rate": 6.834213019128511e-05, "loss": 0.012, "step": 166480 }, { "epoch": 39.94, "learning_rate": 6.833879082693529e-05, "loss": 0.0324, "step": 166490 }, { "epoch": 39.95, "learning_rate": 6.83354513680672e-05, "loss": 0.0107, "step": 166500 }, { "epoch": 39.95, "learning_rate": 6.833211181469805e-05, "loss": 0.0126, "step": 166510 }, { "epoch": 39.95, "learning_rate": 6.832877216684503e-05, "loss": 0.0074, "step": 166520 }, { "epoch": 40.0, "learning_rate": 6.832543242452535e-05, "loss": 0.0124, "step": 166530 }, { "epoch": 40.0, "learning_rate": 6.832209258775626e-05, "loss": 0.0128, "step": 166540 }, { "epoch": 40.01, "learning_rate": 6.831875265655494e-05, "loss": 0.012, "step": 166550 }, { "epoch": 40.01, "learning_rate": 6.831541263093863e-05, "loss": 0.021, "step": 166560 }, { "epoch": 40.01, "learning_rate": 6.831207251092452e-05, "loss": 0.0127, "step": 166570 }, { "epoch": 40.01, "learning_rate": 6.830873229652984e-05, "loss": 0.0089, "step": 166580 }, { "epoch": 40.02, "learning_rate": 6.830539198777178e-05, "loss": 0.0184, "step": 166590 }, { "epoch": 40.02, "learning_rate": 6.830205158466759e-05, "loss": 0.0127, "step": 166600 }, { "epoch": 40.02, "learning_rate": 6.829871108723448e-05, "loss": 0.0101, "step": 166610 }, { "epoch": 40.02, "learning_rate": 6.829537049548966e-05, "loss": 0.0076, "step": 166620 }, { "epoch": 40.03, "learning_rate": 6.829202980945035e-05, "loss": 0.0123, "step": 166630 }, { "epoch": 40.03, "learning_rate": 6.828868902913375e-05, "loss": 0.0094, "step": 166640 }, { "epoch": 40.03, "learning_rate": 6.82853481545571e-05, "loss": 0.0109, "step": 166650 }, { "epoch": 40.03, "learning_rate": 6.828200718573762e-05, "loss": 0.0076, "step": 166660 }, { "epoch": 40.03, "learning_rate": 6.827866612269251e-05, "loss": 0.0095, "step": 166670 }, { "epoch": 40.04, "learning_rate": 6.827532496543903e-05, "loss": 0.0163, "step": 166680 }, { "epoch": 40.04, "learning_rate": 6.827198371399433e-05, "loss": 0.0165, "step": 166690 }, { "epoch": 40.04, "learning_rate": 6.82686423683757e-05, "loss": 0.0126, "step": 166700 }, { "epoch": 40.04, "learning_rate": 6.826530092860033e-05, "loss": 0.0071, "step": 166710 }, { "epoch": 40.05, "learning_rate": 6.826195939468544e-05, "loss": 0.0192, "step": 166720 }, { "epoch": 40.05, "learning_rate": 6.825861776664828e-05, "loss": 0.0072, "step": 166730 }, { "epoch": 40.05, "learning_rate": 6.825527604450604e-05, "loss": 0.021, "step": 166740 }, { "epoch": 40.05, "learning_rate": 6.825193422827594e-05, "loss": 0.0115, "step": 166750 }, { "epoch": 40.05, "learning_rate": 6.824859231797523e-05, "loss": 0.0138, "step": 166760 }, { "epoch": 40.06, "learning_rate": 6.824525031362112e-05, "loss": 0.0113, "step": 166770 }, { "epoch": 40.06, "learning_rate": 6.824190821523084e-05, "loss": 0.0091, "step": 166780 }, { "epoch": 40.06, "learning_rate": 6.823856602282161e-05, "loss": 0.0096, "step": 166790 }, { "epoch": 40.06, "learning_rate": 6.823522373641066e-05, "loss": 0.0136, "step": 166800 }, { "epoch": 40.07, "learning_rate": 6.823188135601522e-05, "loss": 0.0168, "step": 166810 }, { "epoch": 40.07, "learning_rate": 6.82285388816525e-05, "loss": 0.0143, "step": 166820 }, { "epoch": 40.07, "learning_rate": 6.822519631333975e-05, "loss": 0.0205, "step": 166830 }, { "epoch": 40.07, "learning_rate": 6.822185365109419e-05, "loss": 0.0186, "step": 166840 }, { "epoch": 40.08, "learning_rate": 6.821851089493302e-05, "loss": 0.0112, "step": 166850 }, { "epoch": 40.08, "learning_rate": 6.821516804487352e-05, "loss": 0.0213, "step": 166860 }, { "epoch": 40.08, "learning_rate": 6.821182510093286e-05, "loss": 0.012, "step": 166870 }, { "epoch": 40.08, "learning_rate": 6.820848206312833e-05, "loss": 0.0095, "step": 166880 }, { "epoch": 40.08, "learning_rate": 6.820513893147712e-05, "loss": 0.0095, "step": 166890 }, { "epoch": 40.09, "learning_rate": 6.820179570599646e-05, "loss": 0.0114, "step": 166900 }, { "epoch": 40.09, "learning_rate": 6.81984523867036e-05, "loss": 0.0195, "step": 166910 }, { "epoch": 40.09, "learning_rate": 6.819510897361577e-05, "loss": 0.0187, "step": 166920 }, { "epoch": 40.09, "learning_rate": 6.81917654667502e-05, "loss": 0.011, "step": 166930 }, { "epoch": 40.1, "learning_rate": 6.818842186612412e-05, "loss": 0.0138, "step": 166940 }, { "epoch": 40.1, "learning_rate": 6.818507817175475e-05, "loss": 0.0089, "step": 166950 }, { "epoch": 40.1, "learning_rate": 6.818173438365934e-05, "loss": 0.006, "step": 166960 }, { "epoch": 40.1, "learning_rate": 6.817839050185513e-05, "loss": 0.0256, "step": 166970 }, { "epoch": 40.11, "learning_rate": 6.817504652635933e-05, "loss": 0.0143, "step": 166980 }, { "epoch": 40.11, "learning_rate": 6.817170245718919e-05, "loss": 0.0252, "step": 166990 }, { "epoch": 40.11, "learning_rate": 6.816835829436194e-05, "loss": 0.0148, "step": 167000 }, { "epoch": 40.11, "learning_rate": 6.816501403789484e-05, "loss": 0.0099, "step": 167010 }, { "epoch": 40.11, "learning_rate": 6.816166968780509e-05, "loss": 0.0143, "step": 167020 }, { "epoch": 40.12, "learning_rate": 6.815832524410994e-05, "loss": 0.0208, "step": 167030 }, { "epoch": 40.12, "learning_rate": 6.815498070682663e-05, "loss": 0.0244, "step": 167040 }, { "epoch": 40.12, "learning_rate": 6.815163607597239e-05, "loss": 0.0068, "step": 167050 }, { "epoch": 40.12, "learning_rate": 6.814829135156448e-05, "loss": 0.0245, "step": 167060 }, { "epoch": 40.13, "learning_rate": 6.814494653362012e-05, "loss": 0.0159, "step": 167070 }, { "epoch": 40.13, "learning_rate": 6.814160162215658e-05, "loss": 0.0315, "step": 167080 }, { "epoch": 40.13, "learning_rate": 6.813825661719103e-05, "loss": 0.013, "step": 167090 }, { "epoch": 40.13, "learning_rate": 6.813491151874077e-05, "loss": 0.0168, "step": 167100 }, { "epoch": 40.13, "learning_rate": 6.813156632682303e-05, "loss": 0.0104, "step": 167110 }, { "epoch": 40.14, "learning_rate": 6.812822104145505e-05, "loss": 0.0072, "step": 167120 }, { "epoch": 40.14, "learning_rate": 6.812487566265405e-05, "loss": 0.0117, "step": 167130 }, { "epoch": 40.14, "learning_rate": 6.81215301904373e-05, "loss": 0.019, "step": 167140 }, { "epoch": 40.14, "learning_rate": 6.811818462482204e-05, "loss": 0.0116, "step": 167150 }, { "epoch": 40.15, "learning_rate": 6.81148389658255e-05, "loss": 0.0187, "step": 167160 }, { "epoch": 40.15, "learning_rate": 6.811149321346493e-05, "loss": 0.0223, "step": 167170 }, { "epoch": 40.15, "learning_rate": 6.810814736775756e-05, "loss": 0.0118, "step": 167180 }, { "epoch": 40.15, "learning_rate": 6.810480142872065e-05, "loss": 0.0114, "step": 167190 }, { "epoch": 40.16, "learning_rate": 6.810145539637145e-05, "loss": 0.0128, "step": 167200 }, { "epoch": 40.16, "learning_rate": 6.809810927072719e-05, "loss": 0.0128, "step": 167210 }, { "epoch": 40.16, "learning_rate": 6.809476305180512e-05, "loss": 0.0152, "step": 167220 }, { "epoch": 40.16, "learning_rate": 6.80914167396225e-05, "loss": 0.0151, "step": 167230 }, { "epoch": 40.16, "learning_rate": 6.808807033419657e-05, "loss": 0.02, "step": 167240 }, { "epoch": 40.17, "learning_rate": 6.808472383554457e-05, "loss": 0.0107, "step": 167250 }, { "epoch": 40.17, "learning_rate": 6.808137724368375e-05, "loss": 0.0188, "step": 167260 }, { "epoch": 40.17, "learning_rate": 6.807803055863136e-05, "loss": 0.0119, "step": 167270 }, { "epoch": 40.17, "learning_rate": 6.807468378040465e-05, "loss": 0.0064, "step": 167280 }, { "epoch": 40.18, "learning_rate": 6.807133690902087e-05, "loss": 0.022, "step": 167290 }, { "epoch": 40.18, "learning_rate": 6.806798994449728e-05, "loss": 0.0249, "step": 167300 }, { "epoch": 40.18, "learning_rate": 6.80646428868511e-05, "loss": 0.013, "step": 167310 }, { "epoch": 40.18, "learning_rate": 6.80612957360996e-05, "loss": 0.0067, "step": 167320 }, { "epoch": 40.19, "learning_rate": 6.805794849226005e-05, "loss": 0.0068, "step": 167330 }, { "epoch": 40.19, "learning_rate": 6.805460115534966e-05, "loss": 0.0249, "step": 167340 }, { "epoch": 40.19, "learning_rate": 6.805125372538572e-05, "loss": 0.0072, "step": 167350 }, { "epoch": 40.19, "learning_rate": 6.804790620238546e-05, "loss": 0.0144, "step": 167360 }, { "epoch": 40.19, "learning_rate": 6.804455858636614e-05, "loss": 0.0128, "step": 167370 }, { "epoch": 40.2, "learning_rate": 6.804121087734501e-05, "loss": 0.0135, "step": 167380 }, { "epoch": 40.2, "learning_rate": 6.803786307533935e-05, "loss": 0.0121, "step": 167390 }, { "epoch": 40.2, "learning_rate": 6.803451518036636e-05, "loss": 0.0093, "step": 167400 }, { "epoch": 40.2, "learning_rate": 6.803116719244336e-05, "loss": 0.0105, "step": 167410 }, { "epoch": 40.21, "learning_rate": 6.802781911158755e-05, "loss": 0.0093, "step": 167420 }, { "epoch": 40.21, "learning_rate": 6.802447093781622e-05, "loss": 0.0071, "step": 167430 }, { "epoch": 40.21, "learning_rate": 6.802112267114663e-05, "loss": 0.0117, "step": 167440 }, { "epoch": 40.21, "learning_rate": 6.801777431159601e-05, "loss": 0.0119, "step": 167450 }, { "epoch": 40.21, "learning_rate": 6.801442585918163e-05, "loss": 0.0087, "step": 167460 }, { "epoch": 40.22, "learning_rate": 6.801107731392074e-05, "loss": 0.0091, "step": 167470 }, { "epoch": 40.22, "learning_rate": 6.800772867583061e-05, "loss": 0.0082, "step": 167480 }, { "epoch": 40.22, "learning_rate": 6.800437994492851e-05, "loss": 0.0087, "step": 167490 }, { "epoch": 40.22, "learning_rate": 6.800103112123168e-05, "loss": 0.0266, "step": 167500 }, { "epoch": 40.23, "learning_rate": 6.799768220475737e-05, "loss": 0.0167, "step": 167510 }, { "epoch": 40.23, "learning_rate": 6.799433319552286e-05, "loss": 0.0133, "step": 167520 }, { "epoch": 40.23, "learning_rate": 6.799098409354541e-05, "loss": 0.0061, "step": 167530 }, { "epoch": 40.23, "learning_rate": 6.798763489884229e-05, "loss": 0.0118, "step": 167540 }, { "epoch": 40.24, "learning_rate": 6.798428561143074e-05, "loss": 0.0159, "step": 167550 }, { "epoch": 40.24, "learning_rate": 6.798093623132803e-05, "loss": 0.0093, "step": 167560 }, { "epoch": 40.24, "learning_rate": 6.797758675855143e-05, "loss": 0.0092, "step": 167570 }, { "epoch": 40.24, "learning_rate": 6.797423719311818e-05, "loss": 0.0074, "step": 167580 }, { "epoch": 40.24, "learning_rate": 6.79708875350456e-05, "loss": 0.0148, "step": 167590 }, { "epoch": 40.25, "learning_rate": 6.796753778435087e-05, "loss": 0.0142, "step": 167600 }, { "epoch": 40.25, "learning_rate": 6.796418794105133e-05, "loss": 0.0108, "step": 167610 }, { "epoch": 40.25, "learning_rate": 6.79608380051642e-05, "loss": 0.0186, "step": 167620 }, { "epoch": 40.25, "learning_rate": 6.795748797670677e-05, "loss": 0.0335, "step": 167630 }, { "epoch": 40.26, "learning_rate": 6.79541378556963e-05, "loss": 0.0123, "step": 167640 }, { "epoch": 40.26, "learning_rate": 6.795078764215004e-05, "loss": 0.0116, "step": 167650 }, { "epoch": 40.26, "learning_rate": 6.794743733608528e-05, "loss": 0.0169, "step": 167660 }, { "epoch": 40.26, "learning_rate": 6.794408693751928e-05, "loss": 0.019, "step": 167670 }, { "epoch": 40.27, "learning_rate": 6.79407364464693e-05, "loss": 0.0271, "step": 167680 }, { "epoch": 40.27, "learning_rate": 6.793738586295259e-05, "loss": 0.0159, "step": 167690 }, { "epoch": 40.27, "learning_rate": 6.793403518698648e-05, "loss": 0.0137, "step": 167700 }, { "epoch": 40.27, "learning_rate": 6.793068441858819e-05, "loss": 0.0111, "step": 167710 }, { "epoch": 40.27, "learning_rate": 6.7927333557775e-05, "loss": 0.0177, "step": 167720 }, { "epoch": 40.28, "learning_rate": 6.79239826045642e-05, "loss": 0.0173, "step": 167730 }, { "epoch": 40.28, "learning_rate": 6.792063155897302e-05, "loss": 0.018, "step": 167740 }, { "epoch": 40.28, "learning_rate": 6.791728042101877e-05, "loss": 0.0136, "step": 167750 }, { "epoch": 40.28, "learning_rate": 6.791392919071871e-05, "loss": 0.0062, "step": 167760 }, { "epoch": 40.29, "learning_rate": 6.79105778680901e-05, "loss": 0.0149, "step": 167770 }, { "epoch": 40.29, "learning_rate": 6.790722645315022e-05, "loss": 0.0229, "step": 167780 }, { "epoch": 40.29, "learning_rate": 6.790387494591634e-05, "loss": 0.0126, "step": 167790 }, { "epoch": 40.29, "learning_rate": 6.790052334640576e-05, "loss": 0.0149, "step": 167800 }, { "epoch": 40.29, "learning_rate": 6.789717165463571e-05, "loss": 0.0098, "step": 167810 }, { "epoch": 40.3, "learning_rate": 6.78938198706235e-05, "loss": 0.0307, "step": 167820 }, { "epoch": 40.3, "learning_rate": 6.789046799438638e-05, "loss": 0.0092, "step": 167830 }, { "epoch": 40.3, "learning_rate": 6.788711602594167e-05, "loss": 0.0125, "step": 167840 }, { "epoch": 40.3, "learning_rate": 6.788376396530658e-05, "loss": 0.0111, "step": 167850 }, { "epoch": 40.31, "learning_rate": 6.788041181249844e-05, "loss": 0.007, "step": 167860 }, { "epoch": 40.31, "learning_rate": 6.787705956753451e-05, "loss": 0.0241, "step": 167870 }, { "epoch": 40.31, "learning_rate": 6.787370723043206e-05, "loss": 0.0107, "step": 167880 }, { "epoch": 40.31, "learning_rate": 6.787035480120838e-05, "loss": 0.0078, "step": 167890 }, { "epoch": 40.32, "learning_rate": 6.786700227988072e-05, "loss": 0.0176, "step": 167900 }, { "epoch": 40.32, "learning_rate": 6.78636496664664e-05, "loss": 0.008, "step": 167910 }, { "epoch": 40.32, "learning_rate": 6.786029696098268e-05, "loss": 0.0118, "step": 167920 }, { "epoch": 40.32, "learning_rate": 6.785694416344683e-05, "loss": 0.0149, "step": 167930 }, { "epoch": 40.32, "learning_rate": 6.785359127387615e-05, "loss": 0.0211, "step": 167940 }, { "epoch": 40.33, "learning_rate": 6.78502382922879e-05, "loss": 0.0119, "step": 167950 }, { "epoch": 40.33, "learning_rate": 6.784688521869938e-05, "loss": 0.0072, "step": 167960 }, { "epoch": 40.33, "learning_rate": 6.784353205312787e-05, "loss": 0.009, "step": 167970 }, { "epoch": 40.33, "learning_rate": 6.784017879559064e-05, "loss": 0.0099, "step": 167980 }, { "epoch": 40.34, "learning_rate": 6.783682544610497e-05, "loss": 0.0117, "step": 167990 }, { "epoch": 40.34, "learning_rate": 6.783347200468817e-05, "loss": 0.0114, "step": 168000 }, { "epoch": 40.34, "learning_rate": 6.78301184713575e-05, "loss": 0.0169, "step": 168010 }, { "epoch": 40.34, "learning_rate": 6.782676484613026e-05, "loss": 0.016, "step": 168020 }, { "epoch": 40.35, "learning_rate": 6.782341112902372e-05, "loss": 0.006, "step": 168030 }, { "epoch": 40.35, "learning_rate": 6.782005732005517e-05, "loss": 0.0289, "step": 168040 }, { "epoch": 40.35, "learning_rate": 6.781670341924188e-05, "loss": 0.0184, "step": 168050 }, { "epoch": 40.35, "learning_rate": 6.781334942660116e-05, "loss": 0.0163, "step": 168060 }, { "epoch": 40.35, "learning_rate": 6.78099953421503e-05, "loss": 0.012, "step": 168070 }, { "epoch": 40.36, "learning_rate": 6.780664116590656e-05, "loss": 0.0111, "step": 168080 }, { "epoch": 40.36, "learning_rate": 6.780328689788726e-05, "loss": 0.0135, "step": 168090 }, { "epoch": 40.36, "learning_rate": 6.779993253810963e-05, "loss": 0.0117, "step": 168100 }, { "epoch": 40.36, "learning_rate": 6.779657808659103e-05, "loss": 0.0157, "step": 168110 }, { "epoch": 40.37, "learning_rate": 6.779322354334871e-05, "loss": 0.0107, "step": 168120 }, { "epoch": 40.37, "learning_rate": 6.778986890839998e-05, "loss": 0.0134, "step": 168130 }, { "epoch": 40.37, "learning_rate": 6.778651418176211e-05, "loss": 0.007, "step": 168140 }, { "epoch": 40.37, "learning_rate": 6.778315936345239e-05, "loss": 0.0122, "step": 168150 }, { "epoch": 40.37, "learning_rate": 6.777980445348815e-05, "loss": 0.0119, "step": 168160 }, { "epoch": 40.38, "learning_rate": 6.777644945188662e-05, "loss": 0.0136, "step": 168170 }, { "epoch": 40.38, "learning_rate": 6.777309435866512e-05, "loss": 0.0146, "step": 168180 }, { "epoch": 40.38, "learning_rate": 6.776973917384095e-05, "loss": 0.0315, "step": 168190 }, { "epoch": 40.38, "learning_rate": 6.77663838974314e-05, "loss": 0.0096, "step": 168200 }, { "epoch": 40.39, "learning_rate": 6.776302852945374e-05, "loss": 0.0089, "step": 168210 }, { "epoch": 40.39, "learning_rate": 6.77596730699253e-05, "loss": 0.01, "step": 168220 }, { "epoch": 40.39, "learning_rate": 6.775631751886335e-05, "loss": 0.0081, "step": 168230 }, { "epoch": 40.39, "learning_rate": 6.77529618762852e-05, "loss": 0.0159, "step": 168240 }, { "epoch": 40.4, "learning_rate": 6.774960614220813e-05, "loss": 0.0084, "step": 168250 }, { "epoch": 40.4, "learning_rate": 6.774625031664943e-05, "loss": 0.0092, "step": 168260 }, { "epoch": 40.4, "learning_rate": 6.774289439962641e-05, "loss": 0.0364, "step": 168270 }, { "epoch": 40.4, "learning_rate": 6.773953839115637e-05, "loss": 0.0099, "step": 168280 }, { "epoch": 40.4, "learning_rate": 6.773618229125661e-05, "loss": 0.0074, "step": 168290 }, { "epoch": 40.41, "learning_rate": 6.773282609994443e-05, "loss": 0.0065, "step": 168300 }, { "epoch": 40.41, "learning_rate": 6.772946981723709e-05, "loss": 0.0091, "step": 168310 }, { "epoch": 40.41, "learning_rate": 6.772611344315192e-05, "loss": 0.0146, "step": 168320 }, { "epoch": 40.41, "learning_rate": 6.77227569777062e-05, "loss": 0.0083, "step": 168330 }, { "epoch": 40.42, "learning_rate": 6.771940042091727e-05, "loss": 0.0112, "step": 168340 }, { "epoch": 40.42, "learning_rate": 6.771604377280239e-05, "loss": 0.0099, "step": 168350 }, { "epoch": 40.42, "learning_rate": 6.771268703337887e-05, "loss": 0.0133, "step": 168360 }, { "epoch": 40.42, "learning_rate": 6.770933020266401e-05, "loss": 0.0134, "step": 168370 }, { "epoch": 40.43, "learning_rate": 6.770597328067513e-05, "loss": 0.0166, "step": 168380 }, { "epoch": 40.43, "learning_rate": 6.77026162674295e-05, "loss": 0.0106, "step": 168390 }, { "epoch": 40.43, "learning_rate": 6.769925916294444e-05, "loss": 0.0136, "step": 168400 }, { "epoch": 40.43, "learning_rate": 6.769590196723724e-05, "loss": 0.0097, "step": 168410 }, { "epoch": 40.43, "learning_rate": 6.769254468032522e-05, "loss": 0.012, "step": 168420 }, { "epoch": 40.44, "learning_rate": 6.768918730222569e-05, "loss": 0.0124, "step": 168430 }, { "epoch": 40.44, "learning_rate": 6.768582983295593e-05, "loss": 0.0108, "step": 168440 }, { "epoch": 40.44, "learning_rate": 6.768247227253328e-05, "loss": 0.0156, "step": 168450 }, { "epoch": 40.44, "learning_rate": 6.767911462097498e-05, "loss": 0.0087, "step": 168460 }, { "epoch": 40.45, "learning_rate": 6.76757568782984e-05, "loss": 0.017, "step": 168470 }, { "epoch": 40.45, "learning_rate": 6.767239904452081e-05, "loss": 0.0116, "step": 168480 }, { "epoch": 40.45, "learning_rate": 6.766904111965954e-05, "loss": 0.0107, "step": 168490 }, { "epoch": 40.45, "learning_rate": 6.766568310373187e-05, "loss": 0.0138, "step": 168500 }, { "epoch": 40.45, "learning_rate": 6.766232499675514e-05, "loss": 0.0112, "step": 168510 }, { "epoch": 40.46, "learning_rate": 6.765896679874663e-05, "loss": 0.042, "step": 168520 }, { "epoch": 40.46, "learning_rate": 6.765560850972365e-05, "loss": 0.0112, "step": 168530 }, { "epoch": 40.46, "learning_rate": 6.765225012970353e-05, "loss": 0.0116, "step": 168540 }, { "epoch": 40.46, "learning_rate": 6.764889165870355e-05, "loss": 0.0114, "step": 168550 }, { "epoch": 40.47, "learning_rate": 6.764553309674105e-05, "loss": 0.0144, "step": 168560 }, { "epoch": 40.47, "learning_rate": 6.76421744438333e-05, "loss": 0.0127, "step": 168570 }, { "epoch": 40.47, "learning_rate": 6.763881569999765e-05, "loss": 0.0162, "step": 168580 }, { "epoch": 40.47, "learning_rate": 6.763545686525141e-05, "loss": 0.0116, "step": 168590 }, { "epoch": 40.48, "learning_rate": 6.763209793961187e-05, "loss": 0.01, "step": 168600 }, { "epoch": 40.48, "learning_rate": 6.762873892309635e-05, "loss": 0.0084, "step": 168610 }, { "epoch": 40.48, "learning_rate": 6.762537981572214e-05, "loss": 0.0124, "step": 168620 }, { "epoch": 40.48, "learning_rate": 6.76220206175066e-05, "loss": 0.0083, "step": 168630 }, { "epoch": 40.48, "learning_rate": 6.761866132846702e-05, "loss": 0.0231, "step": 168640 }, { "epoch": 40.49, "learning_rate": 6.76153019486207e-05, "loss": 0.0267, "step": 168650 }, { "epoch": 40.49, "learning_rate": 6.761194247798498e-05, "loss": 0.0123, "step": 168660 }, { "epoch": 40.49, "learning_rate": 6.760858291657714e-05, "loss": 0.0166, "step": 168670 }, { "epoch": 40.49, "learning_rate": 6.760522326441454e-05, "loss": 0.0131, "step": 168680 }, { "epoch": 40.5, "learning_rate": 6.760186352151446e-05, "loss": 0.0083, "step": 168690 }, { "epoch": 40.5, "learning_rate": 6.759850368789424e-05, "loss": 0.0083, "step": 168700 }, { "epoch": 40.5, "learning_rate": 6.759514376357116e-05, "loss": 0.0131, "step": 168710 }, { "epoch": 40.5, "learning_rate": 6.759178374856257e-05, "loss": 0.031, "step": 168720 }, { "epoch": 40.51, "learning_rate": 6.758842364288578e-05, "loss": 0.0552, "step": 168730 }, { "epoch": 40.51, "learning_rate": 6.758506344655813e-05, "loss": 0.0156, "step": 168740 }, { "epoch": 40.51, "learning_rate": 6.758170315959689e-05, "loss": 0.013, "step": 168750 }, { "epoch": 40.51, "learning_rate": 6.757834278201943e-05, "loss": 0.009, "step": 168760 }, { "epoch": 40.51, "learning_rate": 6.757498231384302e-05, "loss": 0.0096, "step": 168770 }, { "epoch": 40.52, "learning_rate": 6.7571621755085e-05, "loss": 0.0248, "step": 168780 }, { "epoch": 40.52, "learning_rate": 6.75682611057627e-05, "loss": 0.0065, "step": 168790 }, { "epoch": 40.52, "learning_rate": 6.756490036589346e-05, "loss": 0.0108, "step": 168800 }, { "epoch": 40.52, "learning_rate": 6.756153953549457e-05, "loss": 0.0131, "step": 168810 }, { "epoch": 40.53, "learning_rate": 6.755817861458335e-05, "loss": 0.0188, "step": 168820 }, { "epoch": 40.53, "learning_rate": 6.755481760317712e-05, "loss": 0.0089, "step": 168830 }, { "epoch": 40.53, "learning_rate": 6.755145650129322e-05, "loss": 0.0105, "step": 168840 }, { "epoch": 40.53, "learning_rate": 6.754809530894896e-05, "loss": 0.0126, "step": 168850 }, { "epoch": 40.53, "learning_rate": 6.754473402616169e-05, "loss": 0.0251, "step": 168860 }, { "epoch": 40.54, "learning_rate": 6.75413726529487e-05, "loss": 0.0217, "step": 168870 }, { "epoch": 40.54, "learning_rate": 6.753801118932733e-05, "loss": 0.0187, "step": 168880 }, { "epoch": 40.54, "learning_rate": 6.753464963531491e-05, "loss": 0.0299, "step": 168890 }, { "epoch": 40.54, "learning_rate": 6.753128799092875e-05, "loss": 0.0161, "step": 168900 }, { "epoch": 40.55, "learning_rate": 6.752792625618618e-05, "loss": 0.0133, "step": 168910 }, { "epoch": 40.55, "learning_rate": 6.752456443110456e-05, "loss": 0.0159, "step": 168920 }, { "epoch": 40.55, "learning_rate": 6.752120251570116e-05, "loss": 0.0155, "step": 168930 }, { "epoch": 40.55, "learning_rate": 6.751784050999335e-05, "loss": 0.0198, "step": 168940 }, { "epoch": 40.56, "learning_rate": 6.751447841399844e-05, "loss": 0.0178, "step": 168950 }, { "epoch": 40.56, "learning_rate": 6.751111622773376e-05, "loss": 0.0168, "step": 168960 }, { "epoch": 40.56, "learning_rate": 6.750775395121665e-05, "loss": 0.0128, "step": 168970 }, { "epoch": 40.56, "learning_rate": 6.750439158446441e-05, "loss": 0.0101, "step": 168980 }, { "epoch": 40.56, "learning_rate": 6.750102912749439e-05, "loss": 0.0311, "step": 168990 }, { "epoch": 40.57, "learning_rate": 6.749766658032393e-05, "loss": 0.0092, "step": 169000 }, { "epoch": 40.57, "learning_rate": 6.749430394297036e-05, "loss": 0.0218, "step": 169010 }, { "epoch": 40.57, "learning_rate": 6.749094121545099e-05, "loss": 0.0213, "step": 169020 }, { "epoch": 40.57, "learning_rate": 6.748757839778317e-05, "loss": 0.0063, "step": 169030 }, { "epoch": 40.58, "learning_rate": 6.748421548998422e-05, "loss": 0.0233, "step": 169040 }, { "epoch": 40.58, "learning_rate": 6.748085249207147e-05, "loss": 0.0155, "step": 169050 }, { "epoch": 40.58, "learning_rate": 6.747748940406227e-05, "loss": 0.0296, "step": 169060 }, { "epoch": 40.58, "learning_rate": 6.747412622597394e-05, "loss": 0.0223, "step": 169070 }, { "epoch": 40.59, "learning_rate": 6.747076295782381e-05, "loss": 0.0109, "step": 169080 }, { "epoch": 40.59, "learning_rate": 6.746739959962925e-05, "loss": 0.017, "step": 169090 }, { "epoch": 40.59, "learning_rate": 6.746403615140753e-05, "loss": 0.024, "step": 169100 }, { "epoch": 40.59, "learning_rate": 6.746067261317603e-05, "loss": 0.0156, "step": 169110 }, { "epoch": 40.59, "learning_rate": 6.74573089849521e-05, "loss": 0.0115, "step": 169120 }, { "epoch": 40.6, "learning_rate": 6.745394526675303e-05, "loss": 0.0144, "step": 169130 }, { "epoch": 40.6, "learning_rate": 6.74505814585962e-05, "loss": 0.0166, "step": 169140 }, { "epoch": 40.6, "learning_rate": 6.744721756049889e-05, "loss": 0.0133, "step": 169150 }, { "epoch": 40.6, "learning_rate": 6.744385357247851e-05, "loss": 0.0133, "step": 169160 }, { "epoch": 40.61, "learning_rate": 6.744048949455235e-05, "loss": 0.0092, "step": 169170 }, { "epoch": 40.61, "learning_rate": 6.743712532673777e-05, "loss": 0.0134, "step": 169180 }, { "epoch": 40.61, "learning_rate": 6.743376106905209e-05, "loss": 0.0268, "step": 169190 }, { "epoch": 40.61, "learning_rate": 6.743039672151267e-05, "loss": 0.0263, "step": 169200 }, { "epoch": 40.61, "learning_rate": 6.742703228413683e-05, "loss": 0.0185, "step": 169210 }, { "epoch": 40.62, "learning_rate": 6.742366775694194e-05, "loss": 0.0127, "step": 169220 }, { "epoch": 40.62, "learning_rate": 6.742030313994529e-05, "loss": 0.0121, "step": 169230 }, { "epoch": 40.62, "learning_rate": 6.741693843316427e-05, "loss": 0.0214, "step": 169240 }, { "epoch": 40.62, "learning_rate": 6.741357363661621e-05, "loss": 0.0127, "step": 169250 }, { "epoch": 40.63, "learning_rate": 6.741020875031844e-05, "loss": 0.018, "step": 169260 }, { "epoch": 40.63, "learning_rate": 6.74068437742883e-05, "loss": 0.0168, "step": 169270 }, { "epoch": 40.63, "learning_rate": 6.740347870854315e-05, "loss": 0.014, "step": 169280 }, { "epoch": 40.63, "learning_rate": 6.740011355310032e-05, "loss": 0.0205, "step": 169290 }, { "epoch": 40.64, "learning_rate": 6.739674830797715e-05, "loss": 0.0161, "step": 169300 }, { "epoch": 40.64, "learning_rate": 6.739338297319101e-05, "loss": 0.0167, "step": 169310 }, { "epoch": 40.64, "learning_rate": 6.739001754875922e-05, "loss": 0.0169, "step": 169320 }, { "epoch": 40.64, "learning_rate": 6.738665203469914e-05, "loss": 0.0201, "step": 169330 }, { "epoch": 40.64, "learning_rate": 6.738328643102811e-05, "loss": 0.0081, "step": 169340 }, { "epoch": 40.65, "learning_rate": 6.737992073776348e-05, "loss": 0.01, "step": 169350 }, { "epoch": 40.65, "learning_rate": 6.737655495492259e-05, "loss": 0.0134, "step": 169360 }, { "epoch": 40.65, "learning_rate": 6.737318908252279e-05, "loss": 0.0264, "step": 169370 }, { "epoch": 40.65, "learning_rate": 6.736982312058142e-05, "loss": 0.0115, "step": 169380 }, { "epoch": 40.66, "learning_rate": 6.736645706911585e-05, "loss": 0.0163, "step": 169390 }, { "epoch": 40.66, "learning_rate": 6.736309092814342e-05, "loss": 0.0101, "step": 169400 }, { "epoch": 40.66, "learning_rate": 6.735972469768145e-05, "loss": 0.0225, "step": 169410 }, { "epoch": 40.66, "learning_rate": 6.735635837774732e-05, "loss": 0.0127, "step": 169420 }, { "epoch": 40.66, "learning_rate": 6.735299196835838e-05, "loss": 0.0065, "step": 169430 }, { "epoch": 40.67, "learning_rate": 6.734962546953198e-05, "loss": 0.0226, "step": 169440 }, { "epoch": 40.67, "learning_rate": 6.734625888128546e-05, "loss": 0.0128, "step": 169450 }, { "epoch": 40.67, "learning_rate": 6.734289220363617e-05, "loss": 0.0243, "step": 169460 }, { "epoch": 40.67, "learning_rate": 6.733952543660148e-05, "loss": 0.0196, "step": 169470 }, { "epoch": 40.68, "learning_rate": 6.733615858019873e-05, "loss": 0.0152, "step": 169480 }, { "epoch": 40.68, "learning_rate": 6.733279163444526e-05, "loss": 0.0129, "step": 169490 }, { "epoch": 40.68, "learning_rate": 6.732942459935845e-05, "loss": 0.0188, "step": 169500 }, { "epoch": 40.68, "learning_rate": 6.732605747495563e-05, "loss": 0.0154, "step": 169510 }, { "epoch": 40.69, "learning_rate": 6.732269026125419e-05, "loss": 0.0162, "step": 169520 }, { "epoch": 40.69, "learning_rate": 6.731932295827144e-05, "loss": 0.0194, "step": 169530 }, { "epoch": 40.69, "learning_rate": 6.731595556602476e-05, "loss": 0.0168, "step": 169540 }, { "epoch": 40.69, "learning_rate": 6.731258808453149e-05, "loss": 0.0109, "step": 169550 }, { "epoch": 40.69, "learning_rate": 6.730922051380901e-05, "loss": 0.0119, "step": 169560 }, { "epoch": 40.7, "learning_rate": 6.730585285387465e-05, "loss": 0.0084, "step": 169570 }, { "epoch": 40.7, "learning_rate": 6.730248510474579e-05, "loss": 0.0081, "step": 169580 }, { "epoch": 40.7, "learning_rate": 6.729911726643977e-05, "loss": 0.0136, "step": 169590 }, { "epoch": 40.7, "learning_rate": 6.729574933897397e-05, "loss": 0.0129, "step": 169600 }, { "epoch": 40.71, "learning_rate": 6.729238132236571e-05, "loss": 0.0138, "step": 169610 }, { "epoch": 40.71, "learning_rate": 6.728901321663239e-05, "loss": 0.0133, "step": 169620 }, { "epoch": 40.71, "learning_rate": 6.728564502179133e-05, "loss": 0.0079, "step": 169630 }, { "epoch": 40.71, "learning_rate": 6.728227673785993e-05, "loss": 0.017, "step": 169640 }, { "epoch": 40.72, "learning_rate": 6.727890836485553e-05, "loss": 0.0231, "step": 169650 }, { "epoch": 40.72, "learning_rate": 6.72755399027955e-05, "loss": 0.0124, "step": 169660 }, { "epoch": 40.72, "learning_rate": 6.727217135169718e-05, "loss": 0.0062, "step": 169670 }, { "epoch": 40.72, "learning_rate": 6.726880271157795e-05, "loss": 0.0183, "step": 169680 }, { "epoch": 40.72, "learning_rate": 6.726543398245516e-05, "loss": 0.0176, "step": 169690 }, { "epoch": 40.73, "learning_rate": 6.726206516434619e-05, "loss": 0.0092, "step": 169700 }, { "epoch": 40.73, "learning_rate": 6.725869625726838e-05, "loss": 0.0215, "step": 169710 }, { "epoch": 40.73, "learning_rate": 6.725532726123911e-05, "loss": 0.014, "step": 169720 }, { "epoch": 40.73, "learning_rate": 6.725195817627573e-05, "loss": 0.0094, "step": 169730 }, { "epoch": 40.74, "learning_rate": 6.724858900239563e-05, "loss": 0.0083, "step": 169740 }, { "epoch": 40.74, "learning_rate": 6.724521973961615e-05, "loss": 0.0138, "step": 169750 }, { "epoch": 40.74, "learning_rate": 6.724185038795466e-05, "loss": 0.0113, "step": 169760 }, { "epoch": 40.74, "learning_rate": 6.723848094742853e-05, "loss": 0.0159, "step": 169770 }, { "epoch": 40.74, "learning_rate": 6.723511141805512e-05, "loss": 0.0135, "step": 169780 }, { "epoch": 40.75, "learning_rate": 6.723174179985182e-05, "loss": 0.0222, "step": 169790 }, { "epoch": 40.75, "learning_rate": 6.722837209283595e-05, "loss": 0.0113, "step": 169800 }, { "epoch": 40.75, "learning_rate": 6.722500229702494e-05, "loss": 0.0144, "step": 169810 }, { "epoch": 40.75, "learning_rate": 6.722163241243611e-05, "loss": 0.0118, "step": 169820 }, { "epoch": 40.76, "learning_rate": 6.721826243908684e-05, "loss": 0.0118, "step": 169830 }, { "epoch": 40.76, "learning_rate": 6.72148923769945e-05, "loss": 0.0188, "step": 169840 }, { "epoch": 40.76, "learning_rate": 6.721152222617646e-05, "loss": 0.0175, "step": 169850 }, { "epoch": 40.76, "learning_rate": 6.72081519866501e-05, "loss": 0.008, "step": 169860 }, { "epoch": 40.77, "learning_rate": 6.720478165843277e-05, "loss": 0.0117, "step": 169870 }, { "epoch": 40.77, "learning_rate": 6.720141124154187e-05, "loss": 0.0078, "step": 169880 }, { "epoch": 40.77, "learning_rate": 6.719804073599473e-05, "loss": 0.0104, "step": 169890 }, { "epoch": 40.77, "learning_rate": 6.719467014180875e-05, "loss": 0.0226, "step": 169900 }, { "epoch": 40.77, "learning_rate": 6.71912994590013e-05, "loss": 0.0119, "step": 169910 }, { "epoch": 40.78, "learning_rate": 6.718792868758974e-05, "loss": 0.0114, "step": 169920 }, { "epoch": 40.78, "learning_rate": 6.718455782759145e-05, "loss": 0.0179, "step": 169930 }, { "epoch": 40.78, "learning_rate": 6.718118687902382e-05, "loss": 0.0121, "step": 169940 }, { "epoch": 40.78, "learning_rate": 6.717781584190422e-05, "loss": 0.0113, "step": 169950 }, { "epoch": 40.79, "learning_rate": 6.717444471625e-05, "loss": 0.0173, "step": 169960 }, { "epoch": 40.79, "learning_rate": 6.717107350207854e-05, "loss": 0.0132, "step": 169970 }, { "epoch": 40.79, "learning_rate": 6.716770219940723e-05, "loss": 0.0093, "step": 169980 }, { "epoch": 40.79, "learning_rate": 6.716433080825344e-05, "loss": 0.0178, "step": 169990 }, { "epoch": 40.8, "learning_rate": 6.716095932863454e-05, "loss": 0.0138, "step": 170000 }, { "epoch": 40.8, "learning_rate": 6.715758776056793e-05, "loss": 0.0151, "step": 170010 }, { "epoch": 40.8, "learning_rate": 6.715421610407095e-05, "loss": 0.0149, "step": 170020 }, { "epoch": 40.8, "learning_rate": 6.7150844359161e-05, "loss": 0.0107, "step": 170030 }, { "epoch": 40.8, "learning_rate": 6.714747252585547e-05, "loss": 0.0113, "step": 170040 }, { "epoch": 40.81, "learning_rate": 6.714410060417171e-05, "loss": 0.0096, "step": 170050 }, { "epoch": 40.81, "learning_rate": 6.714072859412711e-05, "loss": 0.0074, "step": 170060 }, { "epoch": 40.81, "learning_rate": 6.713735649573905e-05, "loss": 0.0156, "step": 170070 }, { "epoch": 40.81, "learning_rate": 6.713398430902491e-05, "loss": 0.0159, "step": 170080 }, { "epoch": 40.82, "learning_rate": 6.713061203400207e-05, "loss": 0.0242, "step": 170090 }, { "epoch": 40.82, "learning_rate": 6.712723967068794e-05, "loss": 0.0048, "step": 170100 }, { "epoch": 40.82, "learning_rate": 6.712386721909985e-05, "loss": 0.0166, "step": 170110 }, { "epoch": 40.82, "learning_rate": 6.712049467925521e-05, "loss": 0.0162, "step": 170120 }, { "epoch": 40.82, "learning_rate": 6.711712205117139e-05, "loss": 0.0136, "step": 170130 }, { "epoch": 40.83, "learning_rate": 6.711374933486578e-05, "loss": 0.0108, "step": 170140 }, { "epoch": 40.83, "learning_rate": 6.711037653035578e-05, "loss": 0.0171, "step": 170150 }, { "epoch": 40.83, "learning_rate": 6.710700363765874e-05, "loss": 0.0103, "step": 170160 }, { "epoch": 40.83, "learning_rate": 6.710363065679209e-05, "loss": 0.0137, "step": 170170 }, { "epoch": 40.84, "learning_rate": 6.710025758777314e-05, "loss": 0.0112, "step": 170180 }, { "epoch": 40.84, "learning_rate": 6.709688443061934e-05, "loss": 0.0097, "step": 170190 }, { "epoch": 40.84, "learning_rate": 6.709351118534806e-05, "loss": 0.0208, "step": 170200 }, { "epoch": 40.84, "learning_rate": 6.709013785197667e-05, "loss": 0.0052, "step": 170210 }, { "epoch": 40.85, "learning_rate": 6.708676443052257e-05, "loss": 0.0169, "step": 170220 }, { "epoch": 40.85, "learning_rate": 6.708339092100315e-05, "loss": 0.0132, "step": 170230 }, { "epoch": 40.85, "learning_rate": 6.708001732343578e-05, "loss": 0.011, "step": 170240 }, { "epoch": 40.85, "learning_rate": 6.707664363783787e-05, "loss": 0.0114, "step": 170250 }, { "epoch": 40.85, "learning_rate": 6.707326986422679e-05, "loss": 0.0106, "step": 170260 }, { "epoch": 40.86, "learning_rate": 6.706989600261992e-05, "loss": 0.0107, "step": 170270 }, { "epoch": 40.86, "learning_rate": 6.706652205303468e-05, "loss": 0.0125, "step": 170280 }, { "epoch": 40.86, "learning_rate": 6.706314801548845e-05, "loss": 0.0091, "step": 170290 }, { "epoch": 40.86, "learning_rate": 6.70597738899986e-05, "loss": 0.0076, "step": 170300 }, { "epoch": 40.87, "learning_rate": 6.705639967658254e-05, "loss": 0.0111, "step": 170310 }, { "epoch": 40.87, "learning_rate": 6.705302537525765e-05, "loss": 0.0137, "step": 170320 }, { "epoch": 40.87, "learning_rate": 6.704965098604132e-05, "loss": 0.0243, "step": 170330 }, { "epoch": 40.87, "learning_rate": 6.704627650895094e-05, "loss": 0.0066, "step": 170340 }, { "epoch": 40.88, "learning_rate": 6.704290194400394e-05, "loss": 0.0103, "step": 170350 }, { "epoch": 40.88, "learning_rate": 6.703952729121765e-05, "loss": 0.0111, "step": 170360 }, { "epoch": 40.88, "learning_rate": 6.70361525506095e-05, "loss": 0.0099, "step": 170370 }, { "epoch": 40.88, "learning_rate": 6.703277772219687e-05, "loss": 0.0076, "step": 170380 }, { "epoch": 40.88, "learning_rate": 6.702940280599717e-05, "loss": 0.0226, "step": 170390 }, { "epoch": 40.89, "learning_rate": 6.702602780202779e-05, "loss": 0.0182, "step": 170400 }, { "epoch": 40.89, "learning_rate": 6.702265271030612e-05, "loss": 0.0209, "step": 170410 }, { "epoch": 40.89, "learning_rate": 6.701927753084956e-05, "loss": 0.0116, "step": 170420 }, { "epoch": 40.89, "learning_rate": 6.701590226367548e-05, "loss": 0.0086, "step": 170430 }, { "epoch": 40.9, "learning_rate": 6.701252690880131e-05, "loss": 0.0085, "step": 170440 }, { "epoch": 40.9, "learning_rate": 6.700915146624445e-05, "loss": 0.0227, "step": 170450 }, { "epoch": 40.9, "learning_rate": 6.700577593602228e-05, "loss": 0.0099, "step": 170460 }, { "epoch": 40.9, "learning_rate": 6.700240031815217e-05, "loss": 0.0173, "step": 170470 }, { "epoch": 40.9, "learning_rate": 6.699902461265157e-05, "loss": 0.0187, "step": 170480 }, { "epoch": 40.91, "learning_rate": 6.699564881953784e-05, "loss": 0.0077, "step": 170490 }, { "epoch": 40.91, "learning_rate": 6.699227293882841e-05, "loss": 0.0102, "step": 170500 }, { "epoch": 40.91, "learning_rate": 6.698889697054065e-05, "loss": 0.0078, "step": 170510 }, { "epoch": 40.91, "learning_rate": 6.698552091469198e-05, "loss": 0.0239, "step": 170520 }, { "epoch": 40.92, "learning_rate": 6.698214477129978e-05, "loss": 0.0115, "step": 170530 }, { "epoch": 40.92, "learning_rate": 6.697876854038148e-05, "loss": 0.008, "step": 170540 }, { "epoch": 40.92, "learning_rate": 6.697539222195446e-05, "loss": 0.0087, "step": 170550 }, { "epoch": 40.92, "learning_rate": 6.697201581603613e-05, "loss": 0.0218, "step": 170560 }, { "epoch": 40.93, "learning_rate": 6.696863932264388e-05, "loss": 0.0217, "step": 170570 }, { "epoch": 40.93, "learning_rate": 6.696526274179514e-05, "loss": 0.0114, "step": 170580 }, { "epoch": 40.93, "learning_rate": 6.696188607350726e-05, "loss": 0.0106, "step": 170590 }, { "epoch": 40.93, "learning_rate": 6.695850931779771e-05, "loss": 0.0226, "step": 170600 }, { "epoch": 40.93, "learning_rate": 6.695513247468386e-05, "loss": 0.0109, "step": 170610 }, { "epoch": 40.94, "learning_rate": 6.695175554418309e-05, "loss": 0.0144, "step": 170620 }, { "epoch": 40.94, "learning_rate": 6.694837852631284e-05, "loss": 0.0103, "step": 170630 }, { "epoch": 40.94, "learning_rate": 6.694500142109052e-05, "loss": 0.0116, "step": 170640 }, { "epoch": 40.94, "learning_rate": 6.694162422853351e-05, "loss": 0.009, "step": 170650 }, { "epoch": 40.95, "learning_rate": 6.693824694865922e-05, "loss": 0.0111, "step": 170660 }, { "epoch": 40.95, "learning_rate": 6.693486958148507e-05, "loss": 0.0045, "step": 170670 }, { "epoch": 40.95, "learning_rate": 6.693149212702847e-05, "loss": 0.0207, "step": 170680 }, { "epoch": 41.0, "learning_rate": 6.692811458530681e-05, "loss": 0.0103, "step": 170690 }, { "epoch": 41.0, "learning_rate": 6.692473695633749e-05, "loss": 0.0082, "step": 170700 }, { "epoch": 41.01, "learning_rate": 6.692135924013795e-05, "loss": 0.0082, "step": 170710 }, { "epoch": 41.01, "learning_rate": 6.69179814367256e-05, "loss": 0.0123, "step": 170720 }, { "epoch": 41.01, "learning_rate": 6.69146035461178e-05, "loss": 0.0082, "step": 170730 }, { "epoch": 41.01, "learning_rate": 6.691122556833201e-05, "loss": 0.0135, "step": 170740 }, { "epoch": 41.02, "learning_rate": 6.690784750338563e-05, "loss": 0.0101, "step": 170750 }, { "epoch": 41.02, "learning_rate": 6.690446935129606e-05, "loss": 0.0109, "step": 170760 }, { "epoch": 41.02, "learning_rate": 6.69010911120807e-05, "loss": 0.0077, "step": 170770 }, { "epoch": 41.02, "learning_rate": 6.689771278575698e-05, "loss": 0.0152, "step": 170780 }, { "epoch": 41.02, "learning_rate": 6.689433437234231e-05, "loss": 0.0082, "step": 170790 }, { "epoch": 41.03, "learning_rate": 6.68909558718541e-05, "loss": 0.0111, "step": 170800 }, { "epoch": 41.03, "learning_rate": 6.688757728430976e-05, "loss": 0.0108, "step": 170810 }, { "epoch": 41.03, "learning_rate": 6.68841986097267e-05, "loss": 0.0135, "step": 170820 }, { "epoch": 41.03, "learning_rate": 6.688081984812236e-05, "loss": 0.0152, "step": 170830 }, { "epoch": 41.04, "learning_rate": 6.68774409995141e-05, "loss": 0.0117, "step": 170840 }, { "epoch": 41.04, "learning_rate": 6.687406206391939e-05, "loss": 0.011, "step": 170850 }, { "epoch": 41.04, "learning_rate": 6.687068304135561e-05, "loss": 0.0127, "step": 170860 }, { "epoch": 41.04, "learning_rate": 6.686730393184021e-05, "loss": 0.0116, "step": 170870 }, { "epoch": 41.05, "learning_rate": 6.686392473539057e-05, "loss": 0.0154, "step": 170880 }, { "epoch": 41.05, "learning_rate": 6.686054545202413e-05, "loss": 0.012, "step": 170890 }, { "epoch": 41.05, "learning_rate": 6.685716608175829e-05, "loss": 0.0138, "step": 170900 }, { "epoch": 41.05, "learning_rate": 6.685378662461048e-05, "loss": 0.0199, "step": 170910 }, { "epoch": 41.05, "learning_rate": 6.685040708059811e-05, "loss": 0.0101, "step": 170920 }, { "epoch": 41.06, "learning_rate": 6.68470274497386e-05, "loss": 0.0137, "step": 170930 }, { "epoch": 41.06, "learning_rate": 6.684364773204936e-05, "loss": 0.0444, "step": 170940 }, { "epoch": 41.06, "learning_rate": 6.684026792754783e-05, "loss": 0.0139, "step": 170950 }, { "epoch": 41.06, "learning_rate": 6.683688803625144e-05, "loss": 0.0114, "step": 170960 }, { "epoch": 41.07, "learning_rate": 6.683350805817753e-05, "loss": 0.007, "step": 170970 }, { "epoch": 41.07, "learning_rate": 6.683012799334362e-05, "loss": 0.0136, "step": 170980 }, { "epoch": 41.07, "learning_rate": 6.68267478417671e-05, "loss": 0.0084, "step": 170990 }, { "epoch": 41.07, "learning_rate": 6.682336760346536e-05, "loss": 0.0131, "step": 171000 }, { "epoch": 41.07, "learning_rate": 6.681998727845585e-05, "loss": 0.0096, "step": 171010 }, { "epoch": 41.08, "learning_rate": 6.681660686675598e-05, "loss": 0.0113, "step": 171020 }, { "epoch": 41.08, "learning_rate": 6.681322636838318e-05, "loss": 0.0178, "step": 171030 }, { "epoch": 41.08, "learning_rate": 6.680984578335487e-05, "loss": 0.0164, "step": 171040 }, { "epoch": 41.08, "learning_rate": 6.680646511168847e-05, "loss": 0.0158, "step": 171050 }, { "epoch": 41.09, "learning_rate": 6.680308435340142e-05, "loss": 0.0076, "step": 171060 }, { "epoch": 41.09, "learning_rate": 6.679970350851113e-05, "loss": 0.0119, "step": 171070 }, { "epoch": 41.09, "learning_rate": 6.679632257703502e-05, "loss": 0.0103, "step": 171080 }, { "epoch": 41.09, "learning_rate": 6.679294155899053e-05, "loss": 0.0097, "step": 171090 }, { "epoch": 41.1, "learning_rate": 6.678956045439508e-05, "loss": 0.0099, "step": 171100 }, { "epoch": 41.1, "learning_rate": 6.678617926326609e-05, "loss": 0.0127, "step": 171110 }, { "epoch": 41.1, "learning_rate": 6.678279798562098e-05, "loss": 0.0085, "step": 171120 }, { "epoch": 41.1, "learning_rate": 6.67794166214772e-05, "loss": 0.0107, "step": 171130 }, { "epoch": 41.1, "learning_rate": 6.677603517085218e-05, "loss": 0.0142, "step": 171140 }, { "epoch": 41.11, "learning_rate": 6.677265363376332e-05, "loss": 0.0153, "step": 171150 }, { "epoch": 41.11, "learning_rate": 6.676927201022807e-05, "loss": 0.0092, "step": 171160 }, { "epoch": 41.11, "learning_rate": 6.676589030026384e-05, "loss": 0.0131, "step": 171170 }, { "epoch": 41.11, "learning_rate": 6.67625085038881e-05, "loss": 0.0126, "step": 171180 }, { "epoch": 41.12, "learning_rate": 6.675912662111822e-05, "loss": 0.0154, "step": 171190 }, { "epoch": 41.12, "learning_rate": 6.675574465197167e-05, "loss": 0.0108, "step": 171200 }, { "epoch": 41.12, "learning_rate": 6.675236259646586e-05, "loss": 0.0112, "step": 171210 }, { "epoch": 41.12, "learning_rate": 6.674898045461826e-05, "loss": 0.0109, "step": 171220 }, { "epoch": 41.12, "learning_rate": 6.674559822644626e-05, "loss": 0.0132, "step": 171230 }, { "epoch": 41.13, "learning_rate": 6.674221591196729e-05, "loss": 0.0122, "step": 171240 }, { "epoch": 41.13, "learning_rate": 6.673883351119883e-05, "loss": 0.0138, "step": 171250 }, { "epoch": 41.13, "learning_rate": 6.673545102415828e-05, "loss": 0.0186, "step": 171260 }, { "epoch": 41.13, "learning_rate": 6.673206845086306e-05, "loss": 0.0147, "step": 171270 }, { "epoch": 41.14, "learning_rate": 6.672868579133061e-05, "loss": 0.0065, "step": 171280 }, { "epoch": 41.14, "learning_rate": 6.672530304557839e-05, "loss": 0.0105, "step": 171290 }, { "epoch": 41.14, "learning_rate": 6.672192021362382e-05, "loss": 0.006, "step": 171300 }, { "epoch": 41.14, "learning_rate": 6.671853729548433e-05, "loss": 0.0077, "step": 171310 }, { "epoch": 41.15, "learning_rate": 6.671515429117736e-05, "loss": 0.0065, "step": 171320 }, { "epoch": 41.15, "learning_rate": 6.671177120072034e-05, "loss": 0.0117, "step": 171330 }, { "epoch": 41.15, "learning_rate": 6.670838802413072e-05, "loss": 0.0111, "step": 171340 }, { "epoch": 41.15, "learning_rate": 6.670500476142593e-05, "loss": 0.013, "step": 171350 }, { "epoch": 41.15, "learning_rate": 6.67016214126234e-05, "loss": 0.0065, "step": 171360 }, { "epoch": 41.16, "learning_rate": 6.669823797774056e-05, "loss": 0.0199, "step": 171370 }, { "epoch": 41.16, "learning_rate": 6.669485445679488e-05, "loss": 0.0064, "step": 171380 }, { "epoch": 41.16, "learning_rate": 6.669147084980378e-05, "loss": 0.0089, "step": 171390 }, { "epoch": 41.16, "learning_rate": 6.66880871567847e-05, "loss": 0.0067, "step": 171400 }, { "epoch": 41.17, "learning_rate": 6.668470337775508e-05, "loss": 0.0072, "step": 171410 }, { "epoch": 41.17, "learning_rate": 6.668131951273235e-05, "loss": 0.0116, "step": 171420 }, { "epoch": 41.17, "learning_rate": 6.667793556173396e-05, "loss": 0.0168, "step": 171430 }, { "epoch": 41.17, "learning_rate": 6.667455152477734e-05, "loss": 0.0102, "step": 171440 }, { "epoch": 41.18, "learning_rate": 6.667116740187995e-05, "loss": 0.0089, "step": 171450 }, { "epoch": 41.18, "learning_rate": 6.666778319305924e-05, "loss": 0.0095, "step": 171460 }, { "epoch": 41.18, "learning_rate": 6.666439889833263e-05, "loss": 0.0113, "step": 171470 }, { "epoch": 41.18, "learning_rate": 6.666101451771757e-05, "loss": 0.0153, "step": 171480 }, { "epoch": 41.18, "learning_rate": 6.665763005123149e-05, "loss": 0.0095, "step": 171490 }, { "epoch": 41.19, "learning_rate": 6.665424549889185e-05, "loss": 0.0094, "step": 171500 }, { "epoch": 41.19, "learning_rate": 6.665086086071611e-05, "loss": 0.0155, "step": 171510 }, { "epoch": 41.19, "learning_rate": 6.664747613672167e-05, "loss": 0.0126, "step": 171520 }, { "epoch": 41.19, "learning_rate": 6.664409132692601e-05, "loss": 0.0154, "step": 171530 }, { "epoch": 41.2, "learning_rate": 6.664070643134655e-05, "loss": 0.0072, "step": 171540 }, { "epoch": 41.2, "learning_rate": 6.663732145000077e-05, "loss": 0.0057, "step": 171550 }, { "epoch": 41.2, "learning_rate": 6.663393638290608e-05, "loss": 0.0088, "step": 171560 }, { "epoch": 41.2, "learning_rate": 6.663055123007995e-05, "loss": 0.0094, "step": 171570 }, { "epoch": 41.2, "learning_rate": 6.662716599153982e-05, "loss": 0.0092, "step": 171580 }, { "epoch": 41.21, "learning_rate": 6.662378066730313e-05, "loss": 0.0223, "step": 171590 }, { "epoch": 41.21, "learning_rate": 6.662039525738732e-05, "loss": 0.01, "step": 171600 }, { "epoch": 41.21, "learning_rate": 6.66170097618099e-05, "loss": 0.0116, "step": 171610 }, { "epoch": 41.21, "learning_rate": 6.661362418058825e-05, "loss": 0.0094, "step": 171620 }, { "epoch": 41.22, "learning_rate": 6.661023851373983e-05, "loss": 0.0138, "step": 171630 }, { "epoch": 41.22, "learning_rate": 6.660685276128211e-05, "loss": 0.0098, "step": 171640 }, { "epoch": 41.22, "learning_rate": 6.660346692323254e-05, "loss": 0.0162, "step": 171650 }, { "epoch": 41.22, "learning_rate": 6.660008099960854e-05, "loss": 0.0115, "step": 171660 }, { "epoch": 41.23, "learning_rate": 6.65966949904276e-05, "loss": 0.015, "step": 171670 }, { "epoch": 41.23, "learning_rate": 6.659330889570717e-05, "loss": 0.0133, "step": 171680 }, { "epoch": 41.23, "learning_rate": 6.658992271546467e-05, "loss": 0.0131, "step": 171690 }, { "epoch": 41.23, "learning_rate": 6.658653644971758e-05, "loss": 0.0092, "step": 171700 }, { "epoch": 41.23, "learning_rate": 6.658315009848332e-05, "loss": 0.0154, "step": 171710 }, { "epoch": 41.24, "learning_rate": 6.657976366177939e-05, "loss": 0.0105, "step": 171720 }, { "epoch": 41.24, "learning_rate": 6.657637713962321e-05, "loss": 0.0125, "step": 171730 }, { "epoch": 41.24, "learning_rate": 6.657299053203224e-05, "loss": 0.0124, "step": 171740 }, { "epoch": 41.24, "learning_rate": 6.656960383902394e-05, "loss": 0.0064, "step": 171750 }, { "epoch": 41.25, "learning_rate": 6.656621706061576e-05, "loss": 0.0061, "step": 171760 }, { "epoch": 41.25, "learning_rate": 6.656283019682516e-05, "loss": 0.0061, "step": 171770 }, { "epoch": 41.25, "learning_rate": 6.65594432476696e-05, "loss": 0.0141, "step": 171780 }, { "epoch": 41.25, "learning_rate": 6.655605621316655e-05, "loss": 0.0075, "step": 171790 }, { "epoch": 41.26, "learning_rate": 6.655266909333341e-05, "loss": 0.0071, "step": 171800 }, { "epoch": 41.26, "learning_rate": 6.65492818881877e-05, "loss": 0.0137, "step": 171810 }, { "epoch": 41.26, "learning_rate": 6.654589459774685e-05, "loss": 0.0044, "step": 171820 }, { "epoch": 41.26, "learning_rate": 6.654250722202832e-05, "loss": 0.0079, "step": 171830 }, { "epoch": 41.26, "learning_rate": 6.653911976104956e-05, "loss": 0.0079, "step": 171840 }, { "epoch": 41.27, "learning_rate": 6.653573221482805e-05, "loss": 0.0118, "step": 171850 }, { "epoch": 41.27, "learning_rate": 6.653234458338123e-05, "loss": 0.0068, "step": 171860 }, { "epoch": 41.27, "learning_rate": 6.652895686672657e-05, "loss": 0.014, "step": 171870 }, { "epoch": 41.27, "learning_rate": 6.652556906488154e-05, "loss": 0.0075, "step": 171880 }, { "epoch": 41.28, "learning_rate": 6.652218117786356e-05, "loss": 0.0094, "step": 171890 }, { "epoch": 41.28, "learning_rate": 6.651879320569014e-05, "loss": 0.0125, "step": 171900 }, { "epoch": 41.28, "learning_rate": 6.651540514837872e-05, "loss": 0.0055, "step": 171910 }, { "epoch": 41.28, "learning_rate": 6.651201700594676e-05, "loss": 0.0117, "step": 171920 }, { "epoch": 41.28, "learning_rate": 6.650862877841172e-05, "loss": 0.0153, "step": 171930 }, { "epoch": 41.29, "learning_rate": 6.650524046579109e-05, "loss": 0.0172, "step": 171940 }, { "epoch": 41.29, "learning_rate": 6.65018520681023e-05, "loss": 0.0066, "step": 171950 }, { "epoch": 41.29, "learning_rate": 6.649846358536282e-05, "loss": 0.0141, "step": 171960 }, { "epoch": 41.29, "learning_rate": 6.649507501759014e-05, "loss": 0.0089, "step": 171970 }, { "epoch": 41.3, "learning_rate": 6.64916863648017e-05, "loss": 0.0126, "step": 171980 }, { "epoch": 41.3, "learning_rate": 6.648829762701496e-05, "loss": 0.0118, "step": 171990 }, { "epoch": 41.3, "learning_rate": 6.64849088042474e-05, "loss": 0.0084, "step": 172000 }, { "epoch": 41.3, "learning_rate": 6.648151989651649e-05, "loss": 0.012, "step": 172010 }, { "epoch": 41.31, "learning_rate": 6.647813090383967e-05, "loss": 0.0186, "step": 172020 }, { "epoch": 41.31, "learning_rate": 6.647474182623445e-05, "loss": 0.0099, "step": 172030 }, { "epoch": 41.31, "learning_rate": 6.647135266371825e-05, "loss": 0.008, "step": 172040 }, { "epoch": 41.31, "learning_rate": 6.646796341630858e-05, "loss": 0.011, "step": 172050 }, { "epoch": 41.31, "learning_rate": 6.646457408402288e-05, "loss": 0.0061, "step": 172060 }, { "epoch": 41.32, "learning_rate": 6.646118466687863e-05, "loss": 0.0056, "step": 172070 }, { "epoch": 41.32, "learning_rate": 6.645779516489329e-05, "loss": 0.0107, "step": 172080 }, { "epoch": 41.32, "learning_rate": 6.645440557808434e-05, "loss": 0.0217, "step": 172090 }, { "epoch": 41.32, "learning_rate": 6.645101590646923e-05, "loss": 0.012, "step": 172100 }, { "epoch": 41.33, "learning_rate": 6.644762615006548e-05, "loss": 0.0099, "step": 172110 }, { "epoch": 41.33, "learning_rate": 6.644423630889052e-05, "loss": 0.0112, "step": 172120 }, { "epoch": 41.33, "learning_rate": 6.644084638296183e-05, "loss": 0.0053, "step": 172130 }, { "epoch": 41.33, "learning_rate": 6.643745637229686e-05, "loss": 0.0068, "step": 172140 }, { "epoch": 41.34, "learning_rate": 6.643406627691311e-05, "loss": 0.0117, "step": 172150 }, { "epoch": 41.34, "learning_rate": 6.643067609682803e-05, "loss": 0.0112, "step": 172160 }, { "epoch": 41.34, "learning_rate": 6.642728583205913e-05, "loss": 0.0144, "step": 172170 }, { "epoch": 41.34, "learning_rate": 6.642389548262387e-05, "loss": 0.0119, "step": 172180 }, { "epoch": 41.34, "learning_rate": 6.64205050485397e-05, "loss": 0.0209, "step": 172190 }, { "epoch": 41.35, "learning_rate": 6.64171145298241e-05, "loss": 0.0095, "step": 172200 }, { "epoch": 41.35, "learning_rate": 6.641372392649456e-05, "loss": 0.0075, "step": 172210 }, { "epoch": 41.35, "learning_rate": 6.641033323856856e-05, "loss": 0.0098, "step": 172220 }, { "epoch": 41.35, "learning_rate": 6.640694246606357e-05, "loss": 0.0102, "step": 172230 }, { "epoch": 41.36, "learning_rate": 6.640355160899705e-05, "loss": 0.0152, "step": 172240 }, { "epoch": 41.36, "learning_rate": 6.640016066738649e-05, "loss": 0.0064, "step": 172250 }, { "epoch": 41.36, "learning_rate": 6.639676964124937e-05, "loss": 0.0132, "step": 172260 }, { "epoch": 41.36, "learning_rate": 6.639337853060316e-05, "loss": 0.0041, "step": 172270 }, { "epoch": 41.36, "learning_rate": 6.638998733546533e-05, "loss": 0.0126, "step": 172280 }, { "epoch": 41.37, "learning_rate": 6.638659605585338e-05, "loss": 0.01, "step": 172290 }, { "epoch": 41.37, "learning_rate": 6.638320469178477e-05, "loss": 0.0095, "step": 172300 }, { "epoch": 41.37, "learning_rate": 6.637981324327698e-05, "loss": 0.0073, "step": 172310 }, { "epoch": 41.37, "learning_rate": 6.63764217103475e-05, "loss": 0.0109, "step": 172320 }, { "epoch": 41.38, "learning_rate": 6.637303009301382e-05, "loss": 0.0065, "step": 172330 }, { "epoch": 41.38, "learning_rate": 6.63696383912934e-05, "loss": 0.0127, "step": 172340 }, { "epoch": 41.38, "learning_rate": 6.636624660520371e-05, "loss": 0.0051, "step": 172350 }, { "epoch": 41.38, "learning_rate": 6.636285473476227e-05, "loss": 0.0161, "step": 172360 }, { "epoch": 41.39, "learning_rate": 6.635946277998653e-05, "loss": 0.0173, "step": 172370 }, { "epoch": 41.39, "learning_rate": 6.635607074089398e-05, "loss": 0.007, "step": 172380 }, { "epoch": 41.39, "learning_rate": 6.635267861750211e-05, "loss": 0.0048, "step": 172390 }, { "epoch": 41.39, "learning_rate": 6.63492864098284e-05, "loss": 0.0133, "step": 172400 }, { "epoch": 41.39, "learning_rate": 6.634589411789032e-05, "loss": 0.0117, "step": 172410 }, { "epoch": 41.4, "learning_rate": 6.634250174170538e-05, "loss": 0.0069, "step": 172420 }, { "epoch": 41.4, "learning_rate": 6.633910928129104e-05, "loss": 0.0087, "step": 172430 }, { "epoch": 41.4, "learning_rate": 6.633571673666479e-05, "loss": 0.0121, "step": 172440 }, { "epoch": 41.4, "learning_rate": 6.633232410784413e-05, "loss": 0.0116, "step": 172450 }, { "epoch": 41.41, "learning_rate": 6.632893139484652e-05, "loss": 0.0142, "step": 172460 }, { "epoch": 41.41, "learning_rate": 6.632553859768949e-05, "loss": 0.0093, "step": 172470 }, { "epoch": 41.41, "learning_rate": 6.632214571639046e-05, "loss": 0.0102, "step": 172480 }, { "epoch": 41.41, "learning_rate": 6.631875275096697e-05, "loss": 0.0097, "step": 172490 }, { "epoch": 41.42, "learning_rate": 6.63153597014365e-05, "loss": 0.0123, "step": 172500 }, { "epoch": 41.42, "learning_rate": 6.631196656781653e-05, "loss": 0.0198, "step": 172510 }, { "epoch": 41.42, "learning_rate": 6.630857335012454e-05, "loss": 0.0139, "step": 172520 }, { "epoch": 41.42, "learning_rate": 6.630518004837802e-05, "loss": 0.0087, "step": 172530 }, { "epoch": 41.42, "learning_rate": 6.63017866625945e-05, "loss": 0.0109, "step": 172540 }, { "epoch": 41.43, "learning_rate": 6.62983931927914e-05, "loss": 0.0082, "step": 172550 }, { "epoch": 41.43, "learning_rate": 6.629499963898625e-05, "loss": 0.0134, "step": 172560 }, { "epoch": 41.43, "learning_rate": 6.629160600119655e-05, "loss": 0.0071, "step": 172570 }, { "epoch": 41.43, "learning_rate": 6.628821227943977e-05, "loss": 0.0117, "step": 172580 }, { "epoch": 41.44, "learning_rate": 6.62848184737334e-05, "loss": 0.0115, "step": 172590 }, { "epoch": 41.44, "learning_rate": 6.628142458409494e-05, "loss": 0.0116, "step": 172600 }, { "epoch": 41.44, "learning_rate": 6.62780306105419e-05, "loss": 0.0082, "step": 172610 }, { "epoch": 41.44, "learning_rate": 6.627463655309174e-05, "loss": 0.0112, "step": 172620 }, { "epoch": 41.44, "learning_rate": 6.627124241176197e-05, "loss": 0.0091, "step": 172630 }, { "epoch": 41.45, "learning_rate": 6.626784818657006e-05, "loss": 0.0061, "step": 172640 }, { "epoch": 41.45, "learning_rate": 6.626445387753355e-05, "loss": 0.0096, "step": 172650 }, { "epoch": 41.45, "learning_rate": 6.62610594846699e-05, "loss": 0.0089, "step": 172660 }, { "epoch": 41.45, "learning_rate": 6.625766500799661e-05, "loss": 0.0214, "step": 172670 }, { "epoch": 41.46, "learning_rate": 6.62542704475312e-05, "loss": 0.0287, "step": 172680 }, { "epoch": 41.46, "learning_rate": 6.625087580329112e-05, "loss": 0.0117, "step": 172690 }, { "epoch": 41.46, "learning_rate": 6.62474810752939e-05, "loss": 0.0115, "step": 172700 }, { "epoch": 41.46, "learning_rate": 6.624408626355703e-05, "loss": 0.0099, "step": 172710 }, { "epoch": 41.47, "learning_rate": 6.6240691368098e-05, "loss": 0.0127, "step": 172720 }, { "epoch": 41.47, "learning_rate": 6.62372963889343e-05, "loss": 0.0147, "step": 172730 }, { "epoch": 41.47, "learning_rate": 6.623390132608344e-05, "loss": 0.006, "step": 172740 }, { "epoch": 41.47, "learning_rate": 6.623050617956294e-05, "loss": 0.0159, "step": 172750 }, { "epoch": 41.47, "learning_rate": 6.622711094939027e-05, "loss": 0.0082, "step": 172760 }, { "epoch": 41.48, "learning_rate": 6.622371563558292e-05, "loss": 0.0096, "step": 172770 }, { "epoch": 41.48, "learning_rate": 6.62203202381584e-05, "loss": 0.0233, "step": 172780 }, { "epoch": 41.48, "learning_rate": 6.621692475713424e-05, "loss": 0.0096, "step": 172790 }, { "epoch": 41.48, "learning_rate": 6.621352919252788e-05, "loss": 0.0044, "step": 172800 }, { "epoch": 41.49, "learning_rate": 6.621013354435687e-05, "loss": 0.0244, "step": 172810 }, { "epoch": 41.49, "learning_rate": 6.62067378126387e-05, "loss": 0.0088, "step": 172820 }, { "epoch": 41.49, "learning_rate": 6.620334199739087e-05, "loss": 0.0117, "step": 172830 }, { "epoch": 41.49, "learning_rate": 6.619994609863087e-05, "loss": 0.0119, "step": 172840 }, { "epoch": 41.5, "learning_rate": 6.619655011637623e-05, "loss": 0.0175, "step": 172850 }, { "epoch": 41.5, "learning_rate": 6.619315405064441e-05, "loss": 0.0156, "step": 172860 }, { "epoch": 41.5, "learning_rate": 6.618975790145297e-05, "loss": 0.0105, "step": 172870 }, { "epoch": 41.5, "learning_rate": 6.618636166881936e-05, "loss": 0.0569, "step": 172880 }, { "epoch": 41.5, "learning_rate": 6.61829653527611e-05, "loss": 0.0093, "step": 172890 }, { "epoch": 41.51, "learning_rate": 6.617956895329574e-05, "loss": 0.0165, "step": 172900 }, { "epoch": 41.51, "learning_rate": 6.61761724704407e-05, "loss": 0.0087, "step": 172910 }, { "epoch": 41.51, "learning_rate": 6.617277590421356e-05, "loss": 0.0115, "step": 172920 }, { "epoch": 41.51, "learning_rate": 6.616937925463179e-05, "loss": 0.0048, "step": 172930 }, { "epoch": 41.52, "learning_rate": 6.61659825217129e-05, "loss": 0.0118, "step": 172940 }, { "epoch": 41.52, "learning_rate": 6.61625857054744e-05, "loss": 0.0081, "step": 172950 }, { "epoch": 41.52, "learning_rate": 6.615918880593379e-05, "loss": 0.013, "step": 172960 }, { "epoch": 41.52, "learning_rate": 6.615579182310862e-05, "loss": 0.015, "step": 172970 }, { "epoch": 41.52, "learning_rate": 6.615239475701633e-05, "loss": 0.0158, "step": 172980 }, { "epoch": 41.53, "learning_rate": 6.614899760767448e-05, "loss": 0.0156, "step": 172990 }, { "epoch": 41.53, "learning_rate": 6.614560037510056e-05, "loss": 0.0137, "step": 173000 }, { "epoch": 41.53, "learning_rate": 6.614220305931207e-05, "loss": 0.0113, "step": 173010 }, { "epoch": 41.53, "learning_rate": 6.613880566032653e-05, "loss": 0.0151, "step": 173020 }, { "epoch": 41.54, "learning_rate": 6.613540817816147e-05, "loss": 0.0236, "step": 173030 }, { "epoch": 41.54, "learning_rate": 6.613201061283437e-05, "loss": 0.0175, "step": 173040 }, { "epoch": 41.54, "learning_rate": 6.612861296436275e-05, "loss": 0.0175, "step": 173050 }, { "epoch": 41.54, "learning_rate": 6.612521523276413e-05, "loss": 0.0093, "step": 173060 }, { "epoch": 41.55, "learning_rate": 6.612181741805601e-05, "loss": 0.0176, "step": 173070 }, { "epoch": 41.55, "learning_rate": 6.61184195202559e-05, "loss": 0.0354, "step": 173080 }, { "epoch": 41.55, "learning_rate": 6.611502153938134e-05, "loss": 0.0196, "step": 173090 }, { "epoch": 41.55, "learning_rate": 6.611162347544981e-05, "loss": 0.0084, "step": 173100 }, { "epoch": 41.55, "learning_rate": 6.610822532847884e-05, "loss": 0.0145, "step": 173110 }, { "epoch": 41.56, "learning_rate": 6.610482709848595e-05, "loss": 0.0263, "step": 173120 }, { "epoch": 41.56, "learning_rate": 6.610142878548864e-05, "loss": 0.0102, "step": 173130 }, { "epoch": 41.56, "learning_rate": 6.609803038950443e-05, "loss": 0.0128, "step": 173140 }, { "epoch": 41.56, "learning_rate": 6.609463191055084e-05, "loss": 0.0158, "step": 173150 }, { "epoch": 41.57, "learning_rate": 6.60912333486454e-05, "loss": 0.0126, "step": 173160 }, { "epoch": 41.57, "learning_rate": 6.608783470380558e-05, "loss": 0.0114, "step": 173170 }, { "epoch": 41.57, "learning_rate": 6.608443597604894e-05, "loss": 0.0188, "step": 173180 }, { "epoch": 41.57, "learning_rate": 6.608103716539298e-05, "loss": 0.0141, "step": 173190 }, { "epoch": 41.58, "learning_rate": 6.607763827185522e-05, "loss": 0.0201, "step": 173200 }, { "epoch": 41.58, "learning_rate": 6.607423929545318e-05, "loss": 0.0078, "step": 173210 }, { "epoch": 41.58, "learning_rate": 6.607084023620437e-05, "loss": 0.0104, "step": 173220 }, { "epoch": 41.58, "learning_rate": 6.606744109412633e-05, "loss": 0.0164, "step": 173230 }, { "epoch": 41.58, "learning_rate": 6.606404186923654e-05, "loss": 0.0163, "step": 173240 }, { "epoch": 41.59, "learning_rate": 6.606064256155255e-05, "loss": 0.0159, "step": 173250 }, { "epoch": 41.59, "learning_rate": 6.605724317109189e-05, "loss": 0.0112, "step": 173260 }, { "epoch": 41.59, "learning_rate": 6.605384369787205e-05, "loss": 0.0199, "step": 173270 }, { "epoch": 41.59, "learning_rate": 6.605044414191057e-05, "loss": 0.0139, "step": 173280 }, { "epoch": 41.6, "learning_rate": 6.604704450322496e-05, "loss": 0.0088, "step": 173290 }, { "epoch": 41.6, "learning_rate": 6.604364478183278e-05, "loss": 0.0233, "step": 173300 }, { "epoch": 41.6, "learning_rate": 6.604024497775147e-05, "loss": 0.0107, "step": 173310 }, { "epoch": 41.6, "learning_rate": 6.603684509099865e-05, "loss": 0.0196, "step": 173320 }, { "epoch": 41.6, "learning_rate": 6.603344512159178e-05, "loss": 0.0112, "step": 173330 }, { "epoch": 41.61, "learning_rate": 6.60300450695484e-05, "loss": 0.015, "step": 173340 }, { "epoch": 41.61, "learning_rate": 6.602664493488602e-05, "loss": 0.0158, "step": 173350 }, { "epoch": 41.61, "learning_rate": 6.602324471762219e-05, "loss": 0.0172, "step": 173360 }, { "epoch": 41.61, "learning_rate": 6.601984441777443e-05, "loss": 0.0173, "step": 173370 }, { "epoch": 41.62, "learning_rate": 6.601644403536024e-05, "loss": 0.0142, "step": 173380 }, { "epoch": 41.62, "learning_rate": 6.601304357039717e-05, "loss": 0.0112, "step": 173390 }, { "epoch": 41.62, "learning_rate": 6.600964302290274e-05, "loss": 0.0156, "step": 173400 }, { "epoch": 41.62, "learning_rate": 6.600624239289448e-05, "loss": 0.013, "step": 173410 }, { "epoch": 41.63, "learning_rate": 6.60028416803899e-05, "loss": 0.0132, "step": 173420 }, { "epoch": 41.63, "learning_rate": 6.599944088540655e-05, "loss": 0.0117, "step": 173430 }, { "epoch": 41.63, "learning_rate": 6.599604000796196e-05, "loss": 0.0111, "step": 173440 }, { "epoch": 41.63, "learning_rate": 6.599263904807363e-05, "loss": 0.0067, "step": 173450 }, { "epoch": 41.63, "learning_rate": 6.598923800575911e-05, "loss": 0.0186, "step": 173460 }, { "epoch": 41.64, "learning_rate": 6.598583688103593e-05, "loss": 0.0204, "step": 173470 }, { "epoch": 41.64, "learning_rate": 6.598243567392161e-05, "loss": 0.0136, "step": 173480 }, { "epoch": 41.64, "learning_rate": 6.597903438443368e-05, "loss": 0.009, "step": 173490 }, { "epoch": 41.64, "learning_rate": 6.597563301258967e-05, "loss": 0.0234, "step": 173500 }, { "epoch": 41.65, "learning_rate": 6.597223155840712e-05, "loss": 0.0206, "step": 173510 }, { "epoch": 41.65, "learning_rate": 6.596883002190355e-05, "loss": 0.0114, "step": 173520 }, { "epoch": 41.65, "learning_rate": 6.59654284030965e-05, "loss": 0.0193, "step": 173530 }, { "epoch": 41.65, "learning_rate": 6.596202670200349e-05, "loss": 0.0153, "step": 173540 }, { "epoch": 41.66, "learning_rate": 6.595862491864207e-05, "loss": 0.0253, "step": 173550 }, { "epoch": 41.66, "learning_rate": 6.595522305302976e-05, "loss": 0.0097, "step": 173560 }, { "epoch": 41.66, "learning_rate": 6.59518211051841e-05, "loss": 0.019, "step": 173570 }, { "epoch": 41.66, "learning_rate": 6.594841907512261e-05, "loss": 0.0158, "step": 173580 }, { "epoch": 41.66, "learning_rate": 6.594501696286284e-05, "loss": 0.0105, "step": 173590 }, { "epoch": 41.67, "learning_rate": 6.594161476842234e-05, "loss": 0.0212, "step": 173600 }, { "epoch": 41.67, "learning_rate": 6.593821249181859e-05, "loss": 0.0134, "step": 173610 }, { "epoch": 41.67, "learning_rate": 6.593481013306919e-05, "loss": 0.0146, "step": 173620 }, { "epoch": 41.67, "learning_rate": 6.593140769219164e-05, "loss": 0.022, "step": 173630 }, { "epoch": 41.68, "learning_rate": 6.592800516920348e-05, "loss": 0.0122, "step": 173640 }, { "epoch": 41.68, "learning_rate": 6.592460256412223e-05, "loss": 0.0055, "step": 173650 }, { "epoch": 41.68, "learning_rate": 6.592119987696545e-05, "loss": 0.0127, "step": 173660 }, { "epoch": 41.68, "learning_rate": 6.59177971077507e-05, "loss": 0.0071, "step": 173670 }, { "epoch": 41.68, "learning_rate": 6.591439425649546e-05, "loss": 0.0229, "step": 173680 }, { "epoch": 41.69, "learning_rate": 6.59109913232173e-05, "loss": 0.018, "step": 173690 }, { "epoch": 41.69, "learning_rate": 6.590758830793377e-05, "loss": 0.0203, "step": 173700 }, { "epoch": 41.69, "learning_rate": 6.590418521066241e-05, "loss": 0.0101, "step": 173710 }, { "epoch": 41.69, "learning_rate": 6.590078203142072e-05, "loss": 0.0085, "step": 173720 }, { "epoch": 41.7, "learning_rate": 6.589737877022628e-05, "loss": 0.01, "step": 173730 }, { "epoch": 41.7, "learning_rate": 6.589397542709661e-05, "loss": 0.0084, "step": 173740 }, { "epoch": 41.7, "learning_rate": 6.589057200204926e-05, "loss": 0.0096, "step": 173750 }, { "epoch": 41.7, "learning_rate": 6.58871684951018e-05, "loss": 0.0199, "step": 173760 }, { "epoch": 41.71, "learning_rate": 6.58837649062717e-05, "loss": 0.0079, "step": 173770 }, { "epoch": 41.71, "learning_rate": 6.588036123557655e-05, "loss": 0.0085, "step": 173780 }, { "epoch": 41.71, "learning_rate": 6.58769574830339e-05, "loss": 0.0131, "step": 173790 }, { "epoch": 41.71, "learning_rate": 6.587355364866126e-05, "loss": 0.0136, "step": 173800 }, { "epoch": 41.71, "learning_rate": 6.58701497324762e-05, "loss": 0.0103, "step": 173810 }, { "epoch": 41.72, "learning_rate": 6.586674573449626e-05, "loss": 0.0099, "step": 173820 }, { "epoch": 41.72, "learning_rate": 6.586334165473898e-05, "loss": 0.0183, "step": 173830 }, { "epoch": 41.72, "learning_rate": 6.58599374932219e-05, "loss": 0.0107, "step": 173840 }, { "epoch": 41.72, "learning_rate": 6.585653324996257e-05, "loss": 0.0215, "step": 173850 }, { "epoch": 41.73, "learning_rate": 6.585312892497853e-05, "loss": 0.0163, "step": 173860 }, { "epoch": 41.73, "learning_rate": 6.584972451828734e-05, "loss": 0.0127, "step": 173870 }, { "epoch": 41.73, "learning_rate": 6.584632002990653e-05, "loss": 0.013, "step": 173880 }, { "epoch": 41.73, "learning_rate": 6.584291545985366e-05, "loss": 0.0068, "step": 173890 }, { "epoch": 41.74, "learning_rate": 6.583951080814627e-05, "loss": 0.0132, "step": 173900 }, { "epoch": 41.74, "learning_rate": 6.583610607480191e-05, "loss": 0.012, "step": 173910 }, { "epoch": 41.74, "learning_rate": 6.583270125983812e-05, "loss": 0.0144, "step": 173920 }, { "epoch": 41.74, "learning_rate": 6.582929636327246e-05, "loss": 0.0185, "step": 173930 }, { "epoch": 41.74, "learning_rate": 6.582589138512247e-05, "loss": 0.0119, "step": 173940 }, { "epoch": 41.75, "learning_rate": 6.582248632540572e-05, "loss": 0.0141, "step": 173950 }, { "epoch": 41.75, "learning_rate": 6.581908118413973e-05, "loss": 0.0211, "step": 173960 }, { "epoch": 41.75, "learning_rate": 6.581567596134206e-05, "loss": 0.0181, "step": 173970 }, { "epoch": 41.75, "learning_rate": 6.581227065703029e-05, "loss": 0.0195, "step": 173980 }, { "epoch": 41.76, "learning_rate": 6.58088652712219e-05, "loss": 0.012, "step": 173990 }, { "epoch": 41.76, "learning_rate": 6.580545980393451e-05, "loss": 0.0173, "step": 174000 }, { "epoch": 41.76, "learning_rate": 6.580205425518564e-05, "loss": 0.0179, "step": 174010 }, { "epoch": 41.76, "learning_rate": 6.579864862499286e-05, "loss": 0.0108, "step": 174020 }, { "epoch": 41.76, "learning_rate": 6.579524291337372e-05, "loss": 0.0233, "step": 174030 }, { "epoch": 41.77, "learning_rate": 6.579183712034576e-05, "loss": 0.011, "step": 174040 }, { "epoch": 41.77, "learning_rate": 6.578843124592654e-05, "loss": 0.0159, "step": 174050 }, { "epoch": 41.77, "learning_rate": 6.57850252901336e-05, "loss": 0.0102, "step": 174060 }, { "epoch": 41.77, "learning_rate": 6.578161925298453e-05, "loss": 0.0171, "step": 174070 }, { "epoch": 41.78, "learning_rate": 6.577821313449685e-05, "loss": 0.0233, "step": 174080 }, { "epoch": 41.78, "learning_rate": 6.577480693468812e-05, "loss": 0.0211, "step": 174090 }, { "epoch": 41.78, "learning_rate": 6.577140065357591e-05, "loss": 0.0113, "step": 174100 }, { "epoch": 41.78, "learning_rate": 6.576799429117778e-05, "loss": 0.0183, "step": 174110 }, { "epoch": 41.79, "learning_rate": 6.576458784751127e-05, "loss": 0.006, "step": 174120 }, { "epoch": 41.79, "learning_rate": 6.576118132259394e-05, "loss": 0.0093, "step": 174130 }, { "epoch": 41.79, "learning_rate": 6.575777471644334e-05, "loss": 0.0151, "step": 174140 }, { "epoch": 41.79, "learning_rate": 6.575436802907704e-05, "loss": 0.0128, "step": 174150 }, { "epoch": 41.79, "learning_rate": 6.57509612605126e-05, "loss": 0.0119, "step": 174160 }, { "epoch": 41.8, "learning_rate": 6.574755441076756e-05, "loss": 0.0398, "step": 174170 }, { "epoch": 41.8, "learning_rate": 6.574414747985951e-05, "loss": 0.0111, "step": 174180 }, { "epoch": 41.8, "learning_rate": 6.574074046780601e-05, "loss": 0.0195, "step": 174190 }, { "epoch": 41.8, "learning_rate": 6.573733337462458e-05, "loss": 0.0115, "step": 174200 }, { "epoch": 41.81, "learning_rate": 6.573392620033281e-05, "loss": 0.0204, "step": 174210 }, { "epoch": 41.81, "learning_rate": 6.573051894494823e-05, "loss": 0.0074, "step": 174220 }, { "epoch": 41.81, "learning_rate": 6.572711160848845e-05, "loss": 0.0111, "step": 174230 }, { "epoch": 41.81, "learning_rate": 6.572370419097099e-05, "loss": 0.0077, "step": 174240 }, { "epoch": 41.82, "learning_rate": 6.572029669241344e-05, "loss": 0.0101, "step": 174250 }, { "epoch": 41.82, "learning_rate": 6.571688911283334e-05, "loss": 0.0109, "step": 174260 }, { "epoch": 41.82, "learning_rate": 6.571348145224827e-05, "loss": 0.0097, "step": 174270 }, { "epoch": 41.82, "learning_rate": 6.57100737106758e-05, "loss": 0.0117, "step": 174280 }, { "epoch": 41.82, "learning_rate": 6.570666588813345e-05, "loss": 0.0129, "step": 174290 }, { "epoch": 41.83, "learning_rate": 6.570325798463881e-05, "loss": 0.0108, "step": 174300 }, { "epoch": 41.83, "learning_rate": 6.569985000020946e-05, "loss": 0.013, "step": 174310 }, { "epoch": 41.83, "learning_rate": 6.569644193486293e-05, "loss": 0.0143, "step": 174320 }, { "epoch": 41.83, "learning_rate": 6.569303378861685e-05, "loss": 0.0139, "step": 174330 }, { "epoch": 41.84, "learning_rate": 6.568962556148872e-05, "loss": 0.0075, "step": 174340 }, { "epoch": 41.84, "learning_rate": 6.568621725349613e-05, "loss": 0.0126, "step": 174350 }, { "epoch": 41.84, "learning_rate": 6.568280886465664e-05, "loss": 0.0138, "step": 174360 }, { "epoch": 41.84, "learning_rate": 6.567940039498783e-05, "loss": 0.0143, "step": 174370 }, { "epoch": 41.84, "learning_rate": 6.567599184450725e-05, "loss": 0.0045, "step": 174380 }, { "epoch": 41.85, "learning_rate": 6.567258321323249e-05, "loss": 0.0122, "step": 174390 }, { "epoch": 41.85, "learning_rate": 6.566917450118108e-05, "loss": 0.0108, "step": 174400 }, { "epoch": 41.85, "learning_rate": 6.566576570837065e-05, "loss": 0.0094, "step": 174410 }, { "epoch": 41.85, "learning_rate": 6.566235683481871e-05, "loss": 0.0093, "step": 174420 }, { "epoch": 41.86, "learning_rate": 6.565894788054287e-05, "loss": 0.0101, "step": 174430 }, { "epoch": 41.86, "learning_rate": 6.565553884556065e-05, "loss": 0.0135, "step": 174440 }, { "epoch": 41.86, "learning_rate": 6.565212972988967e-05, "loss": 0.023, "step": 174450 }, { "epoch": 41.86, "learning_rate": 6.564872053354749e-05, "loss": 0.0241, "step": 174460 }, { "epoch": 41.87, "learning_rate": 6.564531125655166e-05, "loss": 0.0056, "step": 174470 }, { "epoch": 41.87, "learning_rate": 6.564190189891978e-05, "loss": 0.0099, "step": 174480 }, { "epoch": 41.87, "learning_rate": 6.56384924606694e-05, "loss": 0.0222, "step": 174490 }, { "epoch": 41.87, "learning_rate": 6.563508294181808e-05, "loss": 0.0146, "step": 174500 }, { "epoch": 41.87, "learning_rate": 6.563167334238343e-05, "loss": 0.0123, "step": 174510 }, { "epoch": 41.88, "learning_rate": 6.562826366238301e-05, "loss": 0.019, "step": 174520 }, { "epoch": 41.88, "learning_rate": 6.562485390183438e-05, "loss": 0.0119, "step": 174530 }, { "epoch": 41.88, "learning_rate": 6.562144406075513e-05, "loss": 0.0194, "step": 174540 }, { "epoch": 41.88, "learning_rate": 6.561803413916283e-05, "loss": 0.0097, "step": 174550 }, { "epoch": 41.89, "learning_rate": 6.561462413707504e-05, "loss": 0.0287, "step": 174560 }, { "epoch": 41.89, "learning_rate": 6.561121405450934e-05, "loss": 0.0095, "step": 174570 }, { "epoch": 41.89, "learning_rate": 6.560780389148333e-05, "loss": 0.0149, "step": 174580 }, { "epoch": 41.89, "learning_rate": 6.560439364801457e-05, "loss": 0.0085, "step": 174590 }, { "epoch": 41.9, "learning_rate": 6.560098332412061e-05, "loss": 0.0133, "step": 174600 }, { "epoch": 41.9, "learning_rate": 6.559757291981908e-05, "loss": 0.0083, "step": 174610 }, { "epoch": 41.9, "learning_rate": 6.55941624351275e-05, "loss": 0.0107, "step": 174620 }, { "epoch": 41.9, "learning_rate": 6.55907518700635e-05, "loss": 0.0126, "step": 174630 }, { "epoch": 41.9, "learning_rate": 6.558734122464462e-05, "loss": 0.0096, "step": 174640 }, { "epoch": 41.91, "learning_rate": 6.558393049888846e-05, "loss": 0.0062, "step": 174650 }, { "epoch": 41.91, "learning_rate": 6.558051969281258e-05, "loss": 0.0126, "step": 174660 }, { "epoch": 41.91, "learning_rate": 6.557710880643458e-05, "loss": 0.0086, "step": 174670 }, { "epoch": 41.91, "learning_rate": 6.557369783977204e-05, "loss": 0.0072, "step": 174680 }, { "epoch": 41.92, "learning_rate": 6.557028679284254e-05, "loss": 0.0066, "step": 174690 }, { "epoch": 41.92, "learning_rate": 6.556687566566363e-05, "loss": 0.0196, "step": 174700 }, { "epoch": 41.92, "learning_rate": 6.556346445825293e-05, "loss": 0.0117, "step": 174710 }, { "epoch": 41.92, "learning_rate": 6.556005317062798e-05, "loss": 0.0087, "step": 174720 }, { "epoch": 41.92, "learning_rate": 6.55566418028064e-05, "loss": 0.0136, "step": 174730 }, { "epoch": 41.93, "learning_rate": 6.555323035480575e-05, "loss": 0.0114, "step": 174740 }, { "epoch": 41.93, "learning_rate": 6.554981882664363e-05, "loss": 0.0107, "step": 174750 }, { "epoch": 41.93, "learning_rate": 6.554640721833761e-05, "loss": 0.0088, "step": 174760 }, { "epoch": 41.93, "learning_rate": 6.554299552990529e-05, "loss": 0.0062, "step": 174770 }, { "epoch": 41.94, "learning_rate": 6.553958376136422e-05, "loss": 0.008, "step": 174780 }, { "epoch": 41.94, "learning_rate": 6.553617191273202e-05, "loss": 0.0095, "step": 174790 }, { "epoch": 41.94, "learning_rate": 6.553275998402625e-05, "loss": 0.0133, "step": 174800 }, { "epoch": 41.94, "learning_rate": 6.55293479752645e-05, "loss": 0.0077, "step": 174810 }, { "epoch": 41.95, "learning_rate": 6.552593588646439e-05, "loss": 0.01, "step": 174820 }, { "epoch": 41.95, "learning_rate": 6.552252371764344e-05, "loss": 0.0194, "step": 174830 }, { "epoch": 41.95, "learning_rate": 6.55191114688193e-05, "loss": 0.0164, "step": 174840 }, { "epoch": 42.0, "learning_rate": 6.551569914000953e-05, "loss": 0.0073, "step": 174850 }, { "epoch": 42.0, "learning_rate": 6.551228673123171e-05, "loss": 0.0095, "step": 174860 }, { "epoch": 42.01, "learning_rate": 6.550887424250342e-05, "loss": 0.0107, "step": 174870 }, { "epoch": 42.01, "learning_rate": 6.550546167384228e-05, "loss": 0.0127, "step": 174880 }, { "epoch": 42.01, "learning_rate": 6.550204902526586e-05, "loss": 0.0086, "step": 174890 }, { "epoch": 42.01, "learning_rate": 6.549863629679173e-05, "loss": 0.0235, "step": 174900 }, { "epoch": 42.01, "learning_rate": 6.549522348843752e-05, "loss": 0.0106, "step": 174910 }, { "epoch": 42.02, "learning_rate": 6.549181060022079e-05, "loss": 0.0247, "step": 174920 }, { "epoch": 42.02, "learning_rate": 6.548839763215915e-05, "loss": 0.0241, "step": 174930 }, { "epoch": 42.02, "learning_rate": 6.548498458427016e-05, "loss": 0.0293, "step": 174940 }, { "epoch": 42.02, "learning_rate": 6.548157145657144e-05, "loss": 0.0093, "step": 174950 }, { "epoch": 42.03, "learning_rate": 6.547815824908057e-05, "loss": 0.0071, "step": 174960 }, { "epoch": 42.03, "learning_rate": 6.547474496181515e-05, "loss": 0.0133, "step": 174970 }, { "epoch": 42.03, "learning_rate": 6.547133159479277e-05, "loss": 0.0164, "step": 174980 }, { "epoch": 42.03, "learning_rate": 6.546791814803102e-05, "loss": 0.0104, "step": 174990 }, { "epoch": 42.04, "learning_rate": 6.546450462154748e-05, "loss": 0.0112, "step": 175000 }, { "epoch": 42.04, "learning_rate": 6.546109101535973e-05, "loss": 0.0106, "step": 175010 }, { "epoch": 42.04, "learning_rate": 6.545767732948542e-05, "loss": 0.004, "step": 175020 }, { "epoch": 42.04, "learning_rate": 6.54542635639421e-05, "loss": 0.0125, "step": 175030 }, { "epoch": 42.04, "learning_rate": 6.545084971874738e-05, "loss": 0.0128, "step": 175040 }, { "epoch": 42.05, "learning_rate": 6.544743579391884e-05, "loss": 0.0136, "step": 175050 }, { "epoch": 42.05, "learning_rate": 6.544402178947411e-05, "loss": 0.0116, "step": 175060 }, { "epoch": 42.05, "learning_rate": 6.544060770543075e-05, "loss": 0.0121, "step": 175070 }, { "epoch": 42.05, "learning_rate": 6.543719354180635e-05, "loss": 0.0157, "step": 175080 }, { "epoch": 42.06, "learning_rate": 6.543377929861855e-05, "loss": 0.0195, "step": 175090 }, { "epoch": 42.06, "learning_rate": 6.543036497588491e-05, "loss": 0.0099, "step": 175100 }, { "epoch": 42.06, "learning_rate": 6.542695057362305e-05, "loss": 0.0124, "step": 175110 }, { "epoch": 42.06, "learning_rate": 6.542353609185057e-05, "loss": 0.0053, "step": 175120 }, { "epoch": 42.06, "learning_rate": 6.542012153058503e-05, "loss": 0.0153, "step": 175130 }, { "epoch": 42.07, "learning_rate": 6.541670688984408e-05, "loss": 0.0131, "step": 175140 }, { "epoch": 42.07, "learning_rate": 6.541329216964527e-05, "loss": 0.0193, "step": 175150 }, { "epoch": 42.07, "learning_rate": 6.540987737000622e-05, "loss": 0.0101, "step": 175160 }, { "epoch": 42.07, "learning_rate": 6.540646249094455e-05, "loss": 0.0085, "step": 175170 }, { "epoch": 42.08, "learning_rate": 6.540304753247783e-05, "loss": 0.0062, "step": 175180 }, { "epoch": 42.08, "learning_rate": 6.539963249462368e-05, "loss": 0.0078, "step": 175190 }, { "epoch": 42.08, "learning_rate": 6.53962173773997e-05, "loss": 0.0051, "step": 175200 }, { "epoch": 42.08, "learning_rate": 6.539280218082349e-05, "loss": 0.0109, "step": 175210 }, { "epoch": 42.09, "learning_rate": 6.538938690491264e-05, "loss": 0.012, "step": 175220 }, { "epoch": 42.09, "learning_rate": 6.538597154968476e-05, "loss": 0.0114, "step": 175230 }, { "epoch": 42.09, "learning_rate": 6.538255611515747e-05, "loss": 0.0116, "step": 175240 }, { "epoch": 42.09, "learning_rate": 6.537914060134834e-05, "loss": 0.0134, "step": 175250 }, { "epoch": 42.09, "learning_rate": 6.5375725008275e-05, "loss": 0.0105, "step": 175260 }, { "epoch": 42.1, "learning_rate": 6.537230933595505e-05, "loss": 0.0156, "step": 175270 }, { "epoch": 42.1, "learning_rate": 6.536889358440608e-05, "loss": 0.0142, "step": 175280 }, { "epoch": 42.1, "learning_rate": 6.53654777536457e-05, "loss": 0.0167, "step": 175290 }, { "epoch": 42.1, "learning_rate": 6.536206184369152e-05, "loss": 0.0093, "step": 175300 }, { "epoch": 42.11, "learning_rate": 6.535864585456115e-05, "loss": 0.0111, "step": 175310 }, { "epoch": 42.11, "learning_rate": 6.53552297862722e-05, "loss": 0.0071, "step": 175320 }, { "epoch": 42.11, "learning_rate": 6.535181363884225e-05, "loss": 0.0119, "step": 175330 }, { "epoch": 42.11, "learning_rate": 6.534839741228895e-05, "loss": 0.0092, "step": 175340 }, { "epoch": 42.12, "learning_rate": 6.534498110662985e-05, "loss": 0.0113, "step": 175350 }, { "epoch": 42.12, "learning_rate": 6.53415647218826e-05, "loss": 0.0063, "step": 175360 }, { "epoch": 42.12, "learning_rate": 6.533814825806479e-05, "loss": 0.0124, "step": 175370 }, { "epoch": 42.12, "learning_rate": 6.533473171519406e-05, "loss": 0.0068, "step": 175380 }, { "epoch": 42.12, "learning_rate": 6.533131509328797e-05, "loss": 0.0075, "step": 175390 }, { "epoch": 42.13, "learning_rate": 6.532789839236416e-05, "loss": 0.0159, "step": 175400 }, { "epoch": 42.13, "learning_rate": 6.532448161244025e-05, "loss": 0.0101, "step": 175410 }, { "epoch": 42.13, "learning_rate": 6.532106475353381e-05, "loss": 0.0076, "step": 175420 }, { "epoch": 42.13, "learning_rate": 6.53176478156625e-05, "loss": 0.0094, "step": 175430 }, { "epoch": 42.14, "learning_rate": 6.531423079884388e-05, "loss": 0.0093, "step": 175440 }, { "epoch": 42.14, "learning_rate": 6.53108137030956e-05, "loss": 0.0189, "step": 175450 }, { "epoch": 42.14, "learning_rate": 6.530739652843525e-05, "loss": 0.0135, "step": 175460 }, { "epoch": 42.14, "learning_rate": 6.530397927488046e-05, "loss": 0.019, "step": 175470 }, { "epoch": 42.14, "learning_rate": 6.530056194244883e-05, "loss": 0.0195, "step": 175480 }, { "epoch": 42.15, "learning_rate": 6.529714453115798e-05, "loss": 0.0092, "step": 175490 }, { "epoch": 42.15, "learning_rate": 6.529372704102551e-05, "loss": 0.0084, "step": 175500 }, { "epoch": 42.15, "learning_rate": 6.529030947206903e-05, "loss": 0.0099, "step": 175510 }, { "epoch": 42.15, "learning_rate": 6.528689182430619e-05, "loss": 0.0096, "step": 175520 }, { "epoch": 42.16, "learning_rate": 6.528347409775458e-05, "loss": 0.0094, "step": 175530 }, { "epoch": 42.16, "learning_rate": 6.52800562924318e-05, "loss": 0.0149, "step": 175540 }, { "epoch": 42.16, "learning_rate": 6.527663840835551e-05, "loss": 0.0151, "step": 175550 }, { "epoch": 42.16, "learning_rate": 6.527322044554327e-05, "loss": 0.0078, "step": 175560 }, { "epoch": 42.17, "learning_rate": 6.526980240401274e-05, "loss": 0.0093, "step": 175570 }, { "epoch": 42.17, "learning_rate": 6.526638428378151e-05, "loss": 0.0078, "step": 175580 }, { "epoch": 42.17, "learning_rate": 6.526296608486721e-05, "loss": 0.0122, "step": 175590 }, { "epoch": 42.17, "learning_rate": 6.525954780728747e-05, "loss": 0.0154, "step": 175600 }, { "epoch": 42.17, "learning_rate": 6.525612945105988e-05, "loss": 0.0079, "step": 175610 }, { "epoch": 42.18, "learning_rate": 6.525271101620207e-05, "loss": 0.008, "step": 175620 }, { "epoch": 42.18, "learning_rate": 6.524929250273167e-05, "loss": 0.0058, "step": 175630 }, { "epoch": 42.18, "learning_rate": 6.524587391066629e-05, "loss": 0.0069, "step": 175640 }, { "epoch": 42.18, "learning_rate": 6.524245524002353e-05, "loss": 0.0059, "step": 175650 }, { "epoch": 42.19, "learning_rate": 6.523903649082104e-05, "loss": 0.013, "step": 175660 }, { "epoch": 42.19, "learning_rate": 6.523561766307641e-05, "loss": 0.0191, "step": 175670 }, { "epoch": 42.19, "learning_rate": 6.52321987568073e-05, "loss": 0.0051, "step": 175680 }, { "epoch": 42.19, "learning_rate": 6.522877977203132e-05, "loss": 0.018, "step": 175690 }, { "epoch": 42.2, "learning_rate": 6.522536070876608e-05, "loss": 0.0152, "step": 175700 }, { "epoch": 42.2, "learning_rate": 6.522194156702918e-05, "loss": 0.0122, "step": 175710 }, { "epoch": 42.2, "learning_rate": 6.52185223468383e-05, "loss": 0.007, "step": 175720 }, { "epoch": 42.2, "learning_rate": 6.521510304821099e-05, "loss": 0.0138, "step": 175730 }, { "epoch": 42.2, "learning_rate": 6.521168367116494e-05, "loss": 0.0081, "step": 175740 }, { "epoch": 42.21, "learning_rate": 6.520826421571773e-05, "loss": 0.0254, "step": 175750 }, { "epoch": 42.21, "learning_rate": 6.5204844681887e-05, "loss": 0.0114, "step": 175760 }, { "epoch": 42.21, "learning_rate": 6.520142506969039e-05, "loss": 0.0111, "step": 175770 }, { "epoch": 42.21, "learning_rate": 6.519800537914549e-05, "loss": 0.0151, "step": 175780 }, { "epoch": 42.22, "learning_rate": 6.519458561026995e-05, "loss": 0.0092, "step": 175790 }, { "epoch": 42.22, "learning_rate": 6.519116576308138e-05, "loss": 0.0108, "step": 175800 }, { "epoch": 42.22, "learning_rate": 6.518774583759742e-05, "loss": 0.0122, "step": 175810 }, { "epoch": 42.22, "learning_rate": 6.518432583383569e-05, "loss": 0.0071, "step": 175820 }, { "epoch": 42.22, "learning_rate": 6.518090575181381e-05, "loss": 0.0091, "step": 175830 }, { "epoch": 42.23, "learning_rate": 6.517748559154945e-05, "loss": 0.0145, "step": 175840 }, { "epoch": 42.23, "learning_rate": 6.517406535306016e-05, "loss": 0.0085, "step": 175850 }, { "epoch": 42.23, "learning_rate": 6.517064503636364e-05, "loss": 0.0181, "step": 175860 }, { "epoch": 42.23, "learning_rate": 6.516722464147748e-05, "loss": 0.0099, "step": 175870 }, { "epoch": 42.24, "learning_rate": 6.51638041684193e-05, "loss": 0.0082, "step": 175880 }, { "epoch": 42.24, "learning_rate": 6.516038361720676e-05, "loss": 0.0141, "step": 175890 }, { "epoch": 42.24, "learning_rate": 6.515696298785749e-05, "loss": 0.0134, "step": 175900 }, { "epoch": 42.24, "learning_rate": 6.51535422803891e-05, "loss": 0.017, "step": 175910 }, { "epoch": 42.25, "learning_rate": 6.515012149481922e-05, "loss": 0.0081, "step": 175920 }, { "epoch": 42.25, "learning_rate": 6.514670063116549e-05, "loss": 0.0155, "step": 175930 }, { "epoch": 42.25, "learning_rate": 6.514327968944552e-05, "loss": 0.0078, "step": 175940 }, { "epoch": 42.25, "learning_rate": 6.513985866967698e-05, "loss": 0.0154, "step": 175950 }, { "epoch": 42.25, "learning_rate": 6.513643757187748e-05, "loss": 0.0161, "step": 175960 }, { "epoch": 42.26, "learning_rate": 6.513301639606466e-05, "loss": 0.0065, "step": 175970 }, { "epoch": 42.26, "learning_rate": 6.512959514225612e-05, "loss": 0.0107, "step": 175980 }, { "epoch": 42.26, "learning_rate": 6.512617381046954e-05, "loss": 0.01, "step": 175990 }, { "epoch": 42.26, "learning_rate": 6.512275240072253e-05, "loss": 0.0122, "step": 176000 }, { "epoch": 42.27, "learning_rate": 6.511933091303273e-05, "loss": 0.0087, "step": 176010 }, { "epoch": 42.27, "learning_rate": 6.511590934741778e-05, "loss": 0.0165, "step": 176020 }, { "epoch": 42.27, "learning_rate": 6.511248770389529e-05, "loss": 0.0131, "step": 176030 }, { "epoch": 42.27, "learning_rate": 6.510906598248292e-05, "loss": 0.0199, "step": 176040 }, { "epoch": 42.28, "learning_rate": 6.51056441831983e-05, "loss": 0.0122, "step": 176050 }, { "epoch": 42.28, "learning_rate": 6.510222230605907e-05, "loss": 0.019, "step": 176060 }, { "epoch": 42.28, "learning_rate": 6.509880035108285e-05, "loss": 0.0172, "step": 176070 }, { "epoch": 42.28, "learning_rate": 6.509537831828729e-05, "loss": 0.0069, "step": 176080 }, { "epoch": 42.28, "learning_rate": 6.509195620769002e-05, "loss": 0.0152, "step": 176090 }, { "epoch": 42.29, "learning_rate": 6.508853401930868e-05, "loss": 0.0155, "step": 176100 }, { "epoch": 42.29, "learning_rate": 6.508511175316092e-05, "loss": 0.0056, "step": 176110 }, { "epoch": 42.29, "learning_rate": 6.508168940926436e-05, "loss": 0.0109, "step": 176120 }, { "epoch": 42.29, "learning_rate": 6.507826698763665e-05, "loss": 0.0075, "step": 176130 }, { "epoch": 42.3, "learning_rate": 6.507484448829542e-05, "loss": 0.0086, "step": 176140 }, { "epoch": 42.3, "learning_rate": 6.507142191125832e-05, "loss": 0.0159, "step": 176150 }, { "epoch": 42.3, "learning_rate": 6.5067999256543e-05, "loss": 0.0131, "step": 176160 }, { "epoch": 42.3, "learning_rate": 6.506457652416706e-05, "loss": 0.0118, "step": 176170 }, { "epoch": 42.3, "learning_rate": 6.506115371414817e-05, "loss": 0.0153, "step": 176180 }, { "epoch": 42.31, "learning_rate": 6.505773082650397e-05, "loss": 0.0124, "step": 176190 }, { "epoch": 42.31, "learning_rate": 6.505430786125212e-05, "loss": 0.0256, "step": 176200 }, { "epoch": 42.31, "learning_rate": 6.505088481841023e-05, "loss": 0.0094, "step": 176210 }, { "epoch": 42.31, "learning_rate": 6.504746169799595e-05, "loss": 0.009, "step": 176220 }, { "epoch": 42.32, "learning_rate": 6.504403850002693e-05, "loss": 0.0095, "step": 176230 }, { "epoch": 42.32, "learning_rate": 6.50406152245208e-05, "loss": 0.011, "step": 176240 }, { "epoch": 42.32, "learning_rate": 6.503719187149522e-05, "loss": 0.0132, "step": 176250 }, { "epoch": 42.32, "learning_rate": 6.503376844096783e-05, "loss": 0.0104, "step": 176260 }, { "epoch": 42.33, "learning_rate": 6.503034493295627e-05, "loss": 0.0137, "step": 176270 }, { "epoch": 42.33, "learning_rate": 6.502692134747818e-05, "loss": 0.0102, "step": 176280 }, { "epoch": 42.33, "learning_rate": 6.502349768455122e-05, "loss": 0.0102, "step": 176290 }, { "epoch": 42.33, "learning_rate": 6.502007394419302e-05, "loss": 0.0122, "step": 176300 }, { "epoch": 42.33, "learning_rate": 6.501665012642125e-05, "loss": 0.0175, "step": 176310 }, { "epoch": 42.34, "learning_rate": 6.501322623125352e-05, "loss": 0.0149, "step": 176320 }, { "epoch": 42.34, "learning_rate": 6.500980225870749e-05, "loss": 0.0118, "step": 176330 }, { "epoch": 42.34, "learning_rate": 6.500637820880085e-05, "loss": 0.0137, "step": 176340 }, { "epoch": 42.34, "learning_rate": 6.500295408155119e-05, "loss": 0.0138, "step": 176350 }, { "epoch": 42.35, "learning_rate": 6.499952987697618e-05, "loss": 0.0114, "step": 176360 }, { "epoch": 42.35, "learning_rate": 6.499610559509346e-05, "loss": 0.01, "step": 176370 }, { "epoch": 42.35, "learning_rate": 6.499268123592069e-05, "loss": 0.0159, "step": 176380 }, { "epoch": 42.35, "learning_rate": 6.498925679947552e-05, "loss": 0.0077, "step": 176390 }, { "epoch": 42.36, "learning_rate": 6.498583228577559e-05, "loss": 0.0077, "step": 176400 }, { "epoch": 42.36, "learning_rate": 6.498240769483856e-05, "loss": 0.0104, "step": 176410 }, { "epoch": 42.36, "learning_rate": 6.497898302668208e-05, "loss": 0.0077, "step": 176420 }, { "epoch": 42.36, "learning_rate": 6.497555828132379e-05, "loss": 0.0085, "step": 176430 }, { "epoch": 42.36, "learning_rate": 6.497213345878135e-05, "loss": 0.0098, "step": 176440 }, { "epoch": 42.37, "learning_rate": 6.49687085590724e-05, "loss": 0.0194, "step": 176450 }, { "epoch": 42.37, "learning_rate": 6.496528358221461e-05, "loss": 0.0123, "step": 176460 }, { "epoch": 42.37, "learning_rate": 6.496185852822562e-05, "loss": 0.0075, "step": 176470 }, { "epoch": 42.37, "learning_rate": 6.495843339712309e-05, "loss": 0.0144, "step": 176480 }, { "epoch": 42.38, "learning_rate": 6.495500818892467e-05, "loss": 0.0121, "step": 176490 }, { "epoch": 42.38, "learning_rate": 6.495158290364801e-05, "loss": 0.0084, "step": 176500 }, { "epoch": 42.38, "learning_rate": 6.494815754131077e-05, "loss": 0.0092, "step": 176510 }, { "epoch": 42.38, "learning_rate": 6.49447321019306e-05, "loss": 0.0087, "step": 176520 }, { "epoch": 42.38, "learning_rate": 6.494130658552516e-05, "loss": 0.0134, "step": 176530 }, { "epoch": 42.39, "learning_rate": 6.493788099211209e-05, "loss": 0.0141, "step": 176540 }, { "epoch": 42.39, "learning_rate": 6.493445532170906e-05, "loss": 0.0138, "step": 176550 }, { "epoch": 42.39, "learning_rate": 6.493102957433371e-05, "loss": 0.008, "step": 176560 }, { "epoch": 42.39, "learning_rate": 6.492760375000372e-05, "loss": 0.0097, "step": 176570 }, { "epoch": 42.4, "learning_rate": 6.492417784873675e-05, "loss": 0.0135, "step": 176580 }, { "epoch": 42.4, "learning_rate": 6.492075187055042e-05, "loss": 0.0093, "step": 176590 }, { "epoch": 42.4, "learning_rate": 6.491732581546242e-05, "loss": 0.0064, "step": 176600 }, { "epoch": 42.4, "learning_rate": 6.49138996834904e-05, "loss": 0.019, "step": 176610 }, { "epoch": 42.41, "learning_rate": 6.491047347465201e-05, "loss": 0.0154, "step": 176620 }, { "epoch": 42.41, "learning_rate": 6.490704718896493e-05, "loss": 0.0112, "step": 176630 }, { "epoch": 42.41, "learning_rate": 6.49036208264468e-05, "loss": 0.009, "step": 176640 }, { "epoch": 42.41, "learning_rate": 6.490019438711528e-05, "loss": 0.009, "step": 176650 }, { "epoch": 42.41, "learning_rate": 6.489676787098802e-05, "loss": 0.0148, "step": 176660 }, { "epoch": 42.42, "learning_rate": 6.489334127808272e-05, "loss": 0.0177, "step": 176670 }, { "epoch": 42.42, "learning_rate": 6.488991460841698e-05, "loss": 0.025, "step": 176680 }, { "epoch": 42.42, "learning_rate": 6.488648786200851e-05, "loss": 0.0091, "step": 176690 }, { "epoch": 42.42, "learning_rate": 6.488306103887499e-05, "loss": 0.0099, "step": 176700 }, { "epoch": 42.43, "learning_rate": 6.4879634139034e-05, "loss": 0.0136, "step": 176710 }, { "epoch": 42.43, "learning_rate": 6.487620716250328e-05, "loss": 0.0037, "step": 176720 }, { "epoch": 42.43, "learning_rate": 6.487278010930045e-05, "loss": 0.0198, "step": 176730 }, { "epoch": 42.43, "learning_rate": 6.486935297944319e-05, "loss": 0.0087, "step": 176740 }, { "epoch": 42.44, "learning_rate": 6.486592577294917e-05, "loss": 0.0214, "step": 176750 }, { "epoch": 42.44, "learning_rate": 6.486249848983603e-05, "loss": 0.0126, "step": 176760 }, { "epoch": 42.44, "learning_rate": 6.485907113012146e-05, "loss": 0.0034, "step": 176770 }, { "epoch": 42.44, "learning_rate": 6.485564369382313e-05, "loss": 0.0114, "step": 176780 }, { "epoch": 42.44, "learning_rate": 6.485221618095865e-05, "loss": 0.0096, "step": 176790 }, { "epoch": 42.45, "learning_rate": 6.484878859154576e-05, "loss": 0.0118, "step": 176800 }, { "epoch": 42.45, "learning_rate": 6.484536092560206e-05, "loss": 0.0098, "step": 176810 }, { "epoch": 42.45, "learning_rate": 6.484193318314526e-05, "loss": 0.0103, "step": 176820 }, { "epoch": 42.45, "learning_rate": 6.4838505364193e-05, "loss": 0.0141, "step": 176830 }, { "epoch": 42.46, "learning_rate": 6.483507746876297e-05, "loss": 0.0256, "step": 176840 }, { "epoch": 42.46, "learning_rate": 6.483164949687283e-05, "loss": 0.0151, "step": 176850 }, { "epoch": 42.46, "learning_rate": 6.482822144854025e-05, "loss": 0.0171, "step": 176860 }, { "epoch": 42.46, "learning_rate": 6.482479332378286e-05, "loss": 0.0163, "step": 176870 }, { "epoch": 42.46, "learning_rate": 6.48213651226184e-05, "loss": 0.0104, "step": 176880 }, { "epoch": 42.47, "learning_rate": 6.481793684506447e-05, "loss": 0.0099, "step": 176890 }, { "epoch": 42.47, "learning_rate": 6.48145084911388e-05, "loss": 0.0074, "step": 176900 }, { "epoch": 42.47, "learning_rate": 6.4811080060859e-05, "loss": 0.0065, "step": 176910 }, { "epoch": 42.47, "learning_rate": 6.48076515542428e-05, "loss": 0.0064, "step": 176920 }, { "epoch": 42.48, "learning_rate": 6.480422297130781e-05, "loss": 0.0106, "step": 176930 }, { "epoch": 42.48, "learning_rate": 6.480079431207175e-05, "loss": 0.0155, "step": 176940 }, { "epoch": 42.48, "learning_rate": 6.479736557655228e-05, "loss": 0.0129, "step": 176950 }, { "epoch": 42.48, "learning_rate": 6.479393676476704e-05, "loss": 0.0085, "step": 176960 }, { "epoch": 42.49, "learning_rate": 6.479050787673373e-05, "loss": 0.0176, "step": 176970 }, { "epoch": 42.49, "learning_rate": 6.478707891247003e-05, "loss": 0.0198, "step": 176980 }, { "epoch": 42.49, "learning_rate": 6.47836498719936e-05, "loss": 0.0079, "step": 176990 }, { "epoch": 42.49, "learning_rate": 6.478022075532212e-05, "loss": 0.0068, "step": 177000 }, { "epoch": 42.49, "learning_rate": 6.477679156247325e-05, "loss": 0.0103, "step": 177010 }, { "epoch": 42.5, "learning_rate": 6.477336229346466e-05, "loss": 0.0091, "step": 177020 }, { "epoch": 42.5, "learning_rate": 6.476993294831405e-05, "loss": 0.0106, "step": 177030 }, { "epoch": 42.5, "learning_rate": 6.476650352703908e-05, "loss": 0.0209, "step": 177040 }, { "epoch": 42.5, "learning_rate": 6.476307402965743e-05, "loss": 0.0094, "step": 177050 }, { "epoch": 42.51, "learning_rate": 6.475964445618679e-05, "loss": 0.0139, "step": 177060 }, { "epoch": 42.51, "learning_rate": 6.47562148066448e-05, "loss": 0.0047, "step": 177070 }, { "epoch": 42.51, "learning_rate": 6.475278508104915e-05, "loss": 0.0176, "step": 177080 }, { "epoch": 42.51, "learning_rate": 6.474935527941754e-05, "loss": 0.0137, "step": 177090 }, { "epoch": 42.52, "learning_rate": 6.474592540176762e-05, "loss": 0.013, "step": 177100 }, { "epoch": 42.52, "learning_rate": 6.474249544811707e-05, "loss": 0.0174, "step": 177110 }, { "epoch": 42.52, "learning_rate": 6.473906541848358e-05, "loss": 0.0105, "step": 177120 }, { "epoch": 42.52, "learning_rate": 6.473563531288483e-05, "loss": 0.0132, "step": 177130 }, { "epoch": 42.52, "learning_rate": 6.47322051313385e-05, "loss": 0.0112, "step": 177140 }, { "epoch": 42.53, "learning_rate": 6.472877487386224e-05, "loss": 0.0223, "step": 177150 }, { "epoch": 42.53, "learning_rate": 6.472534454047376e-05, "loss": 0.0161, "step": 177160 }, { "epoch": 42.53, "learning_rate": 6.472191413119074e-05, "loss": 0.0165, "step": 177170 }, { "epoch": 42.53, "learning_rate": 6.471848364603083e-05, "loss": 0.0106, "step": 177180 }, { "epoch": 42.54, "learning_rate": 6.471505308501175e-05, "loss": 0.022, "step": 177190 }, { "epoch": 42.54, "learning_rate": 6.471162244815115e-05, "loss": 0.0166, "step": 177200 }, { "epoch": 42.54, "learning_rate": 6.470819173546676e-05, "loss": 0.0216, "step": 177210 }, { "epoch": 42.54, "learning_rate": 6.470476094697619e-05, "loss": 0.0125, "step": 177220 }, { "epoch": 42.54, "learning_rate": 6.470133008269717e-05, "loss": 0.0131, "step": 177230 }, { "epoch": 42.55, "learning_rate": 6.469789914264736e-05, "loss": 0.0114, "step": 177240 }, { "epoch": 42.55, "learning_rate": 6.469446812684447e-05, "loss": 0.0121, "step": 177250 }, { "epoch": 42.55, "learning_rate": 6.469103703530619e-05, "loss": 0.0228, "step": 177260 }, { "epoch": 42.55, "learning_rate": 6.468760586805013e-05, "loss": 0.014, "step": 177270 }, { "epoch": 42.56, "learning_rate": 6.468417462509408e-05, "loss": 0.0127, "step": 177280 }, { "epoch": 42.56, "learning_rate": 6.468074330645564e-05, "loss": 0.0066, "step": 177290 }, { "epoch": 42.56, "learning_rate": 6.467731191215254e-05, "loss": 0.0443, "step": 177300 }, { "epoch": 42.56, "learning_rate": 6.467388044220244e-05, "loss": 0.0209, "step": 177310 }, { "epoch": 42.57, "learning_rate": 6.467044889662304e-05, "loss": 0.0157, "step": 177320 }, { "epoch": 42.57, "learning_rate": 6.466701727543203e-05, "loss": 0.0217, "step": 177330 }, { "epoch": 42.57, "learning_rate": 6.466358557864707e-05, "loss": 0.0137, "step": 177340 }, { "epoch": 42.57, "learning_rate": 6.46601538062859e-05, "loss": 0.0112, "step": 177350 }, { "epoch": 42.57, "learning_rate": 6.465672195836615e-05, "loss": 0.0217, "step": 177360 }, { "epoch": 42.58, "learning_rate": 6.465329003490555e-05, "loss": 0.0211, "step": 177370 }, { "epoch": 42.58, "learning_rate": 6.464985803592176e-05, "loss": 0.0126, "step": 177380 }, { "epoch": 42.58, "learning_rate": 6.464642596143247e-05, "loss": 0.0178, "step": 177390 }, { "epoch": 42.58, "learning_rate": 6.46429938114554e-05, "loss": 0.0164, "step": 177400 }, { "epoch": 42.59, "learning_rate": 6.46395615860082e-05, "loss": 0.012, "step": 177410 }, { "epoch": 42.59, "learning_rate": 6.463612928510859e-05, "loss": 0.0382, "step": 177420 }, { "epoch": 42.59, "learning_rate": 6.463269690877423e-05, "loss": 0.0159, "step": 177430 }, { "epoch": 42.59, "learning_rate": 6.462926445702284e-05, "loss": 0.018, "step": 177440 }, { "epoch": 42.6, "learning_rate": 6.46258319298721e-05, "loss": 0.0192, "step": 177450 }, { "epoch": 42.6, "learning_rate": 6.46223993273397e-05, "loss": 0.0132, "step": 177460 }, { "epoch": 42.6, "learning_rate": 6.461896664944332e-05, "loss": 0.0383, "step": 177470 }, { "epoch": 42.6, "learning_rate": 6.461553389620068e-05, "loss": 0.0142, "step": 177480 }, { "epoch": 42.6, "learning_rate": 6.461210106762946e-05, "loss": 0.0176, "step": 177490 }, { "epoch": 42.61, "learning_rate": 6.460866816374733e-05, "loss": 0.0133, "step": 177500 }, { "epoch": 42.61, "learning_rate": 6.4605235184572e-05, "loss": 0.0179, "step": 177510 }, { "epoch": 42.61, "learning_rate": 6.460180213012117e-05, "loss": 0.0134, "step": 177520 }, { "epoch": 42.61, "learning_rate": 6.459836900041254e-05, "loss": 0.0165, "step": 177530 }, { "epoch": 42.62, "learning_rate": 6.459493579546378e-05, "loss": 0.0158, "step": 177540 }, { "epoch": 42.62, "learning_rate": 6.459150251529261e-05, "loss": 0.0144, "step": 177550 }, { "epoch": 42.62, "learning_rate": 6.458806915991672e-05, "loss": 0.0169, "step": 177560 }, { "epoch": 42.62, "learning_rate": 6.458463572935381e-05, "loss": 0.023, "step": 177570 }, { "epoch": 42.62, "learning_rate": 6.458120222362154e-05, "loss": 0.011, "step": 177580 }, { "epoch": 42.63, "learning_rate": 6.457776864273764e-05, "loss": 0.0141, "step": 177590 }, { "epoch": 42.63, "learning_rate": 6.457433498671978e-05, "loss": 0.0131, "step": 177600 }, { "epoch": 42.63, "learning_rate": 6.45709012555857e-05, "loss": 0.0197, "step": 177610 }, { "epoch": 42.63, "learning_rate": 6.456746744935306e-05, "loss": 0.0165, "step": 177620 }, { "epoch": 42.64, "learning_rate": 6.45640335680396e-05, "loss": 0.0091, "step": 177630 }, { "epoch": 42.64, "learning_rate": 6.456059961166295e-05, "loss": 0.0096, "step": 177640 }, { "epoch": 42.64, "learning_rate": 6.455716558024087e-05, "loss": 0.0059, "step": 177650 }, { "epoch": 42.64, "learning_rate": 6.455373147379102e-05, "loss": 0.0118, "step": 177660 }, { "epoch": 42.65, "learning_rate": 6.455029729233114e-05, "loss": 0.0095, "step": 177670 }, { "epoch": 42.65, "learning_rate": 6.454686303587889e-05, "loss": 0.0109, "step": 177680 }, { "epoch": 42.65, "learning_rate": 6.454342870445199e-05, "loss": 0.0121, "step": 177690 }, { "epoch": 42.65, "learning_rate": 6.453999429806814e-05, "loss": 0.0113, "step": 177700 }, { "epoch": 42.65, "learning_rate": 6.453655981674505e-05, "loss": 0.0137, "step": 177710 }, { "epoch": 42.66, "learning_rate": 6.453312526050039e-05, "loss": 0.0196, "step": 177720 }, { "epoch": 42.66, "learning_rate": 6.452969062935188e-05, "loss": 0.0207, "step": 177730 }, { "epoch": 42.66, "learning_rate": 6.452625592331722e-05, "loss": 0.0087, "step": 177740 }, { "epoch": 42.66, "learning_rate": 6.452282114241413e-05, "loss": 0.0108, "step": 177750 }, { "epoch": 42.67, "learning_rate": 6.45193862866603e-05, "loss": 0.0145, "step": 177760 }, { "epoch": 42.67, "learning_rate": 6.451595135607343e-05, "loss": 0.0368, "step": 177770 }, { "epoch": 42.67, "learning_rate": 6.451251635067121e-05, "loss": 0.0102, "step": 177780 }, { "epoch": 42.67, "learning_rate": 6.450908127047137e-05, "loss": 0.0149, "step": 177790 }, { "epoch": 42.68, "learning_rate": 6.45056461154916e-05, "loss": 0.0158, "step": 177800 }, { "epoch": 42.68, "learning_rate": 6.450221088574962e-05, "loss": 0.022, "step": 177810 }, { "epoch": 42.68, "learning_rate": 6.44987755812631e-05, "loss": 0.0163, "step": 177820 }, { "epoch": 42.68, "learning_rate": 6.44953402020498e-05, "loss": 0.0165, "step": 177830 }, { "epoch": 42.68, "learning_rate": 6.449190474812736e-05, "loss": 0.0114, "step": 177840 }, { "epoch": 42.69, "learning_rate": 6.448846921951355e-05, "loss": 0.019, "step": 177850 }, { "epoch": 42.69, "learning_rate": 6.448503361622606e-05, "loss": 0.0192, "step": 177860 }, { "epoch": 42.69, "learning_rate": 6.448159793828255e-05, "loss": 0.0197, "step": 177870 }, { "epoch": 42.69, "learning_rate": 6.447816218570078e-05, "loss": 0.012, "step": 177880 }, { "epoch": 42.7, "learning_rate": 6.447472635849845e-05, "loss": 0.0141, "step": 177890 }, { "epoch": 42.7, "learning_rate": 6.447129045669324e-05, "loss": 0.0097, "step": 177900 }, { "epoch": 42.7, "learning_rate": 6.44678544803029e-05, "loss": 0.0087, "step": 177910 }, { "epoch": 42.7, "learning_rate": 6.44644184293451e-05, "loss": 0.011, "step": 177920 }, { "epoch": 42.7, "learning_rate": 6.446098230383757e-05, "loss": 0.0099, "step": 177930 }, { "epoch": 42.71, "learning_rate": 6.445754610379802e-05, "loss": 0.0099, "step": 177940 }, { "epoch": 42.71, "learning_rate": 6.445410982924415e-05, "loss": 0.0088, "step": 177950 }, { "epoch": 42.71, "learning_rate": 6.445067348019367e-05, "loss": 0.0077, "step": 177960 }, { "epoch": 42.71, "learning_rate": 6.444723705666431e-05, "loss": 0.008, "step": 177970 }, { "epoch": 42.72, "learning_rate": 6.444380055867377e-05, "loss": 0.0116, "step": 177980 }, { "epoch": 42.72, "learning_rate": 6.444036398623976e-05, "loss": 0.0118, "step": 177990 }, { "epoch": 42.72, "learning_rate": 6.443692733938e-05, "loss": 0.0067, "step": 178000 }, { "epoch": 42.72, "learning_rate": 6.443349061811219e-05, "loss": 0.0072, "step": 178010 }, { "epoch": 42.73, "learning_rate": 6.443005382245405e-05, "loss": 0.0098, "step": 178020 }, { "epoch": 42.73, "learning_rate": 6.44266169524233e-05, "loss": 0.0063, "step": 178030 }, { "epoch": 42.73, "learning_rate": 6.442318000803763e-05, "loss": 0.0147, "step": 178040 }, { "epoch": 42.73, "learning_rate": 6.441974298931477e-05, "loss": 0.0111, "step": 178050 }, { "epoch": 42.73, "learning_rate": 6.441630589627244e-05, "loss": 0.0193, "step": 178060 }, { "epoch": 42.74, "learning_rate": 6.441286872892836e-05, "loss": 0.0142, "step": 178070 }, { "epoch": 42.74, "learning_rate": 6.440943148730021e-05, "loss": 0.0083, "step": 178080 }, { "epoch": 42.74, "learning_rate": 6.440599417140574e-05, "loss": 0.011, "step": 178090 }, { "epoch": 42.74, "learning_rate": 6.440255678126265e-05, "loss": 0.0214, "step": 178100 }, { "epoch": 42.75, "learning_rate": 6.439911931688868e-05, "loss": 0.0188, "step": 178110 }, { "epoch": 42.75, "learning_rate": 6.439568177830152e-05, "loss": 0.007, "step": 178120 }, { "epoch": 42.75, "learning_rate": 6.439224416551889e-05, "loss": 0.0106, "step": 178130 }, { "epoch": 42.75, "learning_rate": 6.438880647855853e-05, "loss": 0.0061, "step": 178140 }, { "epoch": 42.76, "learning_rate": 6.438536871743812e-05, "loss": 0.0083, "step": 178150 }, { "epoch": 42.76, "learning_rate": 6.438193088217541e-05, "loss": 0.0096, "step": 178160 }, { "epoch": 42.76, "learning_rate": 6.43784929727881e-05, "loss": 0.008, "step": 178170 }, { "epoch": 42.76, "learning_rate": 6.437505498929393e-05, "loss": 0.005, "step": 178180 }, { "epoch": 42.76, "learning_rate": 6.43716169317106e-05, "loss": 0.0084, "step": 178190 }, { "epoch": 42.77, "learning_rate": 6.436817880005583e-05, "loss": 0.0054, "step": 178200 }, { "epoch": 42.77, "learning_rate": 6.436474059434736e-05, "loss": 0.0168, "step": 178210 }, { "epoch": 42.77, "learning_rate": 6.436130231460289e-05, "loss": 0.009, "step": 178220 }, { "epoch": 42.77, "learning_rate": 6.435786396084013e-05, "loss": 0.0112, "step": 178230 }, { "epoch": 42.78, "learning_rate": 6.435442553307685e-05, "loss": 0.0069, "step": 178240 }, { "epoch": 42.78, "learning_rate": 6.435098703133072e-05, "loss": 0.0124, "step": 178250 }, { "epoch": 42.78, "learning_rate": 6.434754845561949e-05, "loss": 0.0116, "step": 178260 }, { "epoch": 42.78, "learning_rate": 6.434410980596088e-05, "loss": 0.0177, "step": 178270 }, { "epoch": 42.78, "learning_rate": 6.434067108237261e-05, "loss": 0.0108, "step": 178280 }, { "epoch": 42.79, "learning_rate": 6.43372322848724e-05, "loss": 0.0118, "step": 178290 }, { "epoch": 42.79, "learning_rate": 6.433379341347797e-05, "loss": 0.0101, "step": 178300 }, { "epoch": 42.79, "learning_rate": 6.433035446820704e-05, "loss": 0.007, "step": 178310 }, { "epoch": 42.79, "learning_rate": 6.432691544907735e-05, "loss": 0.0132, "step": 178320 }, { "epoch": 42.8, "learning_rate": 6.432347635610663e-05, "loss": 0.0158, "step": 178330 }, { "epoch": 42.8, "learning_rate": 6.432003718931256e-05, "loss": 0.0153, "step": 178340 }, { "epoch": 42.8, "learning_rate": 6.431659794871294e-05, "loss": 0.0111, "step": 178350 }, { "epoch": 42.8, "learning_rate": 6.431315863432544e-05, "loss": 0.0114, "step": 178360 }, { "epoch": 42.81, "learning_rate": 6.43097192461678e-05, "loss": 0.0116, "step": 178370 }, { "epoch": 42.81, "learning_rate": 6.430627978425772e-05, "loss": 0.0117, "step": 178380 }, { "epoch": 42.81, "learning_rate": 6.430284024861298e-05, "loss": 0.0073, "step": 178390 }, { "epoch": 42.81, "learning_rate": 6.429940063925128e-05, "loss": 0.0118, "step": 178400 }, { "epoch": 42.81, "learning_rate": 6.429596095619035e-05, "loss": 0.0208, "step": 178410 }, { "epoch": 42.82, "learning_rate": 6.429252119944791e-05, "loss": 0.0067, "step": 178420 }, { "epoch": 42.82, "learning_rate": 6.428908136904172e-05, "loss": 0.0109, "step": 178430 }, { "epoch": 42.82, "learning_rate": 6.428564146498948e-05, "loss": 0.0092, "step": 178440 }, { "epoch": 42.82, "learning_rate": 6.42822014873089e-05, "loss": 0.0118, "step": 178450 }, { "epoch": 42.83, "learning_rate": 6.427876143601775e-05, "loss": 0.0106, "step": 178460 }, { "epoch": 42.83, "learning_rate": 6.427532131113374e-05, "loss": 0.0159, "step": 178470 }, { "epoch": 42.83, "learning_rate": 6.427188111267461e-05, "loss": 0.0279, "step": 178480 }, { "epoch": 42.83, "learning_rate": 6.426844084065809e-05, "loss": 0.0063, "step": 178490 }, { "epoch": 42.84, "learning_rate": 6.426500049510191e-05, "loss": 0.0064, "step": 178500 }, { "epoch": 42.84, "learning_rate": 6.426156007602378e-05, "loss": 0.0173, "step": 178510 }, { "epoch": 42.84, "learning_rate": 6.425811958344145e-05, "loss": 0.0078, "step": 178520 }, { "epoch": 42.84, "learning_rate": 6.425467901737267e-05, "loss": 0.0096, "step": 178530 }, { "epoch": 42.84, "learning_rate": 6.425123837783514e-05, "loss": 0.0161, "step": 178540 }, { "epoch": 42.85, "learning_rate": 6.424779766484659e-05, "loss": 0.0112, "step": 178550 }, { "epoch": 42.85, "learning_rate": 6.42443568784248e-05, "loss": 0.0122, "step": 178560 }, { "epoch": 42.85, "learning_rate": 6.424091601858749e-05, "loss": 0.0127, "step": 178570 }, { "epoch": 42.85, "learning_rate": 6.423747508535235e-05, "loss": 0.0126, "step": 178580 }, { "epoch": 42.86, "learning_rate": 6.423403407873716e-05, "loss": 0.0075, "step": 178590 }, { "epoch": 42.86, "learning_rate": 6.423059299875963e-05, "loss": 0.0124, "step": 178600 }, { "epoch": 42.86, "learning_rate": 6.42271518454375e-05, "loss": 0.0047, "step": 178610 }, { "epoch": 42.86, "learning_rate": 6.422371061878853e-05, "loss": 0.0068, "step": 178620 }, { "epoch": 42.86, "learning_rate": 6.422026931883041e-05, "loss": 0.0142, "step": 178630 }, { "epoch": 42.87, "learning_rate": 6.421682794558093e-05, "loss": 0.0134, "step": 178640 }, { "epoch": 42.87, "learning_rate": 6.421338649905779e-05, "loss": 0.0065, "step": 178650 }, { "epoch": 42.87, "learning_rate": 6.420994497927874e-05, "loss": 0.01, "step": 178660 }, { "epoch": 42.87, "learning_rate": 6.420650338626151e-05, "loss": 0.0143, "step": 178670 }, { "epoch": 42.88, "learning_rate": 6.420306172002385e-05, "loss": 0.0072, "step": 178680 }, { "epoch": 42.88, "learning_rate": 6.419961998058347e-05, "loss": 0.0099, "step": 178690 }, { "epoch": 42.88, "learning_rate": 6.419617816795815e-05, "loss": 0.0107, "step": 178700 }, { "epoch": 42.88, "learning_rate": 6.41927362821656e-05, "loss": 0.0124, "step": 178710 }, { "epoch": 42.89, "learning_rate": 6.418929432322358e-05, "loss": 0.0068, "step": 178720 }, { "epoch": 42.89, "learning_rate": 6.41858522911498e-05, "loss": 0.0066, "step": 178730 }, { "epoch": 42.89, "learning_rate": 6.418241018596204e-05, "loss": 0.0146, "step": 178740 }, { "epoch": 42.89, "learning_rate": 6.417896800767801e-05, "loss": 0.0087, "step": 178750 }, { "epoch": 42.89, "learning_rate": 6.417552575631545e-05, "loss": 0.0121, "step": 178760 }, { "epoch": 42.9, "learning_rate": 6.417208343189213e-05, "loss": 0.0119, "step": 178770 }, { "epoch": 42.9, "learning_rate": 6.416864103442576e-05, "loss": 0.0081, "step": 178780 }, { "epoch": 42.9, "learning_rate": 6.41651985639341e-05, "loss": 0.0048, "step": 178790 }, { "epoch": 42.9, "learning_rate": 6.416175602043489e-05, "loss": 0.007, "step": 178800 }, { "epoch": 42.91, "learning_rate": 6.415831340394587e-05, "loss": 0.0065, "step": 178810 }, { "epoch": 42.91, "learning_rate": 6.415487071448479e-05, "loss": 0.008, "step": 178820 }, { "epoch": 42.91, "learning_rate": 6.415142795206937e-05, "loss": 0.0136, "step": 178830 }, { "epoch": 42.91, "learning_rate": 6.414798511671739e-05, "loss": 0.0068, "step": 178840 }, { "epoch": 42.91, "learning_rate": 6.414454220844656e-05, "loss": 0.0101, "step": 178850 }, { "epoch": 42.92, "learning_rate": 6.414109922727465e-05, "loss": 0.0094, "step": 178860 }, { "epoch": 42.92, "learning_rate": 6.413765617321941e-05, "loss": 0.0084, "step": 178870 }, { "epoch": 42.92, "learning_rate": 6.413421304629856e-05, "loss": 0.0619, "step": 178880 }, { "epoch": 42.92, "learning_rate": 6.413076984652987e-05, "loss": 0.01, "step": 178890 }, { "epoch": 42.93, "learning_rate": 6.412732657393104e-05, "loss": 0.0112, "step": 178900 }, { "epoch": 42.93, "learning_rate": 6.412388322851987e-05, "loss": 0.0135, "step": 178910 }, { "epoch": 42.93, "learning_rate": 6.41204398103141e-05, "loss": 0.0086, "step": 178920 }, { "epoch": 42.93, "learning_rate": 6.411699631933146e-05, "loss": 0.0098, "step": 178930 }, { "epoch": 42.94, "learning_rate": 6.41135527555897e-05, "loss": 0.007, "step": 178940 }, { "epoch": 42.94, "learning_rate": 6.411010911910657e-05, "loss": 0.0081, "step": 178950 }, { "epoch": 42.94, "learning_rate": 6.410666540989983e-05, "loss": 0.0058, "step": 178960 }, { "epoch": 42.94, "learning_rate": 6.41032216279872e-05, "loss": 0.0103, "step": 178970 }, { "epoch": 42.94, "learning_rate": 6.409977777338645e-05, "loss": 0.0087, "step": 178980 }, { "epoch": 42.95, "learning_rate": 6.409633384611533e-05, "loss": 0.0151, "step": 178990 }, { "epoch": 42.95, "learning_rate": 6.40928898461916e-05, "loss": 0.0075, "step": 179000 }, { "epoch": 43.0, "learning_rate": 6.408944577363299e-05, "loss": 0.0106, "step": 179010 }, { "epoch": 43.0, "learning_rate": 6.408600162845725e-05, "loss": 0.0083, "step": 179020 }, { "epoch": 43.0, "learning_rate": 6.408255741068215e-05, "loss": 0.0132, "step": 179030 }, { "epoch": 43.01, "learning_rate": 6.407911312032542e-05, "loss": 0.0081, "step": 179040 }, { "epoch": 43.01, "learning_rate": 6.407566875740483e-05, "loss": 0.0229, "step": 179050 }, { "epoch": 43.01, "learning_rate": 6.407222432193813e-05, "loss": 0.0092, "step": 179060 }, { "epoch": 43.01, "learning_rate": 6.406877981394308e-05, "loss": 0.0067, "step": 179070 }, { "epoch": 43.02, "learning_rate": 6.406533523343741e-05, "loss": 0.0211, "step": 179080 }, { "epoch": 43.02, "learning_rate": 6.406189058043887e-05, "loss": 0.0089, "step": 179090 }, { "epoch": 43.02, "learning_rate": 6.405844585496524e-05, "loss": 0.0155, "step": 179100 }, { "epoch": 43.02, "learning_rate": 6.405500105703426e-05, "loss": 0.0108, "step": 179110 }, { "epoch": 43.03, "learning_rate": 6.40515561866637e-05, "loss": 0.0071, "step": 179120 }, { "epoch": 43.03, "learning_rate": 6.404811124387127e-05, "loss": 0.0094, "step": 179130 }, { "epoch": 43.03, "learning_rate": 6.404466622867479e-05, "loss": 0.0112, "step": 179140 }, { "epoch": 43.03, "learning_rate": 6.404122114109196e-05, "loss": 0.0168, "step": 179150 }, { "epoch": 43.03, "learning_rate": 6.403777598114057e-05, "loss": 0.006, "step": 179160 }, { "epoch": 43.04, "learning_rate": 6.403433074883838e-05, "loss": 0.0213, "step": 179170 }, { "epoch": 43.04, "learning_rate": 6.403088544420311e-05, "loss": 0.0089, "step": 179180 }, { "epoch": 43.04, "learning_rate": 6.402744006725254e-05, "loss": 0.008, "step": 179190 }, { "epoch": 43.04, "learning_rate": 6.402399461800443e-05, "loss": 0.0127, "step": 179200 }, { "epoch": 43.05, "learning_rate": 6.402054909647654e-05, "loss": 0.0078, "step": 179210 }, { "epoch": 43.05, "learning_rate": 6.401710350268664e-05, "loss": 0.0268, "step": 179220 }, { "epoch": 43.05, "learning_rate": 6.401365783665245e-05, "loss": 0.011, "step": 179230 }, { "epoch": 43.05, "learning_rate": 6.401021209839175e-05, "loss": 0.0151, "step": 179240 }, { "epoch": 43.06, "learning_rate": 6.40067662879223e-05, "loss": 0.0135, "step": 179250 }, { "epoch": 43.06, "learning_rate": 6.400332040526187e-05, "loss": 0.0106, "step": 179260 }, { "epoch": 43.06, "learning_rate": 6.39998744504282e-05, "loss": 0.0068, "step": 179270 }, { "epoch": 43.06, "learning_rate": 6.399642842343906e-05, "loss": 0.0096, "step": 179280 }, { "epoch": 43.06, "learning_rate": 6.399298232431222e-05, "loss": 0.0095, "step": 179290 }, { "epoch": 43.07, "learning_rate": 6.398953615306541e-05, "loss": 0.0082, "step": 179300 }, { "epoch": 43.07, "learning_rate": 6.398608990971642e-05, "loss": 0.0098, "step": 179310 }, { "epoch": 43.07, "learning_rate": 6.398264359428302e-05, "loss": 0.0067, "step": 179320 }, { "epoch": 43.07, "learning_rate": 6.397919720678296e-05, "loss": 0.0085, "step": 179330 }, { "epoch": 43.08, "learning_rate": 6.397575074723399e-05, "loss": 0.0063, "step": 179340 }, { "epoch": 43.08, "learning_rate": 6.397230421565388e-05, "loss": 0.0112, "step": 179350 }, { "epoch": 43.08, "learning_rate": 6.396885761206042e-05, "loss": 0.0058, "step": 179360 }, { "epoch": 43.08, "learning_rate": 6.396541093647132e-05, "loss": 0.0057, "step": 179370 }, { "epoch": 43.08, "learning_rate": 6.39619641889044e-05, "loss": 0.007, "step": 179380 }, { "epoch": 43.09, "learning_rate": 6.395851736937739e-05, "loss": 0.0179, "step": 179390 }, { "epoch": 43.09, "learning_rate": 6.395507047790806e-05, "loss": 0.0041, "step": 179400 }, { "epoch": 43.09, "learning_rate": 6.395162351451417e-05, "loss": 0.0101, "step": 179410 }, { "epoch": 43.09, "learning_rate": 6.394817647921353e-05, "loss": 0.0093, "step": 179420 }, { "epoch": 43.1, "learning_rate": 6.394472937202385e-05, "loss": 0.0044, "step": 179430 }, { "epoch": 43.1, "learning_rate": 6.394128219296292e-05, "loss": 0.0145, "step": 179440 }, { "epoch": 43.1, "learning_rate": 6.39378349420485e-05, "loss": 0.0069, "step": 179450 }, { "epoch": 43.1, "learning_rate": 6.393438761929837e-05, "loss": 0.0119, "step": 179460 }, { "epoch": 43.11, "learning_rate": 6.393094022473029e-05, "loss": 0.0129, "step": 179470 }, { "epoch": 43.11, "learning_rate": 6.392749275836203e-05, "loss": 0.0124, "step": 179480 }, { "epoch": 43.11, "learning_rate": 6.392404522021134e-05, "loss": 0.0069, "step": 179490 }, { "epoch": 43.11, "learning_rate": 6.392059761029603e-05, "loss": 0.0046, "step": 179500 }, { "epoch": 43.11, "learning_rate": 6.391714992863383e-05, "loss": 0.01, "step": 179510 }, { "epoch": 43.12, "learning_rate": 6.391370217524252e-05, "loss": 0.0046, "step": 179520 }, { "epoch": 43.12, "learning_rate": 6.391025435013987e-05, "loss": 0.0092, "step": 179530 }, { "epoch": 43.12, "learning_rate": 6.390680645334366e-05, "loss": 0.0086, "step": 179540 }, { "epoch": 43.12, "learning_rate": 6.390335848487166e-05, "loss": 0.0101, "step": 179550 }, { "epoch": 43.13, "learning_rate": 6.389991044474162e-05, "loss": 0.0175, "step": 179560 }, { "epoch": 43.13, "learning_rate": 6.389646233297135e-05, "loss": 0.0069, "step": 179570 }, { "epoch": 43.13, "learning_rate": 6.389301414957856e-05, "loss": 0.0108, "step": 179580 }, { "epoch": 43.13, "learning_rate": 6.388956589458107e-05, "loss": 0.0124, "step": 179590 }, { "epoch": 43.14, "learning_rate": 6.388611756799666e-05, "loss": 0.0069, "step": 179600 }, { "epoch": 43.14, "learning_rate": 6.388266916984305e-05, "loss": 0.0075, "step": 179610 }, { "epoch": 43.14, "learning_rate": 6.387922070013807e-05, "loss": 0.0137, "step": 179620 }, { "epoch": 43.14, "learning_rate": 6.387577215889948e-05, "loss": 0.0059, "step": 179630 }, { "epoch": 43.14, "learning_rate": 6.387232354614504e-05, "loss": 0.0111, "step": 179640 }, { "epoch": 43.15, "learning_rate": 6.386887486189253e-05, "loss": 0.0136, "step": 179650 }, { "epoch": 43.15, "learning_rate": 6.386542610615971e-05, "loss": 0.0271, "step": 179660 }, { "epoch": 43.15, "learning_rate": 6.386197727896437e-05, "loss": 0.0098, "step": 179670 }, { "epoch": 43.15, "learning_rate": 6.385852838032429e-05, "loss": 0.0169, "step": 179680 }, { "epoch": 43.16, "learning_rate": 6.385507941025724e-05, "loss": 0.0124, "step": 179690 }, { "epoch": 43.16, "learning_rate": 6.385163036878097e-05, "loss": 0.0105, "step": 179700 }, { "epoch": 43.16, "learning_rate": 6.38481812559133e-05, "loss": 0.0048, "step": 179710 }, { "epoch": 43.16, "learning_rate": 6.384473207167201e-05, "loss": 0.014, "step": 179720 }, { "epoch": 43.16, "learning_rate": 6.384128281607483e-05, "loss": 0.0088, "step": 179730 }, { "epoch": 43.17, "learning_rate": 6.383783348913957e-05, "loss": 0.0106, "step": 179740 }, { "epoch": 43.17, "learning_rate": 6.383438409088398e-05, "loss": 0.0143, "step": 179750 }, { "epoch": 43.17, "learning_rate": 6.383093462132588e-05, "loss": 0.0086, "step": 179760 }, { "epoch": 43.17, "learning_rate": 6.382748508048304e-05, "loss": 0.0228, "step": 179770 }, { "epoch": 43.18, "learning_rate": 6.38240354683732e-05, "loss": 0.0101, "step": 179780 }, { "epoch": 43.18, "learning_rate": 6.382058578501417e-05, "loss": 0.0134, "step": 179790 }, { "epoch": 43.18, "learning_rate": 6.381713603042374e-05, "loss": 0.0068, "step": 179800 }, { "epoch": 43.18, "learning_rate": 6.381368620461968e-05, "loss": 0.0061, "step": 179810 }, { "epoch": 43.19, "learning_rate": 6.381023630761974e-05, "loss": 0.0188, "step": 179820 }, { "epoch": 43.19, "learning_rate": 6.380678633944174e-05, "loss": 0.0075, "step": 179830 }, { "epoch": 43.19, "learning_rate": 6.380333630010345e-05, "loss": 0.0148, "step": 179840 }, { "epoch": 43.19, "learning_rate": 6.379988618962265e-05, "loss": 0.0093, "step": 179850 }, { "epoch": 43.19, "learning_rate": 6.379643600801712e-05, "loss": 0.0087, "step": 179860 }, { "epoch": 43.2, "learning_rate": 6.379298575530463e-05, "loss": 0.0081, "step": 179870 }, { "epoch": 43.2, "learning_rate": 6.3789535431503e-05, "loss": 0.0085, "step": 179880 }, { "epoch": 43.2, "learning_rate": 6.378608503662996e-05, "loss": 0.0142, "step": 179890 }, { "epoch": 43.2, "learning_rate": 6.378263457070334e-05, "loss": 0.0108, "step": 179900 }, { "epoch": 43.21, "learning_rate": 6.37791840337409e-05, "loss": 0.0074, "step": 179910 }, { "epoch": 43.21, "learning_rate": 6.377573342576044e-05, "loss": 0.0087, "step": 179920 }, { "epoch": 43.21, "learning_rate": 6.377228274677974e-05, "loss": 0.0097, "step": 179930 }, { "epoch": 43.21, "learning_rate": 6.376883199681656e-05, "loss": 0.0051, "step": 179940 }, { "epoch": 43.22, "learning_rate": 6.376538117588873e-05, "loss": 0.0086, "step": 179950 }, { "epoch": 43.22, "learning_rate": 6.376193028401398e-05, "loss": 0.0049, "step": 179960 }, { "epoch": 43.22, "learning_rate": 6.375847932121015e-05, "loss": 0.0085, "step": 179970 }, { "epoch": 43.22, "learning_rate": 6.375502828749499e-05, "loss": 0.0151, "step": 179980 }, { "epoch": 43.22, "learning_rate": 6.37515771828863e-05, "loss": 0.0058, "step": 179990 }, { "epoch": 43.23, "learning_rate": 6.374812600740187e-05, "loss": 0.0086, "step": 180000 }, { "epoch": 43.23, "learning_rate": 6.374467476105949e-05, "loss": 0.0081, "step": 180010 }, { "epoch": 43.23, "learning_rate": 6.374122344387694e-05, "loss": 0.0298, "step": 180020 }, { "epoch": 43.23, "learning_rate": 6.373777205587201e-05, "loss": 0.0154, "step": 180030 }, { "epoch": 43.24, "learning_rate": 6.373432059706247e-05, "loss": 0.0296, "step": 180040 }, { "epoch": 43.24, "learning_rate": 6.373086906746613e-05, "loss": 0.0077, "step": 180050 }, { "epoch": 43.24, "learning_rate": 6.372741746710079e-05, "loss": 0.0081, "step": 180060 }, { "epoch": 43.24, "learning_rate": 6.37239657959842e-05, "loss": 0.0226, "step": 180070 }, { "epoch": 43.24, "learning_rate": 6.372051405413421e-05, "loss": 0.0095, "step": 180080 }, { "epoch": 43.25, "learning_rate": 6.371706224156858e-05, "loss": 0.0128, "step": 180090 }, { "epoch": 43.25, "learning_rate": 6.371361035830507e-05, "loss": 0.0091, "step": 180100 }, { "epoch": 43.25, "learning_rate": 6.37101584043615e-05, "loss": 0.0091, "step": 180110 }, { "epoch": 43.25, "learning_rate": 6.370670637975566e-05, "loss": 0.0143, "step": 180120 }, { "epoch": 43.26, "learning_rate": 6.370325428450535e-05, "loss": 0.0048, "step": 180130 }, { "epoch": 43.26, "learning_rate": 6.369980211862836e-05, "loss": 0.0043, "step": 180140 }, { "epoch": 43.26, "learning_rate": 6.369634988214246e-05, "loss": 0.0071, "step": 180150 }, { "epoch": 43.26, "learning_rate": 6.369289757506547e-05, "loss": 0.0112, "step": 180160 }, { "epoch": 43.27, "learning_rate": 6.368944519741515e-05, "loss": 0.0164, "step": 180170 }, { "epoch": 43.27, "learning_rate": 6.368599274920933e-05, "loss": 0.0059, "step": 180180 }, { "epoch": 43.27, "learning_rate": 6.36825402304658e-05, "loss": 0.0169, "step": 180190 }, { "epoch": 43.27, "learning_rate": 6.367908764120232e-05, "loss": 0.014, "step": 180200 }, { "epoch": 43.27, "learning_rate": 6.367563498143671e-05, "loss": 0.0123, "step": 180210 }, { "epoch": 43.28, "learning_rate": 6.367218225118678e-05, "loss": 0.0142, "step": 180220 }, { "epoch": 43.28, "learning_rate": 6.36687294504703e-05, "loss": 0.0085, "step": 180230 }, { "epoch": 43.28, "learning_rate": 6.366527657930508e-05, "loss": 0.0124, "step": 180240 }, { "epoch": 43.28, "learning_rate": 6.36618236377089e-05, "loss": 0.0172, "step": 180250 }, { "epoch": 43.29, "learning_rate": 6.365837062569957e-05, "loss": 0.014, "step": 180260 }, { "epoch": 43.29, "learning_rate": 6.36549175432949e-05, "loss": 0.0151, "step": 180270 }, { "epoch": 43.29, "learning_rate": 6.365146439051263e-05, "loss": 0.0125, "step": 180280 }, { "epoch": 43.29, "learning_rate": 6.364801116737064e-05, "loss": 0.0248, "step": 180290 }, { "epoch": 43.3, "learning_rate": 6.364455787388668e-05, "loss": 0.0254, "step": 180300 }, { "epoch": 43.3, "learning_rate": 6.364110451007854e-05, "loss": 0.0088, "step": 180310 }, { "epoch": 43.3, "learning_rate": 6.363765107596404e-05, "loss": 0.0132, "step": 180320 }, { "epoch": 43.3, "learning_rate": 6.363419757156097e-05, "loss": 0.0103, "step": 180330 }, { "epoch": 43.3, "learning_rate": 6.363074399688713e-05, "loss": 0.0055, "step": 180340 }, { "epoch": 43.31, "learning_rate": 6.362729035196032e-05, "loss": 0.0107, "step": 180350 }, { "epoch": 43.31, "learning_rate": 6.362383663679836e-05, "loss": 0.0117, "step": 180360 }, { "epoch": 43.31, "learning_rate": 6.3620382851419e-05, "loss": 0.0095, "step": 180370 }, { "epoch": 43.31, "learning_rate": 6.36169289958401e-05, "loss": 0.0042, "step": 180380 }, { "epoch": 43.32, "learning_rate": 6.361347507007941e-05, "loss": 0.0105, "step": 180390 }, { "epoch": 43.32, "learning_rate": 6.361002107415477e-05, "loss": 0.0076, "step": 180400 }, { "epoch": 43.32, "learning_rate": 6.360656700808399e-05, "loss": 0.0103, "step": 180410 }, { "epoch": 43.32, "learning_rate": 6.360311287188482e-05, "loss": 0.0223, "step": 180420 }, { "epoch": 43.32, "learning_rate": 6.35996586655751e-05, "loss": 0.0117, "step": 180430 }, { "epoch": 43.33, "learning_rate": 6.359620438917263e-05, "loss": 0.0139, "step": 180440 }, { "epoch": 43.33, "learning_rate": 6.35927500426952e-05, "loss": 0.0101, "step": 180450 }, { "epoch": 43.33, "learning_rate": 6.358929562616064e-05, "loss": 0.0169, "step": 180460 }, { "epoch": 43.33, "learning_rate": 6.358584113958672e-05, "loss": 0.0102, "step": 180470 }, { "epoch": 43.34, "learning_rate": 6.358238658299127e-05, "loss": 0.0111, "step": 180480 }, { "epoch": 43.34, "learning_rate": 6.357893195639207e-05, "loss": 0.0129, "step": 180490 }, { "epoch": 43.34, "learning_rate": 6.357547725980697e-05, "loss": 0.0055, "step": 180500 }, { "epoch": 43.34, "learning_rate": 6.357202249325371e-05, "loss": 0.0061, "step": 180510 }, { "epoch": 43.35, "learning_rate": 6.356856765675016e-05, "loss": 0.01, "step": 180520 }, { "epoch": 43.35, "learning_rate": 6.35651127503141e-05, "loss": 0.0052, "step": 180530 }, { "epoch": 43.35, "learning_rate": 6.356165777396332e-05, "loss": 0.0099, "step": 180540 }, { "epoch": 43.35, "learning_rate": 6.355820272771564e-05, "loss": 0.005, "step": 180550 }, { "epoch": 43.35, "learning_rate": 6.355474761158888e-05, "loss": 0.0153, "step": 180560 }, { "epoch": 43.36, "learning_rate": 6.355129242560084e-05, "loss": 0.0098, "step": 180570 }, { "epoch": 43.36, "learning_rate": 6.354783716976933e-05, "loss": 0.0521, "step": 180580 }, { "epoch": 43.36, "learning_rate": 6.354438184411216e-05, "loss": 0.0087, "step": 180590 }, { "epoch": 43.36, "learning_rate": 6.35409264486471e-05, "loss": 0.0139, "step": 180600 }, { "epoch": 43.37, "learning_rate": 6.353747098339203e-05, "loss": 0.012, "step": 180610 }, { "epoch": 43.37, "learning_rate": 6.353401544836469e-05, "loss": 0.0092, "step": 180620 }, { "epoch": 43.37, "learning_rate": 6.353055984358293e-05, "loss": 0.0187, "step": 180630 }, { "epoch": 43.37, "learning_rate": 6.352710416906456e-05, "loss": 0.0073, "step": 180640 }, { "epoch": 43.38, "learning_rate": 6.352364842482738e-05, "loss": 0.0073, "step": 180650 }, { "epoch": 43.38, "learning_rate": 6.35201926108892e-05, "loss": 0.01, "step": 180660 }, { "epoch": 43.38, "learning_rate": 6.351673672726782e-05, "loss": 0.0076, "step": 180670 }, { "epoch": 43.38, "learning_rate": 6.351328077398109e-05, "loss": 0.021, "step": 180680 }, { "epoch": 43.38, "learning_rate": 6.350982475104679e-05, "loss": 0.018, "step": 180690 }, { "epoch": 43.39, "learning_rate": 6.350636865848273e-05, "loss": 0.0071, "step": 180700 }, { "epoch": 43.39, "learning_rate": 6.350291249630675e-05, "loss": 0.0123, "step": 180710 }, { "epoch": 43.39, "learning_rate": 6.349945626453663e-05, "loss": 0.0069, "step": 180720 }, { "epoch": 43.39, "learning_rate": 6.349599996319023e-05, "loss": 0.0114, "step": 180730 }, { "epoch": 43.4, "learning_rate": 6.349254359228529e-05, "loss": 0.0141, "step": 180740 }, { "epoch": 43.4, "learning_rate": 6.34890871518397e-05, "loss": 0.0077, "step": 180750 }, { "epoch": 43.4, "learning_rate": 6.348563064187122e-05, "loss": 0.0142, "step": 180760 }, { "epoch": 43.4, "learning_rate": 6.348217406239769e-05, "loss": 0.0122, "step": 180770 }, { "epoch": 43.4, "learning_rate": 6.347871741343694e-05, "loss": 0.0114, "step": 180780 }, { "epoch": 43.41, "learning_rate": 6.347526069500676e-05, "loss": 0.0115, "step": 180790 }, { "epoch": 43.41, "learning_rate": 6.347180390712497e-05, "loss": 0.0084, "step": 180800 }, { "epoch": 43.41, "learning_rate": 6.346834704980938e-05, "loss": 0.0139, "step": 180810 }, { "epoch": 43.41, "learning_rate": 6.346489012307784e-05, "loss": 0.0144, "step": 180820 }, { "epoch": 43.42, "learning_rate": 6.346143312694812e-05, "loss": 0.0094, "step": 180830 }, { "epoch": 43.42, "learning_rate": 6.345797606143808e-05, "loss": 0.0063, "step": 180840 }, { "epoch": 43.42, "learning_rate": 6.345451892656552e-05, "loss": 0.0064, "step": 180850 }, { "epoch": 43.42, "learning_rate": 6.345106172234823e-05, "loss": 0.005, "step": 180860 }, { "epoch": 43.43, "learning_rate": 6.344760444880408e-05, "loss": 0.0068, "step": 180870 }, { "epoch": 43.43, "learning_rate": 6.344414710595087e-05, "loss": 0.0177, "step": 180880 }, { "epoch": 43.43, "learning_rate": 6.34406896938064e-05, "loss": 0.0124, "step": 180890 }, { "epoch": 43.43, "learning_rate": 6.34372322123885e-05, "loss": 0.0092, "step": 180900 }, { "epoch": 43.43, "learning_rate": 6.3433774661715e-05, "loss": 0.0055, "step": 180910 }, { "epoch": 43.44, "learning_rate": 6.34303170418037e-05, "loss": 0.0068, "step": 180920 }, { "epoch": 43.44, "learning_rate": 6.342685935267245e-05, "loss": 0.0046, "step": 180930 }, { "epoch": 43.44, "learning_rate": 6.342340159433905e-05, "loss": 0.0075, "step": 180940 }, { "epoch": 43.44, "learning_rate": 6.341994376682132e-05, "loss": 0.0216, "step": 180950 }, { "epoch": 43.45, "learning_rate": 6.341648587013708e-05, "loss": 0.0075, "step": 180960 }, { "epoch": 43.45, "learning_rate": 6.341302790430419e-05, "loss": 0.0077, "step": 180970 }, { "epoch": 43.45, "learning_rate": 6.340956986934043e-05, "loss": 0.0095, "step": 180980 }, { "epoch": 43.45, "learning_rate": 6.340611176526362e-05, "loss": 0.0088, "step": 180990 }, { "epoch": 43.45, "learning_rate": 6.340265359209161e-05, "loss": 0.0065, "step": 181000 }, { "epoch": 43.46, "learning_rate": 6.339919534984221e-05, "loss": 0.0248, "step": 181010 }, { "epoch": 43.46, "learning_rate": 6.339573703853324e-05, "loss": 0.0099, "step": 181020 }, { "epoch": 43.46, "learning_rate": 6.339227865818254e-05, "loss": 0.0111, "step": 181030 }, { "epoch": 43.46, "learning_rate": 6.338882020880792e-05, "loss": 0.0075, "step": 181040 }, { "epoch": 43.47, "learning_rate": 6.33853616904272e-05, "loss": 0.0067, "step": 181050 }, { "epoch": 43.47, "learning_rate": 6.338190310305822e-05, "loss": 0.0107, "step": 181060 }, { "epoch": 43.47, "learning_rate": 6.33784444467188e-05, "loss": 0.0128, "step": 181070 }, { "epoch": 43.47, "learning_rate": 6.337498572142677e-05, "loss": 0.0053, "step": 181080 }, { "epoch": 43.48, "learning_rate": 6.337152692719994e-05, "loss": 0.0099, "step": 181090 }, { "epoch": 43.48, "learning_rate": 6.336806806405615e-05, "loss": 0.011, "step": 181100 }, { "epoch": 43.48, "learning_rate": 6.336460913201323e-05, "loss": 0.0059, "step": 181110 }, { "epoch": 43.48, "learning_rate": 6.3361150131089e-05, "loss": 0.0068, "step": 181120 }, { "epoch": 43.48, "learning_rate": 6.335769106130129e-05, "loss": 0.0095, "step": 181130 }, { "epoch": 43.49, "learning_rate": 6.335423192266794e-05, "loss": 0.005, "step": 181140 }, { "epoch": 43.49, "learning_rate": 6.335077271520676e-05, "loss": 0.0155, "step": 181150 }, { "epoch": 43.49, "learning_rate": 6.334731343893559e-05, "loss": 0.0078, "step": 181160 }, { "epoch": 43.49, "learning_rate": 6.334385409387224e-05, "loss": 0.0082, "step": 181170 }, { "epoch": 43.5, "learning_rate": 6.334039468003457e-05, "loss": 0.0089, "step": 181180 }, { "epoch": 43.5, "learning_rate": 6.33369351974404e-05, "loss": 0.0088, "step": 181190 }, { "epoch": 43.5, "learning_rate": 6.333347564610753e-05, "loss": 0.006, "step": 181200 }, { "epoch": 43.5, "learning_rate": 6.333001602605383e-05, "loss": 0.0091, "step": 181210 }, { "epoch": 43.51, "learning_rate": 6.332655633729711e-05, "loss": 0.007, "step": 181220 }, { "epoch": 43.51, "learning_rate": 6.332309657985523e-05, "loss": 0.0073, "step": 181230 }, { "epoch": 43.51, "learning_rate": 6.331963675374597e-05, "loss": 0.0133, "step": 181240 }, { "epoch": 43.51, "learning_rate": 6.33161768589872e-05, "loss": 0.0166, "step": 181250 }, { "epoch": 43.51, "learning_rate": 6.331271689559674e-05, "loss": 0.0178, "step": 181260 }, { "epoch": 43.52, "learning_rate": 6.330925686359242e-05, "loss": 0.0072, "step": 181270 }, { "epoch": 43.52, "learning_rate": 6.33057967629921e-05, "loss": 0.0077, "step": 181280 }, { "epoch": 43.52, "learning_rate": 6.330233659381357e-05, "loss": 0.0102, "step": 181290 }, { "epoch": 43.52, "learning_rate": 6.329887635607472e-05, "loss": 0.0126, "step": 181300 }, { "epoch": 43.53, "learning_rate": 6.329541604979333e-05, "loss": 0.0119, "step": 181310 }, { "epoch": 43.53, "learning_rate": 6.329195567498724e-05, "loss": 0.011, "step": 181320 }, { "epoch": 43.53, "learning_rate": 6.328849523167432e-05, "loss": 0.0106, "step": 181330 }, { "epoch": 43.53, "learning_rate": 6.328503471987238e-05, "loss": 0.0098, "step": 181340 }, { "epoch": 43.53, "learning_rate": 6.328157413959925e-05, "loss": 0.0142, "step": 181350 }, { "epoch": 43.54, "learning_rate": 6.327811349087279e-05, "loss": 0.0164, "step": 181360 }, { "epoch": 43.54, "learning_rate": 6.327465277371081e-05, "loss": 0.0132, "step": 181370 }, { "epoch": 43.54, "learning_rate": 6.327119198813116e-05, "loss": 0.0131, "step": 181380 }, { "epoch": 43.54, "learning_rate": 6.326773113415168e-05, "loss": 0.0074, "step": 181390 }, { "epoch": 43.55, "learning_rate": 6.32642702117902e-05, "loss": 0.011, "step": 181400 }, { "epoch": 43.55, "learning_rate": 6.326080922106455e-05, "loss": 0.0174, "step": 181410 }, { "epoch": 43.55, "learning_rate": 6.32573481619926e-05, "loss": 0.0169, "step": 181420 }, { "epoch": 43.55, "learning_rate": 6.325388703459214e-05, "loss": 0.0087, "step": 181430 }, { "epoch": 43.56, "learning_rate": 6.325042583888106e-05, "loss": 0.0102, "step": 181440 }, { "epoch": 43.56, "learning_rate": 6.324696457487718e-05, "loss": 0.0149, "step": 181450 }, { "epoch": 43.56, "learning_rate": 6.324350324259831e-05, "loss": 0.0077, "step": 181460 }, { "epoch": 43.56, "learning_rate": 6.324004184206232e-05, "loss": 0.0095, "step": 181470 }, { "epoch": 43.56, "learning_rate": 6.323658037328706e-05, "loss": 0.0123, "step": 181480 }, { "epoch": 43.57, "learning_rate": 6.323311883629033e-05, "loss": 0.0078, "step": 181490 }, { "epoch": 43.57, "learning_rate": 6.322965723109001e-05, "loss": 0.0169, "step": 181500 }, { "epoch": 43.57, "learning_rate": 6.322619555770392e-05, "loss": 0.0132, "step": 181510 }, { "epoch": 43.57, "learning_rate": 6.322273381614992e-05, "loss": 0.016, "step": 181520 }, { "epoch": 43.58, "learning_rate": 6.321927200644583e-05, "loss": 0.0241, "step": 181530 }, { "epoch": 43.58, "learning_rate": 6.32158101286095e-05, "loss": 0.0084, "step": 181540 }, { "epoch": 43.58, "learning_rate": 6.321234818265877e-05, "loss": 0.033, "step": 181550 }, { "epoch": 43.58, "learning_rate": 6.32088861686115e-05, "loss": 0.0151, "step": 181560 }, { "epoch": 43.59, "learning_rate": 6.32054240864855e-05, "loss": 0.0118, "step": 181570 }, { "epoch": 43.59, "learning_rate": 6.320196193629866e-05, "loss": 0.0098, "step": 181580 }, { "epoch": 43.59, "learning_rate": 6.319849971806878e-05, "loss": 0.0117, "step": 181590 }, { "epoch": 43.59, "learning_rate": 6.319503743181372e-05, "loss": 0.011, "step": 181600 }, { "epoch": 43.59, "learning_rate": 6.319157507755133e-05, "loss": 0.0162, "step": 181610 }, { "epoch": 43.6, "learning_rate": 6.318811265529946e-05, "loss": 0.0149, "step": 181620 }, { "epoch": 43.6, "learning_rate": 6.318465016507595e-05, "loss": 0.0097, "step": 181630 }, { "epoch": 43.6, "learning_rate": 6.318118760689863e-05, "loss": 0.0095, "step": 181640 }, { "epoch": 43.6, "learning_rate": 6.317772498078536e-05, "loss": 0.011, "step": 181650 }, { "epoch": 43.61, "learning_rate": 6.3174262286754e-05, "loss": 0.0108, "step": 181660 }, { "epoch": 43.61, "learning_rate": 6.317079952482237e-05, "loss": 0.0092, "step": 181670 }, { "epoch": 43.61, "learning_rate": 6.316733669500833e-05, "loss": 0.0226, "step": 181680 }, { "epoch": 43.61, "learning_rate": 6.316387379732973e-05, "loss": 0.0162, "step": 181690 }, { "epoch": 43.61, "learning_rate": 6.31604108318044e-05, "loss": 0.0123, "step": 181700 }, { "epoch": 43.62, "learning_rate": 6.315694779845021e-05, "loss": 0.0094, "step": 181710 }, { "epoch": 43.62, "learning_rate": 6.3153484697285e-05, "loss": 0.0128, "step": 181720 }, { "epoch": 43.62, "learning_rate": 6.315002152832664e-05, "loss": 0.0105, "step": 181730 }, { "epoch": 43.62, "learning_rate": 6.314655829159294e-05, "loss": 0.0106, "step": 181740 }, { "epoch": 43.63, "learning_rate": 6.314309498710178e-05, "loss": 0.0195, "step": 181750 }, { "epoch": 43.63, "learning_rate": 6.313963161487098e-05, "loss": 0.0408, "step": 181760 }, { "epoch": 43.63, "learning_rate": 6.313616817491844e-05, "loss": 0.0126, "step": 181770 }, { "epoch": 43.63, "learning_rate": 6.313270466726194e-05, "loss": 0.0094, "step": 181780 }, { "epoch": 43.64, "learning_rate": 6.31292410919194e-05, "loss": 0.0091, "step": 181790 }, { "epoch": 43.64, "learning_rate": 6.312577744890864e-05, "loss": 0.0107, "step": 181800 }, { "epoch": 43.64, "learning_rate": 6.31223137382475e-05, "loss": 0.0076, "step": 181810 }, { "epoch": 43.64, "learning_rate": 6.311884995995385e-05, "loss": 0.0185, "step": 181820 }, { "epoch": 43.64, "learning_rate": 6.311538611404554e-05, "loss": 0.0047, "step": 181830 }, { "epoch": 43.65, "learning_rate": 6.31119222005404e-05, "loss": 0.0079, "step": 181840 }, { "epoch": 43.65, "learning_rate": 6.310845821945634e-05, "loss": 0.0057, "step": 181850 }, { "epoch": 43.65, "learning_rate": 6.310499417081114e-05, "loss": 0.0166, "step": 181860 }, { "epoch": 43.65, "learning_rate": 6.310153005462272e-05, "loss": 0.0147, "step": 181870 }, { "epoch": 43.66, "learning_rate": 6.309806587090889e-05, "loss": 0.0146, "step": 181880 }, { "epoch": 43.66, "learning_rate": 6.309460161968752e-05, "loss": 0.0136, "step": 181890 }, { "epoch": 43.66, "learning_rate": 6.309113730097647e-05, "loss": 0.0078, "step": 181900 }, { "epoch": 43.66, "learning_rate": 6.308767291479358e-05, "loss": 0.0119, "step": 181910 }, { "epoch": 43.67, "learning_rate": 6.308420846115672e-05, "loss": 0.0085, "step": 181920 }, { "epoch": 43.67, "learning_rate": 6.308074394008374e-05, "loss": 0.0065, "step": 181930 }, { "epoch": 43.67, "learning_rate": 6.307727935159251e-05, "loss": 0.0134, "step": 181940 }, { "epoch": 43.67, "learning_rate": 6.307381469570086e-05, "loss": 0.0093, "step": 181950 }, { "epoch": 43.67, "learning_rate": 6.307034997242665e-05, "loss": 0.0144, "step": 181960 }, { "epoch": 43.68, "learning_rate": 6.306688518178775e-05, "loss": 0.0122, "step": 181970 }, { "epoch": 43.68, "learning_rate": 6.306342032380204e-05, "loss": 0.0152, "step": 181980 }, { "epoch": 43.68, "learning_rate": 6.305995539848733e-05, "loss": 0.0102, "step": 181990 }, { "epoch": 43.68, "learning_rate": 6.30564904058615e-05, "loss": 0.0054, "step": 182000 }, { "epoch": 43.69, "learning_rate": 6.305302534594241e-05, "loss": 0.0141, "step": 182010 }, { "epoch": 43.69, "learning_rate": 6.304956021874791e-05, "loss": 0.016, "step": 182020 }, { "epoch": 43.69, "learning_rate": 6.304609502429588e-05, "loss": 0.0126, "step": 182030 }, { "epoch": 43.69, "learning_rate": 6.304262976260418e-05, "loss": 0.0087, "step": 182040 }, { "epoch": 43.69, "learning_rate": 6.303916443369064e-05, "loss": 0.0152, "step": 182050 }, { "epoch": 43.7, "learning_rate": 6.303569903757314e-05, "loss": 0.0097, "step": 182060 }, { "epoch": 43.7, "learning_rate": 6.303223357426953e-05, "loss": 0.0096, "step": 182070 }, { "epoch": 43.7, "learning_rate": 6.302876804379769e-05, "loss": 0.0061, "step": 182080 }, { "epoch": 43.7, "learning_rate": 6.302530244617549e-05, "loss": 0.008, "step": 182090 }, { "epoch": 43.71, "learning_rate": 6.302183678142074e-05, "loss": 0.011, "step": 182100 }, { "epoch": 43.71, "learning_rate": 6.301837104955135e-05, "loss": 0.0144, "step": 182110 }, { "epoch": 43.71, "learning_rate": 6.301490525058515e-05, "loss": 0.008, "step": 182120 }, { "epoch": 43.71, "learning_rate": 6.301143938454003e-05, "loss": 0.008, "step": 182130 }, { "epoch": 43.72, "learning_rate": 6.300797345143386e-05, "loss": 0.0108, "step": 182140 }, { "epoch": 43.72, "learning_rate": 6.300450745128445e-05, "loss": 0.0157, "step": 182150 }, { "epoch": 43.72, "learning_rate": 6.300104138410974e-05, "loss": 0.0127, "step": 182160 }, { "epoch": 43.72, "learning_rate": 6.299757524992753e-05, "loss": 0.0056, "step": 182170 }, { "epoch": 43.72, "learning_rate": 6.299410904875572e-05, "loss": 0.0064, "step": 182180 }, { "epoch": 43.73, "learning_rate": 6.299064278061213e-05, "loss": 0.0077, "step": 182190 }, { "epoch": 43.73, "learning_rate": 6.298717644551469e-05, "loss": 0.005, "step": 182200 }, { "epoch": 43.73, "learning_rate": 6.298371004348124e-05, "loss": 0.0046, "step": 182210 }, { "epoch": 43.73, "learning_rate": 6.298024357452963e-05, "loss": 0.011, "step": 182220 }, { "epoch": 43.74, "learning_rate": 6.297677703867773e-05, "loss": 0.0081, "step": 182230 }, { "epoch": 43.74, "learning_rate": 6.297331043594343e-05, "loss": 0.0112, "step": 182240 }, { "epoch": 43.74, "learning_rate": 6.296984376634455e-05, "loss": 0.0153, "step": 182250 }, { "epoch": 43.74, "learning_rate": 6.296637702989902e-05, "loss": 0.0123, "step": 182260 }, { "epoch": 43.75, "learning_rate": 6.296291022662465e-05, "loss": 0.0069, "step": 182270 }, { "epoch": 43.75, "learning_rate": 6.295944335653934e-05, "loss": 0.0147, "step": 182280 }, { "epoch": 43.75, "learning_rate": 6.295597641966096e-05, "loss": 0.007, "step": 182290 }, { "epoch": 43.75, "learning_rate": 6.295250941600736e-05, "loss": 0.0085, "step": 182300 }, { "epoch": 43.75, "learning_rate": 6.294904234559641e-05, "loss": 0.0207, "step": 182310 }, { "epoch": 43.76, "learning_rate": 6.2945575208446e-05, "loss": 0.0197, "step": 182320 }, { "epoch": 43.76, "learning_rate": 6.294210800457399e-05, "loss": 0.0124, "step": 182330 }, { "epoch": 43.76, "learning_rate": 6.293864073399823e-05, "loss": 0.0299, "step": 182340 }, { "epoch": 43.76, "learning_rate": 6.293517339673662e-05, "loss": 0.0105, "step": 182350 }, { "epoch": 43.77, "learning_rate": 6.2931705992807e-05, "loss": 0.0112, "step": 182360 }, { "epoch": 43.77, "learning_rate": 6.29282385222273e-05, "loss": 0.0192, "step": 182370 }, { "epoch": 43.77, "learning_rate": 6.292477098501533e-05, "loss": 0.0095, "step": 182380 }, { "epoch": 43.77, "learning_rate": 6.292130338118898e-05, "loss": 0.0087, "step": 182390 }, { "epoch": 43.77, "learning_rate": 6.291783571076611e-05, "loss": 0.0101, "step": 182400 }, { "epoch": 43.78, "learning_rate": 6.291436797376462e-05, "loss": 0.0056, "step": 182410 }, { "epoch": 43.78, "learning_rate": 6.291090017020237e-05, "loss": 0.0112, "step": 182420 }, { "epoch": 43.78, "learning_rate": 6.290743230009724e-05, "loss": 0.011, "step": 182430 }, { "epoch": 43.78, "learning_rate": 6.290396436346708e-05, "loss": 0.0084, "step": 182440 }, { "epoch": 43.79, "learning_rate": 6.290049636032979e-05, "loss": 0.009, "step": 182450 }, { "epoch": 43.79, "learning_rate": 6.289702829070323e-05, "loss": 0.0139, "step": 182460 }, { "epoch": 43.79, "learning_rate": 6.289356015460529e-05, "loss": 0.0135, "step": 182470 }, { "epoch": 43.79, "learning_rate": 6.28900919520538e-05, "loss": 0.011, "step": 182480 }, { "epoch": 43.8, "learning_rate": 6.28866236830667e-05, "loss": 0.0113, "step": 182490 }, { "epoch": 43.8, "learning_rate": 6.288315534766183e-05, "loss": 0.0106, "step": 182500 }, { "epoch": 43.8, "learning_rate": 6.287968694585707e-05, "loss": 0.0079, "step": 182510 }, { "epoch": 43.8, "learning_rate": 6.28762184776703e-05, "loss": 0.0151, "step": 182520 }, { "epoch": 43.8, "learning_rate": 6.287274994311937e-05, "loss": 0.0115, "step": 182530 }, { "epoch": 43.81, "learning_rate": 6.286928134222218e-05, "loss": 0.0069, "step": 182540 }, { "epoch": 43.81, "learning_rate": 6.286581267499662e-05, "loss": 0.0146, "step": 182550 }, { "epoch": 43.81, "learning_rate": 6.286234394146055e-05, "loss": 0.0101, "step": 182560 }, { "epoch": 43.81, "learning_rate": 6.285887514163186e-05, "loss": 0.0128, "step": 182570 }, { "epoch": 43.82, "learning_rate": 6.285540627552842e-05, "loss": 0.0111, "step": 182580 }, { "epoch": 43.82, "learning_rate": 6.285193734316812e-05, "loss": 0.0092, "step": 182590 }, { "epoch": 43.82, "learning_rate": 6.28484683445688e-05, "loss": 0.0153, "step": 182600 }, { "epoch": 43.82, "learning_rate": 6.284499927974837e-05, "loss": 0.0116, "step": 182610 }, { "epoch": 43.83, "learning_rate": 6.284153014872471e-05, "loss": 0.013, "step": 182620 }, { "epoch": 43.83, "learning_rate": 6.28380609515157e-05, "loss": 0.0153, "step": 182630 }, { "epoch": 43.83, "learning_rate": 6.283459168813921e-05, "loss": 0.0072, "step": 182640 }, { "epoch": 43.83, "learning_rate": 6.283112235861313e-05, "loss": 0.0115, "step": 182650 }, { "epoch": 43.83, "learning_rate": 6.282765296295537e-05, "loss": 0.0118, "step": 182660 }, { "epoch": 43.84, "learning_rate": 6.282418350118374e-05, "loss": 0.0135, "step": 182670 }, { "epoch": 43.84, "learning_rate": 6.282071397331616e-05, "loss": 0.0087, "step": 182680 }, { "epoch": 43.84, "learning_rate": 6.281724437937053e-05, "loss": 0.0079, "step": 182690 }, { "epoch": 43.84, "learning_rate": 6.281377471936472e-05, "loss": 0.0095, "step": 182700 }, { "epoch": 43.85, "learning_rate": 6.281030499331659e-05, "loss": 0.0149, "step": 182710 }, { "epoch": 43.85, "learning_rate": 6.280683520124406e-05, "loss": 0.0073, "step": 182720 }, { "epoch": 43.85, "learning_rate": 6.280336534316498e-05, "loss": 0.007, "step": 182730 }, { "epoch": 43.85, "learning_rate": 6.279989541909726e-05, "loss": 0.0085, "step": 182740 }, { "epoch": 43.85, "learning_rate": 6.279642542905876e-05, "loss": 0.016, "step": 182750 }, { "epoch": 43.86, "learning_rate": 6.279295537306738e-05, "loss": 0.009, "step": 182760 }, { "epoch": 43.86, "learning_rate": 6.278948525114098e-05, "loss": 0.0164, "step": 182770 }, { "epoch": 43.86, "learning_rate": 6.27860150632975e-05, "loss": 0.0085, "step": 182780 }, { "epoch": 43.86, "learning_rate": 6.278254480955478e-05, "loss": 0.0061, "step": 182790 }, { "epoch": 43.87, "learning_rate": 6.277907448993072e-05, "loss": 0.0136, "step": 182800 }, { "epoch": 43.87, "learning_rate": 6.27756041044432e-05, "loss": 0.0099, "step": 182810 }, { "epoch": 43.87, "learning_rate": 6.27721336531101e-05, "loss": 0.0082, "step": 182820 }, { "epoch": 43.87, "learning_rate": 6.276866313594933e-05, "loss": 0.0066, "step": 182830 }, { "epoch": 43.88, "learning_rate": 6.276519255297876e-05, "loss": 0.018, "step": 182840 }, { "epoch": 43.88, "learning_rate": 6.276172190421627e-05, "loss": 0.0042, "step": 182850 }, { "epoch": 43.88, "learning_rate": 6.275825118967977e-05, "loss": 0.0072, "step": 182860 }, { "epoch": 43.88, "learning_rate": 6.275478040938714e-05, "loss": 0.0088, "step": 182870 }, { "epoch": 43.88, "learning_rate": 6.275130956335628e-05, "loss": 0.0064, "step": 182880 }, { "epoch": 43.89, "learning_rate": 6.274783865160504e-05, "loss": 0.0055, "step": 182890 }, { "epoch": 43.89, "learning_rate": 6.274436767415133e-05, "loss": 0.0104, "step": 182900 }, { "epoch": 43.89, "learning_rate": 6.274089663101306e-05, "loss": 0.014, "step": 182910 }, { "epoch": 43.89, "learning_rate": 6.273742552220807e-05, "loss": 0.0077, "step": 182920 }, { "epoch": 43.9, "learning_rate": 6.27339543477543e-05, "loss": 0.0049, "step": 182930 }, { "epoch": 43.9, "learning_rate": 6.273048310766964e-05, "loss": 0.0063, "step": 182940 }, { "epoch": 43.9, "learning_rate": 6.272701180197195e-05, "loss": 0.0089, "step": 182950 }, { "epoch": 43.9, "learning_rate": 6.272354043067915e-05, "loss": 0.005, "step": 182960 }, { "epoch": 43.91, "learning_rate": 6.272006899380909e-05, "loss": 0.0091, "step": 182970 }, { "epoch": 43.91, "learning_rate": 6.27165974913797e-05, "loss": 0.0192, "step": 182980 }, { "epoch": 43.91, "learning_rate": 6.271312592340886e-05, "loss": 0.0109, "step": 182990 }, { "epoch": 43.91, "learning_rate": 6.270965428991447e-05, "loss": 0.0108, "step": 183000 }, { "epoch": 43.91, "learning_rate": 6.27061825909144e-05, "loss": 0.0078, "step": 183010 }, { "epoch": 43.92, "learning_rate": 6.270271082642658e-05, "loss": 0.0063, "step": 183020 }, { "epoch": 43.92, "learning_rate": 6.269923899646887e-05, "loss": 0.0124, "step": 183030 }, { "epoch": 43.92, "learning_rate": 6.269576710105917e-05, "loss": 0.0218, "step": 183040 }, { "epoch": 43.92, "learning_rate": 6.269229514021538e-05, "loss": 0.0058, "step": 183050 }, { "epoch": 43.93, "learning_rate": 6.26888231139554e-05, "loss": 0.0183, "step": 183060 }, { "epoch": 43.93, "learning_rate": 6.268535102229713e-05, "loss": 0.0139, "step": 183070 }, { "epoch": 43.93, "learning_rate": 6.268187886525842e-05, "loss": 0.0119, "step": 183080 }, { "epoch": 43.93, "learning_rate": 6.267840664285724e-05, "loss": 0.022, "step": 183090 }, { "epoch": 43.93, "learning_rate": 6.267493435511143e-05, "loss": 0.0062, "step": 183100 }, { "epoch": 43.94, "learning_rate": 6.26714620020389e-05, "loss": 0.008, "step": 183110 }, { "epoch": 43.94, "learning_rate": 6.266798958365756e-05, "loss": 0.0062, "step": 183120 }, { "epoch": 43.94, "learning_rate": 6.266451709998529e-05, "loss": 0.0129, "step": 183130 }, { "epoch": 43.94, "learning_rate": 6.266104455103998e-05, "loss": 0.0067, "step": 183140 }, { "epoch": 43.95, "learning_rate": 6.265757193683956e-05, "loss": 0.0102, "step": 183150 }, { "epoch": 43.95, "learning_rate": 6.265409925740191e-05, "loss": 0.0058, "step": 183160 }, { "epoch": 43.95, "learning_rate": 6.265062651274491e-05, "loss": 0.0087, "step": 183170 }, { "epoch": 44.0, "learning_rate": 6.264715370288649e-05, "loss": 0.0071, "step": 183180 }, { "epoch": 44.0, "learning_rate": 6.264368082784452e-05, "loss": 0.0113, "step": 183190 }, { "epoch": 44.01, "learning_rate": 6.264020788763691e-05, "loss": 0.011, "step": 183200 }, { "epoch": 44.01, "learning_rate": 6.263673488228159e-05, "loss": 0.0161, "step": 183210 }, { "epoch": 44.01, "learning_rate": 6.263326181179641e-05, "loss": 0.0128, "step": 183220 }, { "epoch": 44.01, "learning_rate": 6.26297886761993e-05, "loss": 0.0083, "step": 183230 }, { "epoch": 44.02, "learning_rate": 6.262631547550815e-05, "loss": 0.0084, "step": 183240 }, { "epoch": 44.02, "learning_rate": 6.262284220974086e-05, "loss": 0.007, "step": 183250 }, { "epoch": 44.02, "learning_rate": 6.261936887891535e-05, "loss": 0.0169, "step": 183260 }, { "epoch": 44.02, "learning_rate": 6.26158954830495e-05, "loss": 0.009, "step": 183270 }, { "epoch": 44.02, "learning_rate": 6.261242202216121e-05, "loss": 0.0133, "step": 183280 }, { "epoch": 44.03, "learning_rate": 6.26089484962684e-05, "loss": 0.0057, "step": 183290 }, { "epoch": 44.03, "learning_rate": 6.260547490538897e-05, "loss": 0.0044, "step": 183300 }, { "epoch": 44.03, "learning_rate": 6.260200124954082e-05, "loss": 0.0063, "step": 183310 }, { "epoch": 44.03, "learning_rate": 6.259852752874184e-05, "loss": 0.0115, "step": 183320 }, { "epoch": 44.04, "learning_rate": 6.259505374300994e-05, "loss": 0.0041, "step": 183330 }, { "epoch": 44.04, "learning_rate": 6.259157989236303e-05, "loss": 0.0096, "step": 183340 }, { "epoch": 44.04, "learning_rate": 6.258810597681903e-05, "loss": 0.0063, "step": 183350 }, { "epoch": 44.04, "learning_rate": 6.25846319963958e-05, "loss": 0.0115, "step": 183360 }, { "epoch": 44.05, "learning_rate": 6.258115795111129e-05, "loss": 0.0091, "step": 183370 }, { "epoch": 44.05, "learning_rate": 6.257768384098337e-05, "loss": 0.0131, "step": 183380 }, { "epoch": 44.05, "learning_rate": 6.257420966602997e-05, "loss": 0.0051, "step": 183390 }, { "epoch": 44.05, "learning_rate": 6.257073542626899e-05, "loss": 0.0088, "step": 183400 }, { "epoch": 44.05, "learning_rate": 6.256726112171834e-05, "loss": 0.0083, "step": 183410 }, { "epoch": 44.06, "learning_rate": 6.256378675239592e-05, "loss": 0.0069, "step": 183420 }, { "epoch": 44.06, "learning_rate": 6.256031231831963e-05, "loss": 0.0129, "step": 183430 }, { "epoch": 44.06, "learning_rate": 6.255683781950739e-05, "loss": 0.0106, "step": 183440 }, { "epoch": 44.06, "learning_rate": 6.255336325597712e-05, "loss": 0.0091, "step": 183450 }, { "epoch": 44.07, "learning_rate": 6.254988862774668e-05, "loss": 0.0111, "step": 183460 }, { "epoch": 44.07, "learning_rate": 6.254641393483402e-05, "loss": 0.0123, "step": 183470 }, { "epoch": 44.07, "learning_rate": 6.254293917725704e-05, "loss": 0.012, "step": 183480 }, { "epoch": 44.07, "learning_rate": 6.253946435503365e-05, "loss": 0.0125, "step": 183490 }, { "epoch": 44.07, "learning_rate": 6.253598946818176e-05, "loss": 0.0085, "step": 183500 }, { "epoch": 44.08, "learning_rate": 6.253251451671926e-05, "loss": 0.0152, "step": 183510 }, { "epoch": 44.08, "learning_rate": 6.252903950066409e-05, "loss": 0.0046, "step": 183520 }, { "epoch": 44.08, "learning_rate": 6.252556442003414e-05, "loss": 0.0075, "step": 183530 }, { "epoch": 44.08, "learning_rate": 6.252208927484732e-05, "loss": 0.0086, "step": 183540 }, { "epoch": 44.09, "learning_rate": 6.251861406512155e-05, "loss": 0.008, "step": 183550 }, { "epoch": 44.09, "learning_rate": 6.251513879087474e-05, "loss": 0.0087, "step": 183560 }, { "epoch": 44.09, "learning_rate": 6.25116634521248e-05, "loss": 0.0087, "step": 183570 }, { "epoch": 44.09, "learning_rate": 6.250818804888964e-05, "loss": 0.0084, "step": 183580 }, { "epoch": 44.1, "learning_rate": 6.250471258118718e-05, "loss": 0.0115, "step": 183590 }, { "epoch": 44.1, "learning_rate": 6.250123704903534e-05, "loss": 0.0112, "step": 183600 }, { "epoch": 44.1, "learning_rate": 6.2497761452452e-05, "loss": 0.0073, "step": 183610 }, { "epoch": 44.1, "learning_rate": 6.249428579145509e-05, "loss": 0.0044, "step": 183620 }, { "epoch": 44.1, "learning_rate": 6.249081006606253e-05, "loss": 0.0117, "step": 183630 }, { "epoch": 44.11, "learning_rate": 6.248733427629225e-05, "loss": 0.0066, "step": 183640 }, { "epoch": 44.11, "learning_rate": 6.248385842216212e-05, "loss": 0.0128, "step": 183650 }, { "epoch": 44.11, "learning_rate": 6.248038250369008e-05, "loss": 0.0148, "step": 183660 }, { "epoch": 44.11, "learning_rate": 6.247690652089407e-05, "loss": 0.0069, "step": 183670 }, { "epoch": 44.12, "learning_rate": 6.247343047379194e-05, "loss": 0.0068, "step": 183680 }, { "epoch": 44.12, "learning_rate": 6.246995436240168e-05, "loss": 0.0057, "step": 183690 }, { "epoch": 44.12, "learning_rate": 6.246647818674115e-05, "loss": 0.0074, "step": 183700 }, { "epoch": 44.12, "learning_rate": 6.24630019468283e-05, "loss": 0.0074, "step": 183710 }, { "epoch": 44.13, "learning_rate": 6.245952564268103e-05, "loss": 0.0179, "step": 183720 }, { "epoch": 44.13, "learning_rate": 6.245604927431725e-05, "loss": 0.005, "step": 183730 }, { "epoch": 44.13, "learning_rate": 6.245257284175492e-05, "loss": 0.004, "step": 183740 }, { "epoch": 44.13, "learning_rate": 6.24490963450119e-05, "loss": 0.0088, "step": 183750 }, { "epoch": 44.13, "learning_rate": 6.244561978410613e-05, "loss": 0.0059, "step": 183760 }, { "epoch": 44.14, "learning_rate": 6.244214315905554e-05, "loss": 0.0113, "step": 183770 }, { "epoch": 44.14, "learning_rate": 6.243866646987804e-05, "loss": 0.0058, "step": 183780 }, { "epoch": 44.14, "learning_rate": 6.243518971659155e-05, "loss": 0.0097, "step": 183790 }, { "epoch": 44.14, "learning_rate": 6.243171289921399e-05, "loss": 0.014, "step": 183800 }, { "epoch": 44.15, "learning_rate": 6.242823601776327e-05, "loss": 0.0092, "step": 183810 }, { "epoch": 44.15, "learning_rate": 6.24247590722573e-05, "loss": 0.0077, "step": 183820 }, { "epoch": 44.15, "learning_rate": 6.242128206271405e-05, "loss": 0.0068, "step": 183830 }, { "epoch": 44.15, "learning_rate": 6.24178049891514e-05, "loss": 0.005, "step": 183840 }, { "epoch": 44.15, "learning_rate": 6.241432785158727e-05, "loss": 0.0071, "step": 183850 }, { "epoch": 44.16, "learning_rate": 6.24108506500396e-05, "loss": 0.0159, "step": 183860 }, { "epoch": 44.16, "learning_rate": 6.24073733845263e-05, "loss": 0.0108, "step": 183870 }, { "epoch": 44.16, "learning_rate": 6.24038960550653e-05, "loss": 0.0158, "step": 183880 }, { "epoch": 44.16, "learning_rate": 6.240041866167451e-05, "loss": 0.0092, "step": 183890 }, { "epoch": 44.17, "learning_rate": 6.239694120437186e-05, "loss": 0.0106, "step": 183900 }, { "epoch": 44.17, "learning_rate": 6.239346368317527e-05, "loss": 0.0139, "step": 183910 }, { "epoch": 44.17, "learning_rate": 6.238998609810266e-05, "loss": 0.0139, "step": 183920 }, { "epoch": 44.17, "learning_rate": 6.238650844917196e-05, "loss": 0.0091, "step": 183930 }, { "epoch": 44.18, "learning_rate": 6.23830307364011e-05, "loss": 0.0097, "step": 183940 }, { "epoch": 44.18, "learning_rate": 6.2379552959808e-05, "loss": 0.0213, "step": 183950 }, { "epoch": 44.18, "learning_rate": 6.237607511941056e-05, "loss": 0.0107, "step": 183960 }, { "epoch": 44.18, "learning_rate": 6.237259721522673e-05, "loss": 0.0114, "step": 183970 }, { "epoch": 44.18, "learning_rate": 6.236911924727443e-05, "loss": 0.0101, "step": 183980 }, { "epoch": 44.19, "learning_rate": 6.23656412155716e-05, "loss": 0.0156, "step": 183990 }, { "epoch": 44.19, "learning_rate": 6.236216312013614e-05, "loss": 0.0081, "step": 184000 }, { "epoch": 44.19, "learning_rate": 6.235868496098599e-05, "loss": 0.0145, "step": 184010 }, { "epoch": 44.19, "learning_rate": 6.235520673813908e-05, "loss": 0.0078, "step": 184020 }, { "epoch": 44.2, "learning_rate": 6.235172845161333e-05, "loss": 0.0075, "step": 184030 }, { "epoch": 44.2, "learning_rate": 6.234825010142668e-05, "loss": 0.0085, "step": 184040 }, { "epoch": 44.2, "learning_rate": 6.234477168759703e-05, "loss": 0.0061, "step": 184050 }, { "epoch": 44.2, "learning_rate": 6.234129321014231e-05, "loss": 0.0083, "step": 184060 }, { "epoch": 44.21, "learning_rate": 6.233781466908048e-05, "loss": 0.0086, "step": 184070 }, { "epoch": 44.21, "learning_rate": 6.233433606442945e-05, "loss": 0.0069, "step": 184080 }, { "epoch": 44.21, "learning_rate": 6.233085739620714e-05, "loss": 0.0091, "step": 184090 }, { "epoch": 44.21, "learning_rate": 6.232737866443152e-05, "loss": 0.0044, "step": 184100 }, { "epoch": 44.21, "learning_rate": 6.232389986912045e-05, "loss": 0.0148, "step": 184110 }, { "epoch": 44.22, "learning_rate": 6.23204210102919e-05, "loss": 0.0105, "step": 184120 }, { "epoch": 44.22, "learning_rate": 6.23169420879638e-05, "loss": 0.007, "step": 184130 }, { "epoch": 44.22, "learning_rate": 6.231346310215409e-05, "loss": 0.0052, "step": 184140 }, { "epoch": 44.22, "learning_rate": 6.230998405288067e-05, "loss": 0.0152, "step": 184150 }, { "epoch": 44.23, "learning_rate": 6.23065049401615e-05, "loss": 0.0113, "step": 184160 }, { "epoch": 44.23, "learning_rate": 6.230302576401453e-05, "loss": 0.007, "step": 184170 }, { "epoch": 44.23, "learning_rate": 6.229954652445761e-05, "loss": 0.0066, "step": 184180 }, { "epoch": 44.23, "learning_rate": 6.229606722150876e-05, "loss": 0.0103, "step": 184190 }, { "epoch": 44.23, "learning_rate": 6.229258785518585e-05, "loss": 0.0176, "step": 184200 }, { "epoch": 44.24, "learning_rate": 6.228910842550685e-05, "loss": 0.0059, "step": 184210 }, { "epoch": 44.24, "learning_rate": 6.22856289324897e-05, "loss": 0.0051, "step": 184220 }, { "epoch": 44.24, "learning_rate": 6.22821493761523e-05, "loss": 0.0094, "step": 184230 }, { "epoch": 44.24, "learning_rate": 6.227866975651261e-05, "loss": 0.0152, "step": 184240 }, { "epoch": 44.25, "learning_rate": 6.227519007358855e-05, "loss": 0.0163, "step": 184250 }, { "epoch": 44.25, "learning_rate": 6.227171032739804e-05, "loss": 0.0066, "step": 184260 }, { "epoch": 44.25, "learning_rate": 6.226823051795906e-05, "loss": 0.01, "step": 184270 }, { "epoch": 44.25, "learning_rate": 6.226475064528948e-05, "loss": 0.0081, "step": 184280 }, { "epoch": 44.26, "learning_rate": 6.22612707094073e-05, "loss": 0.0085, "step": 184290 }, { "epoch": 44.26, "learning_rate": 6.225779071033042e-05, "loss": 0.0124, "step": 184300 }, { "epoch": 44.26, "learning_rate": 6.225431064807679e-05, "loss": 0.0079, "step": 184310 }, { "epoch": 44.26, "learning_rate": 6.225083052266435e-05, "loss": 0.0085, "step": 184320 }, { "epoch": 44.26, "learning_rate": 6.224735033411101e-05, "loss": 0.0076, "step": 184330 }, { "epoch": 44.27, "learning_rate": 6.224387008243472e-05, "loss": 0.0036, "step": 184340 }, { "epoch": 44.27, "learning_rate": 6.224038976765344e-05, "loss": 0.0063, "step": 184350 }, { "epoch": 44.27, "learning_rate": 6.223690938978508e-05, "loss": 0.0059, "step": 184360 }, { "epoch": 44.27, "learning_rate": 6.223342894884758e-05, "loss": 0.0048, "step": 184370 }, { "epoch": 44.28, "learning_rate": 6.222994844485891e-05, "loss": 0.0042, "step": 184380 }, { "epoch": 44.28, "learning_rate": 6.222646787783696e-05, "loss": 0.0121, "step": 184390 }, { "epoch": 44.28, "learning_rate": 6.222298724779971e-05, "loss": 0.0072, "step": 184400 }, { "epoch": 44.28, "learning_rate": 6.221950655476505e-05, "loss": 0.0072, "step": 184410 }, { "epoch": 44.29, "learning_rate": 6.221602579875098e-05, "loss": 0.0075, "step": 184420 }, { "epoch": 44.29, "learning_rate": 6.22125449797754e-05, "loss": 0.0079, "step": 184430 }, { "epoch": 44.29, "learning_rate": 6.220906409785625e-05, "loss": 0.0083, "step": 184440 }, { "epoch": 44.29, "learning_rate": 6.22055831530115e-05, "loss": 0.012, "step": 184450 }, { "epoch": 44.29, "learning_rate": 6.220210214525907e-05, "loss": 0.0094, "step": 184460 }, { "epoch": 44.3, "learning_rate": 6.21986210746169e-05, "loss": 0.0087, "step": 184470 }, { "epoch": 44.3, "learning_rate": 6.219513994110293e-05, "loss": 0.0147, "step": 184480 }, { "epoch": 44.3, "learning_rate": 6.21916587447351e-05, "loss": 0.0067, "step": 184490 }, { "epoch": 44.3, "learning_rate": 6.218817748553138e-05, "loss": 0.0066, "step": 184500 }, { "epoch": 44.31, "learning_rate": 6.218469616350968e-05, "loss": 0.0088, "step": 184510 }, { "epoch": 44.31, "learning_rate": 6.218121477868795e-05, "loss": 0.009, "step": 184520 }, { "epoch": 44.31, "learning_rate": 6.217773333108416e-05, "loss": 0.0059, "step": 184530 }, { "epoch": 44.31, "learning_rate": 6.217425182071621e-05, "loss": 0.0052, "step": 184540 }, { "epoch": 44.31, "learning_rate": 6.217077024760206e-05, "loss": 0.0064, "step": 184550 }, { "epoch": 44.32, "learning_rate": 6.216728861175967e-05, "loss": 0.006, "step": 184560 }, { "epoch": 44.32, "learning_rate": 6.216380691320697e-05, "loss": 0.009, "step": 184570 }, { "epoch": 44.32, "learning_rate": 6.21603251519619e-05, "loss": 0.0073, "step": 184580 }, { "epoch": 44.32, "learning_rate": 6.215684332804241e-05, "loss": 0.0069, "step": 184590 }, { "epoch": 44.33, "learning_rate": 6.215336144146646e-05, "loss": 0.0125, "step": 184600 }, { "epoch": 44.33, "learning_rate": 6.214987949225198e-05, "loss": 0.0071, "step": 184610 }, { "epoch": 44.33, "learning_rate": 6.214639748041693e-05, "loss": 0.0113, "step": 184620 }, { "epoch": 44.33, "learning_rate": 6.214291540597922e-05, "loss": 0.0048, "step": 184630 }, { "epoch": 44.34, "learning_rate": 6.213943326895685e-05, "loss": 0.0098, "step": 184640 }, { "epoch": 44.34, "learning_rate": 6.213595106936772e-05, "loss": 0.0098, "step": 184650 }, { "epoch": 44.34, "learning_rate": 6.21324688072298e-05, "loss": 0.0221, "step": 184660 }, { "epoch": 44.34, "learning_rate": 6.212898648256106e-05, "loss": 0.0057, "step": 184670 }, { "epoch": 44.34, "learning_rate": 6.212550409537939e-05, "loss": 0.0083, "step": 184680 }, { "epoch": 44.35, "learning_rate": 6.21220216457028e-05, "loss": 0.0066, "step": 184690 }, { "epoch": 44.35, "learning_rate": 6.211853913354918e-05, "loss": 0.009, "step": 184700 }, { "epoch": 44.35, "learning_rate": 6.211505655893651e-05, "loss": 0.0138, "step": 184710 }, { "epoch": 44.35, "learning_rate": 6.211157392188274e-05, "loss": 0.0116, "step": 184720 }, { "epoch": 44.36, "learning_rate": 6.210809122240585e-05, "loss": 0.01, "step": 184730 }, { "epoch": 44.36, "learning_rate": 6.210460846052372e-05, "loss": 0.0104, "step": 184740 }, { "epoch": 44.36, "learning_rate": 6.210112563625434e-05, "loss": 0.0081, "step": 184750 }, { "epoch": 44.36, "learning_rate": 6.209764274961566e-05, "loss": 0.0113, "step": 184760 }, { "epoch": 44.37, "learning_rate": 6.209415980062563e-05, "loss": 0.0108, "step": 184770 }, { "epoch": 44.37, "learning_rate": 6.209067678930221e-05, "loss": 0.013, "step": 184780 }, { "epoch": 44.37, "learning_rate": 6.208719371566333e-05, "loss": 0.005, "step": 184790 }, { "epoch": 44.37, "learning_rate": 6.208371057972694e-05, "loss": 0.0229, "step": 184800 }, { "epoch": 44.37, "learning_rate": 6.208022738151104e-05, "loss": 0.0133, "step": 184810 }, { "epoch": 44.38, "learning_rate": 6.207674412103353e-05, "loss": 0.0064, "step": 184820 }, { "epoch": 44.38, "learning_rate": 6.207326079831238e-05, "loss": 0.0125, "step": 184830 }, { "epoch": 44.38, "learning_rate": 6.206977741336553e-05, "loss": 0.0102, "step": 184840 }, { "epoch": 44.38, "learning_rate": 6.206629396621095e-05, "loss": 0.0064, "step": 184850 }, { "epoch": 44.39, "learning_rate": 6.206281045686659e-05, "loss": 0.0072, "step": 184860 }, { "epoch": 44.39, "learning_rate": 6.205932688535041e-05, "loss": 0.0047, "step": 184870 }, { "epoch": 44.39, "learning_rate": 6.205584325168036e-05, "loss": 0.0104, "step": 184880 }, { "epoch": 44.39, "learning_rate": 6.205235955587438e-05, "loss": 0.0098, "step": 184890 }, { "epoch": 44.39, "learning_rate": 6.204887579795045e-05, "loss": 0.007, "step": 184900 }, { "epoch": 44.4, "learning_rate": 6.204539197792651e-05, "loss": 0.0119, "step": 184910 }, { "epoch": 44.4, "learning_rate": 6.204190809582053e-05, "loss": 0.0071, "step": 184920 }, { "epoch": 44.4, "learning_rate": 6.203842415165044e-05, "loss": 0.0123, "step": 184930 }, { "epoch": 44.4, "learning_rate": 6.203494014543422e-05, "loss": 0.0094, "step": 184940 }, { "epoch": 44.41, "learning_rate": 6.203145607718982e-05, "loss": 0.008, "step": 184950 }, { "epoch": 44.41, "learning_rate": 6.202797194693519e-05, "loss": 0.0095, "step": 184960 }, { "epoch": 44.41, "learning_rate": 6.20244877546883e-05, "loss": 0.0118, "step": 184970 }, { "epoch": 44.41, "learning_rate": 6.20210035004671e-05, "loss": 0.0085, "step": 184980 }, { "epoch": 44.42, "learning_rate": 6.201751918428953e-05, "loss": 0.0078, "step": 184990 }, { "epoch": 44.42, "learning_rate": 6.201403480617357e-05, "loss": 0.0192, "step": 185000 }, { "epoch": 44.42, "learning_rate": 6.201055036613718e-05, "loss": 0.0124, "step": 185010 }, { "epoch": 44.42, "learning_rate": 6.200706586419831e-05, "loss": 0.0049, "step": 185020 }, { "epoch": 44.42, "learning_rate": 6.200358130037492e-05, "loss": 0.0042, "step": 185030 }, { "epoch": 44.43, "learning_rate": 6.200009667468498e-05, "loss": 0.0049, "step": 185040 }, { "epoch": 44.43, "learning_rate": 6.199661198714643e-05, "loss": 0.0092, "step": 185050 }, { "epoch": 44.43, "learning_rate": 6.199312723777725e-05, "loss": 0.0053, "step": 185060 }, { "epoch": 44.43, "learning_rate": 6.198964242659539e-05, "loss": 0.0071, "step": 185070 }, { "epoch": 44.44, "learning_rate": 6.198615755361883e-05, "loss": 0.0064, "step": 185080 }, { "epoch": 44.44, "learning_rate": 6.198267261886549e-05, "loss": 0.0131, "step": 185090 }, { "epoch": 44.44, "learning_rate": 6.197918762235337e-05, "loss": 0.0054, "step": 185100 }, { "epoch": 44.44, "learning_rate": 6.197570256410042e-05, "loss": 0.0196, "step": 185110 }, { "epoch": 44.45, "learning_rate": 6.197221744412458e-05, "loss": 0.0089, "step": 185120 }, { "epoch": 44.45, "learning_rate": 6.196873226244384e-05, "loss": 0.0177, "step": 185130 }, { "epoch": 44.45, "learning_rate": 6.196524701907615e-05, "loss": 0.0087, "step": 185140 }, { "epoch": 44.45, "learning_rate": 6.196176171403948e-05, "loss": 0.0092, "step": 185150 }, { "epoch": 44.45, "learning_rate": 6.19582763473518e-05, "loss": 0.0057, "step": 185160 }, { "epoch": 44.46, "learning_rate": 6.195479091903104e-05, "loss": 0.0139, "step": 185170 }, { "epoch": 44.46, "learning_rate": 6.195130542909521e-05, "loss": 0.0063, "step": 185180 }, { "epoch": 44.46, "learning_rate": 6.194781987756224e-05, "loss": 0.0144, "step": 185190 }, { "epoch": 44.46, "learning_rate": 6.19443342644501e-05, "loss": 0.0073, "step": 185200 }, { "epoch": 44.47, "learning_rate": 6.194084858977678e-05, "loss": 0.0191, "step": 185210 }, { "epoch": 44.47, "learning_rate": 6.193736285356023e-05, "loss": 0.0108, "step": 185220 }, { "epoch": 44.47, "learning_rate": 6.193387705581838e-05, "loss": 0.0143, "step": 185230 }, { "epoch": 44.47, "learning_rate": 6.193039119656926e-05, "loss": 0.0084, "step": 185240 }, { "epoch": 44.47, "learning_rate": 6.192690527583081e-05, "loss": 0.0103, "step": 185250 }, { "epoch": 44.48, "learning_rate": 6.192341929362097e-05, "loss": 0.011, "step": 185260 }, { "epoch": 44.48, "learning_rate": 6.191993324995772e-05, "loss": 0.0044, "step": 185270 }, { "epoch": 44.48, "learning_rate": 6.191644714485904e-05, "loss": 0.0075, "step": 185280 }, { "epoch": 44.48, "learning_rate": 6.191296097834291e-05, "loss": 0.0155, "step": 185290 }, { "epoch": 44.49, "learning_rate": 6.190947475042725e-05, "loss": 0.0128, "step": 185300 }, { "epoch": 44.49, "learning_rate": 6.190598846113008e-05, "loss": 0.0057, "step": 185310 }, { "epoch": 44.49, "learning_rate": 6.190250211046934e-05, "loss": 0.0084, "step": 185320 }, { "epoch": 44.49, "learning_rate": 6.189901569846301e-05, "loss": 0.0125, "step": 185330 }, { "epoch": 44.5, "learning_rate": 6.189552922512903e-05, "loss": 0.0096, "step": 185340 }, { "epoch": 44.5, "learning_rate": 6.189204269048542e-05, "loss": 0.0079, "step": 185350 }, { "epoch": 44.5, "learning_rate": 6.188855609455012e-05, "loss": 0.0042, "step": 185360 }, { "epoch": 44.5, "learning_rate": 6.188506943734108e-05, "loss": 0.0073, "step": 185370 }, { "epoch": 44.5, "learning_rate": 6.188158271887632e-05, "loss": 0.0136, "step": 185380 }, { "epoch": 44.51, "learning_rate": 6.187809593917378e-05, "loss": 0.0107, "step": 185390 }, { "epoch": 44.51, "learning_rate": 6.187460909825142e-05, "loss": 0.008, "step": 185400 }, { "epoch": 44.51, "learning_rate": 6.187112219612723e-05, "loss": 0.0041, "step": 185410 }, { "epoch": 44.51, "learning_rate": 6.186763523281918e-05, "loss": 0.0088, "step": 185420 }, { "epoch": 44.52, "learning_rate": 6.186414820834524e-05, "loss": 0.0056, "step": 185430 }, { "epoch": 44.52, "learning_rate": 6.186066112272337e-05, "loss": 0.0095, "step": 185440 }, { "epoch": 44.52, "learning_rate": 6.185717397597156e-05, "loss": 0.0048, "step": 185450 }, { "epoch": 44.52, "learning_rate": 6.185368676810779e-05, "loss": 0.0076, "step": 185460 }, { "epoch": 44.53, "learning_rate": 6.185019949915001e-05, "loss": 0.0065, "step": 185470 }, { "epoch": 44.53, "learning_rate": 6.184671216911619e-05, "loss": 0.0282, "step": 185480 }, { "epoch": 44.53, "learning_rate": 6.184322477802432e-05, "loss": 0.0106, "step": 185490 }, { "epoch": 44.53, "learning_rate": 6.183973732589237e-05, "loss": 0.0167, "step": 185500 }, { "epoch": 44.53, "learning_rate": 6.183624981273833e-05, "loss": 0.0127, "step": 185510 }, { "epoch": 44.54, "learning_rate": 6.183276223858016e-05, "loss": 0.0201, "step": 185520 }, { "epoch": 44.54, "learning_rate": 6.182927460343582e-05, "loss": 0.0127, "step": 185530 }, { "epoch": 44.54, "learning_rate": 6.182578690732332e-05, "loss": 0.0138, "step": 185540 }, { "epoch": 44.54, "learning_rate": 6.18222991502606e-05, "loss": 0.0091, "step": 185550 }, { "epoch": 44.55, "learning_rate": 6.181881133226565e-05, "loss": 0.0243, "step": 185560 }, { "epoch": 44.55, "learning_rate": 6.181532345335644e-05, "loss": 0.0157, "step": 185570 }, { "epoch": 44.55, "learning_rate": 6.181183551355096e-05, "loss": 0.0146, "step": 185580 }, { "epoch": 44.55, "learning_rate": 6.18083475128672e-05, "loss": 0.0088, "step": 185590 }, { "epoch": 44.55, "learning_rate": 6.18048594513231e-05, "loss": 0.0196, "step": 185600 }, { "epoch": 44.56, "learning_rate": 6.180137132893666e-05, "loss": 0.014, "step": 185610 }, { "epoch": 44.56, "learning_rate": 6.179788314572585e-05, "loss": 0.0122, "step": 185620 }, { "epoch": 44.56, "learning_rate": 6.179439490170866e-05, "loss": 0.0156, "step": 185630 }, { "epoch": 44.56, "learning_rate": 6.179090659690305e-05, "loss": 0.0149, "step": 185640 }, { "epoch": 44.57, "learning_rate": 6.178741823132701e-05, "loss": 0.0165, "step": 185650 }, { "epoch": 44.57, "learning_rate": 6.178392980499851e-05, "loss": 0.0184, "step": 185660 }, { "epoch": 44.57, "learning_rate": 6.178044131793556e-05, "loss": 0.0086, "step": 185670 }, { "epoch": 44.57, "learning_rate": 6.177695277015612e-05, "loss": 0.0175, "step": 185680 }, { "epoch": 44.58, "learning_rate": 6.177346416167813e-05, "loss": 0.0134, "step": 185690 }, { "epoch": 44.58, "learning_rate": 6.176997549251964e-05, "loss": 0.015, "step": 185700 }, { "epoch": 44.58, "learning_rate": 6.176648676269858e-05, "loss": 0.0127, "step": 185710 }, { "epoch": 44.58, "learning_rate": 6.176299797223296e-05, "loss": 0.0152, "step": 185720 }, { "epoch": 44.58, "learning_rate": 6.175950912114074e-05, "loss": 0.022, "step": 185730 }, { "epoch": 44.59, "learning_rate": 6.175602020943994e-05, "loss": 0.015, "step": 185740 }, { "epoch": 44.59, "learning_rate": 6.17525312371485e-05, "loss": 0.0122, "step": 185750 }, { "epoch": 44.59, "learning_rate": 6.17490422042844e-05, "loss": 0.018, "step": 185760 }, { "epoch": 44.59, "learning_rate": 6.174555311086563e-05, "loss": 0.0114, "step": 185770 }, { "epoch": 44.6, "learning_rate": 6.174206395691021e-05, "loss": 0.0147, "step": 185780 }, { "epoch": 44.6, "learning_rate": 6.173857474243607e-05, "loss": 0.0084, "step": 185790 }, { "epoch": 44.6, "learning_rate": 6.173508546746122e-05, "loss": 0.0194, "step": 185800 }, { "epoch": 44.6, "learning_rate": 6.173159613200366e-05, "loss": 0.0155, "step": 185810 }, { "epoch": 44.61, "learning_rate": 6.172810673608136e-05, "loss": 0.0107, "step": 185820 }, { "epoch": 44.61, "learning_rate": 6.172461727971228e-05, "loss": 0.0228, "step": 185830 }, { "epoch": 44.61, "learning_rate": 6.172112776291444e-05, "loss": 0.0147, "step": 185840 }, { "epoch": 44.61, "learning_rate": 6.171763818570578e-05, "loss": 0.012, "step": 185850 }, { "epoch": 44.61, "learning_rate": 6.171414854810434e-05, "loss": 0.0116, "step": 185860 }, { "epoch": 44.62, "learning_rate": 6.171065885012808e-05, "loss": 0.0101, "step": 185870 }, { "epoch": 44.62, "learning_rate": 6.170716909179498e-05, "loss": 0.0124, "step": 185880 }, { "epoch": 44.62, "learning_rate": 6.170367927312304e-05, "loss": 0.0118, "step": 185890 }, { "epoch": 44.62, "learning_rate": 6.170018939413023e-05, "loss": 0.0127, "step": 185900 }, { "epoch": 44.63, "learning_rate": 6.169669945483455e-05, "loss": 0.0114, "step": 185910 }, { "epoch": 44.63, "learning_rate": 6.169320945525398e-05, "loss": 0.0073, "step": 185920 }, { "epoch": 44.63, "learning_rate": 6.168971939540653e-05, "loss": 0.0106, "step": 185930 }, { "epoch": 44.63, "learning_rate": 6.168622927531014e-05, "loss": 0.0209, "step": 185940 }, { "epoch": 44.63, "learning_rate": 6.168273909498282e-05, "loss": 0.0124, "step": 185950 }, { "epoch": 44.64, "learning_rate": 6.167924885444259e-05, "loss": 0.0111, "step": 185960 }, { "epoch": 44.64, "learning_rate": 6.167575855370742e-05, "loss": 0.0138, "step": 185970 }, { "epoch": 44.64, "learning_rate": 6.167226819279528e-05, "loss": 0.0148, "step": 185980 }, { "epoch": 44.64, "learning_rate": 6.166877777172417e-05, "loss": 0.0062, "step": 185990 }, { "epoch": 44.65, "learning_rate": 6.166528729051209e-05, "loss": 0.0107, "step": 186000 }, { "epoch": 44.65, "learning_rate": 6.1661796749177e-05, "loss": 0.0086, "step": 186010 }, { "epoch": 44.65, "learning_rate": 6.165830614773693e-05, "loss": 0.0147, "step": 186020 }, { "epoch": 44.65, "learning_rate": 6.165481548620987e-05, "loss": 0.012, "step": 186030 }, { "epoch": 44.66, "learning_rate": 6.165132476461377e-05, "loss": 0.0105, "step": 186040 }, { "epoch": 44.66, "learning_rate": 6.164783398296666e-05, "loss": 0.0204, "step": 186050 }, { "epoch": 44.66, "learning_rate": 6.164434314128648e-05, "loss": 0.0101, "step": 186060 }, { "epoch": 44.66, "learning_rate": 6.16408522395913e-05, "loss": 0.0156, "step": 186070 }, { "epoch": 44.66, "learning_rate": 6.163736127789906e-05, "loss": 0.0072, "step": 186080 }, { "epoch": 44.67, "learning_rate": 6.163387025622774e-05, "loss": 0.0105, "step": 186090 }, { "epoch": 44.67, "learning_rate": 6.163037917459537e-05, "loss": 0.0069, "step": 186100 }, { "epoch": 44.67, "learning_rate": 6.162688803301993e-05, "loss": 0.008, "step": 186110 }, { "epoch": 44.67, "learning_rate": 6.162339683151942e-05, "loss": 0.0108, "step": 186120 }, { "epoch": 44.68, "learning_rate": 6.161990557011181e-05, "loss": 0.014, "step": 186130 }, { "epoch": 44.68, "learning_rate": 6.161641424881513e-05, "loss": 0.0127, "step": 186140 }, { "epoch": 44.68, "learning_rate": 6.161292286764732e-05, "loss": 0.0359, "step": 186150 }, { "epoch": 44.68, "learning_rate": 6.160943142662644e-05, "loss": 0.0121, "step": 186160 }, { "epoch": 44.69, "learning_rate": 6.160593992577044e-05, "loss": 0.015, "step": 186170 }, { "epoch": 44.69, "learning_rate": 6.160244836509734e-05, "loss": 0.0087, "step": 186180 }, { "epoch": 44.69, "learning_rate": 6.159895674462512e-05, "loss": 0.0165, "step": 186190 }, { "epoch": 44.69, "learning_rate": 6.159546506437177e-05, "loss": 0.0078, "step": 186200 }, { "epoch": 44.69, "learning_rate": 6.159197332435532e-05, "loss": 0.0111, "step": 186210 }, { "epoch": 44.7, "learning_rate": 6.158848152459371e-05, "loss": 0.0071, "step": 186220 }, { "epoch": 44.7, "learning_rate": 6.158498966510499e-05, "loss": 0.007, "step": 186230 }, { "epoch": 44.7, "learning_rate": 6.158149774590712e-05, "loss": 0.0088, "step": 186240 }, { "epoch": 44.7, "learning_rate": 6.157800576701813e-05, "loss": 0.0055, "step": 186250 }, { "epoch": 44.71, "learning_rate": 6.157451372845599e-05, "loss": 0.0096, "step": 186260 }, { "epoch": 44.71, "learning_rate": 6.157102163023871e-05, "loss": 0.009, "step": 186270 }, { "epoch": 44.71, "learning_rate": 6.15675294723843e-05, "loss": 0.0119, "step": 186280 }, { "epoch": 44.71, "learning_rate": 6.156403725491074e-05, "loss": 0.0114, "step": 186290 }, { "epoch": 44.71, "learning_rate": 6.156054497783604e-05, "loss": 0.0076, "step": 186300 }, { "epoch": 44.72, "learning_rate": 6.155705264117818e-05, "loss": 0.0089, "step": 186310 }, { "epoch": 44.72, "learning_rate": 6.15535602449552e-05, "loss": 0.0092, "step": 186320 }, { "epoch": 44.72, "learning_rate": 6.155006778918505e-05, "loss": 0.0058, "step": 186330 }, { "epoch": 44.72, "learning_rate": 6.154657527388576e-05, "loss": 0.0097, "step": 186340 }, { "epoch": 44.73, "learning_rate": 6.154308269907533e-05, "loss": 0.0355, "step": 186350 }, { "epoch": 44.73, "learning_rate": 6.153959006477175e-05, "loss": 0.0091, "step": 186360 }, { "epoch": 44.73, "learning_rate": 6.153609737099301e-05, "loss": 0.0099, "step": 186370 }, { "epoch": 44.73, "learning_rate": 6.153260461775717e-05, "loss": 0.0061, "step": 186380 }, { "epoch": 44.74, "learning_rate": 6.152911180508215e-05, "loss": 0.0159, "step": 186390 }, { "epoch": 44.74, "learning_rate": 6.1525618932986e-05, "loss": 0.0099, "step": 186400 }, { "epoch": 44.74, "learning_rate": 6.152212600148672e-05, "loss": 0.0078, "step": 186410 }, { "epoch": 44.74, "learning_rate": 6.151863301060231e-05, "loss": 0.0079, "step": 186420 }, { "epoch": 44.74, "learning_rate": 6.151513996035076e-05, "loss": 0.0102, "step": 186430 }, { "epoch": 44.75, "learning_rate": 6.151164685075009e-05, "loss": 0.0182, "step": 186440 }, { "epoch": 44.75, "learning_rate": 6.15081536818183e-05, "loss": 0.0333, "step": 186450 }, { "epoch": 44.75, "learning_rate": 6.150466045357338e-05, "loss": 0.0086, "step": 186460 }, { "epoch": 44.75, "learning_rate": 6.150116716603335e-05, "loss": 0.0068, "step": 186470 }, { "epoch": 44.76, "learning_rate": 6.14976738192162e-05, "loss": 0.0102, "step": 186480 }, { "epoch": 44.76, "learning_rate": 6.149418041313996e-05, "loss": 0.0075, "step": 186490 }, { "epoch": 44.76, "learning_rate": 6.149068694782261e-05, "loss": 0.0135, "step": 186500 }, { "epoch": 44.76, "learning_rate": 6.148719342328215e-05, "loss": 0.0196, "step": 186510 }, { "epoch": 44.77, "learning_rate": 6.148369983953662e-05, "loss": 0.0146, "step": 186520 }, { "epoch": 44.77, "learning_rate": 6.148020619660398e-05, "loss": 0.0131, "step": 186530 }, { "epoch": 44.77, "learning_rate": 6.147671249450227e-05, "loss": 0.0118, "step": 186540 }, { "epoch": 44.77, "learning_rate": 6.14732187332495e-05, "loss": 0.0158, "step": 186550 }, { "epoch": 44.77, "learning_rate": 6.146972491286365e-05, "loss": 0.013, "step": 186560 }, { "epoch": 44.78, "learning_rate": 6.146623103336275e-05, "loss": 0.0093, "step": 186570 }, { "epoch": 44.78, "learning_rate": 6.146273709476481e-05, "loss": 0.008, "step": 186580 }, { "epoch": 44.78, "learning_rate": 6.145924309708781e-05, "loss": 0.0068, "step": 186590 }, { "epoch": 44.78, "learning_rate": 6.145574904034979e-05, "loss": 0.0069, "step": 186600 }, { "epoch": 44.79, "learning_rate": 6.145225492456874e-05, "loss": 0.0216, "step": 186610 }, { "epoch": 44.79, "learning_rate": 6.144876074976266e-05, "loss": 0.0139, "step": 186620 }, { "epoch": 44.79, "learning_rate": 6.144526651594959e-05, "loss": 0.0114, "step": 186630 }, { "epoch": 44.79, "learning_rate": 6.144177222314751e-05, "loss": 0.0103, "step": 186640 }, { "epoch": 44.79, "learning_rate": 6.143827787137443e-05, "loss": 0.0092, "step": 186650 }, { "epoch": 44.8, "learning_rate": 6.143478346064838e-05, "loss": 0.0054, "step": 186660 }, { "epoch": 44.8, "learning_rate": 6.143128899098737e-05, "loss": 0.0088, "step": 186670 }, { "epoch": 44.8, "learning_rate": 6.142779446240939e-05, "loss": 0.0109, "step": 186680 }, { "epoch": 44.8, "learning_rate": 6.142429987493246e-05, "loss": 0.0067, "step": 186690 }, { "epoch": 44.81, "learning_rate": 6.142080522857459e-05, "loss": 0.0154, "step": 186700 }, { "epoch": 44.81, "learning_rate": 6.141731052335381e-05, "loss": 0.0089, "step": 186710 }, { "epoch": 44.81, "learning_rate": 6.141381575928811e-05, "loss": 0.0084, "step": 186720 }, { "epoch": 44.81, "learning_rate": 6.14103209363955e-05, "loss": 0.008, "step": 186730 }, { "epoch": 44.82, "learning_rate": 6.1406826054694e-05, "loss": 0.0064, "step": 186740 }, { "epoch": 44.82, "learning_rate": 6.140333111420164e-05, "loss": 0.0093, "step": 186750 }, { "epoch": 44.82, "learning_rate": 6.13998361149364e-05, "loss": 0.0085, "step": 186760 }, { "epoch": 44.82, "learning_rate": 6.139634105691632e-05, "loss": 0.0119, "step": 186770 }, { "epoch": 44.82, "learning_rate": 6.139284594015939e-05, "loss": 0.0072, "step": 186780 }, { "epoch": 44.83, "learning_rate": 6.138935076468365e-05, "loss": 0.0106, "step": 186790 }, { "epoch": 44.83, "learning_rate": 6.13858555305071e-05, "loss": 0.0073, "step": 186800 }, { "epoch": 44.83, "learning_rate": 6.138236023764774e-05, "loss": 0.0134, "step": 186810 }, { "epoch": 44.83, "learning_rate": 6.137886488612364e-05, "loss": 0.0056, "step": 186820 }, { "epoch": 44.84, "learning_rate": 6.137536947595272e-05, "loss": 0.0068, "step": 186830 }, { "epoch": 44.84, "learning_rate": 6.137187400715307e-05, "loss": 0.0096, "step": 186840 }, { "epoch": 44.84, "learning_rate": 6.13683784797427e-05, "loss": 0.0118, "step": 186850 }, { "epoch": 44.84, "learning_rate": 6.136488289373961e-05, "loss": 0.0067, "step": 186860 }, { "epoch": 44.85, "learning_rate": 6.136138724916181e-05, "loss": 0.0117, "step": 186870 }, { "epoch": 44.85, "learning_rate": 6.135789154602733e-05, "loss": 0.0096, "step": 186880 }, { "epoch": 44.85, "learning_rate": 6.135439578435418e-05, "loss": 0.0075, "step": 186890 }, { "epoch": 44.85, "learning_rate": 6.135089996416039e-05, "loss": 0.007, "step": 186900 }, { "epoch": 44.85, "learning_rate": 6.134740408546395e-05, "loss": 0.0079, "step": 186910 }, { "epoch": 44.86, "learning_rate": 6.13439081482829e-05, "loss": 0.0072, "step": 186920 }, { "epoch": 44.86, "learning_rate": 6.134041215263527e-05, "loss": 0.0084, "step": 186930 }, { "epoch": 44.86, "learning_rate": 6.133691609853904e-05, "loss": 0.0088, "step": 186940 }, { "epoch": 44.86, "learning_rate": 6.133341998601225e-05, "loss": 0.0085, "step": 186950 }, { "epoch": 44.87, "learning_rate": 6.132992381507292e-05, "loss": 0.0129, "step": 186960 }, { "epoch": 44.87, "learning_rate": 6.132642758573908e-05, "loss": 0.0055, "step": 186970 }, { "epoch": 44.87, "learning_rate": 6.132293129802873e-05, "loss": 0.0109, "step": 186980 }, { "epoch": 44.87, "learning_rate": 6.131943495195989e-05, "loss": 0.0122, "step": 186990 }, { "epoch": 44.87, "learning_rate": 6.13159385475506e-05, "loss": 0.0137, "step": 187000 }, { "epoch": 44.88, "learning_rate": 6.131244208481885e-05, "loss": 0.0082, "step": 187010 }, { "epoch": 44.88, "learning_rate": 6.13089455637827e-05, "loss": 0.0091, "step": 187020 }, { "epoch": 44.88, "learning_rate": 6.130544898446014e-05, "loss": 0.0105, "step": 187030 }, { "epoch": 44.88, "learning_rate": 6.130195234686921e-05, "loss": 0.0119, "step": 187040 }, { "epoch": 44.89, "learning_rate": 6.12984556510279e-05, "loss": 0.01, "step": 187050 }, { "epoch": 44.89, "learning_rate": 6.129495889695428e-05, "loss": 0.0069, "step": 187060 }, { "epoch": 44.89, "learning_rate": 6.129146208466634e-05, "loss": 0.0121, "step": 187070 }, { "epoch": 44.89, "learning_rate": 6.128796521418211e-05, "loss": 0.0069, "step": 187080 }, { "epoch": 44.9, "learning_rate": 6.12844682855196e-05, "loss": 0.0081, "step": 187090 }, { "epoch": 44.9, "learning_rate": 6.128097129869686e-05, "loss": 0.0107, "step": 187100 }, { "epoch": 44.9, "learning_rate": 6.127747425373191e-05, "loss": 0.0101, "step": 187110 }, { "epoch": 44.9, "learning_rate": 6.127397715064274e-05, "loss": 0.0093, "step": 187120 }, { "epoch": 44.9, "learning_rate": 6.127047998944741e-05, "loss": 0.0103, "step": 187130 }, { "epoch": 44.91, "learning_rate": 6.126698277016393e-05, "loss": 0.01, "step": 187140 }, { "epoch": 44.91, "learning_rate": 6.126348549281033e-05, "loss": 0.0136, "step": 187150 }, { "epoch": 44.91, "learning_rate": 6.125998815740461e-05, "loss": 0.0099, "step": 187160 }, { "epoch": 44.91, "learning_rate": 6.125649076396485e-05, "loss": 0.005, "step": 187170 }, { "epoch": 44.92, "learning_rate": 6.125299331250903e-05, "loss": 0.0102, "step": 187180 }, { "epoch": 44.92, "learning_rate": 6.12494958030552e-05, "loss": 0.0106, "step": 187190 }, { "epoch": 44.92, "learning_rate": 6.124599823562135e-05, "loss": 0.0134, "step": 187200 }, { "epoch": 44.92, "learning_rate": 6.124250061022554e-05, "loss": 0.0074, "step": 187210 }, { "epoch": 44.93, "learning_rate": 6.123900292688579e-05, "loss": 0.0085, "step": 187220 }, { "epoch": 44.93, "learning_rate": 6.123550518562012e-05, "loss": 0.0069, "step": 187230 }, { "epoch": 44.93, "learning_rate": 6.123200738644657e-05, "loss": 0.0075, "step": 187240 }, { "epoch": 44.93, "learning_rate": 6.122850952938315e-05, "loss": 0.0067, "step": 187250 }, { "epoch": 44.93, "learning_rate": 6.122501161444791e-05, "loss": 0.0186, "step": 187260 }, { "epoch": 44.94, "learning_rate": 6.122151364165887e-05, "loss": 0.0181, "step": 187270 }, { "epoch": 44.94, "learning_rate": 6.121801561103404e-05, "loss": 0.0503, "step": 187280 }, { "epoch": 44.94, "learning_rate": 6.121451752259147e-05, "loss": 0.0102, "step": 187290 }, { "epoch": 44.94, "learning_rate": 6.121101937634919e-05, "loss": 0.0123, "step": 187300 }, { "epoch": 44.95, "learning_rate": 6.12075211723252e-05, "loss": 0.0057, "step": 187310 }, { "epoch": 44.95, "learning_rate": 6.120402291053757e-05, "loss": 0.0053, "step": 187320 }, { "epoch": 44.95, "learning_rate": 6.120052459100431e-05, "loss": 0.0143, "step": 187330 }, { "epoch": 45.0, "learning_rate": 6.119702621374346e-05, "loss": 0.008, "step": 187340 }, { "epoch": 45.0, "learning_rate": 6.119352777877303e-05, "loss": 0.0145, "step": 187350 }, { "epoch": 45.01, "learning_rate": 6.119002928611107e-05, "loss": 0.0222, "step": 187360 }, { "epoch": 45.01, "learning_rate": 6.11865307357756e-05, "loss": 0.0065, "step": 187370 }, { "epoch": 45.01, "learning_rate": 6.118303212778467e-05, "loss": 0.0058, "step": 187380 }, { "epoch": 45.01, "learning_rate": 6.117953346215629e-05, "loss": 0.0148, "step": 187390 }, { "epoch": 45.01, "learning_rate": 6.117603473890851e-05, "loss": 0.0055, "step": 187400 }, { "epoch": 45.02, "learning_rate": 6.117253595805935e-05, "loss": 0.0078, "step": 187410 }, { "epoch": 45.02, "learning_rate": 6.116903711962684e-05, "loss": 0.0077, "step": 187420 }, { "epoch": 45.02, "learning_rate": 6.116553822362902e-05, "loss": 0.0213, "step": 187430 }, { "epoch": 45.02, "learning_rate": 6.116203927008392e-05, "loss": 0.0058, "step": 187440 }, { "epoch": 45.03, "learning_rate": 6.11585402590096e-05, "loss": 0.0056, "step": 187450 }, { "epoch": 45.03, "learning_rate": 6.115504119042402e-05, "loss": 0.0067, "step": 187460 }, { "epoch": 45.03, "learning_rate": 6.115154206434531e-05, "loss": 0.0061, "step": 187470 }, { "epoch": 45.03, "learning_rate": 6.114804288079145e-05, "loss": 0.0111, "step": 187480 }, { "epoch": 45.04, "learning_rate": 6.114454363978047e-05, "loss": 0.0166, "step": 187490 }, { "epoch": 45.04, "learning_rate": 6.114104434133043e-05, "loss": 0.0136, "step": 187500 }, { "epoch": 45.04, "learning_rate": 6.113754498545934e-05, "loss": 0.0063, "step": 187510 }, { "epoch": 45.04, "learning_rate": 6.113404557218527e-05, "loss": 0.0102, "step": 187520 }, { "epoch": 45.04, "learning_rate": 6.113054610152623e-05, "loss": 0.0266, "step": 187530 }, { "epoch": 45.05, "learning_rate": 6.112704657350026e-05, "loss": 0.016, "step": 187540 }, { "epoch": 45.05, "learning_rate": 6.11235469881254e-05, "loss": 0.0067, "step": 187550 }, { "epoch": 45.05, "learning_rate": 6.11200473454197e-05, "loss": 0.0209, "step": 187560 }, { "epoch": 45.05, "learning_rate": 6.111654764540116e-05, "loss": 0.0084, "step": 187570 }, { "epoch": 45.06, "learning_rate": 6.111304788808785e-05, "loss": 0.0146, "step": 187580 }, { "epoch": 45.06, "learning_rate": 6.110954807349779e-05, "loss": 0.0077, "step": 187590 }, { "epoch": 45.06, "learning_rate": 6.110604820164903e-05, "loss": 0.007, "step": 187600 }, { "epoch": 45.06, "learning_rate": 6.110254827255961e-05, "loss": 0.0063, "step": 187610 }, { "epoch": 45.07, "learning_rate": 6.109904828624756e-05, "loss": 0.0048, "step": 187620 }, { "epoch": 45.07, "learning_rate": 6.109554824273093e-05, "loss": 0.014, "step": 187630 }, { "epoch": 45.07, "learning_rate": 6.109204814202774e-05, "loss": 0.0058, "step": 187640 }, { "epoch": 45.07, "learning_rate": 6.108854798415604e-05, "loss": 0.0092, "step": 187650 }, { "epoch": 45.07, "learning_rate": 6.108504776913388e-05, "loss": 0.0126, "step": 187660 }, { "epoch": 45.08, "learning_rate": 6.108154749697929e-05, "loss": 0.0078, "step": 187670 }, { "epoch": 45.08, "learning_rate": 6.10780471677103e-05, "loss": 0.007, "step": 187680 }, { "epoch": 45.08, "learning_rate": 6.107454678134499e-05, "loss": 0.0059, "step": 187690 }, { "epoch": 45.08, "learning_rate": 6.107104633790136e-05, "loss": 0.0064, "step": 187700 }, { "epoch": 45.09, "learning_rate": 6.106754583739746e-05, "loss": 0.0194, "step": 187710 }, { "epoch": 45.09, "learning_rate": 6.106404527985133e-05, "loss": 0.0114, "step": 187720 }, { "epoch": 45.09, "learning_rate": 6.106054466528103e-05, "loss": 0.0057, "step": 187730 }, { "epoch": 45.09, "learning_rate": 6.105704399370458e-05, "loss": 0.0051, "step": 187740 }, { "epoch": 45.09, "learning_rate": 6.105354326514004e-05, "loss": 0.0097, "step": 187750 }, { "epoch": 45.1, "learning_rate": 6.105004247960544e-05, "loss": 0.0075, "step": 187760 }, { "epoch": 45.1, "learning_rate": 6.104654163711882e-05, "loss": 0.0107, "step": 187770 }, { "epoch": 45.1, "learning_rate": 6.104304073769825e-05, "loss": 0.0309, "step": 187780 }, { "epoch": 45.1, "learning_rate": 6.103953978136175e-05, "loss": 0.0134, "step": 187790 }, { "epoch": 45.11, "learning_rate": 6.103603876812737e-05, "loss": 0.0069, "step": 187800 }, { "epoch": 45.11, "learning_rate": 6.103253769801316e-05, "loss": 0.0049, "step": 187810 }, { "epoch": 45.11, "learning_rate": 6.102903657103715e-05, "loss": 0.0076, "step": 187820 }, { "epoch": 45.11, "learning_rate": 6.10255353872174e-05, "loss": 0.0065, "step": 187830 }, { "epoch": 45.12, "learning_rate": 6.102203414657195e-05, "loss": 0.0062, "step": 187840 }, { "epoch": 45.12, "learning_rate": 6.101853284911882e-05, "loss": 0.0085, "step": 187850 }, { "epoch": 45.12, "learning_rate": 6.101503149487611e-05, "loss": 0.0093, "step": 187860 }, { "epoch": 45.12, "learning_rate": 6.1011530083861824e-05, "loss": 0.0055, "step": 187870 }, { "epoch": 45.12, "learning_rate": 6.1008028616094015e-05, "loss": 0.0082, "step": 187880 }, { "epoch": 45.13, "learning_rate": 6.100452709159073e-05, "loss": 0.0172, "step": 187890 }, { "epoch": 45.13, "learning_rate": 6.1001025510370035e-05, "loss": 0.0049, "step": 187900 }, { "epoch": 45.13, "learning_rate": 6.0997523872449956e-05, "loss": 0.0088, "step": 187910 }, { "epoch": 45.13, "learning_rate": 6.099402217784854e-05, "loss": 0.0112, "step": 187920 }, { "epoch": 45.14, "learning_rate": 6.099052042658385e-05, "loss": 0.0063, "step": 187930 }, { "epoch": 45.14, "learning_rate": 6.098701861867393e-05, "loss": 0.0082, "step": 187940 }, { "epoch": 45.14, "learning_rate": 6.098351675413682e-05, "loss": 0.0124, "step": 187950 }, { "epoch": 45.14, "learning_rate": 6.098001483299057e-05, "loss": 0.0095, "step": 187960 }, { "epoch": 45.15, "learning_rate": 6.097651285525324e-05, "loss": 0.0065, "step": 187970 }, { "epoch": 45.15, "learning_rate": 6.097301082094286e-05, "loss": 0.011, "step": 187980 }, { "epoch": 45.15, "learning_rate": 6.09695087300775e-05, "loss": 0.0152, "step": 187990 }, { "epoch": 45.15, "learning_rate": 6.096600658267519e-05, "loss": 0.0066, "step": 188000 }, { "epoch": 45.15, "learning_rate": 6.0962504378754e-05, "loss": 0.0133, "step": 188010 }, { "epoch": 45.16, "learning_rate": 6.095900211833196e-05, "loss": 0.0173, "step": 188020 }, { "epoch": 45.16, "learning_rate": 6.095549980142714e-05, "loss": 0.0121, "step": 188030 }, { "epoch": 45.16, "learning_rate": 6.095199742805758e-05, "loss": 0.0159, "step": 188040 }, { "epoch": 45.16, "learning_rate": 6.094849499824134e-05, "loss": 0.0067, "step": 188050 }, { "epoch": 45.17, "learning_rate": 6.0944992511996456e-05, "loss": 0.0061, "step": 188060 }, { "epoch": 45.17, "learning_rate": 6.094148996934099e-05, "loss": 0.0042, "step": 188070 }, { "epoch": 45.17, "learning_rate": 6.0937987370293005e-05, "loss": 0.0079, "step": 188080 }, { "epoch": 45.17, "learning_rate": 6.093448471487053e-05, "loss": 0.0105, "step": 188090 }, { "epoch": 45.17, "learning_rate": 6.093098200309163e-05, "loss": 0.0078, "step": 188100 }, { "epoch": 45.18, "learning_rate": 6.092747923497436e-05, "loss": 0.0068, "step": 188110 }, { "epoch": 45.18, "learning_rate": 6.0923976410536774e-05, "loss": 0.0119, "step": 188120 }, { "epoch": 45.18, "learning_rate": 6.0920473529796916e-05, "loss": 0.0132, "step": 188130 }, { "epoch": 45.18, "learning_rate": 6.091697059277285e-05, "loss": 0.0156, "step": 188140 }, { "epoch": 45.19, "learning_rate": 6.0913467599482624e-05, "loss": 0.0076, "step": 188150 }, { "epoch": 45.19, "learning_rate": 6.09099645499443e-05, "loss": 0.0046, "step": 188160 }, { "epoch": 45.19, "learning_rate": 6.090646144417592e-05, "loss": 0.0136, "step": 188170 }, { "epoch": 45.19, "learning_rate": 6.0902958282195546e-05, "loss": 0.0065, "step": 188180 }, { "epoch": 45.2, "learning_rate": 6.0899455064021236e-05, "loss": 0.0076, "step": 188190 }, { "epoch": 45.2, "learning_rate": 6.089595178967104e-05, "loss": 0.0077, "step": 188200 }, { "epoch": 45.2, "learning_rate": 6.089244845916303e-05, "loss": 0.0125, "step": 188210 }, { "epoch": 45.2, "learning_rate": 6.0888945072515245e-05, "loss": 0.0072, "step": 188220 }, { "epoch": 45.2, "learning_rate": 6.0885441629745744e-05, "loss": 0.0069, "step": 188230 }, { "epoch": 45.21, "learning_rate": 6.088193813087258e-05, "loss": 0.0157, "step": 188240 }, { "epoch": 45.21, "learning_rate": 6.0878434575913824e-05, "loss": 0.0156, "step": 188250 }, { "epoch": 45.21, "learning_rate": 6.087493096488753e-05, "loss": 0.0073, "step": 188260 }, { "epoch": 45.21, "learning_rate": 6.0871427297811745e-05, "loss": 0.0207, "step": 188270 }, { "epoch": 45.22, "learning_rate": 6.086792357470452e-05, "loss": 0.008, "step": 188280 }, { "epoch": 45.22, "learning_rate": 6.086441979558394e-05, "loss": 0.009, "step": 188290 }, { "epoch": 45.22, "learning_rate": 6.0860915960468046e-05, "loss": 0.0109, "step": 188300 }, { "epoch": 45.22, "learning_rate": 6.0857412069374896e-05, "loss": 0.0074, "step": 188310 }, { "epoch": 45.23, "learning_rate": 6.085390812232257e-05, "loss": 0.0058, "step": 188320 }, { "epoch": 45.23, "learning_rate": 6.085040411932911e-05, "loss": 0.0088, "step": 188330 }, { "epoch": 45.23, "learning_rate": 6.084690006041256e-05, "loss": 0.0046, "step": 188340 }, { "epoch": 45.23, "learning_rate": 6.0843395945590984e-05, "loss": 0.008, "step": 188350 }, { "epoch": 45.23, "learning_rate": 6.083989177488247e-05, "loss": 0.0041, "step": 188360 }, { "epoch": 45.24, "learning_rate": 6.083638754830507e-05, "loss": 0.006, "step": 188370 }, { "epoch": 45.24, "learning_rate": 6.083288326587684e-05, "loss": 0.0147, "step": 188380 }, { "epoch": 45.24, "learning_rate": 6.082937892761583e-05, "loss": 0.0052, "step": 188390 }, { "epoch": 45.24, "learning_rate": 6.0825874533540116e-05, "loss": 0.0068, "step": 188400 }, { "epoch": 45.25, "learning_rate": 6.082237008366776e-05, "loss": 0.006, "step": 188410 }, { "epoch": 45.25, "learning_rate": 6.081886557801681e-05, "loss": 0.0104, "step": 188420 }, { "epoch": 45.25, "learning_rate": 6.081536101660533e-05, "loss": 0.0071, "step": 188430 }, { "epoch": 45.25, "learning_rate": 6.081185639945139e-05, "loss": 0.0058, "step": 188440 }, { "epoch": 45.25, "learning_rate": 6.080835172657306e-05, "loss": 0.0063, "step": 188450 }, { "epoch": 45.26, "learning_rate": 6.08048469979884e-05, "loss": 0.0064, "step": 188460 }, { "epoch": 45.26, "learning_rate": 6.080134221371545e-05, "loss": 0.0084, "step": 188470 }, { "epoch": 45.26, "learning_rate": 6.079783737377231e-05, "loss": 0.0053, "step": 188480 }, { "epoch": 45.26, "learning_rate": 6.079433247817702e-05, "loss": 0.0098, "step": 188490 }, { "epoch": 45.27, "learning_rate": 6.079082752694765e-05, "loss": 0.0112, "step": 188500 }, { "epoch": 45.27, "learning_rate": 6.078732252010225e-05, "loss": 0.0072, "step": 188510 }, { "epoch": 45.27, "learning_rate": 6.078381745765891e-05, "loss": 0.0072, "step": 188520 }, { "epoch": 45.27, "learning_rate": 6.078031233963569e-05, "loss": 0.0191, "step": 188530 }, { "epoch": 45.28, "learning_rate": 6.077680716605064e-05, "loss": 0.0119, "step": 188540 }, { "epoch": 45.28, "learning_rate": 6.077330193692186e-05, "loss": 0.0075, "step": 188550 }, { "epoch": 45.28, "learning_rate": 6.0769796652267375e-05, "loss": 0.0072, "step": 188560 }, { "epoch": 45.28, "learning_rate": 6.0766291312105264e-05, "loss": 0.0056, "step": 188570 }, { "epoch": 45.28, "learning_rate": 6.07627859164536e-05, "loss": 0.0096, "step": 188580 }, { "epoch": 45.29, "learning_rate": 6.075928046533045e-05, "loss": 0.0064, "step": 188590 }, { "epoch": 45.29, "learning_rate": 6.0755774958753877e-05, "loss": 0.0123, "step": 188600 }, { "epoch": 45.29, "learning_rate": 6.0752269396741945e-05, "loss": 0.0044, "step": 188610 }, { "epoch": 45.29, "learning_rate": 6.074876377931275e-05, "loss": 0.0134, "step": 188620 }, { "epoch": 45.3, "learning_rate": 6.0745258106484314e-05, "loss": 0.0052, "step": 188630 }, { "epoch": 45.3, "learning_rate": 6.074175237827473e-05, "loss": 0.008, "step": 188640 }, { "epoch": 45.3, "learning_rate": 6.073824659470206e-05, "loss": 0.0134, "step": 188650 }, { "epoch": 45.3, "learning_rate": 6.073474075578438e-05, "loss": 0.0051, "step": 188660 }, { "epoch": 45.31, "learning_rate": 6.0731234861539754e-05, "loss": 0.0051, "step": 188670 }, { "epoch": 45.31, "learning_rate": 6.072772891198626e-05, "loss": 0.0107, "step": 188680 }, { "epoch": 45.31, "learning_rate": 6.072422290714197e-05, "loss": 0.0189, "step": 188690 }, { "epoch": 45.31, "learning_rate": 6.072071684702494e-05, "loss": 0.0139, "step": 188700 }, { "epoch": 45.31, "learning_rate": 6.071721073165324e-05, "loss": 0.0056, "step": 188710 }, { "epoch": 45.32, "learning_rate": 6.071370456104495e-05, "loss": 0.0064, "step": 188720 }, { "epoch": 45.32, "learning_rate": 6.0710198335218135e-05, "loss": 0.0099, "step": 188730 }, { "epoch": 45.32, "learning_rate": 6.0706692054190875e-05, "loss": 0.0144, "step": 188740 }, { "epoch": 45.32, "learning_rate": 6.070318571798123e-05, "loss": 0.0086, "step": 188750 }, { "epoch": 45.33, "learning_rate": 6.0699679326607285e-05, "loss": 0.0054, "step": 188760 }, { "epoch": 45.33, "learning_rate": 6.069617288008709e-05, "loss": 0.0098, "step": 188770 }, { "epoch": 45.33, "learning_rate": 6.069266637843873e-05, "loss": 0.0084, "step": 188780 }, { "epoch": 45.33, "learning_rate": 6.0689159821680285e-05, "loss": 0.0095, "step": 188790 }, { "epoch": 45.33, "learning_rate": 6.068565320982982e-05, "loss": 0.0073, "step": 188800 }, { "epoch": 45.34, "learning_rate": 6.068214654290541e-05, "loss": 0.0081, "step": 188810 }, { "epoch": 45.34, "learning_rate": 6.067863982092511e-05, "loss": 0.0084, "step": 188820 }, { "epoch": 45.34, "learning_rate": 6.067513304390704e-05, "loss": 0.008, "step": 188830 }, { "epoch": 45.34, "learning_rate": 6.067162621186923e-05, "loss": 0.0109, "step": 188840 }, { "epoch": 45.35, "learning_rate": 6.0668119324829764e-05, "loss": 0.0125, "step": 188850 }, { "epoch": 45.35, "learning_rate": 6.066461238280673e-05, "loss": 0.0049, "step": 188860 }, { "epoch": 45.35, "learning_rate": 6.0661105385818196e-05, "loss": 0.0164, "step": 188870 }, { "epoch": 45.35, "learning_rate": 6.065759833388223e-05, "loss": 0.0138, "step": 188880 }, { "epoch": 45.36, "learning_rate": 6.065409122701692e-05, "loss": 0.0116, "step": 188890 }, { "epoch": 45.36, "learning_rate": 6.065058406524032e-05, "loss": 0.0138, "step": 188900 }, { "epoch": 45.36, "learning_rate": 6.064707684857055e-05, "loss": 0.0087, "step": 188910 }, { "epoch": 45.36, "learning_rate": 6.0643569577025635e-05, "loss": 0.0087, "step": 188920 }, { "epoch": 45.36, "learning_rate": 6.064006225062368e-05, "loss": 0.0058, "step": 188930 }, { "epoch": 45.37, "learning_rate": 6.063655486938275e-05, "loss": 0.0155, "step": 188940 }, { "epoch": 45.37, "learning_rate": 6.063304743332092e-05, "loss": 0.0065, "step": 188950 }, { "epoch": 45.37, "learning_rate": 6.062953994245629e-05, "loss": 0.0107, "step": 188960 }, { "epoch": 45.37, "learning_rate": 6.062603239680691e-05, "loss": 0.0062, "step": 188970 }, { "epoch": 45.38, "learning_rate": 6.062252479639088e-05, "loss": 0.0069, "step": 188980 }, { "epoch": 45.38, "learning_rate": 6.061901714122627e-05, "loss": 0.0089, "step": 188990 }, { "epoch": 45.38, "learning_rate": 6.061550943133114e-05, "loss": 0.0056, "step": 189000 }, { "epoch": 45.38, "learning_rate": 6.0612001666723605e-05, "loss": 0.0044, "step": 189010 }, { "epoch": 45.39, "learning_rate": 6.060849384742171e-05, "loss": 0.0117, "step": 189020 }, { "epoch": 45.39, "learning_rate": 6.060498597344356e-05, "loss": 0.0058, "step": 189030 }, { "epoch": 45.39, "learning_rate": 6.0601478044807215e-05, "loss": 0.0109, "step": 189040 }, { "epoch": 45.39, "learning_rate": 6.059797006153079e-05, "loss": 0.0165, "step": 189050 }, { "epoch": 45.39, "learning_rate": 6.05944620236323e-05, "loss": 0.0283, "step": 189060 }, { "epoch": 45.4, "learning_rate": 6.059095393112989e-05, "loss": 0.0049, "step": 189070 }, { "epoch": 45.4, "learning_rate": 6.0587445784041606e-05, "loss": 0.0089, "step": 189080 }, { "epoch": 45.4, "learning_rate": 6.058393758238554e-05, "loss": 0.0069, "step": 189090 }, { "epoch": 45.4, "learning_rate": 6.058042932617976e-05, "loss": 0.0068, "step": 189100 }, { "epoch": 45.41, "learning_rate": 6.057692101544237e-05, "loss": 0.0096, "step": 189110 }, { "epoch": 45.41, "learning_rate": 6.057341265019144e-05, "loss": 0.0108, "step": 189120 }, { "epoch": 45.41, "learning_rate": 6.056990423044505e-05, "loss": 0.0053, "step": 189130 }, { "epoch": 45.41, "learning_rate": 6.056639575622128e-05, "loss": 0.0175, "step": 189140 }, { "epoch": 45.41, "learning_rate": 6.056288722753824e-05, "loss": 0.0036, "step": 189150 }, { "epoch": 45.42, "learning_rate": 6.055937864441397e-05, "loss": 0.0113, "step": 189160 }, { "epoch": 45.42, "learning_rate": 6.0555870006866576e-05, "loss": 0.0119, "step": 189170 }, { "epoch": 45.42, "learning_rate": 6.0552361314914144e-05, "loss": 0.0059, "step": 189180 }, { "epoch": 45.42, "learning_rate": 6.054885256857476e-05, "loss": 0.02, "step": 189190 }, { "epoch": 45.43, "learning_rate": 6.054534376786649e-05, "loss": 0.0196, "step": 189200 }, { "epoch": 45.43, "learning_rate": 6.054183491280744e-05, "loss": 0.0061, "step": 189210 }, { "epoch": 45.43, "learning_rate": 6.053832600341568e-05, "loss": 0.0064, "step": 189220 }, { "epoch": 45.43, "learning_rate": 6.05348170397093e-05, "loss": 0.0062, "step": 189230 }, { "epoch": 45.44, "learning_rate": 6.053130802170638e-05, "loss": 0.0073, "step": 189240 }, { "epoch": 45.44, "learning_rate": 6.0527798949425015e-05, "loss": 0.0056, "step": 189250 }, { "epoch": 45.44, "learning_rate": 6.052428982288328e-05, "loss": 0.008, "step": 189260 }, { "epoch": 45.44, "learning_rate": 6.0520780642099286e-05, "loss": 0.0063, "step": 189270 }, { "epoch": 45.44, "learning_rate": 6.051727140709108e-05, "loss": 0.0056, "step": 189280 }, { "epoch": 45.45, "learning_rate": 6.0513762117876784e-05, "loss": 0.0067, "step": 189290 }, { "epoch": 45.45, "learning_rate": 6.051025277447445e-05, "loss": 0.0113, "step": 189300 }, { "epoch": 45.45, "learning_rate": 6.050674337690221e-05, "loss": 0.0061, "step": 189310 }, { "epoch": 45.45, "learning_rate": 6.0503233925178104e-05, "loss": 0.014, "step": 189320 }, { "epoch": 45.46, "learning_rate": 6.049972441932026e-05, "loss": 0.0081, "step": 189330 }, { "epoch": 45.46, "learning_rate": 6.049621485934676e-05, "loss": 0.0123, "step": 189340 }, { "epoch": 45.46, "learning_rate": 6.049270524527565e-05, "loss": 0.0139, "step": 189350 }, { "epoch": 45.46, "learning_rate": 6.048919557712507e-05, "loss": 0.0122, "step": 189360 }, { "epoch": 45.47, "learning_rate": 6.048568585491308e-05, "loss": 0.009, "step": 189370 }, { "epoch": 45.47, "learning_rate": 6.048217607865777e-05, "loss": 0.0042, "step": 189380 }, { "epoch": 45.47, "learning_rate": 6.047866624837725e-05, "loss": 0.0042, "step": 189390 }, { "epoch": 45.47, "learning_rate": 6.047515636408959e-05, "loss": 0.0074, "step": 189400 }, { "epoch": 45.47, "learning_rate": 6.0471646425812886e-05, "loss": 0.0074, "step": 189410 }, { "epoch": 45.48, "learning_rate": 6.0468136433565235e-05, "loss": 0.008, "step": 189420 }, { "epoch": 45.48, "learning_rate": 6.046462638736472e-05, "loss": 0.0052, "step": 189430 }, { "epoch": 45.48, "learning_rate": 6.046111628722942e-05, "loss": 0.0431, "step": 189440 }, { "epoch": 45.48, "learning_rate": 6.045760613317746e-05, "loss": 0.0145, "step": 189450 }, { "epoch": 45.49, "learning_rate": 6.0454095925226896e-05, "loss": 0.0073, "step": 189460 }, { "epoch": 45.49, "learning_rate": 6.0450585663395844e-05, "loss": 0.0077, "step": 189470 }, { "epoch": 45.49, "learning_rate": 6.044707534770239e-05, "loss": 0.0144, "step": 189480 }, { "epoch": 45.49, "learning_rate": 6.044356497816461e-05, "loss": 0.0042, "step": 189490 }, { "epoch": 45.49, "learning_rate": 6.044005455480061e-05, "loss": 0.0052, "step": 189500 }, { "epoch": 45.5, "learning_rate": 6.0436544077628486e-05, "loss": 0.0126, "step": 189510 }, { "epoch": 45.5, "learning_rate": 6.0433033546666315e-05, "loss": 0.0045, "step": 189520 }, { "epoch": 45.5, "learning_rate": 6.0429522961932216e-05, "loss": 0.0138, "step": 189530 }, { "epoch": 45.5, "learning_rate": 6.042601232344427e-05, "loss": 0.014, "step": 189540 }, { "epoch": 45.51, "learning_rate": 6.042250163122056e-05, "loss": 0.0037, "step": 189550 }, { "epoch": 45.51, "learning_rate": 6.041899088527919e-05, "loss": 0.0058, "step": 189560 }, { "epoch": 45.51, "learning_rate": 6.041548008563825e-05, "loss": 0.0076, "step": 189570 }, { "epoch": 45.51, "learning_rate": 6.041196923231585e-05, "loss": 0.0114, "step": 189580 }, { "epoch": 45.52, "learning_rate": 6.040845832533006e-05, "loss": 0.0118, "step": 189590 }, { "epoch": 45.52, "learning_rate": 6.0404947364699004e-05, "loss": 0.0096, "step": 189600 }, { "epoch": 45.52, "learning_rate": 6.040143635044075e-05, "loss": 0.0153, "step": 189610 }, { "epoch": 45.52, "learning_rate": 6.039792528257343e-05, "loss": 0.0182, "step": 189620 }, { "epoch": 45.52, "learning_rate": 6.0394414161115096e-05, "loss": 0.0093, "step": 189630 }, { "epoch": 45.53, "learning_rate": 6.0390902986083865e-05, "loss": 0.0087, "step": 189640 }, { "epoch": 45.53, "learning_rate": 6.038739175749784e-05, "loss": 0.01, "step": 189650 }, { "epoch": 45.53, "learning_rate": 6.03838804753751e-05, "loss": 0.009, "step": 189660 }, { "epoch": 45.53, "learning_rate": 6.038036913973375e-05, "loss": 0.0059, "step": 189670 }, { "epoch": 45.54, "learning_rate": 6.037685775059191e-05, "loss": 0.0132, "step": 189680 }, { "epoch": 45.54, "learning_rate": 6.037334630796765e-05, "loss": 0.0121, "step": 189690 }, { "epoch": 45.54, "learning_rate": 6.036983481187908e-05, "loss": 0.0133, "step": 189700 }, { "epoch": 45.54, "learning_rate": 6.036632326234427e-05, "loss": 0.0141, "step": 189710 }, { "epoch": 45.55, "learning_rate": 6.036281165938137e-05, "loss": 0.007, "step": 189720 }, { "epoch": 45.55, "learning_rate": 6.035930000300845e-05, "loss": 0.0136, "step": 189730 }, { "epoch": 45.55, "learning_rate": 6.0355788293243595e-05, "loss": 0.0096, "step": 189740 }, { "epoch": 45.55, "learning_rate": 6.0352276530104934e-05, "loss": 0.0114, "step": 189750 }, { "epoch": 45.55, "learning_rate": 6.034876471361055e-05, "loss": 0.0251, "step": 189760 }, { "epoch": 45.56, "learning_rate": 6.0345252843778554e-05, "loss": 0.0111, "step": 189770 }, { "epoch": 45.56, "learning_rate": 6.0341740920627034e-05, "loss": 0.0203, "step": 189780 }, { "epoch": 45.56, "learning_rate": 6.033822894417409e-05, "loss": 0.0096, "step": 189790 }, { "epoch": 45.56, "learning_rate": 6.033471691443783e-05, "loss": 0.0136, "step": 189800 }, { "epoch": 45.57, "learning_rate": 6.033120483143635e-05, "loss": 0.0127, "step": 189810 }, { "epoch": 45.57, "learning_rate": 6.0327692695187756e-05, "loss": 0.0149, "step": 189820 }, { "epoch": 45.57, "learning_rate": 6.032418050571015e-05, "loss": 0.009, "step": 189830 }, { "epoch": 45.57, "learning_rate": 6.032066826302163e-05, "loss": 0.0312, "step": 189840 }, { "epoch": 45.57, "learning_rate": 6.0317155967140304e-05, "loss": 0.0154, "step": 189850 }, { "epoch": 45.58, "learning_rate": 6.031364361808425e-05, "loss": 0.0088, "step": 189860 }, { "epoch": 45.58, "learning_rate": 6.03101312158716e-05, "loss": 0.009, "step": 189870 }, { "epoch": 45.58, "learning_rate": 6.0306618760520463e-05, "loss": 0.0102, "step": 189880 }, { "epoch": 45.58, "learning_rate": 6.0303106252048916e-05, "loss": 0.012, "step": 189890 }, { "epoch": 45.59, "learning_rate": 6.0299593690475064e-05, "loss": 0.0081, "step": 189900 }, { "epoch": 45.59, "learning_rate": 6.029608107581705e-05, "loss": 0.0085, "step": 189910 }, { "epoch": 45.59, "learning_rate": 6.029256840809292e-05, "loss": 0.0164, "step": 189920 }, { "epoch": 45.59, "learning_rate": 6.0289055687320815e-05, "loss": 0.0076, "step": 189930 }, { "epoch": 45.6, "learning_rate": 6.0285542913518825e-05, "loss": 0.0118, "step": 189940 }, { "epoch": 45.6, "learning_rate": 6.028203008670506e-05, "loss": 0.0119, "step": 189950 }, { "epoch": 45.6, "learning_rate": 6.027851720689763e-05, "loss": 0.0097, "step": 189960 }, { "epoch": 45.6, "learning_rate": 6.0275004274114647e-05, "loss": 0.0126, "step": 189970 }, { "epoch": 45.6, "learning_rate": 6.0271491288374206e-05, "loss": 0.013, "step": 189980 }, { "epoch": 45.61, "learning_rate": 6.02679782496944e-05, "loss": 0.0187, "step": 189990 }, { "epoch": 45.61, "learning_rate": 6.026446515809335e-05, "loss": 0.0127, "step": 190000 }, { "epoch": 45.61, "learning_rate": 6.0260952013589166e-05, "loss": 0.01, "step": 190010 }, { "epoch": 45.61, "learning_rate": 6.025743881619994e-05, "loss": 0.009, "step": 190020 }, { "epoch": 45.62, "learning_rate": 6.0253925565943794e-05, "loss": 0.0198, "step": 190030 }, { "epoch": 45.62, "learning_rate": 6.025041226283883e-05, "loss": 0.0082, "step": 190040 }, { "epoch": 45.62, "learning_rate": 6.024689890690316e-05, "loss": 0.013, "step": 190050 }, { "epoch": 45.62, "learning_rate": 6.0243385498154895e-05, "loss": 0.0055, "step": 190060 }, { "epoch": 45.62, "learning_rate": 6.023987203661212e-05, "loss": 0.0059, "step": 190070 }, { "epoch": 45.63, "learning_rate": 6.0236358522292967e-05, "loss": 0.0095, "step": 190080 }, { "epoch": 45.63, "learning_rate": 6.0232844955215525e-05, "loss": 0.0062, "step": 190090 }, { "epoch": 45.63, "learning_rate": 6.022933133539793e-05, "loss": 0.0139, "step": 190100 }, { "epoch": 45.63, "learning_rate": 6.0225817662858266e-05, "loss": 0.0154, "step": 190110 }, { "epoch": 45.64, "learning_rate": 6.022230393761465e-05, "loss": 0.0109, "step": 190120 }, { "epoch": 45.64, "learning_rate": 6.021879015968521e-05, "loss": 0.0324, "step": 190130 }, { "epoch": 45.64, "learning_rate": 6.0215276329088035e-05, "loss": 0.014, "step": 190140 }, { "epoch": 45.64, "learning_rate": 6.0211762445841234e-05, "loss": 0.0107, "step": 190150 }, { "epoch": 45.65, "learning_rate": 6.020824850996292e-05, "loss": 0.0064, "step": 190160 }, { "epoch": 45.65, "learning_rate": 6.0204734521471215e-05, "loss": 0.0086, "step": 190170 }, { "epoch": 45.65, "learning_rate": 6.0201220480384216e-05, "loss": 0.0057, "step": 190180 }, { "epoch": 45.65, "learning_rate": 6.019770638672003e-05, "loss": 0.0064, "step": 190190 }, { "epoch": 45.65, "learning_rate": 6.0194192240496816e-05, "loss": 0.0096, "step": 190200 }, { "epoch": 45.66, "learning_rate": 6.019067804173263e-05, "loss": 0.006, "step": 190210 }, { "epoch": 45.66, "learning_rate": 6.01871637904456e-05, "loss": 0.0123, "step": 190220 }, { "epoch": 45.66, "learning_rate": 6.018364948665385e-05, "loss": 0.0146, "step": 190230 }, { "epoch": 45.66, "learning_rate": 6.018013513037548e-05, "loss": 0.0061, "step": 190240 }, { "epoch": 45.67, "learning_rate": 6.0176620721628605e-05, "loss": 0.0177, "step": 190250 }, { "epoch": 45.67, "learning_rate": 6.017310626043134e-05, "loss": 0.0093, "step": 190260 }, { "epoch": 45.67, "learning_rate": 6.016959174680182e-05, "loss": 0.0063, "step": 190270 }, { "epoch": 45.67, "learning_rate": 6.016607718075813e-05, "loss": 0.0088, "step": 190280 }, { "epoch": 45.68, "learning_rate": 6.016256256231839e-05, "loss": 0.0067, "step": 190290 }, { "epoch": 45.68, "learning_rate": 6.015904789150072e-05, "loss": 0.0093, "step": 190300 }, { "epoch": 45.68, "learning_rate": 6.015553316832323e-05, "loss": 0.0083, "step": 190310 }, { "epoch": 45.68, "learning_rate": 6.015201839280403e-05, "loss": 0.0066, "step": 190320 }, { "epoch": 45.68, "learning_rate": 6.014850356496124e-05, "loss": 0.0097, "step": 190330 }, { "epoch": 45.69, "learning_rate": 6.0144988684813e-05, "loss": 0.008, "step": 190340 }, { "epoch": 45.69, "learning_rate": 6.014147375237739e-05, "loss": 0.0086, "step": 190350 }, { "epoch": 45.69, "learning_rate": 6.0137958767672544e-05, "loss": 0.0281, "step": 190360 }, { "epoch": 45.69, "learning_rate": 6.013444373071656e-05, "loss": 0.0064, "step": 190370 }, { "epoch": 45.7, "learning_rate": 6.013092864152758e-05, "loss": 0.0062, "step": 190380 }, { "epoch": 45.7, "learning_rate": 6.012741350012371e-05, "loss": 0.0105, "step": 190390 }, { "epoch": 45.7, "learning_rate": 6.0123898306523067e-05, "loss": 0.0106, "step": 190400 }, { "epoch": 45.7, "learning_rate": 6.012038306074377e-05, "loss": 0.014, "step": 190410 }, { "epoch": 45.7, "learning_rate": 6.0116867762803933e-05, "loss": 0.0135, "step": 190420 }, { "epoch": 45.71, "learning_rate": 6.011335241272167e-05, "loss": 0.0074, "step": 190430 }, { "epoch": 45.71, "learning_rate": 6.01098370105151e-05, "loss": 0.0077, "step": 190440 }, { "epoch": 45.71, "learning_rate": 6.010632155620235e-05, "loss": 0.0106, "step": 190450 }, { "epoch": 45.71, "learning_rate": 6.010280604980153e-05, "loss": 0.0145, "step": 190460 }, { "epoch": 45.72, "learning_rate": 6.009929049133076e-05, "loss": 0.0107, "step": 190470 }, { "epoch": 45.72, "learning_rate": 6.009577488080817e-05, "loss": 0.0087, "step": 190480 }, { "epoch": 45.72, "learning_rate": 6.009225921825188e-05, "loss": 0.0118, "step": 190490 }, { "epoch": 45.72, "learning_rate": 6.008874350367999e-05, "loss": 0.005, "step": 190500 }, { "epoch": 45.73, "learning_rate": 6.008522773711064e-05, "loss": 0.014, "step": 190510 }, { "epoch": 45.73, "learning_rate": 6.008171191856193e-05, "loss": 0.0179, "step": 190520 }, { "epoch": 45.73, "learning_rate": 6.0078196048052e-05, "loss": 0.0149, "step": 190530 }, { "epoch": 45.73, "learning_rate": 6.007468012559896e-05, "loss": 0.0267, "step": 190540 }, { "epoch": 45.73, "learning_rate": 6.007116415122094e-05, "loss": 0.0117, "step": 190550 }, { "epoch": 45.74, "learning_rate": 6.006764812493606e-05, "loss": 0.0183, "step": 190560 }, { "epoch": 45.74, "learning_rate": 6.006413204676243e-05, "loss": 0.0078, "step": 190570 }, { "epoch": 45.74, "learning_rate": 6.006061591671818e-05, "loss": 0.0079, "step": 190580 }, { "epoch": 45.74, "learning_rate": 6.005709973482143e-05, "loss": 0.0095, "step": 190590 }, { "epoch": 45.75, "learning_rate": 6.00535835010903e-05, "loss": 0.0119, "step": 190600 }, { "epoch": 45.75, "learning_rate": 6.005006721554293e-05, "loss": 0.0077, "step": 190610 }, { "epoch": 45.75, "learning_rate": 6.0046550878197416e-05, "loss": 0.0117, "step": 190620 }, { "epoch": 45.75, "learning_rate": 6.004303448907189e-05, "loss": 0.0136, "step": 190630 }, { "epoch": 45.76, "learning_rate": 6.0039518048184495e-05, "loss": 0.0074, "step": 190640 }, { "epoch": 45.76, "learning_rate": 6.0036001555553333e-05, "loss": 0.017, "step": 190650 }, { "epoch": 45.76, "learning_rate": 6.003248501119654e-05, "loss": 0.0102, "step": 190660 }, { "epoch": 45.76, "learning_rate": 6.002896841513223e-05, "loss": 0.0124, "step": 190670 }, { "epoch": 45.76, "learning_rate": 6.002545176737854e-05, "loss": 0.0074, "step": 190680 }, { "epoch": 45.77, "learning_rate": 6.002193506795358e-05, "loss": 0.008, "step": 190690 }, { "epoch": 45.77, "learning_rate": 6.001841831687549e-05, "loss": 0.0111, "step": 190700 }, { "epoch": 45.77, "learning_rate": 6.001490151416239e-05, "loss": 0.0091, "step": 190710 }, { "epoch": 45.77, "learning_rate": 6.001138465983241e-05, "loss": 0.0111, "step": 190720 }, { "epoch": 45.78, "learning_rate": 6.000786775390365e-05, "loss": 0.0087, "step": 190730 }, { "epoch": 45.78, "learning_rate": 6.000435079639426e-05, "loss": 0.006, "step": 190740 }, { "epoch": 45.78, "learning_rate": 6.000083378732236e-05, "loss": 0.0076, "step": 190750 }, { "epoch": 45.78, "learning_rate": 5.999731672670609e-05, "loss": 0.0109, "step": 190760 }, { "epoch": 45.78, "learning_rate": 5.999379961456356e-05, "loss": 0.006, "step": 190770 }, { "epoch": 45.79, "learning_rate": 5.9990282450912905e-05, "loss": 0.0179, "step": 190780 }, { "epoch": 45.79, "learning_rate": 5.998676523577225e-05, "loss": 0.0114, "step": 190790 }, { "epoch": 45.79, "learning_rate": 5.998324796915973e-05, "loss": 0.0064, "step": 190800 }, { "epoch": 45.79, "learning_rate": 5.997973065109346e-05, "loss": 0.0048, "step": 190810 }, { "epoch": 45.8, "learning_rate": 5.997621328159156e-05, "loss": 0.0091, "step": 190820 }, { "epoch": 45.8, "learning_rate": 5.99726958606722e-05, "loss": 0.0129, "step": 190830 }, { "epoch": 45.8, "learning_rate": 5.9969178388353474e-05, "loss": 0.0087, "step": 190840 }, { "epoch": 45.8, "learning_rate": 5.9965660864653514e-05, "loss": 0.0092, "step": 190850 }, { "epoch": 45.81, "learning_rate": 5.9962143289590465e-05, "loss": 0.0125, "step": 190860 }, { "epoch": 45.81, "learning_rate": 5.9958625663182434e-05, "loss": 0.0057, "step": 190870 }, { "epoch": 45.81, "learning_rate": 5.995510798544757e-05, "loss": 0.0089, "step": 190880 }, { "epoch": 45.81, "learning_rate": 5.995159025640399e-05, "loss": 0.01, "step": 190890 }, { "epoch": 45.81, "learning_rate": 5.994807247606984e-05, "loss": 0.0054, "step": 190900 }, { "epoch": 45.82, "learning_rate": 5.9944554644463225e-05, "loss": 0.0049, "step": 190910 }, { "epoch": 45.82, "learning_rate": 5.994103676160231e-05, "loss": 0.0048, "step": 190920 }, { "epoch": 45.82, "learning_rate": 5.99375188275052e-05, "loss": 0.0068, "step": 190930 }, { "epoch": 45.82, "learning_rate": 5.993400084219003e-05, "loss": 0.0059, "step": 190940 }, { "epoch": 45.83, "learning_rate": 5.9930482805674946e-05, "loss": 0.0055, "step": 190950 }, { "epoch": 45.83, "learning_rate": 5.9926964717978064e-05, "loss": 0.0162, "step": 190960 }, { "epoch": 45.83, "learning_rate": 5.9923446579117526e-05, "loss": 0.0098, "step": 190970 }, { "epoch": 45.83, "learning_rate": 5.991992838911146e-05, "loss": 0.0093, "step": 190980 }, { "epoch": 45.84, "learning_rate": 5.9916410147978006e-05, "loss": 0.0144, "step": 190990 }, { "epoch": 45.84, "learning_rate": 5.9912891855735285e-05, "loss": 0.0149, "step": 191000 }, { "epoch": 45.84, "learning_rate": 5.990937351240145e-05, "loss": 0.01, "step": 191010 }, { "epoch": 45.84, "learning_rate": 5.9905855117994605e-05, "loss": 0.0095, "step": 191020 }, { "epoch": 45.84, "learning_rate": 5.99023366725329e-05, "loss": 0.006, "step": 191030 }, { "epoch": 45.85, "learning_rate": 5.989881817603448e-05, "loss": 0.0105, "step": 191040 }, { "epoch": 45.85, "learning_rate": 5.9895299628517454e-05, "loss": 0.0053, "step": 191050 }, { "epoch": 45.85, "learning_rate": 5.9891781029999985e-05, "loss": 0.0054, "step": 191060 }, { "epoch": 45.85, "learning_rate": 5.988826238050018e-05, "loss": 0.009, "step": 191070 }, { "epoch": 45.86, "learning_rate": 5.988474368003619e-05, "loss": 0.0116, "step": 191080 }, { "epoch": 45.86, "learning_rate": 5.988122492862616e-05, "loss": 0.0045, "step": 191090 }, { "epoch": 45.86, "learning_rate": 5.98777061262882e-05, "loss": 0.0052, "step": 191100 }, { "epoch": 45.86, "learning_rate": 5.987418727304047e-05, "loss": 0.0259, "step": 191110 }, { "epoch": 45.86, "learning_rate": 5.987066836890109e-05, "loss": 0.0078, "step": 191120 }, { "epoch": 45.87, "learning_rate": 5.9867149413888225e-05, "loss": 0.0101, "step": 191130 }, { "epoch": 45.87, "learning_rate": 5.986363040801997e-05, "loss": 0.0066, "step": 191140 }, { "epoch": 45.87, "learning_rate": 5.986011135131449e-05, "loss": 0.0065, "step": 191150 }, { "epoch": 45.87, "learning_rate": 5.98565922437899e-05, "loss": 0.0112, "step": 191160 }, { "epoch": 45.88, "learning_rate": 5.985307308546436e-05, "loss": 0.0059, "step": 191170 }, { "epoch": 45.88, "learning_rate": 5.984955387635599e-05, "loss": 0.0068, "step": 191180 }, { "epoch": 45.88, "learning_rate": 5.984603461648295e-05, "loss": 0.0059, "step": 191190 }, { "epoch": 45.88, "learning_rate": 5.984251530586337e-05, "loss": 0.0124, "step": 191200 }, { "epoch": 45.89, "learning_rate": 5.983899594451536e-05, "loss": 0.0053, "step": 191210 }, { "epoch": 45.89, "learning_rate": 5.983547653245709e-05, "loss": 0.0073, "step": 191220 }, { "epoch": 45.89, "learning_rate": 5.98319570697067e-05, "loss": 0.0056, "step": 191230 }, { "epoch": 45.89, "learning_rate": 5.9828437556282314e-05, "loss": 0.0119, "step": 191240 }, { "epoch": 45.89, "learning_rate": 5.982491799220209e-05, "loss": 0.0074, "step": 191250 }, { "epoch": 45.9, "learning_rate": 5.982139837748415e-05, "loss": 0.0073, "step": 191260 }, { "epoch": 45.9, "learning_rate": 5.981787871214664e-05, "loss": 0.0115, "step": 191270 }, { "epoch": 45.9, "learning_rate": 5.981435899620771e-05, "loss": 0.0086, "step": 191280 }, { "epoch": 45.9, "learning_rate": 5.981083922968548e-05, "loss": 0.006, "step": 191290 }, { "epoch": 45.91, "learning_rate": 5.980731941259811e-05, "loss": 0.0049, "step": 191300 }, { "epoch": 45.91, "learning_rate": 5.980379954496372e-05, "loss": 0.0149, "step": 191310 }, { "epoch": 45.91, "learning_rate": 5.9800279626800485e-05, "loss": 0.0058, "step": 191320 }, { "epoch": 45.91, "learning_rate": 5.979675965812651e-05, "loss": 0.0081, "step": 191330 }, { "epoch": 45.92, "learning_rate": 5.979323963895996e-05, "loss": 0.0064, "step": 191340 }, { "epoch": 45.92, "learning_rate": 5.978971956931898e-05, "loss": 0.0132, "step": 191350 }, { "epoch": 45.92, "learning_rate": 5.978619944922169e-05, "loss": 0.0082, "step": 191360 }, { "epoch": 45.92, "learning_rate": 5.978267927868626e-05, "loss": 0.0107, "step": 191370 }, { "epoch": 45.92, "learning_rate": 5.977915905773079e-05, "loss": 0.0056, "step": 191380 }, { "epoch": 45.93, "learning_rate": 5.977563878637348e-05, "loss": 0.0099, "step": 191390 }, { "epoch": 45.93, "learning_rate": 5.9772118464632435e-05, "loss": 0.0053, "step": 191400 }, { "epoch": 45.93, "learning_rate": 5.976859809252582e-05, "loss": 0.0034, "step": 191410 }, { "epoch": 45.93, "learning_rate": 5.9765077670071764e-05, "loss": 0.0045, "step": 191420 }, { "epoch": 45.94, "learning_rate": 5.976155719728842e-05, "loss": 0.0054, "step": 191430 }, { "epoch": 45.94, "learning_rate": 5.975803667419392e-05, "loss": 0.0092, "step": 191440 }, { "epoch": 45.94, "learning_rate": 5.9754516100806423e-05, "loss": 0.005, "step": 191450 }, { "epoch": 45.94, "learning_rate": 5.9750995477144065e-05, "loss": 0.0062, "step": 191460 }, { "epoch": 45.94, "learning_rate": 5.974747480322499e-05, "loss": 0.0105, "step": 191470 }, { "epoch": 45.95, "learning_rate": 5.974395407906736e-05, "loss": 0.0048, "step": 191480 }, { "epoch": 45.95, "learning_rate": 5.97404333046893e-05, "loss": 0.0033, "step": 191490 }, { "epoch": 46.0, "learning_rate": 5.9736912480108974e-05, "loss": 0.0043, "step": 191500 }, { "epoch": 46.0, "learning_rate": 5.973339160534451e-05, "loss": 0.0052, "step": 191510 }, { "epoch": 46.01, "learning_rate": 5.972987068041408e-05, "loss": 0.0084, "step": 191520 }, { "epoch": 46.01, "learning_rate": 5.972634970533579e-05, "loss": 0.0067, "step": 191530 }, { "epoch": 46.01, "learning_rate": 5.9722828680127816e-05, "loss": 0.01, "step": 191540 }, { "epoch": 46.01, "learning_rate": 5.971930760480832e-05, "loss": 0.0092, "step": 191550 }, { "epoch": 46.01, "learning_rate": 5.971578647939543e-05, "loss": 0.0113, "step": 191560 }, { "epoch": 46.02, "learning_rate": 5.971226530390729e-05, "loss": 0.0105, "step": 191570 }, { "epoch": 46.02, "learning_rate": 5.9708744078362054e-05, "loss": 0.0107, "step": 191580 }, { "epoch": 46.02, "learning_rate": 5.970522280277786e-05, "loss": 0.0205, "step": 191590 }, { "epoch": 46.02, "learning_rate": 5.970170147717288e-05, "loss": 0.0057, "step": 191600 }, { "epoch": 46.03, "learning_rate": 5.9698180101565236e-05, "loss": 0.0129, "step": 191610 }, { "epoch": 46.03, "learning_rate": 5.96946586759731e-05, "loss": 0.0096, "step": 191620 }, { "epoch": 46.03, "learning_rate": 5.9691137200414626e-05, "loss": 0.0082, "step": 191630 }, { "epoch": 46.03, "learning_rate": 5.968761567490794e-05, "loss": 0.0056, "step": 191640 }, { "epoch": 46.03, "learning_rate": 5.968409409947119e-05, "loss": 0.0091, "step": 191650 }, { "epoch": 46.04, "learning_rate": 5.968057247412254e-05, "loss": 0.0064, "step": 191660 }, { "epoch": 46.04, "learning_rate": 5.967705079888015e-05, "loss": 0.0078, "step": 191670 }, { "epoch": 46.04, "learning_rate": 5.9673529073762146e-05, "loss": 0.0116, "step": 191680 }, { "epoch": 46.04, "learning_rate": 5.9670007298786687e-05, "loss": 0.0065, "step": 191690 }, { "epoch": 46.05, "learning_rate": 5.9666485473971944e-05, "loss": 0.0091, "step": 191700 }, { "epoch": 46.05, "learning_rate": 5.9662963599336065e-05, "loss": 0.0097, "step": 191710 }, { "epoch": 46.05, "learning_rate": 5.9659441674897176e-05, "loss": 0.0122, "step": 191720 }, { "epoch": 46.05, "learning_rate": 5.965591970067344e-05, "loss": 0.0078, "step": 191730 }, { "epoch": 46.06, "learning_rate": 5.965239767668302e-05, "loss": 0.0052, "step": 191740 }, { "epoch": 46.06, "learning_rate": 5.9648875602944055e-05, "loss": 0.0437, "step": 191750 }, { "epoch": 46.06, "learning_rate": 5.964535347947471e-05, "loss": 0.0059, "step": 191760 }, { "epoch": 46.06, "learning_rate": 5.9641831306293125e-05, "loss": 0.0086, "step": 191770 }, { "epoch": 46.06, "learning_rate": 5.9638309083417484e-05, "loss": 0.0087, "step": 191780 }, { "epoch": 46.07, "learning_rate": 5.96347868108659e-05, "loss": 0.0115, "step": 191790 }, { "epoch": 46.07, "learning_rate": 5.963126448865655e-05, "loss": 0.0057, "step": 191800 }, { "epoch": 46.07, "learning_rate": 5.962774211680757e-05, "loss": 0.0074, "step": 191810 }, { "epoch": 46.07, "learning_rate": 5.9624219695337135e-05, "loss": 0.0047, "step": 191820 }, { "epoch": 46.08, "learning_rate": 5.9620697224263386e-05, "loss": 0.0104, "step": 191830 }, { "epoch": 46.08, "learning_rate": 5.96171747036045e-05, "loss": 0.0079, "step": 191840 }, { "epoch": 46.08, "learning_rate": 5.9613652133378595e-05, "loss": 0.0084, "step": 191850 }, { "epoch": 46.08, "learning_rate": 5.9610129513603855e-05, "loss": 0.0074, "step": 191860 }, { "epoch": 46.09, "learning_rate": 5.960660684429843e-05, "loss": 0.0053, "step": 191870 }, { "epoch": 46.09, "learning_rate": 5.9603084125480465e-05, "loss": 0.013, "step": 191880 }, { "epoch": 46.09, "learning_rate": 5.959956135716813e-05, "loss": 0.0185, "step": 191890 }, { "epoch": 46.09, "learning_rate": 5.959603853937957e-05, "loss": 0.0096, "step": 191900 }, { "epoch": 46.09, "learning_rate": 5.959251567213295e-05, "loss": 0.0086, "step": 191910 }, { "epoch": 46.1, "learning_rate": 5.958899275544644e-05, "loss": 0.0072, "step": 191920 }, { "epoch": 46.1, "learning_rate": 5.958546978933817e-05, "loss": 0.0129, "step": 191930 }, { "epoch": 46.1, "learning_rate": 5.95819467738263e-05, "loss": 0.0048, "step": 191940 }, { "epoch": 46.1, "learning_rate": 5.9578423708929e-05, "loss": 0.0035, "step": 191950 }, { "epoch": 46.11, "learning_rate": 5.957490059466443e-05, "loss": 0.0098, "step": 191960 }, { "epoch": 46.11, "learning_rate": 5.957137743105074e-05, "loss": 0.0117, "step": 191970 }, { "epoch": 46.11, "learning_rate": 5.956785421810608e-05, "loss": 0.0124, "step": 191980 }, { "epoch": 46.11, "learning_rate": 5.9564330955848624e-05, "loss": 0.0087, "step": 191990 }, { "epoch": 46.11, "learning_rate": 5.956080764429653e-05, "loss": 0.0083, "step": 192000 }, { "epoch": 46.12, "learning_rate": 5.955728428346796e-05, "loss": 0.007, "step": 192010 }, { "epoch": 46.12, "learning_rate": 5.955376087338106e-05, "loss": 0.0098, "step": 192020 }, { "epoch": 46.12, "learning_rate": 5.955023741405399e-05, "loss": 0.0085, "step": 192030 }, { "epoch": 46.12, "learning_rate": 5.9546713905504925e-05, "loss": 0.0098, "step": 192040 }, { "epoch": 46.13, "learning_rate": 5.954319034775202e-05, "loss": 0.0101, "step": 192050 }, { "epoch": 46.13, "learning_rate": 5.9539666740813425e-05, "loss": 0.0106, "step": 192060 }, { "epoch": 46.13, "learning_rate": 5.953614308470732e-05, "loss": 0.006, "step": 192070 }, { "epoch": 46.13, "learning_rate": 5.9532619379451846e-05, "loss": 0.0082, "step": 192080 }, { "epoch": 46.14, "learning_rate": 5.952909562506517e-05, "loss": 0.01, "step": 192090 }, { "epoch": 46.14, "learning_rate": 5.952557182156545e-05, "loss": 0.0045, "step": 192100 }, { "epoch": 46.14, "learning_rate": 5.952204796897086e-05, "loss": 0.019, "step": 192110 }, { "epoch": 46.14, "learning_rate": 5.9518524067299554e-05, "loss": 0.0061, "step": 192120 }, { "epoch": 46.14, "learning_rate": 5.95150001165697e-05, "loss": 0.0126, "step": 192130 }, { "epoch": 46.15, "learning_rate": 5.951147611679945e-05, "loss": 0.0074, "step": 192140 }, { "epoch": 46.15, "learning_rate": 5.9507952068006976e-05, "loss": 0.006, "step": 192150 }, { "epoch": 46.15, "learning_rate": 5.950442797021043e-05, "loss": 0.0119, "step": 192160 }, { "epoch": 46.15, "learning_rate": 5.950090382342799e-05, "loss": 0.0109, "step": 192170 }, { "epoch": 46.16, "learning_rate": 5.949737962767781e-05, "loss": 0.0075, "step": 192180 }, { "epoch": 46.16, "learning_rate": 5.949385538297806e-05, "loss": 0.0094, "step": 192190 }, { "epoch": 46.16, "learning_rate": 5.94903310893469e-05, "loss": 0.0081, "step": 192200 }, { "epoch": 46.16, "learning_rate": 5.948680674680249e-05, "loss": 0.0077, "step": 192210 }, { "epoch": 46.16, "learning_rate": 5.9483282355363e-05, "loss": 0.0077, "step": 192220 }, { "epoch": 46.17, "learning_rate": 5.94797579150466e-05, "loss": 0.0066, "step": 192230 }, { "epoch": 46.17, "learning_rate": 5.9476233425871444e-05, "loss": 0.0082, "step": 192240 }, { "epoch": 46.17, "learning_rate": 5.94727088878557e-05, "loss": 0.0044, "step": 192250 }, { "epoch": 46.17, "learning_rate": 5.946918430101753e-05, "loss": 0.0085, "step": 192260 }, { "epoch": 46.18, "learning_rate": 5.946565966537511e-05, "loss": 0.0101, "step": 192270 }, { "epoch": 46.18, "learning_rate": 5.9462134980946594e-05, "loss": 0.0111, "step": 192280 }, { "epoch": 46.18, "learning_rate": 5.9458610247750165e-05, "loss": 0.0054, "step": 192290 }, { "epoch": 46.18, "learning_rate": 5.9455085465803975e-05, "loss": 0.0047, "step": 192300 }, { "epoch": 46.19, "learning_rate": 5.9451560635126204e-05, "loss": 0.006, "step": 192310 }, { "epoch": 46.19, "learning_rate": 5.9448035755735e-05, "loss": 0.0063, "step": 192320 }, { "epoch": 46.19, "learning_rate": 5.9444510827648534e-05, "loss": 0.0044, "step": 192330 }, { "epoch": 46.19, "learning_rate": 5.9440985850885004e-05, "loss": 0.0151, "step": 192340 }, { "epoch": 46.19, "learning_rate": 5.943746082546254e-05, "loss": 0.008, "step": 192350 }, { "epoch": 46.2, "learning_rate": 5.9433935751399325e-05, "loss": 0.004, "step": 192360 }, { "epoch": 46.2, "learning_rate": 5.9430410628713526e-05, "loss": 0.0076, "step": 192370 }, { "epoch": 46.2, "learning_rate": 5.942688545742331e-05, "loss": 0.005, "step": 192380 }, { "epoch": 46.2, "learning_rate": 5.9423360237546854e-05, "loss": 0.0078, "step": 192390 }, { "epoch": 46.21, "learning_rate": 5.941983496910232e-05, "loss": 0.0126, "step": 192400 }, { "epoch": 46.21, "learning_rate": 5.941630965210787e-05, "loss": 0.0103, "step": 192410 }, { "epoch": 46.21, "learning_rate": 5.941278428658168e-05, "loss": 0.0084, "step": 192420 }, { "epoch": 46.21, "learning_rate": 5.9409258872541926e-05, "loss": 0.0109, "step": 192430 }, { "epoch": 46.22, "learning_rate": 5.940573341000677e-05, "loss": 0.0114, "step": 192440 }, { "epoch": 46.22, "learning_rate": 5.940220789899439e-05, "loss": 0.0041, "step": 192450 }, { "epoch": 46.22, "learning_rate": 5.939868233952295e-05, "loss": 0.0062, "step": 192460 }, { "epoch": 46.22, "learning_rate": 5.9395156731610623e-05, "loss": 0.0106, "step": 192470 }, { "epoch": 46.22, "learning_rate": 5.9391631075275575e-05, "loss": 0.0056, "step": 192480 }, { "epoch": 46.23, "learning_rate": 5.938810537053599e-05, "loss": 0.0071, "step": 192490 }, { "epoch": 46.23, "learning_rate": 5.9384579617410043e-05, "loss": 0.0117, "step": 192500 }, { "epoch": 46.23, "learning_rate": 5.9381053815915875e-05, "loss": 0.0258, "step": 192510 }, { "epoch": 46.23, "learning_rate": 5.937752796607168e-05, "loss": 0.0075, "step": 192520 }, { "epoch": 46.24, "learning_rate": 5.937400206789563e-05, "loss": 0.0049, "step": 192530 }, { "epoch": 46.24, "learning_rate": 5.9370476121405894e-05, "loss": 0.0075, "step": 192540 }, { "epoch": 46.24, "learning_rate": 5.9366950126620644e-05, "loss": 0.0125, "step": 192550 }, { "epoch": 46.24, "learning_rate": 5.936342408355806e-05, "loss": 0.005, "step": 192560 }, { "epoch": 46.24, "learning_rate": 5.9359897992236315e-05, "loss": 0.0126, "step": 192570 }, { "epoch": 46.25, "learning_rate": 5.935637185267355e-05, "loss": 0.0099, "step": 192580 }, { "epoch": 46.25, "learning_rate": 5.9352845664887994e-05, "loss": 0.0067, "step": 192590 }, { "epoch": 46.25, "learning_rate": 5.934931942889778e-05, "loss": 0.015, "step": 192600 }, { "epoch": 46.25, "learning_rate": 5.934579314472109e-05, "loss": 0.0065, "step": 192610 }, { "epoch": 46.26, "learning_rate": 5.934226681237612e-05, "loss": 0.0061, "step": 192620 }, { "epoch": 46.26, "learning_rate": 5.933874043188102e-05, "loss": 0.0139, "step": 192630 }, { "epoch": 46.26, "learning_rate": 5.9335214003253995e-05, "loss": 0.0244, "step": 192640 }, { "epoch": 46.26, "learning_rate": 5.933168752651318e-05, "loss": 0.0127, "step": 192650 }, { "epoch": 46.27, "learning_rate": 5.932816100167677e-05, "loss": 0.009, "step": 192660 }, { "epoch": 46.27, "learning_rate": 5.932463442876294e-05, "loss": 0.0077, "step": 192670 }, { "epoch": 46.27, "learning_rate": 5.9321107807789866e-05, "loss": 0.0046, "step": 192680 }, { "epoch": 46.27, "learning_rate": 5.931758113877573e-05, "loss": 0.0071, "step": 192690 }, { "epoch": 46.27, "learning_rate": 5.931405442173868e-05, "loss": 0.0078, "step": 192700 }, { "epoch": 46.28, "learning_rate": 5.9310527656696954e-05, "loss": 0.0045, "step": 192710 }, { "epoch": 46.28, "learning_rate": 5.930700084366867e-05, "loss": 0.0047, "step": 192720 }, { "epoch": 46.28, "learning_rate": 5.930347398267202e-05, "loss": 0.0133, "step": 192730 }, { "epoch": 46.28, "learning_rate": 5.929994707372519e-05, "loss": 0.0086, "step": 192740 }, { "epoch": 46.29, "learning_rate": 5.929642011684635e-05, "loss": 0.0111, "step": 192750 }, { "epoch": 46.29, "learning_rate": 5.9292893112053694e-05, "loss": 0.0063, "step": 192760 }, { "epoch": 46.29, "learning_rate": 5.928936605936539e-05, "loss": 0.006, "step": 192770 }, { "epoch": 46.29, "learning_rate": 5.928583895879962e-05, "loss": 0.0099, "step": 192780 }, { "epoch": 46.3, "learning_rate": 5.9282311810374544e-05, "loss": 0.007, "step": 192790 }, { "epoch": 46.3, "learning_rate": 5.9278784614108375e-05, "loss": 0.0097, "step": 192800 }, { "epoch": 46.3, "learning_rate": 5.9275257370019256e-05, "loss": 0.0055, "step": 192810 }, { "epoch": 46.3, "learning_rate": 5.9271730078125385e-05, "loss": 0.0042, "step": 192820 }, { "epoch": 46.3, "learning_rate": 5.926820273844493e-05, "loss": 0.0037, "step": 192830 }, { "epoch": 46.31, "learning_rate": 5.92646753509961e-05, "loss": 0.0054, "step": 192840 }, { "epoch": 46.31, "learning_rate": 5.9261147915797057e-05, "loss": 0.0062, "step": 192850 }, { "epoch": 46.31, "learning_rate": 5.925762043286597e-05, "loss": 0.0067, "step": 192860 }, { "epoch": 46.31, "learning_rate": 5.925409290222104e-05, "loss": 0.0052, "step": 192870 }, { "epoch": 46.32, "learning_rate": 5.9250565323880424e-05, "loss": 0.0067, "step": 192880 }, { "epoch": 46.32, "learning_rate": 5.9247037697862305e-05, "loss": 0.0059, "step": 192890 }, { "epoch": 46.32, "learning_rate": 5.924351002418489e-05, "loss": 0.0095, "step": 192900 }, { "epoch": 46.32, "learning_rate": 5.923998230286636e-05, "loss": 0.0054, "step": 192910 }, { "epoch": 46.32, "learning_rate": 5.923645453392487e-05, "loss": 0.0077, "step": 192920 }, { "epoch": 46.33, "learning_rate": 5.9232926717378635e-05, "loss": 0.0047, "step": 192930 }, { "epoch": 46.33, "learning_rate": 5.92293988532458e-05, "loss": 0.0053, "step": 192940 }, { "epoch": 46.33, "learning_rate": 5.922587094154457e-05, "loss": 0.0053, "step": 192950 }, { "epoch": 46.33, "learning_rate": 5.922234298229312e-05, "loss": 0.01, "step": 192960 }, { "epoch": 46.34, "learning_rate": 5.921881497550964e-05, "loss": 0.0082, "step": 192970 }, { "epoch": 46.34, "learning_rate": 5.921528692121231e-05, "loss": 0.0076, "step": 192980 }, { "epoch": 46.34, "learning_rate": 5.9211758819419314e-05, "loss": 0.0083, "step": 192990 }, { "epoch": 46.34, "learning_rate": 5.920823067014885e-05, "loss": 0.0031, "step": 193000 }, { "epoch": 46.35, "learning_rate": 5.920470247341907e-05, "loss": 0.0068, "step": 193010 }, { "epoch": 46.35, "learning_rate": 5.9201174229248194e-05, "loss": 0.007, "step": 193020 }, { "epoch": 46.35, "learning_rate": 5.919764593765438e-05, "loss": 0.0092, "step": 193030 }, { "epoch": 46.35, "learning_rate": 5.9194117598655805e-05, "loss": 0.0068, "step": 193040 }, { "epoch": 46.35, "learning_rate": 5.919058921227068e-05, "loss": 0.0062, "step": 193050 }, { "epoch": 46.36, "learning_rate": 5.918706077851719e-05, "loss": 0.0145, "step": 193060 }, { "epoch": 46.36, "learning_rate": 5.9183532297413516e-05, "loss": 0.0049, "step": 193070 }, { "epoch": 46.36, "learning_rate": 5.918000376897783e-05, "loss": 0.0071, "step": 193080 }, { "epoch": 46.36, "learning_rate": 5.917647519322833e-05, "loss": 0.0065, "step": 193090 }, { "epoch": 46.37, "learning_rate": 5.9172946570183206e-05, "loss": 0.0061, "step": 193100 }, { "epoch": 46.37, "learning_rate": 5.916941789986063e-05, "loss": 0.0073, "step": 193110 }, { "epoch": 46.37, "learning_rate": 5.91658891822788e-05, "loss": 0.0045, "step": 193120 }, { "epoch": 46.37, "learning_rate": 5.916236041745591e-05, "loss": 0.0093, "step": 193130 }, { "epoch": 46.38, "learning_rate": 5.9158831605410136e-05, "loss": 0.0106, "step": 193140 }, { "epoch": 46.38, "learning_rate": 5.9155302746159656e-05, "loss": 0.0072, "step": 193150 }, { "epoch": 46.38, "learning_rate": 5.915177383972268e-05, "loss": 0.0058, "step": 193160 }, { "epoch": 46.38, "learning_rate": 5.9148244886117376e-05, "loss": 0.0136, "step": 193170 }, { "epoch": 46.38, "learning_rate": 5.9144715885361944e-05, "loss": 0.0095, "step": 193180 }, { "epoch": 46.39, "learning_rate": 5.914118683747457e-05, "loss": 0.005, "step": 193190 }, { "epoch": 46.39, "learning_rate": 5.913765774247343e-05, "loss": 0.0094, "step": 193200 }, { "epoch": 46.39, "learning_rate": 5.9134128600376746e-05, "loss": 0.0055, "step": 193210 }, { "epoch": 46.39, "learning_rate": 5.913059941120268e-05, "loss": 0.0076, "step": 193220 }, { "epoch": 46.4, "learning_rate": 5.9127070174969424e-05, "loss": 0.0048, "step": 193230 }, { "epoch": 46.4, "learning_rate": 5.9123540891695185e-05, "loss": 0.0065, "step": 193240 }, { "epoch": 46.4, "learning_rate": 5.912001156139812e-05, "loss": 0.0054, "step": 193250 }, { "epoch": 46.4, "learning_rate": 5.911648218409646e-05, "loss": 0.0152, "step": 193260 }, { "epoch": 46.4, "learning_rate": 5.911295275980836e-05, "loss": 0.0189, "step": 193270 }, { "epoch": 46.41, "learning_rate": 5.910942328855202e-05, "loss": 0.0051, "step": 193280 }, { "epoch": 46.41, "learning_rate": 5.910589377034567e-05, "loss": 0.0069, "step": 193290 }, { "epoch": 46.41, "learning_rate": 5.910236420520744e-05, "loss": 0.0047, "step": 193300 }, { "epoch": 46.41, "learning_rate": 5.909883459315555e-05, "loss": 0.0048, "step": 193310 }, { "epoch": 46.42, "learning_rate": 5.909530493420818e-05, "loss": 0.0073, "step": 193320 }, { "epoch": 46.42, "learning_rate": 5.909177522838355e-05, "loss": 0.0049, "step": 193330 }, { "epoch": 46.42, "learning_rate": 5.908824547569983e-05, "loss": 0.0031, "step": 193340 }, { "epoch": 46.42, "learning_rate": 5.9084715676175216e-05, "loss": 0.0063, "step": 193350 }, { "epoch": 46.43, "learning_rate": 5.9081185829827904e-05, "loss": 0.0073, "step": 193360 }, { "epoch": 46.43, "learning_rate": 5.907765593667608e-05, "loss": 0.0054, "step": 193370 }, { "epoch": 46.43, "learning_rate": 5.907412599673795e-05, "loss": 0.007, "step": 193380 }, { "epoch": 46.43, "learning_rate": 5.907059601003169e-05, "loss": 0.0068, "step": 193390 }, { "epoch": 46.43, "learning_rate": 5.9067065976575496e-05, "loss": 0.0066, "step": 193400 }, { "epoch": 46.44, "learning_rate": 5.9063535896387575e-05, "loss": 0.0085, "step": 193410 }, { "epoch": 46.44, "learning_rate": 5.9060005769486126e-05, "loss": 0.0056, "step": 193420 }, { "epoch": 46.44, "learning_rate": 5.905647559588933e-05, "loss": 0.0148, "step": 193430 }, { "epoch": 46.44, "learning_rate": 5.905294537561537e-05, "loss": 0.0079, "step": 193440 }, { "epoch": 46.45, "learning_rate": 5.904941510868246e-05, "loss": 0.0049, "step": 193450 }, { "epoch": 46.45, "learning_rate": 5.9045884795108784e-05, "loss": 0.0112, "step": 193460 }, { "epoch": 46.45, "learning_rate": 5.904235443491255e-05, "loss": 0.0105, "step": 193470 }, { "epoch": 46.45, "learning_rate": 5.903882402811194e-05, "loss": 0.005, "step": 193480 }, { "epoch": 46.46, "learning_rate": 5.903529357472516e-05, "loss": 0.006, "step": 193490 }, { "epoch": 46.46, "learning_rate": 5.9031763074770395e-05, "loss": 0.0107, "step": 193500 }, { "epoch": 46.46, "learning_rate": 5.9028232528265846e-05, "loss": 0.0074, "step": 193510 }, { "epoch": 46.46, "learning_rate": 5.902470193522972e-05, "loss": 0.0098, "step": 193520 }, { "epoch": 46.46, "learning_rate": 5.90211712956802e-05, "loss": 0.0092, "step": 193530 }, { "epoch": 46.47, "learning_rate": 5.901764060963548e-05, "loss": 0.0217, "step": 193540 }, { "epoch": 46.47, "learning_rate": 5.901410987711378e-05, "loss": 0.0046, "step": 193550 }, { "epoch": 46.47, "learning_rate": 5.9010579098133276e-05, "loss": 0.0116, "step": 193560 }, { "epoch": 46.47, "learning_rate": 5.900704827271218e-05, "loss": 0.0092, "step": 193570 }, { "epoch": 46.48, "learning_rate": 5.900351740086867e-05, "loss": 0.0072, "step": 193580 }, { "epoch": 46.48, "learning_rate": 5.899998648262096e-05, "loss": 0.0067, "step": 193590 }, { "epoch": 46.48, "learning_rate": 5.899645551798725e-05, "loss": 0.0049, "step": 193600 }, { "epoch": 46.48, "learning_rate": 5.8992924506985724e-05, "loss": 0.0069, "step": 193610 }, { "epoch": 46.48, "learning_rate": 5.898939344963459e-05, "loss": 0.0107, "step": 193620 }, { "epoch": 46.49, "learning_rate": 5.898586234595205e-05, "loss": 0.01, "step": 193630 }, { "epoch": 46.49, "learning_rate": 5.89823311959563e-05, "loss": 0.0115, "step": 193640 }, { "epoch": 46.49, "learning_rate": 5.8978799999665536e-05, "loss": 0.0121, "step": 193650 }, { "epoch": 46.49, "learning_rate": 5.897526875709797e-05, "loss": 0.0105, "step": 193660 }, { "epoch": 46.5, "learning_rate": 5.8971737468271795e-05, "loss": 0.0088, "step": 193670 }, { "epoch": 46.5, "learning_rate": 5.896820613320519e-05, "loss": 0.0077, "step": 193680 }, { "epoch": 46.5, "learning_rate": 5.8964674751916396e-05, "loss": 0.0205, "step": 193690 }, { "epoch": 46.5, "learning_rate": 5.8961143324423585e-05, "loss": 0.0055, "step": 193700 }, { "epoch": 46.51, "learning_rate": 5.8957611850744974e-05, "loss": 0.0088, "step": 193710 }, { "epoch": 46.51, "learning_rate": 5.8954080330898764e-05, "loss": 0.0057, "step": 193720 }, { "epoch": 46.51, "learning_rate": 5.895054876490314e-05, "loss": 0.0042, "step": 193730 }, { "epoch": 46.51, "learning_rate": 5.894701715277631e-05, "loss": 0.0063, "step": 193740 }, { "epoch": 46.51, "learning_rate": 5.8943485494536474e-05, "loss": 0.0047, "step": 193750 }, { "epoch": 46.52, "learning_rate": 5.893995379020184e-05, "loss": 0.0112, "step": 193760 }, { "epoch": 46.52, "learning_rate": 5.893642203979062e-05, "loss": 0.0041, "step": 193770 }, { "epoch": 46.52, "learning_rate": 5.8932890243320994e-05, "loss": 0.0075, "step": 193780 }, { "epoch": 46.52, "learning_rate": 5.892935840081118e-05, "loss": 0.0123, "step": 193790 }, { "epoch": 46.53, "learning_rate": 5.892582651227938e-05, "loss": 0.0038, "step": 193800 }, { "epoch": 46.53, "learning_rate": 5.89222945777438e-05, "loss": 0.0077, "step": 193810 }, { "epoch": 46.53, "learning_rate": 5.8918762597222635e-05, "loss": 0.0095, "step": 193820 }, { "epoch": 46.53, "learning_rate": 5.891523057073409e-05, "loss": 0.0077, "step": 193830 }, { "epoch": 46.54, "learning_rate": 5.891169849829637e-05, "loss": 0.0092, "step": 193840 }, { "epoch": 46.54, "learning_rate": 5.890816637992769e-05, "loss": 0.0087, "step": 193850 }, { "epoch": 46.54, "learning_rate": 5.890463421564625e-05, "loss": 0.0141, "step": 193860 }, { "epoch": 46.54, "learning_rate": 5.8901102005470244e-05, "loss": 0.0071, "step": 193870 }, { "epoch": 46.54, "learning_rate": 5.8897569749417894e-05, "loss": 0.0128, "step": 193880 }, { "epoch": 46.55, "learning_rate": 5.889403744750738e-05, "loss": 0.0111, "step": 193890 }, { "epoch": 46.55, "learning_rate": 5.889050509975692e-05, "loss": 0.0116, "step": 193900 }, { "epoch": 46.55, "learning_rate": 5.888697270618473e-05, "loss": 0.0111, "step": 193910 }, { "epoch": 46.55, "learning_rate": 5.888344026680901e-05, "loss": 0.0055, "step": 193920 }, { "epoch": 46.56, "learning_rate": 5.887990778164796e-05, "loss": 0.0088, "step": 193930 }, { "epoch": 46.56, "learning_rate": 5.88763752507198e-05, "loss": 0.0067, "step": 193940 }, { "epoch": 46.56, "learning_rate": 5.8872842674042715e-05, "loss": 0.0094, "step": 193950 }, { "epoch": 46.56, "learning_rate": 5.886931005163493e-05, "loss": 0.0154, "step": 193960 }, { "epoch": 46.56, "learning_rate": 5.886577738351465e-05, "loss": 0.0065, "step": 193970 }, { "epoch": 46.57, "learning_rate": 5.8862244669700075e-05, "loss": 0.0141, "step": 193980 }, { "epoch": 46.57, "learning_rate": 5.885871191020942e-05, "loss": 0.0096, "step": 193990 }, { "epoch": 46.57, "learning_rate": 5.88551791050609e-05, "loss": 0.0178, "step": 194000 }, { "epoch": 46.57, "learning_rate": 5.8851646254272694e-05, "loss": 0.0178, "step": 194010 }, { "epoch": 46.58, "learning_rate": 5.8848113357863044e-05, "loss": 0.0173, "step": 194020 }, { "epoch": 46.58, "learning_rate": 5.8844580415850135e-05, "loss": 0.0115, "step": 194030 }, { "epoch": 46.58, "learning_rate": 5.8841047428252184e-05, "loss": 0.0191, "step": 194040 }, { "epoch": 46.58, "learning_rate": 5.8837514395087404e-05, "loss": 0.0077, "step": 194050 }, { "epoch": 46.59, "learning_rate": 5.8833981316373996e-05, "loss": 0.0153, "step": 194060 }, { "epoch": 46.59, "learning_rate": 5.883044819213018e-05, "loss": 0.0144, "step": 194070 }, { "epoch": 46.59, "learning_rate": 5.882691502237417e-05, "loss": 0.0156, "step": 194080 }, { "epoch": 46.59, "learning_rate": 5.882338180712415e-05, "loss": 0.0055, "step": 194090 }, { "epoch": 46.59, "learning_rate": 5.881984854639835e-05, "loss": 0.0089, "step": 194100 }, { "epoch": 46.6, "learning_rate": 5.881631524021498e-05, "loss": 0.0128, "step": 194110 }, { "epoch": 46.6, "learning_rate": 5.881278188859224e-05, "loss": 0.0058, "step": 194120 }, { "epoch": 46.6, "learning_rate": 5.8809248491548355e-05, "loss": 0.0083, "step": 194130 }, { "epoch": 46.6, "learning_rate": 5.880571504910153e-05, "loss": 0.0119, "step": 194140 }, { "epoch": 46.61, "learning_rate": 5.880218156126999e-05, "loss": 0.0128, "step": 194150 }, { "epoch": 46.61, "learning_rate": 5.879864802807191e-05, "loss": 0.0117, "step": 194160 }, { "epoch": 46.61, "learning_rate": 5.8795114449525536e-05, "loss": 0.007, "step": 194170 }, { "epoch": 46.61, "learning_rate": 5.8791580825649065e-05, "loss": 0.0053, "step": 194180 }, { "epoch": 46.62, "learning_rate": 5.878804715646071e-05, "loss": 0.0087, "step": 194190 }, { "epoch": 46.62, "learning_rate": 5.878451344197868e-05, "loss": 0.0091, "step": 194200 }, { "epoch": 46.62, "learning_rate": 5.878097968222121e-05, "loss": 0.0195, "step": 194210 }, { "epoch": 46.62, "learning_rate": 5.8777445877206504e-05, "loss": 0.0067, "step": 194220 }, { "epoch": 46.62, "learning_rate": 5.877391202695275e-05, "loss": 0.0075, "step": 194230 }, { "epoch": 46.63, "learning_rate": 5.877037813147819e-05, "loss": 0.0141, "step": 194240 }, { "epoch": 46.63, "learning_rate": 5.876684419080101e-05, "loss": 0.0165, "step": 194250 }, { "epoch": 46.63, "learning_rate": 5.8763310204939446e-05, "loss": 0.006, "step": 194260 }, { "epoch": 46.63, "learning_rate": 5.875977617391173e-05, "loss": 0.0112, "step": 194270 }, { "epoch": 46.64, "learning_rate": 5.8756242097736035e-05, "loss": 0.0042, "step": 194280 }, { "epoch": 46.64, "learning_rate": 5.875270797643061e-05, "loss": 0.0108, "step": 194290 }, { "epoch": 46.64, "learning_rate": 5.8749173810013646e-05, "loss": 0.0037, "step": 194300 }, { "epoch": 46.64, "learning_rate": 5.8745639598503366e-05, "loss": 0.004, "step": 194310 }, { "epoch": 46.64, "learning_rate": 5.874210534191798e-05, "loss": 0.0097, "step": 194320 }, { "epoch": 46.65, "learning_rate": 5.8738571040275726e-05, "loss": 0.0081, "step": 194330 }, { "epoch": 46.65, "learning_rate": 5.873503669359479e-05, "loss": 0.0104, "step": 194340 }, { "epoch": 46.65, "learning_rate": 5.8731502301893415e-05, "loss": 0.015, "step": 194350 }, { "epoch": 46.65, "learning_rate": 5.8727967865189804e-05, "loss": 0.0098, "step": 194360 }, { "epoch": 46.66, "learning_rate": 5.872443338350216e-05, "loss": 0.0123, "step": 194370 }, { "epoch": 46.66, "learning_rate": 5.872089885684873e-05, "loss": 0.0096, "step": 194380 }, { "epoch": 46.66, "learning_rate": 5.87173642852477e-05, "loss": 0.0074, "step": 194390 }, { "epoch": 46.66, "learning_rate": 5.871382966871729e-05, "loss": 0.0113, "step": 194400 }, { "epoch": 46.67, "learning_rate": 5.871029500727575e-05, "loss": 0.0146, "step": 194410 }, { "epoch": 46.67, "learning_rate": 5.870676030094127e-05, "loss": 0.006, "step": 194420 }, { "epoch": 46.67, "learning_rate": 5.8703225549732086e-05, "loss": 0.0141, "step": 194430 }, { "epoch": 46.67, "learning_rate": 5.869969075366639e-05, "loss": 0.0108, "step": 194440 }, { "epoch": 46.67, "learning_rate": 5.869615591276242e-05, "loss": 0.0077, "step": 194450 }, { "epoch": 46.68, "learning_rate": 5.8692621027038395e-05, "loss": 0.0046, "step": 194460 }, { "epoch": 46.68, "learning_rate": 5.868908609651252e-05, "loss": 0.0131, "step": 194470 }, { "epoch": 46.68, "learning_rate": 5.868555112120302e-05, "loss": 0.007, "step": 194480 }, { "epoch": 46.68, "learning_rate": 5.8682016101128126e-05, "loss": 0.0116, "step": 194490 }, { "epoch": 46.69, "learning_rate": 5.867848103630605e-05, "loss": 0.0042, "step": 194500 }, { "epoch": 46.69, "learning_rate": 5.867494592675501e-05, "loss": 0.0103, "step": 194510 }, { "epoch": 46.69, "learning_rate": 5.867141077249323e-05, "loss": 0.0097, "step": 194520 }, { "epoch": 46.69, "learning_rate": 5.866787557353891e-05, "loss": 0.0075, "step": 194530 }, { "epoch": 46.7, "learning_rate": 5.8664340329910296e-05, "loss": 0.0094, "step": 194540 }, { "epoch": 46.7, "learning_rate": 5.86608050416256e-05, "loss": 0.011, "step": 194550 }, { "epoch": 46.7, "learning_rate": 5.865726970870302e-05, "loss": 0.0073, "step": 194560 }, { "epoch": 46.7, "learning_rate": 5.865373433116082e-05, "loss": 0.0166, "step": 194570 }, { "epoch": 46.7, "learning_rate": 5.8650198909017217e-05, "loss": 0.0165, "step": 194580 }, { "epoch": 46.71, "learning_rate": 5.8646663442290404e-05, "loss": 0.0306, "step": 194590 }, { "epoch": 46.71, "learning_rate": 5.8643127930998607e-05, "loss": 0.0094, "step": 194600 }, { "epoch": 46.71, "learning_rate": 5.8639592375160066e-05, "loss": 0.0105, "step": 194610 }, { "epoch": 46.71, "learning_rate": 5.863605677479299e-05, "loss": 0.0048, "step": 194620 }, { "epoch": 46.72, "learning_rate": 5.86325211299156e-05, "loss": 0.0079, "step": 194630 }, { "epoch": 46.72, "learning_rate": 5.862898544054612e-05, "loss": 0.0051, "step": 194640 }, { "epoch": 46.72, "learning_rate": 5.862544970670281e-05, "loss": 0.0061, "step": 194650 }, { "epoch": 46.72, "learning_rate": 5.862191392840383e-05, "loss": 0.0042, "step": 194660 }, { "epoch": 46.72, "learning_rate": 5.8618378105667436e-05, "loss": 0.006, "step": 194670 }, { "epoch": 46.73, "learning_rate": 5.8614842238511855e-05, "loss": 0.0075, "step": 194680 }, { "epoch": 46.73, "learning_rate": 5.861130632695531e-05, "loss": 0.0044, "step": 194690 }, { "epoch": 46.73, "learning_rate": 5.8607770371016e-05, "loss": 0.0088, "step": 194700 }, { "epoch": 46.73, "learning_rate": 5.8604234370712186e-05, "loss": 0.0054, "step": 194710 }, { "epoch": 46.74, "learning_rate": 5.860069832606208e-05, "loss": 0.013, "step": 194720 }, { "epoch": 46.74, "learning_rate": 5.859716223708388e-05, "loss": 0.0127, "step": 194730 }, { "epoch": 46.74, "learning_rate": 5.859362610379585e-05, "loss": 0.0077, "step": 194740 }, { "epoch": 46.74, "learning_rate": 5.85900899262162e-05, "loss": 0.0068, "step": 194750 }, { "epoch": 46.75, "learning_rate": 5.858655370436315e-05, "loss": 0.0104, "step": 194760 }, { "epoch": 46.75, "learning_rate": 5.858301743825494e-05, "loss": 0.0071, "step": 194770 }, { "epoch": 46.75, "learning_rate": 5.857948112790977e-05, "loss": 0.005, "step": 194780 }, { "epoch": 46.75, "learning_rate": 5.8575944773345915e-05, "loss": 0.0113, "step": 194790 }, { "epoch": 46.75, "learning_rate": 5.857240837458155e-05, "loss": 0.0055, "step": 194800 }, { "epoch": 46.76, "learning_rate": 5.8568871931634905e-05, "loss": 0.0117, "step": 194810 }, { "epoch": 46.76, "learning_rate": 5.856533544452424e-05, "loss": 0.0066, "step": 194820 }, { "epoch": 46.76, "learning_rate": 5.856179891326775e-05, "loss": 0.0059, "step": 194830 }, { "epoch": 46.76, "learning_rate": 5.8558262337883686e-05, "loss": 0.0217, "step": 194840 }, { "epoch": 46.77, "learning_rate": 5.855472571839027e-05, "loss": 0.0088, "step": 194850 }, { "epoch": 46.77, "learning_rate": 5.855118905480572e-05, "loss": 0.0163, "step": 194860 }, { "epoch": 46.77, "learning_rate": 5.854765234714827e-05, "loss": 0.0063, "step": 194870 }, { "epoch": 46.77, "learning_rate": 5.854411559543616e-05, "loss": 0.0144, "step": 194880 }, { "epoch": 46.78, "learning_rate": 5.854057879968759e-05, "loss": 0.0051, "step": 194890 }, { "epoch": 46.78, "learning_rate": 5.8537041959920814e-05, "loss": 0.0151, "step": 194900 }, { "epoch": 46.78, "learning_rate": 5.853350507615405e-05, "loss": 0.0067, "step": 194910 }, { "epoch": 46.78, "learning_rate": 5.8529968148405535e-05, "loss": 0.008, "step": 194920 }, { "epoch": 46.78, "learning_rate": 5.8526431176693486e-05, "loss": 0.0081, "step": 194930 }, { "epoch": 46.79, "learning_rate": 5.852289416103615e-05, "loss": 0.0127, "step": 194940 }, { "epoch": 46.79, "learning_rate": 5.8519357101451735e-05, "loss": 0.0085, "step": 194950 }, { "epoch": 46.79, "learning_rate": 5.851581999795849e-05, "loss": 0.0075, "step": 194960 }, { "epoch": 46.79, "learning_rate": 5.851228285057463e-05, "loss": 0.0064, "step": 194970 }, { "epoch": 46.8, "learning_rate": 5.85087456593184e-05, "loss": 0.0037, "step": 194980 }, { "epoch": 46.8, "learning_rate": 5.850520842420801e-05, "loss": 0.0085, "step": 194990 }, { "epoch": 46.8, "learning_rate": 5.8501671145261715e-05, "loss": 0.0053, "step": 195000 }, { "epoch": 46.8, "learning_rate": 5.8498133822497735e-05, "loss": 0.0058, "step": 195010 }, { "epoch": 46.8, "learning_rate": 5.849459645593431e-05, "loss": 0.0072, "step": 195020 }, { "epoch": 46.81, "learning_rate": 5.849105904558966e-05, "loss": 0.0105, "step": 195030 }, { "epoch": 46.81, "learning_rate": 5.8487521591482005e-05, "loss": 0.0094, "step": 195040 }, { "epoch": 46.81, "learning_rate": 5.8483984093629606e-05, "loss": 0.0066, "step": 195050 }, { "epoch": 46.81, "learning_rate": 5.848044655205068e-05, "loss": 0.0078, "step": 195060 }, { "epoch": 46.82, "learning_rate": 5.8476908966763464e-05, "loss": 0.0101, "step": 195070 }, { "epoch": 46.82, "learning_rate": 5.84733713377862e-05, "loss": 0.0062, "step": 195080 }, { "epoch": 46.82, "learning_rate": 5.84698336651371e-05, "loss": 0.009, "step": 195090 }, { "epoch": 46.82, "learning_rate": 5.84662959488344e-05, "loss": 0.0095, "step": 195100 }, { "epoch": 46.83, "learning_rate": 5.846275818889634e-05, "loss": 0.0096, "step": 195110 }, { "epoch": 46.83, "learning_rate": 5.8459220385341165e-05, "loss": 0.0079, "step": 195120 }, { "epoch": 46.83, "learning_rate": 5.845568253818708e-05, "loss": 0.0092, "step": 195130 }, { "epoch": 46.83, "learning_rate": 5.845214464745234e-05, "loss": 0.0056, "step": 195140 }, { "epoch": 46.83, "learning_rate": 5.8448606713155186e-05, "loss": 0.0058, "step": 195150 }, { "epoch": 46.84, "learning_rate": 5.8445068735313834e-05, "loss": 0.0165, "step": 195160 }, { "epoch": 46.84, "learning_rate": 5.8441530713946536e-05, "loss": 0.0111, "step": 195170 }, { "epoch": 46.84, "learning_rate": 5.843799264907152e-05, "loss": 0.0072, "step": 195180 }, { "epoch": 46.84, "learning_rate": 5.8434454540707004e-05, "loss": 0.0063, "step": 195190 }, { "epoch": 46.85, "learning_rate": 5.843091638887125e-05, "loss": 0.0066, "step": 195200 }, { "epoch": 46.85, "learning_rate": 5.842737819358247e-05, "loss": 0.0079, "step": 195210 }, { "epoch": 46.85, "learning_rate": 5.842383995485894e-05, "loss": 0.0064, "step": 195220 }, { "epoch": 46.85, "learning_rate": 5.842030167271885e-05, "loss": 0.0066, "step": 195230 }, { "epoch": 46.86, "learning_rate": 5.8416763347180446e-05, "loss": 0.0054, "step": 195240 }, { "epoch": 46.86, "learning_rate": 5.8413224978261984e-05, "loss": 0.0055, "step": 195250 }, { "epoch": 46.86, "learning_rate": 5.840968656598169e-05, "loss": 0.0198, "step": 195260 }, { "epoch": 46.86, "learning_rate": 5.84061481103578e-05, "loss": 0.0181, "step": 195270 }, { "epoch": 46.86, "learning_rate": 5.8402609611408554e-05, "loss": 0.0069, "step": 195280 }, { "epoch": 46.87, "learning_rate": 5.839907106915219e-05, "loss": 0.0125, "step": 195290 }, { "epoch": 46.87, "learning_rate": 5.839553248360693e-05, "loss": 0.0084, "step": 195300 }, { "epoch": 46.87, "learning_rate": 5.839199385479104e-05, "loss": 0.0063, "step": 195310 }, { "epoch": 46.87, "learning_rate": 5.8388455182722735e-05, "loss": 0.0125, "step": 195320 }, { "epoch": 46.88, "learning_rate": 5.838491646742027e-05, "loss": 0.0051, "step": 195330 }, { "epoch": 46.88, "learning_rate": 5.8381377708901864e-05, "loss": 0.0093, "step": 195340 }, { "epoch": 46.88, "learning_rate": 5.837783890718578e-05, "loss": 0.0071, "step": 195350 }, { "epoch": 46.88, "learning_rate": 5.8374300062290235e-05, "loss": 0.0091, "step": 195360 }, { "epoch": 46.88, "learning_rate": 5.837076117423349e-05, "loss": 0.0133, "step": 195370 }, { "epoch": 46.89, "learning_rate": 5.836722224303376e-05, "loss": 0.0121, "step": 195380 }, { "epoch": 46.89, "learning_rate": 5.83636832687093e-05, "loss": 0.0087, "step": 195390 }, { "epoch": 46.89, "learning_rate": 5.8360144251278345e-05, "loss": 0.0093, "step": 195400 }, { "epoch": 46.89, "learning_rate": 5.835660519075914e-05, "loss": 0.0135, "step": 195410 }, { "epoch": 46.9, "learning_rate": 5.835306608716992e-05, "loss": 0.0047, "step": 195420 }, { "epoch": 46.9, "learning_rate": 5.834952694052892e-05, "loss": 0.0057, "step": 195430 }, { "epoch": 46.9, "learning_rate": 5.83459877508544e-05, "loss": 0.0066, "step": 195440 }, { "epoch": 46.9, "learning_rate": 5.834244851816458e-05, "loss": 0.0075, "step": 195450 }, { "epoch": 46.91, "learning_rate": 5.833890924247771e-05, "loss": 0.0053, "step": 195460 }, { "epoch": 46.91, "learning_rate": 5.8335369923812045e-05, "loss": 0.0148, "step": 195470 }, { "epoch": 46.91, "learning_rate": 5.833183056218581e-05, "loss": 0.0096, "step": 195480 }, { "epoch": 46.91, "learning_rate": 5.832829115761724e-05, "loss": 0.0126, "step": 195490 }, { "epoch": 46.91, "learning_rate": 5.832475171012459e-05, "loss": 0.0042, "step": 195500 }, { "epoch": 46.92, "learning_rate": 5.832121221972612e-05, "loss": 0.0047, "step": 195510 }, { "epoch": 46.92, "learning_rate": 5.8317672686440036e-05, "loss": 0.0093, "step": 195520 }, { "epoch": 46.92, "learning_rate": 5.83141331102846e-05, "loss": 0.0051, "step": 195530 }, { "epoch": 46.92, "learning_rate": 5.831059349127806e-05, "loss": 0.009, "step": 195540 }, { "epoch": 46.93, "learning_rate": 5.830705382943863e-05, "loss": 0.0044, "step": 195550 }, { "epoch": 46.93, "learning_rate": 5.830351412478459e-05, "loss": 0.0052, "step": 195560 }, { "epoch": 46.93, "learning_rate": 5.829997437733417e-05, "loss": 0.0057, "step": 195570 }, { "epoch": 46.93, "learning_rate": 5.829643458710562e-05, "loss": 0.007, "step": 195580 }, { "epoch": 46.94, "learning_rate": 5.829289475411717e-05, "loss": 0.0056, "step": 195590 }, { "epoch": 46.94, "learning_rate": 5.828935487838705e-05, "loss": 0.009, "step": 195600 }, { "epoch": 46.94, "learning_rate": 5.828581495993354e-05, "loss": 0.0087, "step": 195610 }, { "epoch": 46.94, "learning_rate": 5.828227499877488e-05, "loss": 0.0092, "step": 195620 }, { "epoch": 46.94, "learning_rate": 5.8278734994929285e-05, "loss": 0.0077, "step": 195630 }, { "epoch": 46.95, "learning_rate": 5.827519494841504e-05, "loss": 0.0051, "step": 195640 }, { "epoch": 46.95, "learning_rate": 5.827165485925038e-05, "loss": 0.007, "step": 195650 }, { "epoch": 46.95, "learning_rate": 5.826811472745353e-05, "loss": 0.0047, "step": 195660 }, { "epoch": 47.0, "learning_rate": 5.826457455304274e-05, "loss": 0.0061, "step": 195670 }, { "epoch": 47.0, "learning_rate": 5.826103433603627e-05, "loss": 0.0073, "step": 195680 }, { "epoch": 47.01, "learning_rate": 5.825749407645236e-05, "loss": 0.0062, "step": 195690 }, { "epoch": 47.01, "learning_rate": 5.8253953774309246e-05, "loss": 0.0167, "step": 195700 }, { "epoch": 47.01, "learning_rate": 5.82504134296252e-05, "loss": 0.0041, "step": 195710 }, { "epoch": 47.01, "learning_rate": 5.824687304241845e-05, "loss": 0.0083, "step": 195720 }, { "epoch": 47.02, "learning_rate": 5.8243332612707245e-05, "loss": 0.0057, "step": 195730 }, { "epoch": 47.02, "learning_rate": 5.823979214050984e-05, "loss": 0.0108, "step": 195740 }, { "epoch": 47.02, "learning_rate": 5.823625162584447e-05, "loss": 0.0054, "step": 195750 }, { "epoch": 47.02, "learning_rate": 5.8232711068729384e-05, "loss": 0.0062, "step": 195760 }, { "epoch": 47.02, "learning_rate": 5.8229170469182845e-05, "loss": 0.0038, "step": 195770 }, { "epoch": 47.03, "learning_rate": 5.8225629827223096e-05, "loss": 0.008, "step": 195780 }, { "epoch": 47.03, "learning_rate": 5.822208914286837e-05, "loss": 0.0104, "step": 195790 }, { "epoch": 47.03, "learning_rate": 5.8218548416136956e-05, "loss": 0.0058, "step": 195800 }, { "epoch": 47.03, "learning_rate": 5.821500764704706e-05, "loss": 0.0116, "step": 195810 }, { "epoch": 47.04, "learning_rate": 5.821146683561693e-05, "loss": 0.0099, "step": 195820 }, { "epoch": 47.04, "learning_rate": 5.8207925981864855e-05, "loss": 0.0119, "step": 195830 }, { "epoch": 47.04, "learning_rate": 5.8204385085809046e-05, "loss": 0.008, "step": 195840 }, { "epoch": 47.04, "learning_rate": 5.820084414746777e-05, "loss": 0.0102, "step": 195850 }, { "epoch": 47.05, "learning_rate": 5.819730316685927e-05, "loss": 0.0065, "step": 195860 }, { "epoch": 47.05, "learning_rate": 5.8193762144001816e-05, "loss": 0.0052, "step": 195870 }, { "epoch": 47.05, "learning_rate": 5.819022107891363e-05, "loss": 0.0079, "step": 195880 }, { "epoch": 47.05, "learning_rate": 5.818667997161299e-05, "loss": 0.0113, "step": 195890 }, { "epoch": 47.05, "learning_rate": 5.818313882211812e-05, "loss": 0.0127, "step": 195900 }, { "epoch": 47.06, "learning_rate": 5.817959763044729e-05, "loss": 0.0054, "step": 195910 }, { "epoch": 47.06, "learning_rate": 5.8176056396618725e-05, "loss": 0.008, "step": 195920 }, { "epoch": 47.06, "learning_rate": 5.8172515120650716e-05, "loss": 0.0096, "step": 195930 }, { "epoch": 47.06, "learning_rate": 5.81689738025615e-05, "loss": 0.0086, "step": 195940 }, { "epoch": 47.07, "learning_rate": 5.8165432442369324e-05, "loss": 0.006, "step": 195950 }, { "epoch": 47.07, "learning_rate": 5.816189104009243e-05, "loss": 0.0097, "step": 195960 }, { "epoch": 47.07, "learning_rate": 5.815834959574909e-05, "loss": 0.0073, "step": 195970 }, { "epoch": 47.07, "learning_rate": 5.8154808109357554e-05, "loss": 0.0039, "step": 195980 }, { "epoch": 47.08, "learning_rate": 5.8151266580936056e-05, "loss": 0.0088, "step": 195990 }, { "epoch": 47.08, "learning_rate": 5.8147725010502864e-05, "loss": 0.0035, "step": 196000 }, { "epoch": 47.08, "learning_rate": 5.814418339807624e-05, "loss": 0.0102, "step": 196010 }, { "epoch": 47.08, "learning_rate": 5.814064174367442e-05, "loss": 0.0124, "step": 196020 }, { "epoch": 47.08, "learning_rate": 5.813710004731566e-05, "loss": 0.0079, "step": 196030 }, { "epoch": 47.09, "learning_rate": 5.813355830901822e-05, "loss": 0.0119, "step": 196040 }, { "epoch": 47.09, "learning_rate": 5.8130016528800356e-05, "loss": 0.0052, "step": 196050 }, { "epoch": 47.09, "learning_rate": 5.812647470668031e-05, "loss": 0.0051, "step": 196060 }, { "epoch": 47.09, "learning_rate": 5.812293284267636e-05, "loss": 0.0077, "step": 196070 }, { "epoch": 47.1, "learning_rate": 5.8119390936806714e-05, "loss": 0.0112, "step": 196080 }, { "epoch": 47.1, "learning_rate": 5.8115848989089705e-05, "loss": 0.0094, "step": 196090 }, { "epoch": 47.1, "learning_rate": 5.811230699954352e-05, "loss": 0.0116, "step": 196100 }, { "epoch": 47.1, "learning_rate": 5.810876496818644e-05, "loss": 0.0083, "step": 196110 }, { "epoch": 47.1, "learning_rate": 5.8105222895036704e-05, "loss": 0.0088, "step": 196120 }, { "epoch": 47.11, "learning_rate": 5.81016807801126e-05, "loss": 0.009, "step": 196130 }, { "epoch": 47.11, "learning_rate": 5.809813862343235e-05, "loss": 0.0115, "step": 196140 }, { "epoch": 47.11, "learning_rate": 5.809459642501424e-05, "loss": 0.009, "step": 196150 }, { "epoch": 47.11, "learning_rate": 5.809105418487651e-05, "loss": 0.0055, "step": 196160 }, { "epoch": 47.12, "learning_rate": 5.8087511903037416e-05, "loss": 0.0062, "step": 196170 }, { "epoch": 47.12, "learning_rate": 5.808396957951522e-05, "loss": 0.011, "step": 196180 }, { "epoch": 47.12, "learning_rate": 5.808042721432817e-05, "loss": 0.0089, "step": 196190 }, { "epoch": 47.12, "learning_rate": 5.8076884807494536e-05, "loss": 0.0091, "step": 196200 }, { "epoch": 47.13, "learning_rate": 5.807334235903257e-05, "loss": 0.013, "step": 196210 }, { "epoch": 47.13, "learning_rate": 5.806979986896053e-05, "loss": 0.0089, "step": 196220 }, { "epoch": 47.13, "learning_rate": 5.806625733729667e-05, "loss": 0.0064, "step": 196230 }, { "epoch": 47.13, "learning_rate": 5.8062714764059254e-05, "loss": 0.0078, "step": 196240 }, { "epoch": 47.13, "learning_rate": 5.8059172149266536e-05, "loss": 0.0079, "step": 196250 }, { "epoch": 47.14, "learning_rate": 5.805562949293679e-05, "loss": 0.0083, "step": 196260 }, { "epoch": 47.14, "learning_rate": 5.8052086795088246e-05, "loss": 0.0036, "step": 196270 }, { "epoch": 47.14, "learning_rate": 5.80485440557392e-05, "loss": 0.0391, "step": 196280 }, { "epoch": 47.14, "learning_rate": 5.804500127490787e-05, "loss": 0.0049, "step": 196290 }, { "epoch": 47.15, "learning_rate": 5.804145845261255e-05, "loss": 0.0106, "step": 196300 }, { "epoch": 47.15, "learning_rate": 5.8037915588871484e-05, "loss": 0.0056, "step": 196310 }, { "epoch": 47.15, "learning_rate": 5.803437268370293e-05, "loss": 0.0054, "step": 196320 }, { "epoch": 47.15, "learning_rate": 5.803082973712515e-05, "loss": 0.02, "step": 196330 }, { "epoch": 47.16, "learning_rate": 5.802728674915641e-05, "loss": 0.0049, "step": 196340 }, { "epoch": 47.16, "learning_rate": 5.802374371981496e-05, "loss": 0.0147, "step": 196350 }, { "epoch": 47.16, "learning_rate": 5.8020200649119075e-05, "loss": 0.0042, "step": 196360 }, { "epoch": 47.16, "learning_rate": 5.8016657537087e-05, "loss": 0.0087, "step": 196370 }, { "epoch": 47.16, "learning_rate": 5.801311438373702e-05, "loss": 0.0061, "step": 196380 }, { "epoch": 47.17, "learning_rate": 5.8009571189087375e-05, "loss": 0.0063, "step": 196390 }, { "epoch": 47.17, "learning_rate": 5.800602795315633e-05, "loss": 0.008, "step": 196400 }, { "epoch": 47.17, "learning_rate": 5.800248467596216e-05, "loss": 0.0041, "step": 196410 }, { "epoch": 47.17, "learning_rate": 5.79989413575231e-05, "loss": 0.0102, "step": 196420 }, { "epoch": 47.18, "learning_rate": 5.799539799785744e-05, "loss": 0.0064, "step": 196430 }, { "epoch": 47.18, "learning_rate": 5.7991854596983445e-05, "loss": 0.0067, "step": 196440 }, { "epoch": 47.18, "learning_rate": 5.7988311154919336e-05, "loss": 0.0068, "step": 196450 }, { "epoch": 47.18, "learning_rate": 5.798476767168343e-05, "loss": 0.0061, "step": 196460 }, { "epoch": 47.18, "learning_rate": 5.7981224147293946e-05, "loss": 0.0092, "step": 196470 }, { "epoch": 47.19, "learning_rate": 5.797768058176917e-05, "loss": 0.0146, "step": 196480 }, { "epoch": 47.19, "learning_rate": 5.797413697512737e-05, "loss": 0.0042, "step": 196490 }, { "epoch": 47.19, "learning_rate": 5.797059332738679e-05, "loss": 0.0251, "step": 196500 }, { "epoch": 47.19, "learning_rate": 5.796704963856571e-05, "loss": 0.005, "step": 196510 }, { "epoch": 47.2, "learning_rate": 5.796350590868239e-05, "loss": 0.0045, "step": 196520 }, { "epoch": 47.2, "learning_rate": 5.79599621377551e-05, "loss": 0.0072, "step": 196530 }, { "epoch": 47.2, "learning_rate": 5.7956418325802084e-05, "loss": 0.0176, "step": 196540 }, { "epoch": 47.2, "learning_rate": 5.7952874472841636e-05, "loss": 0.0076, "step": 196550 }, { "epoch": 47.21, "learning_rate": 5.7949330578892e-05, "loss": 0.0061, "step": 196560 }, { "epoch": 47.21, "learning_rate": 5.794578664397145e-05, "loss": 0.0072, "step": 196570 }, { "epoch": 47.21, "learning_rate": 5.7942242668098244e-05, "loss": 0.003, "step": 196580 }, { "epoch": 47.21, "learning_rate": 5.793869865129067e-05, "loss": 0.0081, "step": 196590 }, { "epoch": 47.21, "learning_rate": 5.7935154593566965e-05, "loss": 0.0045, "step": 196600 }, { "epoch": 47.22, "learning_rate": 5.79316104949454e-05, "loss": 0.0055, "step": 196610 }, { "epoch": 47.22, "learning_rate": 5.7928066355444256e-05, "loss": 0.0048, "step": 196620 }, { "epoch": 47.22, "learning_rate": 5.7924522175081796e-05, "loss": 0.0122, "step": 196630 }, { "epoch": 47.22, "learning_rate": 5.7920977953876274e-05, "loss": 0.0043, "step": 196640 }, { "epoch": 47.23, "learning_rate": 5.7917433691845967e-05, "loss": 0.0045, "step": 196650 }, { "epoch": 47.23, "learning_rate": 5.7913889389009135e-05, "loss": 0.0063, "step": 196660 }, { "epoch": 47.23, "learning_rate": 5.791034504538406e-05, "loss": 0.0067, "step": 196670 }, { "epoch": 47.23, "learning_rate": 5.7906800660989004e-05, "loss": 0.0045, "step": 196680 }, { "epoch": 47.24, "learning_rate": 5.790325623584222e-05, "loss": 0.0049, "step": 196690 }, { "epoch": 47.24, "learning_rate": 5.7899711769961996e-05, "loss": 0.0043, "step": 196700 }, { "epoch": 47.24, "learning_rate": 5.7896167263366585e-05, "loss": 0.0056, "step": 196710 }, { "epoch": 47.24, "learning_rate": 5.789262271607426e-05, "loss": 0.0052, "step": 196720 }, { "epoch": 47.24, "learning_rate": 5.788907812810331e-05, "loss": 0.0105, "step": 196730 }, { "epoch": 47.25, "learning_rate": 5.788553349947197e-05, "loss": 0.0115, "step": 196740 }, { "epoch": 47.25, "learning_rate": 5.788198883019853e-05, "loss": 0.005, "step": 196750 }, { "epoch": 47.25, "learning_rate": 5.787844412030124e-05, "loss": 0.0043, "step": 196760 }, { "epoch": 47.25, "learning_rate": 5.78748993697984e-05, "loss": 0.0104, "step": 196770 }, { "epoch": 47.26, "learning_rate": 5.787135457870825e-05, "loss": 0.0034, "step": 196780 }, { "epoch": 47.26, "learning_rate": 5.786780974704908e-05, "loss": 0.0058, "step": 196790 }, { "epoch": 47.26, "learning_rate": 5.7864264874839144e-05, "loss": 0.0078, "step": 196800 }, { "epoch": 47.26, "learning_rate": 5.7860719962096734e-05, "loss": 0.0059, "step": 196810 }, { "epoch": 47.26, "learning_rate": 5.78571750088401e-05, "loss": 0.013, "step": 196820 }, { "epoch": 47.27, "learning_rate": 5.785363001508752e-05, "loss": 0.0036, "step": 196830 }, { "epoch": 47.27, "learning_rate": 5.785008498085727e-05, "loss": 0.0059, "step": 196840 }, { "epoch": 47.27, "learning_rate": 5.784653990616762e-05, "loss": 0.0051, "step": 196850 }, { "epoch": 47.27, "learning_rate": 5.784299479103683e-05, "loss": 0.0067, "step": 196860 }, { "epoch": 47.28, "learning_rate": 5.783944963548319e-05, "loss": 0.0101, "step": 196870 }, { "epoch": 47.28, "learning_rate": 5.7835904439524946e-05, "loss": 0.0088, "step": 196880 }, { "epoch": 47.28, "learning_rate": 5.7832359203180395e-05, "loss": 0.0094, "step": 196890 }, { "epoch": 47.28, "learning_rate": 5.78288139264678e-05, "loss": 0.0063, "step": 196900 }, { "epoch": 47.29, "learning_rate": 5.7825268609405426e-05, "loss": 0.0058, "step": 196910 }, { "epoch": 47.29, "learning_rate": 5.782172325201155e-05, "loss": 0.0058, "step": 196920 }, { "epoch": 47.29, "learning_rate": 5.7818177854304446e-05, "loss": 0.0078, "step": 196930 }, { "epoch": 47.29, "learning_rate": 5.78146324163024e-05, "loss": 0.0054, "step": 196940 }, { "epoch": 47.29, "learning_rate": 5.7811086938023674e-05, "loss": 0.0149, "step": 196950 }, { "epoch": 47.3, "learning_rate": 5.780754141948652e-05, "loss": 0.0064, "step": 196960 }, { "epoch": 47.3, "learning_rate": 5.780399586070925e-05, "loss": 0.0055, "step": 196970 }, { "epoch": 47.3, "learning_rate": 5.780045026171011e-05, "loss": 0.0104, "step": 196980 }, { "epoch": 47.3, "learning_rate": 5.779690462250739e-05, "loss": 0.0046, "step": 196990 }, { "epoch": 47.31, "learning_rate": 5.7793358943119355e-05, "loss": 0.0071, "step": 197000 }, { "epoch": 47.31, "learning_rate": 5.778981322356428e-05, "loss": 0.0054, "step": 197010 }, { "epoch": 47.31, "learning_rate": 5.7786267463860466e-05, "loss": 0.0085, "step": 197020 }, { "epoch": 47.31, "learning_rate": 5.778272166402614e-05, "loss": 0.0163, "step": 197030 }, { "epoch": 47.32, "learning_rate": 5.777917582407961e-05, "loss": 0.0085, "step": 197040 }, { "epoch": 47.32, "learning_rate": 5.777562994403915e-05, "loss": 0.0058, "step": 197050 }, { "epoch": 47.32, "learning_rate": 5.7772084023923014e-05, "loss": 0.0086, "step": 197060 }, { "epoch": 47.32, "learning_rate": 5.776853806374949e-05, "loss": 0.011, "step": 197070 }, { "epoch": 47.32, "learning_rate": 5.7764992063536875e-05, "loss": 0.013, "step": 197080 }, { "epoch": 47.33, "learning_rate": 5.776144602330341e-05, "loss": 0.0041, "step": 197090 }, { "epoch": 47.33, "learning_rate": 5.77578999430674e-05, "loss": 0.0067, "step": 197100 }, { "epoch": 47.33, "learning_rate": 5.7754353822847096e-05, "loss": 0.0037, "step": 197110 }, { "epoch": 47.33, "learning_rate": 5.775080766266078e-05, "loss": 0.0057, "step": 197120 }, { "epoch": 47.34, "learning_rate": 5.774726146252675e-05, "loss": 0.0073, "step": 197130 }, { "epoch": 47.34, "learning_rate": 5.774371522246327e-05, "loss": 0.0191, "step": 197140 }, { "epoch": 47.34, "learning_rate": 5.774016894248861e-05, "loss": 0.0079, "step": 197150 }, { "epoch": 47.34, "learning_rate": 5.7736622622621074e-05, "loss": 0.0069, "step": 197160 }, { "epoch": 47.34, "learning_rate": 5.7733076262878903e-05, "loss": 0.0045, "step": 197170 }, { "epoch": 47.35, "learning_rate": 5.77295298632804e-05, "loss": 0.0037, "step": 197180 }, { "epoch": 47.35, "learning_rate": 5.7725983423843824e-05, "loss": 0.0098, "step": 197190 }, { "epoch": 47.35, "learning_rate": 5.772243694458748e-05, "loss": 0.0064, "step": 197200 }, { "epoch": 47.35, "learning_rate": 5.771889042552961e-05, "loss": 0.0072, "step": 197210 }, { "epoch": 47.36, "learning_rate": 5.7715343866688534e-05, "loss": 0.0046, "step": 197220 }, { "epoch": 47.36, "learning_rate": 5.771179726808251e-05, "loss": 0.0131, "step": 197230 }, { "epoch": 47.36, "learning_rate": 5.770825062972981e-05, "loss": 0.006, "step": 197240 }, { "epoch": 47.36, "learning_rate": 5.770470395164873e-05, "loss": 0.0066, "step": 197250 }, { "epoch": 47.37, "learning_rate": 5.770115723385754e-05, "loss": 0.0067, "step": 197260 }, { "epoch": 47.37, "learning_rate": 5.7697610476374496e-05, "loss": 0.0068, "step": 197270 }, { "epoch": 47.37, "learning_rate": 5.7694063679217925e-05, "loss": 0.0063, "step": 197280 }, { "epoch": 47.37, "learning_rate": 5.7690516842406084e-05, "loss": 0.0119, "step": 197290 }, { "epoch": 47.37, "learning_rate": 5.768696996595726e-05, "loss": 0.0081, "step": 197300 }, { "epoch": 47.38, "learning_rate": 5.7683423049889726e-05, "loss": 0.0064, "step": 197310 }, { "epoch": 47.38, "learning_rate": 5.7679876094221774e-05, "loss": 0.0062, "step": 197320 }, { "epoch": 47.38, "learning_rate": 5.767632909897166e-05, "loss": 0.0149, "step": 197330 }, { "epoch": 47.38, "learning_rate": 5.7672782064157696e-05, "loss": 0.0125, "step": 197340 }, { "epoch": 47.39, "learning_rate": 5.7669234989798134e-05, "loss": 0.006, "step": 197350 }, { "epoch": 47.39, "learning_rate": 5.766568787591128e-05, "loss": 0.005, "step": 197360 }, { "epoch": 47.39, "learning_rate": 5.76621407225154e-05, "loss": 0.0054, "step": 197370 }, { "epoch": 47.39, "learning_rate": 5.76585935296288e-05, "loss": 0.0159, "step": 197380 }, { "epoch": 47.4, "learning_rate": 5.765504629726973e-05, "loss": 0.0094, "step": 197390 }, { "epoch": 47.4, "learning_rate": 5.765149902545649e-05, "loss": 0.0045, "step": 197400 }, { "epoch": 47.4, "learning_rate": 5.764795171420736e-05, "loss": 0.0083, "step": 197410 }, { "epoch": 47.4, "learning_rate": 5.7644404363540616e-05, "loss": 0.0063, "step": 197420 }, { "epoch": 47.4, "learning_rate": 5.764085697347454e-05, "loss": 0.014, "step": 197430 }, { "epoch": 47.41, "learning_rate": 5.763730954402744e-05, "loss": 0.0117, "step": 197440 }, { "epoch": 47.41, "learning_rate": 5.76337620752176e-05, "loss": 0.0098, "step": 197450 }, { "epoch": 47.41, "learning_rate": 5.7630214567063257e-05, "loss": 0.0052, "step": 197460 }, { "epoch": 47.41, "learning_rate": 5.7626667019582736e-05, "loss": 0.0039, "step": 197470 }, { "epoch": 47.42, "learning_rate": 5.7623119432794316e-05, "loss": 0.0113, "step": 197480 }, { "epoch": 47.42, "learning_rate": 5.7619571806716266e-05, "loss": 0.0069, "step": 197490 }, { "epoch": 47.42, "learning_rate": 5.7616024141366876e-05, "loss": 0.006, "step": 197500 }, { "epoch": 47.42, "learning_rate": 5.761247643676444e-05, "loss": 0.0061, "step": 197510 }, { "epoch": 47.42, "learning_rate": 5.760892869292724e-05, "loss": 0.0066, "step": 197520 }, { "epoch": 47.43, "learning_rate": 5.760538090987355e-05, "loss": 0.0062, "step": 197530 }, { "epoch": 47.43, "learning_rate": 5.7601833087621674e-05, "loss": 0.0056, "step": 197540 }, { "epoch": 47.43, "learning_rate": 5.7598285226189875e-05, "loss": 0.0068, "step": 197550 }, { "epoch": 47.43, "learning_rate": 5.759473732559645e-05, "loss": 0.0098, "step": 197560 }, { "epoch": 47.44, "learning_rate": 5.759118938585969e-05, "loss": 0.008, "step": 197570 }, { "epoch": 47.44, "learning_rate": 5.758764140699787e-05, "loss": 0.013, "step": 197580 }, { "epoch": 47.44, "learning_rate": 5.7584093389029294e-05, "loss": 0.006, "step": 197590 }, { "epoch": 47.44, "learning_rate": 5.758054533197223e-05, "loss": 0.0127, "step": 197600 }, { "epoch": 47.45, "learning_rate": 5.7576997235844974e-05, "loss": 0.0042, "step": 197610 }, { "epoch": 47.45, "learning_rate": 5.757344910066581e-05, "loss": 0.0046, "step": 197620 }, { "epoch": 47.45, "learning_rate": 5.7569900926453026e-05, "loss": 0.0064, "step": 197630 }, { "epoch": 47.45, "learning_rate": 5.75663527132249e-05, "loss": 0.0096, "step": 197640 }, { "epoch": 47.45, "learning_rate": 5.756280446099974e-05, "loss": 0.0066, "step": 197650 }, { "epoch": 47.46, "learning_rate": 5.755925616979584e-05, "loss": 0.0054, "step": 197660 }, { "epoch": 47.46, "learning_rate": 5.7555707839631446e-05, "loss": 0.0084, "step": 197670 }, { "epoch": 47.46, "learning_rate": 5.755215947052488e-05, "loss": 0.0055, "step": 197680 }, { "epoch": 47.46, "learning_rate": 5.754861106249442e-05, "loss": 0.0052, "step": 197690 }, { "epoch": 47.47, "learning_rate": 5.754506261555834e-05, "loss": 0.0047, "step": 197700 }, { "epoch": 47.47, "learning_rate": 5.7541514129734964e-05, "loss": 0.0103, "step": 197710 }, { "epoch": 47.47, "learning_rate": 5.7537965605042554e-05, "loss": 0.0041, "step": 197720 }, { "epoch": 47.47, "learning_rate": 5.75344170414994e-05, "loss": 0.0063, "step": 197730 }, { "epoch": 47.48, "learning_rate": 5.753086843912381e-05, "loss": 0.0158, "step": 197740 }, { "epoch": 47.48, "learning_rate": 5.752731979793405e-05, "loss": 0.0054, "step": 197750 }, { "epoch": 47.48, "learning_rate": 5.752377111794843e-05, "loss": 0.0088, "step": 197760 }, { "epoch": 47.48, "learning_rate": 5.752022239918522e-05, "loss": 0.01, "step": 197770 }, { "epoch": 47.48, "learning_rate": 5.751667364166273e-05, "loss": 0.0056, "step": 197780 }, { "epoch": 47.49, "learning_rate": 5.751312484539923e-05, "loss": 0.0054, "step": 197790 }, { "epoch": 47.49, "learning_rate": 5.750957601041305e-05, "loss": 0.0101, "step": 197800 }, { "epoch": 47.49, "learning_rate": 5.750602713672244e-05, "loss": 0.0105, "step": 197810 }, { "epoch": 47.49, "learning_rate": 5.750247822434569e-05, "loss": 0.0049, "step": 197820 }, { "epoch": 47.5, "learning_rate": 5.7498929273301115e-05, "loss": 0.017, "step": 197830 }, { "epoch": 47.5, "learning_rate": 5.749538028360699e-05, "loss": 0.0049, "step": 197840 }, { "epoch": 47.5, "learning_rate": 5.749183125528161e-05, "loss": 0.0094, "step": 197850 }, { "epoch": 47.5, "learning_rate": 5.748828218834328e-05, "loss": 0.0043, "step": 197860 }, { "epoch": 47.5, "learning_rate": 5.748473308281027e-05, "loss": 0.005, "step": 197870 }, { "epoch": 47.51, "learning_rate": 5.748118393870089e-05, "loss": 0.0057, "step": 197880 }, { "epoch": 47.51, "learning_rate": 5.747763475603342e-05, "loss": 0.0032, "step": 197890 }, { "epoch": 47.51, "learning_rate": 5.747408553482616e-05, "loss": 0.0087, "step": 197900 }, { "epoch": 47.51, "learning_rate": 5.74705362750974e-05, "loss": 0.0071, "step": 197910 }, { "epoch": 47.52, "learning_rate": 5.746698697686543e-05, "loss": 0.0103, "step": 197920 }, { "epoch": 47.52, "learning_rate": 5.7463437640148556e-05, "loss": 0.0053, "step": 197930 }, { "epoch": 47.52, "learning_rate": 5.7459888264965054e-05, "loss": 0.0096, "step": 197940 }, { "epoch": 47.52, "learning_rate": 5.7456338851333243e-05, "loss": 0.0033, "step": 197950 }, { "epoch": 47.53, "learning_rate": 5.745278939927139e-05, "loss": 0.0072, "step": 197960 }, { "epoch": 47.53, "learning_rate": 5.744923990879779e-05, "loss": 0.0037, "step": 197970 }, { "epoch": 47.53, "learning_rate": 5.744569037993075e-05, "loss": 0.0097, "step": 197980 }, { "epoch": 47.53, "learning_rate": 5.744214081268855e-05, "loss": 0.0301, "step": 197990 }, { "epoch": 47.53, "learning_rate": 5.743859120708951e-05, "loss": 0.0066, "step": 198000 }, { "epoch": 47.54, "learning_rate": 5.7435041563151895e-05, "loss": 0.0075, "step": 198010 }, { "epoch": 47.54, "learning_rate": 5.743149188089403e-05, "loss": 0.0082, "step": 198020 }, { "epoch": 47.54, "learning_rate": 5.742794216033418e-05, "loss": 0.0135, "step": 198030 }, { "epoch": 47.54, "learning_rate": 5.742439240149066e-05, "loss": 0.0149, "step": 198040 }, { "epoch": 47.55, "learning_rate": 5.742084260438175e-05, "loss": 0.0311, "step": 198050 }, { "epoch": 47.55, "learning_rate": 5.741729276902577e-05, "loss": 0.0062, "step": 198060 }, { "epoch": 47.55, "learning_rate": 5.741374289544098e-05, "loss": 0.0093, "step": 198070 }, { "epoch": 47.55, "learning_rate": 5.7410192983645714e-05, "loss": 0.0122, "step": 198080 }, { "epoch": 47.56, "learning_rate": 5.740664303365825e-05, "loss": 0.0157, "step": 198090 }, { "epoch": 47.56, "learning_rate": 5.740309304549689e-05, "loss": 0.0185, "step": 198100 }, { "epoch": 47.56, "learning_rate": 5.7399543019179925e-05, "loss": 0.0117, "step": 198110 }, { "epoch": 47.56, "learning_rate": 5.739599295472564e-05, "loss": 0.0058, "step": 198120 }, { "epoch": 47.56, "learning_rate": 5.7392442852152365e-05, "loss": 0.0167, "step": 198130 }, { "epoch": 47.57, "learning_rate": 5.738889271147836e-05, "loss": 0.0078, "step": 198140 }, { "epoch": 47.57, "learning_rate": 5.7385342532721954e-05, "loss": 0.0147, "step": 198150 }, { "epoch": 47.57, "learning_rate": 5.738179231590142e-05, "loss": 0.0119, "step": 198160 }, { "epoch": 47.57, "learning_rate": 5.737824206103507e-05, "loss": 0.0192, "step": 198170 }, { "epoch": 47.58, "learning_rate": 5.73746917681412e-05, "loss": 0.0131, "step": 198180 }, { "epoch": 47.58, "learning_rate": 5.7371141437238105e-05, "loss": 0.0073, "step": 198190 }, { "epoch": 47.58, "learning_rate": 5.7367591068344085e-05, "loss": 0.0112, "step": 198200 }, { "epoch": 47.58, "learning_rate": 5.736404066147745e-05, "loss": 0.0056, "step": 198210 }, { "epoch": 47.58, "learning_rate": 5.736049021665647e-05, "loss": 0.0142, "step": 198220 }, { "epoch": 47.59, "learning_rate": 5.735693973389947e-05, "loss": 0.0072, "step": 198230 }, { "epoch": 47.59, "learning_rate": 5.735338921322475e-05, "loss": 0.0067, "step": 198240 }, { "epoch": 47.59, "learning_rate": 5.73498386546506e-05, "loss": 0.011, "step": 198250 }, { "epoch": 47.59, "learning_rate": 5.734628805819531e-05, "loss": 0.0133, "step": 198260 }, { "epoch": 47.6, "learning_rate": 5.734273742387719e-05, "loss": 0.0068, "step": 198270 }, { "epoch": 47.6, "learning_rate": 5.7339186751714544e-05, "loss": 0.0123, "step": 198280 }, { "epoch": 47.6, "learning_rate": 5.733563604172567e-05, "loss": 0.0075, "step": 198290 }, { "epoch": 47.6, "learning_rate": 5.733208529392886e-05, "loss": 0.0089, "step": 198300 }, { "epoch": 47.61, "learning_rate": 5.732853450834244e-05, "loss": 0.0048, "step": 198310 }, { "epoch": 47.61, "learning_rate": 5.732498368498466e-05, "loss": 0.0102, "step": 198320 }, { "epoch": 47.61, "learning_rate": 5.7321432823873864e-05, "loss": 0.0085, "step": 198330 }, { "epoch": 47.61, "learning_rate": 5.731788192502835e-05, "loss": 0.005, "step": 198340 }, { "epoch": 47.61, "learning_rate": 5.7314330988466406e-05, "loss": 0.0112, "step": 198350 }, { "epoch": 47.62, "learning_rate": 5.731078001420635e-05, "loss": 0.0129, "step": 198360 }, { "epoch": 47.62, "learning_rate": 5.730722900226646e-05, "loss": 0.0145, "step": 198370 }, { "epoch": 47.62, "learning_rate": 5.730367795266506e-05, "loss": 0.0117, "step": 198380 }, { "epoch": 47.62, "learning_rate": 5.7300126865420435e-05, "loss": 0.0148, "step": 198390 }, { "epoch": 47.63, "learning_rate": 5.72965757405509e-05, "loss": 0.0067, "step": 198400 }, { "epoch": 47.63, "learning_rate": 5.729302457807475e-05, "loss": 0.0083, "step": 198410 }, { "epoch": 47.63, "learning_rate": 5.728947337801029e-05, "loss": 0.0091, "step": 198420 }, { "epoch": 47.63, "learning_rate": 5.728592214037582e-05, "loss": 0.0074, "step": 198430 }, { "epoch": 47.64, "learning_rate": 5.728237086518966e-05, "loss": 0.0234, "step": 198440 }, { "epoch": 47.64, "learning_rate": 5.72788195524701e-05, "loss": 0.0142, "step": 198450 }, { "epoch": 47.64, "learning_rate": 5.7275268202235434e-05, "loss": 0.0182, "step": 198460 }, { "epoch": 47.64, "learning_rate": 5.727171681450396e-05, "loss": 0.0111, "step": 198470 }, { "epoch": 47.64, "learning_rate": 5.7268165389294004e-05, "loss": 0.0048, "step": 198480 }, { "epoch": 47.65, "learning_rate": 5.726461392662388e-05, "loss": 0.0098, "step": 198490 }, { "epoch": 47.65, "learning_rate": 5.7261062426511856e-05, "loss": 0.0105, "step": 198500 }, { "epoch": 47.65, "learning_rate": 5.725751088897626e-05, "loss": 0.0052, "step": 198510 }, { "epoch": 47.65, "learning_rate": 5.72539593140354e-05, "loss": 0.0072, "step": 198520 }, { "epoch": 47.66, "learning_rate": 5.7250407701707575e-05, "loss": 0.0058, "step": 198530 }, { "epoch": 47.66, "learning_rate": 5.724685605201109e-05, "loss": 0.0103, "step": 198540 }, { "epoch": 47.66, "learning_rate": 5.7243304364964236e-05, "loss": 0.0095, "step": 198550 }, { "epoch": 47.66, "learning_rate": 5.7239752640585345e-05, "loss": 0.0119, "step": 198560 }, { "epoch": 47.66, "learning_rate": 5.72362008788927e-05, "loss": 0.0109, "step": 198570 }, { "epoch": 47.67, "learning_rate": 5.723264907990461e-05, "loss": 0.0075, "step": 198580 }, { "epoch": 47.67, "learning_rate": 5.722909724363939e-05, "loss": 0.014, "step": 198590 }, { "epoch": 47.67, "learning_rate": 5.7225545370115355e-05, "loss": 0.0068, "step": 198600 }, { "epoch": 47.67, "learning_rate": 5.7221993459350775e-05, "loss": 0.0097, "step": 198610 }, { "epoch": 47.68, "learning_rate": 5.7218441511363995e-05, "loss": 0.0071, "step": 198620 }, { "epoch": 47.68, "learning_rate": 5.72148895261733e-05, "loss": 0.0099, "step": 198630 }, { "epoch": 47.68, "learning_rate": 5.7211337503797e-05, "loss": 0.0067, "step": 198640 }, { "epoch": 47.68, "learning_rate": 5.7207785444253416e-05, "loss": 0.0331, "step": 198650 }, { "epoch": 47.69, "learning_rate": 5.720423334756084e-05, "loss": 0.0127, "step": 198660 }, { "epoch": 47.69, "learning_rate": 5.720068121373761e-05, "loss": 0.008, "step": 198670 }, { "epoch": 47.69, "learning_rate": 5.719712904280198e-05, "loss": 0.011, "step": 198680 }, { "epoch": 47.69, "learning_rate": 5.71935768347723e-05, "loss": 0.0187, "step": 198690 }, { "epoch": 47.69, "learning_rate": 5.719002458966686e-05, "loss": 0.0077, "step": 198700 }, { "epoch": 47.7, "learning_rate": 5.718647230750397e-05, "loss": 0.011, "step": 198710 }, { "epoch": 47.7, "learning_rate": 5.718291998830194e-05, "loss": 0.0142, "step": 198720 }, { "epoch": 47.7, "learning_rate": 5.7179367632079085e-05, "loss": 0.0066, "step": 198730 }, { "epoch": 47.7, "learning_rate": 5.7175815238853726e-05, "loss": 0.0091, "step": 198740 }, { "epoch": 47.71, "learning_rate": 5.717226280864414e-05, "loss": 0.0128, "step": 198750 }, { "epoch": 47.71, "learning_rate": 5.716871034146865e-05, "loss": 0.0119, "step": 198760 }, { "epoch": 47.71, "learning_rate": 5.716515783734556e-05, "loss": 0.0177, "step": 198770 }, { "epoch": 47.71, "learning_rate": 5.7161605296293194e-05, "loss": 0.0051, "step": 198780 }, { "epoch": 47.72, "learning_rate": 5.7158052718329834e-05, "loss": 0.0041, "step": 198790 }, { "epoch": 47.72, "learning_rate": 5.715450010347384e-05, "loss": 0.0044, "step": 198800 }, { "epoch": 47.72, "learning_rate": 5.7150947451743485e-05, "loss": 0.0061, "step": 198810 }, { "epoch": 47.72, "learning_rate": 5.714739476315709e-05, "loss": 0.0078, "step": 198820 }, { "epoch": 47.72, "learning_rate": 5.7143842037732954e-05, "loss": 0.0125, "step": 198830 }, { "epoch": 47.73, "learning_rate": 5.71402892754894e-05, "loss": 0.0059, "step": 198840 }, { "epoch": 47.73, "learning_rate": 5.713673647644474e-05, "loss": 0.0114, "step": 198850 }, { "epoch": 47.73, "learning_rate": 5.713318364061727e-05, "loss": 0.0109, "step": 198860 }, { "epoch": 47.73, "learning_rate": 5.7129630768025324e-05, "loss": 0.0065, "step": 198870 }, { "epoch": 47.74, "learning_rate": 5.71260778586872e-05, "loss": 0.0113, "step": 198880 }, { "epoch": 47.74, "learning_rate": 5.712252491262121e-05, "loss": 0.0078, "step": 198890 }, { "epoch": 47.74, "learning_rate": 5.7118971929845665e-05, "loss": 0.0113, "step": 198900 }, { "epoch": 47.74, "learning_rate": 5.711541891037887e-05, "loss": 0.0119, "step": 198910 }, { "epoch": 47.74, "learning_rate": 5.711186585423915e-05, "loss": 0.0056, "step": 198920 }, { "epoch": 47.75, "learning_rate": 5.7108312761444825e-05, "loss": 0.0067, "step": 198930 }, { "epoch": 47.75, "learning_rate": 5.710475963201419e-05, "loss": 0.0042, "step": 198940 }, { "epoch": 47.75, "learning_rate": 5.710120646596555e-05, "loss": 0.0087, "step": 198950 }, { "epoch": 47.75, "learning_rate": 5.7097653263317266e-05, "loss": 0.0083, "step": 198960 }, { "epoch": 47.76, "learning_rate": 5.709410002408759e-05, "loss": 0.0061, "step": 198970 }, { "epoch": 47.76, "learning_rate": 5.709054674829487e-05, "loss": 0.0102, "step": 198980 }, { "epoch": 47.76, "learning_rate": 5.7086993435957414e-05, "loss": 0.019, "step": 198990 }, { "epoch": 47.76, "learning_rate": 5.708344008709354e-05, "loss": 0.0076, "step": 199000 }, { "epoch": 47.77, "learning_rate": 5.707988670172155e-05, "loss": 0.0074, "step": 199010 }, { "epoch": 47.77, "learning_rate": 5.7076333279859765e-05, "loss": 0.0172, "step": 199020 }, { "epoch": 47.77, "learning_rate": 5.707277982152651e-05, "loss": 0.0087, "step": 199030 }, { "epoch": 47.77, "learning_rate": 5.7069226326740076e-05, "loss": 0.0052, "step": 199040 }, { "epoch": 47.77, "learning_rate": 5.70656727955188e-05, "loss": 0.0077, "step": 199050 }, { "epoch": 47.78, "learning_rate": 5.706211922788098e-05, "loss": 0.0061, "step": 199060 }, { "epoch": 47.78, "learning_rate": 5.7058565623844936e-05, "loss": 0.0107, "step": 199070 }, { "epoch": 47.78, "learning_rate": 5.705501198342899e-05, "loss": 0.0108, "step": 199080 }, { "epoch": 47.78, "learning_rate": 5.705145830665145e-05, "loss": 0.0048, "step": 199090 }, { "epoch": 47.79, "learning_rate": 5.704790459353064e-05, "loss": 0.0097, "step": 199100 }, { "epoch": 47.79, "learning_rate": 5.704435084408487e-05, "loss": 0.0049, "step": 199110 }, { "epoch": 47.79, "learning_rate": 5.704079705833245e-05, "loss": 0.0085, "step": 199120 }, { "epoch": 47.79, "learning_rate": 5.703724323629171e-05, "loss": 0.0123, "step": 199130 }, { "epoch": 47.8, "learning_rate": 5.703368937798096e-05, "loss": 0.0054, "step": 199140 }, { "epoch": 47.8, "learning_rate": 5.703013548341851e-05, "loss": 0.0102, "step": 199150 }, { "epoch": 47.8, "learning_rate": 5.702658155262268e-05, "loss": 0.0084, "step": 199160 }, { "epoch": 47.8, "learning_rate": 5.702302758561181e-05, "loss": 0.0145, "step": 199170 }, { "epoch": 47.8, "learning_rate": 5.701947358240418e-05, "loss": 0.0094, "step": 199180 }, { "epoch": 47.81, "learning_rate": 5.7015919543018134e-05, "loss": 0.005, "step": 199190 }, { "epoch": 47.81, "learning_rate": 5.7012365467471975e-05, "loss": 0.0059, "step": 199200 }, { "epoch": 47.81, "learning_rate": 5.700881135578402e-05, "loss": 0.004, "step": 199210 }, { "epoch": 47.81, "learning_rate": 5.7005257207972606e-05, "loss": 0.012, "step": 199220 }, { "epoch": 47.82, "learning_rate": 5.700170302405603e-05, "loss": 0.012, "step": 199230 }, { "epoch": 47.82, "learning_rate": 5.699814880405261e-05, "loss": 0.0051, "step": 199240 }, { "epoch": 47.82, "learning_rate": 5.699459454798068e-05, "loss": 0.0068, "step": 199250 }, { "epoch": 47.82, "learning_rate": 5.699104025585855e-05, "loss": 0.0071, "step": 199260 }, { "epoch": 47.82, "learning_rate": 5.698748592770454e-05, "loss": 0.0181, "step": 199270 }, { "epoch": 47.83, "learning_rate": 5.6983931563536976e-05, "loss": 0.0105, "step": 199280 }, { "epoch": 47.83, "learning_rate": 5.698037716337417e-05, "loss": 0.0095, "step": 199290 }, { "epoch": 47.83, "learning_rate": 5.6976822727234435e-05, "loss": 0.0079, "step": 199300 }, { "epoch": 47.83, "learning_rate": 5.697326825513609e-05, "loss": 0.0094, "step": 199310 }, { "epoch": 47.84, "learning_rate": 5.6969713747097486e-05, "loss": 0.0047, "step": 199320 }, { "epoch": 47.84, "learning_rate": 5.69661592031369e-05, "loss": 0.0084, "step": 199330 }, { "epoch": 47.84, "learning_rate": 5.6962604623272674e-05, "loss": 0.0057, "step": 199340 }, { "epoch": 47.84, "learning_rate": 5.695905000752313e-05, "loss": 0.0065, "step": 199350 }, { "epoch": 47.85, "learning_rate": 5.695549535590659e-05, "loss": 0.0048, "step": 199360 }, { "epoch": 47.85, "learning_rate": 5.695194066844135e-05, "loss": 0.0107, "step": 199370 }, { "epoch": 47.85, "learning_rate": 5.694838594514577e-05, "loss": 0.0051, "step": 199380 }, { "epoch": 47.85, "learning_rate": 5.694483118603813e-05, "loss": 0.0063, "step": 199390 }, { "epoch": 47.85, "learning_rate": 5.694127639113679e-05, "loss": 0.0052, "step": 199400 }, { "epoch": 47.86, "learning_rate": 5.6937721560460044e-05, "loss": 0.0081, "step": 199410 }, { "epoch": 47.86, "learning_rate": 5.6934166694026225e-05, "loss": 0.0079, "step": 199420 }, { "epoch": 47.86, "learning_rate": 5.693061179185365e-05, "loss": 0.0076, "step": 199430 }, { "epoch": 47.86, "learning_rate": 5.6927056853960646e-05, "loss": 0.0068, "step": 199440 }, { "epoch": 47.87, "learning_rate": 5.692350188036554e-05, "loss": 0.0061, "step": 199450 }, { "epoch": 47.87, "learning_rate": 5.6919946871086646e-05, "loss": 0.0064, "step": 199460 }, { "epoch": 47.87, "learning_rate": 5.691639182614228e-05, "loss": 0.0116, "step": 199470 }, { "epoch": 47.87, "learning_rate": 5.691283674555078e-05, "loss": 0.0281, "step": 199480 }, { "epoch": 47.88, "learning_rate": 5.690928162933046e-05, "loss": 0.0126, "step": 199490 }, { "epoch": 47.88, "learning_rate": 5.690572647749963e-05, "loss": 0.0085, "step": 199500 }, { "epoch": 47.88, "learning_rate": 5.6902171290076644e-05, "loss": 0.0071, "step": 199510 }, { "epoch": 47.88, "learning_rate": 5.6898616067079813e-05, "loss": 0.0089, "step": 199520 }, { "epoch": 47.88, "learning_rate": 5.689506080852745e-05, "loss": 0.0057, "step": 199530 }, { "epoch": 47.89, "learning_rate": 5.689150551443788e-05, "loss": 0.0057, "step": 199540 }, { "epoch": 47.89, "learning_rate": 5.6887950184829445e-05, "loss": 0.0156, "step": 199550 }, { "epoch": 47.89, "learning_rate": 5.688439481972044e-05, "loss": 0.0445, "step": 199560 }, { "epoch": 47.89, "learning_rate": 5.688083941912923e-05, "loss": 0.0085, "step": 199570 }, { "epoch": 47.9, "learning_rate": 5.68772839830741e-05, "loss": 0.005, "step": 199580 }, { "epoch": 47.9, "learning_rate": 5.687372851157339e-05, "loss": 0.0061, "step": 199590 }, { "epoch": 47.9, "learning_rate": 5.687017300464544e-05, "loss": 0.0092, "step": 199600 }, { "epoch": 47.9, "learning_rate": 5.686661746230856e-05, "loss": 0.0125, "step": 199610 }, { "epoch": 47.9, "learning_rate": 5.686306188458106e-05, "loss": 0.0036, "step": 199620 }, { "epoch": 47.91, "learning_rate": 5.6859506271481286e-05, "loss": 0.0115, "step": 199630 }, { "epoch": 47.91, "learning_rate": 5.6855950623027565e-05, "loss": 0.0091, "step": 199640 }, { "epoch": 47.91, "learning_rate": 5.685239493923822e-05, "loss": 0.0056, "step": 199650 }, { "epoch": 47.91, "learning_rate": 5.684883922013157e-05, "loss": 0.0052, "step": 199660 }, { "epoch": 47.92, "learning_rate": 5.684528346572594e-05, "loss": 0.0114, "step": 199670 }, { "epoch": 47.92, "learning_rate": 5.684172767603967e-05, "loss": 0.0093, "step": 199680 }, { "epoch": 47.92, "learning_rate": 5.683817185109107e-05, "loss": 0.0062, "step": 199690 }, { "epoch": 47.92, "learning_rate": 5.683461599089848e-05, "loss": 0.0036, "step": 199700 }, { "epoch": 47.93, "learning_rate": 5.683106009548021e-05, "loss": 0.0064, "step": 199710 }, { "epoch": 47.93, "learning_rate": 5.6827504164854616e-05, "loss": 0.0048, "step": 199720 }, { "epoch": 47.93, "learning_rate": 5.682394819904001e-05, "loss": 0.0071, "step": 199730 }, { "epoch": 47.93, "learning_rate": 5.682039219805471e-05, "loss": 0.0056, "step": 199740 }, { "epoch": 47.93, "learning_rate": 5.681683616191706e-05, "loss": 0.006, "step": 199750 }, { "epoch": 47.94, "learning_rate": 5.681328009064537e-05, "loss": 0.0097, "step": 199760 }, { "epoch": 47.94, "learning_rate": 5.680972398425798e-05, "loss": 0.005, "step": 199770 }, { "epoch": 47.94, "learning_rate": 5.680616784277322e-05, "loss": 0.0062, "step": 199780 }, { "epoch": 47.94, "learning_rate": 5.6802611666209405e-05, "loss": 0.008, "step": 199790 }, { "epoch": 47.95, "learning_rate": 5.679905545458488e-05, "loss": 0.0069, "step": 199800 }, { "epoch": 47.95, "learning_rate": 5.679549920791796e-05, "loss": 0.0084, "step": 199810 }, { "epoch": 47.95, "learning_rate": 5.679194292622699e-05, "loss": 0.0044, "step": 199820 }, { "epoch": 48.0, "learning_rate": 5.678838660953028e-05, "loss": 0.0047, "step": 199830 }, { "epoch": 48.0, "learning_rate": 5.678483025784617e-05, "loss": 0.0068, "step": 199840 }, { "epoch": 48.01, "learning_rate": 5.678127387119299e-05, "loss": 0.0039, "step": 199850 }, { "epoch": 48.01, "learning_rate": 5.6777717449589066e-05, "loss": 0.0061, "step": 199860 }, { "epoch": 48.01, "learning_rate": 5.6774160993052727e-05, "loss": 0.0087, "step": 199870 }, { "epoch": 48.01, "learning_rate": 5.677060450160232e-05, "loss": 0.0069, "step": 199880 }, { "epoch": 48.02, "learning_rate": 5.676704797525616e-05, "loss": 0.0085, "step": 199890 }, { "epoch": 48.02, "learning_rate": 5.6763491414032566e-05, "loss": 0.0097, "step": 199900 }, { "epoch": 48.02, "learning_rate": 5.675993481794988e-05, "loss": 0.0072, "step": 199910 }, { "epoch": 48.02, "learning_rate": 5.675637818702644e-05, "loss": 0.0078, "step": 199920 }, { "epoch": 48.02, "learning_rate": 5.675282152128056e-05, "loss": 0.0153, "step": 199930 }, { "epoch": 48.03, "learning_rate": 5.67492648207306e-05, "loss": 0.0065, "step": 199940 }, { "epoch": 48.03, "learning_rate": 5.6745708085394856e-05, "loss": 0.0051, "step": 199950 }, { "epoch": 48.03, "learning_rate": 5.674215131529169e-05, "loss": 0.0072, "step": 199960 }, { "epoch": 48.03, "learning_rate": 5.673859451043941e-05, "loss": 0.009, "step": 199970 }, { "epoch": 48.04, "learning_rate": 5.673503767085636e-05, "loss": 0.0154, "step": 199980 }, { "epoch": 48.04, "learning_rate": 5.6731480796560865e-05, "loss": 0.0049, "step": 199990 }, { "epoch": 48.04, "learning_rate": 5.6727923887571265e-05, "loss": 0.0082, "step": 200000 }, { "epoch": 48.04, "learning_rate": 5.6724366943905885e-05, "loss": 0.0065, "step": 200010 }, { "epoch": 48.04, "learning_rate": 5.672080996558307e-05, "loss": 0.007, "step": 200020 }, { "epoch": 48.05, "learning_rate": 5.671725295262115e-05, "loss": 0.006, "step": 200030 }, { "epoch": 48.05, "learning_rate": 5.671369590503843e-05, "loss": 0.0044, "step": 200040 }, { "epoch": 48.05, "learning_rate": 5.671013882285329e-05, "loss": 0.0077, "step": 200050 }, { "epoch": 48.05, "learning_rate": 5.670658170608403e-05, "loss": 0.007, "step": 200060 }, { "epoch": 48.06, "learning_rate": 5.6703024554748984e-05, "loss": 0.0047, "step": 200070 }, { "epoch": 48.06, "learning_rate": 5.669946736886649e-05, "loss": 0.0077, "step": 200080 }, { "epoch": 48.06, "learning_rate": 5.669591014845489e-05, "loss": 0.0148, "step": 200090 }, { "epoch": 48.06, "learning_rate": 5.6692352893532517e-05, "loss": 0.0052, "step": 200100 }, { "epoch": 48.07, "learning_rate": 5.668879560411772e-05, "loss": 0.0089, "step": 200110 }, { "epoch": 48.07, "learning_rate": 5.668523828022878e-05, "loss": 0.0102, "step": 200120 }, { "epoch": 48.07, "learning_rate": 5.6681680921884085e-05, "loss": 0.0112, "step": 200130 }, { "epoch": 48.07, "learning_rate": 5.667812352910195e-05, "loss": 0.0136, "step": 200140 }, { "epoch": 48.07, "learning_rate": 5.6674566101900694e-05, "loss": 0.0079, "step": 200150 }, { "epoch": 48.08, "learning_rate": 5.667100864029868e-05, "loss": 0.0082, "step": 200160 }, { "epoch": 48.08, "learning_rate": 5.666745114431423e-05, "loss": 0.0046, "step": 200170 }, { "epoch": 48.08, "learning_rate": 5.666389361396569e-05, "loss": 0.0047, "step": 200180 }, { "epoch": 48.08, "learning_rate": 5.666033604927139e-05, "loss": 0.0138, "step": 200190 }, { "epoch": 48.09, "learning_rate": 5.665677845024965e-05, "loss": 0.0094, "step": 200200 }, { "epoch": 48.09, "learning_rate": 5.6653220816918815e-05, "loss": 0.0056, "step": 200210 }, { "epoch": 48.09, "learning_rate": 5.664966314929724e-05, "loss": 0.0069, "step": 200220 }, { "epoch": 48.09, "learning_rate": 5.664610544740323e-05, "loss": 0.0131, "step": 200230 }, { "epoch": 48.1, "learning_rate": 5.6642547711255145e-05, "loss": 0.004, "step": 200240 }, { "epoch": 48.1, "learning_rate": 5.6638989940871324e-05, "loss": 0.0048, "step": 200250 }, { "epoch": 48.1, "learning_rate": 5.6635432136270075e-05, "loss": 0.012, "step": 200260 }, { "epoch": 48.1, "learning_rate": 5.6631874297469756e-05, "loss": 0.0046, "step": 200270 }, { "epoch": 48.1, "learning_rate": 5.66283164244887e-05, "loss": 0.0045, "step": 200280 }, { "epoch": 48.11, "learning_rate": 5.662475851734525e-05, "loss": 0.0058, "step": 200290 }, { "epoch": 48.11, "learning_rate": 5.662120057605773e-05, "loss": 0.012, "step": 200300 }, { "epoch": 48.11, "learning_rate": 5.661764260064451e-05, "loss": 0.0075, "step": 200310 }, { "epoch": 48.11, "learning_rate": 5.66140845911239e-05, "loss": 0.0039, "step": 200320 }, { "epoch": 48.12, "learning_rate": 5.661052654751423e-05, "loss": 0.0044, "step": 200330 }, { "epoch": 48.12, "learning_rate": 5.6606968469833856e-05, "loss": 0.006, "step": 200340 }, { "epoch": 48.12, "learning_rate": 5.66034103581011e-05, "loss": 0.0044, "step": 200350 }, { "epoch": 48.12, "learning_rate": 5.659985221233432e-05, "loss": 0.0044, "step": 200360 }, { "epoch": 48.12, "learning_rate": 5.659629403255186e-05, "loss": 0.0046, "step": 200370 }, { "epoch": 48.13, "learning_rate": 5.6592735818772025e-05, "loss": 0.004, "step": 200380 }, { "epoch": 48.13, "learning_rate": 5.6589177571013195e-05, "loss": 0.0044, "step": 200390 }, { "epoch": 48.13, "learning_rate": 5.6585619289293676e-05, "loss": 0.0094, "step": 200400 }, { "epoch": 48.13, "learning_rate": 5.6582060973631825e-05, "loss": 0.0045, "step": 200410 }, { "epoch": 48.14, "learning_rate": 5.6578502624045973e-05, "loss": 0.0034, "step": 200420 }, { "epoch": 48.14, "learning_rate": 5.657494424055446e-05, "loss": 0.0043, "step": 200430 }, { "epoch": 48.14, "learning_rate": 5.657138582317564e-05, "loss": 0.0039, "step": 200440 }, { "epoch": 48.14, "learning_rate": 5.656782737192783e-05, "loss": 0.0054, "step": 200450 }, { "epoch": 48.15, "learning_rate": 5.656426888682938e-05, "loss": 0.0066, "step": 200460 }, { "epoch": 48.15, "learning_rate": 5.656071036789865e-05, "loss": 0.005, "step": 200470 }, { "epoch": 48.15, "learning_rate": 5.6557151815153955e-05, "loss": 0.0058, "step": 200480 }, { "epoch": 48.15, "learning_rate": 5.6553593228613645e-05, "loss": 0.0043, "step": 200490 }, { "epoch": 48.15, "learning_rate": 5.655003460829605e-05, "loss": 0.0198, "step": 200500 }, { "epoch": 48.16, "learning_rate": 5.6546475954219535e-05, "loss": 0.009, "step": 200510 }, { "epoch": 48.16, "learning_rate": 5.654291726640243e-05, "loss": 0.0054, "step": 200520 }, { "epoch": 48.16, "learning_rate": 5.653935854486307e-05, "loss": 0.0065, "step": 200530 }, { "epoch": 48.16, "learning_rate": 5.653579978961981e-05, "loss": 0.0058, "step": 200540 }, { "epoch": 48.17, "learning_rate": 5.6532241000690975e-05, "loss": 0.0072, "step": 200550 }, { "epoch": 48.17, "learning_rate": 5.6528682178094915e-05, "loss": 0.006, "step": 200560 }, { "epoch": 48.17, "learning_rate": 5.652512332184997e-05, "loss": 0.0064, "step": 200570 }, { "epoch": 48.17, "learning_rate": 5.65215644319745e-05, "loss": 0.005, "step": 200580 }, { "epoch": 48.18, "learning_rate": 5.651800550848682e-05, "loss": 0.0078, "step": 200590 }, { "epoch": 48.18, "learning_rate": 5.651444655140528e-05, "loss": 0.0109, "step": 200600 }, { "epoch": 48.18, "learning_rate": 5.6510887560748224e-05, "loss": 0.0075, "step": 200610 }, { "epoch": 48.18, "learning_rate": 5.650732853653402e-05, "loss": 0.0048, "step": 200620 }, { "epoch": 48.18, "learning_rate": 5.650376947878098e-05, "loss": 0.0066, "step": 200630 }, { "epoch": 48.19, "learning_rate": 5.650021038750745e-05, "loss": 0.0057, "step": 200640 }, { "epoch": 48.19, "learning_rate": 5.6496651262731795e-05, "loss": 0.0074, "step": 200650 }, { "epoch": 48.19, "learning_rate": 5.649309210447233e-05, "loss": 0.0043, "step": 200660 }, { "epoch": 48.19, "learning_rate": 5.648953291274742e-05, "loss": 0.0068, "step": 200670 }, { "epoch": 48.2, "learning_rate": 5.6485973687575424e-05, "loss": 0.0066, "step": 200680 }, { "epoch": 48.2, "learning_rate": 5.648241442897464e-05, "loss": 0.0049, "step": 200690 }, { "epoch": 48.2, "learning_rate": 5.647885513696345e-05, "loss": 0.0058, "step": 200700 }, { "epoch": 48.2, "learning_rate": 5.647529581156017e-05, "loss": 0.009, "step": 200710 }, { "epoch": 48.2, "learning_rate": 5.647173645278318e-05, "loss": 0.0108, "step": 200720 }, { "epoch": 48.21, "learning_rate": 5.64681770606508e-05, "loss": 0.0058, "step": 200730 }, { "epoch": 48.21, "learning_rate": 5.646461763518137e-05, "loss": 0.0047, "step": 200740 }, { "epoch": 48.21, "learning_rate": 5.6461058176393255e-05, "loss": 0.0144, "step": 200750 }, { "epoch": 48.21, "learning_rate": 5.64574986843048e-05, "loss": 0.0057, "step": 200760 }, { "epoch": 48.22, "learning_rate": 5.645393915893433e-05, "loss": 0.0159, "step": 200770 }, { "epoch": 48.22, "learning_rate": 5.645037960030022e-05, "loss": 0.008, "step": 200780 }, { "epoch": 48.22, "learning_rate": 5.6446820008420786e-05, "loss": 0.0094, "step": 200790 }, { "epoch": 48.22, "learning_rate": 5.644326038331439e-05, "loss": 0.0104, "step": 200800 }, { "epoch": 48.23, "learning_rate": 5.643970072499938e-05, "loss": 0.0107, "step": 200810 }, { "epoch": 48.23, "learning_rate": 5.643614103349411e-05, "loss": 0.0081, "step": 200820 }, { "epoch": 48.23, "learning_rate": 5.643258130881689e-05, "loss": 0.0083, "step": 200830 }, { "epoch": 48.23, "learning_rate": 5.6429021550986105e-05, "loss": 0.0072, "step": 200840 }, { "epoch": 48.23, "learning_rate": 5.6425461760020096e-05, "loss": 0.0042, "step": 200850 }, { "epoch": 48.24, "learning_rate": 5.642190193593719e-05, "loss": 0.0075, "step": 200860 }, { "epoch": 48.24, "learning_rate": 5.641834207875575e-05, "loss": 0.0105, "step": 200870 }, { "epoch": 48.24, "learning_rate": 5.641478218849412e-05, "loss": 0.0079, "step": 200880 }, { "epoch": 48.24, "learning_rate": 5.641122226517066e-05, "loss": 0.008, "step": 200890 }, { "epoch": 48.25, "learning_rate": 5.64076623088037e-05, "loss": 0.0132, "step": 200900 }, { "epoch": 48.25, "learning_rate": 5.640410231941159e-05, "loss": 0.0064, "step": 200910 }, { "epoch": 48.25, "learning_rate": 5.640054229701269e-05, "loss": 0.0051, "step": 200920 }, { "epoch": 48.25, "learning_rate": 5.639698224162534e-05, "loss": 0.0051, "step": 200930 }, { "epoch": 48.26, "learning_rate": 5.639342215326788e-05, "loss": 0.0045, "step": 200940 }, { "epoch": 48.26, "learning_rate": 5.6389862031958685e-05, "loss": 0.0135, "step": 200950 }, { "epoch": 48.26, "learning_rate": 5.638630187771609e-05, "loss": 0.0063, "step": 200960 }, { "epoch": 48.26, "learning_rate": 5.638274169055844e-05, "loss": 0.0062, "step": 200970 }, { "epoch": 48.26, "learning_rate": 5.637918147050407e-05, "loss": 0.0062, "step": 200980 }, { "epoch": 48.27, "learning_rate": 5.637562121757136e-05, "loss": 0.014, "step": 200990 }, { "epoch": 48.27, "learning_rate": 5.6372060931778633e-05, "loss": 0.0052, "step": 201000 }, { "epoch": 48.27, "learning_rate": 5.636850061314426e-05, "loss": 0.0063, "step": 201010 }, { "epoch": 48.27, "learning_rate": 5.636494026168657e-05, "loss": 0.0078, "step": 201020 }, { "epoch": 48.28, "learning_rate": 5.6361379877423935e-05, "loss": 0.0119, "step": 201030 }, { "epoch": 48.28, "learning_rate": 5.6357819460374695e-05, "loss": 0.0031, "step": 201040 }, { "epoch": 48.28, "learning_rate": 5.63542590105572e-05, "loss": 0.0054, "step": 201050 }, { "epoch": 48.28, "learning_rate": 5.63506985279898e-05, "loss": 0.004, "step": 201060 }, { "epoch": 48.28, "learning_rate": 5.634713801269085e-05, "loss": 0.0057, "step": 201070 }, { "epoch": 48.29, "learning_rate": 5.634357746467869e-05, "loss": 0.0079, "step": 201080 }, { "epoch": 48.29, "learning_rate": 5.634001688397168e-05, "loss": 0.0049, "step": 201090 }, { "epoch": 48.29, "learning_rate": 5.633645627058817e-05, "loss": 0.0067, "step": 201100 }, { "epoch": 48.29, "learning_rate": 5.6332895624546534e-05, "loss": 0.0117, "step": 201110 }, { "epoch": 48.3, "learning_rate": 5.632933494586507e-05, "loss": 0.0056, "step": 201120 }, { "epoch": 48.3, "learning_rate": 5.632577423456218e-05, "loss": 0.007, "step": 201130 }, { "epoch": 48.3, "learning_rate": 5.6322213490656184e-05, "loss": 0.0081, "step": 201140 }, { "epoch": 48.3, "learning_rate": 5.631865271416546e-05, "loss": 0.0117, "step": 201150 }, { "epoch": 48.31, "learning_rate": 5.631509190510833e-05, "loss": 0.0084, "step": 201160 }, { "epoch": 48.31, "learning_rate": 5.6311531063503174e-05, "loss": 0.0094, "step": 201170 }, { "epoch": 48.31, "learning_rate": 5.630797018936834e-05, "loss": 0.0046, "step": 201180 }, { "epoch": 48.31, "learning_rate": 5.6304409282722156e-05, "loss": 0.0046, "step": 201190 }, { "epoch": 48.31, "learning_rate": 5.6300848343583004e-05, "loss": 0.004, "step": 201200 }, { "epoch": 48.32, "learning_rate": 5.629728737196922e-05, "loss": 0.0064, "step": 201210 }, { "epoch": 48.32, "learning_rate": 5.629372636789918e-05, "loss": 0.0102, "step": 201220 }, { "epoch": 48.32, "learning_rate": 5.629016533139121e-05, "loss": 0.0124, "step": 201230 }, { "epoch": 48.32, "learning_rate": 5.6286604262463684e-05, "loss": 0.0106, "step": 201240 }, { "epoch": 48.33, "learning_rate": 5.6283043161134954e-05, "loss": 0.0076, "step": 201250 }, { "epoch": 48.33, "learning_rate": 5.627948202742335e-05, "loss": 0.0072, "step": 201260 }, { "epoch": 48.33, "learning_rate": 5.6275920861347244e-05, "loss": 0.0072, "step": 201270 }, { "epoch": 48.33, "learning_rate": 5.627235966292499e-05, "loss": 0.0077, "step": 201280 }, { "epoch": 48.34, "learning_rate": 5.626879843217495e-05, "loss": 0.0042, "step": 201290 }, { "epoch": 48.34, "learning_rate": 5.626523716911547e-05, "loss": 0.0063, "step": 201300 }, { "epoch": 48.34, "learning_rate": 5.6261675873764896e-05, "loss": 0.0052, "step": 201310 }, { "epoch": 48.34, "learning_rate": 5.62581145461416e-05, "loss": 0.0055, "step": 201320 }, { "epoch": 48.34, "learning_rate": 5.6254553186263934e-05, "loss": 0.0062, "step": 201330 }, { "epoch": 48.35, "learning_rate": 5.6250991794150244e-05, "loss": 0.0086, "step": 201340 }, { "epoch": 48.35, "learning_rate": 5.6247430369818876e-05, "loss": 0.0162, "step": 201350 }, { "epoch": 48.35, "learning_rate": 5.6243868913288215e-05, "loss": 0.0077, "step": 201360 }, { "epoch": 48.35, "learning_rate": 5.624030742457659e-05, "loss": 0.0055, "step": 201370 }, { "epoch": 48.36, "learning_rate": 5.623674590370238e-05, "loss": 0.0071, "step": 201380 }, { "epoch": 48.36, "learning_rate": 5.6233184350683924e-05, "loss": 0.0084, "step": 201390 }, { "epoch": 48.36, "learning_rate": 5.622962276553959e-05, "loss": 0.0059, "step": 201400 }, { "epoch": 48.36, "learning_rate": 5.622606114828772e-05, "loss": 0.0094, "step": 201410 }, { "epoch": 48.36, "learning_rate": 5.622249949894669e-05, "loss": 0.008, "step": 201420 }, { "epoch": 48.37, "learning_rate": 5.6218937817534834e-05, "loss": 0.0055, "step": 201430 }, { "epoch": 48.37, "learning_rate": 5.6215376104070525e-05, "loss": 0.0064, "step": 201440 }, { "epoch": 48.37, "learning_rate": 5.6211814358572114e-05, "loss": 0.0051, "step": 201450 }, { "epoch": 48.37, "learning_rate": 5.6208252581057965e-05, "loss": 0.009, "step": 201460 }, { "epoch": 48.38, "learning_rate": 5.620469077154643e-05, "loss": 0.0108, "step": 201470 }, { "epoch": 48.38, "learning_rate": 5.620112893005587e-05, "loss": 0.0131, "step": 201480 }, { "epoch": 48.38, "learning_rate": 5.6197567056604625e-05, "loss": 0.0043, "step": 201490 }, { "epoch": 48.38, "learning_rate": 5.619400515121107e-05, "loss": 0.0059, "step": 201500 }, { "epoch": 48.39, "learning_rate": 5.619044321389356e-05, "loss": 0.0133, "step": 201510 }, { "epoch": 48.39, "learning_rate": 5.6186881244670465e-05, "loss": 0.0053, "step": 201520 }, { "epoch": 48.39, "learning_rate": 5.6183319243560116e-05, "loss": 0.004, "step": 201530 }, { "epoch": 48.39, "learning_rate": 5.617975721058092e-05, "loss": 0.0045, "step": 201540 }, { "epoch": 48.39, "learning_rate": 5.6176195145751174e-05, "loss": 0.0088, "step": 201550 }, { "epoch": 48.4, "learning_rate": 5.6172633049089275e-05, "loss": 0.0047, "step": 201560 }, { "epoch": 48.4, "learning_rate": 5.6169070920613576e-05, "loss": 0.0056, "step": 201570 }, { "epoch": 48.4, "learning_rate": 5.616550876034244e-05, "loss": 0.01, "step": 201580 }, { "epoch": 48.4, "learning_rate": 5.616194656829421e-05, "loss": 0.0057, "step": 201590 }, { "epoch": 48.41, "learning_rate": 5.615838434448726e-05, "loss": 0.0103, "step": 201600 }, { "epoch": 48.41, "learning_rate": 5.615482208893995e-05, "loss": 0.0113, "step": 201610 }, { "epoch": 48.41, "learning_rate": 5.615125980167063e-05, "loss": 0.0044, "step": 201620 }, { "epoch": 48.41, "learning_rate": 5.614769748269766e-05, "loss": 0.0059, "step": 201630 }, { "epoch": 48.41, "learning_rate": 5.614413513203941e-05, "loss": 0.0098, "step": 201640 }, { "epoch": 48.42, "learning_rate": 5.6140572749714234e-05, "loss": 0.015, "step": 201650 }, { "epoch": 48.42, "learning_rate": 5.613701033574049e-05, "loss": 0.0134, "step": 201660 }, { "epoch": 48.42, "learning_rate": 5.6133447890136545e-05, "loss": 0.0088, "step": 201670 }, { "epoch": 48.42, "learning_rate": 5.612988541292078e-05, "loss": 0.0051, "step": 201680 }, { "epoch": 48.43, "learning_rate": 5.6126322904111514e-05, "loss": 0.0078, "step": 201690 }, { "epoch": 48.43, "learning_rate": 5.6122760363727137e-05, "loss": 0.0065, "step": 201700 }, { "epoch": 48.43, "learning_rate": 5.611919779178599e-05, "loss": 0.0068, "step": 201710 }, { "epoch": 48.43, "learning_rate": 5.611563518830646e-05, "loss": 0.0055, "step": 201720 }, { "epoch": 48.44, "learning_rate": 5.6112072553306896e-05, "loss": 0.0058, "step": 201730 }, { "epoch": 48.44, "learning_rate": 5.610850988680565e-05, "loss": 0.0128, "step": 201740 }, { "epoch": 48.44, "learning_rate": 5.610494718882109e-05, "loss": 0.0081, "step": 201750 }, { "epoch": 48.44, "learning_rate": 5.6101384459371596e-05, "loss": 0.0094, "step": 201760 }, { "epoch": 48.44, "learning_rate": 5.6097821698475506e-05, "loss": 0.006, "step": 201770 }, { "epoch": 48.45, "learning_rate": 5.60942589061512e-05, "loss": 0.0065, "step": 201780 }, { "epoch": 48.45, "learning_rate": 5.6090696082417014e-05, "loss": 0.0053, "step": 201790 }, { "epoch": 48.45, "learning_rate": 5.608713322729134e-05, "loss": 0.0043, "step": 201800 }, { "epoch": 48.45, "learning_rate": 5.6083570340792536e-05, "loss": 0.0077, "step": 201810 }, { "epoch": 48.46, "learning_rate": 5.6080007422938944e-05, "loss": 0.0094, "step": 201820 }, { "epoch": 48.46, "learning_rate": 5.6076444473748954e-05, "loss": 0.0053, "step": 201830 }, { "epoch": 48.46, "learning_rate": 5.6072881493240924e-05, "loss": 0.0073, "step": 201840 }, { "epoch": 48.46, "learning_rate": 5.606931848143321e-05, "loss": 0.0032, "step": 201850 }, { "epoch": 48.47, "learning_rate": 5.606575543834417e-05, "loss": 0.0053, "step": 201860 }, { "epoch": 48.47, "learning_rate": 5.606219236399217e-05, "loss": 0.0113, "step": 201870 }, { "epoch": 48.47, "learning_rate": 5.60586292583956e-05, "loss": 0.0128, "step": 201880 }, { "epoch": 48.47, "learning_rate": 5.605506612157279e-05, "loss": 0.0116, "step": 201890 }, { "epoch": 48.47, "learning_rate": 5.605150295354213e-05, "loss": 0.0068, "step": 201900 }, { "epoch": 48.48, "learning_rate": 5.604793975432197e-05, "loss": 0.0057, "step": 201910 }, { "epoch": 48.48, "learning_rate": 5.604437652393067e-05, "loss": 0.0045, "step": 201920 }, { "epoch": 48.48, "learning_rate": 5.6040813262386605e-05, "loss": 0.0031, "step": 201930 }, { "epoch": 48.48, "learning_rate": 5.603724996970814e-05, "loss": 0.0074, "step": 201940 }, { "epoch": 48.49, "learning_rate": 5.603368664591363e-05, "loss": 0.012, "step": 201950 }, { "epoch": 48.49, "learning_rate": 5.6030123291021466e-05, "loss": 0.0038, "step": 201960 }, { "epoch": 48.49, "learning_rate": 5.602655990504998e-05, "loss": 0.004, "step": 201970 }, { "epoch": 48.49, "learning_rate": 5.6022996488017556e-05, "loss": 0.0044, "step": 201980 }, { "epoch": 48.49, "learning_rate": 5.601943303994256e-05, "loss": 0.0052, "step": 201990 }, { "epoch": 48.5, "learning_rate": 5.601586956084336e-05, "loss": 0.0087, "step": 202000 }, { "epoch": 48.5, "learning_rate": 5.601230605073832e-05, "loss": 0.0033, "step": 202010 }, { "epoch": 48.5, "learning_rate": 5.600874250964579e-05, "loss": 0.0051, "step": 202020 }, { "epoch": 48.5, "learning_rate": 5.600517893758417e-05, "loss": 0.0091, "step": 202030 }, { "epoch": 48.51, "learning_rate": 5.60016153345718e-05, "loss": 0.0082, "step": 202040 }, { "epoch": 48.51, "learning_rate": 5.599805170062705e-05, "loss": 0.0068, "step": 202050 }, { "epoch": 48.51, "learning_rate": 5.59944880357683e-05, "loss": 0.01, "step": 202060 }, { "epoch": 48.51, "learning_rate": 5.59909243400139e-05, "loss": 0.0045, "step": 202070 }, { "epoch": 48.52, "learning_rate": 5.598736061338223e-05, "loss": 0.0156, "step": 202080 }, { "epoch": 48.52, "learning_rate": 5.5983796855891645e-05, "loss": 0.0049, "step": 202090 }, { "epoch": 48.52, "learning_rate": 5.598023306756053e-05, "loss": 0.0044, "step": 202100 }, { "epoch": 48.52, "learning_rate": 5.597666924840724e-05, "loss": 0.0048, "step": 202110 }, { "epoch": 48.52, "learning_rate": 5.5973105398450155e-05, "loss": 0.0055, "step": 202120 }, { "epoch": 48.53, "learning_rate": 5.596954151770763e-05, "loss": 0.0109, "step": 202130 }, { "epoch": 48.53, "learning_rate": 5.596597760619803e-05, "loss": 0.0053, "step": 202140 }, { "epoch": 48.53, "learning_rate": 5.596241366393974e-05, "loss": 0.0096, "step": 202150 }, { "epoch": 48.53, "learning_rate": 5.595884969095111e-05, "loss": 0.0066, "step": 202160 }, { "epoch": 48.54, "learning_rate": 5.5955285687250524e-05, "loss": 0.0112, "step": 202170 }, { "epoch": 48.54, "learning_rate": 5.595172165285636e-05, "loss": 0.0077, "step": 202180 }, { "epoch": 48.54, "learning_rate": 5.5948157587786963e-05, "loss": 0.0129, "step": 202190 }, { "epoch": 48.54, "learning_rate": 5.594459349206072e-05, "loss": 0.0049, "step": 202200 }, { "epoch": 48.55, "learning_rate": 5.5941029365695976e-05, "loss": 0.0089, "step": 202210 }, { "epoch": 48.55, "learning_rate": 5.593746520871113e-05, "loss": 0.0223, "step": 202220 }, { "epoch": 48.55, "learning_rate": 5.593390102112453e-05, "loss": 0.0115, "step": 202230 }, { "epoch": 48.55, "learning_rate": 5.593033680295455e-05, "loss": 0.0105, "step": 202240 }, { "epoch": 48.55, "learning_rate": 5.592677255421958e-05, "loss": 0.0083, "step": 202250 }, { "epoch": 48.56, "learning_rate": 5.592320827493795e-05, "loss": 0.0122, "step": 202260 }, { "epoch": 48.56, "learning_rate": 5.591964396512808e-05, "loss": 0.0096, "step": 202270 }, { "epoch": 48.56, "learning_rate": 5.5916079624808305e-05, "loss": 0.006, "step": 202280 }, { "epoch": 48.56, "learning_rate": 5.591251525399701e-05, "loss": 0.0117, "step": 202290 }, { "epoch": 48.57, "learning_rate": 5.590895085271256e-05, "loss": 0.0077, "step": 202300 }, { "epoch": 48.57, "learning_rate": 5.5905386420973325e-05, "loss": 0.0099, "step": 202310 }, { "epoch": 48.57, "learning_rate": 5.590182195879768e-05, "loss": 0.0159, "step": 202320 }, { "epoch": 48.57, "learning_rate": 5.589825746620401e-05, "loss": 0.0084, "step": 202330 }, { "epoch": 48.57, "learning_rate": 5.5894692943210655e-05, "loss": 0.0089, "step": 202340 }, { "epoch": 48.58, "learning_rate": 5.589112838983601e-05, "loss": 0.0139, "step": 202350 }, { "epoch": 48.58, "learning_rate": 5.588756380609844e-05, "loss": 0.0118, "step": 202360 }, { "epoch": 48.58, "learning_rate": 5.588399919201631e-05, "loss": 0.0075, "step": 202370 }, { "epoch": 48.58, "learning_rate": 5.588043454760801e-05, "loss": 0.0236, "step": 202380 }, { "epoch": 48.59, "learning_rate": 5.587686987289189e-05, "loss": 0.0072, "step": 202390 }, { "epoch": 48.59, "learning_rate": 5.5873305167886334e-05, "loss": 0.0074, "step": 202400 }, { "epoch": 48.59, "learning_rate": 5.586974043260972e-05, "loss": 0.0137, "step": 202410 }, { "epoch": 48.59, "learning_rate": 5.5866175667080414e-05, "loss": 0.0072, "step": 202420 }, { "epoch": 48.6, "learning_rate": 5.586261087131679e-05, "loss": 0.0067, "step": 202430 }, { "epoch": 48.6, "learning_rate": 5.5859046045337216e-05, "loss": 0.0247, "step": 202440 }, { "epoch": 48.6, "learning_rate": 5.585548118916008e-05, "loss": 0.0082, "step": 202450 }, { "epoch": 48.6, "learning_rate": 5.585191630280373e-05, "loss": 0.0082, "step": 202460 }, { "epoch": 48.6, "learning_rate": 5.584835138628657e-05, "loss": 0.0053, "step": 202470 }, { "epoch": 48.61, "learning_rate": 5.584478643962695e-05, "loss": 0.0093, "step": 202480 }, { "epoch": 48.61, "learning_rate": 5.584122146284325e-05, "loss": 0.0092, "step": 202490 }, { "epoch": 48.61, "learning_rate": 5.5837656455953846e-05, "loss": 0.0132, "step": 202500 }, { "epoch": 48.61, "learning_rate": 5.583409141897712e-05, "loss": 0.0099, "step": 202510 }, { "epoch": 48.62, "learning_rate": 5.583052635193142e-05, "loss": 0.0104, "step": 202520 }, { "epoch": 48.62, "learning_rate": 5.5826961254835154e-05, "loss": 0.0085, "step": 202530 }, { "epoch": 48.62, "learning_rate": 5.5823396127706684e-05, "loss": 0.0056, "step": 202540 }, { "epoch": 48.62, "learning_rate": 5.581983097056437e-05, "loss": 0.0105, "step": 202550 }, { "epoch": 48.63, "learning_rate": 5.58162657834266e-05, "loss": 0.0134, "step": 202560 }, { "epoch": 48.63, "learning_rate": 5.581270056631175e-05, "loss": 0.0156, "step": 202570 }, { "epoch": 48.63, "learning_rate": 5.580913531923819e-05, "loss": 0.0056, "step": 202580 }, { "epoch": 48.63, "learning_rate": 5.5805570042224306e-05, "loss": 0.0087, "step": 202590 }, { "epoch": 48.63, "learning_rate": 5.580200473528846e-05, "loss": 0.0083, "step": 202600 }, { "epoch": 48.64, "learning_rate": 5.579843939844903e-05, "loss": 0.0077, "step": 202610 }, { "epoch": 48.64, "learning_rate": 5.579487403172441e-05, "loss": 0.0091, "step": 202620 }, { "epoch": 48.64, "learning_rate": 5.5791308635132955e-05, "loss": 0.0049, "step": 202630 }, { "epoch": 48.64, "learning_rate": 5.578774320869305e-05, "loss": 0.0091, "step": 202640 }, { "epoch": 48.65, "learning_rate": 5.578417775242305e-05, "loss": 0.0068, "step": 202650 }, { "epoch": 48.65, "learning_rate": 5.578061226634136e-05, "loss": 0.0083, "step": 202660 }, { "epoch": 48.65, "learning_rate": 5.5777046750466343e-05, "loss": 0.0039, "step": 202670 }, { "epoch": 48.65, "learning_rate": 5.577348120481638e-05, "loss": 0.0044, "step": 202680 }, { "epoch": 48.65, "learning_rate": 5.5769915629409865e-05, "loss": 0.0136, "step": 202690 }, { "epoch": 48.66, "learning_rate": 5.576635002426512e-05, "loss": 0.0064, "step": 202700 }, { "epoch": 48.66, "learning_rate": 5.576278438940058e-05, "loss": 0.0079, "step": 202710 }, { "epoch": 48.66, "learning_rate": 5.5759218724834596e-05, "loss": 0.0068, "step": 202720 }, { "epoch": 48.66, "learning_rate": 5.575565303058555e-05, "loss": 0.0066, "step": 202730 }, { "epoch": 48.67, "learning_rate": 5.575208730667183e-05, "loss": 0.0093, "step": 202740 }, { "epoch": 48.67, "learning_rate": 5.57485215531118e-05, "loss": 0.0094, "step": 202750 }, { "epoch": 48.67, "learning_rate": 5.5744955769923844e-05, "loss": 0.0047, "step": 202760 }, { "epoch": 48.67, "learning_rate": 5.574138995712633e-05, "loss": 0.0055, "step": 202770 }, { "epoch": 48.68, "learning_rate": 5.573782411473766e-05, "loss": 0.0109, "step": 202780 }, { "epoch": 48.68, "learning_rate": 5.573425824277618e-05, "loss": 0.0045, "step": 202790 }, { "epoch": 48.68, "learning_rate": 5.5730692341260294e-05, "loss": 0.0073, "step": 202800 }, { "epoch": 48.68, "learning_rate": 5.572712641020836e-05, "loss": 0.0122, "step": 202810 }, { "epoch": 48.68, "learning_rate": 5.572356044963878e-05, "loss": 0.0064, "step": 202820 }, { "epoch": 48.69, "learning_rate": 5.571999445956992e-05, "loss": 0.0087, "step": 202830 }, { "epoch": 48.69, "learning_rate": 5.571642844002016e-05, "loss": 0.0049, "step": 202840 }, { "epoch": 48.69, "learning_rate": 5.571286239100788e-05, "loss": 0.01, "step": 202850 }, { "epoch": 48.69, "learning_rate": 5.570929631255144e-05, "loss": 0.0095, "step": 202860 }, { "epoch": 48.7, "learning_rate": 5.570573020466926e-05, "loss": 0.0057, "step": 202870 }, { "epoch": 48.7, "learning_rate": 5.5702164067379694e-05, "loss": 0.0052, "step": 202880 }, { "epoch": 48.7, "learning_rate": 5.569859790070113e-05, "loss": 0.0067, "step": 202890 }, { "epoch": 48.7, "learning_rate": 5.569503170465196e-05, "loss": 0.0062, "step": 202900 }, { "epoch": 48.71, "learning_rate": 5.569146547925053e-05, "loss": 0.0081, "step": 202910 }, { "epoch": 48.71, "learning_rate": 5.568789922451524e-05, "loss": 0.0053, "step": 202920 }, { "epoch": 48.71, "learning_rate": 5.568433294046447e-05, "loss": 0.0136, "step": 202930 }, { "epoch": 48.71, "learning_rate": 5.56807666271166e-05, "loss": 0.0047, "step": 202940 }, { "epoch": 48.71, "learning_rate": 5.567720028449002e-05, "loss": 0.0082, "step": 202950 }, { "epoch": 48.72, "learning_rate": 5.567363391260309e-05, "loss": 0.0081, "step": 202960 }, { "epoch": 48.72, "learning_rate": 5.567006751147421e-05, "loss": 0.0061, "step": 202970 }, { "epoch": 48.72, "learning_rate": 5.566650108112176e-05, "loss": 0.0108, "step": 202980 }, { "epoch": 48.72, "learning_rate": 5.566293462156411e-05, "loss": 0.0039, "step": 202990 }, { "epoch": 48.73, "learning_rate": 5.565936813281964e-05, "loss": 0.0087, "step": 203000 }, { "epoch": 48.73, "learning_rate": 5.565580161490675e-05, "loss": 0.0059, "step": 203010 }, { "epoch": 48.73, "learning_rate": 5.565223506784379e-05, "loss": 0.0041, "step": 203020 }, { "epoch": 48.73, "learning_rate": 5.564866849164919e-05, "loss": 0.0068, "step": 203030 }, { "epoch": 48.73, "learning_rate": 5.56451018863413e-05, "loss": 0.0044, "step": 203040 }, { "epoch": 48.74, "learning_rate": 5.5641535251938513e-05, "loss": 0.0029, "step": 203050 }, { "epoch": 48.74, "learning_rate": 5.56379685884592e-05, "loss": 0.0123, "step": 203060 }, { "epoch": 48.74, "learning_rate": 5.563440189592174e-05, "loss": 0.0043, "step": 203070 }, { "epoch": 48.74, "learning_rate": 5.563083517434453e-05, "loss": 0.0059, "step": 203080 }, { "epoch": 48.75, "learning_rate": 5.5627268423745946e-05, "loss": 0.0048, "step": 203090 }, { "epoch": 48.75, "learning_rate": 5.562370164414439e-05, "loss": 0.0147, "step": 203100 }, { "epoch": 48.75, "learning_rate": 5.562013483555821e-05, "loss": 0.0042, "step": 203110 }, { "epoch": 48.75, "learning_rate": 5.561656799800583e-05, "loss": 0.0086, "step": 203120 }, { "epoch": 48.76, "learning_rate": 5.561300113150559e-05, "loss": 0.0094, "step": 203130 }, { "epoch": 48.76, "learning_rate": 5.5609434236075905e-05, "loss": 0.0119, "step": 203140 }, { "epoch": 48.76, "learning_rate": 5.560586731173515e-05, "loss": 0.0151, "step": 203150 }, { "epoch": 48.76, "learning_rate": 5.56023003585017e-05, "loss": 0.0056, "step": 203160 }, { "epoch": 48.76, "learning_rate": 5.559873337639394e-05, "loss": 0.0045, "step": 203170 }, { "epoch": 48.77, "learning_rate": 5.5595166365430274e-05, "loss": 0.0061, "step": 203180 }, { "epoch": 48.77, "learning_rate": 5.5591599325629086e-05, "loss": 0.0105, "step": 203190 }, { "epoch": 48.77, "learning_rate": 5.558803225700873e-05, "loss": 0.0098, "step": 203200 }, { "epoch": 48.77, "learning_rate": 5.5584465159587615e-05, "loss": 0.0131, "step": 203210 }, { "epoch": 48.78, "learning_rate": 5.558089803338412e-05, "loss": 0.0081, "step": 203220 }, { "epoch": 48.78, "learning_rate": 5.5577330878416625e-05, "loss": 0.0051, "step": 203230 }, { "epoch": 48.78, "learning_rate": 5.5573763694703516e-05, "loss": 0.0051, "step": 203240 }, { "epoch": 48.78, "learning_rate": 5.557019648226319e-05, "loss": 0.0054, "step": 203250 }, { "epoch": 48.79, "learning_rate": 5.5566629241114044e-05, "loss": 0.0087, "step": 203260 }, { "epoch": 48.79, "learning_rate": 5.556306197127442e-05, "loss": 0.0049, "step": 203270 }, { "epoch": 48.79, "learning_rate": 5.5559494672762734e-05, "loss": 0.0039, "step": 203280 }, { "epoch": 48.79, "learning_rate": 5.555592734559737e-05, "loss": 0.0066, "step": 203290 }, { "epoch": 48.79, "learning_rate": 5.55523599897967e-05, "loss": 0.0086, "step": 203300 }, { "epoch": 48.8, "learning_rate": 5.554879260537913e-05, "loss": 0.0077, "step": 203310 }, { "epoch": 48.8, "learning_rate": 5.5545225192363025e-05, "loss": 0.0039, "step": 203320 }, { "epoch": 48.8, "learning_rate": 5.5541657750766785e-05, "loss": 0.0069, "step": 203330 }, { "epoch": 48.8, "learning_rate": 5.5538090280608804e-05, "loss": 0.0051, "step": 203340 }, { "epoch": 48.81, "learning_rate": 5.553452278190746e-05, "loss": 0.0058, "step": 203350 }, { "epoch": 48.81, "learning_rate": 5.553095525468113e-05, "loss": 0.013, "step": 203360 }, { "epoch": 48.81, "learning_rate": 5.552738769894822e-05, "loss": 0.0068, "step": 203370 }, { "epoch": 48.81, "learning_rate": 5.5523820114727096e-05, "loss": 0.0093, "step": 203380 }, { "epoch": 48.81, "learning_rate": 5.552025250203616e-05, "loss": 0.0135, "step": 203390 }, { "epoch": 48.82, "learning_rate": 5.55166848608938e-05, "loss": 0.0057, "step": 203400 }, { "epoch": 48.82, "learning_rate": 5.551311719131841e-05, "loss": 0.0042, "step": 203410 }, { "epoch": 48.82, "learning_rate": 5.550954949332836e-05, "loss": 0.0041, "step": 203420 }, { "epoch": 48.82, "learning_rate": 5.550598176694204e-05, "loss": 0.0362, "step": 203430 }, { "epoch": 48.83, "learning_rate": 5.550241401217785e-05, "loss": 0.0035, "step": 203440 }, { "epoch": 48.83, "learning_rate": 5.5498846229054166e-05, "loss": 0.0124, "step": 203450 }, { "epoch": 48.83, "learning_rate": 5.5495278417589395e-05, "loss": 0.012, "step": 203460 }, { "epoch": 48.83, "learning_rate": 5.54917105778019e-05, "loss": 0.0047, "step": 203470 }, { "epoch": 48.84, "learning_rate": 5.548814270971009e-05, "loss": 0.0041, "step": 203480 }, { "epoch": 48.84, "learning_rate": 5.5484574813332335e-05, "loss": 0.0089, "step": 203490 }, { "epoch": 48.84, "learning_rate": 5.548100688868705e-05, "loss": 0.0072, "step": 203500 }, { "epoch": 48.84, "learning_rate": 5.5477438935792604e-05, "loss": 0.0066, "step": 203510 }, { "epoch": 48.84, "learning_rate": 5.5473870954667384e-05, "loss": 0.0059, "step": 203520 }, { "epoch": 48.85, "learning_rate": 5.54703029453298e-05, "loss": 0.0081, "step": 203530 }, { "epoch": 48.85, "learning_rate": 5.5466734907798225e-05, "loss": 0.0073, "step": 203540 }, { "epoch": 48.85, "learning_rate": 5.546316684209106e-05, "loss": 0.0044, "step": 203550 }, { "epoch": 48.85, "learning_rate": 5.5459598748226684e-05, "loss": 0.0109, "step": 203560 }, { "epoch": 48.86, "learning_rate": 5.545603062622347e-05, "loss": 0.0068, "step": 203570 }, { "epoch": 48.86, "learning_rate": 5.545246247609985e-05, "loss": 0.0153, "step": 203580 }, { "epoch": 48.86, "learning_rate": 5.5448894297874187e-05, "loss": 0.0074, "step": 203590 }, { "epoch": 48.86, "learning_rate": 5.544532609156488e-05, "loss": 0.0055, "step": 203600 }, { "epoch": 48.87, "learning_rate": 5.544175785719031e-05, "loss": 0.0045, "step": 203610 }, { "epoch": 48.87, "learning_rate": 5.543818959476889e-05, "loss": 0.0077, "step": 203620 }, { "epoch": 48.87, "learning_rate": 5.543462130431898e-05, "loss": 0.0062, "step": 203630 }, { "epoch": 48.87, "learning_rate": 5.543105298585899e-05, "loss": 0.0078, "step": 203640 }, { "epoch": 48.87, "learning_rate": 5.54274846394073e-05, "loss": 0.0076, "step": 203650 }, { "epoch": 48.88, "learning_rate": 5.5423916264982325e-05, "loss": 0.0041, "step": 203660 }, { "epoch": 48.88, "learning_rate": 5.5420347862602426e-05, "loss": 0.0064, "step": 203670 }, { "epoch": 48.88, "learning_rate": 5.541677943228601e-05, "loss": 0.0087, "step": 203680 }, { "epoch": 48.88, "learning_rate": 5.541321097405149e-05, "loss": 0.0081, "step": 203690 }, { "epoch": 48.89, "learning_rate": 5.5409642487917216e-05, "loss": 0.0061, "step": 203700 }, { "epoch": 48.89, "learning_rate": 5.5406073973901594e-05, "loss": 0.0057, "step": 203710 }, { "epoch": 48.89, "learning_rate": 5.540250543202303e-05, "loss": 0.0053, "step": 203720 }, { "epoch": 48.89, "learning_rate": 5.539893686229991e-05, "loss": 0.0056, "step": 203730 }, { "epoch": 48.89, "learning_rate": 5.5395368264750624e-05, "loss": 0.0093, "step": 203740 }, { "epoch": 48.9, "learning_rate": 5.539179963939356e-05, "loss": 0.0046, "step": 203750 }, { "epoch": 48.9, "learning_rate": 5.5388230986247117e-05, "loss": 0.0442, "step": 203760 }, { "epoch": 48.9, "learning_rate": 5.538466230532968e-05, "loss": 0.0078, "step": 203770 }, { "epoch": 48.9, "learning_rate": 5.538109359665966e-05, "loss": 0.0059, "step": 203780 }, { "epoch": 48.91, "learning_rate": 5.5377524860255425e-05, "loss": 0.0059, "step": 203790 }, { "epoch": 48.91, "learning_rate": 5.5373956096135395e-05, "loss": 0.0056, "step": 203800 }, { "epoch": 48.91, "learning_rate": 5.537038730431795e-05, "loss": 0.0067, "step": 203810 }, { "epoch": 48.91, "learning_rate": 5.536681848482148e-05, "loss": 0.0058, "step": 203820 }, { "epoch": 48.92, "learning_rate": 5.536324963766438e-05, "loss": 0.004, "step": 203830 }, { "epoch": 48.92, "learning_rate": 5.535968076286506e-05, "loss": 0.0038, "step": 203840 }, { "epoch": 48.92, "learning_rate": 5.5356111860441886e-05, "loss": 0.0049, "step": 203850 }, { "epoch": 48.92, "learning_rate": 5.5352542930413275e-05, "loss": 0.007, "step": 203860 }, { "epoch": 48.92, "learning_rate": 5.53489739727976e-05, "loss": 0.0136, "step": 203870 }, { "epoch": 48.93, "learning_rate": 5.534540498761328e-05, "loss": 0.0106, "step": 203880 }, { "epoch": 48.93, "learning_rate": 5.5341835974878695e-05, "loss": 0.008, "step": 203890 }, { "epoch": 48.93, "learning_rate": 5.5338266934612236e-05, "loss": 0.0052, "step": 203900 }, { "epoch": 48.93, "learning_rate": 5.533469786683232e-05, "loss": 0.0078, "step": 203910 }, { "epoch": 48.94, "learning_rate": 5.533112877155732e-05, "loss": 0.0088, "step": 203920 }, { "epoch": 48.94, "learning_rate": 5.5327559648805625e-05, "loss": 0.0039, "step": 203930 }, { "epoch": 48.94, "learning_rate": 5.532399049859566e-05, "loss": 0.0114, "step": 203940 }, { "epoch": 48.94, "learning_rate": 5.5320421320945795e-05, "loss": 0.0069, "step": 203950 }, { "epoch": 48.95, "learning_rate": 5.5316852115874427e-05, "loss": 0.01, "step": 203960 }, { "epoch": 48.95, "learning_rate": 5.531328288339998e-05, "loss": 0.0111, "step": 203970 }, { "epoch": 48.95, "learning_rate": 5.530971362354083e-05, "loss": 0.0052, "step": 203980 }, { "epoch": 49.0, "learning_rate": 5.530614433631535e-05, "loss": 0.0049, "step": 203990 }, { "epoch": 49.0, "learning_rate": 5.5302575021741967e-05, "loss": 0.0094, "step": 204000 }, { "epoch": 49.01, "learning_rate": 5.5299005679839066e-05, "loss": 0.0114, "step": 204010 }, { "epoch": 49.01, "learning_rate": 5.529543631062505e-05, "loss": 0.0104, "step": 204020 }, { "epoch": 49.01, "learning_rate": 5.5291866914118294e-05, "loss": 0.0045, "step": 204030 }, { "epoch": 49.01, "learning_rate": 5.5288297490337225e-05, "loss": 0.0055, "step": 204040 }, { "epoch": 49.01, "learning_rate": 5.5284728039300234e-05, "loss": 0.0122, "step": 204050 }, { "epoch": 49.02, "learning_rate": 5.52811585610257e-05, "loss": 0.0034, "step": 204060 }, { "epoch": 49.02, "learning_rate": 5.527758905553203e-05, "loss": 0.007, "step": 204070 }, { "epoch": 49.02, "learning_rate": 5.527401952283763e-05, "loss": 0.0058, "step": 204080 }, { "epoch": 49.02, "learning_rate": 5.527044996296088e-05, "loss": 0.0076, "step": 204090 }, { "epoch": 49.03, "learning_rate": 5.526688037592019e-05, "loss": 0.0064, "step": 204100 }, { "epoch": 49.03, "learning_rate": 5.5263310761733955e-05, "loss": 0.0046, "step": 204110 }, { "epoch": 49.03, "learning_rate": 5.525974112042058e-05, "loss": 0.0079, "step": 204120 }, { "epoch": 49.03, "learning_rate": 5.525617145199846e-05, "loss": 0.0033, "step": 204130 }, { "epoch": 49.03, "learning_rate": 5.5252601756485975e-05, "loss": 0.0066, "step": 204140 }, { "epoch": 49.04, "learning_rate": 5.524903203390154e-05, "loss": 0.0074, "step": 204150 }, { "epoch": 49.04, "learning_rate": 5.5245462284263547e-05, "loss": 0.0058, "step": 204160 }, { "epoch": 49.04, "learning_rate": 5.52418925075904e-05, "loss": 0.0049, "step": 204170 }, { "epoch": 49.04, "learning_rate": 5.523832270390049e-05, "loss": 0.007, "step": 204180 }, { "epoch": 49.05, "learning_rate": 5.5234752873212226e-05, "loss": 0.0076, "step": 204190 }, { "epoch": 49.05, "learning_rate": 5.523118301554401e-05, "loss": 0.0065, "step": 204200 }, { "epoch": 49.05, "learning_rate": 5.522761313091422e-05, "loss": 0.007, "step": 204210 }, { "epoch": 49.05, "learning_rate": 5.522404321934127e-05, "loss": 0.0037, "step": 204220 }, { "epoch": 49.06, "learning_rate": 5.5220473280843556e-05, "loss": 0.0058, "step": 204230 }, { "epoch": 49.06, "learning_rate": 5.5216903315439486e-05, "loss": 0.0048, "step": 204240 }, { "epoch": 49.06, "learning_rate": 5.5213333323147446e-05, "loss": 0.0146, "step": 204250 }, { "epoch": 49.06, "learning_rate": 5.5209763303985854e-05, "loss": 0.0053, "step": 204260 }, { "epoch": 49.06, "learning_rate": 5.5206193257973094e-05, "loss": 0.0085, "step": 204270 }, { "epoch": 49.07, "learning_rate": 5.5202623185127564e-05, "loss": 0.0172, "step": 204280 }, { "epoch": 49.07, "learning_rate": 5.519905308546768e-05, "loss": 0.0078, "step": 204290 }, { "epoch": 49.07, "learning_rate": 5.519548295901182e-05, "loss": 0.0095, "step": 204300 }, { "epoch": 49.07, "learning_rate": 5.519191280577841e-05, "loss": 0.0064, "step": 204310 }, { "epoch": 49.08, "learning_rate": 5.518834262578583e-05, "loss": 0.0098, "step": 204320 }, { "epoch": 49.08, "learning_rate": 5.5184772419052485e-05, "loss": 0.0089, "step": 204330 }, { "epoch": 49.08, "learning_rate": 5.51812021855968e-05, "loss": 0.0045, "step": 204340 }, { "epoch": 49.08, "learning_rate": 5.5177631925437146e-05, "loss": 0.0069, "step": 204350 }, { "epoch": 49.09, "learning_rate": 5.5174061638591926e-05, "loss": 0.0053, "step": 204360 }, { "epoch": 49.09, "learning_rate": 5.517049132507954e-05, "loss": 0.006, "step": 204370 }, { "epoch": 49.09, "learning_rate": 5.5166920984918415e-05, "loss": 0.0071, "step": 204380 }, { "epoch": 49.09, "learning_rate": 5.516335061812693e-05, "loss": 0.0041, "step": 204390 }, { "epoch": 49.09, "learning_rate": 5.515978022472349e-05, "loss": 0.0094, "step": 204400 }, { "epoch": 49.1, "learning_rate": 5.515620980472651e-05, "loss": 0.0036, "step": 204410 }, { "epoch": 49.1, "learning_rate": 5.515263935815438e-05, "loss": 0.0081, "step": 204420 }, { "epoch": 49.1, "learning_rate": 5.51490688850255e-05, "loss": 0.0081, "step": 204430 }, { "epoch": 49.1, "learning_rate": 5.514549838535827e-05, "loss": 0.0074, "step": 204440 }, { "epoch": 49.11, "learning_rate": 5.514192785917111e-05, "loss": 0.0048, "step": 204450 }, { "epoch": 49.11, "learning_rate": 5.51383573064824e-05, "loss": 0.0092, "step": 204460 }, { "epoch": 49.11, "learning_rate": 5.513478672731056e-05, "loss": 0.0057, "step": 204470 }, { "epoch": 49.11, "learning_rate": 5.513121612167399e-05, "loss": 0.0062, "step": 204480 }, { "epoch": 49.11, "learning_rate": 5.512764548959108e-05, "loss": 0.0046, "step": 204490 }, { "epoch": 49.12, "learning_rate": 5.512407483108025e-05, "loss": 0.0051, "step": 204500 }, { "epoch": 49.12, "learning_rate": 5.512050414615989e-05, "loss": 0.0058, "step": 204510 }, { "epoch": 49.12, "learning_rate": 5.511693343484842e-05, "loss": 0.0128, "step": 204520 }, { "epoch": 49.12, "learning_rate": 5.5113362697164205e-05, "loss": 0.0055, "step": 204530 }, { "epoch": 49.13, "learning_rate": 5.510979193312569e-05, "loss": 0.0069, "step": 204540 }, { "epoch": 49.13, "learning_rate": 5.510622114275127e-05, "loss": 0.0127, "step": 204550 }, { "epoch": 49.13, "learning_rate": 5.510265032605935e-05, "loss": 0.0092, "step": 204560 }, { "epoch": 49.13, "learning_rate": 5.5099079483068316e-05, "loss": 0.0092, "step": 204570 }, { "epoch": 49.14, "learning_rate": 5.509550861379659e-05, "loss": 0.0055, "step": 204580 }, { "epoch": 49.14, "learning_rate": 5.509193771826257e-05, "loss": 0.0073, "step": 204590 }, { "epoch": 49.14, "learning_rate": 5.508836679648465e-05, "loss": 0.0051, "step": 204600 }, { "epoch": 49.14, "learning_rate": 5.508479584848125e-05, "loss": 0.0053, "step": 204610 }, { "epoch": 49.14, "learning_rate": 5.508122487427078e-05, "loss": 0.008, "step": 204620 }, { "epoch": 49.15, "learning_rate": 5.507765387387163e-05, "loss": 0.0071, "step": 204630 }, { "epoch": 49.15, "learning_rate": 5.507408284730221e-05, "loss": 0.011, "step": 204640 }, { "epoch": 49.15, "learning_rate": 5.507051179458092e-05, "loss": 0.0045, "step": 204650 }, { "epoch": 49.15, "learning_rate": 5.5066940715726166e-05, "loss": 0.0038, "step": 204660 }, { "epoch": 49.16, "learning_rate": 5.5063369610756367e-05, "loss": 0.0134, "step": 204670 }, { "epoch": 49.16, "learning_rate": 5.505979847968991e-05, "loss": 0.0127, "step": 204680 }, { "epoch": 49.16, "learning_rate": 5.50562273225452e-05, "loss": 0.0071, "step": 204690 }, { "epoch": 49.16, "learning_rate": 5.5052656139340676e-05, "loss": 0.0047, "step": 204700 }, { "epoch": 49.17, "learning_rate": 5.504908493009471e-05, "loss": 0.0065, "step": 204710 }, { "epoch": 49.17, "learning_rate": 5.504551369482571e-05, "loss": 0.0105, "step": 204720 }, { "epoch": 49.17, "learning_rate": 5.5041942433552093e-05, "loss": 0.0043, "step": 204730 }, { "epoch": 49.17, "learning_rate": 5.5038371146292265e-05, "loss": 0.0038, "step": 204740 }, { "epoch": 49.17, "learning_rate": 5.503479983306464e-05, "loss": 0.0166, "step": 204750 }, { "epoch": 49.18, "learning_rate": 5.50312284938876e-05, "loss": 0.006, "step": 204760 }, { "epoch": 49.18, "learning_rate": 5.5027657128779587e-05, "loss": 0.0066, "step": 204770 }, { "epoch": 49.18, "learning_rate": 5.502408573775897e-05, "loss": 0.0099, "step": 204780 }, { "epoch": 49.18, "learning_rate": 5.502051432084417e-05, "loss": 0.0035, "step": 204790 }, { "epoch": 49.19, "learning_rate": 5.501694287805361e-05, "loss": 0.0042, "step": 204800 }, { "epoch": 49.19, "learning_rate": 5.5013371409405675e-05, "loss": 0.0052, "step": 204810 }, { "epoch": 49.19, "learning_rate": 5.500979991491879e-05, "loss": 0.0097, "step": 204820 }, { "epoch": 49.19, "learning_rate": 5.500622839461135e-05, "loss": 0.01, "step": 204830 }, { "epoch": 49.19, "learning_rate": 5.500265684850176e-05, "loss": 0.0039, "step": 204840 }, { "epoch": 49.2, "learning_rate": 5.499908527660844e-05, "loss": 0.0043, "step": 204850 }, { "epoch": 49.2, "learning_rate": 5.49955136789498e-05, "loss": 0.0096, "step": 204860 }, { "epoch": 49.2, "learning_rate": 5.499194205554422e-05, "loss": 0.0052, "step": 204870 }, { "epoch": 49.2, "learning_rate": 5.498837040641015e-05, "loss": 0.0078, "step": 204880 }, { "epoch": 49.21, "learning_rate": 5.498479873156597e-05, "loss": 0.0056, "step": 204890 }, { "epoch": 49.21, "learning_rate": 5.498122703103009e-05, "loss": 0.0047, "step": 204900 }, { "epoch": 49.21, "learning_rate": 5.497765530482094e-05, "loss": 0.0077, "step": 204910 }, { "epoch": 49.21, "learning_rate": 5.4974083552956904e-05, "loss": 0.0039, "step": 204920 }, { "epoch": 49.22, "learning_rate": 5.49705117754564e-05, "loss": 0.0085, "step": 204930 }, { "epoch": 49.22, "learning_rate": 5.496693997233784e-05, "loss": 0.0052, "step": 204940 }, { "epoch": 49.22, "learning_rate": 5.496336814361962e-05, "loss": 0.0111, "step": 204950 }, { "epoch": 49.22, "learning_rate": 5.495979628932017e-05, "loss": 0.0064, "step": 204960 }, { "epoch": 49.22, "learning_rate": 5.495622440945788e-05, "loss": 0.0029, "step": 204970 }, { "epoch": 49.23, "learning_rate": 5.495265250405116e-05, "loss": 0.0049, "step": 204980 }, { "epoch": 49.23, "learning_rate": 5.494908057311844e-05, "loss": 0.0055, "step": 204990 }, { "epoch": 49.23, "learning_rate": 5.494550861667812e-05, "loss": 0.0043, "step": 205000 }, { "epoch": 49.23, "learning_rate": 5.49419366347486e-05, "loss": 0.0043, "step": 205010 }, { "epoch": 49.24, "learning_rate": 5.49383646273483e-05, "loss": 0.006, "step": 205020 }, { "epoch": 49.24, "learning_rate": 5.493479259449563e-05, "loss": 0.0057, "step": 205030 }, { "epoch": 49.24, "learning_rate": 5.493122053620899e-05, "loss": 0.005, "step": 205040 }, { "epoch": 49.24, "learning_rate": 5.492764845250681e-05, "loss": 0.0066, "step": 205050 }, { "epoch": 49.25, "learning_rate": 5.492407634340749e-05, "loss": 0.0231, "step": 205060 }, { "epoch": 49.25, "learning_rate": 5.4920504208929426e-05, "loss": 0.0065, "step": 205070 }, { "epoch": 49.25, "learning_rate": 5.491693204909105e-05, "loss": 0.0054, "step": 205080 }, { "epoch": 49.25, "learning_rate": 5.491335986391076e-05, "loss": 0.0038, "step": 205090 }, { "epoch": 49.25, "learning_rate": 5.4909787653406974e-05, "loss": 0.0073, "step": 205100 }, { "epoch": 49.26, "learning_rate": 5.4906215417598106e-05, "loss": 0.0049, "step": 205110 }, { "epoch": 49.26, "learning_rate": 5.4902643156502554e-05, "loss": 0.0071, "step": 205120 }, { "epoch": 49.26, "learning_rate": 5.489907087013875e-05, "loss": 0.0044, "step": 205130 }, { "epoch": 49.26, "learning_rate": 5.489549855852508e-05, "loss": 0.0051, "step": 205140 }, { "epoch": 49.27, "learning_rate": 5.489192622167998e-05, "loss": 0.0071, "step": 205150 }, { "epoch": 49.27, "learning_rate": 5.488835385962184e-05, "loss": 0.0117, "step": 205160 }, { "epoch": 49.27, "learning_rate": 5.4884781472369094e-05, "loss": 0.0072, "step": 205170 }, { "epoch": 49.27, "learning_rate": 5.488120905994014e-05, "loss": 0.0037, "step": 205180 }, { "epoch": 49.27, "learning_rate": 5.48776366223534e-05, "loss": 0.0067, "step": 205190 }, { "epoch": 49.28, "learning_rate": 5.487406415962728e-05, "loss": 0.0153, "step": 205200 }, { "epoch": 49.28, "learning_rate": 5.487049167178019e-05, "loss": 0.0048, "step": 205210 }, { "epoch": 49.28, "learning_rate": 5.486691915883054e-05, "loss": 0.0053, "step": 205220 }, { "epoch": 49.28, "learning_rate": 5.486334662079675e-05, "loss": 0.0045, "step": 205230 }, { "epoch": 49.29, "learning_rate": 5.485977405769723e-05, "loss": 0.0065, "step": 205240 }, { "epoch": 49.29, "learning_rate": 5.485620146955039e-05, "loss": 0.0093, "step": 205250 }, { "epoch": 49.29, "learning_rate": 5.4852628856374664e-05, "loss": 0.0074, "step": 205260 }, { "epoch": 49.29, "learning_rate": 5.484905621818843e-05, "loss": 0.008, "step": 205270 }, { "epoch": 49.3, "learning_rate": 5.484548355501012e-05, "loss": 0.0025, "step": 205280 }, { "epoch": 49.3, "learning_rate": 5.484191086685816e-05, "loss": 0.0081, "step": 205290 }, { "epoch": 49.3, "learning_rate": 5.4838338153750944e-05, "loss": 0.0114, "step": 205300 }, { "epoch": 49.3, "learning_rate": 5.483476541570689e-05, "loss": 0.0056, "step": 205310 }, { "epoch": 49.3, "learning_rate": 5.483119265274442e-05, "loss": 0.0035, "step": 205320 }, { "epoch": 49.31, "learning_rate": 5.482761986488194e-05, "loss": 0.0073, "step": 205330 }, { "epoch": 49.31, "learning_rate": 5.482404705213787e-05, "loss": 0.0052, "step": 205340 }, { "epoch": 49.31, "learning_rate": 5.482047421453063e-05, "loss": 0.0084, "step": 205350 }, { "epoch": 49.31, "learning_rate": 5.481690135207861e-05, "loss": 0.0137, "step": 205360 }, { "epoch": 49.32, "learning_rate": 5.481332846480025e-05, "loss": 0.0082, "step": 205370 }, { "epoch": 49.32, "learning_rate": 5.480975555271395e-05, "loss": 0.0088, "step": 205380 }, { "epoch": 49.32, "learning_rate": 5.480618261583812e-05, "loss": 0.0093, "step": 205390 }, { "epoch": 49.32, "learning_rate": 5.480260965419119e-05, "loss": 0.0128, "step": 205400 }, { "epoch": 49.33, "learning_rate": 5.479903666779158e-05, "loss": 0.0062, "step": 205410 }, { "epoch": 49.33, "learning_rate": 5.4795463656657684e-05, "loss": 0.0134, "step": 205420 }, { "epoch": 49.33, "learning_rate": 5.479189062080793e-05, "loss": 0.0087, "step": 205430 }, { "epoch": 49.33, "learning_rate": 5.478831756026074e-05, "loss": 0.0095, "step": 205440 }, { "epoch": 49.33, "learning_rate": 5.478474447503451e-05, "loss": 0.006, "step": 205450 }, { "epoch": 49.34, "learning_rate": 5.4781171365147674e-05, "loss": 0.0038, "step": 205460 }, { "epoch": 49.34, "learning_rate": 5.4777598230618635e-05, "loss": 0.0069, "step": 205470 }, { "epoch": 49.34, "learning_rate": 5.477402507146582e-05, "loss": 0.0043, "step": 205480 }, { "epoch": 49.34, "learning_rate": 5.477045188770765e-05, "loss": 0.0049, "step": 205490 }, { "epoch": 49.35, "learning_rate": 5.4766878679362523e-05, "loss": 0.0045, "step": 205500 }, { "epoch": 49.35, "learning_rate": 5.476330544644885e-05, "loss": 0.0063, "step": 205510 }, { "epoch": 49.35, "learning_rate": 5.475973218898508e-05, "loss": 0.007, "step": 205520 }, { "epoch": 49.35, "learning_rate": 5.47561589069896e-05, "loss": 0.0035, "step": 205530 }, { "epoch": 49.35, "learning_rate": 5.4752585600480834e-05, "loss": 0.0061, "step": 205540 }, { "epoch": 49.36, "learning_rate": 5.474901226947721e-05, "loss": 0.0051, "step": 205550 }, { "epoch": 49.36, "learning_rate": 5.4745438913997146e-05, "loss": 0.0061, "step": 205560 }, { "epoch": 49.36, "learning_rate": 5.474186553405902e-05, "loss": 0.0083, "step": 205570 }, { "epoch": 49.36, "learning_rate": 5.47382921296813e-05, "loss": 0.0053, "step": 205580 }, { "epoch": 49.37, "learning_rate": 5.473471870088238e-05, "loss": 0.0164, "step": 205590 }, { "epoch": 49.37, "learning_rate": 5.473114524768068e-05, "loss": 0.004, "step": 205600 }, { "epoch": 49.37, "learning_rate": 5.472757177009462e-05, "loss": 0.0077, "step": 205610 }, { "epoch": 49.37, "learning_rate": 5.472399826814262e-05, "loss": 0.0062, "step": 205620 }, { "epoch": 49.38, "learning_rate": 5.472042474184309e-05, "loss": 0.0047, "step": 205630 }, { "epoch": 49.38, "learning_rate": 5.4716851191214446e-05, "loss": 0.004, "step": 205640 }, { "epoch": 49.38, "learning_rate": 5.471327761627512e-05, "loss": 0.0068, "step": 205650 }, { "epoch": 49.38, "learning_rate": 5.4709704017043516e-05, "loss": 0.0054, "step": 205660 }, { "epoch": 49.38, "learning_rate": 5.4706130393538057e-05, "loss": 0.0054, "step": 205670 }, { "epoch": 49.39, "learning_rate": 5.470255674577716e-05, "loss": 0.0184, "step": 205680 }, { "epoch": 49.39, "learning_rate": 5.469898307377925e-05, "loss": 0.005, "step": 205690 }, { "epoch": 49.39, "learning_rate": 5.469540937756276e-05, "loss": 0.0078, "step": 205700 }, { "epoch": 49.39, "learning_rate": 5.469183565714606e-05, "loss": 0.0053, "step": 205710 }, { "epoch": 49.4, "learning_rate": 5.468826191254762e-05, "loss": 0.0042, "step": 205720 }, { "epoch": 49.4, "learning_rate": 5.4684688143785824e-05, "loss": 0.0043, "step": 205730 }, { "epoch": 49.4, "learning_rate": 5.46811143508791e-05, "loss": 0.0058, "step": 205740 }, { "epoch": 49.4, "learning_rate": 5.467754053384589e-05, "loss": 0.009, "step": 205750 }, { "epoch": 49.41, "learning_rate": 5.46739666927046e-05, "loss": 0.0031, "step": 205760 }, { "epoch": 49.41, "learning_rate": 5.467039282747364e-05, "loss": 0.0052, "step": 205770 }, { "epoch": 49.41, "learning_rate": 5.466681893817145e-05, "loss": 0.0041, "step": 205780 }, { "epoch": 49.41, "learning_rate": 5.4663245024816424e-05, "loss": 0.0054, "step": 205790 }, { "epoch": 49.41, "learning_rate": 5.465967108742699e-05, "loss": 0.0064, "step": 205800 }, { "epoch": 49.42, "learning_rate": 5.4656097126021574e-05, "loss": 0.0047, "step": 205810 }, { "epoch": 49.42, "learning_rate": 5.46525231406186e-05, "loss": 0.0061, "step": 205820 }, { "epoch": 49.42, "learning_rate": 5.464894913123647e-05, "loss": 0.0047, "step": 205830 }, { "epoch": 49.42, "learning_rate": 5.4645375097893626e-05, "loss": 0.0033, "step": 205840 }, { "epoch": 49.43, "learning_rate": 5.46418010406085e-05, "loss": 0.0084, "step": 205850 }, { "epoch": 49.43, "learning_rate": 5.463822695939946e-05, "loss": 0.0042, "step": 205860 }, { "epoch": 49.43, "learning_rate": 5.463465285428498e-05, "loss": 0.0061, "step": 205870 }, { "epoch": 49.43, "learning_rate": 5.463107872528346e-05, "loss": 0.0037, "step": 205880 }, { "epoch": 49.43, "learning_rate": 5.46275045724133e-05, "loss": 0.008, "step": 205890 }, { "epoch": 49.44, "learning_rate": 5.462393039569296e-05, "loss": 0.005, "step": 205900 }, { "epoch": 49.44, "learning_rate": 5.462035619514083e-05, "loss": 0.0117, "step": 205910 }, { "epoch": 49.44, "learning_rate": 5.461678197077538e-05, "loss": 0.0124, "step": 205920 }, { "epoch": 49.44, "learning_rate": 5.461320772261497e-05, "loss": 0.0042, "step": 205930 }, { "epoch": 49.45, "learning_rate": 5.4609633450678045e-05, "loss": 0.0043, "step": 205940 }, { "epoch": 49.45, "learning_rate": 5.4606059154983035e-05, "loss": 0.0068, "step": 205950 }, { "epoch": 49.45, "learning_rate": 5.460248483554836e-05, "loss": 0.0053, "step": 205960 }, { "epoch": 49.45, "learning_rate": 5.459891049239244e-05, "loss": 0.0059, "step": 205970 }, { "epoch": 49.46, "learning_rate": 5.4595336125533706e-05, "loss": 0.0077, "step": 205980 }, { "epoch": 49.46, "learning_rate": 5.459176173499057e-05, "loss": 0.0069, "step": 205990 }, { "epoch": 49.46, "learning_rate": 5.4588187320781445e-05, "loss": 0.0064, "step": 206000 }, { "epoch": 49.46, "learning_rate": 5.458461288292477e-05, "loss": 0.0069, "step": 206010 }, { "epoch": 49.46, "learning_rate": 5.4581038421438955e-05, "loss": 0.0141, "step": 206020 }, { "epoch": 49.47, "learning_rate": 5.4577463936342444e-05, "loss": 0.0085, "step": 206030 }, { "epoch": 49.47, "learning_rate": 5.4573889427653626e-05, "loss": 0.0044, "step": 206040 }, { "epoch": 49.47, "learning_rate": 5.457031489539095e-05, "loss": 0.0248, "step": 206050 }, { "epoch": 49.47, "learning_rate": 5.456674033957284e-05, "loss": 0.0073, "step": 206060 }, { "epoch": 49.48, "learning_rate": 5.456316576021772e-05, "loss": 0.0061, "step": 206070 }, { "epoch": 49.48, "learning_rate": 5.455959115734398e-05, "loss": 0.0036, "step": 206080 }, { "epoch": 49.48, "learning_rate": 5.455601653097009e-05, "loss": 0.0046, "step": 206090 }, { "epoch": 49.48, "learning_rate": 5.4552441881114445e-05, "loss": 0.0041, "step": 206100 }, { "epoch": 49.49, "learning_rate": 5.4548867207795476e-05, "loss": 0.0035, "step": 206110 }, { "epoch": 49.49, "learning_rate": 5.454529251103161e-05, "loss": 0.0045, "step": 206120 }, { "epoch": 49.49, "learning_rate": 5.4541717790841276e-05, "loss": 0.004, "step": 206130 }, { "epoch": 49.49, "learning_rate": 5.4538143047242886e-05, "loss": 0.0098, "step": 206140 }, { "epoch": 49.49, "learning_rate": 5.453456828025486e-05, "loss": 0.0039, "step": 206150 }, { "epoch": 49.5, "learning_rate": 5.453099348989563e-05, "loss": 0.0055, "step": 206160 }, { "epoch": 49.5, "learning_rate": 5.452741867618363e-05, "loss": 0.0059, "step": 206170 }, { "epoch": 49.5, "learning_rate": 5.452384383913728e-05, "loss": 0.0078, "step": 206180 }, { "epoch": 49.5, "learning_rate": 5.452026897877499e-05, "loss": 0.0065, "step": 206190 }, { "epoch": 49.51, "learning_rate": 5.451669409511518e-05, "loss": 0.0028, "step": 206200 }, { "epoch": 49.51, "learning_rate": 5.451311918817633e-05, "loss": 0.0062, "step": 206210 }, { "epoch": 49.51, "learning_rate": 5.450954425797681e-05, "loss": 0.0051, "step": 206220 }, { "epoch": 49.51, "learning_rate": 5.4505969304535055e-05, "loss": 0.0063, "step": 206230 }, { "epoch": 49.51, "learning_rate": 5.45023943278695e-05, "loss": 0.005, "step": 206240 }, { "epoch": 49.52, "learning_rate": 5.449881932799856e-05, "loss": 0.0056, "step": 206250 }, { "epoch": 49.52, "learning_rate": 5.4495244304940684e-05, "loss": 0.0129, "step": 206260 }, { "epoch": 49.52, "learning_rate": 5.4491669258714275e-05, "loss": 0.0054, "step": 206270 }, { "epoch": 49.52, "learning_rate": 5.448809418933777e-05, "loss": 0.0134, "step": 206280 }, { "epoch": 49.53, "learning_rate": 5.4484519096829576e-05, "loss": 0.0089, "step": 206290 }, { "epoch": 49.53, "learning_rate": 5.448094398120814e-05, "loss": 0.0086, "step": 206300 }, { "epoch": 49.53, "learning_rate": 5.447736884249188e-05, "loss": 0.0057, "step": 206310 }, { "epoch": 49.53, "learning_rate": 5.4473793680699225e-05, "loss": 0.0107, "step": 206320 }, { "epoch": 49.54, "learning_rate": 5.44702184958486e-05, "loss": 0.0104, "step": 206330 }, { "epoch": 49.54, "learning_rate": 5.446664328795843e-05, "loss": 0.0138, "step": 206340 }, { "epoch": 49.54, "learning_rate": 5.4463068057047137e-05, "loss": 0.0057, "step": 206350 }, { "epoch": 49.54, "learning_rate": 5.445949280313316e-05, "loss": 0.0095, "step": 206360 }, { "epoch": 49.54, "learning_rate": 5.445591752623492e-05, "loss": 0.0098, "step": 206370 }, { "epoch": 49.55, "learning_rate": 5.4452342226370845e-05, "loss": 0.0048, "step": 206380 }, { "epoch": 49.55, "learning_rate": 5.4448766903559366e-05, "loss": 0.0117, "step": 206390 }, { "epoch": 49.55, "learning_rate": 5.4445191557818894e-05, "loss": 0.0047, "step": 206400 }, { "epoch": 49.55, "learning_rate": 5.4441616189167876e-05, "loss": 0.0058, "step": 206410 }, { "epoch": 49.56, "learning_rate": 5.4438040797624735e-05, "loss": 0.0161, "step": 206420 }, { "epoch": 49.56, "learning_rate": 5.443446538320789e-05, "loss": 0.0069, "step": 206430 }, { "epoch": 49.56, "learning_rate": 5.443088994593577e-05, "loss": 0.0104, "step": 206440 }, { "epoch": 49.56, "learning_rate": 5.442731448582681e-05, "loss": 0.0235, "step": 206450 }, { "epoch": 49.57, "learning_rate": 5.442373900289943e-05, "loss": 0.0126, "step": 206460 }, { "epoch": 49.57, "learning_rate": 5.442016349717206e-05, "loss": 0.0084, "step": 206470 }, { "epoch": 49.57, "learning_rate": 5.441658796866313e-05, "loss": 0.007, "step": 206480 }, { "epoch": 49.57, "learning_rate": 5.441301241739107e-05, "loss": 0.0057, "step": 206490 }, { "epoch": 49.57, "learning_rate": 5.440943684337432e-05, "loss": 0.0051, "step": 206500 }, { "epoch": 49.58, "learning_rate": 5.440586124663128e-05, "loss": 0.0044, "step": 206510 }, { "epoch": 49.58, "learning_rate": 5.4402285627180394e-05, "loss": 0.0071, "step": 206520 }, { "epoch": 49.58, "learning_rate": 5.4398709985040096e-05, "loss": 0.0106, "step": 206530 }, { "epoch": 49.58, "learning_rate": 5.439513432022881e-05, "loss": 0.0107, "step": 206540 }, { "epoch": 49.59, "learning_rate": 5.4391558632764973e-05, "loss": 0.0124, "step": 206550 }, { "epoch": 49.59, "learning_rate": 5.438798292266699e-05, "loss": 0.009, "step": 206560 }, { "epoch": 49.59, "learning_rate": 5.438440718995333e-05, "loss": 0.0142, "step": 206570 }, { "epoch": 49.59, "learning_rate": 5.4380831434642385e-05, "loss": 0.0057, "step": 206580 }, { "epoch": 49.59, "learning_rate": 5.43772556567526e-05, "loss": 0.0045, "step": 206590 }, { "epoch": 49.6, "learning_rate": 5.4373679856302395e-05, "loss": 0.0039, "step": 206600 }, { "epoch": 49.6, "learning_rate": 5.437010403331021e-05, "loss": 0.0032, "step": 206610 }, { "epoch": 49.6, "learning_rate": 5.4366528187794474e-05, "loss": 0.0046, "step": 206620 }, { "epoch": 49.6, "learning_rate": 5.4362952319773616e-05, "loss": 0.0073, "step": 206630 }, { "epoch": 49.61, "learning_rate": 5.435937642926606e-05, "loss": 0.0068, "step": 206640 }, { "epoch": 49.61, "learning_rate": 5.4355800516290256e-05, "loss": 0.0057, "step": 206650 }, { "epoch": 49.61, "learning_rate": 5.435222458086461e-05, "loss": 0.0051, "step": 206660 }, { "epoch": 49.61, "learning_rate": 5.434864862300756e-05, "loss": 0.0073, "step": 206670 }, { "epoch": 49.62, "learning_rate": 5.434507264273754e-05, "loss": 0.0082, "step": 206680 }, { "epoch": 49.62, "learning_rate": 5.434149664007297e-05, "loss": 0.0079, "step": 206690 }, { "epoch": 49.62, "learning_rate": 5.433792061503231e-05, "loss": 0.0075, "step": 206700 }, { "epoch": 49.62, "learning_rate": 5.4334344567633966e-05, "loss": 0.0115, "step": 206710 }, { "epoch": 49.62, "learning_rate": 5.4330768497896365e-05, "loss": 0.0039, "step": 206720 }, { "epoch": 49.63, "learning_rate": 5.4327192405837956e-05, "loss": 0.0067, "step": 206730 }, { "epoch": 49.63, "learning_rate": 5.4323616291477156e-05, "loss": 0.0067, "step": 206740 }, { "epoch": 49.63, "learning_rate": 5.432004015483241e-05, "loss": 0.0135, "step": 206750 }, { "epoch": 49.63, "learning_rate": 5.431646399592213e-05, "loss": 0.0094, "step": 206760 }, { "epoch": 49.64, "learning_rate": 5.431288781476476e-05, "loss": 0.006, "step": 206770 }, { "epoch": 49.64, "learning_rate": 5.430931161137872e-05, "loss": 0.0295, "step": 206780 }, { "epoch": 49.64, "learning_rate": 5.4305735385782464e-05, "loss": 0.0136, "step": 206790 }, { "epoch": 49.64, "learning_rate": 5.430215913799441e-05, "loss": 0.0047, "step": 206800 }, { "epoch": 49.65, "learning_rate": 5.4298582868033e-05, "loss": 0.0119, "step": 206810 }, { "epoch": 49.65, "learning_rate": 5.429500657591665e-05, "loss": 0.0061, "step": 206820 }, { "epoch": 49.65, "learning_rate": 5.42914302616638e-05, "loss": 0.0103, "step": 206830 }, { "epoch": 49.65, "learning_rate": 5.4287853925292887e-05, "loss": 0.0093, "step": 206840 }, { "epoch": 49.65, "learning_rate": 5.428427756682234e-05, "loss": 0.0059, "step": 206850 }, { "epoch": 49.66, "learning_rate": 5.428070118627059e-05, "loss": 0.0055, "step": 206860 }, { "epoch": 49.66, "learning_rate": 5.4277124783656067e-05, "loss": 0.0069, "step": 206870 }, { "epoch": 49.66, "learning_rate": 5.427354835899721e-05, "loss": 0.0085, "step": 206880 }, { "epoch": 49.66, "learning_rate": 5.4269971912312436e-05, "loss": 0.016, "step": 206890 }, { "epoch": 49.67, "learning_rate": 5.4266395443620197e-05, "loss": 0.0092, "step": 206900 }, { "epoch": 49.67, "learning_rate": 5.4262818952938934e-05, "loss": 0.0034, "step": 206910 }, { "epoch": 49.67, "learning_rate": 5.425924244028706e-05, "loss": 0.007, "step": 206920 }, { "epoch": 49.67, "learning_rate": 5.425566590568299e-05, "loss": 0.0083, "step": 206930 }, { "epoch": 49.67, "learning_rate": 5.425208934914521e-05, "loss": 0.0183, "step": 206940 }, { "epoch": 49.68, "learning_rate": 5.424851277069212e-05, "loss": 0.0083, "step": 206950 }, { "epoch": 49.68, "learning_rate": 5.4244936170342166e-05, "loss": 0.0046, "step": 206960 }, { "epoch": 49.68, "learning_rate": 5.4241359548113767e-05, "loss": 0.0062, "step": 206970 }, { "epoch": 49.68, "learning_rate": 5.423778290402536e-05, "loss": 0.0047, "step": 206980 }, { "epoch": 49.69, "learning_rate": 5.42342062380954e-05, "loss": 0.0108, "step": 206990 }, { "epoch": 49.69, "learning_rate": 5.4230629550342305e-05, "loss": 0.0325, "step": 207000 }, { "epoch": 49.69, "learning_rate": 5.42270528407845e-05, "loss": 0.0059, "step": 207010 }, { "epoch": 49.69, "learning_rate": 5.422347610944043e-05, "loss": 0.0074, "step": 207020 }, { "epoch": 49.7, "learning_rate": 5.421989935632853e-05, "loss": 0.0086, "step": 207030 }, { "epoch": 49.7, "learning_rate": 5.421632258146724e-05, "loss": 0.0073, "step": 207040 }, { "epoch": 49.7, "learning_rate": 5.421274578487497e-05, "loss": 0.0056, "step": 207050 }, { "epoch": 49.7, "learning_rate": 5.420916896657019e-05, "loss": 0.0132, "step": 207060 }, { "epoch": 49.7, "learning_rate": 5.4205592126571327e-05, "loss": 0.0102, "step": 207070 }, { "epoch": 49.71, "learning_rate": 5.420201526489679e-05, "loss": 0.0059, "step": 207080 }, { "epoch": 49.71, "learning_rate": 5.419843838156502e-05, "loss": 0.004, "step": 207090 }, { "epoch": 49.71, "learning_rate": 5.4194861476594484e-05, "loss": 0.009, "step": 207100 }, { "epoch": 49.71, "learning_rate": 5.4191284550003585e-05, "loss": 0.0084, "step": 207110 }, { "epoch": 49.72, "learning_rate": 5.418770760181078e-05, "loss": 0.0078, "step": 207120 }, { "epoch": 49.72, "learning_rate": 5.418413063203449e-05, "loss": 0.0071, "step": 207130 }, { "epoch": 49.72, "learning_rate": 5.4180553640693166e-05, "loss": 0.0071, "step": 207140 }, { "epoch": 49.72, "learning_rate": 5.417697662780522e-05, "loss": 0.0062, "step": 207150 }, { "epoch": 49.73, "learning_rate": 5.417339959338911e-05, "loss": 0.0064, "step": 207160 }, { "epoch": 49.73, "learning_rate": 5.416982253746325e-05, "loss": 0.0073, "step": 207170 }, { "epoch": 49.73, "learning_rate": 5.4166245460046104e-05, "loss": 0.01, "step": 207180 }, { "epoch": 49.73, "learning_rate": 5.416266836115609e-05, "loss": 0.0064, "step": 207190 }, { "epoch": 49.73, "learning_rate": 5.4159091240811646e-05, "loss": 0.0088, "step": 207200 }, { "epoch": 49.74, "learning_rate": 5.415551409903122e-05, "loss": 0.0036, "step": 207210 }, { "epoch": 49.74, "learning_rate": 5.4151936935833236e-05, "loss": 0.0033, "step": 207220 }, { "epoch": 49.74, "learning_rate": 5.4148359751236136e-05, "loss": 0.0124, "step": 207230 }, { "epoch": 49.74, "learning_rate": 5.414478254525833e-05, "loss": 0.0094, "step": 207240 }, { "epoch": 49.75, "learning_rate": 5.414120531791831e-05, "loss": 0.0064, "step": 207250 }, { "epoch": 49.75, "learning_rate": 5.413762806923447e-05, "loss": 0.0026, "step": 207260 }, { "epoch": 49.75, "learning_rate": 5.413405079922525e-05, "loss": 0.005, "step": 207270 }, { "epoch": 49.75, "learning_rate": 5.413047350790913e-05, "loss": 0.0065, "step": 207280 }, { "epoch": 49.75, "learning_rate": 5.41268961953045e-05, "loss": 0.0046, "step": 207290 }, { "epoch": 49.76, "learning_rate": 5.4123318861429804e-05, "loss": 0.0104, "step": 207300 }, { "epoch": 49.76, "learning_rate": 5.411974150630349e-05, "loss": 0.0043, "step": 207310 }, { "epoch": 49.76, "learning_rate": 5.4116164129944006e-05, "loss": 0.004, "step": 207320 }, { "epoch": 49.76, "learning_rate": 5.411258673236976e-05, "loss": 0.0073, "step": 207330 }, { "epoch": 49.77, "learning_rate": 5.4109009313599215e-05, "loss": 0.0064, "step": 207340 }, { "epoch": 49.77, "learning_rate": 5.4105431873650805e-05, "loss": 0.0045, "step": 207350 }, { "epoch": 49.77, "learning_rate": 5.410185441254297e-05, "loss": 0.0076, "step": 207360 }, { "epoch": 49.77, "learning_rate": 5.4098276930294136e-05, "loss": 0.0065, "step": 207370 }, { "epoch": 49.78, "learning_rate": 5.4094699426922745e-05, "loss": 0.0076, "step": 207380 }, { "epoch": 49.78, "learning_rate": 5.409112190244725e-05, "loss": 0.0317, "step": 207390 }, { "epoch": 49.78, "learning_rate": 5.408754435688606e-05, "loss": 0.0093, "step": 207400 }, { "epoch": 49.78, "learning_rate": 5.4083966790257636e-05, "loss": 0.0069, "step": 207410 }, { "epoch": 49.78, "learning_rate": 5.408038920258042e-05, "loss": 0.0088, "step": 207420 }, { "epoch": 49.79, "learning_rate": 5.407681159387286e-05, "loss": 0.0093, "step": 207430 }, { "epoch": 49.79, "learning_rate": 5.407323396415336e-05, "loss": 0.0071, "step": 207440 }, { "epoch": 49.79, "learning_rate": 5.4069656313440376e-05, "loss": 0.0052, "step": 207450 }, { "epoch": 49.79, "learning_rate": 5.406607864175235e-05, "loss": 0.0042, "step": 207460 }, { "epoch": 49.8, "learning_rate": 5.406250094910773e-05, "loss": 0.0043, "step": 207470 }, { "epoch": 49.8, "learning_rate": 5.405892323552494e-05, "loss": 0.0068, "step": 207480 }, { "epoch": 49.8, "learning_rate": 5.405534550102243e-05, "loss": 0.0058, "step": 207490 }, { "epoch": 49.8, "learning_rate": 5.4051767745618634e-05, "loss": 0.0041, "step": 207500 }, { "epoch": 49.81, "learning_rate": 5.4048189969331994e-05, "loss": 0.0044, "step": 207510 }, { "epoch": 49.81, "learning_rate": 5.404461217218094e-05, "loss": 0.0042, "step": 207520 }, { "epoch": 49.81, "learning_rate": 5.4041034354183926e-05, "loss": 0.0098, "step": 207530 }, { "epoch": 49.81, "learning_rate": 5.4037456515359394e-05, "loss": 0.0041, "step": 207540 }, { "epoch": 49.81, "learning_rate": 5.403387865572577e-05, "loss": 0.0052, "step": 207550 }, { "epoch": 49.82, "learning_rate": 5.403030077530149e-05, "loss": 0.0068, "step": 207560 }, { "epoch": 49.82, "learning_rate": 5.402672287410503e-05, "loss": 0.0038, "step": 207570 }, { "epoch": 49.82, "learning_rate": 5.40231449521548e-05, "loss": 0.0038, "step": 207580 }, { "epoch": 49.82, "learning_rate": 5.401956700946924e-05, "loss": 0.0066, "step": 207590 }, { "epoch": 49.83, "learning_rate": 5.4015989046066804e-05, "loss": 0.0071, "step": 207600 }, { "epoch": 49.83, "learning_rate": 5.4012411061965917e-05, "loss": 0.0077, "step": 207610 }, { "epoch": 49.83, "learning_rate": 5.400883305718504e-05, "loss": 0.0062, "step": 207620 }, { "epoch": 49.83, "learning_rate": 5.400525503174261e-05, "loss": 0.0057, "step": 207630 }, { "epoch": 49.83, "learning_rate": 5.4001676985657054e-05, "loss": 0.008, "step": 207640 }, { "epoch": 49.84, "learning_rate": 5.3998098918946826e-05, "loss": 0.0061, "step": 207650 }, { "epoch": 49.84, "learning_rate": 5.399452083163036e-05, "loss": 0.0126, "step": 207660 }, { "epoch": 49.84, "learning_rate": 5.399094272372609e-05, "loss": 0.0045, "step": 207670 }, { "epoch": 49.84, "learning_rate": 5.398736459525248e-05, "loss": 0.0041, "step": 207680 }, { "epoch": 49.85, "learning_rate": 5.3983786446227946e-05, "loss": 0.0054, "step": 207690 }, { "epoch": 49.85, "learning_rate": 5.398020827667095e-05, "loss": 0.0068, "step": 207700 }, { "epoch": 49.85, "learning_rate": 5.397663008659993e-05, "loss": 0.0076, "step": 207710 }, { "epoch": 49.85, "learning_rate": 5.397305187603333e-05, "loss": 0.0114, "step": 207720 }, { "epoch": 49.86, "learning_rate": 5.396947364498959e-05, "loss": 0.0043, "step": 207730 }, { "epoch": 49.86, "learning_rate": 5.3965895393487134e-05, "loss": 0.0097, "step": 207740 }, { "epoch": 49.86, "learning_rate": 5.396231712154443e-05, "loss": 0.0048, "step": 207750 }, { "epoch": 49.86, "learning_rate": 5.39587388291799e-05, "loss": 0.0054, "step": 207760 }, { "epoch": 49.86, "learning_rate": 5.3955160516412005e-05, "loss": 0.0057, "step": 207770 }, { "epoch": 49.87, "learning_rate": 5.395158218325919e-05, "loss": 0.0051, "step": 207780 }, { "epoch": 49.87, "learning_rate": 5.394800382973988e-05, "loss": 0.0111, "step": 207790 }, { "epoch": 49.87, "learning_rate": 5.394442545587253e-05, "loss": 0.0181, "step": 207800 }, { "epoch": 49.87, "learning_rate": 5.394084706167557e-05, "loss": 0.0115, "step": 207810 }, { "epoch": 49.88, "learning_rate": 5.393726864716745e-05, "loss": 0.0049, "step": 207820 }, { "epoch": 49.88, "learning_rate": 5.393369021236662e-05, "loss": 0.0057, "step": 207830 }, { "epoch": 49.88, "learning_rate": 5.393011175729151e-05, "loss": 0.0128, "step": 207840 }, { "epoch": 49.88, "learning_rate": 5.392653328196058e-05, "loss": 0.004, "step": 207850 }, { "epoch": 49.89, "learning_rate": 5.392295478639225e-05, "loss": 0.0073, "step": 207860 }, { "epoch": 49.89, "learning_rate": 5.3919376270604995e-05, "loss": 0.0356, "step": 207870 }, { "epoch": 49.89, "learning_rate": 5.3915797734617236e-05, "loss": 0.0067, "step": 207880 }, { "epoch": 49.89, "learning_rate": 5.391221917844742e-05, "loss": 0.0038, "step": 207890 }, { "epoch": 49.89, "learning_rate": 5.390864060211399e-05, "loss": 0.0055, "step": 207900 }, { "epoch": 49.9, "learning_rate": 5.39050620056354e-05, "loss": 0.0085, "step": 207910 }, { "epoch": 49.9, "learning_rate": 5.390148338903008e-05, "loss": 0.0027, "step": 207920 }, { "epoch": 49.9, "learning_rate": 5.3897904752316505e-05, "loss": 0.0103, "step": 207930 }, { "epoch": 49.9, "learning_rate": 5.389432609551308e-05, "loss": 0.006, "step": 207940 }, { "epoch": 49.91, "learning_rate": 5.3890747418638266e-05, "loss": 0.0068, "step": 207950 }, { "epoch": 49.91, "learning_rate": 5.388716872171051e-05, "loss": 0.0041, "step": 207960 }, { "epoch": 49.91, "learning_rate": 5.388359000474825e-05, "loss": 0.0042, "step": 207970 }, { "epoch": 49.91, "learning_rate": 5.388001126776994e-05, "loss": 0.0089, "step": 207980 }, { "epoch": 49.91, "learning_rate": 5.3876432510794016e-05, "loss": 0.008, "step": 207990 }, { "epoch": 49.92, "learning_rate": 5.387285373383892e-05, "loss": 0.0081, "step": 208000 }, { "epoch": 49.92, "learning_rate": 5.386927493692311e-05, "loss": 0.0038, "step": 208010 }, { "epoch": 49.92, "learning_rate": 5.386569612006502e-05, "loss": 0.0039, "step": 208020 }, { "epoch": 49.92, "learning_rate": 5.386211728328311e-05, "loss": 0.0047, "step": 208030 }, { "epoch": 49.93, "learning_rate": 5.385853842659581e-05, "loss": 0.0046, "step": 208040 }, { "epoch": 49.93, "learning_rate": 5.385495955002157e-05, "loss": 0.0028, "step": 208050 }, { "epoch": 49.93, "learning_rate": 5.385138065357883e-05, "loss": 0.0055, "step": 208060 }, { "epoch": 49.93, "learning_rate": 5.3847801737286065e-05, "loss": 0.0058, "step": 208070 }, { "epoch": 49.94, "learning_rate": 5.3844222801161684e-05, "loss": 0.0049, "step": 208080 }, { "epoch": 49.94, "learning_rate": 5.384064384522414e-05, "loss": 0.0049, "step": 208090 }, { "epoch": 49.94, "learning_rate": 5.3837064869491885e-05, "loss": 0.0051, "step": 208100 }, { "epoch": 49.94, "learning_rate": 5.383348587398337e-05, "loss": 0.0068, "step": 208110 }, { "epoch": 49.94, "learning_rate": 5.3829906858717036e-05, "loss": 0.0028, "step": 208120 }, { "epoch": 49.95, "learning_rate": 5.382632782371133e-05, "loss": 0.0052, "step": 208130 }, { "epoch": 49.95, "learning_rate": 5.3822748768984696e-05, "loss": 0.0052, "step": 208140 }, { "epoch": 49.95, "learning_rate": 5.381916969455558e-05, "loss": 0.0061, "step": 208150 }, { "epoch": 50.0, "learning_rate": 5.3815590600442445e-05, "loss": 0.0085, "step": 208160 }, { "epoch": 50.0, "learning_rate": 5.381201148666372e-05, "loss": 0.0055, "step": 208170 }, { "epoch": 50.01, "learning_rate": 5.380843235323785e-05, "loss": 0.0043, "step": 208180 }, { "epoch": 50.01, "learning_rate": 5.380485320018329e-05, "loss": 0.0052, "step": 208190 }, { "epoch": 50.01, "learning_rate": 5.380127402751848e-05, "loss": 0.0039, "step": 208200 }, { "epoch": 50.01, "learning_rate": 5.379769483526188e-05, "loss": 0.0063, "step": 208210 }, { "epoch": 50.02, "learning_rate": 5.379411562343193e-05, "loss": 0.0116, "step": 208220 }, { "epoch": 50.02, "learning_rate": 5.3790536392047077e-05, "loss": 0.0058, "step": 208230 }, { "epoch": 50.02, "learning_rate": 5.378695714112576e-05, "loss": 0.0058, "step": 208240 }, { "epoch": 50.02, "learning_rate": 5.378337787068644e-05, "loss": 0.006, "step": 208250 }, { "epoch": 50.03, "learning_rate": 5.377979858074755e-05, "loss": 0.0042, "step": 208260 }, { "epoch": 50.03, "learning_rate": 5.377621927132756e-05, "loss": 0.0109, "step": 208270 }, { "epoch": 50.03, "learning_rate": 5.3772639942444894e-05, "loss": 0.0071, "step": 208280 }, { "epoch": 50.03, "learning_rate": 5.3769060594118014e-05, "loss": 0.0226, "step": 208290 }, { "epoch": 50.03, "learning_rate": 5.3765481226365354e-05, "loss": 0.0059, "step": 208300 }, { "epoch": 50.04, "learning_rate": 5.376190183920539e-05, "loss": 0.0058, "step": 208310 }, { "epoch": 50.04, "learning_rate": 5.375832243265654e-05, "loss": 0.0038, "step": 208320 }, { "epoch": 50.04, "learning_rate": 5.375474300673727e-05, "loss": 0.0098, "step": 208330 }, { "epoch": 50.04, "learning_rate": 5.375116356146602e-05, "loss": 0.0064, "step": 208340 }, { "epoch": 50.05, "learning_rate": 5.374758409686125e-05, "loss": 0.0079, "step": 208350 }, { "epoch": 50.05, "learning_rate": 5.37440046129414e-05, "loss": 0.005, "step": 208360 }, { "epoch": 50.05, "learning_rate": 5.374042510972491e-05, "loss": 0.0079, "step": 208370 }, { "epoch": 50.05, "learning_rate": 5.373684558723024e-05, "loss": 0.0044, "step": 208380 }, { "epoch": 50.05, "learning_rate": 5.373326604547584e-05, "loss": 0.0058, "step": 208390 }, { "epoch": 50.06, "learning_rate": 5.372968648448015e-05, "loss": 0.0074, "step": 208400 }, { "epoch": 50.06, "learning_rate": 5.372610690426163e-05, "loss": 0.0062, "step": 208410 }, { "epoch": 50.06, "learning_rate": 5.372252730483872e-05, "loss": 0.0117, "step": 208420 }, { "epoch": 50.06, "learning_rate": 5.371894768622988e-05, "loss": 0.0096, "step": 208430 }, { "epoch": 50.07, "learning_rate": 5.371536804845354e-05, "loss": 0.0068, "step": 208440 }, { "epoch": 50.07, "learning_rate": 5.371178839152816e-05, "loss": 0.0054, "step": 208450 }, { "epoch": 50.07, "learning_rate": 5.370820871547221e-05, "loss": 0.0065, "step": 208460 }, { "epoch": 50.07, "learning_rate": 5.370462902030411e-05, "loss": 0.0046, "step": 208470 }, { "epoch": 50.08, "learning_rate": 5.3701049306042315e-05, "loss": 0.0041, "step": 208480 }, { "epoch": 50.08, "learning_rate": 5.3697469572705295e-05, "loss": 0.0049, "step": 208490 }, { "epoch": 50.08, "learning_rate": 5.369388982031149e-05, "loss": 0.0119, "step": 208500 }, { "epoch": 50.08, "learning_rate": 5.3690310048879334e-05, "loss": 0.0055, "step": 208510 }, { "epoch": 50.08, "learning_rate": 5.368673025842729e-05, "loss": 0.0073, "step": 208520 }, { "epoch": 50.09, "learning_rate": 5.368315044897381e-05, "loss": 0.0037, "step": 208530 }, { "epoch": 50.09, "learning_rate": 5.367957062053733e-05, "loss": 0.0086, "step": 208540 }, { "epoch": 50.09, "learning_rate": 5.367599077313633e-05, "loss": 0.0043, "step": 208550 }, { "epoch": 50.09, "learning_rate": 5.3672410906789237e-05, "loss": 0.007, "step": 208560 }, { "epoch": 50.1, "learning_rate": 5.3668831021514496e-05, "loss": 0.0066, "step": 208570 }, { "epoch": 50.1, "learning_rate": 5.366525111733059e-05, "loss": 0.007, "step": 208580 }, { "epoch": 50.1, "learning_rate": 5.366167119425595e-05, "loss": 0.0043, "step": 208590 }, { "epoch": 50.1, "learning_rate": 5.365809125230899e-05, "loss": 0.0074, "step": 208600 }, { "epoch": 50.11, "learning_rate": 5.365451129150823e-05, "loss": 0.0058, "step": 208610 }, { "epoch": 50.11, "learning_rate": 5.365093131187208e-05, "loss": 0.0055, "step": 208620 }, { "epoch": 50.11, "learning_rate": 5.364735131341899e-05, "loss": 0.0081, "step": 208630 }, { "epoch": 50.11, "learning_rate": 5.364377129616743e-05, "loss": 0.005, "step": 208640 }, { "epoch": 50.11, "learning_rate": 5.3640191260135863e-05, "loss": 0.0079, "step": 208650 }, { "epoch": 50.12, "learning_rate": 5.363661120534269e-05, "loss": 0.0092, "step": 208660 }, { "epoch": 50.12, "learning_rate": 5.363303113180641e-05, "loss": 0.0068, "step": 208670 }, { "epoch": 50.12, "learning_rate": 5.362945103954544e-05, "loss": 0.0066, "step": 208680 }, { "epoch": 50.12, "learning_rate": 5.362587092857826e-05, "loss": 0.0063, "step": 208690 }, { "epoch": 50.13, "learning_rate": 5.3622290798923315e-05, "loss": 0.0086, "step": 208700 }, { "epoch": 50.13, "learning_rate": 5.361871065059904e-05, "loss": 0.0042, "step": 208710 }, { "epoch": 50.13, "learning_rate": 5.361513048362392e-05, "loss": 0.0036, "step": 208720 }, { "epoch": 50.13, "learning_rate": 5.361155029801637e-05, "loss": 0.0044, "step": 208730 }, { "epoch": 50.13, "learning_rate": 5.360797009379487e-05, "loss": 0.0083, "step": 208740 }, { "epoch": 50.14, "learning_rate": 5.3604389870977845e-05, "loss": 0.0043, "step": 208750 }, { "epoch": 50.14, "learning_rate": 5.360080962958377e-05, "loss": 0.0076, "step": 208760 }, { "epoch": 50.14, "learning_rate": 5.35972293696311e-05, "loss": 0.0042, "step": 208770 }, { "epoch": 50.14, "learning_rate": 5.359364909113827e-05, "loss": 0.0057, "step": 208780 }, { "epoch": 50.15, "learning_rate": 5.359006879412376e-05, "loss": 0.0101, "step": 208790 }, { "epoch": 50.15, "learning_rate": 5.358648847860599e-05, "loss": 0.0043, "step": 208800 }, { "epoch": 50.15, "learning_rate": 5.358290814460344e-05, "loss": 0.0053, "step": 208810 }, { "epoch": 50.15, "learning_rate": 5.357932779213454e-05, "loss": 0.0071, "step": 208820 }, { "epoch": 50.16, "learning_rate": 5.357574742121776e-05, "loss": 0.0042, "step": 208830 }, { "epoch": 50.16, "learning_rate": 5.3572167031871544e-05, "loss": 0.0045, "step": 208840 }, { "epoch": 50.16, "learning_rate": 5.356858662411435e-05, "loss": 0.0079, "step": 208850 }, { "epoch": 50.16, "learning_rate": 5.3565006197964654e-05, "loss": 0.0089, "step": 208860 }, { "epoch": 50.16, "learning_rate": 5.3561425753440855e-05, "loss": 0.0051, "step": 208870 }, { "epoch": 50.17, "learning_rate": 5.3557845290561446e-05, "loss": 0.0144, "step": 208880 }, { "epoch": 50.17, "learning_rate": 5.355426480934488e-05, "loss": 0.0046, "step": 208890 }, { "epoch": 50.17, "learning_rate": 5.35506843098096e-05, "loss": 0.0053, "step": 208900 }, { "epoch": 50.17, "learning_rate": 5.354710379197405e-05, "loss": 0.0035, "step": 208910 }, { "epoch": 50.18, "learning_rate": 5.3543523255856706e-05, "loss": 0.0039, "step": 208920 }, { "epoch": 50.18, "learning_rate": 5.3539942701476034e-05, "loss": 0.0036, "step": 208930 }, { "epoch": 50.18, "learning_rate": 5.353636212885045e-05, "loss": 0.0093, "step": 208940 }, { "epoch": 50.18, "learning_rate": 5.353278153799842e-05, "loss": 0.0038, "step": 208950 }, { "epoch": 50.19, "learning_rate": 5.3529200928938406e-05, "loss": 0.0108, "step": 208960 }, { "epoch": 50.19, "learning_rate": 5.352562030168887e-05, "loss": 0.0103, "step": 208970 }, { "epoch": 50.19, "learning_rate": 5.352203965626825e-05, "loss": 0.003, "step": 208980 }, { "epoch": 50.19, "learning_rate": 5.3518458992695005e-05, "loss": 0.0037, "step": 208990 }, { "epoch": 50.19, "learning_rate": 5.35148783109876e-05, "loss": 0.0172, "step": 209000 }, { "epoch": 50.2, "learning_rate": 5.35112976111645e-05, "loss": 0.0044, "step": 209010 }, { "epoch": 50.2, "learning_rate": 5.350771689324412e-05, "loss": 0.0038, "step": 209020 }, { "epoch": 50.2, "learning_rate": 5.3504136157244945e-05, "loss": 0.0062, "step": 209030 }, { "epoch": 50.2, "learning_rate": 5.350055540318542e-05, "loss": 0.0079, "step": 209040 }, { "epoch": 50.21, "learning_rate": 5.3496974631084007e-05, "loss": 0.0069, "step": 209050 }, { "epoch": 50.21, "learning_rate": 5.349339384095915e-05, "loss": 0.0041, "step": 209060 }, { "epoch": 50.21, "learning_rate": 5.34898130328293e-05, "loss": 0.0074, "step": 209070 }, { "epoch": 50.21, "learning_rate": 5.348623220671296e-05, "loss": 0.0029, "step": 209080 }, { "epoch": 50.21, "learning_rate": 5.3482651362628535e-05, "loss": 0.005, "step": 209090 }, { "epoch": 50.22, "learning_rate": 5.3479070500594485e-05, "loss": 0.0081, "step": 209100 }, { "epoch": 50.22, "learning_rate": 5.3475489620629284e-05, "loss": 0.0034, "step": 209110 }, { "epoch": 50.22, "learning_rate": 5.3471908722751375e-05, "loss": 0.0035, "step": 209120 }, { "epoch": 50.22, "learning_rate": 5.3468327806979224e-05, "loss": 0.0031, "step": 209130 }, { "epoch": 50.23, "learning_rate": 5.346474687333128e-05, "loss": 0.0081, "step": 209140 }, { "epoch": 50.23, "learning_rate": 5.346116592182602e-05, "loss": 0.0083, "step": 209150 }, { "epoch": 50.23, "learning_rate": 5.3457584952481865e-05, "loss": 0.0042, "step": 209160 }, { "epoch": 50.23, "learning_rate": 5.345400396531729e-05, "loss": 0.0039, "step": 209170 }, { "epoch": 50.24, "learning_rate": 5.345042296035074e-05, "loss": 0.0084, "step": 209180 }, { "epoch": 50.24, "learning_rate": 5.34468419376007e-05, "loss": 0.0063, "step": 209190 }, { "epoch": 50.24, "learning_rate": 5.344326089708559e-05, "loss": 0.0043, "step": 209200 }, { "epoch": 50.24, "learning_rate": 5.3439679838823895e-05, "loss": 0.0052, "step": 209210 }, { "epoch": 50.24, "learning_rate": 5.343609876283407e-05, "loss": 0.007, "step": 209220 }, { "epoch": 50.25, "learning_rate": 5.343251766913454e-05, "loss": 0.0041, "step": 209230 }, { "epoch": 50.25, "learning_rate": 5.3428936557743804e-05, "loss": 0.0206, "step": 209240 }, { "epoch": 50.25, "learning_rate": 5.3425355428680293e-05, "loss": 0.0029, "step": 209250 }, { "epoch": 50.25, "learning_rate": 5.342177428196247e-05, "loss": 0.0087, "step": 209260 }, { "epoch": 50.26, "learning_rate": 5.3418193117608794e-05, "loss": 0.0062, "step": 209270 }, { "epoch": 50.26, "learning_rate": 5.341461193563773e-05, "loss": 0.0057, "step": 209280 }, { "epoch": 50.26, "learning_rate": 5.3411030736067724e-05, "loss": 0.0039, "step": 209290 }, { "epoch": 50.26, "learning_rate": 5.340744951891723e-05, "loss": 0.0069, "step": 209300 }, { "epoch": 50.27, "learning_rate": 5.340386828420472e-05, "loss": 0.0043, "step": 209310 }, { "epoch": 50.27, "learning_rate": 5.3400287031948635e-05, "loss": 0.0041, "step": 209320 }, { "epoch": 50.27, "learning_rate": 5.339670576216745e-05, "loss": 0.0037, "step": 209330 }, { "epoch": 50.27, "learning_rate": 5.339312447487962e-05, "loss": 0.0041, "step": 209340 }, { "epoch": 50.27, "learning_rate": 5.3389543170103595e-05, "loss": 0.0054, "step": 209350 }, { "epoch": 50.28, "learning_rate": 5.338596184785782e-05, "loss": 0.0073, "step": 209360 }, { "epoch": 50.28, "learning_rate": 5.338238050816079e-05, "loss": 0.0108, "step": 209370 }, { "epoch": 50.28, "learning_rate": 5.337879915103094e-05, "loss": 0.0033, "step": 209380 }, { "epoch": 50.28, "learning_rate": 5.337521777648672e-05, "loss": 0.0047, "step": 209390 }, { "epoch": 50.29, "learning_rate": 5.337163638454661e-05, "loss": 0.0035, "step": 209400 }, { "epoch": 50.29, "learning_rate": 5.3368054975229055e-05, "loss": 0.0045, "step": 209410 }, { "epoch": 50.29, "learning_rate": 5.336447354855251e-05, "loss": 0.0058, "step": 209420 }, { "epoch": 50.29, "learning_rate": 5.3360892104535444e-05, "loss": 0.0048, "step": 209430 }, { "epoch": 50.29, "learning_rate": 5.3357310643196324e-05, "loss": 0.0063, "step": 209440 }, { "epoch": 50.3, "learning_rate": 5.335372916455359e-05, "loss": 0.009, "step": 209450 }, { "epoch": 50.3, "learning_rate": 5.33501476686257e-05, "loss": 0.011, "step": 209460 }, { "epoch": 50.3, "learning_rate": 5.3346566155431124e-05, "loss": 0.0031, "step": 209470 }, { "epoch": 50.3, "learning_rate": 5.3342984624988326e-05, "loss": 0.0061, "step": 209480 }, { "epoch": 50.31, "learning_rate": 5.333940307731574e-05, "loss": 0.0073, "step": 209490 }, { "epoch": 50.31, "learning_rate": 5.333582151243186e-05, "loss": 0.0059, "step": 209500 }, { "epoch": 50.31, "learning_rate": 5.333223993035512e-05, "loss": 0.0118, "step": 209510 }, { "epoch": 50.31, "learning_rate": 5.332865833110399e-05, "loss": 0.0082, "step": 209520 }, { "epoch": 50.32, "learning_rate": 5.332507671469692e-05, "loss": 0.0071, "step": 209530 }, { "epoch": 50.32, "learning_rate": 5.3321495081152384e-05, "loss": 0.0042, "step": 209540 }, { "epoch": 50.32, "learning_rate": 5.331791343048883e-05, "loss": 0.0066, "step": 209550 }, { "epoch": 50.32, "learning_rate": 5.3314331762724726e-05, "loss": 0.0102, "step": 209560 }, { "epoch": 50.32, "learning_rate": 5.331075007787852e-05, "loss": 0.0052, "step": 209570 }, { "epoch": 50.33, "learning_rate": 5.330716837596871e-05, "loss": 0.005, "step": 209580 }, { "epoch": 50.33, "learning_rate": 5.330358665701371e-05, "loss": 0.0155, "step": 209590 }, { "epoch": 50.33, "learning_rate": 5.3300004921031974e-05, "loss": 0.0039, "step": 209600 }, { "epoch": 50.33, "learning_rate": 5.329642316804201e-05, "loss": 0.0063, "step": 209610 }, { "epoch": 50.34, "learning_rate": 5.3292841398062244e-05, "loss": 0.0039, "step": 209620 }, { "epoch": 50.34, "learning_rate": 5.328925961111115e-05, "loss": 0.0108, "step": 209630 }, { "epoch": 50.34, "learning_rate": 5.328567780720718e-05, "loss": 0.0105, "step": 209640 }, { "epoch": 50.34, "learning_rate": 5.3282095986368806e-05, "loss": 0.0051, "step": 209650 }, { "epoch": 50.35, "learning_rate": 5.327851414861448e-05, "loss": 0.0067, "step": 209660 }, { "epoch": 50.35, "learning_rate": 5.327493229396266e-05, "loss": 0.0037, "step": 209670 }, { "epoch": 50.35, "learning_rate": 5.327135042243181e-05, "loss": 0.0047, "step": 209680 }, { "epoch": 50.35, "learning_rate": 5.32677685340404e-05, "loss": 0.0068, "step": 209690 }, { "epoch": 50.35, "learning_rate": 5.326418662880688e-05, "loss": 0.0097, "step": 209700 }, { "epoch": 50.36, "learning_rate": 5.326060470674971e-05, "loss": 0.0045, "step": 209710 }, { "epoch": 50.36, "learning_rate": 5.325702276788736e-05, "loss": 0.0045, "step": 209720 }, { "epoch": 50.36, "learning_rate": 5.32534408122383e-05, "loss": 0.0031, "step": 209730 }, { "epoch": 50.36, "learning_rate": 5.324985883982097e-05, "loss": 0.0055, "step": 209740 }, { "epoch": 50.37, "learning_rate": 5.324627685065383e-05, "loss": 0.0042, "step": 209750 }, { "epoch": 50.37, "learning_rate": 5.324269484475536e-05, "loss": 0.0031, "step": 209760 }, { "epoch": 50.37, "learning_rate": 5.323911282214401e-05, "loss": 0.0069, "step": 209770 }, { "epoch": 50.37, "learning_rate": 5.323553078283825e-05, "loss": 0.0041, "step": 209780 }, { "epoch": 50.37, "learning_rate": 5.323194872685654e-05, "loss": 0.0055, "step": 209790 }, { "epoch": 50.38, "learning_rate": 5.322836665421733e-05, "loss": 0.0071, "step": 209800 }, { "epoch": 50.38, "learning_rate": 5.32247845649391e-05, "loss": 0.0123, "step": 209810 }, { "epoch": 50.38, "learning_rate": 5.32212024590403e-05, "loss": 0.0031, "step": 209820 }, { "epoch": 50.38, "learning_rate": 5.321762033653939e-05, "loss": 0.0058, "step": 209830 }, { "epoch": 50.39, "learning_rate": 5.321403819745484e-05, "loss": 0.004, "step": 209840 }, { "epoch": 50.39, "learning_rate": 5.321045604180512e-05, "loss": 0.0095, "step": 209850 }, { "epoch": 50.39, "learning_rate": 5.320687386960867e-05, "loss": 0.0059, "step": 209860 }, { "epoch": 50.39, "learning_rate": 5.320329168088398e-05, "loss": 0.0053, "step": 209870 }, { "epoch": 50.4, "learning_rate": 5.31997094756495e-05, "loss": 0.0027, "step": 209880 }, { "epoch": 50.4, "learning_rate": 5.319612725392368e-05, "loss": 0.0039, "step": 209890 }, { "epoch": 50.4, "learning_rate": 5.319254501572499e-05, "loss": 0.0059, "step": 209900 }, { "epoch": 50.4, "learning_rate": 5.31889627610719e-05, "loss": 0.0077, "step": 209910 }, { "epoch": 50.4, "learning_rate": 5.3185380489982864e-05, "loss": 0.0046, "step": 209920 }, { "epoch": 50.41, "learning_rate": 5.318179820247635e-05, "loss": 0.0076, "step": 209930 }, { "epoch": 50.41, "learning_rate": 5.317821589857085e-05, "loss": 0.0062, "step": 209940 }, { "epoch": 50.41, "learning_rate": 5.317463357828477e-05, "loss": 0.0053, "step": 209950 }, { "epoch": 50.41, "learning_rate": 5.3171051241636595e-05, "loss": 0.0056, "step": 209960 }, { "epoch": 50.42, "learning_rate": 5.316746888864481e-05, "loss": 0.008, "step": 209970 }, { "epoch": 50.42, "learning_rate": 5.316388651932786e-05, "loss": 0.0034, "step": 209980 }, { "epoch": 50.42, "learning_rate": 5.316030413370421e-05, "loss": 0.0079, "step": 209990 }, { "epoch": 50.42, "learning_rate": 5.3156721731792336e-05, "loss": 0.0056, "step": 210000 }, { "epoch": 50.43, "learning_rate": 5.315313931361069e-05, "loss": 0.0052, "step": 210010 }, { "epoch": 50.43, "learning_rate": 5.314955687917774e-05, "loss": 0.0045, "step": 210020 }, { "epoch": 50.43, "learning_rate": 5.314597442851193e-05, "loss": 0.0036, "step": 210030 }, { "epoch": 50.43, "learning_rate": 5.3142391961631765e-05, "loss": 0.0046, "step": 210040 }, { "epoch": 50.43, "learning_rate": 5.3138809478555677e-05, "loss": 0.0063, "step": 210050 }, { "epoch": 50.44, "learning_rate": 5.313522697930212e-05, "loss": 0.0062, "step": 210060 }, { "epoch": 50.44, "learning_rate": 5.31316444638896e-05, "loss": 0.0066, "step": 210070 }, { "epoch": 50.44, "learning_rate": 5.312806193233656e-05, "loss": 0.0087, "step": 210080 }, { "epoch": 50.44, "learning_rate": 5.312447938466145e-05, "loss": 0.0061, "step": 210090 }, { "epoch": 50.45, "learning_rate": 5.312089682088275e-05, "loss": 0.0083, "step": 210100 }, { "epoch": 50.45, "learning_rate": 5.3117314241018914e-05, "loss": 0.0046, "step": 210110 }, { "epoch": 50.45, "learning_rate": 5.311373164508842e-05, "loss": 0.0034, "step": 210120 }, { "epoch": 50.45, "learning_rate": 5.3110149033109724e-05, "loss": 0.0125, "step": 210130 }, { "epoch": 50.45, "learning_rate": 5.31065664051013e-05, "loss": 0.0063, "step": 210140 }, { "epoch": 50.46, "learning_rate": 5.310298376108162e-05, "loss": 0.0041, "step": 210150 }, { "epoch": 50.46, "learning_rate": 5.309940110106912e-05, "loss": 0.0093, "step": 210160 }, { "epoch": 50.46, "learning_rate": 5.3095818425082275e-05, "loss": 0.003, "step": 210170 }, { "epoch": 50.46, "learning_rate": 5.309223573313957e-05, "loss": 0.005, "step": 210180 }, { "epoch": 50.47, "learning_rate": 5.308865302525945e-05, "loss": 0.0069, "step": 210190 }, { "epoch": 50.47, "learning_rate": 5.3085070301460384e-05, "loss": 0.0107, "step": 210200 }, { "epoch": 50.47, "learning_rate": 5.3081487561760844e-05, "loss": 0.0066, "step": 210210 }, { "epoch": 50.47, "learning_rate": 5.307790480617929e-05, "loss": 0.0026, "step": 210220 }, { "epoch": 50.48, "learning_rate": 5.307432203473419e-05, "loss": 0.0047, "step": 210230 }, { "epoch": 50.48, "learning_rate": 5.307073924744401e-05, "loss": 0.0034, "step": 210240 }, { "epoch": 50.48, "learning_rate": 5.306715644432722e-05, "loss": 0.0053, "step": 210250 }, { "epoch": 50.48, "learning_rate": 5.306357362540226e-05, "loss": 0.006, "step": 210260 }, { "epoch": 50.48, "learning_rate": 5.305999079068762e-05, "loss": 0.0053, "step": 210270 }, { "epoch": 50.49, "learning_rate": 5.305640794020177e-05, "loss": 0.0052, "step": 210280 }, { "epoch": 50.49, "learning_rate": 5.3052825073963164e-05, "loss": 0.004, "step": 210290 }, { "epoch": 50.49, "learning_rate": 5.304924219199029e-05, "loss": 0.0053, "step": 210300 }, { "epoch": 50.49, "learning_rate": 5.304565929430158e-05, "loss": 0.0137, "step": 210310 }, { "epoch": 50.5, "learning_rate": 5.304207638091552e-05, "loss": 0.0074, "step": 210320 }, { "epoch": 50.5, "learning_rate": 5.303849345185057e-05, "loss": 0.005, "step": 210330 }, { "epoch": 50.5, "learning_rate": 5.303491050712519e-05, "loss": 0.0049, "step": 210340 }, { "epoch": 50.5, "learning_rate": 5.303132754675787e-05, "loss": 0.0053, "step": 210350 }, { "epoch": 50.51, "learning_rate": 5.302774457076706e-05, "loss": 0.0171, "step": 210360 }, { "epoch": 50.51, "learning_rate": 5.302416157917124e-05, "loss": 0.007, "step": 210370 }, { "epoch": 50.51, "learning_rate": 5.3020578571988845e-05, "loss": 0.008, "step": 210380 }, { "epoch": 50.51, "learning_rate": 5.3016995549238366e-05, "loss": 0.0097, "step": 210390 }, { "epoch": 50.51, "learning_rate": 5.301341251093828e-05, "loss": 0.0053, "step": 210400 }, { "epoch": 50.52, "learning_rate": 5.300982945710703e-05, "loss": 0.0052, "step": 210410 }, { "epoch": 50.52, "learning_rate": 5.300624638776309e-05, "loss": 0.0042, "step": 210420 }, { "epoch": 50.52, "learning_rate": 5.300266330292494e-05, "loss": 0.0082, "step": 210430 }, { "epoch": 50.52, "learning_rate": 5.299908020261104e-05, "loss": 0.0036, "step": 210440 }, { "epoch": 50.53, "learning_rate": 5.2995497086839854e-05, "loss": 0.0122, "step": 210450 }, { "epoch": 50.53, "learning_rate": 5.299191395562985e-05, "loss": 0.0108, "step": 210460 }, { "epoch": 50.53, "learning_rate": 5.2988330808999485e-05, "loss": 0.0049, "step": 210470 }, { "epoch": 50.53, "learning_rate": 5.2984747646967244e-05, "loss": 0.0066, "step": 210480 }, { "epoch": 50.53, "learning_rate": 5.2981164469551605e-05, "loss": 0.0057, "step": 210490 }, { "epoch": 50.54, "learning_rate": 5.2977581276771004e-05, "loss": 0.0057, "step": 210500 }, { "epoch": 50.54, "learning_rate": 5.2973998068643935e-05, "loss": 0.0077, "step": 210510 }, { "epoch": 50.54, "learning_rate": 5.297041484518884e-05, "loss": 0.0128, "step": 210520 }, { "epoch": 50.54, "learning_rate": 5.296683160642421e-05, "loss": 0.0063, "step": 210530 }, { "epoch": 50.55, "learning_rate": 5.296324835236851e-05, "loss": 0.006, "step": 210540 }, { "epoch": 50.55, "learning_rate": 5.295966508304019e-05, "loss": 0.0057, "step": 210550 }, { "epoch": 50.55, "learning_rate": 5.295608179845774e-05, "loss": 0.0043, "step": 210560 }, { "epoch": 50.55, "learning_rate": 5.295249849863962e-05, "loss": 0.0068, "step": 210570 }, { "epoch": 50.56, "learning_rate": 5.2948915183604296e-05, "loss": 0.0084, "step": 210580 }, { "epoch": 50.56, "learning_rate": 5.294533185337024e-05, "loss": 0.0082, "step": 210590 }, { "epoch": 50.56, "learning_rate": 5.2941748507955914e-05, "loss": 0.0096, "step": 210600 }, { "epoch": 50.56, "learning_rate": 5.29381651473798e-05, "loss": 0.0041, "step": 210610 }, { "epoch": 50.56, "learning_rate": 5.293458177166035e-05, "loss": 0.0049, "step": 210620 }, { "epoch": 50.57, "learning_rate": 5.2930998380816045e-05, "loss": 0.0057, "step": 210630 }, { "epoch": 50.57, "learning_rate": 5.292741497486535e-05, "loss": 0.0095, "step": 210640 }, { "epoch": 50.57, "learning_rate": 5.292383155382673e-05, "loss": 0.0038, "step": 210650 }, { "epoch": 50.57, "learning_rate": 5.2920248117718674e-05, "loss": 0.0082, "step": 210660 }, { "epoch": 50.58, "learning_rate": 5.2916664666559624e-05, "loss": 0.0058, "step": 210670 }, { "epoch": 50.58, "learning_rate": 5.291308120036805e-05, "loss": 0.0291, "step": 210680 }, { "epoch": 50.58, "learning_rate": 5.2909497719162445e-05, "loss": 0.0149, "step": 210690 }, { "epoch": 50.58, "learning_rate": 5.290591422296126e-05, "loss": 0.0083, "step": 210700 }, { "epoch": 50.59, "learning_rate": 5.290233071178297e-05, "loss": 0.0086, "step": 210710 }, { "epoch": 50.59, "learning_rate": 5.289874718564604e-05, "loss": 0.015, "step": 210720 }, { "epoch": 50.59, "learning_rate": 5.2895163644568946e-05, "loss": 0.0077, "step": 210730 }, { "epoch": 50.59, "learning_rate": 5.289158008857015e-05, "loss": 0.0066, "step": 210740 }, { "epoch": 50.59, "learning_rate": 5.2887996517668124e-05, "loss": 0.0045, "step": 210750 }, { "epoch": 50.6, "learning_rate": 5.2884412931881346e-05, "loss": 0.0065, "step": 210760 }, { "epoch": 50.6, "learning_rate": 5.288082933122828e-05, "loss": 0.0082, "step": 210770 }, { "epoch": 50.6, "learning_rate": 5.287724571572738e-05, "loss": 0.0074, "step": 210780 }, { "epoch": 50.6, "learning_rate": 5.287366208539715e-05, "loss": 0.0059, "step": 210790 }, { "epoch": 50.61, "learning_rate": 5.287007844025604e-05, "loss": 0.0094, "step": 210800 }, { "epoch": 50.61, "learning_rate": 5.2866494780322526e-05, "loss": 0.0078, "step": 210810 }, { "epoch": 50.61, "learning_rate": 5.286291110561506e-05, "loss": 0.011, "step": 210820 }, { "epoch": 50.61, "learning_rate": 5.2859327416152137e-05, "loss": 0.009, "step": 210830 }, { "epoch": 50.61, "learning_rate": 5.285574371195221e-05, "loss": 0.0061, "step": 210840 }, { "epoch": 50.62, "learning_rate": 5.2852159993033756e-05, "loss": 0.0096, "step": 210850 }, { "epoch": 50.62, "learning_rate": 5.284857625941525e-05, "loss": 0.0072, "step": 210860 }, { "epoch": 50.62, "learning_rate": 5.2844992511115155e-05, "loss": 0.0107, "step": 210870 }, { "epoch": 50.62, "learning_rate": 5.284140874815194e-05, "loss": 0.0042, "step": 210880 }, { "epoch": 50.63, "learning_rate": 5.283782497054409e-05, "loss": 0.0096, "step": 210890 }, { "epoch": 50.63, "learning_rate": 5.283424117831006e-05, "loss": 0.0038, "step": 210900 }, { "epoch": 50.63, "learning_rate": 5.283065737146833e-05, "loss": 0.0308, "step": 210910 }, { "epoch": 50.63, "learning_rate": 5.2827073550037365e-05, "loss": 0.0038, "step": 210920 }, { "epoch": 50.64, "learning_rate": 5.2823489714035645e-05, "loss": 0.0073, "step": 210930 }, { "epoch": 50.64, "learning_rate": 5.2819905863481635e-05, "loss": 0.0054, "step": 210940 }, { "epoch": 50.64, "learning_rate": 5.28163219983938e-05, "loss": 0.007, "step": 210950 }, { "epoch": 50.64, "learning_rate": 5.2812738118790625e-05, "loss": 0.0047, "step": 210960 }, { "epoch": 50.64, "learning_rate": 5.280915422469057e-05, "loss": 0.0136, "step": 210970 }, { "epoch": 50.65, "learning_rate": 5.280557031611212e-05, "loss": 0.006, "step": 210980 }, { "epoch": 50.65, "learning_rate": 5.280198639307372e-05, "loss": 0.0143, "step": 210990 }, { "epoch": 50.65, "learning_rate": 5.279840245559387e-05, "loss": 0.0061, "step": 211000 }, { "epoch": 50.65, "learning_rate": 5.279481850369102e-05, "loss": 0.0088, "step": 211010 }, { "epoch": 50.66, "learning_rate": 5.279123453738367e-05, "loss": 0.0143, "step": 211020 }, { "epoch": 50.66, "learning_rate": 5.278765055669026e-05, "loss": 0.0058, "step": 211030 }, { "epoch": 50.66, "learning_rate": 5.278406656162928e-05, "loss": 0.0056, "step": 211040 }, { "epoch": 50.66, "learning_rate": 5.2780482552219204e-05, "loss": 0.0071, "step": 211050 }, { "epoch": 50.66, "learning_rate": 5.277689852847848e-05, "loss": 0.0086, "step": 211060 }, { "epoch": 50.67, "learning_rate": 5.277331449042561e-05, "loss": 0.0075, "step": 211070 }, { "epoch": 50.67, "learning_rate": 5.2769730438079056e-05, "loss": 0.0046, "step": 211080 }, { "epoch": 50.67, "learning_rate": 5.2766146371457295e-05, "loss": 0.0116, "step": 211090 }, { "epoch": 50.67, "learning_rate": 5.276256229057878e-05, "loss": 0.0137, "step": 211100 }, { "epoch": 50.68, "learning_rate": 5.2758978195461994e-05, "loss": 0.0103, "step": 211110 }, { "epoch": 50.68, "learning_rate": 5.275539408612542e-05, "loss": 0.0096, "step": 211120 }, { "epoch": 50.68, "learning_rate": 5.2751809962587516e-05, "loss": 0.0089, "step": 211130 }, { "epoch": 50.68, "learning_rate": 5.274822582486676e-05, "loss": 0.0093, "step": 211140 }, { "epoch": 50.69, "learning_rate": 5.274464167298163e-05, "loss": 0.0121, "step": 211150 }, { "epoch": 50.69, "learning_rate": 5.2741057506950586e-05, "loss": 0.0098, "step": 211160 }, { "epoch": 50.69, "learning_rate": 5.273747332679211e-05, "loss": 0.0069, "step": 211170 }, { "epoch": 50.69, "learning_rate": 5.2733889132524684e-05, "loss": 0.0073, "step": 211180 }, { "epoch": 50.69, "learning_rate": 5.273030492416676e-05, "loss": 0.013, "step": 211190 }, { "epoch": 50.7, "learning_rate": 5.272672070173682e-05, "loss": 0.0053, "step": 211200 }, { "epoch": 50.7, "learning_rate": 5.272313646525335e-05, "loss": 0.0084, "step": 211210 }, { "epoch": 50.7, "learning_rate": 5.27195522147348e-05, "loss": 0.0095, "step": 211220 }, { "epoch": 50.7, "learning_rate": 5.2715967950199674e-05, "loss": 0.0068, "step": 211230 }, { "epoch": 50.71, "learning_rate": 5.271238367166641e-05, "loss": 0.0052, "step": 211240 }, { "epoch": 50.71, "learning_rate": 5.2708799379153506e-05, "loss": 0.0078, "step": 211250 }, { "epoch": 50.71, "learning_rate": 5.2705215072679424e-05, "loss": 0.0042, "step": 211260 }, { "epoch": 50.71, "learning_rate": 5.270163075226263e-05, "loss": 0.0079, "step": 211270 }, { "epoch": 50.72, "learning_rate": 5.269804641792162e-05, "loss": 0.0071, "step": 211280 }, { "epoch": 50.72, "learning_rate": 5.2694462069674854e-05, "loss": 0.0044, "step": 211290 }, { "epoch": 50.72, "learning_rate": 5.269087770754082e-05, "loss": 0.0078, "step": 211300 }, { "epoch": 50.72, "learning_rate": 5.268729333153796e-05, "loss": 0.0076, "step": 211310 }, { "epoch": 50.72, "learning_rate": 5.268370894168477e-05, "loss": 0.0072, "step": 211320 }, { "epoch": 50.73, "learning_rate": 5.268012453799973e-05, "loss": 0.007, "step": 211330 }, { "epoch": 50.73, "learning_rate": 5.2676540120501305e-05, "loss": 0.0054, "step": 211340 }, { "epoch": 50.73, "learning_rate": 5.267295568920797e-05, "loss": 0.0076, "step": 211350 }, { "epoch": 50.73, "learning_rate": 5.266937124413819e-05, "loss": 0.0067, "step": 211360 }, { "epoch": 50.74, "learning_rate": 5.266578678531046e-05, "loss": 0.0037, "step": 211370 }, { "epoch": 50.74, "learning_rate": 5.266220231274325e-05, "loss": 0.0058, "step": 211380 }, { "epoch": 50.74, "learning_rate": 5.265861782645502e-05, "loss": 0.004, "step": 211390 }, { "epoch": 50.74, "learning_rate": 5.2655033326464245e-05, "loss": 0.0054, "step": 211400 }, { "epoch": 50.74, "learning_rate": 5.26514488127894e-05, "loss": 0.0045, "step": 211410 }, { "epoch": 50.75, "learning_rate": 5.264786428544897e-05, "loss": 0.0042, "step": 211420 }, { "epoch": 50.75, "learning_rate": 5.2644279744461434e-05, "loss": 0.0037, "step": 211430 }, { "epoch": 50.75, "learning_rate": 5.264069518984525e-05, "loss": 0.0062, "step": 211440 }, { "epoch": 50.75, "learning_rate": 5.263711062161891e-05, "loss": 0.0051, "step": 211450 }, { "epoch": 50.76, "learning_rate": 5.263352603980087e-05, "loss": 0.006, "step": 211460 }, { "epoch": 50.76, "learning_rate": 5.262994144440961e-05, "loss": 0.0064, "step": 211470 }, { "epoch": 50.76, "learning_rate": 5.262635683546362e-05, "loss": 0.0187, "step": 211480 }, { "epoch": 50.76, "learning_rate": 5.262277221298136e-05, "loss": 0.0077, "step": 211490 }, { "epoch": 50.77, "learning_rate": 5.261918757698131e-05, "loss": 0.004, "step": 211500 }, { "epoch": 50.77, "learning_rate": 5.261560292748196e-05, "loss": 0.0045, "step": 211510 }, { "epoch": 50.77, "learning_rate": 5.261201826450176e-05, "loss": 0.0091, "step": 211520 }, { "epoch": 50.77, "learning_rate": 5.260843358805919e-05, "loss": 0.0094, "step": 211530 }, { "epoch": 50.77, "learning_rate": 5.2604848898172744e-05, "loss": 0.0075, "step": 211540 }, { "epoch": 50.78, "learning_rate": 5.260126419486088e-05, "loss": 0.0064, "step": 211550 }, { "epoch": 50.78, "learning_rate": 5.259767947814207e-05, "loss": 0.0104, "step": 211560 }, { "epoch": 50.78, "learning_rate": 5.259409474803481e-05, "loss": 0.0055, "step": 211570 }, { "epoch": 50.78, "learning_rate": 5.259051000455755e-05, "loss": 0.0206, "step": 211580 }, { "epoch": 50.79, "learning_rate": 5.2586925247728803e-05, "loss": 0.0063, "step": 211590 }, { "epoch": 50.79, "learning_rate": 5.2583340477567e-05, "loss": 0.0059, "step": 211600 }, { "epoch": 50.79, "learning_rate": 5.257975569409065e-05, "loss": 0.0052, "step": 211610 }, { "epoch": 50.79, "learning_rate": 5.257617089731821e-05, "loss": 0.0038, "step": 211620 }, { "epoch": 50.8, "learning_rate": 5.257258608726816e-05, "loss": 0.0066, "step": 211630 }, { "epoch": 50.8, "learning_rate": 5.256900126395898e-05, "loss": 0.0053, "step": 211640 }, { "epoch": 50.8, "learning_rate": 5.256541642740915e-05, "loss": 0.0049, "step": 211650 }, { "epoch": 50.8, "learning_rate": 5.256183157763717e-05, "loss": 0.0086, "step": 211660 }, { "epoch": 50.8, "learning_rate": 5.255824671466145e-05, "loss": 0.006, "step": 211670 }, { "epoch": 50.81, "learning_rate": 5.255466183850052e-05, "loss": 0.0113, "step": 211680 }, { "epoch": 50.81, "learning_rate": 5.255107694917284e-05, "loss": 0.0054, "step": 211690 }, { "epoch": 50.81, "learning_rate": 5.254749204669689e-05, "loss": 0.0073, "step": 211700 }, { "epoch": 50.81, "learning_rate": 5.254390713109114e-05, "loss": 0.0064, "step": 211710 }, { "epoch": 50.82, "learning_rate": 5.254032220237407e-05, "loss": 0.0375, "step": 211720 }, { "epoch": 50.82, "learning_rate": 5.2536737260564176e-05, "loss": 0.0075, "step": 211730 }, { "epoch": 50.82, "learning_rate": 5.25331523056799e-05, "loss": 0.0043, "step": 211740 }, { "epoch": 50.82, "learning_rate": 5.252956733773974e-05, "loss": 0.0056, "step": 211750 }, { "epoch": 50.82, "learning_rate": 5.252598235676217e-05, "loss": 0.0081, "step": 211760 }, { "epoch": 50.83, "learning_rate": 5.252239736276566e-05, "loss": 0.0096, "step": 211770 }, { "epoch": 50.83, "learning_rate": 5.25188123557687e-05, "loss": 0.0059, "step": 211780 }, { "epoch": 50.83, "learning_rate": 5.251522733578974e-05, "loss": 0.0042, "step": 211790 }, { "epoch": 50.83, "learning_rate": 5.2511642302847295e-05, "loss": 0.006, "step": 211800 }, { "epoch": 50.84, "learning_rate": 5.250805725695984e-05, "loss": 0.0111, "step": 211810 }, { "epoch": 50.84, "learning_rate": 5.2504472198145816e-05, "loss": 0.0147, "step": 211820 }, { "epoch": 50.84, "learning_rate": 5.250088712642373e-05, "loss": 0.0045, "step": 211830 }, { "epoch": 50.84, "learning_rate": 5.249730204181205e-05, "loss": 0.011, "step": 211840 }, { "epoch": 50.85, "learning_rate": 5.249371694432924e-05, "loss": 0.0078, "step": 211850 }, { "epoch": 50.85, "learning_rate": 5.24901318339938e-05, "loss": 0.004, "step": 211860 }, { "epoch": 50.85, "learning_rate": 5.24865467108242e-05, "loss": 0.005, "step": 211870 }, { "epoch": 50.85, "learning_rate": 5.248296157483894e-05, "loss": 0.0043, "step": 211880 }, { "epoch": 50.85, "learning_rate": 5.2479376426056446e-05, "loss": 0.0037, "step": 211890 }, { "epoch": 50.86, "learning_rate": 5.2475791264495245e-05, "loss": 0.0052, "step": 211900 }, { "epoch": 50.86, "learning_rate": 5.2472206090173784e-05, "loss": 0.0092, "step": 211910 }, { "epoch": 50.86, "learning_rate": 5.246862090311054e-05, "loss": 0.0034, "step": 211920 }, { "epoch": 50.86, "learning_rate": 5.2465035703324025e-05, "loss": 0.0062, "step": 211930 }, { "epoch": 50.87, "learning_rate": 5.246145049083268e-05, "loss": 0.0051, "step": 211940 }, { "epoch": 50.87, "learning_rate": 5.245786526565501e-05, "loss": 0.0094, "step": 211950 }, { "epoch": 50.87, "learning_rate": 5.2454280027809476e-05, "loss": 0.0048, "step": 211960 }, { "epoch": 50.87, "learning_rate": 5.2450694777314566e-05, "loss": 0.0067, "step": 211970 }, { "epoch": 50.88, "learning_rate": 5.2447109514188755e-05, "loss": 0.0038, "step": 211980 }, { "epoch": 50.88, "learning_rate": 5.2443524238450514e-05, "loss": 0.004, "step": 211990 }, { "epoch": 50.88, "learning_rate": 5.243993895011833e-05, "loss": 0.0047, "step": 212000 }, { "epoch": 50.88, "learning_rate": 5.2436353649210676e-05, "loss": 0.0135, "step": 212010 }, { "epoch": 50.88, "learning_rate": 5.243276833574606e-05, "loss": 0.008, "step": 212020 }, { "epoch": 50.89, "learning_rate": 5.242918300974291e-05, "loss": 0.0047, "step": 212030 }, { "epoch": 50.89, "learning_rate": 5.242559767121974e-05, "loss": 0.0066, "step": 212040 }, { "epoch": 50.89, "learning_rate": 5.242201232019502e-05, "loss": 0.013, "step": 212050 }, { "epoch": 50.89, "learning_rate": 5.241842695668723e-05, "loss": 0.0049, "step": 212060 }, { "epoch": 50.9, "learning_rate": 5.2414841580714835e-05, "loss": 0.0059, "step": 212070 }, { "epoch": 50.9, "learning_rate": 5.241125619229633e-05, "loss": 0.005, "step": 212080 }, { "epoch": 50.9, "learning_rate": 5.2407670791450206e-05, "loss": 0.0036, "step": 212090 }, { "epoch": 50.9, "learning_rate": 5.240408537819491e-05, "loss": 0.0066, "step": 212100 }, { "epoch": 50.9, "learning_rate": 5.2400499952548944e-05, "loss": 0.0071, "step": 212110 }, { "epoch": 50.91, "learning_rate": 5.239691451453078e-05, "loss": 0.0084, "step": 212120 }, { "epoch": 50.91, "learning_rate": 5.2393329064158895e-05, "loss": 0.0089, "step": 212130 }, { "epoch": 50.91, "learning_rate": 5.238974360145178e-05, "loss": 0.0044, "step": 212140 }, { "epoch": 50.91, "learning_rate": 5.2386158126427896e-05, "loss": 0.0055, "step": 212150 }, { "epoch": 50.92, "learning_rate": 5.238257263910575e-05, "loss": 0.0063, "step": 212160 }, { "epoch": 50.92, "learning_rate": 5.23789871395038e-05, "loss": 0.0047, "step": 212170 }, { "epoch": 50.92, "learning_rate": 5.237540162764052e-05, "loss": 0.013, "step": 212180 }, { "epoch": 50.92, "learning_rate": 5.23718161035344e-05, "loss": 0.0041, "step": 212190 }, { "epoch": 50.93, "learning_rate": 5.2368230567203924e-05, "loss": 0.0089, "step": 212200 }, { "epoch": 50.93, "learning_rate": 5.236464501866757e-05, "loss": 0.0061, "step": 212210 }, { "epoch": 50.93, "learning_rate": 5.236105945794382e-05, "loss": 0.0094, "step": 212220 }, { "epoch": 50.93, "learning_rate": 5.2357473885051134e-05, "loss": 0.008, "step": 212230 }, { "epoch": 50.93, "learning_rate": 5.2353888300008025e-05, "loss": 0.0048, "step": 212240 }, { "epoch": 50.94, "learning_rate": 5.2350302702832945e-05, "loss": 0.0039, "step": 212250 }, { "epoch": 50.94, "learning_rate": 5.2346717093544385e-05, "loss": 0.0093, "step": 212260 }, { "epoch": 50.94, "learning_rate": 5.234313147216083e-05, "loss": 0.0056, "step": 212270 }, { "epoch": 50.94, "learning_rate": 5.233954583870075e-05, "loss": 0.0083, "step": 212280 }, { "epoch": 50.95, "learning_rate": 5.233596019318264e-05, "loss": 0.006, "step": 212290 }, { "epoch": 50.95, "learning_rate": 5.233237453562497e-05, "loss": 0.0275, "step": 212300 }, { "epoch": 50.95, "learning_rate": 5.232878886604623e-05, "loss": 0.0085, "step": 212310 }, { "epoch": 51.0, "learning_rate": 5.232520318446489e-05, "loss": 0.0032, "step": 212320 }, { "epoch": 51.0, "learning_rate": 5.232161749089942e-05, "loss": 0.0042, "step": 212330 }, { "epoch": 51.01, "learning_rate": 5.2318031785368326e-05, "loss": 0.0089, "step": 212340 }, { "epoch": 51.01, "learning_rate": 5.2314446067890064e-05, "loss": 0.0046, "step": 212350 }, { "epoch": 51.01, "learning_rate": 5.231086033848314e-05, "loss": 0.0068, "step": 212360 }, { "epoch": 51.01, "learning_rate": 5.230727459716601e-05, "loss": 0.0128, "step": 212370 }, { "epoch": 51.02, "learning_rate": 5.230368884395718e-05, "loss": 0.0041, "step": 212380 }, { "epoch": 51.02, "learning_rate": 5.2300103078875104e-05, "loss": 0.0058, "step": 212390 }, { "epoch": 51.02, "learning_rate": 5.2296517301938294e-05, "loss": 0.0038, "step": 212400 }, { "epoch": 51.02, "learning_rate": 5.229293151316521e-05, "loss": 0.0049, "step": 212410 }, { "epoch": 51.02, "learning_rate": 5.228934571257433e-05, "loss": 0.0073, "step": 212420 }, { "epoch": 51.03, "learning_rate": 5.228575990018415e-05, "loss": 0.0044, "step": 212430 }, { "epoch": 51.03, "learning_rate": 5.2282174076013144e-05, "loss": 0.0063, "step": 212440 }, { "epoch": 51.03, "learning_rate": 5.2278588240079805e-05, "loss": 0.0049, "step": 212450 }, { "epoch": 51.03, "learning_rate": 5.2275002392402584e-05, "loss": 0.0042, "step": 212460 }, { "epoch": 51.04, "learning_rate": 5.2271416532999994e-05, "loss": 0.0037, "step": 212470 }, { "epoch": 51.04, "learning_rate": 5.2267830661890495e-05, "loss": 0.0066, "step": 212480 }, { "epoch": 51.04, "learning_rate": 5.226424477909258e-05, "loss": 0.0057, "step": 212490 }, { "epoch": 51.04, "learning_rate": 5.226065888462473e-05, "loss": 0.0061, "step": 212500 }, { "epoch": 51.05, "learning_rate": 5.2257072978505425e-05, "loss": 0.0064, "step": 212510 }, { "epoch": 51.05, "learning_rate": 5.225348706075315e-05, "loss": 0.0038, "step": 212520 }, { "epoch": 51.05, "learning_rate": 5.224990113138638e-05, "loss": 0.0109, "step": 212530 }, { "epoch": 51.05, "learning_rate": 5.22463151904236e-05, "loss": 0.0074, "step": 212540 }, { "epoch": 51.05, "learning_rate": 5.2242729237883294e-05, "loss": 0.0055, "step": 212550 }, { "epoch": 51.06, "learning_rate": 5.223914327378394e-05, "loss": 0.0045, "step": 212560 }, { "epoch": 51.06, "learning_rate": 5.2235557298144024e-05, "loss": 0.0138, "step": 212570 }, { "epoch": 51.06, "learning_rate": 5.223197131098203e-05, "loss": 0.0119, "step": 212580 }, { "epoch": 51.06, "learning_rate": 5.222838531231644e-05, "loss": 0.0035, "step": 212590 }, { "epoch": 51.07, "learning_rate": 5.222479930216574e-05, "loss": 0.0037, "step": 212600 }, { "epoch": 51.07, "learning_rate": 5.222121328054839e-05, "loss": 0.0035, "step": 212610 }, { "epoch": 51.07, "learning_rate": 5.2217627247482895e-05, "loss": 0.0041, "step": 212620 }, { "epoch": 51.07, "learning_rate": 5.221404120298773e-05, "loss": 0.0042, "step": 212630 }, { "epoch": 51.07, "learning_rate": 5.221045514708137e-05, "loss": 0.0038, "step": 212640 }, { "epoch": 51.08, "learning_rate": 5.2206869079782316e-05, "loss": 0.007, "step": 212650 }, { "epoch": 51.08, "learning_rate": 5.220328300110904e-05, "loss": 0.0052, "step": 212660 }, { "epoch": 51.08, "learning_rate": 5.219969691108002e-05, "loss": 0.0048, "step": 212670 }, { "epoch": 51.08, "learning_rate": 5.219611080971375e-05, "loss": 0.0072, "step": 212680 }, { "epoch": 51.09, "learning_rate": 5.21925246970287e-05, "loss": 0.0079, "step": 212690 }, { "epoch": 51.09, "learning_rate": 5.218893857304336e-05, "loss": 0.0055, "step": 212700 }, { "epoch": 51.09, "learning_rate": 5.218535243777621e-05, "loss": 0.0048, "step": 212710 }, { "epoch": 51.09, "learning_rate": 5.218176629124575e-05, "loss": 0.0056, "step": 212720 }, { "epoch": 51.1, "learning_rate": 5.217818013347043e-05, "loss": 0.0059, "step": 212730 }, { "epoch": 51.1, "learning_rate": 5.217459396446877e-05, "loss": 0.0052, "step": 212740 }, { "epoch": 51.1, "learning_rate": 5.217100778425923e-05, "loss": 0.0047, "step": 212750 }, { "epoch": 51.1, "learning_rate": 5.216742159286029e-05, "loss": 0.0046, "step": 212760 }, { "epoch": 51.1, "learning_rate": 5.216383539029044e-05, "loss": 0.0034, "step": 212770 }, { "epoch": 51.11, "learning_rate": 5.216024917656817e-05, "loss": 0.0058, "step": 212780 }, { "epoch": 51.11, "learning_rate": 5.2156662951711946e-05, "loss": 0.0041, "step": 212790 }, { "epoch": 51.11, "learning_rate": 5.215307671574027e-05, "loss": 0.0041, "step": 212800 }, { "epoch": 51.11, "learning_rate": 5.2149490468671636e-05, "loss": 0.0038, "step": 212810 }, { "epoch": 51.12, "learning_rate": 5.2145904210524485e-05, "loss": 0.0071, "step": 212820 }, { "epoch": 51.12, "learning_rate": 5.2142317941317334e-05, "loss": 0.008, "step": 212830 }, { "epoch": 51.12, "learning_rate": 5.2138731661068653e-05, "loss": 0.0058, "step": 212840 }, { "epoch": 51.12, "learning_rate": 5.2135145369796944e-05, "loss": 0.0071, "step": 212850 }, { "epoch": 51.12, "learning_rate": 5.2131559067520664e-05, "loss": 0.0068, "step": 212860 }, { "epoch": 51.13, "learning_rate": 5.2127972754258326e-05, "loss": 0.0031, "step": 212870 }, { "epoch": 51.13, "learning_rate": 5.2124386430028395e-05, "loss": 0.0061, "step": 212880 }, { "epoch": 51.13, "learning_rate": 5.212080009484935e-05, "loss": 0.0033, "step": 212890 }, { "epoch": 51.13, "learning_rate": 5.211721374873969e-05, "loss": 0.0048, "step": 212900 }, { "epoch": 51.14, "learning_rate": 5.211362739171789e-05, "loss": 0.0045, "step": 212910 }, { "epoch": 51.14, "learning_rate": 5.211004102380244e-05, "loss": 0.0026, "step": 212920 }, { "epoch": 51.14, "learning_rate": 5.2106454645011816e-05, "loss": 0.0049, "step": 212930 }, { "epoch": 51.14, "learning_rate": 5.2102868255364514e-05, "loss": 0.0035, "step": 212940 }, { "epoch": 51.15, "learning_rate": 5.209928185487901e-05, "loss": 0.0042, "step": 212950 }, { "epoch": 51.15, "learning_rate": 5.209569544357379e-05, "loss": 0.0034, "step": 212960 }, { "epoch": 51.15, "learning_rate": 5.209210902146734e-05, "loss": 0.0066, "step": 212970 }, { "epoch": 51.15, "learning_rate": 5.208852258857814e-05, "loss": 0.0061, "step": 212980 }, { "epoch": 51.15, "learning_rate": 5.208493614492466e-05, "loss": 0.0064, "step": 212990 }, { "epoch": 51.16, "learning_rate": 5.2081349690525416e-05, "loss": 0.0041, "step": 213000 }, { "epoch": 51.16, "learning_rate": 5.207776322539888e-05, "loss": 0.0032, "step": 213010 }, { "epoch": 51.16, "learning_rate": 5.207417674956353e-05, "loss": 0.0066, "step": 213020 }, { "epoch": 51.16, "learning_rate": 5.2070590263037864e-05, "loss": 0.0093, "step": 213030 }, { "epoch": 51.17, "learning_rate": 5.206700376584036e-05, "loss": 0.0068, "step": 213040 }, { "epoch": 51.17, "learning_rate": 5.206341725798949e-05, "loss": 0.0058, "step": 213050 }, { "epoch": 51.17, "learning_rate": 5.2059830739503756e-05, "loss": 0.0063, "step": 213060 }, { "epoch": 51.17, "learning_rate": 5.205624421040164e-05, "loss": 0.0066, "step": 213070 }, { "epoch": 51.18, "learning_rate": 5.205265767070162e-05, "loss": 0.0098, "step": 213080 }, { "epoch": 51.18, "learning_rate": 5.204907112042219e-05, "loss": 0.0029, "step": 213090 }, { "epoch": 51.18, "learning_rate": 5.204548455958184e-05, "loss": 0.0076, "step": 213100 }, { "epoch": 51.18, "learning_rate": 5.204189798819903e-05, "loss": 0.0055, "step": 213110 }, { "epoch": 51.18, "learning_rate": 5.203831140629225e-05, "loss": 0.0044, "step": 213120 }, { "epoch": 51.19, "learning_rate": 5.203472481388001e-05, "loss": 0.004, "step": 213130 }, { "epoch": 51.19, "learning_rate": 5.203113821098077e-05, "loss": 0.0062, "step": 213140 }, { "epoch": 51.19, "learning_rate": 5.202755159761303e-05, "loss": 0.0066, "step": 213150 }, { "epoch": 51.19, "learning_rate": 5.202396497379528e-05, "loss": 0.0082, "step": 213160 }, { "epoch": 51.2, "learning_rate": 5.202037833954602e-05, "loss": 0.0049, "step": 213170 }, { "epoch": 51.2, "learning_rate": 5.201679169488368e-05, "loss": 0.0035, "step": 213180 }, { "epoch": 51.2, "learning_rate": 5.2013205039826783e-05, "loss": 0.0073, "step": 213190 }, { "epoch": 51.2, "learning_rate": 5.200961837439382e-05, "loss": 0.006, "step": 213200 }, { "epoch": 51.2, "learning_rate": 5.2006031698603266e-05, "loss": 0.0031, "step": 213210 }, { "epoch": 51.21, "learning_rate": 5.20024450124736e-05, "loss": 0.0111, "step": 213220 }, { "epoch": 51.21, "learning_rate": 5.199885831602332e-05, "loss": 0.0059, "step": 213230 }, { "epoch": 51.21, "learning_rate": 5.199527160927092e-05, "loss": 0.0037, "step": 213240 }, { "epoch": 51.21, "learning_rate": 5.199168489223486e-05, "loss": 0.0048, "step": 213250 }, { "epoch": 51.22, "learning_rate": 5.198809816493364e-05, "loss": 0.0034, "step": 213260 }, { "epoch": 51.22, "learning_rate": 5.198451142738574e-05, "loss": 0.0045, "step": 213270 }, { "epoch": 51.22, "learning_rate": 5.198092467960966e-05, "loss": 0.0089, "step": 213280 }, { "epoch": 51.22, "learning_rate": 5.1977337921623884e-05, "loss": 0.004, "step": 213290 }, { "epoch": 51.23, "learning_rate": 5.197375115344686e-05, "loss": 0.0043, "step": 213300 }, { "epoch": 51.23, "learning_rate": 5.1970164375097144e-05, "loss": 0.0033, "step": 213310 }, { "epoch": 51.23, "learning_rate": 5.196657758659317e-05, "loss": 0.0041, "step": 213320 }, { "epoch": 51.23, "learning_rate": 5.196299078795344e-05, "loss": 0.0038, "step": 213330 }, { "epoch": 51.23, "learning_rate": 5.195940397919643e-05, "loss": 0.01, "step": 213340 }, { "epoch": 51.24, "learning_rate": 5.195581716034065e-05, "loss": 0.0046, "step": 213350 }, { "epoch": 51.24, "learning_rate": 5.1952230331404564e-05, "loss": 0.0074, "step": 213360 }, { "epoch": 51.24, "learning_rate": 5.1948643492406656e-05, "loss": 0.0049, "step": 213370 }, { "epoch": 51.24, "learning_rate": 5.194505664336544e-05, "loss": 0.0027, "step": 213380 }, { "epoch": 51.25, "learning_rate": 5.194146978429939e-05, "loss": 0.0055, "step": 213390 }, { "epoch": 51.25, "learning_rate": 5.1937882915226974e-05, "loss": 0.0041, "step": 213400 }, { "epoch": 51.25, "learning_rate": 5.19342960361667e-05, "loss": 0.0034, "step": 213410 }, { "epoch": 51.25, "learning_rate": 5.193070914713705e-05, "loss": 0.0098, "step": 213420 }, { "epoch": 51.26, "learning_rate": 5.19271222481565e-05, "loss": 0.0044, "step": 213430 }, { "epoch": 51.26, "learning_rate": 5.1923535339243554e-05, "loss": 0.004, "step": 213440 }, { "epoch": 51.26, "learning_rate": 5.191994842041669e-05, "loss": 0.0032, "step": 213450 }, { "epoch": 51.26, "learning_rate": 5.191636149169439e-05, "loss": 0.0046, "step": 213460 }, { "epoch": 51.26, "learning_rate": 5.1912774553095145e-05, "loss": 0.0039, "step": 213470 }, { "epoch": 51.27, "learning_rate": 5.190918760463745e-05, "loss": 0.0041, "step": 213480 }, { "epoch": 51.27, "learning_rate": 5.190560064633978e-05, "loss": 0.0137, "step": 213490 }, { "epoch": 51.27, "learning_rate": 5.190201367822064e-05, "loss": 0.006, "step": 213500 }, { "epoch": 51.27, "learning_rate": 5.18984267002985e-05, "loss": 0.0062, "step": 213510 }, { "epoch": 51.28, "learning_rate": 5.189483971259185e-05, "loss": 0.0066, "step": 213520 }, { "epoch": 51.28, "learning_rate": 5.1891252715119185e-05, "loss": 0.0035, "step": 213530 }, { "epoch": 51.28, "learning_rate": 5.188766570789899e-05, "loss": 0.0061, "step": 213540 }, { "epoch": 51.28, "learning_rate": 5.1884078690949746e-05, "loss": 0.0081, "step": 213550 }, { "epoch": 51.28, "learning_rate": 5.188049166428994e-05, "loss": 0.0047, "step": 213560 }, { "epoch": 51.29, "learning_rate": 5.187690462793807e-05, "loss": 0.0077, "step": 213570 }, { "epoch": 51.29, "learning_rate": 5.1873317581912614e-05, "loss": 0.0093, "step": 213580 }, { "epoch": 51.29, "learning_rate": 5.1869730526232064e-05, "loss": 0.0037, "step": 213590 }, { "epoch": 51.29, "learning_rate": 5.186614346091491e-05, "loss": 0.0048, "step": 213600 }, { "epoch": 51.3, "learning_rate": 5.186255638597963e-05, "loss": 0.0047, "step": 213610 }, { "epoch": 51.3, "learning_rate": 5.185896930144473e-05, "loss": 0.0056, "step": 213620 }, { "epoch": 51.3, "learning_rate": 5.1855382207328684e-05, "loss": 0.0036, "step": 213630 }, { "epoch": 51.3, "learning_rate": 5.185179510364998e-05, "loss": 0.004, "step": 213640 }, { "epoch": 51.31, "learning_rate": 5.18482079904271e-05, "loss": 0.0056, "step": 213650 }, { "epoch": 51.31, "learning_rate": 5.184462086767855e-05, "loss": 0.0094, "step": 213660 }, { "epoch": 51.31, "learning_rate": 5.1841033735422815e-05, "loss": 0.0061, "step": 213670 }, { "epoch": 51.31, "learning_rate": 5.183744659367837e-05, "loss": 0.005, "step": 213680 }, { "epoch": 51.31, "learning_rate": 5.183385944246372e-05, "loss": 0.0049, "step": 213690 }, { "epoch": 51.32, "learning_rate": 5.183027228179732e-05, "loss": 0.0075, "step": 213700 }, { "epoch": 51.32, "learning_rate": 5.18266851116977e-05, "loss": 0.0044, "step": 213710 }, { "epoch": 51.32, "learning_rate": 5.182309793218332e-05, "loss": 0.0087, "step": 213720 }, { "epoch": 51.32, "learning_rate": 5.181951074327268e-05, "loss": 0.0067, "step": 213730 }, { "epoch": 51.33, "learning_rate": 5.181592354498427e-05, "loss": 0.0059, "step": 213740 }, { "epoch": 51.33, "learning_rate": 5.1812336337336574e-05, "loss": 0.0052, "step": 213750 }, { "epoch": 51.33, "learning_rate": 5.180874912034808e-05, "loss": 0.0104, "step": 213760 }, { "epoch": 51.33, "learning_rate": 5.180516189403728e-05, "loss": 0.004, "step": 213770 }, { "epoch": 51.34, "learning_rate": 5.1801574658422655e-05, "loss": 0.006, "step": 213780 }, { "epoch": 51.34, "learning_rate": 5.17979874135227e-05, "loss": 0.0065, "step": 213790 }, { "epoch": 51.34, "learning_rate": 5.1794400159355907e-05, "loss": 0.0078, "step": 213800 }, { "epoch": 51.34, "learning_rate": 5.179081289594076e-05, "loss": 0.0039, "step": 213810 }, { "epoch": 51.34, "learning_rate": 5.178722562329575e-05, "loss": 0.0112, "step": 213820 }, { "epoch": 51.35, "learning_rate": 5.178363834143937e-05, "loss": 0.0031, "step": 213830 }, { "epoch": 51.35, "learning_rate": 5.178005105039009e-05, "loss": 0.004, "step": 213840 }, { "epoch": 51.35, "learning_rate": 5.1776463750166415e-05, "loss": 0.0082, "step": 213850 }, { "epoch": 51.35, "learning_rate": 5.177287644078683e-05, "loss": 0.0042, "step": 213860 }, { "epoch": 51.36, "learning_rate": 5.1769289122269825e-05, "loss": 0.005, "step": 213870 }, { "epoch": 51.36, "learning_rate": 5.176570179463389e-05, "loss": 0.0036, "step": 213880 }, { "epoch": 51.36, "learning_rate": 5.176211445789752e-05, "loss": 0.005, "step": 213890 }, { "epoch": 51.36, "learning_rate": 5.175852711207919e-05, "loss": 0.0046, "step": 213900 }, { "epoch": 51.36, "learning_rate": 5.175493975719741e-05, "loss": 0.0039, "step": 213910 }, { "epoch": 51.37, "learning_rate": 5.175135239327064e-05, "loss": 0.0042, "step": 213920 }, { "epoch": 51.37, "learning_rate": 5.174776502031738e-05, "loss": 0.0067, "step": 213930 }, { "epoch": 51.37, "learning_rate": 5.174417763835614e-05, "loss": 0.0045, "step": 213940 }, { "epoch": 51.37, "learning_rate": 5.1740590247405385e-05, "loss": 0.0079, "step": 213950 }, { "epoch": 51.38, "learning_rate": 5.173700284748363e-05, "loss": 0.0053, "step": 213960 }, { "epoch": 51.38, "learning_rate": 5.1733415438609336e-05, "loss": 0.007, "step": 213970 }, { "epoch": 51.38, "learning_rate": 5.1729828020801e-05, "loss": 0.004, "step": 213980 }, { "epoch": 51.38, "learning_rate": 5.172624059407711e-05, "loss": 0.0076, "step": 213990 }, { "epoch": 51.39, "learning_rate": 5.172265315845618e-05, "loss": 0.0092, "step": 214000 }, { "epoch": 51.39, "learning_rate": 5.1719065713956673e-05, "loss": 0.0045, "step": 214010 }, { "epoch": 51.39, "learning_rate": 5.171547826059708e-05, "loss": 0.0056, "step": 214020 }, { "epoch": 51.39, "learning_rate": 5.1711890798395903e-05, "loss": 0.004, "step": 214030 }, { "epoch": 51.39, "learning_rate": 5.170830332737162e-05, "loss": 0.0062, "step": 214040 }, { "epoch": 51.4, "learning_rate": 5.170471584754274e-05, "loss": 0.0044, "step": 214050 }, { "epoch": 51.4, "learning_rate": 5.170112835892773e-05, "loss": 0.0067, "step": 214060 }, { "epoch": 51.4, "learning_rate": 5.169754086154509e-05, "loss": 0.0058, "step": 214070 }, { "epoch": 51.4, "learning_rate": 5.169395335541332e-05, "loss": 0.0114, "step": 214080 }, { "epoch": 51.41, "learning_rate": 5.169036584055089e-05, "loss": 0.0027, "step": 214090 }, { "epoch": 51.41, "learning_rate": 5.1686778316976325e-05, "loss": 0.0097, "step": 214100 }, { "epoch": 51.41, "learning_rate": 5.1683190784708066e-05, "loss": 0.0093, "step": 214110 }, { "epoch": 51.41, "learning_rate": 5.167960324376463e-05, "loss": 0.0037, "step": 214120 }, { "epoch": 51.42, "learning_rate": 5.1676015694164506e-05, "loss": 0.0097, "step": 214130 }, { "epoch": 51.42, "learning_rate": 5.167242813592619e-05, "loss": 0.0033, "step": 214140 }, { "epoch": 51.42, "learning_rate": 5.1668840569068154e-05, "loss": 0.0052, "step": 214150 }, { "epoch": 51.42, "learning_rate": 5.1665252993608906e-05, "loss": 0.0054, "step": 214160 }, { "epoch": 51.42, "learning_rate": 5.166166540956694e-05, "loss": 0.0045, "step": 214170 }, { "epoch": 51.43, "learning_rate": 5.165807781696071e-05, "loss": 0.0081, "step": 214180 }, { "epoch": 51.43, "learning_rate": 5.1654490215808746e-05, "loss": 0.0038, "step": 214190 }, { "epoch": 51.43, "learning_rate": 5.1650902606129536e-05, "loss": 0.0034, "step": 214200 }, { "epoch": 51.43, "learning_rate": 5.1647314987941555e-05, "loss": 0.004, "step": 214210 }, { "epoch": 51.44, "learning_rate": 5.1643727361263295e-05, "loss": 0.005, "step": 214220 }, { "epoch": 51.44, "learning_rate": 5.164013972611325e-05, "loss": 0.0069, "step": 214230 }, { "epoch": 51.44, "learning_rate": 5.1636552082509915e-05, "loss": 0.0052, "step": 214240 }, { "epoch": 51.44, "learning_rate": 5.1632964430471786e-05, "loss": 0.0078, "step": 214250 }, { "epoch": 51.44, "learning_rate": 5.1629376770017335e-05, "loss": 0.0038, "step": 214260 }, { "epoch": 51.45, "learning_rate": 5.1625789101165054e-05, "loss": 0.005, "step": 214270 }, { "epoch": 51.45, "learning_rate": 5.162220142393345e-05, "loss": 0.0029, "step": 214280 }, { "epoch": 51.45, "learning_rate": 5.1618613738341005e-05, "loss": 0.0059, "step": 214290 }, { "epoch": 51.45, "learning_rate": 5.1615026044406215e-05, "loss": 0.0085, "step": 214300 }, { "epoch": 51.46, "learning_rate": 5.1611438342147564e-05, "loss": 0.0031, "step": 214310 }, { "epoch": 51.46, "learning_rate": 5.160785063158355e-05, "loss": 0.0052, "step": 214320 }, { "epoch": 51.46, "learning_rate": 5.160426291273266e-05, "loss": 0.0039, "step": 214330 }, { "epoch": 51.46, "learning_rate": 5.160067518561338e-05, "loss": 0.0049, "step": 214340 }, { "epoch": 51.47, "learning_rate": 5.15970874502442e-05, "loss": 0.0091, "step": 214350 }, { "epoch": 51.47, "learning_rate": 5.159349970664363e-05, "loss": 0.0111, "step": 214360 }, { "epoch": 51.47, "learning_rate": 5.158991195483015e-05, "loss": 0.0111, "step": 214370 }, { "epoch": 51.47, "learning_rate": 5.158632419482224e-05, "loss": 0.0037, "step": 214380 }, { "epoch": 51.47, "learning_rate": 5.158273642663842e-05, "loss": 0.0032, "step": 214390 }, { "epoch": 51.48, "learning_rate": 5.157914865029715e-05, "loss": 0.0053, "step": 214400 }, { "epoch": 51.48, "learning_rate": 5.157556086581694e-05, "loss": 0.0036, "step": 214410 }, { "epoch": 51.48, "learning_rate": 5.1571973073216274e-05, "loss": 0.0058, "step": 214420 }, { "epoch": 51.48, "learning_rate": 5.1568385272513645e-05, "loss": 0.0043, "step": 214430 }, { "epoch": 51.49, "learning_rate": 5.156479746372754e-05, "loss": 0.0033, "step": 214440 }, { "epoch": 51.49, "learning_rate": 5.156120964687646e-05, "loss": 0.0045, "step": 214450 }, { "epoch": 51.49, "learning_rate": 5.1557621821978905e-05, "loss": 0.006, "step": 214460 }, { "epoch": 51.49, "learning_rate": 5.155403398905334e-05, "loss": 0.0069, "step": 214470 }, { "epoch": 51.5, "learning_rate": 5.155044614811827e-05, "loss": 0.0064, "step": 214480 }, { "epoch": 51.5, "learning_rate": 5.1546858299192194e-05, "loss": 0.0042, "step": 214490 }, { "epoch": 51.5, "learning_rate": 5.154327044229358e-05, "loss": 0.0055, "step": 214500 }, { "epoch": 51.5, "learning_rate": 5.153968257744095e-05, "loss": 0.0033, "step": 214510 }, { "epoch": 51.5, "learning_rate": 5.1536094704652794e-05, "loss": 0.0132, "step": 214520 }, { "epoch": 51.51, "learning_rate": 5.153250682394759e-05, "loss": 0.0142, "step": 214530 }, { "epoch": 51.51, "learning_rate": 5.1528918935343826e-05, "loss": 0.006, "step": 214540 }, { "epoch": 51.51, "learning_rate": 5.1525331038860006e-05, "loss": 0.0043, "step": 214550 }, { "epoch": 51.51, "learning_rate": 5.15217431345146e-05, "loss": 0.0077, "step": 214560 }, { "epoch": 51.52, "learning_rate": 5.151815522232614e-05, "loss": 0.0062, "step": 214570 }, { "epoch": 51.52, "learning_rate": 5.151456730231308e-05, "loss": 0.0119, "step": 214580 }, { "epoch": 51.52, "learning_rate": 5.151097937449393e-05, "loss": 0.0101, "step": 214590 }, { "epoch": 51.52, "learning_rate": 5.1507391438887184e-05, "loss": 0.0044, "step": 214600 }, { "epoch": 51.52, "learning_rate": 5.150380349551134e-05, "loss": 0.0106, "step": 214610 }, { "epoch": 51.53, "learning_rate": 5.150021554438487e-05, "loss": 0.0139, "step": 214620 }, { "epoch": 51.53, "learning_rate": 5.149662758552627e-05, "loss": 0.0041, "step": 214630 }, { "epoch": 51.53, "learning_rate": 5.149303961895404e-05, "loss": 0.0143, "step": 214640 }, { "epoch": 51.53, "learning_rate": 5.1489451644686685e-05, "loss": 0.0061, "step": 214650 }, { "epoch": 51.54, "learning_rate": 5.148586366274265e-05, "loss": 0.0073, "step": 214660 }, { "epoch": 51.54, "learning_rate": 5.148227567314049e-05, "loss": 0.0087, "step": 214670 }, { "epoch": 51.54, "learning_rate": 5.147868767589867e-05, "loss": 0.0117, "step": 214680 }, { "epoch": 51.54, "learning_rate": 5.147509967103568e-05, "loss": 0.0104, "step": 214690 }, { "epoch": 51.55, "learning_rate": 5.147151165857001e-05, "loss": 0.0042, "step": 214700 }, { "epoch": 51.55, "learning_rate": 5.146792363852015e-05, "loss": 0.0057, "step": 214710 }, { "epoch": 51.55, "learning_rate": 5.14643356109046e-05, "loss": 0.007, "step": 214720 }, { "epoch": 51.55, "learning_rate": 5.146074757574186e-05, "loss": 0.0067, "step": 214730 }, { "epoch": 51.55, "learning_rate": 5.145715953305041e-05, "loss": 0.0083, "step": 214740 }, { "epoch": 51.56, "learning_rate": 5.145357148284876e-05, "loss": 0.0098, "step": 214750 }, { "epoch": 51.56, "learning_rate": 5.144998342515538e-05, "loss": 0.0097, "step": 214760 }, { "epoch": 51.56, "learning_rate": 5.1446395359988774e-05, "loss": 0.0045, "step": 214770 }, { "epoch": 51.56, "learning_rate": 5.1442807287367434e-05, "loss": 0.0061, "step": 214780 }, { "epoch": 51.57, "learning_rate": 5.143921920730985e-05, "loss": 0.0165, "step": 214790 }, { "epoch": 51.57, "learning_rate": 5.1435631119834526e-05, "loss": 0.0101, "step": 214800 }, { "epoch": 51.57, "learning_rate": 5.143204302495993e-05, "loss": 0.0034, "step": 214810 }, { "epoch": 51.57, "learning_rate": 5.142845492270459e-05, "loss": 0.0265, "step": 214820 }, { "epoch": 51.58, "learning_rate": 5.142486681308698e-05, "loss": 0.007, "step": 214830 }, { "epoch": 51.58, "learning_rate": 5.1421278696125586e-05, "loss": 0.0044, "step": 214840 }, { "epoch": 51.58, "learning_rate": 5.1417690571838915e-05, "loss": 0.0088, "step": 214850 }, { "epoch": 51.58, "learning_rate": 5.141410244024545e-05, "loss": 0.01, "step": 214860 }, { "epoch": 51.58, "learning_rate": 5.14105143013637e-05, "loss": 0.0102, "step": 214870 }, { "epoch": 51.59, "learning_rate": 5.140692615521213e-05, "loss": 0.0107, "step": 214880 }, { "epoch": 51.59, "learning_rate": 5.1403338001809276e-05, "loss": 0.0055, "step": 214890 }, { "epoch": 51.59, "learning_rate": 5.1399749841173596e-05, "loss": 0.0049, "step": 214900 }, { "epoch": 51.59, "learning_rate": 5.139616167332359e-05, "loss": 0.0123, "step": 214910 }, { "epoch": 51.6, "learning_rate": 5.139257349827775e-05, "loss": 0.0112, "step": 214920 }, { "epoch": 51.6, "learning_rate": 5.138898531605458e-05, "loss": 0.0054, "step": 214930 }, { "epoch": 51.6, "learning_rate": 5.138539712667256e-05, "loss": 0.014, "step": 214940 }, { "epoch": 51.6, "learning_rate": 5.13818089301502e-05, "loss": 0.0043, "step": 214950 }, { "epoch": 51.6, "learning_rate": 5.137822072650599e-05, "loss": 0.0048, "step": 214960 }, { "epoch": 51.61, "learning_rate": 5.137463251575841e-05, "loss": 0.0192, "step": 214970 }, { "epoch": 51.61, "learning_rate": 5.1371044297925964e-05, "loss": 0.0376, "step": 214980 }, { "epoch": 51.61, "learning_rate": 5.136745607302714e-05, "loss": 0.0082, "step": 214990 }, { "epoch": 51.61, "learning_rate": 5.136386784108045e-05, "loss": 0.0081, "step": 215000 }, { "epoch": 51.62, "learning_rate": 5.136027960210436e-05, "loss": 0.0063, "step": 215010 }, { "epoch": 51.62, "learning_rate": 5.135669135611738e-05, "loss": 0.005, "step": 215020 }, { "epoch": 51.62, "learning_rate": 5.1353103103138e-05, "loss": 0.0165, "step": 215030 }, { "epoch": 51.62, "learning_rate": 5.134951484318473e-05, "loss": 0.0056, "step": 215040 }, { "epoch": 51.63, "learning_rate": 5.134592657627605e-05, "loss": 0.0039, "step": 215050 }, { "epoch": 51.63, "learning_rate": 5.134233830243044e-05, "loss": 0.0041, "step": 215060 }, { "epoch": 51.63, "learning_rate": 5.1338750021666405e-05, "loss": 0.0045, "step": 215070 }, { "epoch": 51.63, "learning_rate": 5.133516173400245e-05, "loss": 0.0124, "step": 215080 }, { "epoch": 51.63, "learning_rate": 5.1331573439457045e-05, "loss": 0.0045, "step": 215090 }, { "epoch": 51.64, "learning_rate": 5.132798513804872e-05, "loss": 0.0059, "step": 215100 }, { "epoch": 51.64, "learning_rate": 5.132439682979593e-05, "loss": 0.0066, "step": 215110 }, { "epoch": 51.64, "learning_rate": 5.13208085147172e-05, "loss": 0.0066, "step": 215120 }, { "epoch": 51.64, "learning_rate": 5.1317220192831006e-05, "loss": 0.0056, "step": 215130 }, { "epoch": 51.65, "learning_rate": 5.131363186415584e-05, "loss": 0.0053, "step": 215140 }, { "epoch": 51.65, "learning_rate": 5.131004352871022e-05, "loss": 0.0067, "step": 215150 }, { "epoch": 51.65, "learning_rate": 5.1306455186512614e-05, "loss": 0.0062, "step": 215160 }, { "epoch": 51.65, "learning_rate": 5.130286683758153e-05, "loss": 0.0084, "step": 215170 }, { "epoch": 51.66, "learning_rate": 5.1299278481935474e-05, "loss": 0.0105, "step": 215180 }, { "epoch": 51.66, "learning_rate": 5.129569011959292e-05, "loss": 0.0117, "step": 215190 }, { "epoch": 51.66, "learning_rate": 5.129210175057236e-05, "loss": 0.0055, "step": 215200 }, { "epoch": 51.66, "learning_rate": 5.12885133748923e-05, "loss": 0.0065, "step": 215210 }, { "epoch": 51.66, "learning_rate": 5.1284924992571226e-05, "loss": 0.0068, "step": 215220 }, { "epoch": 51.67, "learning_rate": 5.128133660362764e-05, "loss": 0.0063, "step": 215230 }, { "epoch": 51.67, "learning_rate": 5.127774820808004e-05, "loss": 0.0094, "step": 215240 }, { "epoch": 51.67, "learning_rate": 5.127415980594691e-05, "loss": 0.0034, "step": 215250 }, { "epoch": 51.67, "learning_rate": 5.127057139724675e-05, "loss": 0.0088, "step": 215260 }, { "epoch": 51.68, "learning_rate": 5.126698298199806e-05, "loss": 0.0046, "step": 215270 }, { "epoch": 51.68, "learning_rate": 5.1263394560219316e-05, "loss": 0.0077, "step": 215280 }, { "epoch": 51.68, "learning_rate": 5.125980613192903e-05, "loss": 0.0042, "step": 215290 }, { "epoch": 51.68, "learning_rate": 5.12562176971457e-05, "loss": 0.0072, "step": 215300 }, { "epoch": 51.68, "learning_rate": 5.125262925588781e-05, "loss": 0.0122, "step": 215310 }, { "epoch": 51.69, "learning_rate": 5.124904080817387e-05, "loss": 0.0052, "step": 215320 }, { "epoch": 51.69, "learning_rate": 5.124545235402235e-05, "loss": 0.0075, "step": 215330 }, { "epoch": 51.69, "learning_rate": 5.1241863893451756e-05, "loss": 0.0082, "step": 215340 }, { "epoch": 51.69, "learning_rate": 5.12382754264806e-05, "loss": 0.0068, "step": 215350 }, { "epoch": 51.7, "learning_rate": 5.123468695312734e-05, "loss": 0.0049, "step": 215360 }, { "epoch": 51.7, "learning_rate": 5.123109847341051e-05, "loss": 0.0128, "step": 215370 }, { "epoch": 51.7, "learning_rate": 5.122750998734858e-05, "loss": 0.0112, "step": 215380 }, { "epoch": 51.7, "learning_rate": 5.122392149496006e-05, "loss": 0.0056, "step": 215390 }, { "epoch": 51.71, "learning_rate": 5.122033299626343e-05, "loss": 0.0081, "step": 215400 }, { "epoch": 51.71, "learning_rate": 5.121674449127719e-05, "loss": 0.0058, "step": 215410 }, { "epoch": 51.71, "learning_rate": 5.1213155980019854e-05, "loss": 0.0051, "step": 215420 }, { "epoch": 51.71, "learning_rate": 5.120956746250989e-05, "loss": 0.0053, "step": 215430 }, { "epoch": 51.71, "learning_rate": 5.1205978938765806e-05, "loss": 0.0052, "step": 215440 }, { "epoch": 51.72, "learning_rate": 5.12023904088061e-05, "loss": 0.0091, "step": 215450 }, { "epoch": 51.72, "learning_rate": 5.1198801872649275e-05, "loss": 0.0026, "step": 215460 }, { "epoch": 51.72, "learning_rate": 5.119521333031381e-05, "loss": 0.0049, "step": 215470 }, { "epoch": 51.72, "learning_rate": 5.119162478181819e-05, "loss": 0.0045, "step": 215480 }, { "epoch": 51.73, "learning_rate": 5.1188036227180935e-05, "loss": 0.0041, "step": 215490 }, { "epoch": 51.73, "learning_rate": 5.118444766642053e-05, "loss": 0.004, "step": 215500 }, { "epoch": 51.73, "learning_rate": 5.118085909955548e-05, "loss": 0.0044, "step": 215510 }, { "epoch": 51.73, "learning_rate": 5.117727052660427e-05, "loss": 0.0071, "step": 215520 }, { "epoch": 51.74, "learning_rate": 5.117368194758538e-05, "loss": 0.0034, "step": 215530 }, { "epoch": 51.74, "learning_rate": 5.117009336251735e-05, "loss": 0.0051, "step": 215540 }, { "epoch": 51.74, "learning_rate": 5.116650477141863e-05, "loss": 0.0052, "step": 215550 }, { "epoch": 51.74, "learning_rate": 5.116291617430774e-05, "loss": 0.0064, "step": 215560 }, { "epoch": 51.74, "learning_rate": 5.115932757120318e-05, "loss": 0.0034, "step": 215570 }, { "epoch": 51.75, "learning_rate": 5.115573896212342e-05, "loss": 0.0072, "step": 215580 }, { "epoch": 51.75, "learning_rate": 5.115215034708698e-05, "loss": 0.0087, "step": 215590 }, { "epoch": 51.75, "learning_rate": 5.114856172611234e-05, "loss": 0.0041, "step": 215600 }, { "epoch": 51.75, "learning_rate": 5.1144973099218016e-05, "loss": 0.0064, "step": 215610 }, { "epoch": 51.76, "learning_rate": 5.1141384466422495e-05, "loss": 0.0046, "step": 215620 }, { "epoch": 51.76, "learning_rate": 5.113779582774425e-05, "loss": 0.0042, "step": 215630 }, { "epoch": 51.76, "learning_rate": 5.113420718320181e-05, "loss": 0.0091, "step": 215640 }, { "epoch": 51.76, "learning_rate": 5.1130618532813645e-05, "loss": 0.0053, "step": 215650 }, { "epoch": 51.76, "learning_rate": 5.112702987659827e-05, "loss": 0.0046, "step": 215660 }, { "epoch": 51.77, "learning_rate": 5.112344121457417e-05, "loss": 0.0046, "step": 215670 }, { "epoch": 51.77, "learning_rate": 5.111985254675986e-05, "loss": 0.0057, "step": 215680 }, { "epoch": 51.77, "learning_rate": 5.111626387317381e-05, "loss": 0.0056, "step": 215690 }, { "epoch": 51.77, "learning_rate": 5.111267519383451e-05, "loss": 0.0051, "step": 215700 }, { "epoch": 51.78, "learning_rate": 5.1109086508760484e-05, "loss": 0.0057, "step": 215710 }, { "epoch": 51.78, "learning_rate": 5.110549781797023e-05, "loss": 0.0082, "step": 215720 }, { "epoch": 51.78, "learning_rate": 5.1101909121482215e-05, "loss": 0.0032, "step": 215730 }, { "epoch": 51.78, "learning_rate": 5.109832041931496e-05, "loss": 0.0038, "step": 215740 }, { "epoch": 51.79, "learning_rate": 5.1094731711486956e-05, "loss": 0.0035, "step": 215750 }, { "epoch": 51.79, "learning_rate": 5.1091142998016697e-05, "loss": 0.0047, "step": 215760 }, { "epoch": 51.79, "learning_rate": 5.108755427892267e-05, "loss": 0.0046, "step": 215770 }, { "epoch": 51.79, "learning_rate": 5.1083965554223366e-05, "loss": 0.0043, "step": 215780 }, { "epoch": 51.79, "learning_rate": 5.1080376823937314e-05, "loss": 0.004, "step": 215790 }, { "epoch": 51.8, "learning_rate": 5.107678808808298e-05, "loss": 0.0073, "step": 215800 }, { "epoch": 51.8, "learning_rate": 5.107319934667888e-05, "loss": 0.0064, "step": 215810 }, { "epoch": 51.8, "learning_rate": 5.106961059974349e-05, "loss": 0.0052, "step": 215820 }, { "epoch": 51.8, "learning_rate": 5.1066021847295344e-05, "loss": 0.0039, "step": 215830 }, { "epoch": 51.81, "learning_rate": 5.1062433089352894e-05, "loss": 0.003, "step": 215840 }, { "epoch": 51.81, "learning_rate": 5.105884432593465e-05, "loss": 0.0027, "step": 215850 }, { "epoch": 51.81, "learning_rate": 5.10552555570591e-05, "loss": 0.0045, "step": 215860 }, { "epoch": 51.81, "learning_rate": 5.105166678274478e-05, "loss": 0.0036, "step": 215870 }, { "epoch": 51.82, "learning_rate": 5.104807800301015e-05, "loss": 0.0041, "step": 215880 }, { "epoch": 51.82, "learning_rate": 5.104448921787371e-05, "loss": 0.0041, "step": 215890 }, { "epoch": 51.82, "learning_rate": 5.104090042735399e-05, "loss": 0.0025, "step": 215900 }, { "epoch": 51.82, "learning_rate": 5.103731163146944e-05, "loss": 0.0037, "step": 215910 }, { "epoch": 51.82, "learning_rate": 5.103372283023859e-05, "loss": 0.0058, "step": 215920 }, { "epoch": 51.83, "learning_rate": 5.103013402367991e-05, "loss": 0.0041, "step": 215930 }, { "epoch": 51.83, "learning_rate": 5.102654521181192e-05, "loss": 0.0065, "step": 215940 }, { "epoch": 51.83, "learning_rate": 5.1022956394653096e-05, "loss": 0.0036, "step": 215950 }, { "epoch": 51.83, "learning_rate": 5.1019367572221955e-05, "loss": 0.0091, "step": 215960 }, { "epoch": 51.84, "learning_rate": 5.1015778744537e-05, "loss": 0.0152, "step": 215970 }, { "epoch": 51.84, "learning_rate": 5.101218991161669e-05, "loss": 0.0035, "step": 215980 }, { "epoch": 51.84, "learning_rate": 5.1008601073479553e-05, "loss": 0.0088, "step": 215990 }, { "epoch": 51.84, "learning_rate": 5.100501223014408e-05, "loss": 0.006, "step": 216000 }, { "epoch": 51.84, "learning_rate": 5.100142338162874e-05, "loss": 0.0078, "step": 216010 }, { "epoch": 51.85, "learning_rate": 5.099783452795208e-05, "loss": 0.0059, "step": 216020 }, { "epoch": 51.85, "learning_rate": 5.0994245669132566e-05, "loss": 0.0044, "step": 216030 }, { "epoch": 51.85, "learning_rate": 5.099065680518872e-05, "loss": 0.0041, "step": 216040 }, { "epoch": 51.85, "learning_rate": 5.098706793613901e-05, "loss": 0.0069, "step": 216050 }, { "epoch": 51.86, "learning_rate": 5.098347906200194e-05, "loss": 0.006, "step": 216060 }, { "epoch": 51.86, "learning_rate": 5.097989018279601e-05, "loss": 0.0032, "step": 216070 }, { "epoch": 51.86, "learning_rate": 5.097630129853971e-05, "loss": 0.0047, "step": 216080 }, { "epoch": 51.86, "learning_rate": 5.097271240925156e-05, "loss": 0.0039, "step": 216090 }, { "epoch": 51.87, "learning_rate": 5.0969123514950024e-05, "loss": 0.0041, "step": 216100 }, { "epoch": 51.87, "learning_rate": 5.0965534615653644e-05, "loss": 0.0034, "step": 216110 }, { "epoch": 51.87, "learning_rate": 5.096194571138088e-05, "loss": 0.0039, "step": 216120 }, { "epoch": 51.87, "learning_rate": 5.095835680215023e-05, "loss": 0.0049, "step": 216130 }, { "epoch": 51.87, "learning_rate": 5.0954767887980206e-05, "loss": 0.0035, "step": 216140 }, { "epoch": 51.88, "learning_rate": 5.095117896888929e-05, "loss": 0.0046, "step": 216150 }, { "epoch": 51.88, "learning_rate": 5.0947590044896e-05, "loss": 0.0026, "step": 216160 }, { "epoch": 51.88, "learning_rate": 5.0944001116018816e-05, "loss": 0.0039, "step": 216170 }, { "epoch": 51.88, "learning_rate": 5.0940412182276256e-05, "loss": 0.0031, "step": 216180 }, { "epoch": 51.89, "learning_rate": 5.093682324368679e-05, "loss": 0.0049, "step": 216190 }, { "epoch": 51.89, "learning_rate": 5.093323430026894e-05, "loss": 0.0068, "step": 216200 }, { "epoch": 51.89, "learning_rate": 5.092964535204119e-05, "loss": 0.0039, "step": 216210 }, { "epoch": 51.89, "learning_rate": 5.0926056399022036e-05, "loss": 0.0243, "step": 216220 }, { "epoch": 51.9, "learning_rate": 5.092246744122998e-05, "loss": 0.0039, "step": 216230 }, { "epoch": 51.9, "learning_rate": 5.091887847868352e-05, "loss": 0.0039, "step": 216240 }, { "epoch": 51.9, "learning_rate": 5.0915289511401156e-05, "loss": 0.007, "step": 216250 }, { "epoch": 51.9, "learning_rate": 5.0911700539401385e-05, "loss": 0.0035, "step": 216260 }, { "epoch": 51.9, "learning_rate": 5.09081115627027e-05, "loss": 0.0073, "step": 216270 }, { "epoch": 51.91, "learning_rate": 5.09045225813236e-05, "loss": 0.0095, "step": 216280 }, { "epoch": 51.91, "learning_rate": 5.0900933595282574e-05, "loss": 0.004, "step": 216290 }, { "epoch": 51.91, "learning_rate": 5.0897344604598143e-05, "loss": 0.0041, "step": 216300 }, { "epoch": 51.91, "learning_rate": 5.089375560928877e-05, "loss": 0.005, "step": 216310 }, { "epoch": 51.92, "learning_rate": 5.089016660937299e-05, "loss": 0.0037, "step": 216320 }, { "epoch": 51.92, "learning_rate": 5.0886577604869276e-05, "loss": 0.0083, "step": 216330 }, { "epoch": 51.92, "learning_rate": 5.0882988595796146e-05, "loss": 0.0047, "step": 216340 }, { "epoch": 51.92, "learning_rate": 5.087939958217207e-05, "loss": 0.0052, "step": 216350 }, { "epoch": 51.92, "learning_rate": 5.087581056401557e-05, "loss": 0.0053, "step": 216360 }, { "epoch": 51.93, "learning_rate": 5.0872221541345134e-05, "loss": 0.0083, "step": 216370 }, { "epoch": 51.93, "learning_rate": 5.086863251417925e-05, "loss": 0.0058, "step": 216380 }, { "epoch": 51.93, "learning_rate": 5.0865043482536434e-05, "loss": 0.0049, "step": 216390 }, { "epoch": 51.93, "learning_rate": 5.0861454446435195e-05, "loss": 0.0058, "step": 216400 }, { "epoch": 51.94, "learning_rate": 5.085786540589399e-05, "loss": 0.004, "step": 216410 }, { "epoch": 51.94, "learning_rate": 5.085427636093135e-05, "loss": 0.0042, "step": 216420 }, { "epoch": 51.94, "learning_rate": 5.085068731156576e-05, "loss": 0.0089, "step": 216430 }, { "epoch": 51.94, "learning_rate": 5.084709825781572e-05, "loss": 0.0039, "step": 216440 }, { "epoch": 51.95, "learning_rate": 5.084350919969973e-05, "loss": 0.0041, "step": 216450 }, { "epoch": 51.95, "learning_rate": 5.0839920137236274e-05, "loss": 0.0045, "step": 216460 }, { "epoch": 51.95, "learning_rate": 5.083633107044388e-05, "loss": 0.0041, "step": 216470 }, { "epoch": 52.0, "learning_rate": 5.0832741999341015e-05, "loss": 0.0051, "step": 216480 }, { "epoch": 52.0, "learning_rate": 5.08291529239462e-05, "loss": 0.0031, "step": 216490 }, { "epoch": 52.01, "learning_rate": 5.082556384427791e-05, "loss": 0.0057, "step": 216500 }, { "epoch": 52.01, "learning_rate": 5.0821974760354674e-05, "loss": 0.0033, "step": 216510 }, { "epoch": 52.01, "learning_rate": 5.0818385672194966e-05, "loss": 0.004, "step": 216520 }, { "epoch": 52.01, "learning_rate": 5.081479657981729e-05, "loss": 0.0035, "step": 216530 }, { "epoch": 52.01, "learning_rate": 5.081120748324016e-05, "loss": 0.0028, "step": 216540 }, { "epoch": 52.02, "learning_rate": 5.0807618382482044e-05, "loss": 0.0052, "step": 216550 }, { "epoch": 52.02, "learning_rate": 5.080402927756146e-05, "loss": 0.0051, "step": 216560 }, { "epoch": 52.02, "learning_rate": 5.080044016849691e-05, "loss": 0.0091, "step": 216570 }, { "epoch": 52.02, "learning_rate": 5.079685105530687e-05, "loss": 0.0048, "step": 216580 }, { "epoch": 52.03, "learning_rate": 5.079326193800986e-05, "loss": 0.0034, "step": 216590 }, { "epoch": 52.03, "learning_rate": 5.0789672816624366e-05, "loss": 0.0035, "step": 216600 }, { "epoch": 52.03, "learning_rate": 5.078608369116891e-05, "loss": 0.004, "step": 216610 }, { "epoch": 52.03, "learning_rate": 5.078249456166195e-05, "loss": 0.0048, "step": 216620 }, { "epoch": 52.04, "learning_rate": 5.077890542812201e-05, "loss": 0.011, "step": 216630 }, { "epoch": 52.04, "learning_rate": 5.07753162905676e-05, "loss": 0.0074, "step": 216640 }, { "epoch": 52.04, "learning_rate": 5.077172714901719e-05, "loss": 0.0045, "step": 216650 }, { "epoch": 52.04, "learning_rate": 5.07681380034893e-05, "loss": 0.0042, "step": 216660 }, { "epoch": 52.04, "learning_rate": 5.076454885400241e-05, "loss": 0.0065, "step": 216670 }, { "epoch": 52.05, "learning_rate": 5.076095970057504e-05, "loss": 0.005, "step": 216680 }, { "epoch": 52.05, "learning_rate": 5.075737054322568e-05, "loss": 0.0059, "step": 216690 }, { "epoch": 52.05, "learning_rate": 5.075378138197282e-05, "loss": 0.004, "step": 216700 }, { "epoch": 52.05, "learning_rate": 5.075019221683496e-05, "loss": 0.0073, "step": 216710 }, { "epoch": 52.06, "learning_rate": 5.0746603047830596e-05, "loss": 0.0029, "step": 216720 }, { "epoch": 52.06, "learning_rate": 5.074301387497825e-05, "loss": 0.0049, "step": 216730 }, { "epoch": 52.06, "learning_rate": 5.07394246982964e-05, "loss": 0.0047, "step": 216740 }, { "epoch": 52.06, "learning_rate": 5.0735835517803545e-05, "loss": 0.007, "step": 216750 }, { "epoch": 52.06, "learning_rate": 5.073224633351819e-05, "loss": 0.0057, "step": 216760 }, { "epoch": 52.07, "learning_rate": 5.0728657145458823e-05, "loss": 0.004, "step": 216770 }, { "epoch": 52.07, "learning_rate": 5.072506795364396e-05, "loss": 0.0052, "step": 216780 }, { "epoch": 52.07, "learning_rate": 5.072147875809209e-05, "loss": 0.0093, "step": 216790 }, { "epoch": 52.07, "learning_rate": 5.071788955882171e-05, "loss": 0.0087, "step": 216800 }, { "epoch": 52.08, "learning_rate": 5.071430035585132e-05, "loss": 0.005, "step": 216810 }, { "epoch": 52.08, "learning_rate": 5.071071114919943e-05, "loss": 0.005, "step": 216820 }, { "epoch": 52.08, "learning_rate": 5.070712193888453e-05, "loss": 0.004, "step": 216830 }, { "epoch": 52.08, "learning_rate": 5.0703532724925105e-05, "loss": 0.006, "step": 216840 }, { "epoch": 52.09, "learning_rate": 5.069994350733968e-05, "loss": 0.0051, "step": 216850 }, { "epoch": 52.09, "learning_rate": 5.069635428614672e-05, "loss": 0.0077, "step": 216860 }, { "epoch": 52.09, "learning_rate": 5.069276506136475e-05, "loss": 0.0117, "step": 216870 }, { "epoch": 52.09, "learning_rate": 5.068917583301227e-05, "loss": 0.0039, "step": 216880 }, { "epoch": 52.09, "learning_rate": 5.068558660110777e-05, "loss": 0.004, "step": 216890 }, { "epoch": 52.1, "learning_rate": 5.068199736566975e-05, "loss": 0.0037, "step": 216900 }, { "epoch": 52.1, "learning_rate": 5.067840812671671e-05, "loss": 0.008, "step": 216910 }, { "epoch": 52.1, "learning_rate": 5.067481888426715e-05, "loss": 0.0044, "step": 216920 }, { "epoch": 52.1, "learning_rate": 5.067122963833957e-05, "loss": 0.0047, "step": 216930 }, { "epoch": 52.11, "learning_rate": 5.0667640388952466e-05, "loss": 0.007, "step": 216940 }, { "epoch": 52.11, "learning_rate": 5.0664051136124335e-05, "loss": 0.0086, "step": 216950 }, { "epoch": 52.11, "learning_rate": 5.0660461879873676e-05, "loss": 0.0049, "step": 216960 }, { "epoch": 52.11, "learning_rate": 5.065687262021901e-05, "loss": 0.0063, "step": 216970 }, { "epoch": 52.12, "learning_rate": 5.06532833571788e-05, "loss": 0.0041, "step": 216980 }, { "epoch": 52.12, "learning_rate": 5.064969409077156e-05, "loss": 0.0127, "step": 216990 }, { "epoch": 52.12, "learning_rate": 5.0646104821015795e-05, "loss": 0.006, "step": 217000 }, { "epoch": 52.12, "learning_rate": 5.0642515547930004e-05, "loss": 0.0062, "step": 217010 }, { "epoch": 52.12, "learning_rate": 5.0638926271532686e-05, "loss": 0.0049, "step": 217020 }, { "epoch": 52.13, "learning_rate": 5.063533699184232e-05, "loss": 0.0053, "step": 217030 }, { "epoch": 52.13, "learning_rate": 5.063174770887743e-05, "loss": 0.0045, "step": 217040 }, { "epoch": 52.13, "learning_rate": 5.062815842265652e-05, "loss": 0.0038, "step": 217050 }, { "epoch": 52.13, "learning_rate": 5.0624569133198064e-05, "loss": 0.0035, "step": 217060 }, { "epoch": 52.14, "learning_rate": 5.062097984052056e-05, "loss": 0.0035, "step": 217070 }, { "epoch": 52.14, "learning_rate": 5.061739054464254e-05, "loss": 0.0028, "step": 217080 }, { "epoch": 52.14, "learning_rate": 5.061380124558248e-05, "loss": 0.0044, "step": 217090 }, { "epoch": 52.14, "learning_rate": 5.0610211943358885e-05, "loss": 0.0029, "step": 217100 }, { "epoch": 52.14, "learning_rate": 5.0606622637990255e-05, "loss": 0.0097, "step": 217110 }, { "epoch": 52.15, "learning_rate": 5.0603033329495085e-05, "loss": 0.004, "step": 217120 }, { "epoch": 52.15, "learning_rate": 5.059944401789187e-05, "loss": 0.0065, "step": 217130 }, { "epoch": 52.15, "learning_rate": 5.059585470319912e-05, "loss": 0.0048, "step": 217140 }, { "epoch": 52.15, "learning_rate": 5.0592265385435334e-05, "loss": 0.005, "step": 217150 }, { "epoch": 52.16, "learning_rate": 5.0588676064619e-05, "loss": 0.0068, "step": 217160 }, { "epoch": 52.16, "learning_rate": 5.058508674076862e-05, "loss": 0.0116, "step": 217170 }, { "epoch": 52.16, "learning_rate": 5.05814974139027e-05, "loss": 0.0047, "step": 217180 }, { "epoch": 52.16, "learning_rate": 5.057790808403976e-05, "loss": 0.0038, "step": 217190 }, { "epoch": 52.17, "learning_rate": 5.0574318751198254e-05, "loss": 0.0043, "step": 217200 }, { "epoch": 52.17, "learning_rate": 5.05707294153967e-05, "loss": 0.0038, "step": 217210 }, { "epoch": 52.17, "learning_rate": 5.056714007665361e-05, "loss": 0.0045, "step": 217220 }, { "epoch": 52.17, "learning_rate": 5.056355073498748e-05, "loss": 0.0096, "step": 217230 }, { "epoch": 52.17, "learning_rate": 5.05599613904168e-05, "loss": 0.0032, "step": 217240 }, { "epoch": 52.18, "learning_rate": 5.0556372042960074e-05, "loss": 0.0051, "step": 217250 }, { "epoch": 52.18, "learning_rate": 5.0552782692635814e-05, "loss": 0.0044, "step": 217260 }, { "epoch": 52.18, "learning_rate": 5.0549193339462495e-05, "loss": 0.0045, "step": 217270 }, { "epoch": 52.18, "learning_rate": 5.0545603983458636e-05, "loss": 0.0039, "step": 217280 }, { "epoch": 52.19, "learning_rate": 5.054201462464272e-05, "loss": 0.004, "step": 217290 }, { "epoch": 52.19, "learning_rate": 5.053842526303326e-05, "loss": 0.0042, "step": 217300 }, { "epoch": 52.19, "learning_rate": 5.053483589864875e-05, "loss": 0.0082, "step": 217310 }, { "epoch": 52.19, "learning_rate": 5.053124653150769e-05, "loss": 0.0058, "step": 217320 }, { "epoch": 52.2, "learning_rate": 5.0527657161628594e-05, "loss": 0.0053, "step": 217330 }, { "epoch": 52.2, "learning_rate": 5.0524067789029936e-05, "loss": 0.0359, "step": 217340 }, { "epoch": 52.2, "learning_rate": 5.052047841373023e-05, "loss": 0.0075, "step": 217350 }, { "epoch": 52.2, "learning_rate": 5.051688903574798e-05, "loss": 0.0077, "step": 217360 }, { "epoch": 52.2, "learning_rate": 5.0513299655101665e-05, "loss": 0.0032, "step": 217370 }, { "epoch": 52.21, "learning_rate": 5.0509710271809806e-05, "loss": 0.0024, "step": 217380 }, { "epoch": 52.21, "learning_rate": 5.05061208858909e-05, "loss": 0.0038, "step": 217390 }, { "epoch": 52.21, "learning_rate": 5.050253149736344e-05, "loss": 0.005, "step": 217400 }, { "epoch": 52.21, "learning_rate": 5.049894210624594e-05, "loss": 0.0061, "step": 217410 }, { "epoch": 52.22, "learning_rate": 5.049535271255688e-05, "loss": 0.0081, "step": 217420 }, { "epoch": 52.22, "learning_rate": 5.0491763316314766e-05, "loss": 0.005, "step": 217430 }, { "epoch": 52.22, "learning_rate": 5.0488173917538094e-05, "loss": 0.0052, "step": 217440 }, { "epoch": 52.22, "learning_rate": 5.048458451624537e-05, "loss": 0.0039, "step": 217450 }, { "epoch": 52.22, "learning_rate": 5.0480995112455096e-05, "loss": 0.0083, "step": 217460 }, { "epoch": 52.23, "learning_rate": 5.0477405706185774e-05, "loss": 0.0039, "step": 217470 }, { "epoch": 52.23, "learning_rate": 5.047381629745591e-05, "loss": 0.032, "step": 217480 }, { "epoch": 52.23, "learning_rate": 5.047022688628398e-05, "loss": 0.0056, "step": 217490 }, { "epoch": 52.23, "learning_rate": 5.0466637472688495e-05, "loss": 0.009, "step": 217500 }, { "epoch": 52.24, "learning_rate": 5.046304805668796e-05, "loss": 0.0029, "step": 217510 }, { "epoch": 52.24, "learning_rate": 5.045945863830087e-05, "loss": 0.0079, "step": 217520 }, { "epoch": 52.24, "learning_rate": 5.0455869217545716e-05, "loss": 0.0042, "step": 217530 }, { "epoch": 52.24, "learning_rate": 5.045227979444102e-05, "loss": 0.0038, "step": 217540 }, { "epoch": 52.25, "learning_rate": 5.044869036900527e-05, "loss": 0.0056, "step": 217550 }, { "epoch": 52.25, "learning_rate": 5.0445100941256976e-05, "loss": 0.0043, "step": 217560 }, { "epoch": 52.25, "learning_rate": 5.044151151121461e-05, "loss": 0.008, "step": 217570 }, { "epoch": 52.25, "learning_rate": 5.0437922078896695e-05, "loss": 0.0058, "step": 217580 }, { "epoch": 52.25, "learning_rate": 5.043433264432173e-05, "loss": 0.0064, "step": 217590 }, { "epoch": 52.26, "learning_rate": 5.04307432075082e-05, "loss": 0.0035, "step": 217600 }, { "epoch": 52.26, "learning_rate": 5.042715376847462e-05, "loss": 0.0038, "step": 217610 }, { "epoch": 52.26, "learning_rate": 5.04235643272395e-05, "loss": 0.0035, "step": 217620 }, { "epoch": 52.26, "learning_rate": 5.041997488382132e-05, "loss": 0.0032, "step": 217630 }, { "epoch": 52.27, "learning_rate": 5.041638543823859e-05, "loss": 0.003, "step": 217640 }, { "epoch": 52.27, "learning_rate": 5.0412795990509784e-05, "loss": 0.0082, "step": 217650 }, { "epoch": 52.27, "learning_rate": 5.040920654065344e-05, "loss": 0.003, "step": 217660 }, { "epoch": 52.27, "learning_rate": 5.040561708868804e-05, "loss": 0.0087, "step": 217670 }, { "epoch": 52.28, "learning_rate": 5.0402027634632073e-05, "loss": 0.0067, "step": 217680 }, { "epoch": 52.28, "learning_rate": 5.039843817850408e-05, "loss": 0.0038, "step": 217690 }, { "epoch": 52.28, "learning_rate": 5.0394848720322516e-05, "loss": 0.0048, "step": 217700 }, { "epoch": 52.28, "learning_rate": 5.03912592601059e-05, "loss": 0.0054, "step": 217710 }, { "epoch": 52.28, "learning_rate": 5.038766979787274e-05, "loss": 0.0041, "step": 217720 }, { "epoch": 52.29, "learning_rate": 5.038408033364152e-05, "loss": 0.0044, "step": 217730 }, { "epoch": 52.29, "learning_rate": 5.038049086743074e-05, "loss": 0.0052, "step": 217740 }, { "epoch": 52.29, "learning_rate": 5.0376901399258905e-05, "loss": 0.0054, "step": 217750 }, { "epoch": 52.29, "learning_rate": 5.037331192914454e-05, "loss": 0.0057, "step": 217760 }, { "epoch": 52.3, "learning_rate": 5.036972245710611e-05, "loss": 0.0038, "step": 217770 }, { "epoch": 52.3, "learning_rate": 5.036613298316212e-05, "loss": 0.003, "step": 217780 }, { "epoch": 52.3, "learning_rate": 5.036254350733107e-05, "loss": 0.0108, "step": 217790 }, { "epoch": 52.3, "learning_rate": 5.035895402963149e-05, "loss": 0.0077, "step": 217800 }, { "epoch": 52.3, "learning_rate": 5.035536455008184e-05, "loss": 0.0048, "step": 217810 }, { "epoch": 52.31, "learning_rate": 5.0351775068700646e-05, "loss": 0.0046, "step": 217820 }, { "epoch": 52.31, "learning_rate": 5.0348185585506394e-05, "loss": 0.0073, "step": 217830 }, { "epoch": 52.31, "learning_rate": 5.034459610051759e-05, "loss": 0.0043, "step": 217840 }, { "epoch": 52.31, "learning_rate": 5.034100661375275e-05, "loss": 0.0071, "step": 217850 }, { "epoch": 52.32, "learning_rate": 5.033741712523035e-05, "loss": 0.0057, "step": 217860 }, { "epoch": 52.32, "learning_rate": 5.03338276349689e-05, "loss": 0.0075, "step": 217870 }, { "epoch": 52.32, "learning_rate": 5.03302381429869e-05, "loss": 0.0068, "step": 217880 }, { "epoch": 52.32, "learning_rate": 5.032664864930284e-05, "loss": 0.0052, "step": 217890 }, { "epoch": 52.33, "learning_rate": 5.0323059153935235e-05, "loss": 0.0032, "step": 217900 }, { "epoch": 52.33, "learning_rate": 5.03194696569026e-05, "loss": 0.0042, "step": 217910 }, { "epoch": 52.33, "learning_rate": 5.031588015822339e-05, "loss": 0.0041, "step": 217920 }, { "epoch": 52.33, "learning_rate": 5.031229065791615e-05, "loss": 0.0031, "step": 217930 }, { "epoch": 52.33, "learning_rate": 5.030870115599935e-05, "loss": 0.0024, "step": 217940 }, { "epoch": 52.34, "learning_rate": 5.03051116524915e-05, "loss": 0.004, "step": 217950 }, { "epoch": 52.34, "learning_rate": 5.030152214741111e-05, "loss": 0.0083, "step": 217960 }, { "epoch": 52.34, "learning_rate": 5.0297932640776656e-05, "loss": 0.007, "step": 217970 }, { "epoch": 52.34, "learning_rate": 5.029434313260667e-05, "loss": 0.0134, "step": 217980 }, { "epoch": 52.35, "learning_rate": 5.029075362291964e-05, "loss": 0.0053, "step": 217990 }, { "epoch": 52.35, "learning_rate": 5.028716411173405e-05, "loss": 0.0052, "step": 218000 }, { "epoch": 52.35, "learning_rate": 5.028357459906842e-05, "loss": 0.0092, "step": 218010 }, { "epoch": 52.35, "learning_rate": 5.027998508494125e-05, "loss": 0.0048, "step": 218020 }, { "epoch": 52.36, "learning_rate": 5.0276395569371026e-05, "loss": 0.0094, "step": 218030 }, { "epoch": 52.36, "learning_rate": 5.027280605237626e-05, "loss": 0.0069, "step": 218040 }, { "epoch": 52.36, "learning_rate": 5.026921653397546e-05, "loss": 0.0043, "step": 218050 }, { "epoch": 52.36, "learning_rate": 5.02656270141871e-05, "loss": 0.0082, "step": 218060 }, { "epoch": 52.36, "learning_rate": 5.02620374930297e-05, "loss": 0.004, "step": 218070 }, { "epoch": 52.37, "learning_rate": 5.025844797052176e-05, "loss": 0.0031, "step": 218080 }, { "epoch": 52.37, "learning_rate": 5.025485844668177e-05, "loss": 0.0045, "step": 218090 }, { "epoch": 52.37, "learning_rate": 5.025126892152825e-05, "loss": 0.0041, "step": 218100 }, { "epoch": 52.37, "learning_rate": 5.0247679395079686e-05, "loss": 0.0047, "step": 218110 }, { "epoch": 52.38, "learning_rate": 5.0244089867354574e-05, "loss": 0.0066, "step": 218120 }, { "epoch": 52.38, "learning_rate": 5.024050033837141e-05, "loss": 0.0051, "step": 218130 }, { "epoch": 52.38, "learning_rate": 5.023691080814872e-05, "loss": 0.0073, "step": 218140 }, { "epoch": 52.38, "learning_rate": 5.023332127670499e-05, "loss": 0.0046, "step": 218150 }, { "epoch": 52.38, "learning_rate": 5.0229731744058714e-05, "loss": 0.0045, "step": 218160 }, { "epoch": 52.39, "learning_rate": 5.02261422102284e-05, "loss": 0.008, "step": 218170 }, { "epoch": 52.39, "learning_rate": 5.0222552675232546e-05, "loss": 0.0039, "step": 218180 }, { "epoch": 52.39, "learning_rate": 5.021896313908967e-05, "loss": 0.0067, "step": 218190 }, { "epoch": 52.39, "learning_rate": 5.021537360181824e-05, "loss": 0.0035, "step": 218200 }, { "epoch": 52.4, "learning_rate": 5.021178406343677e-05, "loss": 0.0034, "step": 218210 }, { "epoch": 52.4, "learning_rate": 5.020819452396377e-05, "loss": 0.0045, "step": 218220 }, { "epoch": 52.4, "learning_rate": 5.0204604983417735e-05, "loss": 0.0059, "step": 218230 }, { "epoch": 52.4, "learning_rate": 5.020101544181716e-05, "loss": 0.0096, "step": 218240 }, { "epoch": 52.41, "learning_rate": 5.019742589918055e-05, "loss": 0.0041, "step": 218250 }, { "epoch": 52.41, "learning_rate": 5.0193836355526405e-05, "loss": 0.0056, "step": 218260 }, { "epoch": 52.41, "learning_rate": 5.019024681087323e-05, "loss": 0.0036, "step": 218270 }, { "epoch": 52.41, "learning_rate": 5.018665726523951e-05, "loss": 0.0032, "step": 218280 }, { "epoch": 52.41, "learning_rate": 5.018306771864377e-05, "loss": 0.0139, "step": 218290 }, { "epoch": 52.42, "learning_rate": 5.017947817110449e-05, "loss": 0.0055, "step": 218300 }, { "epoch": 52.42, "learning_rate": 5.017588862264018e-05, "loss": 0.0033, "step": 218310 }, { "epoch": 52.42, "learning_rate": 5.017229907326934e-05, "loss": 0.0084, "step": 218320 }, { "epoch": 52.42, "learning_rate": 5.016870952301047e-05, "loss": 0.009, "step": 218330 }, { "epoch": 52.43, "learning_rate": 5.016511997188208e-05, "loss": 0.0037, "step": 218340 }, { "epoch": 52.43, "learning_rate": 5.0161530419902644e-05, "loss": 0.0026, "step": 218350 }, { "epoch": 52.43, "learning_rate": 5.015794086709068e-05, "loss": 0.0042, "step": 218360 }, { "epoch": 52.43, "learning_rate": 5.015435131346469e-05, "loss": 0.0056, "step": 218370 }, { "epoch": 52.44, "learning_rate": 5.015076175904317e-05, "loss": 0.005, "step": 218380 }, { "epoch": 52.44, "learning_rate": 5.014717220384463e-05, "loss": 0.0033, "step": 218390 }, { "epoch": 52.44, "learning_rate": 5.0143582647887556e-05, "loss": 0.0237, "step": 218400 }, { "epoch": 52.44, "learning_rate": 5.013999309119046e-05, "loss": 0.0057, "step": 218410 }, { "epoch": 52.44, "learning_rate": 5.013640353377184e-05, "loss": 0.005, "step": 218420 }, { "epoch": 52.45, "learning_rate": 5.013281397565018e-05, "loss": 0.0055, "step": 218430 }, { "epoch": 52.45, "learning_rate": 5.012922441684401e-05, "loss": 0.0038, "step": 218440 }, { "epoch": 52.45, "learning_rate": 5.012563485737182e-05, "loss": 0.0048, "step": 218450 }, { "epoch": 52.45, "learning_rate": 5.012204529725209e-05, "loss": 0.0058, "step": 218460 }, { "epoch": 52.46, "learning_rate": 5.0118455736503355e-05, "loss": 0.0065, "step": 218470 }, { "epoch": 52.46, "learning_rate": 5.01148661751441e-05, "loss": 0.0142, "step": 218480 }, { "epoch": 52.46, "learning_rate": 5.0111276613192816e-05, "loss": 0.0057, "step": 218490 }, { "epoch": 52.46, "learning_rate": 5.0107687050668006e-05, "loss": 0.003, "step": 218500 }, { "epoch": 52.46, "learning_rate": 5.0104097487588186e-05, "loss": 0.0072, "step": 218510 }, { "epoch": 52.47, "learning_rate": 5.010050792397184e-05, "loss": 0.0036, "step": 218520 }, { "epoch": 52.47, "learning_rate": 5.009691835983747e-05, "loss": 0.0067, "step": 218530 }, { "epoch": 52.47, "learning_rate": 5.0093328795203584e-05, "loss": 0.0045, "step": 218540 }, { "epoch": 52.47, "learning_rate": 5.00897392300887e-05, "loss": 0.0039, "step": 218550 }, { "epoch": 52.48, "learning_rate": 5.008614966451128e-05, "loss": 0.0041, "step": 218560 }, { "epoch": 52.48, "learning_rate": 5.008256009848984e-05, "loss": 0.0066, "step": 218570 }, { "epoch": 52.48, "learning_rate": 5.007897053204289e-05, "loss": 0.0049, "step": 218580 }, { "epoch": 52.48, "learning_rate": 5.007538096518893e-05, "loss": 0.0044, "step": 218590 }, { "epoch": 52.49, "learning_rate": 5.007179139794645e-05, "loss": 0.0081, "step": 218600 }, { "epoch": 52.49, "learning_rate": 5.006820183033396e-05, "loss": 0.0044, "step": 218610 }, { "epoch": 52.49, "learning_rate": 5.006461226236996e-05, "loss": 0.005, "step": 218620 }, { "epoch": 52.49, "learning_rate": 5.0061022694072953e-05, "loss": 0.0054, "step": 218630 }, { "epoch": 52.49, "learning_rate": 5.0057433125461426e-05, "loss": 0.0026, "step": 218640 }, { "epoch": 52.5, "learning_rate": 5.005384355655389e-05, "loss": 0.0026, "step": 218650 }, { "epoch": 52.5, "learning_rate": 5.0050253987368847e-05, "loss": 0.0045, "step": 218660 }, { "epoch": 52.5, "learning_rate": 5.0046664417924794e-05, "loss": 0.0031, "step": 218670 }, { "epoch": 52.5, "learning_rate": 5.0043074848240224e-05, "loss": 0.0071, "step": 218680 }, { "epoch": 52.51, "learning_rate": 5.003948527833365e-05, "loss": 0.0031, "step": 218690 }, { "epoch": 52.51, "learning_rate": 5.003589570822358e-05, "loss": 0.0247, "step": 218700 }, { "epoch": 52.51, "learning_rate": 5.0032306137928496e-05, "loss": 0.0024, "step": 218710 }, { "epoch": 52.51, "learning_rate": 5.002871656746689e-05, "loss": 0.0036, "step": 218720 }, { "epoch": 52.52, "learning_rate": 5.002512699685729e-05, "loss": 0.0039, "step": 218730 }, { "epoch": 52.52, "learning_rate": 5.002153742611818e-05, "loss": 0.0058, "step": 218740 }, { "epoch": 52.52, "learning_rate": 5.0017947855268076e-05, "loss": 0.0118, "step": 218750 }, { "epoch": 52.52, "learning_rate": 5.001435828432546e-05, "loss": 0.0108, "step": 218760 }, { "epoch": 52.52, "learning_rate": 5.0010768713308866e-05, "loss": 0.005, "step": 218770 }, { "epoch": 52.53, "learning_rate": 5.0007179142236734e-05, "loss": 0.0067, "step": 218780 }, { "epoch": 52.53, "learning_rate": 5.000358957112763e-05, "loss": 0.0059, "step": 218790 }, { "epoch": 52.53, "learning_rate": 5e-05, "loss": 0.0252, "step": 218800 }, { "epoch": 52.53, "learning_rate": 4.99964104288724e-05, "loss": 0.0073, "step": 218810 }, { "epoch": 52.54, "learning_rate": 4.999282085776327e-05, "loss": 0.0084, "step": 218820 }, { "epoch": 52.54, "learning_rate": 4.998923128669116e-05, "loss": 0.0077, "step": 218830 }, { "epoch": 52.54, "learning_rate": 4.998564171567454e-05, "loss": 0.0057, "step": 218840 }, { "epoch": 52.54, "learning_rate": 4.9982052144731936e-05, "loss": 0.0074, "step": 218850 }, { "epoch": 52.54, "learning_rate": 4.9978462573881815e-05, "loss": 0.0123, "step": 218860 }, { "epoch": 52.55, "learning_rate": 4.9974873003142724e-05, "loss": 0.0081, "step": 218870 }, { "epoch": 52.55, "learning_rate": 4.997128343253312e-05, "loss": 0.0186, "step": 218880 }, { "epoch": 52.55, "learning_rate": 4.9967693862071516e-05, "loss": 0.0069, "step": 218890 }, { "epoch": 52.55, "learning_rate": 4.996410429177644e-05, "loss": 0.0066, "step": 218900 }, { "epoch": 52.56, "learning_rate": 4.9960514721666354e-05, "loss": 0.0125, "step": 218910 }, { "epoch": 52.56, "learning_rate": 4.995692515175979e-05, "loss": 0.017, "step": 218920 }, { "epoch": 52.56, "learning_rate": 4.995333558207521e-05, "loss": 0.0066, "step": 218930 }, { "epoch": 52.56, "learning_rate": 4.9949746012631165e-05, "loss": 0.0046, "step": 218940 }, { "epoch": 52.57, "learning_rate": 4.994615644344613e-05, "loss": 0.0067, "step": 218950 }, { "epoch": 52.57, "learning_rate": 4.994256687453858e-05, "loss": 0.0044, "step": 218960 }, { "epoch": 52.57, "learning_rate": 4.9938977305927065e-05, "loss": 0.0046, "step": 218970 }, { "epoch": 52.57, "learning_rate": 4.993538773763004e-05, "loss": 0.0042, "step": 218980 }, { "epoch": 52.57, "learning_rate": 4.993179816966604e-05, "loss": 0.0077, "step": 218990 }, { "epoch": 52.58, "learning_rate": 4.9928208602053546e-05, "loss": 0.0035, "step": 219000 }, { "epoch": 52.58, "learning_rate": 4.9924619034811074e-05, "loss": 0.0064, "step": 219010 }, { "epoch": 52.58, "learning_rate": 4.992102946795711e-05, "loss": 0.0135, "step": 219020 }, { "epoch": 52.58, "learning_rate": 4.991743990151017e-05, "loss": 0.0048, "step": 219030 }, { "epoch": 52.59, "learning_rate": 4.991385033548874e-05, "loss": 0.0167, "step": 219040 }, { "epoch": 52.59, "learning_rate": 4.991026076991131e-05, "loss": 0.004, "step": 219050 }, { "epoch": 52.59, "learning_rate": 4.990667120479642e-05, "loss": 0.0126, "step": 219060 }, { "epoch": 52.59, "learning_rate": 4.9903081640162526e-05, "loss": 0.0074, "step": 219070 }, { "epoch": 52.6, "learning_rate": 4.989949207602818e-05, "loss": 0.0078, "step": 219080 }, { "epoch": 52.6, "learning_rate": 4.989590251241184e-05, "loss": 0.0072, "step": 219090 }, { "epoch": 52.6, "learning_rate": 4.9892312949332006e-05, "loss": 0.0065, "step": 219100 }, { "epoch": 52.6, "learning_rate": 4.988872338680721e-05, "loss": 0.0046, "step": 219110 }, { "epoch": 52.6, "learning_rate": 4.9885133824855915e-05, "loss": 0.0038, "step": 219120 }, { "epoch": 52.61, "learning_rate": 4.988154426349666e-05, "loss": 0.0065, "step": 219130 }, { "epoch": 52.61, "learning_rate": 4.9877954702747905e-05, "loss": 0.0103, "step": 219140 }, { "epoch": 52.61, "learning_rate": 4.9874365142628194e-05, "loss": 0.007, "step": 219150 }, { "epoch": 52.61, "learning_rate": 4.9870775583155996e-05, "loss": 0.0079, "step": 219160 }, { "epoch": 52.62, "learning_rate": 4.986718602434983e-05, "loss": 0.0053, "step": 219170 }, { "epoch": 52.62, "learning_rate": 4.986359646622818e-05, "loss": 0.003, "step": 219180 }, { "epoch": 52.62, "learning_rate": 4.986000690880955e-05, "loss": 0.0035, "step": 219190 }, { "epoch": 52.62, "learning_rate": 4.9856417352112456e-05, "loss": 0.0045, "step": 219200 }, { "epoch": 52.62, "learning_rate": 4.985282779615537e-05, "loss": 0.0039, "step": 219210 }, { "epoch": 52.63, "learning_rate": 4.984923824095684e-05, "loss": 0.019, "step": 219220 }, { "epoch": 52.63, "learning_rate": 4.984564868653531e-05, "loss": 0.0053, "step": 219230 }, { "epoch": 52.63, "learning_rate": 4.984205913290933e-05, "loss": 0.0031, "step": 219240 }, { "epoch": 52.63, "learning_rate": 4.983846958009738e-05, "loss": 0.0033, "step": 219250 }, { "epoch": 52.64, "learning_rate": 4.9834880028117934e-05, "loss": 0.0066, "step": 219260 }, { "epoch": 52.64, "learning_rate": 4.9831290476989546e-05, "loss": 0.0077, "step": 219270 }, { "epoch": 52.64, "learning_rate": 4.982770092673066e-05, "loss": 0.0052, "step": 219280 }, { "epoch": 52.64, "learning_rate": 4.9824111377359825e-05, "loss": 0.0042, "step": 219290 }, { "epoch": 52.65, "learning_rate": 4.982052182889551e-05, "loss": 0.0037, "step": 219300 }, { "epoch": 52.65, "learning_rate": 4.9816932281356246e-05, "loss": 0.0047, "step": 219310 }, { "epoch": 52.65, "learning_rate": 4.98133427347605e-05, "loss": 0.0117, "step": 219320 }, { "epoch": 52.65, "learning_rate": 4.980975318912679e-05, "loss": 0.0114, "step": 219330 }, { "epoch": 52.65, "learning_rate": 4.9806163644473607e-05, "loss": 0.0069, "step": 219340 }, { "epoch": 52.66, "learning_rate": 4.980257410081946e-05, "loss": 0.0069, "step": 219350 }, { "epoch": 52.66, "learning_rate": 4.979898455818285e-05, "loss": 0.0069, "step": 219360 }, { "epoch": 52.66, "learning_rate": 4.979539501658226e-05, "loss": 0.0039, "step": 219370 }, { "epoch": 52.66, "learning_rate": 4.9791805476036244e-05, "loss": 0.0139, "step": 219380 }, { "epoch": 52.67, "learning_rate": 4.9788215936563245e-05, "loss": 0.0068, "step": 219390 }, { "epoch": 52.67, "learning_rate": 4.9784626398181775e-05, "loss": 0.0073, "step": 219400 }, { "epoch": 52.67, "learning_rate": 4.978103686091035e-05, "loss": 0.0059, "step": 219410 }, { "epoch": 52.67, "learning_rate": 4.977744732476745e-05, "loss": 0.0052, "step": 219420 }, { "epoch": 52.68, "learning_rate": 4.977385778977161e-05, "loss": 0.0044, "step": 219430 }, { "epoch": 52.68, "learning_rate": 4.977026825594129e-05, "loss": 0.0053, "step": 219440 }, { "epoch": 52.68, "learning_rate": 4.9766678723295026e-05, "loss": 0.0052, "step": 219450 }, { "epoch": 52.68, "learning_rate": 4.976308919185129e-05, "loss": 0.0066, "step": 219460 }, { "epoch": 52.68, "learning_rate": 4.9759499661628596e-05, "loss": 0.0064, "step": 219470 }, { "epoch": 52.69, "learning_rate": 4.9755910132645444e-05, "loss": 0.0052, "step": 219480 }, { "epoch": 52.69, "learning_rate": 4.975232060492033e-05, "loss": 0.0046, "step": 219490 }, { "epoch": 52.69, "learning_rate": 4.974873107847176e-05, "loss": 0.0044, "step": 219500 }, { "epoch": 52.69, "learning_rate": 4.974514155331822e-05, "loss": 0.0058, "step": 219510 }, { "epoch": 52.7, "learning_rate": 4.974155202947825e-05, "loss": 0.0069, "step": 219520 }, { "epoch": 52.7, "learning_rate": 4.973796250697031e-05, "loss": 0.0039, "step": 219530 }, { "epoch": 52.7, "learning_rate": 4.9734372985812905e-05, "loss": 0.0069, "step": 219540 }, { "epoch": 52.7, "learning_rate": 4.973078346602456e-05, "loss": 0.0032, "step": 219550 }, { "epoch": 52.7, "learning_rate": 4.972719394762374e-05, "loss": 0.0103, "step": 219560 }, { "epoch": 52.71, "learning_rate": 4.9723604430628986e-05, "loss": 0.0031, "step": 219570 }, { "epoch": 52.71, "learning_rate": 4.9720014915058756e-05, "loss": 0.0045, "step": 219580 }, { "epoch": 52.71, "learning_rate": 4.9716425400931586e-05, "loss": 0.0079, "step": 219590 }, { "epoch": 52.71, "learning_rate": 4.971283588826597e-05, "loss": 0.0036, "step": 219600 }, { "epoch": 52.72, "learning_rate": 4.970924637708037e-05, "loss": 0.0071, "step": 219610 }, { "epoch": 52.72, "learning_rate": 4.970565686739334e-05, "loss": 0.0061, "step": 219620 }, { "epoch": 52.72, "learning_rate": 4.970206735922335e-05, "loss": 0.007, "step": 219630 }, { "epoch": 52.72, "learning_rate": 4.96984778525889e-05, "loss": 0.005, "step": 219640 }, { "epoch": 52.73, "learning_rate": 4.969488834750851e-05, "loss": 0.005, "step": 219650 }, { "epoch": 52.73, "learning_rate": 4.969129884400066e-05, "loss": 0.0047, "step": 219660 }, { "epoch": 52.73, "learning_rate": 4.968770934208388e-05, "loss": 0.0055, "step": 219670 }, { "epoch": 52.73, "learning_rate": 4.968411984177662e-05, "loss": 0.0033, "step": 219680 }, { "epoch": 52.73, "learning_rate": 4.9680530343097426e-05, "loss": 0.0081, "step": 219690 }, { "epoch": 52.74, "learning_rate": 4.967694084606476e-05, "loss": 0.0046, "step": 219700 }, { "epoch": 52.74, "learning_rate": 4.967335135069717e-05, "loss": 0.0051, "step": 219710 }, { "epoch": 52.74, "learning_rate": 4.9669761857013106e-05, "loss": 0.0117, "step": 219720 }, { "epoch": 52.74, "learning_rate": 4.966617236503112e-05, "loss": 0.0052, "step": 219730 }, { "epoch": 52.75, "learning_rate": 4.966258287476968e-05, "loss": 0.0042, "step": 219740 }, { "epoch": 52.75, "learning_rate": 4.965899338624727e-05, "loss": 0.0061, "step": 219750 }, { "epoch": 52.75, "learning_rate": 4.965540389948242e-05, "loss": 0.0063, "step": 219760 }, { "epoch": 52.75, "learning_rate": 4.965181441449361e-05, "loss": 0.0052, "step": 219770 }, { "epoch": 52.76, "learning_rate": 4.964822493129937e-05, "loss": 0.0071, "step": 219780 }, { "epoch": 52.76, "learning_rate": 4.964463544991817e-05, "loss": 0.0056, "step": 219790 }, { "epoch": 52.76, "learning_rate": 4.9641045970368525e-05, "loss": 0.0041, "step": 219800 }, { "epoch": 52.76, "learning_rate": 4.963745649266895e-05, "loss": 0.0087, "step": 219810 }, { "epoch": 52.76, "learning_rate": 4.96338670168379e-05, "loss": 0.0073, "step": 219820 }, { "epoch": 52.77, "learning_rate": 4.9630277542893925e-05, "loss": 0.0126, "step": 219830 }, { "epoch": 52.77, "learning_rate": 4.9626688070855476e-05, "loss": 0.0046, "step": 219840 }, { "epoch": 52.77, "learning_rate": 4.96230986007411e-05, "loss": 0.0031, "step": 219850 }, { "epoch": 52.77, "learning_rate": 4.961950913256926e-05, "loss": 0.0052, "step": 219860 }, { "epoch": 52.78, "learning_rate": 4.96159196663585e-05, "loss": 0.0061, "step": 219870 }, { "epoch": 52.78, "learning_rate": 4.961233020212729e-05, "loss": 0.0058, "step": 219880 }, { "epoch": 52.78, "learning_rate": 4.96087407398941e-05, "loss": 0.0055, "step": 219890 }, { "epoch": 52.78, "learning_rate": 4.96051512796775e-05, "loss": 0.0046, "step": 219900 }, { "epoch": 52.78, "learning_rate": 4.960156182149593e-05, "loss": 0.0044, "step": 219910 }, { "epoch": 52.79, "learning_rate": 4.959797236536793e-05, "loss": 0.0037, "step": 219920 }, { "epoch": 52.79, "learning_rate": 4.9594382911311965e-05, "loss": 0.0036, "step": 219930 }, { "epoch": 52.79, "learning_rate": 4.959079345934657e-05, "loss": 0.007, "step": 219940 }, { "epoch": 52.79, "learning_rate": 4.958720400949023e-05, "loss": 0.0039, "step": 219950 }, { "epoch": 52.8, "learning_rate": 4.958361456176143e-05, "loss": 0.0031, "step": 219960 }, { "epoch": 52.8, "learning_rate": 4.9580025116178705e-05, "loss": 0.0064, "step": 219970 }, { "epoch": 52.8, "learning_rate": 4.9576435672760503e-05, "loss": 0.0039, "step": 219980 }, { "epoch": 52.8, "learning_rate": 4.9572846231525384e-05, "loss": 0.0083, "step": 219990 }, { "epoch": 52.81, "learning_rate": 4.95692567924918e-05, "loss": 0.0035, "step": 220000 }, { "epoch": 52.81, "learning_rate": 4.9565667355678284e-05, "loss": 0.0048, "step": 220010 }, { "epoch": 52.81, "learning_rate": 4.95620779211033e-05, "loss": 0.006, "step": 220020 }, { "epoch": 52.81, "learning_rate": 4.95584884887854e-05, "loss": 0.006, "step": 220030 }, { "epoch": 52.81, "learning_rate": 4.9554899058743056e-05, "loss": 0.0042, "step": 220040 }, { "epoch": 52.82, "learning_rate": 4.955130963099473e-05, "loss": 0.0073, "step": 220050 }, { "epoch": 52.82, "learning_rate": 4.9547720205558994e-05, "loss": 0.0037, "step": 220060 }, { "epoch": 52.82, "learning_rate": 4.954413078245428e-05, "loss": 0.0077, "step": 220070 }, { "epoch": 52.82, "learning_rate": 4.954054136169914e-05, "loss": 0.0037, "step": 220080 }, { "epoch": 52.83, "learning_rate": 4.953695194331205e-05, "loss": 0.0038, "step": 220090 }, { "epoch": 52.83, "learning_rate": 4.953336252731151e-05, "loss": 0.0066, "step": 220100 }, { "epoch": 52.83, "learning_rate": 4.952977311371604e-05, "loss": 0.0037, "step": 220110 }, { "epoch": 52.83, "learning_rate": 4.9526183702544096e-05, "loss": 0.0061, "step": 220120 }, { "epoch": 52.84, "learning_rate": 4.952259429381423e-05, "loss": 0.0038, "step": 220130 }, { "epoch": 52.84, "learning_rate": 4.9519004887544896e-05, "loss": 0.0038, "step": 220140 }, { "epoch": 52.84, "learning_rate": 4.9515415483754636e-05, "loss": 0.0039, "step": 220150 }, { "epoch": 52.84, "learning_rate": 4.9511826082461904e-05, "loss": 0.0029, "step": 220160 }, { "epoch": 52.84, "learning_rate": 4.950823668368525e-05, "loss": 0.0066, "step": 220170 }, { "epoch": 52.85, "learning_rate": 4.950464728744315e-05, "loss": 0.0067, "step": 220180 }, { "epoch": 52.85, "learning_rate": 4.9501057893754074e-05, "loss": 0.0071, "step": 220190 }, { "epoch": 52.85, "learning_rate": 4.949746850263657e-05, "loss": 0.0035, "step": 220200 }, { "epoch": 52.85, "learning_rate": 4.949387911410911e-05, "loss": 0.0045, "step": 220210 }, { "epoch": 52.86, "learning_rate": 4.9490289728190206e-05, "loss": 0.0027, "step": 220220 }, { "epoch": 52.86, "learning_rate": 4.948670034489834e-05, "loss": 0.0034, "step": 220230 }, { "epoch": 52.86, "learning_rate": 4.9483110964252036e-05, "loss": 0.0034, "step": 220240 }, { "epoch": 52.86, "learning_rate": 4.947952158626979e-05, "loss": 0.0042, "step": 220250 }, { "epoch": 52.86, "learning_rate": 4.947593221097007e-05, "loss": 0.0041, "step": 220260 }, { "epoch": 52.87, "learning_rate": 4.9472342838371424e-05, "loss": 0.0046, "step": 220270 }, { "epoch": 52.87, "learning_rate": 4.9468753468492305e-05, "loss": 0.0049, "step": 220280 }, { "epoch": 52.87, "learning_rate": 4.946516410135126e-05, "loss": 0.0039, "step": 220290 }, { "epoch": 52.87, "learning_rate": 4.9461574736966745e-05, "loss": 0.0086, "step": 220300 }, { "epoch": 52.88, "learning_rate": 4.9457985375357296e-05, "loss": 0.005, "step": 220310 }, { "epoch": 52.88, "learning_rate": 4.9454396016541396e-05, "loss": 0.0078, "step": 220320 }, { "epoch": 52.88, "learning_rate": 4.9450806660537516e-05, "loss": 0.0086, "step": 220330 }, { "epoch": 52.88, "learning_rate": 4.944721730736421e-05, "loss": 0.0028, "step": 220340 }, { "epoch": 52.89, "learning_rate": 4.944362795703993e-05, "loss": 0.0085, "step": 220350 }, { "epoch": 52.89, "learning_rate": 4.944003860958321e-05, "loss": 0.0037, "step": 220360 }, { "epoch": 52.89, "learning_rate": 4.943644926501253e-05, "loss": 0.0036, "step": 220370 }, { "epoch": 52.89, "learning_rate": 4.9432859923346394e-05, "loss": 0.0065, "step": 220380 }, { "epoch": 52.89, "learning_rate": 4.942927058460331e-05, "loss": 0.0073, "step": 220390 }, { "epoch": 52.9, "learning_rate": 4.942568124880175e-05, "loss": 0.0058, "step": 220400 }, { "epoch": 52.9, "learning_rate": 4.9422091915960265e-05, "loss": 0.0046, "step": 220410 }, { "epoch": 52.9, "learning_rate": 4.941850258609729e-05, "loss": 0.004, "step": 220420 }, { "epoch": 52.9, "learning_rate": 4.9414913259231387e-05, "loss": 0.0041, "step": 220430 }, { "epoch": 52.91, "learning_rate": 4.9411323935381006e-05, "loss": 0.0049, "step": 220440 }, { "epoch": 52.91, "learning_rate": 4.9407734614564685e-05, "loss": 0.0037, "step": 220450 }, { "epoch": 52.91, "learning_rate": 4.94041452968009e-05, "loss": 0.0062, "step": 220460 }, { "epoch": 52.91, "learning_rate": 4.940055598210814e-05, "loss": 0.0075, "step": 220470 }, { "epoch": 52.91, "learning_rate": 4.9396966670504934e-05, "loss": 0.0041, "step": 220480 }, { "epoch": 52.92, "learning_rate": 4.939337736200975e-05, "loss": 0.0034, "step": 220490 }, { "epoch": 52.92, "learning_rate": 4.938978805664113e-05, "loss": 0.0042, "step": 220500 }, { "epoch": 52.92, "learning_rate": 4.938619875441752e-05, "loss": 0.0033, "step": 220510 }, { "epoch": 52.92, "learning_rate": 4.938260945535747e-05, "loss": 0.004, "step": 220520 }, { "epoch": 52.93, "learning_rate": 4.937902015947944e-05, "loss": 0.0035, "step": 220530 }, { "epoch": 52.93, "learning_rate": 4.9375430866801955e-05, "loss": 0.0043, "step": 220540 }, { "epoch": 52.93, "learning_rate": 4.93718415773435e-05, "loss": 0.0061, "step": 220550 }, { "epoch": 52.93, "learning_rate": 4.936825229112256e-05, "loss": 0.005, "step": 220560 }, { "epoch": 52.94, "learning_rate": 4.9364663008157683e-05, "loss": 0.0047, "step": 220570 }, { "epoch": 52.94, "learning_rate": 4.936107372846732e-05, "loss": 0.0095, "step": 220580 }, { "epoch": 52.94, "learning_rate": 4.935748445207001e-05, "loss": 0.0048, "step": 220590 }, { "epoch": 52.94, "learning_rate": 4.935389517898422e-05, "loss": 0.0171, "step": 220600 }, { "epoch": 52.94, "learning_rate": 4.935030590922844e-05, "loss": 0.003, "step": 220610 }, { "epoch": 52.95, "learning_rate": 4.934671664282122e-05, "loss": 0.0055, "step": 220620 }, { "epoch": 52.95, "learning_rate": 4.9343127379781004e-05, "loss": 0.0057, "step": 220630 }, { "epoch": 53.0, "learning_rate": 4.9339538120126336e-05, "loss": 0.0028, "step": 220640 }, { "epoch": 53.0, "learning_rate": 4.933594886387566e-05, "loss": 0.0059, "step": 220650 }, { "epoch": 53.0, "learning_rate": 4.9332359611047545e-05, "loss": 0.006, "step": 220660 }, { "epoch": 53.01, "learning_rate": 4.932877036166044e-05, "loss": 0.0046, "step": 220670 }, { "epoch": 53.01, "learning_rate": 4.932518111573286e-05, "loss": 0.0046, "step": 220680 }, { "epoch": 53.01, "learning_rate": 4.93215918732833e-05, "loss": 0.0036, "step": 220690 }, { "epoch": 53.01, "learning_rate": 4.931800263433026e-05, "loss": 0.0032, "step": 220700 }, { "epoch": 53.02, "learning_rate": 4.931441339889224e-05, "loss": 0.003, "step": 220710 }, { "epoch": 53.02, "learning_rate": 4.931082416698772e-05, "loss": 0.0049, "step": 220720 }, { "epoch": 53.02, "learning_rate": 4.930723493863525e-05, "loss": 0.0036, "step": 220730 }, { "epoch": 53.02, "learning_rate": 4.93036457138533e-05, "loss": 0.0069, "step": 220740 }, { "epoch": 53.03, "learning_rate": 4.930005649266034e-05, "loss": 0.0053, "step": 220750 }, { "epoch": 53.03, "learning_rate": 4.929646727507491e-05, "loss": 0.007, "step": 220760 }, { "epoch": 53.03, "learning_rate": 4.9292878061115484e-05, "loss": 0.0039, "step": 220770 }, { "epoch": 53.03, "learning_rate": 4.928928885080059e-05, "loss": 0.0056, "step": 220780 }, { "epoch": 53.03, "learning_rate": 4.9285699644148674e-05, "loss": 0.0043, "step": 220790 }, { "epoch": 53.04, "learning_rate": 4.92821104411783e-05, "loss": 0.0043, "step": 220800 }, { "epoch": 53.04, "learning_rate": 4.9278521241907924e-05, "loss": 0.0035, "step": 220810 }, { "epoch": 53.04, "learning_rate": 4.9274932046356045e-05, "loss": 0.0035, "step": 220820 }, { "epoch": 53.04, "learning_rate": 4.927134285454119e-05, "loss": 0.0028, "step": 220830 }, { "epoch": 53.05, "learning_rate": 4.9267753666481824e-05, "loss": 0.0059, "step": 220840 }, { "epoch": 53.05, "learning_rate": 4.9264164482196467e-05, "loss": 0.004, "step": 220850 }, { "epoch": 53.05, "learning_rate": 4.9260575301703614e-05, "loss": 0.0039, "step": 220860 }, { "epoch": 53.05, "learning_rate": 4.925698612502176e-05, "loss": 0.0033, "step": 220870 }, { "epoch": 53.06, "learning_rate": 4.9253396952169395e-05, "loss": 0.0034, "step": 220880 }, { "epoch": 53.06, "learning_rate": 4.9249807783165053e-05, "loss": 0.0051, "step": 220890 }, { "epoch": 53.06, "learning_rate": 4.924621861802721e-05, "loss": 0.0059, "step": 220900 }, { "epoch": 53.06, "learning_rate": 4.924262945677433e-05, "loss": 0.0073, "step": 220910 }, { "epoch": 53.06, "learning_rate": 4.923904029942498e-05, "loss": 0.0033, "step": 220920 }, { "epoch": 53.07, "learning_rate": 4.923545114599759e-05, "loss": 0.0043, "step": 220930 }, { "epoch": 53.07, "learning_rate": 4.9231861996510714e-05, "loss": 0.0054, "step": 220940 }, { "epoch": 53.07, "learning_rate": 4.922827285098281e-05, "loss": 0.0049, "step": 220950 }, { "epoch": 53.07, "learning_rate": 4.9224683709432414e-05, "loss": 0.011, "step": 220960 }, { "epoch": 53.08, "learning_rate": 4.922109457187799e-05, "loss": 0.0055, "step": 220970 }, { "epoch": 53.08, "learning_rate": 4.921750543833806e-05, "loss": 0.0035, "step": 220980 }, { "epoch": 53.08, "learning_rate": 4.921391630883111e-05, "loss": 0.0039, "step": 220990 }, { "epoch": 53.08, "learning_rate": 4.921032718337564e-05, "loss": 0.0031, "step": 221000 }, { "epoch": 53.08, "learning_rate": 4.920673806199015e-05, "loss": 0.0069, "step": 221010 }, { "epoch": 53.09, "learning_rate": 4.920314894469314e-05, "loss": 0.0089, "step": 221020 }, { "epoch": 53.09, "learning_rate": 4.91995598315031e-05, "loss": 0.0057, "step": 221030 }, { "epoch": 53.09, "learning_rate": 4.919597072243856e-05, "loss": 0.0063, "step": 221040 }, { "epoch": 53.09, "learning_rate": 4.919238161751796e-05, "loss": 0.0049, "step": 221050 }, { "epoch": 53.1, "learning_rate": 4.918879251675986e-05, "loss": 0.0039, "step": 221060 }, { "epoch": 53.1, "learning_rate": 4.918520342018271e-05, "loss": 0.0031, "step": 221070 }, { "epoch": 53.1, "learning_rate": 4.918161432780504e-05, "loss": 0.0043, "step": 221080 }, { "epoch": 53.1, "learning_rate": 4.9178025239645324e-05, "loss": 0.0044, "step": 221090 }, { "epoch": 53.11, "learning_rate": 4.9174436155722094e-05, "loss": 0.0089, "step": 221100 }, { "epoch": 53.11, "learning_rate": 4.917084707605383e-05, "loss": 0.0052, "step": 221110 }, { "epoch": 53.11, "learning_rate": 4.9167258000658996e-05, "loss": 0.0043, "step": 221120 }, { "epoch": 53.11, "learning_rate": 4.916366892955614e-05, "loss": 0.0039, "step": 221130 }, { "epoch": 53.11, "learning_rate": 4.916007986276374e-05, "loss": 0.004, "step": 221140 }, { "epoch": 53.12, "learning_rate": 4.9156490800300285e-05, "loss": 0.0043, "step": 221150 }, { "epoch": 53.12, "learning_rate": 4.915290174218429e-05, "loss": 0.0047, "step": 221160 }, { "epoch": 53.12, "learning_rate": 4.9149312688434254e-05, "loss": 0.0081, "step": 221170 }, { "epoch": 53.12, "learning_rate": 4.9145723639068675e-05, "loss": 0.004, "step": 221180 }, { "epoch": 53.13, "learning_rate": 4.9142134594106014e-05, "loss": 0.0034, "step": 221190 }, { "epoch": 53.13, "learning_rate": 4.913854555356483e-05, "loss": 0.0028, "step": 221200 }, { "epoch": 53.13, "learning_rate": 4.913495651746356e-05, "loss": 0.004, "step": 221210 }, { "epoch": 53.13, "learning_rate": 4.913136748582075e-05, "loss": 0.0053, "step": 221220 }, { "epoch": 53.14, "learning_rate": 4.912777845865487e-05, "loss": 0.007, "step": 221230 }, { "epoch": 53.14, "learning_rate": 4.912418943598445e-05, "loss": 0.0026, "step": 221240 }, { "epoch": 53.14, "learning_rate": 4.9120600417827955e-05, "loss": 0.0039, "step": 221250 }, { "epoch": 53.14, "learning_rate": 4.911701140420387e-05, "loss": 0.0028, "step": 221260 }, { "epoch": 53.14, "learning_rate": 4.911342239513074e-05, "loss": 0.0029, "step": 221270 }, { "epoch": 53.15, "learning_rate": 4.910983339062702e-05, "loss": 0.0025, "step": 221280 }, { "epoch": 53.15, "learning_rate": 4.9106244390711234e-05, "loss": 0.0034, "step": 221290 }, { "epoch": 53.15, "learning_rate": 4.9102655395401875e-05, "loss": 0.0038, "step": 221300 }, { "epoch": 53.15, "learning_rate": 4.909906640471744e-05, "loss": 0.0163, "step": 221310 }, { "epoch": 53.16, "learning_rate": 4.909547741867642e-05, "loss": 0.0046, "step": 221320 }, { "epoch": 53.16, "learning_rate": 4.909188843729731e-05, "loss": 0.0049, "step": 221330 }, { "epoch": 53.16, "learning_rate": 4.908829946059863e-05, "loss": 0.0068, "step": 221340 }, { "epoch": 53.16, "learning_rate": 4.908471048859885e-05, "loss": 0.0052, "step": 221350 }, { "epoch": 53.16, "learning_rate": 4.908112152131649e-05, "loss": 0.0056, "step": 221360 }, { "epoch": 53.17, "learning_rate": 4.907753255877002e-05, "loss": 0.0037, "step": 221370 }, { "epoch": 53.17, "learning_rate": 4.9073943600977976e-05, "loss": 0.0059, "step": 221380 }, { "epoch": 53.17, "learning_rate": 4.907035464795883e-05, "loss": 0.0048, "step": 221390 }, { "epoch": 53.17, "learning_rate": 4.906676569973107e-05, "loss": 0.008, "step": 221400 }, { "epoch": 53.18, "learning_rate": 4.906317675631323e-05, "loss": 0.0111, "step": 221410 }, { "epoch": 53.18, "learning_rate": 4.9059587817723755e-05, "loss": 0.0044, "step": 221420 }, { "epoch": 53.18, "learning_rate": 4.9055998883981196e-05, "loss": 0.0041, "step": 221430 }, { "epoch": 53.18, "learning_rate": 4.905240995510401e-05, "loss": 0.0036, "step": 221440 }, { "epoch": 53.19, "learning_rate": 4.904882103111072e-05, "loss": 0.0031, "step": 221450 }, { "epoch": 53.19, "learning_rate": 4.9045232112019826e-05, "loss": 0.0043, "step": 221460 }, { "epoch": 53.19, "learning_rate": 4.9041643197849786e-05, "loss": 0.0058, "step": 221470 }, { "epoch": 53.19, "learning_rate": 4.903805428861915e-05, "loss": 0.0034, "step": 221480 }, { "epoch": 53.19, "learning_rate": 4.903446538434637e-05, "loss": 0.0388, "step": 221490 }, { "epoch": 53.2, "learning_rate": 4.903087648504998e-05, "loss": 0.0093, "step": 221500 }, { "epoch": 53.2, "learning_rate": 4.902728759074845e-05, "loss": 0.0035, "step": 221510 }, { "epoch": 53.2, "learning_rate": 4.9023698701460304e-05, "loss": 0.0038, "step": 221520 }, { "epoch": 53.2, "learning_rate": 4.902010981720402e-05, "loss": 0.004, "step": 221530 }, { "epoch": 53.21, "learning_rate": 4.901652093799808e-05, "loss": 0.007, "step": 221540 }, { "epoch": 53.21, "learning_rate": 4.901293206386102e-05, "loss": 0.0055, "step": 221550 }, { "epoch": 53.21, "learning_rate": 4.900934319481129e-05, "loss": 0.0073, "step": 221560 }, { "epoch": 53.21, "learning_rate": 4.900575433086744e-05, "loss": 0.0047, "step": 221570 }, { "epoch": 53.22, "learning_rate": 4.900216547204792e-05, "loss": 0.0099, "step": 221580 }, { "epoch": 53.22, "learning_rate": 4.899857661837127e-05, "loss": 0.0332, "step": 221590 }, { "epoch": 53.22, "learning_rate": 4.8994987769855946e-05, "loss": 0.0037, "step": 221600 }, { "epoch": 53.22, "learning_rate": 4.899139892652046e-05, "loss": 0.0045, "step": 221610 }, { "epoch": 53.22, "learning_rate": 4.898781008838333e-05, "loss": 0.0053, "step": 221620 }, { "epoch": 53.23, "learning_rate": 4.898422125546301e-05, "loss": 0.0026, "step": 221630 }, { "epoch": 53.23, "learning_rate": 4.8980632427778056e-05, "loss": 0.0063, "step": 221640 }, { "epoch": 53.23, "learning_rate": 4.89770436053469e-05, "loss": 0.0083, "step": 221650 }, { "epoch": 53.23, "learning_rate": 4.897345478818809e-05, "loss": 0.0038, "step": 221660 }, { "epoch": 53.24, "learning_rate": 4.896986597632009e-05, "loss": 0.0066, "step": 221670 }, { "epoch": 53.24, "learning_rate": 4.8966277169761425e-05, "loss": 0.0028, "step": 221680 }, { "epoch": 53.24, "learning_rate": 4.8962688368530576e-05, "loss": 0.0061, "step": 221690 }, { "epoch": 53.24, "learning_rate": 4.895909957264602e-05, "loss": 0.0034, "step": 221700 }, { "epoch": 53.24, "learning_rate": 4.895551078212629e-05, "loss": 0.0042, "step": 221710 }, { "epoch": 53.25, "learning_rate": 4.895192199698985e-05, "loss": 0.0046, "step": 221720 }, { "epoch": 53.25, "learning_rate": 4.894833321725524e-05, "loss": 0.0269, "step": 221730 }, { "epoch": 53.25, "learning_rate": 4.894474444294089e-05, "loss": 0.0031, "step": 221740 }, { "epoch": 53.25, "learning_rate": 4.8941155674065365e-05, "loss": 0.0029, "step": 221750 }, { "epoch": 53.26, "learning_rate": 4.893756691064714e-05, "loss": 0.0032, "step": 221760 }, { "epoch": 53.26, "learning_rate": 4.8933978152704674e-05, "loss": 0.0066, "step": 221770 }, { "epoch": 53.26, "learning_rate": 4.893038940025652e-05, "loss": 0.0069, "step": 221780 }, { "epoch": 53.26, "learning_rate": 4.892680065332113e-05, "loss": 0.0044, "step": 221790 }, { "epoch": 53.27, "learning_rate": 4.8923211911917036e-05, "loss": 0.0031, "step": 221800 }, { "epoch": 53.27, "learning_rate": 4.891962317606269e-05, "loss": 0.0036, "step": 221810 }, { "epoch": 53.27, "learning_rate": 4.8916034445776645e-05, "loss": 0.0044, "step": 221820 }, { "epoch": 53.27, "learning_rate": 4.891244572107736e-05, "loss": 0.0059, "step": 221830 }, { "epoch": 53.27, "learning_rate": 4.890885700198332e-05, "loss": 0.0062, "step": 221840 }, { "epoch": 53.28, "learning_rate": 4.890526828851307e-05, "loss": 0.0119, "step": 221850 }, { "epoch": 53.28, "learning_rate": 4.8901679580685045e-05, "loss": 0.0032, "step": 221860 }, { "epoch": 53.28, "learning_rate": 4.88980908785178e-05, "loss": 0.0049, "step": 221870 }, { "epoch": 53.28, "learning_rate": 4.8894502182029775e-05, "loss": 0.0043, "step": 221880 }, { "epoch": 53.29, "learning_rate": 4.889091349123952e-05, "loss": 0.0033, "step": 221890 }, { "epoch": 53.29, "learning_rate": 4.88873248061655e-05, "loss": 0.006, "step": 221900 }, { "epoch": 53.29, "learning_rate": 4.88837361268262e-05, "loss": 0.0055, "step": 221910 }, { "epoch": 53.29, "learning_rate": 4.888014745324016e-05, "loss": 0.0037, "step": 221920 }, { "epoch": 53.3, "learning_rate": 4.8876558785425826e-05, "loss": 0.0037, "step": 221930 }, { "epoch": 53.3, "learning_rate": 4.887297012340174e-05, "loss": 0.0044, "step": 221940 }, { "epoch": 53.3, "learning_rate": 4.8869381467186346e-05, "loss": 0.0025, "step": 221950 }, { "epoch": 53.3, "learning_rate": 4.88657928167982e-05, "loss": 0.0047, "step": 221960 }, { "epoch": 53.3, "learning_rate": 4.886220417225576e-05, "loss": 0.006, "step": 221970 }, { "epoch": 53.31, "learning_rate": 4.885861553357752e-05, "loss": 0.0035, "step": 221980 }, { "epoch": 53.31, "learning_rate": 4.8855026900781996e-05, "loss": 0.0045, "step": 221990 }, { "epoch": 53.31, "learning_rate": 4.885143827388766e-05, "loss": 0.003, "step": 222000 }, { "epoch": 53.31, "learning_rate": 4.884784965291304e-05, "loss": 0.0085, "step": 222010 }, { "epoch": 53.32, "learning_rate": 4.8844261037876585e-05, "loss": 0.0052, "step": 222020 }, { "epoch": 53.32, "learning_rate": 4.884067242879684e-05, "loss": 0.0066, "step": 222030 }, { "epoch": 53.32, "learning_rate": 4.883708382569227e-05, "loss": 0.0021, "step": 222040 }, { "epoch": 53.32, "learning_rate": 4.883349522858138e-05, "loss": 0.0047, "step": 222050 }, { "epoch": 53.32, "learning_rate": 4.882990663748266e-05, "loss": 0.0053, "step": 222060 }, { "epoch": 53.33, "learning_rate": 4.882631805241461e-05, "loss": 0.007, "step": 222070 }, { "epoch": 53.33, "learning_rate": 4.8822729473395745e-05, "loss": 0.003, "step": 222080 }, { "epoch": 53.33, "learning_rate": 4.881914090044452e-05, "loss": 0.0022, "step": 222090 }, { "epoch": 53.33, "learning_rate": 4.8815552333579473e-05, "loss": 0.005, "step": 222100 }, { "epoch": 53.34, "learning_rate": 4.881196377281908e-05, "loss": 0.0024, "step": 222110 }, { "epoch": 53.34, "learning_rate": 4.880837521818182e-05, "loss": 0.0036, "step": 222120 }, { "epoch": 53.34, "learning_rate": 4.8804786669686216e-05, "loss": 0.0034, "step": 222130 }, { "epoch": 53.34, "learning_rate": 4.880119812735073e-05, "loss": 0.0069, "step": 222140 }, { "epoch": 53.35, "learning_rate": 4.87976095911939e-05, "loss": 0.0029, "step": 222150 }, { "epoch": 53.35, "learning_rate": 4.879402106123419e-05, "loss": 0.0047, "step": 222160 }, { "epoch": 53.35, "learning_rate": 4.8790432537490124e-05, "loss": 0.0059, "step": 222170 }, { "epoch": 53.35, "learning_rate": 4.878684401998016e-05, "loss": 0.0025, "step": 222180 }, { "epoch": 53.35, "learning_rate": 4.878325550872281e-05, "loss": 0.0054, "step": 222190 }, { "epoch": 53.36, "learning_rate": 4.877966700373659e-05, "loss": 0.0053, "step": 222200 }, { "epoch": 53.36, "learning_rate": 4.8776078505039954e-05, "loss": 0.0056, "step": 222210 }, { "epoch": 53.36, "learning_rate": 4.8772490012651433e-05, "loss": 0.0047, "step": 222220 }, { "epoch": 53.36, "learning_rate": 4.8768901526589497e-05, "loss": 0.0034, "step": 222230 }, { "epoch": 53.37, "learning_rate": 4.876531304687267e-05, "loss": 0.0091, "step": 222240 }, { "epoch": 53.37, "learning_rate": 4.876172457351943e-05, "loss": 0.0043, "step": 222250 }, { "epoch": 53.37, "learning_rate": 4.875813610654825e-05, "loss": 0.0051, "step": 222260 }, { "epoch": 53.37, "learning_rate": 4.8754547645977674e-05, "loss": 0.0042, "step": 222270 }, { "epoch": 53.38, "learning_rate": 4.875095919182614e-05, "loss": 0.005, "step": 222280 }, { "epoch": 53.38, "learning_rate": 4.87473707441122e-05, "loss": 0.0054, "step": 222290 }, { "epoch": 53.38, "learning_rate": 4.87437823028543e-05, "loss": 0.0034, "step": 222300 }, { "epoch": 53.38, "learning_rate": 4.8740193868070974e-05, "loss": 0.0035, "step": 222310 }, { "epoch": 53.38, "learning_rate": 4.8736605439780696e-05, "loss": 0.0076, "step": 222320 }, { "epoch": 53.39, "learning_rate": 4.873301701800196e-05, "loss": 0.0069, "step": 222330 }, { "epoch": 53.39, "learning_rate": 4.8729428602753265e-05, "loss": 0.0039, "step": 222340 }, { "epoch": 53.39, "learning_rate": 4.87258401940531e-05, "loss": 0.0038, "step": 222350 }, { "epoch": 53.39, "learning_rate": 4.8722251791919975e-05, "loss": 0.0084, "step": 222360 }, { "epoch": 53.4, "learning_rate": 4.871866339637237e-05, "loss": 0.0061, "step": 222370 }, { "epoch": 53.4, "learning_rate": 4.8715075007428786e-05, "loss": 0.0065, "step": 222380 }, { "epoch": 53.4, "learning_rate": 4.8711486625107724e-05, "loss": 0.0048, "step": 222390 }, { "epoch": 53.4, "learning_rate": 4.870789824942765e-05, "loss": 0.0036, "step": 222400 }, { "epoch": 53.4, "learning_rate": 4.870430988040711e-05, "loss": 0.0064, "step": 222410 }, { "epoch": 53.41, "learning_rate": 4.870072151806454e-05, "loss": 0.004, "step": 222420 }, { "epoch": 53.41, "learning_rate": 4.8697133162418475e-05, "loss": 0.0027, "step": 222430 }, { "epoch": 53.41, "learning_rate": 4.869354481348738e-05, "loss": 0.009, "step": 222440 }, { "epoch": 53.41, "learning_rate": 4.8689956471289785e-05, "loss": 0.0065, "step": 222450 }, { "epoch": 53.42, "learning_rate": 4.868636813584415e-05, "loss": 0.0051, "step": 222460 }, { "epoch": 53.42, "learning_rate": 4.868277980716901e-05, "loss": 0.013, "step": 222470 }, { "epoch": 53.42, "learning_rate": 4.8679191485282816e-05, "loss": 0.0043, "step": 222480 }, { "epoch": 53.42, "learning_rate": 4.867560317020408e-05, "loss": 0.0057, "step": 222490 }, { "epoch": 53.43, "learning_rate": 4.86720148619513e-05, "loss": 0.007, "step": 222500 }, { "epoch": 53.43, "learning_rate": 4.866842656054296e-05, "loss": 0.0035, "step": 222510 }, { "epoch": 53.43, "learning_rate": 4.866483826599757e-05, "loss": 0.0085, "step": 222520 }, { "epoch": 53.43, "learning_rate": 4.8661249978333606e-05, "loss": 0.0046, "step": 222530 }, { "epoch": 53.43, "learning_rate": 4.865766169756957e-05, "loss": 0.0088, "step": 222540 }, { "epoch": 53.44, "learning_rate": 4.865407342372398e-05, "loss": 0.0053, "step": 222550 }, { "epoch": 53.44, "learning_rate": 4.865048515681527e-05, "loss": 0.0055, "step": 222560 }, { "epoch": 53.44, "learning_rate": 4.8646896896862004e-05, "loss": 0.0035, "step": 222570 }, { "epoch": 53.44, "learning_rate": 4.8643308643882616e-05, "loss": 0.0032, "step": 222580 }, { "epoch": 53.45, "learning_rate": 4.863972039789565e-05, "loss": 0.006, "step": 222590 }, { "epoch": 53.45, "learning_rate": 4.863613215891956e-05, "loss": 0.003, "step": 222600 }, { "epoch": 53.45, "learning_rate": 4.863254392697287e-05, "loss": 0.0028, "step": 222610 }, { "epoch": 53.45, "learning_rate": 4.862895570207406e-05, "loss": 0.0029, "step": 222620 }, { "epoch": 53.45, "learning_rate": 4.86253674842416e-05, "loss": 0.0108, "step": 222630 }, { "epoch": 53.46, "learning_rate": 4.862177927349402e-05, "loss": 0.0071, "step": 222640 }, { "epoch": 53.46, "learning_rate": 4.86181910698498e-05, "loss": 0.0057, "step": 222650 }, { "epoch": 53.46, "learning_rate": 4.8614602873327444e-05, "loss": 0.0027, "step": 222660 }, { "epoch": 53.46, "learning_rate": 4.861101468394543e-05, "loss": 0.0057, "step": 222670 }, { "epoch": 53.47, "learning_rate": 4.8607426501722256e-05, "loss": 0.003, "step": 222680 }, { "epoch": 53.47, "learning_rate": 4.860383832667644e-05, "loss": 0.0057, "step": 222690 }, { "epoch": 53.47, "learning_rate": 4.8600250158826416e-05, "loss": 0.0026, "step": 222700 }, { "epoch": 53.47, "learning_rate": 4.859666199819075e-05, "loss": 0.005, "step": 222710 }, { "epoch": 53.48, "learning_rate": 4.859307384478786e-05, "loss": 0.0116, "step": 222720 }, { "epoch": 53.48, "learning_rate": 4.858948569863632e-05, "loss": 0.005, "step": 222730 }, { "epoch": 53.48, "learning_rate": 4.8585897559754544e-05, "loss": 0.0049, "step": 222740 }, { "epoch": 53.48, "learning_rate": 4.8582309428161096e-05, "loss": 0.005, "step": 222750 }, { "epoch": 53.48, "learning_rate": 4.857872130387444e-05, "loss": 0.0098, "step": 222760 }, { "epoch": 53.49, "learning_rate": 4.857513318691303e-05, "loss": 0.0041, "step": 222770 }, { "epoch": 53.49, "learning_rate": 4.8571545077295426e-05, "loss": 0.0056, "step": 222780 }, { "epoch": 53.49, "learning_rate": 4.856795697504007e-05, "loss": 0.0056, "step": 222790 }, { "epoch": 53.49, "learning_rate": 4.856436888016549e-05, "loss": 0.0028, "step": 222800 }, { "epoch": 53.5, "learning_rate": 4.8560780792690156e-05, "loss": 0.0047, "step": 222810 }, { "epoch": 53.5, "learning_rate": 4.855719271263258e-05, "loss": 0.0033, "step": 222820 }, { "epoch": 53.5, "learning_rate": 4.8553604640011244e-05, "loss": 0.0042, "step": 222830 }, { "epoch": 53.5, "learning_rate": 4.855001657484463e-05, "loss": 0.0054, "step": 222840 }, { "epoch": 53.51, "learning_rate": 4.854642851715126e-05, "loss": 0.003, "step": 222850 }, { "epoch": 53.51, "learning_rate": 4.854284046694959e-05, "loss": 0.005, "step": 222860 }, { "epoch": 53.51, "learning_rate": 4.853925242425815e-05, "loss": 0.0032, "step": 222870 }, { "epoch": 53.51, "learning_rate": 4.853566438909539e-05, "loss": 0.0031, "step": 222880 }, { "epoch": 53.51, "learning_rate": 4.853207636147986e-05, "loss": 0.0032, "step": 222890 }, { "epoch": 53.52, "learning_rate": 4.852848834143002e-05, "loss": 0.0044, "step": 222900 }, { "epoch": 53.52, "learning_rate": 4.8524900328964334e-05, "loss": 0.0117, "step": 222910 }, { "epoch": 53.52, "learning_rate": 4.852131232410135e-05, "loss": 0.0057, "step": 222920 }, { "epoch": 53.52, "learning_rate": 4.851772432685951e-05, "loss": 0.0036, "step": 222930 }, { "epoch": 53.53, "learning_rate": 4.851413633725736e-05, "loss": 0.0042, "step": 222940 }, { "epoch": 53.53, "learning_rate": 4.8510548355313334e-05, "loss": 0.0044, "step": 222950 }, { "epoch": 53.53, "learning_rate": 4.850696038104597e-05, "loss": 0.0117, "step": 222960 }, { "epoch": 53.53, "learning_rate": 4.850337241447375e-05, "loss": 0.0043, "step": 222970 }, { "epoch": 53.53, "learning_rate": 4.849978445561515e-05, "loss": 0.0057, "step": 222980 }, { "epoch": 53.54, "learning_rate": 4.8496196504488684e-05, "loss": 0.0049, "step": 222990 }, { "epoch": 53.54, "learning_rate": 4.849260856111282e-05, "loss": 0.0108, "step": 223000 }, { "epoch": 53.54, "learning_rate": 4.848902062550608e-05, "loss": 0.0051, "step": 223010 }, { "epoch": 53.54, "learning_rate": 4.848543269768692e-05, "loss": 0.0073, "step": 223020 }, { "epoch": 53.55, "learning_rate": 4.848184477767388e-05, "loss": 0.0096, "step": 223030 }, { "epoch": 53.55, "learning_rate": 4.847825686548542e-05, "loss": 0.0047, "step": 223040 }, { "epoch": 53.55, "learning_rate": 4.847466896114001e-05, "loss": 0.0103, "step": 223050 }, { "epoch": 53.55, "learning_rate": 4.84710810646562e-05, "loss": 0.0143, "step": 223060 }, { "epoch": 53.56, "learning_rate": 4.846749317605243e-05, "loss": 0.0075, "step": 223070 }, { "epoch": 53.56, "learning_rate": 4.8463905295347225e-05, "loss": 0.0068, "step": 223080 }, { "epoch": 53.56, "learning_rate": 4.846031742255905e-05, "loss": 0.0059, "step": 223090 }, { "epoch": 53.56, "learning_rate": 4.845672955770643e-05, "loss": 0.0061, "step": 223100 }, { "epoch": 53.56, "learning_rate": 4.8453141700807824e-05, "loss": 0.0055, "step": 223110 }, { "epoch": 53.57, "learning_rate": 4.844955385188173e-05, "loss": 0.0071, "step": 223120 }, { "epoch": 53.57, "learning_rate": 4.844596601094668e-05, "loss": 0.0046, "step": 223130 }, { "epoch": 53.57, "learning_rate": 4.84423781780211e-05, "loss": 0.0054, "step": 223140 }, { "epoch": 53.57, "learning_rate": 4.843879035312355e-05, "loss": 0.0151, "step": 223150 }, { "epoch": 53.58, "learning_rate": 4.8435202536272455e-05, "loss": 0.0052, "step": 223160 }, { "epoch": 53.58, "learning_rate": 4.843161472748637e-05, "loss": 0.0048, "step": 223170 }, { "epoch": 53.58, "learning_rate": 4.842802692678375e-05, "loss": 0.0076, "step": 223180 }, { "epoch": 53.58, "learning_rate": 4.842443913418307e-05, "loss": 0.0081, "step": 223190 }, { "epoch": 53.59, "learning_rate": 4.842085134970287e-05, "loss": 0.0041, "step": 223200 }, { "epoch": 53.59, "learning_rate": 4.841726357336159e-05, "loss": 0.0106, "step": 223210 }, { "epoch": 53.59, "learning_rate": 4.8413675805177775e-05, "loss": 0.0064, "step": 223220 }, { "epoch": 53.59, "learning_rate": 4.8410088045169854e-05, "loss": 0.0103, "step": 223230 }, { "epoch": 53.59, "learning_rate": 4.840650029335638e-05, "loss": 0.0046, "step": 223240 }, { "epoch": 53.6, "learning_rate": 4.8402912549755794e-05, "loss": 0.0081, "step": 223250 }, { "epoch": 53.6, "learning_rate": 4.839932481438664e-05, "loss": 0.0077, "step": 223260 }, { "epoch": 53.6, "learning_rate": 4.839573708726736e-05, "loss": 0.0078, "step": 223270 }, { "epoch": 53.6, "learning_rate": 4.839214936841645e-05, "loss": 0.004, "step": 223280 }, { "epoch": 53.61, "learning_rate": 4.838856165785245e-05, "loss": 0.0038, "step": 223290 }, { "epoch": 53.61, "learning_rate": 4.838497395559379e-05, "loss": 0.0087, "step": 223300 }, { "epoch": 53.61, "learning_rate": 4.838138626165901e-05, "loss": 0.0035, "step": 223310 }, { "epoch": 53.61, "learning_rate": 4.837779857606655e-05, "loss": 0.0047, "step": 223320 }, { "epoch": 53.61, "learning_rate": 4.837421089883496e-05, "loss": 0.0153, "step": 223330 }, { "epoch": 53.62, "learning_rate": 4.837062322998269e-05, "loss": 0.0096, "step": 223340 }, { "epoch": 53.62, "learning_rate": 4.836703556952823e-05, "loss": 0.0061, "step": 223350 }, { "epoch": 53.62, "learning_rate": 4.8363447917490104e-05, "loss": 0.0031, "step": 223360 }, { "epoch": 53.62, "learning_rate": 4.8359860273886757e-05, "loss": 0.0073, "step": 223370 }, { "epoch": 53.63, "learning_rate": 4.8356272638736724e-05, "loss": 0.0041, "step": 223380 }, { "epoch": 53.63, "learning_rate": 4.835268501205845e-05, "loss": 0.0032, "step": 223390 }, { "epoch": 53.63, "learning_rate": 4.834909739387048e-05, "loss": 0.0032, "step": 223400 }, { "epoch": 53.63, "learning_rate": 4.834550978419126e-05, "loss": 0.0154, "step": 223410 }, { "epoch": 53.64, "learning_rate": 4.834192218303929e-05, "loss": 0.0054, "step": 223420 }, { "epoch": 53.64, "learning_rate": 4.833833459043308e-05, "loss": 0.004, "step": 223430 }, { "epoch": 53.64, "learning_rate": 4.833474700639109e-05, "loss": 0.006, "step": 223440 }, { "epoch": 53.64, "learning_rate": 4.833115943093186e-05, "loss": 0.0039, "step": 223450 }, { "epoch": 53.64, "learning_rate": 4.8327571864073816e-05, "loss": 0.0053, "step": 223460 }, { "epoch": 53.65, "learning_rate": 4.83239843058355e-05, "loss": 0.0076, "step": 223470 }, { "epoch": 53.65, "learning_rate": 4.8320396756235394e-05, "loss": 0.004, "step": 223480 }, { "epoch": 53.65, "learning_rate": 4.8316809215291946e-05, "loss": 0.0032, "step": 223490 }, { "epoch": 53.65, "learning_rate": 4.83132216830237e-05, "loss": 0.0064, "step": 223500 }, { "epoch": 53.66, "learning_rate": 4.830963415944911e-05, "loss": 0.0046, "step": 223510 }, { "epoch": 53.66, "learning_rate": 4.8306046644586686e-05, "loss": 0.0109, "step": 223520 }, { "epoch": 53.66, "learning_rate": 4.83024591384549e-05, "loss": 0.0075, "step": 223530 }, { "epoch": 53.66, "learning_rate": 4.829887164107228e-05, "loss": 0.0037, "step": 223540 }, { "epoch": 53.67, "learning_rate": 4.829528415245727e-05, "loss": 0.0086, "step": 223550 }, { "epoch": 53.67, "learning_rate": 4.829169667262838e-05, "loss": 0.0094, "step": 223560 }, { "epoch": 53.67, "learning_rate": 4.828810920160411e-05, "loss": 0.0034, "step": 223570 }, { "epoch": 53.67, "learning_rate": 4.828452173940292e-05, "loss": 0.0039, "step": 223580 }, { "epoch": 53.67, "learning_rate": 4.8280934286043345e-05, "loss": 0.0056, "step": 223590 }, { "epoch": 53.68, "learning_rate": 4.827734684154383e-05, "loss": 0.0172, "step": 223600 }, { "epoch": 53.68, "learning_rate": 4.8273759405922894e-05, "loss": 0.0038, "step": 223610 }, { "epoch": 53.68, "learning_rate": 4.8270171979199027e-05, "loss": 0.0026, "step": 223620 }, { "epoch": 53.68, "learning_rate": 4.8266584561390675e-05, "loss": 0.0056, "step": 223630 }, { "epoch": 53.69, "learning_rate": 4.8262997152516394e-05, "loss": 0.0072, "step": 223640 }, { "epoch": 53.69, "learning_rate": 4.8259409752594613e-05, "loss": 0.0032, "step": 223650 }, { "epoch": 53.69, "learning_rate": 4.825582236164387e-05, "loss": 0.0051, "step": 223660 }, { "epoch": 53.69, "learning_rate": 4.8252234979682615e-05, "loss": 0.0051, "step": 223670 }, { "epoch": 53.69, "learning_rate": 4.8248647606729374e-05, "loss": 0.0042, "step": 223680 }, { "epoch": 53.7, "learning_rate": 4.824506024280261e-05, "loss": 0.0057, "step": 223690 }, { "epoch": 53.7, "learning_rate": 4.824147288792082e-05, "loss": 0.0056, "step": 223700 }, { "epoch": 53.7, "learning_rate": 4.823788554210249e-05, "loss": 0.0035, "step": 223710 }, { "epoch": 53.7, "learning_rate": 4.8234298205366114e-05, "loss": 0.0034, "step": 223720 }, { "epoch": 53.71, "learning_rate": 4.823071087773018e-05, "loss": 0.0035, "step": 223730 }, { "epoch": 53.71, "learning_rate": 4.8227123559213165e-05, "loss": 0.0056, "step": 223740 }, { "epoch": 53.71, "learning_rate": 4.8223536249833596e-05, "loss": 0.0035, "step": 223750 }, { "epoch": 53.71, "learning_rate": 4.821994894960993e-05, "loss": 0.0049, "step": 223760 }, { "epoch": 53.72, "learning_rate": 4.8216361658560644e-05, "loss": 0.0032, "step": 223770 }, { "epoch": 53.72, "learning_rate": 4.8212774376704265e-05, "loss": 0.0067, "step": 223780 }, { "epoch": 53.72, "learning_rate": 4.820918710405924e-05, "loss": 0.0047, "step": 223790 }, { "epoch": 53.72, "learning_rate": 4.8205599840644105e-05, "loss": 0.0037, "step": 223800 }, { "epoch": 53.72, "learning_rate": 4.8202012586477295e-05, "loss": 0.0037, "step": 223810 }, { "epoch": 53.73, "learning_rate": 4.819842534157736e-05, "loss": 0.0076, "step": 223820 }, { "epoch": 53.73, "learning_rate": 4.819483810596275e-05, "loss": 0.0051, "step": 223830 }, { "epoch": 53.73, "learning_rate": 4.819125087965193e-05, "loss": 0.0057, "step": 223840 }, { "epoch": 53.73, "learning_rate": 4.818766366266344e-05, "loss": 0.0043, "step": 223850 }, { "epoch": 53.74, "learning_rate": 4.8184076455015744e-05, "loss": 0.0051, "step": 223860 }, { "epoch": 53.74, "learning_rate": 4.818048925672733e-05, "loss": 0.0061, "step": 223870 }, { "epoch": 53.74, "learning_rate": 4.8176902067816685e-05, "loss": 0.0028, "step": 223880 }, { "epoch": 53.74, "learning_rate": 4.817331488830231e-05, "loss": 0.0032, "step": 223890 }, { "epoch": 53.75, "learning_rate": 4.816972771820269e-05, "loss": 0.0079, "step": 223900 }, { "epoch": 53.75, "learning_rate": 4.81661405575363e-05, "loss": 0.005, "step": 223910 }, { "epoch": 53.75, "learning_rate": 4.816255340632165e-05, "loss": 0.0041, "step": 223920 }, { "epoch": 53.75, "learning_rate": 4.815896626457719e-05, "loss": 0.0153, "step": 223930 }, { "epoch": 53.75, "learning_rate": 4.815537913232146e-05, "loss": 0.0025, "step": 223940 }, { "epoch": 53.76, "learning_rate": 4.8151792009572895e-05, "loss": 0.0063, "step": 223950 }, { "epoch": 53.76, "learning_rate": 4.8148204896350036e-05, "loss": 0.005, "step": 223960 }, { "epoch": 53.76, "learning_rate": 4.814461779267134e-05, "loss": 0.0057, "step": 223970 }, { "epoch": 53.76, "learning_rate": 4.8141030698555276e-05, "loss": 0.0028, "step": 223980 }, { "epoch": 53.77, "learning_rate": 4.8137443614020386e-05, "loss": 0.0043, "step": 223990 }, { "epoch": 53.77, "learning_rate": 4.8133856539085096e-05, "loss": 0.0046, "step": 224000 }, { "epoch": 53.77, "learning_rate": 4.813026947376794e-05, "loss": 0.0062, "step": 224010 }, { "epoch": 53.77, "learning_rate": 4.812668241808739e-05, "loss": 0.0057, "step": 224020 }, { "epoch": 53.77, "learning_rate": 4.812309537206194e-05, "loss": 0.0069, "step": 224030 }, { "epoch": 53.78, "learning_rate": 4.8119508335710064e-05, "loss": 0.0077, "step": 224040 }, { "epoch": 53.78, "learning_rate": 4.8115921309050266e-05, "loss": 0.004, "step": 224050 }, { "epoch": 53.78, "learning_rate": 4.811233429210103e-05, "loss": 0.0037, "step": 224060 }, { "epoch": 53.78, "learning_rate": 4.810874728488082e-05, "loss": 0.0038, "step": 224070 }, { "epoch": 53.79, "learning_rate": 4.8105160287408164e-05, "loss": 0.0048, "step": 224080 }, { "epoch": 53.79, "learning_rate": 4.81015732997015e-05, "loss": 0.0035, "step": 224090 }, { "epoch": 53.79, "learning_rate": 4.809798632177937e-05, "loss": 0.0048, "step": 224100 }, { "epoch": 53.79, "learning_rate": 4.809439935366021e-05, "loss": 0.0052, "step": 224110 }, { "epoch": 53.8, "learning_rate": 4.809081239536256e-05, "loss": 0.0047, "step": 224120 }, { "epoch": 53.8, "learning_rate": 4.8087225446904874e-05, "loss": 0.0034, "step": 224130 }, { "epoch": 53.8, "learning_rate": 4.808363850830562e-05, "loss": 0.0043, "step": 224140 }, { "epoch": 53.8, "learning_rate": 4.8080051579583324e-05, "loss": 0.0066, "step": 224150 }, { "epoch": 53.8, "learning_rate": 4.807646466075646e-05, "loss": 0.0071, "step": 224160 }, { "epoch": 53.81, "learning_rate": 4.807287775184351e-05, "loss": 0.0121, "step": 224170 }, { "epoch": 53.81, "learning_rate": 4.806929085286296e-05, "loss": 0.0058, "step": 224180 }, { "epoch": 53.81, "learning_rate": 4.8065703963833306e-05, "loss": 0.0117, "step": 224190 }, { "epoch": 53.81, "learning_rate": 4.8062117084773044e-05, "loss": 0.0068, "step": 224200 }, { "epoch": 53.82, "learning_rate": 4.805853021570062e-05, "loss": 0.0058, "step": 224210 }, { "epoch": 53.82, "learning_rate": 4.805494335663457e-05, "loss": 0.0032, "step": 224220 }, { "epoch": 53.82, "learning_rate": 4.8051356507593335e-05, "loss": 0.0041, "step": 224230 }, { "epoch": 53.82, "learning_rate": 4.8047769668595455e-05, "loss": 0.0079, "step": 224240 }, { "epoch": 53.83, "learning_rate": 4.804418283965936e-05, "loss": 0.0034, "step": 224250 }, { "epoch": 53.83, "learning_rate": 4.804059602080358e-05, "loss": 0.0055, "step": 224260 }, { "epoch": 53.83, "learning_rate": 4.8037009212046586e-05, "loss": 0.0031, "step": 224270 }, { "epoch": 53.83, "learning_rate": 4.8033422413406844e-05, "loss": 0.0048, "step": 224280 }, { "epoch": 53.83, "learning_rate": 4.802983562490288e-05, "loss": 0.0046, "step": 224290 }, { "epoch": 53.84, "learning_rate": 4.8026248846553136e-05, "loss": 0.0133, "step": 224300 }, { "epoch": 53.84, "learning_rate": 4.8022662078376134e-05, "loss": 0.0035, "step": 224310 }, { "epoch": 53.84, "learning_rate": 4.801907532039035e-05, "loss": 0.0072, "step": 224320 }, { "epoch": 53.84, "learning_rate": 4.8015488572614264e-05, "loss": 0.0051, "step": 224330 }, { "epoch": 53.85, "learning_rate": 4.801190183506638e-05, "loss": 0.0091, "step": 224340 }, { "epoch": 53.85, "learning_rate": 4.800831510776515e-05, "loss": 0.0059, "step": 224350 }, { "epoch": 53.85, "learning_rate": 4.8004728390729103e-05, "loss": 0.0065, "step": 224360 }, { "epoch": 53.85, "learning_rate": 4.800114168397668e-05, "loss": 0.0087, "step": 224370 }, { "epoch": 53.85, "learning_rate": 4.799755498752641e-05, "loss": 0.0062, "step": 224380 }, { "epoch": 53.86, "learning_rate": 4.799396830139673e-05, "loss": 0.0047, "step": 224390 }, { "epoch": 53.86, "learning_rate": 4.799038162560619e-05, "loss": 0.0042, "step": 224400 }, { "epoch": 53.86, "learning_rate": 4.798679496017323e-05, "loss": 0.0088, "step": 224410 }, { "epoch": 53.86, "learning_rate": 4.798320830511633e-05, "loss": 0.0066, "step": 224420 }, { "epoch": 53.87, "learning_rate": 4.797962166045401e-05, "loss": 0.0062, "step": 224430 }, { "epoch": 53.87, "learning_rate": 4.797603502620471e-05, "loss": 0.0055, "step": 224440 }, { "epoch": 53.87, "learning_rate": 4.797244840238697e-05, "loss": 0.0081, "step": 224450 }, { "epoch": 53.87, "learning_rate": 4.796886178901923e-05, "loss": 0.0033, "step": 224460 }, { "epoch": 53.88, "learning_rate": 4.796527518612e-05, "loss": 0.0044, "step": 224470 }, { "epoch": 53.88, "learning_rate": 4.796168859370777e-05, "loss": 0.003, "step": 224480 }, { "epoch": 53.88, "learning_rate": 4.795810201180099e-05, "loss": 0.026, "step": 224490 }, { "epoch": 53.88, "learning_rate": 4.7954515440418194e-05, "loss": 0.0041, "step": 224500 }, { "epoch": 53.88, "learning_rate": 4.7950928879577815e-05, "loss": 0.0052, "step": 224510 }, { "epoch": 53.89, "learning_rate": 4.794734232929839e-05, "loss": 0.0027, "step": 224520 }, { "epoch": 53.89, "learning_rate": 4.794375578959836e-05, "loss": 0.0078, "step": 224530 }, { "epoch": 53.89, "learning_rate": 4.7940169260496256e-05, "loss": 0.0027, "step": 224540 }, { "epoch": 53.89, "learning_rate": 4.793658274201053e-05, "loss": 0.0033, "step": 224550 }, { "epoch": 53.9, "learning_rate": 4.793299623415965e-05, "loss": 0.0046, "step": 224560 }, { "epoch": 53.9, "learning_rate": 4.792940973696215e-05, "loss": 0.0096, "step": 224570 }, { "epoch": 53.9, "learning_rate": 4.792582325043647e-05, "loss": 0.0034, "step": 224580 }, { "epoch": 53.9, "learning_rate": 4.792223677460114e-05, "loss": 0.0037, "step": 224590 }, { "epoch": 53.91, "learning_rate": 4.791865030947458e-05, "loss": 0.0042, "step": 224600 }, { "epoch": 53.91, "learning_rate": 4.791506385507535e-05, "loss": 0.0045, "step": 224610 }, { "epoch": 53.91, "learning_rate": 4.791147741142189e-05, "loss": 0.005, "step": 224620 }, { "epoch": 53.91, "learning_rate": 4.790789097853267e-05, "loss": 0.0062, "step": 224630 }, { "epoch": 53.91, "learning_rate": 4.790430455642623e-05, "loss": 0.0066, "step": 224640 }, { "epoch": 53.92, "learning_rate": 4.790071814512099e-05, "loss": 0.0038, "step": 224650 }, { "epoch": 53.92, "learning_rate": 4.78971317446355e-05, "loss": 0.0033, "step": 224660 }, { "epoch": 53.92, "learning_rate": 4.7893545354988176e-05, "loss": 0.0062, "step": 224670 }, { "epoch": 53.92, "learning_rate": 4.7889958976197566e-05, "loss": 0.0055, "step": 224680 }, { "epoch": 53.93, "learning_rate": 4.788637260828213e-05, "loss": 0.0079, "step": 224690 }, { "epoch": 53.93, "learning_rate": 4.788278625126031e-05, "loss": 0.005, "step": 224700 }, { "epoch": 53.93, "learning_rate": 4.787919990515067e-05, "loss": 0.0033, "step": 224710 }, { "epoch": 53.93, "learning_rate": 4.787561356997161e-05, "loss": 0.0041, "step": 224720 }, { "epoch": 53.93, "learning_rate": 4.787202724574169e-05, "loss": 0.0032, "step": 224730 }, { "epoch": 53.94, "learning_rate": 4.786844093247933e-05, "loss": 0.0037, "step": 224740 }, { "epoch": 53.94, "learning_rate": 4.7864854630203074e-05, "loss": 0.0029, "step": 224750 }, { "epoch": 53.94, "learning_rate": 4.786126833893135e-05, "loss": 0.0035, "step": 224760 }, { "epoch": 53.94, "learning_rate": 4.785768205868268e-05, "loss": 0.0035, "step": 224770 }, { "epoch": 53.95, "learning_rate": 4.7854095789475526e-05, "loss": 0.003, "step": 224780 }, { "epoch": 53.95, "learning_rate": 4.7850509531328376e-05, "loss": 0.0032, "step": 224790 }, { "epoch": 53.95, "learning_rate": 4.784692328425974e-05, "loss": 0.003, "step": 224800 }, { "epoch": 54.0, "learning_rate": 4.784333704828805e-05, "loss": 0.004, "step": 224810 }, { "epoch": 54.0, "learning_rate": 4.783975082343185e-05, "loss": 0.009, "step": 224820 }, { "epoch": 54.01, "learning_rate": 4.7836164609709585e-05, "loss": 0.0046, "step": 224830 }, { "epoch": 54.01, "learning_rate": 4.783257840713973e-05, "loss": 0.0037, "step": 224840 }, { "epoch": 54.01, "learning_rate": 4.78289922157408e-05, "loss": 0.0043, "step": 224850 }, { "epoch": 54.01, "learning_rate": 4.782540603553124e-05, "loss": 0.003, "step": 224860 }, { "epoch": 54.02, "learning_rate": 4.782181986652958e-05, "loss": 0.0055, "step": 224870 }, { "epoch": 54.02, "learning_rate": 4.7818233708754255e-05, "loss": 0.0047, "step": 224880 }, { "epoch": 54.02, "learning_rate": 4.7814647562223794e-05, "loss": 0.0036, "step": 224890 }, { "epoch": 54.02, "learning_rate": 4.781106142695664e-05, "loss": 0.0052, "step": 224900 }, { "epoch": 54.02, "learning_rate": 4.780747530297131e-05, "loss": 0.0029, "step": 224910 }, { "epoch": 54.03, "learning_rate": 4.7803889190286265e-05, "loss": 0.0058, "step": 224920 }, { "epoch": 54.03, "learning_rate": 4.780030308891999e-05, "loss": 0.0036, "step": 224930 }, { "epoch": 54.03, "learning_rate": 4.779671699889097e-05, "loss": 0.0042, "step": 224940 }, { "epoch": 54.03, "learning_rate": 4.779313092021768e-05, "loss": 0.0038, "step": 224950 }, { "epoch": 54.04, "learning_rate": 4.778954485291864e-05, "loss": 0.0033, "step": 224960 }, { "epoch": 54.04, "learning_rate": 4.778595879701227e-05, "loss": 0.0035, "step": 224970 }, { "epoch": 54.04, "learning_rate": 4.7782372752517117e-05, "loss": 0.0038, "step": 224980 }, { "epoch": 54.04, "learning_rate": 4.777878671945163e-05, "loss": 0.0048, "step": 224990 }, { "epoch": 54.05, "learning_rate": 4.7775200697834277e-05, "loss": 0.0085, "step": 225000 }, { "epoch": 54.05, "learning_rate": 4.777161468768357e-05, "loss": 0.0047, "step": 225010 }, { "epoch": 54.05, "learning_rate": 4.7768028689017966e-05, "loss": 0.0029, "step": 225020 }, { "epoch": 54.05, "learning_rate": 4.776444270185598e-05, "loss": 0.0052, "step": 225030 }, { "epoch": 54.05, "learning_rate": 4.7760856726216056e-05, "loss": 0.0037, "step": 225040 }, { "epoch": 54.06, "learning_rate": 4.775727076211672e-05, "loss": 0.0077, "step": 225050 }, { "epoch": 54.06, "learning_rate": 4.775368480957642e-05, "loss": 0.0065, "step": 225060 }, { "epoch": 54.06, "learning_rate": 4.7750098868613636e-05, "loss": 0.0065, "step": 225070 }, { "epoch": 54.06, "learning_rate": 4.774651293924686e-05, "loss": 0.0083, "step": 225080 }, { "epoch": 54.07, "learning_rate": 4.7742927021494586e-05, "loss": 0.0101, "step": 225090 }, { "epoch": 54.07, "learning_rate": 4.773934111537528e-05, "loss": 0.003, "step": 225100 }, { "epoch": 54.07, "learning_rate": 4.773575522090742e-05, "loss": 0.003, "step": 225110 }, { "epoch": 54.07, "learning_rate": 4.773216933810952e-05, "loss": 0.0065, "step": 225120 }, { "epoch": 54.07, "learning_rate": 4.772858346700003e-05, "loss": 0.0036, "step": 225130 }, { "epoch": 54.08, "learning_rate": 4.772499760759742e-05, "loss": 0.006, "step": 225140 }, { "epoch": 54.08, "learning_rate": 4.772141175992022e-05, "loss": 0.0036, "step": 225150 }, { "epoch": 54.08, "learning_rate": 4.771782592398686e-05, "loss": 0.0035, "step": 225160 }, { "epoch": 54.08, "learning_rate": 4.771424009981586e-05, "loss": 0.0037, "step": 225170 }, { "epoch": 54.09, "learning_rate": 4.7710654287425667e-05, "loss": 0.0038, "step": 225180 }, { "epoch": 54.09, "learning_rate": 4.7707068486834804e-05, "loss": 0.0038, "step": 225190 }, { "epoch": 54.09, "learning_rate": 4.770348269806172e-05, "loss": 0.0102, "step": 225200 }, { "epoch": 54.09, "learning_rate": 4.76998969211249e-05, "loss": 0.0056, "step": 225210 }, { "epoch": 54.1, "learning_rate": 4.769631115604283e-05, "loss": 0.0045, "step": 225220 }, { "epoch": 54.1, "learning_rate": 4.7692725402833996e-05, "loss": 0.0046, "step": 225230 }, { "epoch": 54.1, "learning_rate": 4.768913966151687e-05, "loss": 0.0025, "step": 225240 }, { "epoch": 54.1, "learning_rate": 4.7685553932109934e-05, "loss": 0.0047, "step": 225250 }, { "epoch": 54.1, "learning_rate": 4.768196821463169e-05, "loss": 0.0028, "step": 225260 }, { "epoch": 54.11, "learning_rate": 4.76783825091006e-05, "loss": 0.0039, "step": 225270 }, { "epoch": 54.11, "learning_rate": 4.767479681553513e-05, "loss": 0.003, "step": 225280 }, { "epoch": 54.11, "learning_rate": 4.7671211133953784e-05, "loss": 0.0038, "step": 225290 }, { "epoch": 54.11, "learning_rate": 4.7667625464375025e-05, "loss": 0.0031, "step": 225300 }, { "epoch": 54.12, "learning_rate": 4.766403980681737e-05, "loss": 0.003, "step": 225310 }, { "epoch": 54.12, "learning_rate": 4.766045416129924e-05, "loss": 0.0044, "step": 225320 }, { "epoch": 54.12, "learning_rate": 4.765686852783918e-05, "loss": 0.0077, "step": 225330 }, { "epoch": 54.12, "learning_rate": 4.765328290645563e-05, "loss": 0.0039, "step": 225340 }, { "epoch": 54.13, "learning_rate": 4.7649697297167067e-05, "loss": 0.0059, "step": 225350 }, { "epoch": 54.13, "learning_rate": 4.764611169999199e-05, "loss": 0.0077, "step": 225360 }, { "epoch": 54.13, "learning_rate": 4.764252611494887e-05, "loss": 0.0031, "step": 225370 }, { "epoch": 54.13, "learning_rate": 4.76389405420562e-05, "loss": 0.0072, "step": 225380 }, { "epoch": 54.13, "learning_rate": 4.763535498133244e-05, "loss": 0.0056, "step": 225390 }, { "epoch": 54.14, "learning_rate": 4.763176943279609e-05, "loss": 0.003, "step": 225400 }, { "epoch": 54.14, "learning_rate": 4.762818389646562e-05, "loss": 0.0029, "step": 225410 }, { "epoch": 54.14, "learning_rate": 4.762459837235949e-05, "loss": 0.0042, "step": 225420 }, { "epoch": 54.14, "learning_rate": 4.762101286049623e-05, "loss": 0.0029, "step": 225430 }, { "epoch": 54.15, "learning_rate": 4.761742736089426e-05, "loss": 0.0029, "step": 225440 }, { "epoch": 54.15, "learning_rate": 4.761384187357211e-05, "loss": 0.0038, "step": 225450 }, { "epoch": 54.15, "learning_rate": 4.7610256398548226e-05, "loss": 0.0037, "step": 225460 }, { "epoch": 54.15, "learning_rate": 4.760667093584111e-05, "loss": 0.0036, "step": 225470 }, { "epoch": 54.15, "learning_rate": 4.760308548546925e-05, "loss": 0.0028, "step": 225480 }, { "epoch": 54.16, "learning_rate": 4.759950004745107e-05, "loss": 0.0044, "step": 225490 }, { "epoch": 54.16, "learning_rate": 4.759591462180511e-05, "loss": 0.0046, "step": 225500 }, { "epoch": 54.16, "learning_rate": 4.759232920854981e-05, "loss": 0.0043, "step": 225510 }, { "epoch": 54.16, "learning_rate": 4.7588743807703674e-05, "loss": 0.0048, "step": 225520 }, { "epoch": 54.17, "learning_rate": 4.7585158419285176e-05, "loss": 0.0033, "step": 225530 }, { "epoch": 54.17, "learning_rate": 4.758157304331279e-05, "loss": 0.0031, "step": 225540 }, { "epoch": 54.17, "learning_rate": 4.7577987679805e-05, "loss": 0.0046, "step": 225550 }, { "epoch": 54.17, "learning_rate": 4.7574402328780265e-05, "loss": 0.0038, "step": 225560 }, { "epoch": 54.18, "learning_rate": 4.7570816990257104e-05, "loss": 0.0035, "step": 225570 }, { "epoch": 54.18, "learning_rate": 4.756723166425395e-05, "loss": 0.0135, "step": 225580 }, { "epoch": 54.18, "learning_rate": 4.756364635078933e-05, "loss": 0.0096, "step": 225590 }, { "epoch": 54.18, "learning_rate": 4.7560061049881674e-05, "loss": 0.0026, "step": 225600 }, { "epoch": 54.18, "learning_rate": 4.7556475761549504e-05, "loss": 0.0064, "step": 225610 }, { "epoch": 54.19, "learning_rate": 4.755289048581128e-05, "loss": 0.0044, "step": 225620 }, { "epoch": 54.19, "learning_rate": 4.7549305222685446e-05, "loss": 0.0054, "step": 225630 }, { "epoch": 54.19, "learning_rate": 4.754571997219054e-05, "loss": 0.003, "step": 225640 }, { "epoch": 54.19, "learning_rate": 4.7542134734345e-05, "loss": 0.0028, "step": 225650 }, { "epoch": 54.2, "learning_rate": 4.7538549509167334e-05, "loss": 0.005, "step": 225660 }, { "epoch": 54.2, "learning_rate": 4.7534964296675986e-05, "loss": 0.0034, "step": 225670 }, { "epoch": 54.2, "learning_rate": 4.753137909688946e-05, "loss": 0.0118, "step": 225680 }, { "epoch": 54.2, "learning_rate": 4.752779390982623e-05, "loss": 0.0068, "step": 225690 }, { "epoch": 54.21, "learning_rate": 4.752420873550477e-05, "loss": 0.0043, "step": 225700 }, { "epoch": 54.21, "learning_rate": 4.7520623573943565e-05, "loss": 0.0065, "step": 225710 }, { "epoch": 54.21, "learning_rate": 4.7517038425161076e-05, "loss": 0.0045, "step": 225720 }, { "epoch": 54.21, "learning_rate": 4.7513453289175805e-05, "loss": 0.0071, "step": 225730 }, { "epoch": 54.21, "learning_rate": 4.7509868166006196e-05, "loss": 0.0079, "step": 225740 }, { "epoch": 54.22, "learning_rate": 4.750628305567077e-05, "loss": 0.0041, "step": 225750 }, { "epoch": 54.22, "learning_rate": 4.7502697958187956e-05, "loss": 0.0152, "step": 225760 }, { "epoch": 54.22, "learning_rate": 4.749911287357628e-05, "loss": 0.0047, "step": 225770 }, { "epoch": 54.22, "learning_rate": 4.749552780185421e-05, "loss": 0.0045, "step": 225780 }, { "epoch": 54.23, "learning_rate": 4.749194274304017e-05, "loss": 0.0028, "step": 225790 }, { "epoch": 54.23, "learning_rate": 4.748835769715271e-05, "loss": 0.006, "step": 225800 }, { "epoch": 54.23, "learning_rate": 4.748477266421026e-05, "loss": 0.0046, "step": 225810 }, { "epoch": 54.23, "learning_rate": 4.748118764423131e-05, "loss": 0.0039, "step": 225820 }, { "epoch": 54.23, "learning_rate": 4.7477602637234345e-05, "loss": 0.0039, "step": 225830 }, { "epoch": 54.24, "learning_rate": 4.7474017643237836e-05, "loss": 0.0042, "step": 225840 }, { "epoch": 54.24, "learning_rate": 4.747043266226028e-05, "loss": 0.01, "step": 225850 }, { "epoch": 54.24, "learning_rate": 4.74668476943201e-05, "loss": 0.0058, "step": 225860 }, { "epoch": 54.24, "learning_rate": 4.746326273943584e-05, "loss": 0.0033, "step": 225870 }, { "epoch": 54.25, "learning_rate": 4.745967779762592e-05, "loss": 0.0041, "step": 225880 }, { "epoch": 54.25, "learning_rate": 4.745609286890887e-05, "loss": 0.0039, "step": 225890 }, { "epoch": 54.25, "learning_rate": 4.745250795330311e-05, "loss": 0.0046, "step": 225900 }, { "epoch": 54.25, "learning_rate": 4.744892305082717e-05, "loss": 0.0045, "step": 225910 }, { "epoch": 54.26, "learning_rate": 4.7445338161499505e-05, "loss": 0.0044, "step": 225920 }, { "epoch": 54.26, "learning_rate": 4.744175328533856e-05, "loss": 0.0029, "step": 225930 }, { "epoch": 54.26, "learning_rate": 4.7438168422362864e-05, "loss": 0.0048, "step": 225940 }, { "epoch": 54.26, "learning_rate": 4.7434583572590845e-05, "loss": 0.004, "step": 225950 }, { "epoch": 54.26, "learning_rate": 4.7430998736041024e-05, "loss": 0.0053, "step": 225960 }, { "epoch": 54.27, "learning_rate": 4.7427413912731846e-05, "loss": 0.0039, "step": 225970 }, { "epoch": 54.27, "learning_rate": 4.74238291026818e-05, "loss": 0.0044, "step": 225980 }, { "epoch": 54.27, "learning_rate": 4.7420244305909375e-05, "loss": 0.0037, "step": 225990 }, { "epoch": 54.27, "learning_rate": 4.7416659522433006e-05, "loss": 0.0026, "step": 226000 }, { "epoch": 54.28, "learning_rate": 4.741307475227122e-05, "loss": 0.004, "step": 226010 }, { "epoch": 54.28, "learning_rate": 4.740948999544245e-05, "loss": 0.0045, "step": 226020 }, { "epoch": 54.28, "learning_rate": 4.7405905251965203e-05, "loss": 0.0037, "step": 226030 }, { "epoch": 54.28, "learning_rate": 4.740232052185793e-05, "loss": 0.0071, "step": 226040 }, { "epoch": 54.29, "learning_rate": 4.739873580513914e-05, "loss": 0.0043, "step": 226050 }, { "epoch": 54.29, "learning_rate": 4.739515110182728e-05, "loss": 0.0053, "step": 226060 }, { "epoch": 54.29, "learning_rate": 4.7391566411940815e-05, "loss": 0.0027, "step": 226070 }, { "epoch": 54.29, "learning_rate": 4.738798173549826e-05, "loss": 0.007, "step": 226080 }, { "epoch": 54.29, "learning_rate": 4.7384397072518046e-05, "loss": 0.0053, "step": 226090 }, { "epoch": 54.3, "learning_rate": 4.7380812423018694e-05, "loss": 0.0064, "step": 226100 }, { "epoch": 54.3, "learning_rate": 4.7377227787018635e-05, "loss": 0.0042, "step": 226110 }, { "epoch": 54.3, "learning_rate": 4.737364316453639e-05, "loss": 0.004, "step": 226120 }, { "epoch": 54.3, "learning_rate": 4.73700585555904e-05, "loss": 0.0043, "step": 226130 }, { "epoch": 54.31, "learning_rate": 4.736647396019914e-05, "loss": 0.0026, "step": 226140 }, { "epoch": 54.31, "learning_rate": 4.736288937838111e-05, "loss": 0.0027, "step": 226150 }, { "epoch": 54.31, "learning_rate": 4.7359304810154756e-05, "loss": 0.0034, "step": 226160 }, { "epoch": 54.31, "learning_rate": 4.7355720255538584e-05, "loss": 0.0045, "step": 226170 }, { "epoch": 54.31, "learning_rate": 4.7352135714551024e-05, "loss": 0.0052, "step": 226180 }, { "epoch": 54.32, "learning_rate": 4.734855118721061e-05, "loss": 0.005, "step": 226190 }, { "epoch": 54.32, "learning_rate": 4.734496667353579e-05, "loss": 0.004, "step": 226200 }, { "epoch": 54.32, "learning_rate": 4.7341382173545e-05, "loss": 0.0029, "step": 226210 }, { "epoch": 54.32, "learning_rate": 4.7337797687256775e-05, "loss": 0.0056, "step": 226220 }, { "epoch": 54.33, "learning_rate": 4.733421321468954e-05, "loss": 0.0045, "step": 226230 }, { "epoch": 54.33, "learning_rate": 4.733062875586182e-05, "loss": 0.0063, "step": 226240 }, { "epoch": 54.33, "learning_rate": 4.732704431079204e-05, "loss": 0.0032, "step": 226250 }, { "epoch": 54.33, "learning_rate": 4.732345987949871e-05, "loss": 0.004, "step": 226260 }, { "epoch": 54.34, "learning_rate": 4.7319875462000276e-05, "loss": 0.0077, "step": 226270 }, { "epoch": 54.34, "learning_rate": 4.731629105831524e-05, "loss": 0.0047, "step": 226280 }, { "epoch": 54.34, "learning_rate": 4.731270666846205e-05, "loss": 0.0033, "step": 226290 }, { "epoch": 54.34, "learning_rate": 4.730912229245919e-05, "loss": 0.0072, "step": 226300 }, { "epoch": 54.34, "learning_rate": 4.730553793032516e-05, "loss": 0.0043, "step": 226310 }, { "epoch": 54.35, "learning_rate": 4.730195358207838e-05, "loss": 0.0041, "step": 226320 }, { "epoch": 54.35, "learning_rate": 4.7298369247737374e-05, "loss": 0.0044, "step": 226330 }, { "epoch": 54.35, "learning_rate": 4.72947849273206e-05, "loss": 0.0068, "step": 226340 }, { "epoch": 54.35, "learning_rate": 4.7291200620846506e-05, "loss": 0.0032, "step": 226350 }, { "epoch": 54.36, "learning_rate": 4.728761632833361e-05, "loss": 0.0041, "step": 226360 }, { "epoch": 54.36, "learning_rate": 4.728403204980034e-05, "loss": 0.0054, "step": 226370 }, { "epoch": 54.36, "learning_rate": 4.728044778526521e-05, "loss": 0.0037, "step": 226380 }, { "epoch": 54.36, "learning_rate": 4.727686353474665e-05, "loss": 0.0037, "step": 226390 }, { "epoch": 54.37, "learning_rate": 4.727327929826319e-05, "loss": 0.0059, "step": 226400 }, { "epoch": 54.37, "learning_rate": 4.726969507583325e-05, "loss": 0.0048, "step": 226410 }, { "epoch": 54.37, "learning_rate": 4.7266110867475334e-05, "loss": 0.0037, "step": 226420 }, { "epoch": 54.37, "learning_rate": 4.7262526673207897e-05, "loss": 0.0072, "step": 226430 }, { "epoch": 54.37, "learning_rate": 4.7258942493049426e-05, "loss": 0.0058, "step": 226440 }, { "epoch": 54.38, "learning_rate": 4.725535832701839e-05, "loss": 0.0039, "step": 226450 }, { "epoch": 54.38, "learning_rate": 4.725177417513324e-05, "loss": 0.0083, "step": 226460 }, { "epoch": 54.38, "learning_rate": 4.7248190037412495e-05, "loss": 0.006, "step": 226470 }, { "epoch": 54.38, "learning_rate": 4.7244605913874586e-05, "loss": 0.007, "step": 226480 }, { "epoch": 54.39, "learning_rate": 4.724102180453802e-05, "loss": 0.0047, "step": 226490 }, { "epoch": 54.39, "learning_rate": 4.723743770942124e-05, "loss": 0.0039, "step": 226500 }, { "epoch": 54.39, "learning_rate": 4.7233853628542716e-05, "loss": 0.0041, "step": 226510 }, { "epoch": 54.39, "learning_rate": 4.723026956192096e-05, "loss": 0.0036, "step": 226520 }, { "epoch": 54.39, "learning_rate": 4.722668550957439e-05, "loss": 0.0072, "step": 226530 }, { "epoch": 54.4, "learning_rate": 4.722310147152153e-05, "loss": 0.0043, "step": 226540 }, { "epoch": 54.4, "learning_rate": 4.72195174477808e-05, "loss": 0.0083, "step": 226550 }, { "epoch": 54.4, "learning_rate": 4.721593343837073e-05, "loss": 0.0033, "step": 226560 }, { "epoch": 54.4, "learning_rate": 4.721234944330975e-05, "loss": 0.0051, "step": 226570 }, { "epoch": 54.41, "learning_rate": 4.7208765462616347e-05, "loss": 0.0063, "step": 226580 }, { "epoch": 54.41, "learning_rate": 4.720518149630898e-05, "loss": 0.0045, "step": 226590 }, { "epoch": 54.41, "learning_rate": 4.720159754440614e-05, "loss": 0.0025, "step": 226600 }, { "epoch": 54.41, "learning_rate": 4.7198013606926286e-05, "loss": 0.0058, "step": 226610 }, { "epoch": 54.42, "learning_rate": 4.7194429683887886e-05, "loss": 0.0048, "step": 226620 }, { "epoch": 54.42, "learning_rate": 4.719084577530944e-05, "loss": 0.0036, "step": 226630 }, { "epoch": 54.42, "learning_rate": 4.718726188120939e-05, "loss": 0.0028, "step": 226640 }, { "epoch": 54.42, "learning_rate": 4.7183678001606205e-05, "loss": 0.0037, "step": 226650 }, { "epoch": 54.42, "learning_rate": 4.718009413651838e-05, "loss": 0.0035, "step": 226660 }, { "epoch": 54.43, "learning_rate": 4.717651028596436e-05, "loss": 0.006, "step": 226670 }, { "epoch": 54.43, "learning_rate": 4.7172926449962646e-05, "loss": 0.0037, "step": 226680 }, { "epoch": 54.43, "learning_rate": 4.716934262853167e-05, "loss": 0.0101, "step": 226690 }, { "epoch": 54.43, "learning_rate": 4.716575882168995e-05, "loss": 0.0062, "step": 226700 }, { "epoch": 54.44, "learning_rate": 4.716217502945592e-05, "loss": 0.0057, "step": 226710 }, { "epoch": 54.44, "learning_rate": 4.715859125184807e-05, "loss": 0.0077, "step": 226720 }, { "epoch": 54.44, "learning_rate": 4.715500748888486e-05, "loss": 0.0026, "step": 226730 }, { "epoch": 54.44, "learning_rate": 4.7151423740584765e-05, "loss": 0.0032, "step": 226740 }, { "epoch": 54.45, "learning_rate": 4.7147840006966255e-05, "loss": 0.0033, "step": 226750 }, { "epoch": 54.45, "learning_rate": 4.71442562880478e-05, "loss": 0.0049, "step": 226760 }, { "epoch": 54.45, "learning_rate": 4.7140672583847875e-05, "loss": 0.0061, "step": 226770 }, { "epoch": 54.45, "learning_rate": 4.7137088894384956e-05, "loss": 0.004, "step": 226780 }, { "epoch": 54.45, "learning_rate": 4.7133505219677486e-05, "loss": 0.0029, "step": 226790 }, { "epoch": 54.46, "learning_rate": 4.712992155974397e-05, "loss": 0.0089, "step": 226800 }, { "epoch": 54.46, "learning_rate": 4.712633791460285e-05, "loss": 0.003, "step": 226810 }, { "epoch": 54.46, "learning_rate": 4.712275428427262e-05, "loss": 0.0033, "step": 226820 }, { "epoch": 54.46, "learning_rate": 4.7119170668771725e-05, "loss": 0.0063, "step": 226830 }, { "epoch": 54.47, "learning_rate": 4.7115587068118665e-05, "loss": 0.0053, "step": 226840 }, { "epoch": 54.47, "learning_rate": 4.71120034823319e-05, "loss": 0.003, "step": 226850 }, { "epoch": 54.47, "learning_rate": 4.7108419911429864e-05, "loss": 0.0081, "step": 226860 }, { "epoch": 54.47, "learning_rate": 4.710483635543107e-05, "loss": 0.0029, "step": 226870 }, { "epoch": 54.47, "learning_rate": 4.7101252814353973e-05, "loss": 0.0083, "step": 226880 }, { "epoch": 54.48, "learning_rate": 4.7097669288217045e-05, "loss": 0.0041, "step": 226890 }, { "epoch": 54.48, "learning_rate": 4.709408577703875e-05, "loss": 0.0045, "step": 226900 }, { "epoch": 54.48, "learning_rate": 4.709050228083756e-05, "loss": 0.0092, "step": 226910 }, { "epoch": 54.48, "learning_rate": 4.708691879963196e-05, "loss": 0.0068, "step": 226920 }, { "epoch": 54.49, "learning_rate": 4.708333533344039e-05, "loss": 0.0027, "step": 226930 }, { "epoch": 54.49, "learning_rate": 4.7079751882281345e-05, "loss": 0.0032, "step": 226940 }, { "epoch": 54.49, "learning_rate": 4.7076168446173264e-05, "loss": 0.0082, "step": 226950 }, { "epoch": 54.49, "learning_rate": 4.707258502513466e-05, "loss": 0.0042, "step": 226960 }, { "epoch": 54.5, "learning_rate": 4.706900161918395e-05, "loss": 0.0069, "step": 226970 }, { "epoch": 54.5, "learning_rate": 4.706541822833966e-05, "loss": 0.0033, "step": 226980 }, { "epoch": 54.5, "learning_rate": 4.7061834852620224e-05, "loss": 0.0074, "step": 226990 }, { "epoch": 54.5, "learning_rate": 4.705825149204409e-05, "loss": 0.0099, "step": 227000 }, { "epoch": 54.5, "learning_rate": 4.705466814662978e-05, "loss": 0.0058, "step": 227010 }, { "epoch": 54.51, "learning_rate": 4.7051084816395715e-05, "loss": 0.0035, "step": 227020 }, { "epoch": 54.51, "learning_rate": 4.704750150136039e-05, "loss": 0.0029, "step": 227030 }, { "epoch": 54.51, "learning_rate": 4.704391820154227e-05, "loss": 0.0043, "step": 227040 }, { "epoch": 54.51, "learning_rate": 4.704033491695982e-05, "loss": 0.0029, "step": 227050 }, { "epoch": 54.52, "learning_rate": 4.7036751647631514e-05, "loss": 0.0031, "step": 227060 }, { "epoch": 54.52, "learning_rate": 4.70331683935758e-05, "loss": 0.0031, "step": 227070 }, { "epoch": 54.52, "learning_rate": 4.702958515481118e-05, "loss": 0.0066, "step": 227080 }, { "epoch": 54.52, "learning_rate": 4.7026001931356076e-05, "loss": 0.0075, "step": 227090 }, { "epoch": 54.53, "learning_rate": 4.7022418723229014e-05, "loss": 0.0041, "step": 227100 }, { "epoch": 54.53, "learning_rate": 4.70188355304484e-05, "loss": 0.0051, "step": 227110 }, { "epoch": 54.53, "learning_rate": 4.701525235303276e-05, "loss": 0.0082, "step": 227120 }, { "epoch": 54.53, "learning_rate": 4.701166919100053e-05, "loss": 0.0114, "step": 227130 }, { "epoch": 54.53, "learning_rate": 4.700808604437017e-05, "loss": 0.0048, "step": 227140 }, { "epoch": 54.54, "learning_rate": 4.700450291316017e-05, "loss": 0.007, "step": 227150 }, { "epoch": 54.54, "learning_rate": 4.700091979738897e-05, "loss": 0.0042, "step": 227160 }, { "epoch": 54.54, "learning_rate": 4.699733669707508e-05, "loss": 0.007, "step": 227170 }, { "epoch": 54.54, "learning_rate": 4.6993753612236914e-05, "loss": 0.0054, "step": 227180 }, { "epoch": 54.55, "learning_rate": 4.699017054289298e-05, "loss": 0.0063, "step": 227190 }, { "epoch": 54.55, "learning_rate": 4.6986587489061746e-05, "loss": 0.0115, "step": 227200 }, { "epoch": 54.55, "learning_rate": 4.698300445076164e-05, "loss": 0.0111, "step": 227210 }, { "epoch": 54.55, "learning_rate": 4.697942142801117e-05, "loss": 0.0051, "step": 227220 }, { "epoch": 54.55, "learning_rate": 4.697583842082878e-05, "loss": 0.0099, "step": 227230 }, { "epoch": 54.56, "learning_rate": 4.697225542923295e-05, "loss": 0.012, "step": 227240 }, { "epoch": 54.56, "learning_rate": 4.696867245324213e-05, "loss": 0.0074, "step": 227250 }, { "epoch": 54.56, "learning_rate": 4.6965089492874816e-05, "loss": 0.0045, "step": 227260 }, { "epoch": 54.56, "learning_rate": 4.6961506548149434e-05, "loss": 0.0047, "step": 227270 }, { "epoch": 54.57, "learning_rate": 4.69579236190845e-05, "loss": 0.0045, "step": 227280 }, { "epoch": 54.57, "learning_rate": 4.695434070569845e-05, "loss": 0.0122, "step": 227290 }, { "epoch": 54.57, "learning_rate": 4.6950757808009726e-05, "loss": 0.0037, "step": 227300 }, { "epoch": 54.57, "learning_rate": 4.694717492603685e-05, "loss": 0.0043, "step": 227310 }, { "epoch": 54.58, "learning_rate": 4.694359205979823e-05, "loss": 0.0066, "step": 227320 }, { "epoch": 54.58, "learning_rate": 4.694000920931239e-05, "loss": 0.0055, "step": 227330 }, { "epoch": 54.58, "learning_rate": 4.693642637459775e-05, "loss": 0.0065, "step": 227340 }, { "epoch": 54.58, "learning_rate": 4.6932843555672794e-05, "loss": 0.0038, "step": 227350 }, { "epoch": 54.58, "learning_rate": 4.692926075255601e-05, "loss": 0.004, "step": 227360 }, { "epoch": 54.59, "learning_rate": 4.692567796526581e-05, "loss": 0.0039, "step": 227370 }, { "epoch": 54.59, "learning_rate": 4.6922095193820724e-05, "loss": 0.0038, "step": 227380 }, { "epoch": 54.59, "learning_rate": 4.691851243823916e-05, "loss": 0.0053, "step": 227390 }, { "epoch": 54.59, "learning_rate": 4.691492969853963e-05, "loss": 0.0043, "step": 227400 }, { "epoch": 54.6, "learning_rate": 4.691134697474055e-05, "loss": 0.0042, "step": 227410 }, { "epoch": 54.6, "learning_rate": 4.690776426686044e-05, "loss": 0.0057, "step": 227420 }, { "epoch": 54.6, "learning_rate": 4.6904181574917737e-05, "loss": 0.0077, "step": 227430 }, { "epoch": 54.6, "learning_rate": 4.690059889893089e-05, "loss": 0.003, "step": 227440 }, { "epoch": 54.61, "learning_rate": 4.68970162389184e-05, "loss": 0.0048, "step": 227450 }, { "epoch": 54.61, "learning_rate": 4.6893433594898694e-05, "loss": 0.0066, "step": 227460 }, { "epoch": 54.61, "learning_rate": 4.688985096689028e-05, "loss": 0.0044, "step": 227470 }, { "epoch": 54.61, "learning_rate": 4.688626835491158e-05, "loss": 0.0067, "step": 227480 }, { "epoch": 54.61, "learning_rate": 4.68826857589811e-05, "loss": 0.0037, "step": 227490 }, { "epoch": 54.62, "learning_rate": 4.687910317911727e-05, "loss": 0.0045, "step": 227500 }, { "epoch": 54.62, "learning_rate": 4.687552061533856e-05, "loss": 0.0075, "step": 227510 }, { "epoch": 54.62, "learning_rate": 4.687193806766346e-05, "loss": 0.0036, "step": 227520 }, { "epoch": 54.62, "learning_rate": 4.6868355536110405e-05, "loss": 0.0061, "step": 227530 }, { "epoch": 54.63, "learning_rate": 4.6864773020697885e-05, "loss": 0.0051, "step": 227540 }, { "epoch": 54.63, "learning_rate": 4.686119052144433e-05, "loss": 0.008, "step": 227550 }, { "epoch": 54.63, "learning_rate": 4.685760803836825e-05, "loss": 0.005, "step": 227560 }, { "epoch": 54.63, "learning_rate": 4.685402557148808e-05, "loss": 0.0084, "step": 227570 }, { "epoch": 54.63, "learning_rate": 4.6850443120822276e-05, "loss": 0.0053, "step": 227580 }, { "epoch": 54.64, "learning_rate": 4.6846860686389325e-05, "loss": 0.0042, "step": 227590 }, { "epoch": 54.64, "learning_rate": 4.684327826820767e-05, "loss": 0.0055, "step": 227600 }, { "epoch": 54.64, "learning_rate": 4.6839695866295796e-05, "loss": 0.0058, "step": 227610 }, { "epoch": 54.64, "learning_rate": 4.683611348067214e-05, "loss": 0.0046, "step": 227620 }, { "epoch": 54.65, "learning_rate": 4.683253111135521e-05, "loss": 0.0024, "step": 227630 }, { "epoch": 54.65, "learning_rate": 4.682894875836342e-05, "loss": 0.0052, "step": 227640 }, { "epoch": 54.65, "learning_rate": 4.682536642171524e-05, "loss": 0.0053, "step": 227650 }, { "epoch": 54.65, "learning_rate": 4.6821784101429176e-05, "loss": 0.0044, "step": 227660 }, { "epoch": 54.66, "learning_rate": 4.681820179752364e-05, "loss": 0.0031, "step": 227670 }, { "epoch": 54.66, "learning_rate": 4.681461951001714e-05, "loss": 0.0046, "step": 227680 }, { "epoch": 54.66, "learning_rate": 4.6811037238928103e-05, "loss": 0.0081, "step": 227690 }, { "epoch": 54.66, "learning_rate": 4.680745498427502e-05, "loss": 0.0048, "step": 227700 }, { "epoch": 54.66, "learning_rate": 4.680387274607635e-05, "loss": 0.0056, "step": 227710 }, { "epoch": 54.67, "learning_rate": 4.6800290524350514e-05, "loss": 0.0064, "step": 227720 }, { "epoch": 54.67, "learning_rate": 4.679670831911603e-05, "loss": 0.0037, "step": 227730 }, { "epoch": 54.67, "learning_rate": 4.6793126130391326e-05, "loss": 0.0041, "step": 227740 }, { "epoch": 54.67, "learning_rate": 4.6789543958194896e-05, "loss": 0.0046, "step": 227750 }, { "epoch": 54.68, "learning_rate": 4.678596180254515e-05, "loss": 0.005, "step": 227760 }, { "epoch": 54.68, "learning_rate": 4.6782379663460616e-05, "loss": 0.003, "step": 227770 }, { "epoch": 54.68, "learning_rate": 4.677879754095971e-05, "loss": 0.0048, "step": 227780 }, { "epoch": 54.68, "learning_rate": 4.6775215435060916e-05, "loss": 0.0085, "step": 227790 }, { "epoch": 54.69, "learning_rate": 4.6771633345782676e-05, "loss": 0.0052, "step": 227800 }, { "epoch": 54.69, "learning_rate": 4.676805127314346e-05, "loss": 0.0087, "step": 227810 }, { "epoch": 54.69, "learning_rate": 4.676446921716176e-05, "loss": 0.0049, "step": 227820 }, { "epoch": 54.69, "learning_rate": 4.6760887177855986e-05, "loss": 0.003, "step": 227830 }, { "epoch": 54.69, "learning_rate": 4.675730515524465e-05, "loss": 0.0053, "step": 227840 }, { "epoch": 54.7, "learning_rate": 4.675372314934619e-05, "loss": 0.005, "step": 227850 }, { "epoch": 54.7, "learning_rate": 4.675014116017904e-05, "loss": 0.0049, "step": 227860 }, { "epoch": 54.7, "learning_rate": 4.6746559187761724e-05, "loss": 0.0083, "step": 227870 }, { "epoch": 54.7, "learning_rate": 4.674297723211264e-05, "loss": 0.0062, "step": 227880 }, { "epoch": 54.71, "learning_rate": 4.67393952932503e-05, "loss": 0.0047, "step": 227890 }, { "epoch": 54.71, "learning_rate": 4.6735813371193124e-05, "loss": 0.0063, "step": 227900 }, { "epoch": 54.71, "learning_rate": 4.673223146595962e-05, "loss": 0.0075, "step": 227910 }, { "epoch": 54.71, "learning_rate": 4.67286495775682e-05, "loss": 0.003, "step": 227920 }, { "epoch": 54.71, "learning_rate": 4.6725067706037355e-05, "loss": 0.0032, "step": 227930 }, { "epoch": 54.72, "learning_rate": 4.672148585138554e-05, "loss": 0.006, "step": 227940 }, { "epoch": 54.72, "learning_rate": 4.6717904013631206e-05, "loss": 0.004, "step": 227950 }, { "epoch": 54.72, "learning_rate": 4.671432219279283e-05, "loss": 0.003, "step": 227960 }, { "epoch": 54.72, "learning_rate": 4.6710740388888855e-05, "loss": 0.0056, "step": 227970 }, { "epoch": 54.73, "learning_rate": 4.670715860193777e-05, "loss": 0.0033, "step": 227980 }, { "epoch": 54.73, "learning_rate": 4.670357683195801e-05, "loss": 0.0025, "step": 227990 }, { "epoch": 54.73, "learning_rate": 4.669999507896803e-05, "loss": 0.013, "step": 228000 }, { "epoch": 54.73, "learning_rate": 4.6696413342986325e-05, "loss": 0.0051, "step": 228010 }, { "epoch": 54.74, "learning_rate": 4.66928316240313e-05, "loss": 0.0053, "step": 228020 }, { "epoch": 54.74, "learning_rate": 4.6689249922121484e-05, "loss": 0.0036, "step": 228030 }, { "epoch": 54.74, "learning_rate": 4.668566823727528e-05, "loss": 0.0035, "step": 228040 }, { "epoch": 54.74, "learning_rate": 4.668208656951118e-05, "loss": 0.0088, "step": 228050 }, { "epoch": 54.74, "learning_rate": 4.6678504918847614e-05, "loss": 0.0043, "step": 228060 }, { "epoch": 54.75, "learning_rate": 4.667492328530309e-05, "loss": 0.0051, "step": 228070 }, { "epoch": 54.75, "learning_rate": 4.6671341668896023e-05, "loss": 0.0038, "step": 228080 }, { "epoch": 54.75, "learning_rate": 4.66677600696449e-05, "loss": 0.0038, "step": 228090 }, { "epoch": 54.75, "learning_rate": 4.6664178487568156e-05, "loss": 0.0091, "step": 228100 }, { "epoch": 54.76, "learning_rate": 4.6660596922684266e-05, "loss": 0.0054, "step": 228110 }, { "epoch": 54.76, "learning_rate": 4.665701537501169e-05, "loss": 0.0043, "step": 228120 }, { "epoch": 54.76, "learning_rate": 4.6653433844568874e-05, "loss": 0.003, "step": 228130 }, { "epoch": 54.76, "learning_rate": 4.664985233137431e-05, "loss": 0.0046, "step": 228140 }, { "epoch": 54.77, "learning_rate": 4.664627083544644e-05, "loss": 0.0042, "step": 228150 }, { "epoch": 54.77, "learning_rate": 4.664268935680369e-05, "loss": 0.0067, "step": 228160 }, { "epoch": 54.77, "learning_rate": 4.663910789546456e-05, "loss": 0.0045, "step": 228170 }, { "epoch": 54.77, "learning_rate": 4.663552645144749e-05, "loss": 0.0039, "step": 228180 }, { "epoch": 54.77, "learning_rate": 4.663194502477096e-05, "loss": 0.0067, "step": 228190 }, { "epoch": 54.78, "learning_rate": 4.662836361545339e-05, "loss": 0.0343, "step": 228200 }, { "epoch": 54.78, "learning_rate": 4.6624782223513284e-05, "loss": 0.0035, "step": 228210 }, { "epoch": 54.78, "learning_rate": 4.662120084896907e-05, "loss": 0.0057, "step": 228220 }, { "epoch": 54.78, "learning_rate": 4.661761949183922e-05, "loss": 0.0066, "step": 228230 }, { "epoch": 54.79, "learning_rate": 4.661403815214218e-05, "loss": 0.0055, "step": 228240 }, { "epoch": 54.79, "learning_rate": 4.6610456829896424e-05, "loss": 0.0086, "step": 228250 }, { "epoch": 54.79, "learning_rate": 4.6606875525120394e-05, "loss": 0.0072, "step": 228260 }, { "epoch": 54.79, "learning_rate": 4.660329423783256e-05, "loss": 0.0036, "step": 228270 }, { "epoch": 54.79, "learning_rate": 4.659971296805137e-05, "loss": 0.0069, "step": 228280 }, { "epoch": 54.8, "learning_rate": 4.65961317157953e-05, "loss": 0.0057, "step": 228290 }, { "epoch": 54.8, "learning_rate": 4.659255048108277e-05, "loss": 0.0051, "step": 228300 }, { "epoch": 54.8, "learning_rate": 4.6588969263932294e-05, "loss": 0.0032, "step": 228310 }, { "epoch": 54.8, "learning_rate": 4.6585388064362276e-05, "loss": 0.0055, "step": 228320 }, { "epoch": 54.81, "learning_rate": 4.6581806882391225e-05, "loss": 0.0047, "step": 228330 }, { "epoch": 54.81, "learning_rate": 4.657822571803753e-05, "loss": 0.0055, "step": 228340 }, { "epoch": 54.81, "learning_rate": 4.6574644571319725e-05, "loss": 0.0042, "step": 228350 }, { "epoch": 54.81, "learning_rate": 4.657106344225622e-05, "loss": 0.0063, "step": 228360 }, { "epoch": 54.82, "learning_rate": 4.656748233086547e-05, "loss": 0.0047, "step": 228370 }, { "epoch": 54.82, "learning_rate": 4.656390123716595e-05, "loss": 0.0071, "step": 228380 }, { "epoch": 54.82, "learning_rate": 4.6560320161176116e-05, "loss": 0.005, "step": 228390 }, { "epoch": 54.82, "learning_rate": 4.6556739102914416e-05, "loss": 0.0035, "step": 228400 }, { "epoch": 54.82, "learning_rate": 4.6553158062399317e-05, "loss": 0.0055, "step": 228410 }, { "epoch": 54.83, "learning_rate": 4.654957703964927e-05, "loss": 0.0058, "step": 228420 }, { "epoch": 54.83, "learning_rate": 4.654599603468274e-05, "loss": 0.0028, "step": 228430 }, { "epoch": 54.83, "learning_rate": 4.6542415047518146e-05, "loss": 0.0074, "step": 228440 }, { "epoch": 54.83, "learning_rate": 4.6538834078174e-05, "loss": 0.0029, "step": 228450 }, { "epoch": 54.84, "learning_rate": 4.6535253126668715e-05, "loss": 0.0034, "step": 228460 }, { "epoch": 54.84, "learning_rate": 4.653167219302079e-05, "loss": 0.0033, "step": 228470 }, { "epoch": 54.84, "learning_rate": 4.652809127724862e-05, "loss": 0.0044, "step": 228480 }, { "epoch": 54.84, "learning_rate": 4.652451037937073e-05, "loss": 0.003, "step": 228490 }, { "epoch": 54.85, "learning_rate": 4.652092949940554e-05, "loss": 0.0042, "step": 228500 }, { "epoch": 54.85, "learning_rate": 4.6517348637371484e-05, "loss": 0.005, "step": 228510 }, { "epoch": 54.85, "learning_rate": 4.6513767793287065e-05, "loss": 0.0044, "step": 228520 }, { "epoch": 54.85, "learning_rate": 4.6510186967170695e-05, "loss": 0.0037, "step": 228530 }, { "epoch": 54.85, "learning_rate": 4.650660615904086e-05, "loss": 0.0032, "step": 228540 }, { "epoch": 54.86, "learning_rate": 4.650302536891601e-05, "loss": 0.0057, "step": 228550 }, { "epoch": 54.86, "learning_rate": 4.649944459681459e-05, "loss": 0.0038, "step": 228560 }, { "epoch": 54.86, "learning_rate": 4.649586384275508e-05, "loss": 0.0043, "step": 228570 }, { "epoch": 54.86, "learning_rate": 4.649228310675589e-05, "loss": 0.0052, "step": 228580 }, { "epoch": 54.87, "learning_rate": 4.648870238883552e-05, "loss": 0.0039, "step": 228590 }, { "epoch": 54.87, "learning_rate": 4.6485121689012396e-05, "loss": 0.0035, "step": 228600 }, { "epoch": 54.87, "learning_rate": 4.6481541007305e-05, "loss": 0.0054, "step": 228610 }, { "epoch": 54.87, "learning_rate": 4.6477960343731745e-05, "loss": 0.0048, "step": 228620 }, { "epoch": 54.87, "learning_rate": 4.6474379698311146e-05, "loss": 0.0047, "step": 228630 }, { "epoch": 54.88, "learning_rate": 4.647079907106161e-05, "loss": 0.0025, "step": 228640 }, { "epoch": 54.88, "learning_rate": 4.6467218462001596e-05, "loss": 0.0035, "step": 228650 }, { "epoch": 54.88, "learning_rate": 4.6463637871149576e-05, "loss": 0.0032, "step": 228660 }, { "epoch": 54.88, "learning_rate": 4.6460057298523984e-05, "loss": 0.0056, "step": 228670 }, { "epoch": 54.89, "learning_rate": 4.6456476744143305e-05, "loss": 0.003, "step": 228680 }, { "epoch": 54.89, "learning_rate": 4.645289620802595e-05, "loss": 0.0037, "step": 228690 }, { "epoch": 54.89, "learning_rate": 4.6449315690190415e-05, "loss": 0.0025, "step": 228700 }, { "epoch": 54.89, "learning_rate": 4.644573519065514e-05, "loss": 0.0062, "step": 228710 }, { "epoch": 54.9, "learning_rate": 4.6442154709438565e-05, "loss": 0.0028, "step": 228720 }, { "epoch": 54.9, "learning_rate": 4.643857424655916e-05, "loss": 0.0028, "step": 228730 }, { "epoch": 54.9, "learning_rate": 4.6434993802035365e-05, "loss": 0.0053, "step": 228740 }, { "epoch": 54.9, "learning_rate": 4.6431413375885656e-05, "loss": 0.0027, "step": 228750 }, { "epoch": 54.9, "learning_rate": 4.6427832968128454e-05, "loss": 0.0032, "step": 228760 }, { "epoch": 54.91, "learning_rate": 4.642425257878225e-05, "loss": 0.0045, "step": 228770 }, { "epoch": 54.91, "learning_rate": 4.642067220786548e-05, "loss": 0.0029, "step": 228780 }, { "epoch": 54.91, "learning_rate": 4.641709185539658e-05, "loss": 0.004, "step": 228790 }, { "epoch": 54.91, "learning_rate": 4.6413511521394026e-05, "loss": 0.0244, "step": 228800 }, { "epoch": 54.92, "learning_rate": 4.640993120587625e-05, "loss": 0.0057, "step": 228810 }, { "epoch": 54.92, "learning_rate": 4.640635090886174e-05, "loss": 0.0035, "step": 228820 }, { "epoch": 54.92, "learning_rate": 4.6402770630368906e-05, "loss": 0.0491, "step": 228830 }, { "epoch": 54.92, "learning_rate": 4.639919037041624e-05, "loss": 0.0066, "step": 228840 }, { "epoch": 54.93, "learning_rate": 4.6395610129022174e-05, "loss": 0.0066, "step": 228850 }, { "epoch": 54.93, "learning_rate": 4.639202990620515e-05, "loss": 0.0049, "step": 228860 }, { "epoch": 54.93, "learning_rate": 4.638844970198365e-05, "loss": 0.0063, "step": 228870 }, { "epoch": 54.93, "learning_rate": 4.63848695163761e-05, "loss": 0.0033, "step": 228880 }, { "epoch": 54.93, "learning_rate": 4.638128934940097e-05, "loss": 0.0066, "step": 228890 }, { "epoch": 54.94, "learning_rate": 4.637770920107669e-05, "loss": 0.0043, "step": 228900 }, { "epoch": 54.94, "learning_rate": 4.637412907142175e-05, "loss": 0.0026, "step": 228910 }, { "epoch": 54.94, "learning_rate": 4.637054896045456e-05, "loss": 0.0029, "step": 228920 }, { "epoch": 54.94, "learning_rate": 4.63669688681936e-05, "loss": 0.0034, "step": 228930 }, { "epoch": 54.95, "learning_rate": 4.636338879465733e-05, "loss": 0.0026, "step": 228940 }, { "epoch": 54.95, "learning_rate": 4.6359808739864155e-05, "loss": 0.0022, "step": 228950 }, { "epoch": 54.95, "learning_rate": 4.635622870383258e-05, "loss": 0.0026, "step": 228960 }, { "epoch": 55.0, "learning_rate": 4.6352648686581e-05, "loss": 0.0036, "step": 228970 }, { "epoch": 55.0, "learning_rate": 4.634906868812793e-05, "loss": 0.0031, "step": 228980 }, { "epoch": 55.01, "learning_rate": 4.634548870849177e-05, "loss": 0.0033, "step": 228990 }, { "epoch": 55.01, "learning_rate": 4.634190874769102e-05, "loss": 0.0085, "step": 229000 }, { "epoch": 55.01, "learning_rate": 4.6338328805744075e-05, "loss": 0.0026, "step": 229010 }, { "epoch": 55.01, "learning_rate": 4.633474888266941e-05, "loss": 0.0037, "step": 229020 }, { "epoch": 55.01, "learning_rate": 4.633116897848551e-05, "loss": 0.0045, "step": 229030 }, { "epoch": 55.02, "learning_rate": 4.632758909321077e-05, "loss": 0.0086, "step": 229040 }, { "epoch": 55.02, "learning_rate": 4.632400922686368e-05, "loss": 0.0045, "step": 229050 }, { "epoch": 55.02, "learning_rate": 4.632042937946266e-05, "loss": 0.0041, "step": 229060 }, { "epoch": 55.02, "learning_rate": 4.63168495510262e-05, "loss": 0.0038, "step": 229070 }, { "epoch": 55.03, "learning_rate": 4.631326974157273e-05, "loss": 0.0042, "step": 229080 }, { "epoch": 55.03, "learning_rate": 4.630968995112068e-05, "loss": 0.0048, "step": 229090 }, { "epoch": 55.03, "learning_rate": 4.6306110179688534e-05, "loss": 0.0051, "step": 229100 }, { "epoch": 55.03, "learning_rate": 4.63025304272947e-05, "loss": 0.005, "step": 229110 }, { "epoch": 55.04, "learning_rate": 4.629895069395769e-05, "loss": 0.0057, "step": 229120 }, { "epoch": 55.04, "learning_rate": 4.629537097969589e-05, "loss": 0.0031, "step": 229130 }, { "epoch": 55.04, "learning_rate": 4.6291791284527805e-05, "loss": 0.0031, "step": 229140 }, { "epoch": 55.04, "learning_rate": 4.628821160847184e-05, "loss": 0.004, "step": 229150 }, { "epoch": 55.04, "learning_rate": 4.628463195154648e-05, "loss": 0.0056, "step": 229160 }, { "epoch": 55.05, "learning_rate": 4.6281052313770143e-05, "loss": 0.0042, "step": 229170 }, { "epoch": 55.05, "learning_rate": 4.6277472695161284e-05, "loss": 0.0052, "step": 229180 }, { "epoch": 55.05, "learning_rate": 4.6273893095738384e-05, "loss": 0.0038, "step": 229190 }, { "epoch": 55.05, "learning_rate": 4.627031351551985e-05, "loss": 0.0034, "step": 229200 }, { "epoch": 55.06, "learning_rate": 4.626673395452417e-05, "loss": 0.0049, "step": 229210 }, { "epoch": 55.06, "learning_rate": 4.626315441276978e-05, "loss": 0.0045, "step": 229220 }, { "epoch": 55.06, "learning_rate": 4.62595748902751e-05, "loss": 0.0048, "step": 229230 }, { "epoch": 55.06, "learning_rate": 4.625599538705863e-05, "loss": 0.0057, "step": 229240 }, { "epoch": 55.07, "learning_rate": 4.6252415903138755e-05, "loss": 0.0028, "step": 229250 }, { "epoch": 55.07, "learning_rate": 4.624883643853399e-05, "loss": 0.0035, "step": 229260 }, { "epoch": 55.07, "learning_rate": 4.624525699326273e-05, "loss": 0.0051, "step": 229270 }, { "epoch": 55.07, "learning_rate": 4.624167756734347e-05, "loss": 0.0036, "step": 229280 }, { "epoch": 55.07, "learning_rate": 4.6238098160794624e-05, "loss": 0.0036, "step": 229290 }, { "epoch": 55.08, "learning_rate": 4.623451877363465e-05, "loss": 0.0036, "step": 229300 }, { "epoch": 55.08, "learning_rate": 4.6230939405882e-05, "loss": 0.0043, "step": 229310 }, { "epoch": 55.08, "learning_rate": 4.622736005755511e-05, "loss": 0.0032, "step": 229320 }, { "epoch": 55.08, "learning_rate": 4.6223780728672454e-05, "loss": 0.0066, "step": 229330 }, { "epoch": 55.09, "learning_rate": 4.6220201419252447e-05, "loss": 0.0033, "step": 229340 }, { "epoch": 55.09, "learning_rate": 4.621662212931357e-05, "loss": 0.0028, "step": 229350 }, { "epoch": 55.09, "learning_rate": 4.621304285887426e-05, "loss": 0.0046, "step": 229360 }, { "epoch": 55.09, "learning_rate": 4.6209463607952935e-05, "loss": 0.0054, "step": 229370 }, { "epoch": 55.09, "learning_rate": 4.620588437656809e-05, "loss": 0.0066, "step": 229380 }, { "epoch": 55.1, "learning_rate": 4.620230516473813e-05, "loss": 0.0064, "step": 229390 }, { "epoch": 55.1, "learning_rate": 4.6198725972481526e-05, "loss": 0.0055, "step": 229400 }, { "epoch": 55.1, "learning_rate": 4.6195146799816715e-05, "loss": 0.0057, "step": 229410 }, { "epoch": 55.1, "learning_rate": 4.619156764676216e-05, "loss": 0.0059, "step": 229420 }, { "epoch": 55.11, "learning_rate": 4.6187988513336294e-05, "loss": 0.0151, "step": 229430 }, { "epoch": 55.11, "learning_rate": 4.6184409399557566e-05, "loss": 0.0025, "step": 229440 }, { "epoch": 55.11, "learning_rate": 4.618083030544442e-05, "loss": 0.0048, "step": 229450 }, { "epoch": 55.11, "learning_rate": 4.617725123101531e-05, "loss": 0.0037, "step": 229460 }, { "epoch": 55.12, "learning_rate": 4.6173672176288676e-05, "loss": 0.0034, "step": 229470 }, { "epoch": 55.12, "learning_rate": 4.617009314128297e-05, "loss": 0.0033, "step": 229480 }, { "epoch": 55.12, "learning_rate": 4.616651412601664e-05, "loss": 0.007, "step": 229490 }, { "epoch": 55.12, "learning_rate": 4.616293513050813e-05, "loss": 0.0032, "step": 229500 }, { "epoch": 55.12, "learning_rate": 4.6159356154775874e-05, "loss": 0.0033, "step": 229510 }, { "epoch": 55.13, "learning_rate": 4.615577719883835e-05, "loss": 0.0056, "step": 229520 }, { "epoch": 55.13, "learning_rate": 4.6152198262713946e-05, "loss": 0.0036, "step": 229530 }, { "epoch": 55.13, "learning_rate": 4.614861934642118e-05, "loss": 0.0027, "step": 229540 }, { "epoch": 55.13, "learning_rate": 4.6145040449978436e-05, "loss": 0.0074, "step": 229550 }, { "epoch": 55.14, "learning_rate": 4.6141461573404204e-05, "loss": 0.0049, "step": 229560 }, { "epoch": 55.14, "learning_rate": 4.613788271671691e-05, "loss": 0.0063, "step": 229570 }, { "epoch": 55.14, "learning_rate": 4.6134303879934985e-05, "loss": 0.0043, "step": 229580 }, { "epoch": 55.14, "learning_rate": 4.61307250630769e-05, "loss": 0.0049, "step": 229590 }, { "epoch": 55.15, "learning_rate": 4.612714626616109e-05, "loss": 0.0052, "step": 229600 }, { "epoch": 55.15, "learning_rate": 4.6123567489205996e-05, "loss": 0.0033, "step": 229610 }, { "epoch": 55.15, "learning_rate": 4.611998873223007e-05, "loss": 0.003, "step": 229620 }, { "epoch": 55.15, "learning_rate": 4.6116409995251755e-05, "loss": 0.0134, "step": 229630 }, { "epoch": 55.15, "learning_rate": 4.611283127828951e-05, "loss": 0.0104, "step": 229640 }, { "epoch": 55.16, "learning_rate": 4.610925258136174e-05, "loss": 0.0048, "step": 229650 }, { "epoch": 55.16, "learning_rate": 4.610567390448694e-05, "loss": 0.0037, "step": 229660 }, { "epoch": 55.16, "learning_rate": 4.61020952476835e-05, "loss": 0.0067, "step": 229670 }, { "epoch": 55.16, "learning_rate": 4.609851661096992e-05, "loss": 0.0033, "step": 229680 }, { "epoch": 55.17, "learning_rate": 4.6094937994364604e-05, "loss": 0.0036, "step": 229690 }, { "epoch": 55.17, "learning_rate": 4.609135939788602e-05, "loss": 0.0033, "step": 229700 }, { "epoch": 55.17, "learning_rate": 4.6087780821552585e-05, "loss": 0.0041, "step": 229710 }, { "epoch": 55.17, "learning_rate": 4.608420226538278e-05, "loss": 0.004, "step": 229720 }, { "epoch": 55.17, "learning_rate": 4.6080623729395036e-05, "loss": 0.004, "step": 229730 }, { "epoch": 55.18, "learning_rate": 4.607704521360776e-05, "loss": 0.0039, "step": 229740 }, { "epoch": 55.18, "learning_rate": 4.607346671803944e-05, "loss": 0.0025, "step": 229750 }, { "epoch": 55.18, "learning_rate": 4.60698882427085e-05, "loss": 0.0031, "step": 229760 }, { "epoch": 55.18, "learning_rate": 4.60663097876334e-05, "loss": 0.0045, "step": 229770 }, { "epoch": 55.19, "learning_rate": 4.6062731352832564e-05, "loss": 0.0028, "step": 229780 }, { "epoch": 55.19, "learning_rate": 4.605915293832445e-05, "loss": 0.0056, "step": 229790 }, { "epoch": 55.19, "learning_rate": 4.60555745441275e-05, "loss": 0.0038, "step": 229800 }, { "epoch": 55.19, "learning_rate": 4.605199617026012e-05, "loss": 0.0035, "step": 229810 }, { "epoch": 55.2, "learning_rate": 4.6048417816740824e-05, "loss": 0.0042, "step": 229820 }, { "epoch": 55.2, "learning_rate": 4.6044839483587986e-05, "loss": 0.0037, "step": 229830 }, { "epoch": 55.2, "learning_rate": 4.604126117082011e-05, "loss": 0.0064, "step": 229840 }, { "epoch": 55.2, "learning_rate": 4.603768287845557e-05, "loss": 0.0053, "step": 229850 }, { "epoch": 55.2, "learning_rate": 4.603410460651288e-05, "loss": 0.0027, "step": 229860 }, { "epoch": 55.21, "learning_rate": 4.603052635501044e-05, "loss": 0.0052, "step": 229870 }, { "epoch": 55.21, "learning_rate": 4.6026948123966676e-05, "loss": 0.0038, "step": 229880 }, { "epoch": 55.21, "learning_rate": 4.602336991340008e-05, "loss": 0.0075, "step": 229890 }, { "epoch": 55.21, "learning_rate": 4.6019791723329055e-05, "loss": 0.0031, "step": 229900 }, { "epoch": 55.22, "learning_rate": 4.601621355377206e-05, "loss": 0.0029, "step": 229910 }, { "epoch": 55.22, "learning_rate": 4.6012635404747534e-05, "loss": 0.0045, "step": 229920 }, { "epoch": 55.22, "learning_rate": 4.600905727627392e-05, "loss": 0.0053, "step": 229930 }, { "epoch": 55.22, "learning_rate": 4.6005479168369666e-05, "loss": 0.0061, "step": 229940 }, { "epoch": 55.23, "learning_rate": 4.6001901081053186e-05, "loss": 0.0028, "step": 229950 }, { "epoch": 55.23, "learning_rate": 4.5998323014342964e-05, "loss": 0.0043, "step": 229960 }, { "epoch": 55.23, "learning_rate": 4.59947449682574e-05, "loss": 0.003, "step": 229970 }, { "epoch": 55.23, "learning_rate": 4.599116694281497e-05, "loss": 0.0043, "step": 229980 }, { "epoch": 55.23, "learning_rate": 4.5987588938034075e-05, "loss": 0.0089, "step": 229990 }, { "epoch": 55.24, "learning_rate": 4.598401095393321e-05, "loss": 0.005, "step": 230000 }, { "epoch": 55.24, "learning_rate": 4.598043299053078e-05, "loss": 0.0045, "step": 230010 }, { "epoch": 55.24, "learning_rate": 4.597685504784521e-05, "loss": 0.0065, "step": 230020 }, { "epoch": 55.24, "learning_rate": 4.597327712589499e-05, "loss": 0.0045, "step": 230030 }, { "epoch": 55.25, "learning_rate": 4.596969922469851e-05, "loss": 0.0051, "step": 230040 }, { "epoch": 55.25, "learning_rate": 4.5966121344274235e-05, "loss": 0.004, "step": 230050 }, { "epoch": 55.25, "learning_rate": 4.596254348464062e-05, "loss": 0.004, "step": 230060 }, { "epoch": 55.25, "learning_rate": 4.595896564581608e-05, "loss": 0.0026, "step": 230070 }, { "epoch": 55.25, "learning_rate": 4.595538782781908e-05, "loss": 0.0027, "step": 230080 }, { "epoch": 55.26, "learning_rate": 4.595181003066802e-05, "loss": 0.0033, "step": 230090 }, { "epoch": 55.26, "learning_rate": 4.5948232254381384e-05, "loss": 0.0051, "step": 230100 }, { "epoch": 55.26, "learning_rate": 4.594465449897758e-05, "loss": 0.0037, "step": 230110 }, { "epoch": 55.26, "learning_rate": 4.594107676447507e-05, "loss": 0.0039, "step": 230120 }, { "epoch": 55.27, "learning_rate": 4.5937499050892276e-05, "loss": 0.0028, "step": 230130 }, { "epoch": 55.27, "learning_rate": 4.5933921358247654e-05, "loss": 0.008, "step": 230140 }, { "epoch": 55.27, "learning_rate": 4.593034368655965e-05, "loss": 0.0029, "step": 230150 }, { "epoch": 55.27, "learning_rate": 4.592676603584666e-05, "loss": 0.0024, "step": 230160 }, { "epoch": 55.28, "learning_rate": 4.592318840612717e-05, "loss": 0.0056, "step": 230170 }, { "epoch": 55.28, "learning_rate": 4.5919610797419585e-05, "loss": 0.0029, "step": 230180 }, { "epoch": 55.28, "learning_rate": 4.5916033209742375e-05, "loss": 0.0031, "step": 230190 }, { "epoch": 55.28, "learning_rate": 4.591245564311394e-05, "loss": 0.003, "step": 230200 }, { "epoch": 55.28, "learning_rate": 4.590887809755277e-05, "loss": 0.0032, "step": 230210 }, { "epoch": 55.29, "learning_rate": 4.590530057307727e-05, "loss": 0.003, "step": 230220 }, { "epoch": 55.29, "learning_rate": 4.590172306970587e-05, "loss": 0.0065, "step": 230230 }, { "epoch": 55.29, "learning_rate": 4.5898145587457054e-05, "loss": 0.0039, "step": 230240 }, { "epoch": 55.29, "learning_rate": 4.58945681263492e-05, "loss": 0.0034, "step": 230250 }, { "epoch": 55.3, "learning_rate": 4.589099068640079e-05, "loss": 0.0056, "step": 230260 }, { "epoch": 55.3, "learning_rate": 4.5887413267630244e-05, "loss": 0.006, "step": 230270 }, { "epoch": 55.3, "learning_rate": 4.588383587005601e-05, "loss": 0.0091, "step": 230280 }, { "epoch": 55.3, "learning_rate": 4.588025849369653e-05, "loss": 0.0027, "step": 230290 }, { "epoch": 55.31, "learning_rate": 4.58766811385702e-05, "loss": 0.0049, "step": 230300 }, { "epoch": 55.31, "learning_rate": 4.5873103804695524e-05, "loss": 0.0043, "step": 230310 }, { "epoch": 55.31, "learning_rate": 4.586952649209088e-05, "loss": 0.0037, "step": 230320 }, { "epoch": 55.31, "learning_rate": 4.586594920077475e-05, "loss": 0.0091, "step": 230330 }, { "epoch": 55.31, "learning_rate": 4.586237193076553e-05, "loss": 0.0039, "step": 230340 }, { "epoch": 55.32, "learning_rate": 4.585879468208171e-05, "loss": 0.006, "step": 230350 }, { "epoch": 55.32, "learning_rate": 4.585521745474168e-05, "loss": 0.0045, "step": 230360 }, { "epoch": 55.32, "learning_rate": 4.585164024876388e-05, "loss": 0.0035, "step": 230370 }, { "epoch": 55.32, "learning_rate": 4.584806306416678e-05, "loss": 0.0034, "step": 230380 }, { "epoch": 55.33, "learning_rate": 4.5844485900968783e-05, "loss": 0.0031, "step": 230390 }, { "epoch": 55.33, "learning_rate": 4.584090875918836e-05, "loss": 0.0029, "step": 230400 }, { "epoch": 55.33, "learning_rate": 4.583733163884391e-05, "loss": 0.0045, "step": 230410 }, { "epoch": 55.33, "learning_rate": 4.583375453995391e-05, "loss": 0.0037, "step": 230420 }, { "epoch": 55.33, "learning_rate": 4.5830177462536765e-05, "loss": 0.0042, "step": 230430 }, { "epoch": 55.34, "learning_rate": 4.58266004066109e-05, "loss": 0.0077, "step": 230440 }, { "epoch": 55.34, "learning_rate": 4.58230233721948e-05, "loss": 0.0055, "step": 230450 }, { "epoch": 55.34, "learning_rate": 4.581944635930685e-05, "loss": 0.0069, "step": 230460 }, { "epoch": 55.34, "learning_rate": 4.5815869367965523e-05, "loss": 0.0037, "step": 230470 }, { "epoch": 55.35, "learning_rate": 4.5812292398189226e-05, "loss": 0.0045, "step": 230480 }, { "epoch": 55.35, "learning_rate": 4.5808715449996426e-05, "loss": 0.0051, "step": 230490 }, { "epoch": 55.35, "learning_rate": 4.580513852340552e-05, "loss": 0.0037, "step": 230500 }, { "epoch": 55.35, "learning_rate": 4.580156161843499e-05, "loss": 0.0023, "step": 230510 }, { "epoch": 55.36, "learning_rate": 4.5797984735103236e-05, "loss": 0.0034, "step": 230520 }, { "epoch": 55.36, "learning_rate": 4.5794407873428685e-05, "loss": 0.0046, "step": 230530 }, { "epoch": 55.36, "learning_rate": 4.579083103342982e-05, "loss": 0.0035, "step": 230540 }, { "epoch": 55.36, "learning_rate": 4.5787254215125025e-05, "loss": 0.003, "step": 230550 }, { "epoch": 55.36, "learning_rate": 4.578367741853278e-05, "loss": 0.003, "step": 230560 }, { "epoch": 55.37, "learning_rate": 4.578010064367147e-05, "loss": 0.0024, "step": 230570 }, { "epoch": 55.37, "learning_rate": 4.577652389055958e-05, "loss": 0.0029, "step": 230580 }, { "epoch": 55.37, "learning_rate": 4.577294715921552e-05, "loss": 0.0041, "step": 230590 }, { "epoch": 55.37, "learning_rate": 4.576937044965771e-05, "loss": 0.0048, "step": 230600 }, { "epoch": 55.38, "learning_rate": 4.576579376190462e-05, "loss": 0.0033, "step": 230610 }, { "epoch": 55.38, "learning_rate": 4.5762217095974634e-05, "loss": 0.0032, "step": 230620 }, { "epoch": 55.38, "learning_rate": 4.5758640451886245e-05, "loss": 0.0027, "step": 230630 }, { "epoch": 55.38, "learning_rate": 4.575506382965784e-05, "loss": 0.0033, "step": 230640 }, { "epoch": 55.39, "learning_rate": 4.575148722930789e-05, "loss": 0.0037, "step": 230650 }, { "epoch": 55.39, "learning_rate": 4.5747910650854794e-05, "loss": 0.0029, "step": 230660 }, { "epoch": 55.39, "learning_rate": 4.574433409431701e-05, "loss": 0.0026, "step": 230670 }, { "epoch": 55.39, "learning_rate": 4.574075755971296e-05, "loss": 0.0034, "step": 230680 }, { "epoch": 55.39, "learning_rate": 4.573718104706107e-05, "loss": 0.0054, "step": 230690 }, { "epoch": 55.4, "learning_rate": 4.573360455637981e-05, "loss": 0.0054, "step": 230700 }, { "epoch": 55.4, "learning_rate": 4.573002808768756e-05, "loss": 0.0038, "step": 230710 }, { "epoch": 55.4, "learning_rate": 4.572645164100281e-05, "loss": 0.0049, "step": 230720 }, { "epoch": 55.4, "learning_rate": 4.572287521634396e-05, "loss": 0.004, "step": 230730 }, { "epoch": 55.41, "learning_rate": 4.571929881372943e-05, "loss": 0.0064, "step": 230740 }, { "epoch": 55.41, "learning_rate": 4.5715722433177684e-05, "loss": 0.0028, "step": 230750 }, { "epoch": 55.41, "learning_rate": 4.571214607470712e-05, "loss": 0.0032, "step": 230760 }, { "epoch": 55.41, "learning_rate": 4.570856973833622e-05, "loss": 0.0032, "step": 230770 }, { "epoch": 55.41, "learning_rate": 4.570499342408335e-05, "loss": 0.0048, "step": 230780 }, { "epoch": 55.42, "learning_rate": 4.570141713196701e-05, "loss": 0.0028, "step": 230790 }, { "epoch": 55.42, "learning_rate": 4.56978408620056e-05, "loss": 0.0022, "step": 230800 }, { "epoch": 55.42, "learning_rate": 4.569426461421754e-05, "loss": 0.003, "step": 230810 }, { "epoch": 55.42, "learning_rate": 4.5690688388621284e-05, "loss": 0.0031, "step": 230820 }, { "epoch": 55.43, "learning_rate": 4.5687112185235255e-05, "loss": 0.0034, "step": 230830 }, { "epoch": 55.43, "learning_rate": 4.568353600407789e-05, "loss": 0.003, "step": 230840 }, { "epoch": 55.43, "learning_rate": 4.5679959845167595e-05, "loss": 0.0064, "step": 230850 }, { "epoch": 55.43, "learning_rate": 4.567638370852285e-05, "loss": 0.0026, "step": 230860 }, { "epoch": 55.44, "learning_rate": 4.567280759416206e-05, "loss": 0.0053, "step": 230870 }, { "epoch": 55.44, "learning_rate": 4.566923150210364e-05, "loss": 0.0092, "step": 230880 }, { "epoch": 55.44, "learning_rate": 4.566565543236605e-05, "loss": 0.0059, "step": 230890 }, { "epoch": 55.44, "learning_rate": 4.566207938496769e-05, "loss": 0.0043, "step": 230900 }, { "epoch": 55.44, "learning_rate": 4.565850335992703e-05, "loss": 0.0027, "step": 230910 }, { "epoch": 55.45, "learning_rate": 4.565492735726246e-05, "loss": 0.0052, "step": 230920 }, { "epoch": 55.45, "learning_rate": 4.565135137699245e-05, "loss": 0.0024, "step": 230930 }, { "epoch": 55.45, "learning_rate": 4.564777541913541e-05, "loss": 0.0029, "step": 230940 }, { "epoch": 55.45, "learning_rate": 4.564419948370976e-05, "loss": 0.003, "step": 230950 }, { "epoch": 55.46, "learning_rate": 4.5640623570733945e-05, "loss": 0.0047, "step": 230960 }, { "epoch": 55.46, "learning_rate": 4.563704768022639e-05, "loss": 0.0039, "step": 230970 }, { "epoch": 55.46, "learning_rate": 4.563347181220554e-05, "loss": 0.0021, "step": 230980 }, { "epoch": 55.46, "learning_rate": 4.56298959666898e-05, "loss": 0.0056, "step": 230990 }, { "epoch": 55.47, "learning_rate": 4.562632014369762e-05, "loss": 0.004, "step": 231000 }, { "epoch": 55.47, "learning_rate": 4.562274434324742e-05, "loss": 0.0041, "step": 231010 }, { "epoch": 55.47, "learning_rate": 4.561916856535763e-05, "loss": 0.0046, "step": 231020 }, { "epoch": 55.47, "learning_rate": 4.5615592810046693e-05, "loss": 0.0044, "step": 231030 }, { "epoch": 55.47, "learning_rate": 4.5612017077333e-05, "loss": 0.0038, "step": 231040 }, { "epoch": 55.48, "learning_rate": 4.560844136723504e-05, "loss": 0.0066, "step": 231050 }, { "epoch": 55.48, "learning_rate": 4.5604865679771186e-05, "loss": 0.0077, "step": 231060 }, { "epoch": 55.48, "learning_rate": 4.560129001495991e-05, "loss": 0.0048, "step": 231070 }, { "epoch": 55.48, "learning_rate": 4.5597714372819624e-05, "loss": 0.0044, "step": 231080 }, { "epoch": 55.49, "learning_rate": 4.559413875336873e-05, "loss": 0.0059, "step": 231090 }, { "epoch": 55.49, "learning_rate": 4.55905631566257e-05, "loss": 0.0036, "step": 231100 }, { "epoch": 55.49, "learning_rate": 4.558698758260894e-05, "loss": 0.0038, "step": 231110 }, { "epoch": 55.49, "learning_rate": 4.558341203133688e-05, "loss": 0.0034, "step": 231120 }, { "epoch": 55.49, "learning_rate": 4.557983650282795e-05, "loss": 0.0114, "step": 231130 }, { "epoch": 55.5, "learning_rate": 4.5576260997100585e-05, "loss": 0.0049, "step": 231140 }, { "epoch": 55.5, "learning_rate": 4.557268551417322e-05, "loss": 0.0036, "step": 231150 }, { "epoch": 55.5, "learning_rate": 4.556911005406424e-05, "loss": 0.0037, "step": 231160 }, { "epoch": 55.5, "learning_rate": 4.5565534616792135e-05, "loss": 0.0052, "step": 231170 }, { "epoch": 55.51, "learning_rate": 4.5561959202375276e-05, "loss": 0.0051, "step": 231180 }, { "epoch": 55.51, "learning_rate": 4.555838381083214e-05, "loss": 0.0069, "step": 231190 }, { "epoch": 55.51, "learning_rate": 4.555480844218111e-05, "loss": 0.0042, "step": 231200 }, { "epoch": 55.51, "learning_rate": 4.5551233096440646e-05, "loss": 0.0037, "step": 231210 }, { "epoch": 55.52, "learning_rate": 4.5547657773629174e-05, "loss": 0.0039, "step": 231220 }, { "epoch": 55.52, "learning_rate": 4.5544082473765084e-05, "loss": 0.0055, "step": 231230 }, { "epoch": 55.52, "learning_rate": 4.5540507196866864e-05, "loss": 0.0036, "step": 231240 }, { "epoch": 55.52, "learning_rate": 4.553693194295287e-05, "loss": 0.0035, "step": 231250 }, { "epoch": 55.52, "learning_rate": 4.5533356712041584e-05, "loss": 0.0056, "step": 231260 }, { "epoch": 55.53, "learning_rate": 4.5529781504151415e-05, "loss": 0.0037, "step": 231270 }, { "epoch": 55.53, "learning_rate": 4.5526206319300793e-05, "loss": 0.003, "step": 231280 }, { "epoch": 55.53, "learning_rate": 4.5522631157508136e-05, "loss": 0.0029, "step": 231290 }, { "epoch": 55.53, "learning_rate": 4.5519056018791875e-05, "loss": 0.0041, "step": 231300 }, { "epoch": 55.54, "learning_rate": 4.551548090317044e-05, "loss": 0.006, "step": 231310 }, { "epoch": 55.54, "learning_rate": 4.551190581066225e-05, "loss": 0.0025, "step": 231320 }, { "epoch": 55.54, "learning_rate": 4.5508330741285744e-05, "loss": 0.0051, "step": 231330 }, { "epoch": 55.54, "learning_rate": 4.550475569505932e-05, "loss": 0.0069, "step": 231340 }, { "epoch": 55.55, "learning_rate": 4.5501180672001445e-05, "loss": 0.0033, "step": 231350 }, { "epoch": 55.55, "learning_rate": 4.54976056721305e-05, "loss": 0.0092, "step": 231360 }, { "epoch": 55.55, "learning_rate": 4.549403069546496e-05, "loss": 0.0033, "step": 231370 }, { "epoch": 55.55, "learning_rate": 4.5490455742023214e-05, "loss": 0.0041, "step": 231380 }, { "epoch": 55.55, "learning_rate": 4.5486880811823683e-05, "loss": 0.005, "step": 231390 }, { "epoch": 55.56, "learning_rate": 4.548330590488482e-05, "loss": 0.0033, "step": 231400 }, { "epoch": 55.56, "learning_rate": 4.547973102122502e-05, "loss": 0.0043, "step": 231410 }, { "epoch": 55.56, "learning_rate": 4.547615616086274e-05, "loss": 0.0093, "step": 231420 }, { "epoch": 55.56, "learning_rate": 4.547258132381638e-05, "loss": 0.0031, "step": 231430 }, { "epoch": 55.57, "learning_rate": 4.546900651010438e-05, "loss": 0.0051, "step": 231440 }, { "epoch": 55.57, "learning_rate": 4.5465431719745164e-05, "loss": 0.0032, "step": 231450 }, { "epoch": 55.57, "learning_rate": 4.546185695275713e-05, "loss": 0.0042, "step": 231460 }, { "epoch": 55.57, "learning_rate": 4.545828220915875e-05, "loss": 0.0058, "step": 231470 }, { "epoch": 55.57, "learning_rate": 4.545470748896839e-05, "loss": 0.0089, "step": 231480 }, { "epoch": 55.58, "learning_rate": 4.5451132792204535e-05, "loss": 0.0037, "step": 231490 }, { "epoch": 55.58, "learning_rate": 4.544755811888556e-05, "loss": 0.0127, "step": 231500 }, { "epoch": 55.58, "learning_rate": 4.544398346902992e-05, "loss": 0.0039, "step": 231510 }, { "epoch": 55.58, "learning_rate": 4.544040884265604e-05, "loss": 0.0057, "step": 231520 }, { "epoch": 55.59, "learning_rate": 4.54368342397823e-05, "loss": 0.0057, "step": 231530 }, { "epoch": 55.59, "learning_rate": 4.543325966042718e-05, "loss": 0.0028, "step": 231540 }, { "epoch": 55.59, "learning_rate": 4.542968510460905e-05, "loss": 0.0089, "step": 231550 }, { "epoch": 55.59, "learning_rate": 4.542611057234639e-05, "loss": 0.0034, "step": 231560 }, { "epoch": 55.6, "learning_rate": 4.5422536063657575e-05, "loss": 0.0077, "step": 231570 }, { "epoch": 55.6, "learning_rate": 4.541896157856105e-05, "loss": 0.0076, "step": 231580 }, { "epoch": 55.6, "learning_rate": 4.541538711707525e-05, "loss": 0.0051, "step": 231590 }, { "epoch": 55.6, "learning_rate": 4.541181267921856e-05, "loss": 0.0095, "step": 231600 }, { "epoch": 55.6, "learning_rate": 4.540823826500945e-05, "loss": 0.0122, "step": 231610 }, { "epoch": 55.61, "learning_rate": 4.54046638744663e-05, "loss": 0.0092, "step": 231620 }, { "epoch": 55.61, "learning_rate": 4.5401089507607565e-05, "loss": 0.0042, "step": 231630 }, { "epoch": 55.61, "learning_rate": 4.539751516445163e-05, "loss": 0.0028, "step": 231640 }, { "epoch": 55.61, "learning_rate": 4.539394084501697e-05, "loss": 0.0039, "step": 231650 }, { "epoch": 55.62, "learning_rate": 4.539036654932197e-05, "loss": 0.0043, "step": 231660 }, { "epoch": 55.62, "learning_rate": 4.538679227738505e-05, "loss": 0.0051, "step": 231670 }, { "epoch": 55.62, "learning_rate": 4.538321802922465e-05, "loss": 0.0035, "step": 231680 }, { "epoch": 55.62, "learning_rate": 4.537964380485917e-05, "loss": 0.0025, "step": 231690 }, { "epoch": 55.62, "learning_rate": 4.537606960430706e-05, "loss": 0.0029, "step": 231700 }, { "epoch": 55.63, "learning_rate": 4.5372495427586703e-05, "loss": 0.0054, "step": 231710 }, { "epoch": 55.63, "learning_rate": 4.536892127471656e-05, "loss": 0.0027, "step": 231720 }, { "epoch": 55.63, "learning_rate": 4.5365347145715043e-05, "loss": 0.0032, "step": 231730 }, { "epoch": 55.63, "learning_rate": 4.536177304060054e-05, "loss": 0.0061, "step": 231740 }, { "epoch": 55.64, "learning_rate": 4.535819895939153e-05, "loss": 0.0048, "step": 231750 }, { "epoch": 55.64, "learning_rate": 4.5354624902106365e-05, "loss": 0.0042, "step": 231760 }, { "epoch": 55.64, "learning_rate": 4.5351050868763534e-05, "loss": 0.0049, "step": 231770 }, { "epoch": 55.64, "learning_rate": 4.534747685938141e-05, "loss": 0.0039, "step": 231780 }, { "epoch": 55.65, "learning_rate": 4.534390287397844e-05, "loss": 0.0042, "step": 231790 }, { "epoch": 55.65, "learning_rate": 4.534032891257303e-05, "loss": 0.0045, "step": 231800 }, { "epoch": 55.65, "learning_rate": 4.5336754975183594e-05, "loss": 0.0082, "step": 231810 }, { "epoch": 55.65, "learning_rate": 4.533318106182858e-05, "loss": 0.0029, "step": 231820 }, { "epoch": 55.65, "learning_rate": 4.532960717252636e-05, "loss": 0.0026, "step": 231830 }, { "epoch": 55.66, "learning_rate": 4.532603330729541e-05, "loss": 0.005, "step": 231840 }, { "epoch": 55.66, "learning_rate": 4.5322459466154106e-05, "loss": 0.005, "step": 231850 }, { "epoch": 55.66, "learning_rate": 4.5318885649120904e-05, "loss": 0.0054, "step": 231860 }, { "epoch": 55.66, "learning_rate": 4.5315311856214195e-05, "loss": 0.0027, "step": 231870 }, { "epoch": 55.67, "learning_rate": 4.531173808745239e-05, "loss": 0.0063, "step": 231880 }, { "epoch": 55.67, "learning_rate": 4.5308164342853956e-05, "loss": 0.0025, "step": 231890 }, { "epoch": 55.67, "learning_rate": 4.530459062243726e-05, "loss": 0.0033, "step": 231900 }, { "epoch": 55.67, "learning_rate": 4.5301016926220766e-05, "loss": 0.0069, "step": 231910 }, { "epoch": 55.68, "learning_rate": 4.529744325422284e-05, "loss": 0.0032, "step": 231920 }, { "epoch": 55.68, "learning_rate": 4.5293869606461955e-05, "loss": 0.0052, "step": 231930 }, { "epoch": 55.68, "learning_rate": 4.529029598295651e-05, "loss": 0.0051, "step": 231940 }, { "epoch": 55.68, "learning_rate": 4.528672238372489e-05, "loss": 0.0044, "step": 231950 }, { "epoch": 55.68, "learning_rate": 4.528314880878557e-05, "loss": 0.0058, "step": 231960 }, { "epoch": 55.69, "learning_rate": 4.527957525815692e-05, "loss": 0.0035, "step": 231970 }, { "epoch": 55.69, "learning_rate": 4.52760017318574e-05, "loss": 0.0028, "step": 231980 }, { "epoch": 55.69, "learning_rate": 4.527242822990538e-05, "loss": 0.004, "step": 231990 }, { "epoch": 55.69, "learning_rate": 4.5268854752319326e-05, "loss": 0.0064, "step": 232000 }, { "epoch": 55.7, "learning_rate": 4.526528129911763e-05, "loss": 0.0038, "step": 232010 }, { "epoch": 55.7, "learning_rate": 4.526170787031871e-05, "loss": 0.0092, "step": 232020 }, { "epoch": 55.7, "learning_rate": 4.5258134465940985e-05, "loss": 0.0024, "step": 232030 }, { "epoch": 55.7, "learning_rate": 4.5254561086002866e-05, "loss": 0.003, "step": 232040 }, { "epoch": 55.7, "learning_rate": 4.52509877305228e-05, "loss": 0.0041, "step": 232050 }, { "epoch": 55.71, "learning_rate": 4.5247414399519164e-05, "loss": 0.0031, "step": 232060 }, { "epoch": 55.71, "learning_rate": 4.524384109301041e-05, "loss": 0.0038, "step": 232070 }, { "epoch": 55.71, "learning_rate": 4.524026781101492e-05, "loss": 0.0032, "step": 232080 }, { "epoch": 55.71, "learning_rate": 4.523669455355116e-05, "loss": 0.0037, "step": 232090 }, { "epoch": 55.72, "learning_rate": 4.52331213206375e-05, "loss": 0.0081, "step": 232100 }, { "epoch": 55.72, "learning_rate": 4.5229548112292367e-05, "loss": 0.0042, "step": 232110 }, { "epoch": 55.72, "learning_rate": 4.5225974928534186e-05, "loss": 0.0042, "step": 232120 }, { "epoch": 55.72, "learning_rate": 4.522240176938136e-05, "loss": 0.0064, "step": 232130 }, { "epoch": 55.73, "learning_rate": 4.521882863485234e-05, "loss": 0.0022, "step": 232140 }, { "epoch": 55.73, "learning_rate": 4.5215255524965485e-05, "loss": 0.0041, "step": 232150 }, { "epoch": 55.73, "learning_rate": 4.521168243973927e-05, "loss": 0.0041, "step": 232160 }, { "epoch": 55.73, "learning_rate": 4.5208109379192076e-05, "loss": 0.0025, "step": 232170 }, { "epoch": 55.73, "learning_rate": 4.520453634334232e-05, "loss": 0.003, "step": 232180 }, { "epoch": 55.74, "learning_rate": 4.520096333220844e-05, "loss": 0.0029, "step": 232190 }, { "epoch": 55.74, "learning_rate": 4.5197390345808805e-05, "loss": 0.0065, "step": 232200 }, { "epoch": 55.74, "learning_rate": 4.5193817384161894e-05, "loss": 0.0038, "step": 232210 }, { "epoch": 55.74, "learning_rate": 4.5190244447286055e-05, "loss": 0.0069, "step": 232220 }, { "epoch": 55.75, "learning_rate": 4.5186671535199766e-05, "loss": 0.0055, "step": 232230 }, { "epoch": 55.75, "learning_rate": 4.518309864792141e-05, "loss": 0.004, "step": 232240 }, { "epoch": 55.75, "learning_rate": 4.5179525785469385e-05, "loss": 0.0033, "step": 232250 }, { "epoch": 55.75, "learning_rate": 4.517595294786214e-05, "loss": 0.0033, "step": 232260 }, { "epoch": 55.76, "learning_rate": 4.517238013511806e-05, "loss": 0.007, "step": 232270 }, { "epoch": 55.76, "learning_rate": 4.516880734725559e-05, "loss": 0.0033, "step": 232280 }, { "epoch": 55.76, "learning_rate": 4.5165234584293104e-05, "loss": 0.003, "step": 232290 }, { "epoch": 55.76, "learning_rate": 4.516166184624907e-05, "loss": 0.0057, "step": 232300 }, { "epoch": 55.76, "learning_rate": 4.515808913314185e-05, "loss": 0.0037, "step": 232310 }, { "epoch": 55.77, "learning_rate": 4.5154516444989884e-05, "loss": 0.0034, "step": 232320 }, { "epoch": 55.77, "learning_rate": 4.515094378181158e-05, "loss": 0.0029, "step": 232330 }, { "epoch": 55.77, "learning_rate": 4.514737114362535e-05, "loss": 0.003, "step": 232340 }, { "epoch": 55.77, "learning_rate": 4.5143798530449614e-05, "loss": 0.008, "step": 232350 }, { "epoch": 55.78, "learning_rate": 4.514022594230277e-05, "loss": 0.007, "step": 232360 }, { "epoch": 55.78, "learning_rate": 4.5136653379203256e-05, "loss": 0.0024, "step": 232370 }, { "epoch": 55.78, "learning_rate": 4.5133080841169475e-05, "loss": 0.0072, "step": 232380 }, { "epoch": 55.78, "learning_rate": 4.5129508328219816e-05, "loss": 0.0029, "step": 232390 }, { "epoch": 55.78, "learning_rate": 4.512593584037274e-05, "loss": 0.0101, "step": 232400 }, { "epoch": 55.79, "learning_rate": 4.5122363377646596e-05, "loss": 0.0034, "step": 232410 }, { "epoch": 55.79, "learning_rate": 4.5118790940059864e-05, "loss": 0.003, "step": 232420 }, { "epoch": 55.79, "learning_rate": 4.51152185276309e-05, "loss": 0.0024, "step": 232430 }, { "epoch": 55.79, "learning_rate": 4.511164614037816e-05, "loss": 0.0038, "step": 232440 }, { "epoch": 55.8, "learning_rate": 4.510807377832003e-05, "loss": 0.0064, "step": 232450 }, { "epoch": 55.8, "learning_rate": 4.5104501441474925e-05, "loss": 0.0153, "step": 232460 }, { "epoch": 55.8, "learning_rate": 4.5100929129861264e-05, "loss": 0.0029, "step": 232470 }, { "epoch": 55.8, "learning_rate": 4.509735684349745e-05, "loss": 0.003, "step": 232480 }, { "epoch": 55.81, "learning_rate": 4.5093784582401906e-05, "loss": 0.0081, "step": 232490 }, { "epoch": 55.81, "learning_rate": 4.509021234659303e-05, "loss": 0.0048, "step": 232500 }, { "epoch": 55.81, "learning_rate": 4.5086640136089245e-05, "loss": 0.0049, "step": 232510 }, { "epoch": 55.81, "learning_rate": 4.508306795090897e-05, "loss": 0.0042, "step": 232520 }, { "epoch": 55.81, "learning_rate": 4.507949579107058e-05, "loss": 0.0243, "step": 232530 }, { "epoch": 55.82, "learning_rate": 4.5075923656592534e-05, "loss": 0.0031, "step": 232540 }, { "epoch": 55.82, "learning_rate": 4.5072351547493195e-05, "loss": 0.0029, "step": 232550 }, { "epoch": 55.82, "learning_rate": 4.5068779463791014e-05, "loss": 0.0034, "step": 232560 }, { "epoch": 55.82, "learning_rate": 4.5065207405504375e-05, "loss": 0.0031, "step": 232570 }, { "epoch": 55.83, "learning_rate": 4.506163537265171e-05, "loss": 0.0063, "step": 232580 }, { "epoch": 55.83, "learning_rate": 4.505806336525142e-05, "loss": 0.0029, "step": 232590 }, { "epoch": 55.83, "learning_rate": 4.5054491383321896e-05, "loss": 0.003, "step": 232600 }, { "epoch": 55.83, "learning_rate": 4.5050919426881564e-05, "loss": 0.0069, "step": 232610 }, { "epoch": 55.84, "learning_rate": 4.504734749594884e-05, "loss": 0.007, "step": 232620 }, { "epoch": 55.84, "learning_rate": 4.504377559054214e-05, "loss": 0.0047, "step": 232630 }, { "epoch": 55.84, "learning_rate": 4.504020371067985e-05, "loss": 0.0035, "step": 232640 }, { "epoch": 55.84, "learning_rate": 4.503663185638039e-05, "loss": 0.003, "step": 232650 }, { "epoch": 55.84, "learning_rate": 4.503306002766219e-05, "loss": 0.0036, "step": 232660 }, { "epoch": 55.85, "learning_rate": 4.502948822454362e-05, "loss": 0.0026, "step": 232670 }, { "epoch": 55.85, "learning_rate": 4.5025916447043114e-05, "loss": 0.0045, "step": 232680 }, { "epoch": 55.85, "learning_rate": 4.502234469517907e-05, "loss": 0.0028, "step": 232690 }, { "epoch": 55.85, "learning_rate": 4.501877296896992e-05, "loss": 0.0046, "step": 232700 }, { "epoch": 55.86, "learning_rate": 4.501520126843403e-05, "loss": 0.0033, "step": 232710 }, { "epoch": 55.86, "learning_rate": 4.501162959358987e-05, "loss": 0.0027, "step": 232720 }, { "epoch": 55.86, "learning_rate": 4.500805794445579e-05, "loss": 0.0025, "step": 232730 }, { "epoch": 55.86, "learning_rate": 4.500448632105022e-05, "loss": 0.0036, "step": 232740 }, { "epoch": 55.86, "learning_rate": 4.5000914723391585e-05, "loss": 0.0062, "step": 232750 }, { "epoch": 55.87, "learning_rate": 4.499734315149825e-05, "loss": 0.0034, "step": 232760 }, { "epoch": 55.87, "learning_rate": 4.499377160538867e-05, "loss": 0.0035, "step": 232770 }, { "epoch": 55.87, "learning_rate": 4.499020008508122e-05, "loss": 0.0037, "step": 232780 }, { "epoch": 55.87, "learning_rate": 4.498662859059433e-05, "loss": 0.004, "step": 232790 }, { "epoch": 55.88, "learning_rate": 4.4983057121946414e-05, "loss": 0.0062, "step": 232800 }, { "epoch": 55.88, "learning_rate": 4.497948567915583e-05, "loss": 0.0023, "step": 232810 }, { "epoch": 55.88, "learning_rate": 4.497591426224105e-05, "loss": 0.0022, "step": 232820 }, { "epoch": 55.88, "learning_rate": 4.4972342871220425e-05, "loss": 0.0047, "step": 232830 }, { "epoch": 55.89, "learning_rate": 4.496877150611241e-05, "loss": 0.0023, "step": 232840 }, { "epoch": 55.89, "learning_rate": 4.496520016693536e-05, "loss": 0.0034, "step": 232850 }, { "epoch": 55.89, "learning_rate": 4.496162885370774e-05, "loss": 0.0062, "step": 232860 }, { "epoch": 55.89, "learning_rate": 4.495805756644792e-05, "loss": 0.0042, "step": 232870 }, { "epoch": 55.89, "learning_rate": 4.4954486305174295e-05, "loss": 0.0026, "step": 232880 }, { "epoch": 55.9, "learning_rate": 4.4950915069905315e-05, "loss": 0.0034, "step": 232890 }, { "epoch": 55.9, "learning_rate": 4.4947343860659336e-05, "loss": 0.0357, "step": 232900 }, { "epoch": 55.9, "learning_rate": 4.494377267745481e-05, "loss": 0.0044, "step": 232910 }, { "epoch": 55.9, "learning_rate": 4.49402015203101e-05, "loss": 0.0061, "step": 232920 }, { "epoch": 55.91, "learning_rate": 4.493663038924365e-05, "loss": 0.004, "step": 232930 }, { "epoch": 55.91, "learning_rate": 4.4933059284273845e-05, "loss": 0.0034, "step": 232940 }, { "epoch": 55.91, "learning_rate": 4.492948820541909e-05, "loss": 0.0027, "step": 232950 }, { "epoch": 55.91, "learning_rate": 4.492591715269782e-05, "loss": 0.0025, "step": 232960 }, { "epoch": 55.92, "learning_rate": 4.492234612612838e-05, "loss": 0.0038, "step": 232970 }, { "epoch": 55.92, "learning_rate": 4.491877512572923e-05, "loss": 0.0023, "step": 232980 }, { "epoch": 55.92, "learning_rate": 4.491520415151875e-05, "loss": 0.0031, "step": 232990 }, { "epoch": 55.92, "learning_rate": 4.4911633203515355e-05, "loss": 0.0026, "step": 233000 }, { "epoch": 55.92, "learning_rate": 4.4908062281737436e-05, "loss": 0.0023, "step": 233010 }, { "epoch": 55.93, "learning_rate": 4.4904491386203424e-05, "loss": 0.0025, "step": 233020 }, { "epoch": 55.93, "learning_rate": 4.49009205169317e-05, "loss": 0.003, "step": 233030 }, { "epoch": 55.93, "learning_rate": 4.4897349673940655e-05, "loss": 0.0025, "step": 233040 }, { "epoch": 55.93, "learning_rate": 4.489377885724874e-05, "loss": 0.0034, "step": 233050 }, { "epoch": 55.94, "learning_rate": 4.489020806687431e-05, "loss": 0.0042, "step": 233060 }, { "epoch": 55.94, "learning_rate": 4.488663730283581e-05, "loss": 0.0031, "step": 233070 }, { "epoch": 55.94, "learning_rate": 4.48830665651516e-05, "loss": 0.0034, "step": 233080 }, { "epoch": 55.94, "learning_rate": 4.487949585384012e-05, "loss": 0.0034, "step": 233090 }, { "epoch": 55.94, "learning_rate": 4.4875925168919766e-05, "loss": 0.0056, "step": 233100 }, { "epoch": 55.95, "learning_rate": 4.487235451040892e-05, "loss": 0.0049, "step": 233110 }, { "epoch": 55.95, "learning_rate": 4.4868783878326024e-05, "loss": 0.0031, "step": 233120 }, { "epoch": 56.0, "learning_rate": 4.4865213272689444e-05, "loss": 0.0051, "step": 233130 }, { "epoch": 56.0, "learning_rate": 4.486164269351761e-05, "loss": 0.0035, "step": 233140 }, { "epoch": 56.01, "learning_rate": 4.48580721408289e-05, "loss": 0.0048, "step": 233150 }, { "epoch": 56.01, "learning_rate": 4.485450161464174e-05, "loss": 0.0034, "step": 233160 }, { "epoch": 56.01, "learning_rate": 4.4850931114974524e-05, "loss": 0.0028, "step": 233170 }, { "epoch": 56.01, "learning_rate": 4.484736064184563e-05, "loss": 0.0022, "step": 233180 }, { "epoch": 56.01, "learning_rate": 4.4843790195273504e-05, "loss": 0.0022, "step": 233190 }, { "epoch": 56.02, "learning_rate": 4.484021977527651e-05, "loss": 0.0036, "step": 233200 }, { "epoch": 56.02, "learning_rate": 4.4836649381873086e-05, "loss": 0.003, "step": 233210 }, { "epoch": 56.02, "learning_rate": 4.483307901508159e-05, "loss": 0.0031, "step": 233220 }, { "epoch": 56.02, "learning_rate": 4.482950867492047e-05, "loss": 0.0031, "step": 233230 }, { "epoch": 56.03, "learning_rate": 4.482593836140809e-05, "loss": 0.0072, "step": 233240 }, { "epoch": 56.03, "learning_rate": 4.482236807456287e-05, "loss": 0.003, "step": 233250 }, { "epoch": 56.03, "learning_rate": 4.4818797814403216e-05, "loss": 0.0047, "step": 233260 }, { "epoch": 56.03, "learning_rate": 4.481522758094751e-05, "loss": 0.004, "step": 233270 }, { "epoch": 56.03, "learning_rate": 4.4811657374214174e-05, "loss": 0.0034, "step": 233280 }, { "epoch": 56.04, "learning_rate": 4.480808719422159e-05, "loss": 0.0035, "step": 233290 }, { "epoch": 56.04, "learning_rate": 4.480451704098819e-05, "loss": 0.0042, "step": 233300 }, { "epoch": 56.04, "learning_rate": 4.4800946914532345e-05, "loss": 0.0063, "step": 233310 }, { "epoch": 56.04, "learning_rate": 4.479737681487244e-05, "loss": 0.0031, "step": 233320 }, { "epoch": 56.05, "learning_rate": 4.479380674202693e-05, "loss": 0.0027, "step": 233330 }, { "epoch": 56.05, "learning_rate": 4.479023669601415e-05, "loss": 0.0034, "step": 233340 }, { "epoch": 56.05, "learning_rate": 4.478666667685256e-05, "loss": 0.004, "step": 233350 }, { "epoch": 56.05, "learning_rate": 4.478309668456052e-05, "loss": 0.0031, "step": 233360 }, { "epoch": 56.06, "learning_rate": 4.477952671915645e-05, "loss": 0.0031, "step": 233370 }, { "epoch": 56.06, "learning_rate": 4.477595678065875e-05, "loss": 0.0027, "step": 233380 }, { "epoch": 56.06, "learning_rate": 4.477238686908579e-05, "loss": 0.0034, "step": 233390 }, { "epoch": 56.06, "learning_rate": 4.476881698445601e-05, "loss": 0.0036, "step": 233400 }, { "epoch": 56.06, "learning_rate": 4.476524712678777e-05, "loss": 0.0079, "step": 233410 }, { "epoch": 56.07, "learning_rate": 4.476167729609952e-05, "loss": 0.0034, "step": 233420 }, { "epoch": 56.07, "learning_rate": 4.47581074924096e-05, "loss": 0.0031, "step": 233430 }, { "epoch": 56.07, "learning_rate": 4.4754537715736465e-05, "loss": 0.0124, "step": 233440 }, { "epoch": 56.07, "learning_rate": 4.475096796609849e-05, "loss": 0.0031, "step": 233450 }, { "epoch": 56.08, "learning_rate": 4.4747398243514036e-05, "loss": 0.0051, "step": 233460 }, { "epoch": 56.08, "learning_rate": 4.4743828548001565e-05, "loss": 0.0033, "step": 233470 }, { "epoch": 56.08, "learning_rate": 4.4740258879579424e-05, "loss": 0.0062, "step": 233480 }, { "epoch": 56.08, "learning_rate": 4.473668923826605e-05, "loss": 0.01, "step": 233490 }, { "epoch": 56.09, "learning_rate": 4.473311962407981e-05, "loss": 0.0043, "step": 233500 }, { "epoch": 56.09, "learning_rate": 4.4729550037039134e-05, "loss": 0.0052, "step": 233510 }, { "epoch": 56.09, "learning_rate": 4.472598047716238e-05, "loss": 0.0036, "step": 233520 }, { "epoch": 56.09, "learning_rate": 4.472241094446798e-05, "loss": 0.0036, "step": 233530 }, { "epoch": 56.09, "learning_rate": 4.471884143897431e-05, "loss": 0.0048, "step": 233540 }, { "epoch": 56.1, "learning_rate": 4.471527196069977e-05, "loss": 0.0021, "step": 233550 }, { "epoch": 56.1, "learning_rate": 4.471170250966278e-05, "loss": 0.0076, "step": 233560 }, { "epoch": 56.1, "learning_rate": 4.47081330858817e-05, "loss": 0.003, "step": 233570 }, { "epoch": 56.1, "learning_rate": 4.470456368937497e-05, "loss": 0.0048, "step": 233580 }, { "epoch": 56.11, "learning_rate": 4.470099432016096e-05, "loss": 0.0032, "step": 233590 }, { "epoch": 56.11, "learning_rate": 4.4697424978258045e-05, "loss": 0.0022, "step": 233600 }, { "epoch": 56.11, "learning_rate": 4.4693855663684676e-05, "loss": 0.0052, "step": 233610 }, { "epoch": 56.11, "learning_rate": 4.469028637645919e-05, "loss": 0.0069, "step": 233620 }, { "epoch": 56.11, "learning_rate": 4.4686717116600035e-05, "loss": 0.0116, "step": 233630 }, { "epoch": 56.12, "learning_rate": 4.4683147884125565e-05, "loss": 0.0033, "step": 233640 }, { "epoch": 56.12, "learning_rate": 4.4679578679054216e-05, "loss": 0.0049, "step": 233650 }, { "epoch": 56.12, "learning_rate": 4.467600950140435e-05, "loss": 0.0032, "step": 233660 }, { "epoch": 56.12, "learning_rate": 4.467244035119438e-05, "loss": 0.0092, "step": 233670 }, { "epoch": 56.13, "learning_rate": 4.46688712284427e-05, "loss": 0.0062, "step": 233680 }, { "epoch": 56.13, "learning_rate": 4.4665302133167694e-05, "loss": 0.0027, "step": 233690 }, { "epoch": 56.13, "learning_rate": 4.466173306538777e-05, "loss": 0.004, "step": 233700 }, { "epoch": 56.13, "learning_rate": 4.465816402512131e-05, "loss": 0.0048, "step": 233710 }, { "epoch": 56.14, "learning_rate": 4.465459501238673e-05, "loss": 0.0071, "step": 233720 }, { "epoch": 56.14, "learning_rate": 4.4651026027202396e-05, "loss": 0.0029, "step": 233730 }, { "epoch": 56.14, "learning_rate": 4.464745706958674e-05, "loss": 0.0051, "step": 233740 }, { "epoch": 56.14, "learning_rate": 4.464388813955814e-05, "loss": 0.0024, "step": 233750 }, { "epoch": 56.14, "learning_rate": 4.4640319237134956e-05, "loss": 0.005, "step": 233760 }, { "epoch": 56.15, "learning_rate": 4.463675036233563e-05, "loss": 0.0026, "step": 233770 }, { "epoch": 56.15, "learning_rate": 4.463318151517852e-05, "loss": 0.0061, "step": 233780 }, { "epoch": 56.15, "learning_rate": 4.462961269568207e-05, "loss": 0.0049, "step": 233790 }, { "epoch": 56.15, "learning_rate": 4.46260439038646e-05, "loss": 0.0047, "step": 233800 }, { "epoch": 56.16, "learning_rate": 4.462247513974458e-05, "loss": 0.0051, "step": 233810 }, { "epoch": 56.16, "learning_rate": 4.4618906403340356e-05, "loss": 0.0026, "step": 233820 }, { "epoch": 56.16, "learning_rate": 4.461533769467033e-05, "loss": 0.0074, "step": 233830 }, { "epoch": 56.16, "learning_rate": 4.4611769013752895e-05, "loss": 0.0082, "step": 233840 }, { "epoch": 56.16, "learning_rate": 4.460820036060645e-05, "loss": 0.0037, "step": 233850 }, { "epoch": 56.17, "learning_rate": 4.4604631735249394e-05, "loss": 0.0037, "step": 233860 }, { "epoch": 56.17, "learning_rate": 4.460106313770009e-05, "loss": 0.0037, "step": 233870 }, { "epoch": 56.17, "learning_rate": 4.459749456797698e-05, "loss": 0.0021, "step": 233880 }, { "epoch": 56.17, "learning_rate": 4.459392602609842e-05, "loss": 0.0071, "step": 233890 }, { "epoch": 56.18, "learning_rate": 4.4590357512082796e-05, "loss": 0.0031, "step": 233900 }, { "epoch": 56.18, "learning_rate": 4.458678902594853e-05, "loss": 0.003, "step": 233910 }, { "epoch": 56.18, "learning_rate": 4.4583220567713985e-05, "loss": 0.0104, "step": 233920 }, { "epoch": 56.18, "learning_rate": 4.4579652137397585e-05, "loss": 0.0055, "step": 233930 }, { "epoch": 56.19, "learning_rate": 4.457608373501768e-05, "loss": 0.0032, "step": 233940 }, { "epoch": 56.19, "learning_rate": 4.457251536059271e-05, "loss": 0.0038, "step": 233950 }, { "epoch": 56.19, "learning_rate": 4.456894701414103e-05, "loss": 0.0031, "step": 233960 }, { "epoch": 56.19, "learning_rate": 4.456537869568104e-05, "loss": 0.0062, "step": 233970 }, { "epoch": 56.19, "learning_rate": 4.456181040523113e-05, "loss": 0.0064, "step": 233980 }, { "epoch": 56.2, "learning_rate": 4.45582421428097e-05, "loss": 0.0054, "step": 233990 }, { "epoch": 56.2, "learning_rate": 4.4554673908435126e-05, "loss": 0.0028, "step": 234000 }, { "epoch": 56.2, "learning_rate": 4.455110570212582e-05, "loss": 0.0058, "step": 234010 }, { "epoch": 56.2, "learning_rate": 4.454753752390016e-05, "loss": 0.0102, "step": 234020 }, { "epoch": 56.21, "learning_rate": 4.454396937377654e-05, "loss": 0.0044, "step": 234030 }, { "epoch": 56.21, "learning_rate": 4.4540401251773334e-05, "loss": 0.0031, "step": 234040 }, { "epoch": 56.21, "learning_rate": 4.4536833157908965e-05, "loss": 0.0036, "step": 234050 }, { "epoch": 56.21, "learning_rate": 4.453326509220177e-05, "loss": 0.0032, "step": 234060 }, { "epoch": 56.22, "learning_rate": 4.452969705467021e-05, "loss": 0.0023, "step": 234070 }, { "epoch": 56.22, "learning_rate": 4.452612904533261e-05, "loss": 0.0029, "step": 234080 }, { "epoch": 56.22, "learning_rate": 4.452256106420741e-05, "loss": 0.0033, "step": 234090 }, { "epoch": 56.22, "learning_rate": 4.4518993111312976e-05, "loss": 0.0037, "step": 234100 }, { "epoch": 56.22, "learning_rate": 4.451542518666767e-05, "loss": 0.0049, "step": 234110 }, { "epoch": 56.23, "learning_rate": 4.4511857290289926e-05, "loss": 0.0051, "step": 234120 }, { "epoch": 56.23, "learning_rate": 4.450828942219811e-05, "loss": 0.0027, "step": 234130 }, { "epoch": 56.23, "learning_rate": 4.450472158241062e-05, "loss": 0.0039, "step": 234140 }, { "epoch": 56.23, "learning_rate": 4.450115377094584e-05, "loss": 0.0037, "step": 234150 }, { "epoch": 56.24, "learning_rate": 4.449758598782216e-05, "loss": 0.0023, "step": 234160 }, { "epoch": 56.24, "learning_rate": 4.449401823305798e-05, "loss": 0.0029, "step": 234170 }, { "epoch": 56.24, "learning_rate": 4.449045050667165e-05, "loss": 0.0042, "step": 234180 }, { "epoch": 56.24, "learning_rate": 4.4486882808681606e-05, "loss": 0.0037, "step": 234190 }, { "epoch": 56.24, "learning_rate": 4.44833151391062e-05, "loss": 0.0082, "step": 234200 }, { "epoch": 56.25, "learning_rate": 4.447974749796385e-05, "loss": 0.0042, "step": 234210 }, { "epoch": 56.25, "learning_rate": 4.447617988527291e-05, "loss": 0.0057, "step": 234220 }, { "epoch": 56.25, "learning_rate": 4.44726123010518e-05, "loss": 0.0068, "step": 234230 }, { "epoch": 56.25, "learning_rate": 4.446904474531889e-05, "loss": 0.0026, "step": 234240 }, { "epoch": 56.26, "learning_rate": 4.446547721809255e-05, "loss": 0.0049, "step": 234250 }, { "epoch": 56.26, "learning_rate": 4.4461909719391215e-05, "loss": 0.0025, "step": 234260 }, { "epoch": 56.26, "learning_rate": 4.445834224923322e-05, "loss": 0.0042, "step": 234270 }, { "epoch": 56.26, "learning_rate": 4.4454774807636986e-05, "loss": 0.0065, "step": 234280 }, { "epoch": 56.27, "learning_rate": 4.4451207394620885e-05, "loss": 0.0065, "step": 234290 }, { "epoch": 56.27, "learning_rate": 4.444764001020331e-05, "loss": 0.0051, "step": 234300 }, { "epoch": 56.27, "learning_rate": 4.444407265440266e-05, "loss": 0.0051, "step": 234310 }, { "epoch": 56.27, "learning_rate": 4.444050532723728e-05, "loss": 0.0038, "step": 234320 }, { "epoch": 56.27, "learning_rate": 4.44369380287256e-05, "loss": 0.0044, "step": 234330 }, { "epoch": 56.28, "learning_rate": 4.443337075888597e-05, "loss": 0.0063, "step": 234340 }, { "epoch": 56.28, "learning_rate": 4.4429803517736815e-05, "loss": 0.0032, "step": 234350 }, { "epoch": 56.28, "learning_rate": 4.4426236305296475e-05, "loss": 0.006, "step": 234360 }, { "epoch": 56.28, "learning_rate": 4.4422669121583386e-05, "loss": 0.0076, "step": 234370 }, { "epoch": 56.29, "learning_rate": 4.4419101966615906e-05, "loss": 0.0166, "step": 234380 }, { "epoch": 56.29, "learning_rate": 4.44155348404124e-05, "loss": 0.0031, "step": 234390 }, { "epoch": 56.29, "learning_rate": 4.441196774299129e-05, "loss": 0.0044, "step": 234400 }, { "epoch": 56.29, "learning_rate": 4.440840067437093e-05, "loss": 0.0049, "step": 234410 }, { "epoch": 56.3, "learning_rate": 4.440483363456974e-05, "loss": 0.0023, "step": 234420 }, { "epoch": 56.3, "learning_rate": 4.440126662360606e-05, "loss": 0.0032, "step": 234430 }, { "epoch": 56.3, "learning_rate": 4.439769964149831e-05, "loss": 0.0054, "step": 234440 }, { "epoch": 56.3, "learning_rate": 4.439413268826488e-05, "loss": 0.0036, "step": 234450 }, { "epoch": 56.3, "learning_rate": 4.4390565763924106e-05, "loss": 0.0054, "step": 234460 }, { "epoch": 56.31, "learning_rate": 4.4386998868494426e-05, "loss": 0.003, "step": 234470 }, { "epoch": 56.31, "learning_rate": 4.438343200199419e-05, "loss": 0.0072, "step": 234480 }, { "epoch": 56.31, "learning_rate": 4.43798651644418e-05, "loss": 0.0039, "step": 234490 }, { "epoch": 56.31, "learning_rate": 4.4376298355855616e-05, "loss": 0.0042, "step": 234500 }, { "epoch": 56.32, "learning_rate": 4.437273157625406e-05, "loss": 0.0027, "step": 234510 }, { "epoch": 56.32, "learning_rate": 4.4369164825655466e-05, "loss": 0.003, "step": 234520 }, { "epoch": 56.32, "learning_rate": 4.436559810407827e-05, "loss": 0.0045, "step": 234530 }, { "epoch": 56.32, "learning_rate": 4.436203141154083e-05, "loss": 0.0054, "step": 234540 }, { "epoch": 56.32, "learning_rate": 4.43584647480615e-05, "loss": 0.006, "step": 234550 }, { "epoch": 56.33, "learning_rate": 4.4354898113658715e-05, "loss": 0.0036, "step": 234560 }, { "epoch": 56.33, "learning_rate": 4.4351331508350816e-05, "loss": 0.0049, "step": 234570 }, { "epoch": 56.33, "learning_rate": 4.434776493215621e-05, "loss": 0.0027, "step": 234580 }, { "epoch": 56.33, "learning_rate": 4.434419838509326e-05, "loss": 0.0086, "step": 234590 }, { "epoch": 56.34, "learning_rate": 4.434063186718036e-05, "loss": 0.0036, "step": 234600 }, { "epoch": 56.34, "learning_rate": 4.4337065378435913e-05, "loss": 0.0054, "step": 234610 }, { "epoch": 56.34, "learning_rate": 4.4333498918878254e-05, "loss": 0.0088, "step": 234620 }, { "epoch": 56.34, "learning_rate": 4.43299324885258e-05, "loss": 0.0034, "step": 234630 }, { "epoch": 56.35, "learning_rate": 4.432636608739691e-05, "loss": 0.0033, "step": 234640 }, { "epoch": 56.35, "learning_rate": 4.432279971551e-05, "loss": 0.0034, "step": 234650 }, { "epoch": 56.35, "learning_rate": 4.43192333728834e-05, "loss": 0.0042, "step": 234660 }, { "epoch": 56.35, "learning_rate": 4.431566705953554e-05, "loss": 0.0037, "step": 234670 }, { "epoch": 56.35, "learning_rate": 4.4312100775484785e-05, "loss": 0.0061, "step": 234680 }, { "epoch": 56.36, "learning_rate": 4.4308534520749484e-05, "loss": 0.0046, "step": 234690 }, { "epoch": 56.36, "learning_rate": 4.4304968295348065e-05, "loss": 0.0033, "step": 234700 }, { "epoch": 56.36, "learning_rate": 4.4301402099298866e-05, "loss": 0.003, "step": 234710 }, { "epoch": 56.36, "learning_rate": 4.429783593262031e-05, "loss": 0.0029, "step": 234720 }, { "epoch": 56.37, "learning_rate": 4.429426979533074e-05, "loss": 0.0073, "step": 234730 }, { "epoch": 56.37, "learning_rate": 4.4290703687448566e-05, "loss": 0.0038, "step": 234740 }, { "epoch": 56.37, "learning_rate": 4.428713760899214e-05, "loss": 0.0026, "step": 234750 }, { "epoch": 56.37, "learning_rate": 4.428357155997985e-05, "loss": 0.0028, "step": 234760 }, { "epoch": 56.38, "learning_rate": 4.42800055404301e-05, "loss": 0.0042, "step": 234770 }, { "epoch": 56.38, "learning_rate": 4.4276439550361225e-05, "loss": 0.0042, "step": 234780 }, { "epoch": 56.38, "learning_rate": 4.427287358979165e-05, "loss": 0.0027, "step": 234790 }, { "epoch": 56.38, "learning_rate": 4.426930765873971e-05, "loss": 0.0057, "step": 234800 }, { "epoch": 56.38, "learning_rate": 4.426574175722383e-05, "loss": 0.0032, "step": 234810 }, { "epoch": 56.39, "learning_rate": 4.4262175885262366e-05, "loss": 0.0048, "step": 234820 }, { "epoch": 56.39, "learning_rate": 4.4258610042873675e-05, "loss": 0.0031, "step": 234830 }, { "epoch": 56.39, "learning_rate": 4.4255044230076174e-05, "loss": 0.0023, "step": 234840 }, { "epoch": 56.39, "learning_rate": 4.42514784468882e-05, "loss": 0.0031, "step": 234850 }, { "epoch": 56.4, "learning_rate": 4.424791269332818e-05, "loss": 0.0032, "step": 234860 }, { "epoch": 56.4, "learning_rate": 4.424434696941444e-05, "loss": 0.0029, "step": 234870 }, { "epoch": 56.4, "learning_rate": 4.424078127516541e-05, "loss": 0.003, "step": 234880 }, { "epoch": 56.4, "learning_rate": 4.423721561059943e-05, "loss": 0.0041, "step": 234890 }, { "epoch": 56.4, "learning_rate": 4.4233649975734884e-05, "loss": 0.0051, "step": 234900 }, { "epoch": 56.41, "learning_rate": 4.423008437059016e-05, "loss": 0.0034, "step": 234910 }, { "epoch": 56.41, "learning_rate": 4.422651879518362e-05, "loss": 0.0027, "step": 234920 }, { "epoch": 56.41, "learning_rate": 4.422295324953367e-05, "loss": 0.0043, "step": 234930 }, { "epoch": 56.41, "learning_rate": 4.421938773365864e-05, "loss": 0.0025, "step": 234940 }, { "epoch": 56.42, "learning_rate": 4.421582224757696e-05, "loss": 0.0035, "step": 234950 }, { "epoch": 56.42, "learning_rate": 4.4212256791306985e-05, "loss": 0.0025, "step": 234960 }, { "epoch": 56.42, "learning_rate": 4.4208691364867056e-05, "loss": 0.0029, "step": 234970 }, { "epoch": 56.42, "learning_rate": 4.4205125968275607e-05, "loss": 0.0028, "step": 234980 }, { "epoch": 56.43, "learning_rate": 4.420156060155096e-05, "loss": 0.0038, "step": 234990 }, { "epoch": 56.43, "learning_rate": 4.419799526471155e-05, "loss": 0.0054, "step": 235000 }, { "epoch": 56.43, "learning_rate": 4.41944299577757e-05, "loss": 0.0028, "step": 235010 }, { "epoch": 56.43, "learning_rate": 4.4190864680761815e-05, "loss": 0.0022, "step": 235020 }, { "epoch": 56.43, "learning_rate": 4.4187299433688255e-05, "loss": 0.0055, "step": 235030 }, { "epoch": 56.44, "learning_rate": 4.418373421657341e-05, "loss": 0.0059, "step": 235040 }, { "epoch": 56.44, "learning_rate": 4.4180169029435645e-05, "loss": 0.0032, "step": 235050 }, { "epoch": 56.44, "learning_rate": 4.4176603872293335e-05, "loss": 0.0031, "step": 235060 }, { "epoch": 56.44, "learning_rate": 4.417303874516485e-05, "loss": 0.0027, "step": 235070 }, { "epoch": 56.45, "learning_rate": 4.416947364806857e-05, "loss": 0.0034, "step": 235080 }, { "epoch": 56.45, "learning_rate": 4.41659085810229e-05, "loss": 0.0025, "step": 235090 }, { "epoch": 56.45, "learning_rate": 4.416234354404617e-05, "loss": 0.0028, "step": 235100 }, { "epoch": 56.45, "learning_rate": 4.415877853715676e-05, "loss": 0.0023, "step": 235110 }, { "epoch": 56.46, "learning_rate": 4.4155213560373074e-05, "loss": 0.0024, "step": 235120 }, { "epoch": 56.46, "learning_rate": 4.415164861371344e-05, "loss": 0.0025, "step": 235130 }, { "epoch": 56.46, "learning_rate": 4.414808369719629e-05, "loss": 0.0029, "step": 235140 }, { "epoch": 56.46, "learning_rate": 4.414451881083993e-05, "loss": 0.0038, "step": 235150 }, { "epoch": 56.46, "learning_rate": 4.41409539546628e-05, "loss": 0.0026, "step": 235160 }, { "epoch": 56.47, "learning_rate": 4.413738912868323e-05, "loss": 0.0025, "step": 235170 }, { "epoch": 56.47, "learning_rate": 4.41338243329196e-05, "loss": 0.006, "step": 235180 }, { "epoch": 56.47, "learning_rate": 4.413025956739029e-05, "loss": 0.0021, "step": 235190 }, { "epoch": 56.47, "learning_rate": 4.412669483211368e-05, "loss": 0.0032, "step": 235200 }, { "epoch": 56.48, "learning_rate": 4.412313012710813e-05, "loss": 0.0026, "step": 235210 }, { "epoch": 56.48, "learning_rate": 4.4119565452392e-05, "loss": 0.0074, "step": 235220 }, { "epoch": 56.48, "learning_rate": 4.41160008079837e-05, "loss": 0.0033, "step": 235230 }, { "epoch": 56.48, "learning_rate": 4.411243619390158e-05, "loss": 0.0029, "step": 235240 }, { "epoch": 56.48, "learning_rate": 4.4108871610164e-05, "loss": 0.0039, "step": 235250 }, { "epoch": 56.49, "learning_rate": 4.410530705678936e-05, "loss": 0.0032, "step": 235260 }, { "epoch": 56.49, "learning_rate": 4.4101742533796e-05, "loss": 0.0028, "step": 235270 }, { "epoch": 56.49, "learning_rate": 4.409817804120233e-05, "loss": 0.0037, "step": 235280 }, { "epoch": 56.49, "learning_rate": 4.409461357902667e-05, "loss": 0.003, "step": 235290 }, { "epoch": 56.5, "learning_rate": 4.409104914728746e-05, "loss": 0.0033, "step": 235300 }, { "epoch": 56.5, "learning_rate": 4.4087484746002995e-05, "loss": 0.0033, "step": 235310 }, { "epoch": 56.5, "learning_rate": 4.408392037519171e-05, "loss": 0.0032, "step": 235320 }, { "epoch": 56.5, "learning_rate": 4.408035603487193e-05, "loss": 0.003, "step": 235330 }, { "epoch": 56.51, "learning_rate": 4.407679172506205e-05, "loss": 0.0032, "step": 235340 }, { "epoch": 56.51, "learning_rate": 4.407322744578044e-05, "loss": 0.0046, "step": 235350 }, { "epoch": 56.51, "learning_rate": 4.406966319704546e-05, "loss": 0.0033, "step": 235360 }, { "epoch": 56.51, "learning_rate": 4.4066098978875485e-05, "loss": 0.0056, "step": 235370 }, { "epoch": 56.51, "learning_rate": 4.4062534791288876e-05, "loss": 0.0027, "step": 235380 }, { "epoch": 56.52, "learning_rate": 4.4058970634304035e-05, "loss": 0.0029, "step": 235390 }, { "epoch": 56.52, "learning_rate": 4.4055406507939314e-05, "loss": 0.0026, "step": 235400 }, { "epoch": 56.52, "learning_rate": 4.405184241221305e-05, "loss": 0.009, "step": 235410 }, { "epoch": 56.52, "learning_rate": 4.4048278347143656e-05, "loss": 0.0024, "step": 235420 }, { "epoch": 56.53, "learning_rate": 4.404471431274947e-05, "loss": 0.0051, "step": 235430 }, { "epoch": 56.53, "learning_rate": 4.404115030904889e-05, "loss": 0.0119, "step": 235440 }, { "epoch": 56.53, "learning_rate": 4.403758633606026e-05, "loss": 0.0024, "step": 235450 }, { "epoch": 56.53, "learning_rate": 4.403402239380198e-05, "loss": 0.0044, "step": 235460 }, { "epoch": 56.54, "learning_rate": 4.40304584822924e-05, "loss": 0.0096, "step": 235470 }, { "epoch": 56.54, "learning_rate": 4.4026894601549864e-05, "loss": 0.005, "step": 235480 }, { "epoch": 56.54, "learning_rate": 4.402333075159277e-05, "loss": 0.0185, "step": 235490 }, { "epoch": 56.54, "learning_rate": 4.401976693243948e-05, "loss": 0.0038, "step": 235500 }, { "epoch": 56.54, "learning_rate": 4.401620314410836e-05, "loss": 0.0046, "step": 235510 }, { "epoch": 56.55, "learning_rate": 4.401263938661778e-05, "loss": 0.007, "step": 235520 }, { "epoch": 56.55, "learning_rate": 4.400907565998611e-05, "loss": 0.0063, "step": 235530 }, { "epoch": 56.55, "learning_rate": 4.400551196423172e-05, "loss": 0.0055, "step": 235540 }, { "epoch": 56.55, "learning_rate": 4.400194829937296e-05, "loss": 0.0045, "step": 235550 }, { "epoch": 56.56, "learning_rate": 4.3998384665428214e-05, "loss": 0.0037, "step": 235560 }, { "epoch": 56.56, "learning_rate": 4.399482106241584e-05, "loss": 0.0029, "step": 235570 }, { "epoch": 56.56, "learning_rate": 4.399125749035421e-05, "loss": 0.0042, "step": 235580 }, { "epoch": 56.56, "learning_rate": 4.3987693949261686e-05, "loss": 0.0035, "step": 235590 }, { "epoch": 56.56, "learning_rate": 4.398413043915665e-05, "loss": 0.0027, "step": 235600 }, { "epoch": 56.57, "learning_rate": 4.398056696005746e-05, "loss": 0.0041, "step": 235610 }, { "epoch": 56.57, "learning_rate": 4.397700351198245e-05, "loss": 0.004, "step": 235620 }, { "epoch": 56.57, "learning_rate": 4.397344009495004e-05, "loss": 0.0103, "step": 235630 }, { "epoch": 56.57, "learning_rate": 4.396987670897855e-05, "loss": 0.0051, "step": 235640 }, { "epoch": 56.58, "learning_rate": 4.396631335408638e-05, "loss": 0.0051, "step": 235650 }, { "epoch": 56.58, "learning_rate": 4.396275003029187e-05, "loss": 0.0031, "step": 235660 }, { "epoch": 56.58, "learning_rate": 4.3959186737613407e-05, "loss": 0.007, "step": 235670 }, { "epoch": 56.58, "learning_rate": 4.395562347606935e-05, "loss": 0.0038, "step": 235680 }, { "epoch": 56.59, "learning_rate": 4.395206024567804e-05, "loss": 0.0059, "step": 235690 }, { "epoch": 56.59, "learning_rate": 4.394849704645789e-05, "loss": 0.0042, "step": 235700 }, { "epoch": 56.59, "learning_rate": 4.394493387842721e-05, "loss": 0.0035, "step": 235710 }, { "epoch": 56.59, "learning_rate": 4.3941370741604414e-05, "loss": 0.0041, "step": 235720 }, { "epoch": 56.59, "learning_rate": 4.3937807636007825e-05, "loss": 0.006, "step": 235730 }, { "epoch": 56.6, "learning_rate": 4.393424456165584e-05, "loss": 0.0059, "step": 235740 }, { "epoch": 56.6, "learning_rate": 4.3930681518566815e-05, "loss": 0.0048, "step": 235750 }, { "epoch": 56.6, "learning_rate": 4.392711850675909e-05, "loss": 0.0037, "step": 235760 }, { "epoch": 56.6, "learning_rate": 4.392355552625106e-05, "loss": 0.0044, "step": 235770 }, { "epoch": 56.61, "learning_rate": 4.391999257706106e-05, "loss": 0.0063, "step": 235780 }, { "epoch": 56.61, "learning_rate": 4.3916429659207475e-05, "loss": 0.0035, "step": 235790 }, { "epoch": 56.61, "learning_rate": 4.3912866772708664e-05, "loss": 0.0081, "step": 235800 }, { "epoch": 56.61, "learning_rate": 4.3909303917583e-05, "loss": 0.0047, "step": 235810 }, { "epoch": 56.62, "learning_rate": 4.3905741093848826e-05, "loss": 0.0089, "step": 235820 }, { "epoch": 56.62, "learning_rate": 4.3902178301524506e-05, "loss": 0.0032, "step": 235830 }, { "epoch": 56.62, "learning_rate": 4.389861554062842e-05, "loss": 0.0044, "step": 235840 }, { "epoch": 56.62, "learning_rate": 4.389505281117891e-05, "loss": 0.0041, "step": 235850 }, { "epoch": 56.62, "learning_rate": 4.3891490113194363e-05, "loss": 0.0072, "step": 235860 }, { "epoch": 56.63, "learning_rate": 4.388792744669311e-05, "loss": 0.0083, "step": 235870 }, { "epoch": 56.63, "learning_rate": 4.388436481169355e-05, "loss": 0.0052, "step": 235880 }, { "epoch": 56.63, "learning_rate": 4.388080220821403e-05, "loss": 0.0055, "step": 235890 }, { "epoch": 56.63, "learning_rate": 4.3877239636272875e-05, "loss": 0.004, "step": 235900 }, { "epoch": 56.64, "learning_rate": 4.3873677095888504e-05, "loss": 0.0034, "step": 235910 }, { "epoch": 56.64, "learning_rate": 4.387011458707923e-05, "loss": 0.0037, "step": 235920 }, { "epoch": 56.64, "learning_rate": 4.386655210986346e-05, "loss": 0.0053, "step": 235930 }, { "epoch": 56.64, "learning_rate": 4.3862989664259514e-05, "loss": 0.0054, "step": 235940 }, { "epoch": 56.64, "learning_rate": 4.385942725028577e-05, "loss": 0.0074, "step": 235950 }, { "epoch": 56.65, "learning_rate": 4.3855864867960614e-05, "loss": 0.0054, "step": 235960 }, { "epoch": 56.65, "learning_rate": 4.385230251730235e-05, "loss": 0.0081, "step": 235970 }, { "epoch": 56.65, "learning_rate": 4.38487401983294e-05, "loss": 0.0055, "step": 235980 }, { "epoch": 56.65, "learning_rate": 4.384517791106006e-05, "loss": 0.0141, "step": 235990 }, { "epoch": 56.66, "learning_rate": 4.384161565551276e-05, "loss": 0.0062, "step": 236000 }, { "epoch": 56.66, "learning_rate": 4.383805343170579e-05, "loss": 0.004, "step": 236010 }, { "epoch": 56.66, "learning_rate": 4.3834491239657575e-05, "loss": 0.0074, "step": 236020 }, { "epoch": 56.66, "learning_rate": 4.383092907938645e-05, "loss": 0.005, "step": 236030 }, { "epoch": 56.67, "learning_rate": 4.382736695091073e-05, "loss": 0.0063, "step": 236040 }, { "epoch": 56.67, "learning_rate": 4.3823804854248844e-05, "loss": 0.0036, "step": 236050 }, { "epoch": 56.67, "learning_rate": 4.38202427894191e-05, "loss": 0.003, "step": 236060 }, { "epoch": 56.67, "learning_rate": 4.381668075643989e-05, "loss": 0.0059, "step": 236070 }, { "epoch": 56.67, "learning_rate": 4.381311875532954e-05, "loss": 0.0063, "step": 236080 }, { "epoch": 56.68, "learning_rate": 4.380955678610645e-05, "loss": 0.0066, "step": 236090 }, { "epoch": 56.68, "learning_rate": 4.380599484878893e-05, "loss": 0.0045, "step": 236100 }, { "epoch": 56.68, "learning_rate": 4.380243294339538e-05, "loss": 0.0035, "step": 236110 }, { "epoch": 56.68, "learning_rate": 4.379887106994416e-05, "loss": 0.0043, "step": 236120 }, { "epoch": 56.69, "learning_rate": 4.379530922845358e-05, "loss": 0.0031, "step": 236130 }, { "epoch": 56.69, "learning_rate": 4.379174741894205e-05, "loss": 0.0063, "step": 236140 }, { "epoch": 56.69, "learning_rate": 4.3788185641427884e-05, "loss": 0.0035, "step": 236150 }, { "epoch": 56.69, "learning_rate": 4.3784623895929487e-05, "loss": 0.0026, "step": 236160 }, { "epoch": 56.7, "learning_rate": 4.3781062182465164e-05, "loss": 0.0031, "step": 236170 }, { "epoch": 56.7, "learning_rate": 4.3777500501053326e-05, "loss": 0.0067, "step": 236180 }, { "epoch": 56.7, "learning_rate": 4.377393885171229e-05, "loss": 0.0065, "step": 236190 }, { "epoch": 56.7, "learning_rate": 4.377037723446042e-05, "loss": 0.0024, "step": 236200 }, { "epoch": 56.7, "learning_rate": 4.376681564931609e-05, "loss": 0.0072, "step": 236210 }, { "epoch": 56.71, "learning_rate": 4.3763254096297626e-05, "loss": 0.0035, "step": 236220 }, { "epoch": 56.71, "learning_rate": 4.3759692575423415e-05, "loss": 0.0053, "step": 236230 }, { "epoch": 56.71, "learning_rate": 4.375613108671179e-05, "loss": 0.0043, "step": 236240 }, { "epoch": 56.71, "learning_rate": 4.375256963018114e-05, "loss": 0.0055, "step": 236250 }, { "epoch": 56.72, "learning_rate": 4.374900820584978e-05, "loss": 0.0049, "step": 236260 }, { "epoch": 56.72, "learning_rate": 4.374544681373607e-05, "loss": 0.0037, "step": 236270 }, { "epoch": 56.72, "learning_rate": 4.374188545385841e-05, "loss": 0.0055, "step": 236280 }, { "epoch": 56.72, "learning_rate": 4.37383241262351e-05, "loss": 0.0043, "step": 236290 }, { "epoch": 56.72, "learning_rate": 4.3734762830884545e-05, "loss": 0.005, "step": 236300 }, { "epoch": 56.73, "learning_rate": 4.3731201567825045e-05, "loss": 0.008, "step": 236310 }, { "epoch": 56.73, "learning_rate": 4.3727640337075014e-05, "loss": 0.0069, "step": 236320 }, { "epoch": 56.73, "learning_rate": 4.3724079138652774e-05, "loss": 0.0043, "step": 236330 }, { "epoch": 56.73, "learning_rate": 4.372051797257666e-05, "loss": 0.0045, "step": 236340 }, { "epoch": 56.74, "learning_rate": 4.371695683886508e-05, "loss": 0.0023, "step": 236350 }, { "epoch": 56.74, "learning_rate": 4.371339573753632e-05, "loss": 0.0087, "step": 236360 }, { "epoch": 56.74, "learning_rate": 4.3709834668608804e-05, "loss": 0.0036, "step": 236370 }, { "epoch": 56.74, "learning_rate": 4.370627363210082e-05, "loss": 0.0038, "step": 236380 }, { "epoch": 56.75, "learning_rate": 4.370271262803079e-05, "loss": 0.0051, "step": 236390 }, { "epoch": 56.75, "learning_rate": 4.369915165641701e-05, "loss": 0.0035, "step": 236400 }, { "epoch": 56.75, "learning_rate": 4.3695590717277855e-05, "loss": 0.0057, "step": 236410 }, { "epoch": 56.75, "learning_rate": 4.3692029810631686e-05, "loss": 0.0031, "step": 236420 }, { "epoch": 56.75, "learning_rate": 4.368846893649683e-05, "loss": 0.0042, "step": 236430 }, { "epoch": 56.76, "learning_rate": 4.3684908094891686e-05, "loss": 0.0124, "step": 236440 }, { "epoch": 56.76, "learning_rate": 4.368134728583455e-05, "loss": 0.0037, "step": 236450 }, { "epoch": 56.76, "learning_rate": 4.367778650934383e-05, "loss": 0.0035, "step": 236460 }, { "epoch": 56.76, "learning_rate": 4.367422576543785e-05, "loss": 0.0032, "step": 236470 }, { "epoch": 56.77, "learning_rate": 4.367066505413493e-05, "loss": 0.0032, "step": 236480 }, { "epoch": 56.77, "learning_rate": 4.366710437545349e-05, "loss": 0.0034, "step": 236490 }, { "epoch": 56.77, "learning_rate": 4.366354372941183e-05, "loss": 0.0059, "step": 236500 }, { "epoch": 56.77, "learning_rate": 4.365998311602833e-05, "loss": 0.0043, "step": 236510 }, { "epoch": 56.78, "learning_rate": 4.365642253532131e-05, "loss": 0.0031, "step": 236520 }, { "epoch": 56.78, "learning_rate": 4.365286198730917e-05, "loss": 0.0085, "step": 236530 }, { "epoch": 56.78, "learning_rate": 4.364930147201021e-05, "loss": 0.006, "step": 236540 }, { "epoch": 56.78, "learning_rate": 4.3645740989442805e-05, "loss": 0.0063, "step": 236550 }, { "epoch": 56.78, "learning_rate": 4.364218053962531e-05, "loss": 0.0048, "step": 236560 }, { "epoch": 56.79, "learning_rate": 4.363862012257607e-05, "loss": 0.0046, "step": 236570 }, { "epoch": 56.79, "learning_rate": 4.3635059738313436e-05, "loss": 0.0029, "step": 236580 }, { "epoch": 56.79, "learning_rate": 4.363149938685574e-05, "loss": 0.0045, "step": 236590 }, { "epoch": 56.79, "learning_rate": 4.362793906822137e-05, "loss": 0.0031, "step": 236600 }, { "epoch": 56.8, "learning_rate": 4.362437878242867e-05, "loss": 0.0029, "step": 236610 }, { "epoch": 56.8, "learning_rate": 4.362081852949594e-05, "loss": 0.0038, "step": 236620 }, { "epoch": 56.8, "learning_rate": 4.361725830944159e-05, "loss": 0.0033, "step": 236630 }, { "epoch": 56.8, "learning_rate": 4.361369812228392e-05, "loss": 0.0043, "step": 236640 }, { "epoch": 56.8, "learning_rate": 4.361013796804133e-05, "loss": 0.003, "step": 236650 }, { "epoch": 56.81, "learning_rate": 4.360657784673211e-05, "loss": 0.0052, "step": 236660 }, { "epoch": 56.81, "learning_rate": 4.3603017758374675e-05, "loss": 0.0051, "step": 236670 }, { "epoch": 56.81, "learning_rate": 4.359945770298732e-05, "loss": 0.0048, "step": 236680 }, { "epoch": 56.81, "learning_rate": 4.3595897680588424e-05, "loss": 0.0034, "step": 236690 }, { "epoch": 56.82, "learning_rate": 4.3592337691196314e-05, "loss": 0.003, "step": 236700 }, { "epoch": 56.82, "learning_rate": 4.3588777734829355e-05, "loss": 0.0038, "step": 236710 }, { "epoch": 56.82, "learning_rate": 4.358521781150588e-05, "loss": 0.0025, "step": 236720 }, { "epoch": 56.82, "learning_rate": 4.358165792124426e-05, "loss": 0.0026, "step": 236730 }, { "epoch": 56.83, "learning_rate": 4.357809806406282e-05, "loss": 0.0046, "step": 236740 }, { "epoch": 56.83, "learning_rate": 4.3574538239979936e-05, "loss": 0.0032, "step": 236750 }, { "epoch": 56.83, "learning_rate": 4.357097844901391e-05, "loss": 0.003, "step": 236760 }, { "epoch": 56.83, "learning_rate": 4.356741869118313e-05, "loss": 0.0053, "step": 236770 }, { "epoch": 56.83, "learning_rate": 4.356385896650591e-05, "loss": 0.01, "step": 236780 }, { "epoch": 56.84, "learning_rate": 4.356029927500064e-05, "loss": 0.0038, "step": 236790 }, { "epoch": 56.84, "learning_rate": 4.355673961668561e-05, "loss": 0.0029, "step": 236800 }, { "epoch": 56.84, "learning_rate": 4.355317999157923e-05, "loss": 0.0031, "step": 236810 }, { "epoch": 56.84, "learning_rate": 4.3549620399699806e-05, "loss": 0.0056, "step": 236820 }, { "epoch": 56.85, "learning_rate": 4.354606084106568e-05, "loss": 0.0024, "step": 236830 }, { "epoch": 56.85, "learning_rate": 4.354250131569521e-05, "loss": 0.0031, "step": 236840 }, { "epoch": 56.85, "learning_rate": 4.353894182360675e-05, "loss": 0.0023, "step": 236850 }, { "epoch": 56.85, "learning_rate": 4.3535382364818636e-05, "loss": 0.0046, "step": 236860 }, { "epoch": 56.86, "learning_rate": 4.3531822939349214e-05, "loss": 0.0053, "step": 236870 }, { "epoch": 56.86, "learning_rate": 4.352826354721683e-05, "loss": 0.0032, "step": 236880 }, { "epoch": 56.86, "learning_rate": 4.3524704188439844e-05, "loss": 0.0027, "step": 236890 }, { "epoch": 56.86, "learning_rate": 4.352114486303657e-05, "loss": 0.0031, "step": 236900 }, { "epoch": 56.86, "learning_rate": 4.351758557102538e-05, "loss": 0.0047, "step": 236910 }, { "epoch": 56.87, "learning_rate": 4.3514026312424594e-05, "loss": 0.0034, "step": 236920 }, { "epoch": 56.87, "learning_rate": 4.3510467087252585e-05, "loss": 0.0034, "step": 236930 }, { "epoch": 56.87, "learning_rate": 4.350690789552767e-05, "loss": 0.0022, "step": 236940 }, { "epoch": 56.87, "learning_rate": 4.350334873726822e-05, "loss": 0.0052, "step": 236950 }, { "epoch": 56.88, "learning_rate": 4.349978961249255e-05, "loss": 0.007, "step": 236960 }, { "epoch": 56.88, "learning_rate": 4.349623052121904e-05, "loss": 0.0044, "step": 236970 }, { "epoch": 56.88, "learning_rate": 4.349267146346601e-05, "loss": 0.0031, "step": 236980 }, { "epoch": 56.88, "learning_rate": 4.348911243925178e-05, "loss": 0.0032, "step": 236990 }, { "epoch": 56.88, "learning_rate": 4.3485553448594735e-05, "loss": 0.0036, "step": 237000 }, { "epoch": 56.89, "learning_rate": 4.34819944915132e-05, "loss": 0.0027, "step": 237010 }, { "epoch": 56.89, "learning_rate": 4.3478435568025515e-05, "loss": 0.0035, "step": 237020 }, { "epoch": 56.89, "learning_rate": 4.3474876678150035e-05, "loss": 0.0024, "step": 237030 }, { "epoch": 56.89, "learning_rate": 4.3471317821905096e-05, "loss": 0.0055, "step": 237040 }, { "epoch": 56.9, "learning_rate": 4.346775899930904e-05, "loss": 0.0027, "step": 237050 }, { "epoch": 56.9, "learning_rate": 4.34642002103802e-05, "loss": 0.0037, "step": 237060 }, { "epoch": 56.9, "learning_rate": 4.346064145513694e-05, "loss": 0.0138, "step": 237070 }, { "epoch": 56.9, "learning_rate": 4.345708273359757e-05, "loss": 0.0032, "step": 237080 }, { "epoch": 56.91, "learning_rate": 4.345352404578047e-05, "loss": 0.0051, "step": 237090 }, { "epoch": 56.91, "learning_rate": 4.344996539170394e-05, "loss": 0.0033, "step": 237100 }, { "epoch": 56.91, "learning_rate": 4.3446406771386374e-05, "loss": 0.0057, "step": 237110 }, { "epoch": 56.91, "learning_rate": 4.344284818484607e-05, "loss": 0.0031, "step": 237120 }, { "epoch": 56.91, "learning_rate": 4.3439289632101365e-05, "loss": 0.0027, "step": 237130 }, { "epoch": 56.92, "learning_rate": 4.3435731113170635e-05, "loss": 0.0028, "step": 237140 }, { "epoch": 56.92, "learning_rate": 4.343217262807218e-05, "loss": 0.0288, "step": 237150 }, { "epoch": 56.92, "learning_rate": 4.342861417682438e-05, "loss": 0.0059, "step": 237160 }, { "epoch": 56.92, "learning_rate": 4.342505575944555e-05, "loss": 0.0047, "step": 237170 }, { "epoch": 56.93, "learning_rate": 4.342149737595404e-05, "loss": 0.0095, "step": 237180 }, { "epoch": 56.93, "learning_rate": 4.34179390263682e-05, "loss": 0.0057, "step": 237190 }, { "epoch": 56.93, "learning_rate": 4.341438071070633e-05, "loss": 0.0042, "step": 237200 }, { "epoch": 56.93, "learning_rate": 4.3410822428986824e-05, "loss": 0.0285, "step": 237210 }, { "epoch": 56.94, "learning_rate": 4.3407264181227966e-05, "loss": 0.0077, "step": 237220 }, { "epoch": 56.94, "learning_rate": 4.3403705967448153e-05, "loss": 0.0074, "step": 237230 }, { "epoch": 56.94, "learning_rate": 4.3400147787665675e-05, "loss": 0.0029, "step": 237240 }, { "epoch": 56.94, "learning_rate": 4.33965896418989e-05, "loss": 0.0067, "step": 237250 }, { "epoch": 56.94, "learning_rate": 4.3393031530166176e-05, "loss": 0.0026, "step": 237260 }, { "epoch": 56.95, "learning_rate": 4.338947345248579e-05, "loss": 0.005, "step": 237270 }, { "epoch": 56.95, "learning_rate": 4.338591540887613e-05, "loss": 0.0024, "step": 237280 }, { "epoch": 56.95, "learning_rate": 4.33823573993555e-05, "loss": 0.0048, "step": 237290 }, { "epoch": 57.0, "learning_rate": 4.3378799423942276e-05, "loss": 0.0031, "step": 237300 }, { "epoch": 57.0, "learning_rate": 4.337524148265475e-05, "loss": 0.0025, "step": 237310 }, { "epoch": 57.01, "learning_rate": 4.33716835755113e-05, "loss": 0.0036, "step": 237320 }, { "epoch": 57.01, "learning_rate": 4.336812570253026e-05, "loss": 0.0037, "step": 237330 }, { "epoch": 57.01, "learning_rate": 4.336456786372993e-05, "loss": 0.0027, "step": 237340 }, { "epoch": 57.01, "learning_rate": 4.33610100591287e-05, "loss": 0.0023, "step": 237350 }, { "epoch": 57.02, "learning_rate": 4.335745228874486e-05, "loss": 0.0043, "step": 237360 }, { "epoch": 57.02, "learning_rate": 4.335389455259678e-05, "loss": 0.0028, "step": 237370 }, { "epoch": 57.02, "learning_rate": 4.3350336850702764e-05, "loss": 0.003, "step": 237380 }, { "epoch": 57.02, "learning_rate": 4.334677918308119e-05, "loss": 0.0025, "step": 237390 }, { "epoch": 57.02, "learning_rate": 4.3343221549750376e-05, "loss": 0.0041, "step": 237400 }, { "epoch": 57.03, "learning_rate": 4.3339663950728625e-05, "loss": 0.0053, "step": 237410 }, { "epoch": 57.03, "learning_rate": 4.333610638603433e-05, "loss": 0.0026, "step": 237420 }, { "epoch": 57.03, "learning_rate": 4.3332548855685765e-05, "loss": 0.0025, "step": 237430 }, { "epoch": 57.03, "learning_rate": 4.332899135970133e-05, "loss": 0.003, "step": 237440 }, { "epoch": 57.04, "learning_rate": 4.332543389809931e-05, "loss": 0.005, "step": 237450 }, { "epoch": 57.04, "learning_rate": 4.3321876470898064e-05, "loss": 0.0032, "step": 237460 }, { "epoch": 57.04, "learning_rate": 4.331831907811593e-05, "loss": 0.0018, "step": 237470 }, { "epoch": 57.04, "learning_rate": 4.331476171977122e-05, "loss": 0.0064, "step": 237480 }, { "epoch": 57.05, "learning_rate": 4.331120439588231e-05, "loss": 0.0021, "step": 237490 }, { "epoch": 57.05, "learning_rate": 4.330764710646748e-05, "loss": 0.0024, "step": 237500 }, { "epoch": 57.05, "learning_rate": 4.330408985154511e-05, "loss": 0.0028, "step": 237510 }, { "epoch": 57.05, "learning_rate": 4.33005326311335e-05, "loss": 0.0038, "step": 237520 }, { "epoch": 57.05, "learning_rate": 4.329697544525103e-05, "loss": 0.0024, "step": 237530 }, { "epoch": 57.06, "learning_rate": 4.3293418293916e-05, "loss": 0.0041, "step": 237540 }, { "epoch": 57.06, "learning_rate": 4.328986117714672e-05, "loss": 0.003, "step": 237550 }, { "epoch": 57.06, "learning_rate": 4.3286304094961586e-05, "loss": 0.0043, "step": 237560 }, { "epoch": 57.06, "learning_rate": 4.328274704737886e-05, "loss": 0.0041, "step": 237570 }, { "epoch": 57.07, "learning_rate": 4.3279190034416944e-05, "loss": 0.0024, "step": 237580 }, { "epoch": 57.07, "learning_rate": 4.327563305609411e-05, "loss": 0.0026, "step": 237590 }, { "epoch": 57.07, "learning_rate": 4.327207611242875e-05, "loss": 0.0033, "step": 237600 }, { "epoch": 57.07, "learning_rate": 4.326851920343915e-05, "loss": 0.0045, "step": 237610 }, { "epoch": 57.08, "learning_rate": 4.326496232914365e-05, "loss": 0.0031, "step": 237620 }, { "epoch": 57.08, "learning_rate": 4.326140548956061e-05, "loss": 0.0025, "step": 237630 }, { "epoch": 57.08, "learning_rate": 4.325784868470832e-05, "loss": 0.0029, "step": 237640 }, { "epoch": 57.08, "learning_rate": 4.3254291914605155e-05, "loss": 0.0023, "step": 237650 }, { "epoch": 57.08, "learning_rate": 4.3250735179269405e-05, "loss": 0.0033, "step": 237660 }, { "epoch": 57.09, "learning_rate": 4.324717847871944e-05, "loss": 0.0023, "step": 237670 }, { "epoch": 57.09, "learning_rate": 4.324362181297358e-05, "loss": 0.0022, "step": 237680 }, { "epoch": 57.09, "learning_rate": 4.3240065182050125e-05, "loss": 0.0068, "step": 237690 }, { "epoch": 57.09, "learning_rate": 4.323650858596745e-05, "loss": 0.0022, "step": 237700 }, { "epoch": 57.1, "learning_rate": 4.323295202474386e-05, "loss": 0.003, "step": 237710 }, { "epoch": 57.1, "learning_rate": 4.322939549839769e-05, "loss": 0.0028, "step": 237720 }, { "epoch": 57.1, "learning_rate": 4.3225839006947265e-05, "loss": 0.003, "step": 237730 }, { "epoch": 57.1, "learning_rate": 4.322228255041094e-05, "loss": 0.0049, "step": 237740 }, { "epoch": 57.1, "learning_rate": 4.321872612880701e-05, "loss": 0.0043, "step": 237750 }, { "epoch": 57.11, "learning_rate": 4.321516974215384e-05, "loss": 0.0031, "step": 237760 }, { "epoch": 57.11, "learning_rate": 4.321161339046973e-05, "loss": 0.0057, "step": 237770 }, { "epoch": 57.11, "learning_rate": 4.320805707377301e-05, "loss": 0.0021, "step": 237780 }, { "epoch": 57.11, "learning_rate": 4.320450079208205e-05, "loss": 0.0254, "step": 237790 }, { "epoch": 57.12, "learning_rate": 4.320094454541512e-05, "loss": 0.0199, "step": 237800 }, { "epoch": 57.12, "learning_rate": 4.31973883337906e-05, "loss": 0.0032, "step": 237810 }, { "epoch": 57.12, "learning_rate": 4.3193832157226785e-05, "loss": 0.0027, "step": 237820 }, { "epoch": 57.12, "learning_rate": 4.3190276015742026e-05, "loss": 0.0041, "step": 237830 }, { "epoch": 57.13, "learning_rate": 4.3186719909354646e-05, "loss": 0.0055, "step": 237840 }, { "epoch": 57.13, "learning_rate": 4.318316383808295e-05, "loss": 0.0026, "step": 237850 }, { "epoch": 57.13, "learning_rate": 4.3179607801945304e-05, "loss": 0.0027, "step": 237860 }, { "epoch": 57.13, "learning_rate": 4.3176051800959994e-05, "loss": 0.0043, "step": 237870 }, { "epoch": 57.13, "learning_rate": 4.317249583514539e-05, "loss": 0.0035, "step": 237880 }, { "epoch": 57.14, "learning_rate": 4.316893990451978e-05, "loss": 0.0029, "step": 237890 }, { "epoch": 57.14, "learning_rate": 4.316538400910153e-05, "loss": 0.0025, "step": 237900 }, { "epoch": 57.14, "learning_rate": 4.316182814890894e-05, "loss": 0.0037, "step": 237910 }, { "epoch": 57.14, "learning_rate": 4.315827232396035e-05, "loss": 0.0025, "step": 237920 }, { "epoch": 57.15, "learning_rate": 4.3154716534274074e-05, "loss": 0.0039, "step": 237930 }, { "epoch": 57.15, "learning_rate": 4.315116077986844e-05, "loss": 0.0036, "step": 237940 }, { "epoch": 57.15, "learning_rate": 4.31476050607618e-05, "loss": 0.0023, "step": 237950 }, { "epoch": 57.15, "learning_rate": 4.314404937697243e-05, "loss": 0.0055, "step": 237960 }, { "epoch": 57.16, "learning_rate": 4.314049372851872e-05, "loss": 0.0026, "step": 237970 }, { "epoch": 57.16, "learning_rate": 4.313693811541896e-05, "loss": 0.0022, "step": 237980 }, { "epoch": 57.16, "learning_rate": 4.313338253769146e-05, "loss": 0.0031, "step": 237990 }, { "epoch": 57.16, "learning_rate": 4.3129826995354575e-05, "loss": 0.0024, "step": 238000 }, { "epoch": 57.16, "learning_rate": 4.312627148842661e-05, "loss": 0.0023, "step": 238010 }, { "epoch": 57.17, "learning_rate": 4.312271601692591e-05, "loss": 0.0068, "step": 238020 }, { "epoch": 57.17, "learning_rate": 4.3119160580870776e-05, "loss": 0.0027, "step": 238030 }, { "epoch": 57.17, "learning_rate": 4.311560518027956e-05, "loss": 0.0024, "step": 238040 }, { "epoch": 57.17, "learning_rate": 4.311204981517057e-05, "loss": 0.004, "step": 238050 }, { "epoch": 57.18, "learning_rate": 4.310849448556213e-05, "loss": 0.0032, "step": 238060 }, { "epoch": 57.18, "learning_rate": 4.3104939191472565e-05, "loss": 0.0038, "step": 238070 }, { "epoch": 57.18, "learning_rate": 4.3101383932920205e-05, "loss": 0.0047, "step": 238080 }, { "epoch": 57.18, "learning_rate": 4.309782870992336e-05, "loss": 0.0028, "step": 238090 }, { "epoch": 57.18, "learning_rate": 4.309427352250036e-05, "loss": 0.0027, "step": 238100 }, { "epoch": 57.19, "learning_rate": 4.309071837066956e-05, "loss": 0.0029, "step": 238110 }, { "epoch": 57.19, "learning_rate": 4.308716325444924e-05, "loss": 0.002, "step": 238120 }, { "epoch": 57.19, "learning_rate": 4.3083608173857724e-05, "loss": 0.0026, "step": 238130 }, { "epoch": 57.19, "learning_rate": 4.308005312891338e-05, "loss": 0.0036, "step": 238140 }, { "epoch": 57.2, "learning_rate": 4.307649811963447e-05, "loss": 0.0028, "step": 238150 }, { "epoch": 57.2, "learning_rate": 4.3072943146039366e-05, "loss": 0.0028, "step": 238160 }, { "epoch": 57.2, "learning_rate": 4.306938820814635e-05, "loss": 0.0153, "step": 238170 }, { "epoch": 57.2, "learning_rate": 4.306583330597379e-05, "loss": 0.0022, "step": 238180 }, { "epoch": 57.21, "learning_rate": 4.3062278439539975e-05, "loss": 0.0073, "step": 238190 }, { "epoch": 57.21, "learning_rate": 4.3058723608863225e-05, "loss": 0.0031, "step": 238200 }, { "epoch": 57.21, "learning_rate": 4.3055168813961874e-05, "loss": 0.0047, "step": 238210 }, { "epoch": 57.21, "learning_rate": 4.305161405485425e-05, "loss": 0.0039, "step": 238220 }, { "epoch": 57.21, "learning_rate": 4.304805933155865e-05, "loss": 0.0028, "step": 238230 }, { "epoch": 57.22, "learning_rate": 4.304450464409342e-05, "loss": 0.0038, "step": 238240 }, { "epoch": 57.22, "learning_rate": 4.304094999247688e-05, "loss": 0.0027, "step": 238250 }, { "epoch": 57.22, "learning_rate": 4.303739537672734e-05, "loss": 0.0022, "step": 238260 }, { "epoch": 57.22, "learning_rate": 4.303384079686311e-05, "loss": 0.0034, "step": 238270 }, { "epoch": 57.23, "learning_rate": 4.303028625290253e-05, "loss": 0.0065, "step": 238280 }, { "epoch": 57.23, "learning_rate": 4.3026731744863905e-05, "loss": 0.0061, "step": 238290 }, { "epoch": 57.23, "learning_rate": 4.302317727276558e-05, "loss": 0.0026, "step": 238300 }, { "epoch": 57.23, "learning_rate": 4.301962283662583e-05, "loss": 0.0027, "step": 238310 }, { "epoch": 57.24, "learning_rate": 4.3016068436463036e-05, "loss": 0.0066, "step": 238320 }, { "epoch": 57.24, "learning_rate": 4.3012514072295475e-05, "loss": 0.0025, "step": 238330 }, { "epoch": 57.24, "learning_rate": 4.300895974414146e-05, "loss": 0.0033, "step": 238340 }, { "epoch": 57.24, "learning_rate": 4.300540545201933e-05, "loss": 0.0032, "step": 238350 }, { "epoch": 57.24, "learning_rate": 4.3001851195947396e-05, "loss": 0.0022, "step": 238360 }, { "epoch": 57.25, "learning_rate": 4.299829697594398e-05, "loss": 0.0024, "step": 238370 }, { "epoch": 57.25, "learning_rate": 4.299474279202741e-05, "loss": 0.0026, "step": 238380 }, { "epoch": 57.25, "learning_rate": 4.299118864421599e-05, "loss": 0.008, "step": 238390 }, { "epoch": 57.25, "learning_rate": 4.298763453252805e-05, "loss": 0.0033, "step": 238400 }, { "epoch": 57.26, "learning_rate": 4.298408045698188e-05, "loss": 0.0021, "step": 238410 }, { "epoch": 57.26, "learning_rate": 4.298052641759583e-05, "loss": 0.0022, "step": 238420 }, { "epoch": 57.26, "learning_rate": 4.297697241438819e-05, "loss": 0.0026, "step": 238430 }, { "epoch": 57.26, "learning_rate": 4.2973418447377324e-05, "loss": 0.0041, "step": 238440 }, { "epoch": 57.26, "learning_rate": 4.296986451658149e-05, "loss": 0.0045, "step": 238450 }, { "epoch": 57.27, "learning_rate": 4.2966310622019054e-05, "loss": 0.0049, "step": 238460 }, { "epoch": 57.27, "learning_rate": 4.296275676370831e-05, "loss": 0.0043, "step": 238470 }, { "epoch": 57.27, "learning_rate": 4.295920294166756e-05, "loss": 0.0027, "step": 238480 }, { "epoch": 57.27, "learning_rate": 4.295564915591516e-05, "loss": 0.0038, "step": 238490 }, { "epoch": 57.28, "learning_rate": 4.295209540646937e-05, "loss": 0.0034, "step": 238500 }, { "epoch": 57.28, "learning_rate": 4.294854169334856e-05, "loss": 0.0046, "step": 238510 }, { "epoch": 57.28, "learning_rate": 4.294498801657102e-05, "loss": 0.0123, "step": 238520 }, { "epoch": 57.28, "learning_rate": 4.2941434376155075e-05, "loss": 0.0029, "step": 238530 }, { "epoch": 57.29, "learning_rate": 4.2937880772119036e-05, "loss": 0.0055, "step": 238540 }, { "epoch": 57.29, "learning_rate": 4.2934327204481215e-05, "loss": 0.0035, "step": 238550 }, { "epoch": 57.29, "learning_rate": 4.2930773673259935e-05, "loss": 0.0173, "step": 238560 }, { "epoch": 57.29, "learning_rate": 4.29272201784735e-05, "loss": 0.0048, "step": 238570 }, { "epoch": 57.29, "learning_rate": 4.292366672014024e-05, "loss": 0.0026, "step": 238580 }, { "epoch": 57.3, "learning_rate": 4.2920113298278456e-05, "loss": 0.0031, "step": 238590 }, { "epoch": 57.3, "learning_rate": 4.291655991290647e-05, "loss": 0.0029, "step": 238600 }, { "epoch": 57.3, "learning_rate": 4.291300656404258e-05, "loss": 0.0027, "step": 238610 }, { "epoch": 57.3, "learning_rate": 4.290945325170514e-05, "loss": 0.0027, "step": 238620 }, { "epoch": 57.31, "learning_rate": 4.290589997591243e-05, "loss": 0.003, "step": 238630 }, { "epoch": 57.31, "learning_rate": 4.290234673668275e-05, "loss": 0.0024, "step": 238640 }, { "epoch": 57.31, "learning_rate": 4.289879353403446e-05, "loss": 0.0026, "step": 238650 }, { "epoch": 57.31, "learning_rate": 4.2895240367985825e-05, "loss": 0.0053, "step": 238660 }, { "epoch": 57.32, "learning_rate": 4.289168723855519e-05, "loss": 0.0025, "step": 238670 }, { "epoch": 57.32, "learning_rate": 4.288813414576085e-05, "loss": 0.0081, "step": 238680 }, { "epoch": 57.32, "learning_rate": 4.2884581089621135e-05, "loss": 0.007, "step": 238690 }, { "epoch": 57.32, "learning_rate": 4.288102807015436e-05, "loss": 0.0032, "step": 238700 }, { "epoch": 57.32, "learning_rate": 4.28774750873788e-05, "loss": 0.0036, "step": 238710 }, { "epoch": 57.33, "learning_rate": 4.2873922141312814e-05, "loss": 0.0037, "step": 238720 }, { "epoch": 57.33, "learning_rate": 4.2870369231974674e-05, "loss": 0.0031, "step": 238730 }, { "epoch": 57.33, "learning_rate": 4.286681635938274e-05, "loss": 0.0049, "step": 238740 }, { "epoch": 57.33, "learning_rate": 4.2863263523555265e-05, "loss": 0.0053, "step": 238750 }, { "epoch": 57.34, "learning_rate": 4.285971072451061e-05, "loss": 0.0037, "step": 238760 }, { "epoch": 57.34, "learning_rate": 4.2856157962267064e-05, "loss": 0.0053, "step": 238770 }, { "epoch": 57.34, "learning_rate": 4.2852605236842925e-05, "loss": 0.0027, "step": 238780 }, { "epoch": 57.34, "learning_rate": 4.284905254825653e-05, "loss": 0.0168, "step": 238790 }, { "epoch": 57.34, "learning_rate": 4.2845499896526165e-05, "loss": 0.0035, "step": 238800 }, { "epoch": 57.35, "learning_rate": 4.284194728167017e-05, "loss": 0.0039, "step": 238810 }, { "epoch": 57.35, "learning_rate": 4.283839470370682e-05, "loss": 0.0034, "step": 238820 }, { "epoch": 57.35, "learning_rate": 4.2834842162654456e-05, "loss": 0.0021, "step": 238830 }, { "epoch": 57.35, "learning_rate": 4.283128965853138e-05, "loss": 0.0036, "step": 238840 }, { "epoch": 57.36, "learning_rate": 4.2827737191355874e-05, "loss": 0.0023, "step": 238850 }, { "epoch": 57.36, "learning_rate": 4.2824184761146305e-05, "loss": 0.0043, "step": 238860 }, { "epoch": 57.36, "learning_rate": 4.282063236792091e-05, "loss": 0.003, "step": 238870 }, { "epoch": 57.36, "learning_rate": 4.2817080011698066e-05, "loss": 0.0022, "step": 238880 }, { "epoch": 57.37, "learning_rate": 4.281352769249603e-05, "loss": 0.0029, "step": 238890 }, { "epoch": 57.37, "learning_rate": 4.2809975410333155e-05, "loss": 0.0024, "step": 238900 }, { "epoch": 57.37, "learning_rate": 4.280642316522773e-05, "loss": 0.0031, "step": 238910 }, { "epoch": 57.37, "learning_rate": 4.2802870957198026e-05, "loss": 0.0021, "step": 238920 }, { "epoch": 57.37, "learning_rate": 4.279931878626242e-05, "loss": 0.0033, "step": 238930 }, { "epoch": 57.38, "learning_rate": 4.279576665243916e-05, "loss": 0.0023, "step": 238940 }, { "epoch": 57.38, "learning_rate": 4.279221455574659e-05, "loss": 0.0048, "step": 238950 }, { "epoch": 57.38, "learning_rate": 4.2788662496202995e-05, "loss": 0.004, "step": 238960 }, { "epoch": 57.38, "learning_rate": 4.278511047382672e-05, "loss": 0.0056, "step": 238970 }, { "epoch": 57.39, "learning_rate": 4.278155848863602e-05, "loss": 0.007, "step": 238980 }, { "epoch": 57.39, "learning_rate": 4.277800654064923e-05, "loss": 0.0035, "step": 238990 }, { "epoch": 57.39, "learning_rate": 4.2774454629884677e-05, "loss": 0.0035, "step": 239000 }, { "epoch": 57.39, "learning_rate": 4.277090275636062e-05, "loss": 0.0044, "step": 239010 }, { "epoch": 57.4, "learning_rate": 4.2767350920095404e-05, "loss": 0.0024, "step": 239020 }, { "epoch": 57.4, "learning_rate": 4.27637991211073e-05, "loss": 0.0027, "step": 239030 }, { "epoch": 57.4, "learning_rate": 4.276024735941467e-05, "loss": 0.0086, "step": 239040 }, { "epoch": 57.4, "learning_rate": 4.275669563503578e-05, "loss": 0.0031, "step": 239050 }, { "epoch": 57.4, "learning_rate": 4.275314394798892e-05, "loss": 0.0032, "step": 239060 }, { "epoch": 57.41, "learning_rate": 4.274959229829244e-05, "loss": 0.0031, "step": 239070 }, { "epoch": 57.41, "learning_rate": 4.27460406859646e-05, "loss": 0.0042, "step": 239080 }, { "epoch": 57.41, "learning_rate": 4.274248911102375e-05, "loss": 0.0029, "step": 239090 }, { "epoch": 57.41, "learning_rate": 4.273893757348814e-05, "loss": 0.0057, "step": 239100 }, { "epoch": 57.42, "learning_rate": 4.273538607337614e-05, "loss": 0.0022, "step": 239110 }, { "epoch": 57.42, "learning_rate": 4.2731834610706e-05, "loss": 0.0034, "step": 239120 }, { "epoch": 57.42, "learning_rate": 4.272828318549606e-05, "loss": 0.0028, "step": 239130 }, { "epoch": 57.42, "learning_rate": 4.27247317977646e-05, "loss": 0.0093, "step": 239140 }, { "epoch": 57.42, "learning_rate": 4.272118044752992e-05, "loss": 0.0031, "step": 239150 }, { "epoch": 57.43, "learning_rate": 4.2717629134810354e-05, "loss": 0.0034, "step": 239160 }, { "epoch": 57.43, "learning_rate": 4.2714077859624175e-05, "loss": 0.0023, "step": 239170 }, { "epoch": 57.43, "learning_rate": 4.271052662198972e-05, "loss": 0.0029, "step": 239180 }, { "epoch": 57.43, "learning_rate": 4.270697542192527e-05, "loss": 0.0025, "step": 239190 }, { "epoch": 57.44, "learning_rate": 4.2703424259449106e-05, "loss": 0.0027, "step": 239200 }, { "epoch": 57.44, "learning_rate": 4.269987313457958e-05, "loss": 0.0042, "step": 239210 }, { "epoch": 57.44, "learning_rate": 4.2696322047334945e-05, "loss": 0.0046, "step": 239220 }, { "epoch": 57.44, "learning_rate": 4.2692770997733556e-05, "loss": 0.0058, "step": 239230 }, { "epoch": 57.45, "learning_rate": 4.268921998579366e-05, "loss": 0.0037, "step": 239240 }, { "epoch": 57.45, "learning_rate": 4.26856690115336e-05, "loss": 0.0076, "step": 239250 }, { "epoch": 57.45, "learning_rate": 4.2682118074971664e-05, "loss": 0.0034, "step": 239260 }, { "epoch": 57.45, "learning_rate": 4.267856717612615e-05, "loss": 0.0036, "step": 239270 }, { "epoch": 57.45, "learning_rate": 4.267501631501535e-05, "loss": 0.0053, "step": 239280 }, { "epoch": 57.46, "learning_rate": 4.267146549165758e-05, "loss": 0.0026, "step": 239290 }, { "epoch": 57.46, "learning_rate": 4.266791470607116e-05, "loss": 0.003, "step": 239300 }, { "epoch": 57.46, "learning_rate": 4.2664363958274336e-05, "loss": 0.0046, "step": 239310 }, { "epoch": 57.46, "learning_rate": 4.266081324828547e-05, "loss": 0.0032, "step": 239320 }, { "epoch": 57.47, "learning_rate": 4.265726257612281e-05, "loss": 0.0044, "step": 239330 }, { "epoch": 57.47, "learning_rate": 4.2653711941804704e-05, "loss": 0.0035, "step": 239340 }, { "epoch": 57.47, "learning_rate": 4.265016134534943e-05, "loss": 0.0025, "step": 239350 }, { "epoch": 57.47, "learning_rate": 4.2646610786775254e-05, "loss": 0.0029, "step": 239360 }, { "epoch": 57.48, "learning_rate": 4.264306026610054e-05, "loss": 0.0039, "step": 239370 }, { "epoch": 57.48, "learning_rate": 4.2639509783343525e-05, "loss": 0.0036, "step": 239380 }, { "epoch": 57.48, "learning_rate": 4.263595933852257e-05, "loss": 0.0025, "step": 239390 }, { "epoch": 57.48, "learning_rate": 4.263240893165591e-05, "loss": 0.0037, "step": 239400 }, { "epoch": 57.48, "learning_rate": 4.262885856276191e-05, "loss": 0.0037, "step": 239410 }, { "epoch": 57.49, "learning_rate": 4.262530823185881e-05, "loss": 0.0039, "step": 239420 }, { "epoch": 57.49, "learning_rate": 4.262175793896494e-05, "loss": 0.0032, "step": 239430 }, { "epoch": 57.49, "learning_rate": 4.2618207684098595e-05, "loss": 0.0032, "step": 239440 }, { "epoch": 57.49, "learning_rate": 4.261465746727805e-05, "loss": 0.0053, "step": 239450 }, { "epoch": 57.5, "learning_rate": 4.261110728852164e-05, "loss": 0.0054, "step": 239460 }, { "epoch": 57.5, "learning_rate": 4.260755714784764e-05, "loss": 0.0026, "step": 239470 }, { "epoch": 57.5, "learning_rate": 4.2604007045274365e-05, "loss": 0.0029, "step": 239480 }, { "epoch": 57.5, "learning_rate": 4.26004569808201e-05, "loss": 0.0035, "step": 239490 }, { "epoch": 57.5, "learning_rate": 4.259690695450312e-05, "loss": 0.0031, "step": 239500 }, { "epoch": 57.51, "learning_rate": 4.2593356966341764e-05, "loss": 0.0046, "step": 239510 }, { "epoch": 57.51, "learning_rate": 4.2589807016354284e-05, "loss": 0.0053, "step": 239520 }, { "epoch": 57.51, "learning_rate": 4.2586257104559026e-05, "loss": 0.0029, "step": 239530 }, { "epoch": 57.51, "learning_rate": 4.258270723097424e-05, "loss": 0.0027, "step": 239540 }, { "epoch": 57.52, "learning_rate": 4.257915739561826e-05, "loss": 0.0028, "step": 239550 }, { "epoch": 57.52, "learning_rate": 4.257560759850936e-05, "loss": 0.0032, "step": 239560 }, { "epoch": 57.52, "learning_rate": 4.2572057839665835e-05, "loss": 0.0022, "step": 239570 }, { "epoch": 57.52, "learning_rate": 4.2568508119105984e-05, "loss": 0.0025, "step": 239580 }, { "epoch": 57.53, "learning_rate": 4.256495843684811e-05, "loss": 0.0028, "step": 239590 }, { "epoch": 57.53, "learning_rate": 4.256140879291051e-05, "loss": 0.0044, "step": 239600 }, { "epoch": 57.53, "learning_rate": 4.2557859187311445e-05, "loss": 0.0042, "step": 239610 }, { "epoch": 57.53, "learning_rate": 4.255430962006927e-05, "loss": 0.0039, "step": 239620 }, { "epoch": 57.53, "learning_rate": 4.2550760091202236e-05, "loss": 0.0046, "step": 239630 }, { "epoch": 57.54, "learning_rate": 4.2547210600728626e-05, "loss": 0.0037, "step": 239640 }, { "epoch": 57.54, "learning_rate": 4.254366114866678e-05, "loss": 0.0034, "step": 239650 }, { "epoch": 57.54, "learning_rate": 4.2540111735034944e-05, "loss": 0.0084, "step": 239660 }, { "epoch": 57.54, "learning_rate": 4.2536562359851456e-05, "loss": 0.0092, "step": 239670 }, { "epoch": 57.55, "learning_rate": 4.253301302313457e-05, "loss": 0.0065, "step": 239680 }, { "epoch": 57.55, "learning_rate": 4.252946372490261e-05, "loss": 0.0032, "step": 239690 }, { "epoch": 57.55, "learning_rate": 4.252591446517386e-05, "loss": 0.0025, "step": 239700 }, { "epoch": 57.55, "learning_rate": 4.252236524396659e-05, "loss": 0.0054, "step": 239710 }, { "epoch": 57.56, "learning_rate": 4.2518816061299125e-05, "loss": 0.0054, "step": 239720 }, { "epoch": 57.56, "learning_rate": 4.251526691718974e-05, "loss": 0.0095, "step": 239730 }, { "epoch": 57.56, "learning_rate": 4.251171781165674e-05, "loss": 0.0039, "step": 239740 }, { "epoch": 57.56, "learning_rate": 4.25081687447184e-05, "loss": 0.0033, "step": 239750 }, { "epoch": 57.56, "learning_rate": 4.250461971639302e-05, "loss": 0.0045, "step": 239760 }, { "epoch": 57.57, "learning_rate": 4.250107072669891e-05, "loss": 0.0029, "step": 239770 }, { "epoch": 57.57, "learning_rate": 4.249752177565432e-05, "loss": 0.0053, "step": 239780 }, { "epoch": 57.57, "learning_rate": 4.249397286327759e-05, "loss": 0.0115, "step": 239790 }, { "epoch": 57.57, "learning_rate": 4.249042398958696e-05, "loss": 0.0047, "step": 239800 }, { "epoch": 57.58, "learning_rate": 4.248687515460077e-05, "loss": 0.0064, "step": 239810 }, { "epoch": 57.58, "learning_rate": 4.2483326358337266e-05, "loss": 0.0037, "step": 239820 }, { "epoch": 57.58, "learning_rate": 4.2479777600814784e-05, "loss": 0.0052, "step": 239830 }, { "epoch": 57.58, "learning_rate": 4.2476228882051595e-05, "loss": 0.0043, "step": 239840 }, { "epoch": 57.58, "learning_rate": 4.247268020206595e-05, "loss": 0.0039, "step": 239850 }, { "epoch": 57.59, "learning_rate": 4.24691315608762e-05, "loss": 0.0045, "step": 239860 }, { "epoch": 57.59, "learning_rate": 4.2465582958500606e-05, "loss": 0.0132, "step": 239870 }, { "epoch": 57.59, "learning_rate": 4.2462034394957464e-05, "loss": 0.0037, "step": 239880 }, { "epoch": 57.59, "learning_rate": 4.245848587026505e-05, "loss": 0.0069, "step": 239890 }, { "epoch": 57.6, "learning_rate": 4.2454937384441665e-05, "loss": 0.0033, "step": 239900 }, { "epoch": 57.6, "learning_rate": 4.245138893750561e-05, "loss": 0.0032, "step": 239910 }, { "epoch": 57.6, "learning_rate": 4.244784052947514e-05, "loss": 0.0037, "step": 239920 }, { "epoch": 57.6, "learning_rate": 4.244429216036858e-05, "loss": 0.0062, "step": 239930 }, { "epoch": 57.61, "learning_rate": 4.244074383020418e-05, "loss": 0.0047, "step": 239940 }, { "epoch": 57.61, "learning_rate": 4.243719553900027e-05, "loss": 0.0047, "step": 239950 }, { "epoch": 57.61, "learning_rate": 4.243364728677509e-05, "loss": 0.0039, "step": 239960 }, { "epoch": 57.61, "learning_rate": 4.243009907354699e-05, "loss": 0.0046, "step": 239970 }, { "epoch": 57.61, "learning_rate": 4.242655089933422e-05, "loss": 0.0041, "step": 239980 }, { "epoch": 57.62, "learning_rate": 4.242300276415504e-05, "loss": 0.004, "step": 239990 }, { "epoch": 57.62, "learning_rate": 4.241945466802779e-05, "loss": 0.0048, "step": 240000 }, { "epoch": 57.62, "learning_rate": 4.2415906610970724e-05, "loss": 0.0071, "step": 240010 }, { "epoch": 57.62, "learning_rate": 4.241235859300214e-05, "loss": 0.0045, "step": 240020 }, { "epoch": 57.63, "learning_rate": 4.2408810614140324e-05, "loss": 0.0024, "step": 240030 }, { "epoch": 57.63, "learning_rate": 4.240526267440356e-05, "loss": 0.0058, "step": 240040 }, { "epoch": 57.63, "learning_rate": 4.240171477381015e-05, "loss": 0.0193, "step": 240050 }, { "epoch": 57.63, "learning_rate": 4.2398166912378345e-05, "loss": 0.0048, "step": 240060 }, { "epoch": 57.64, "learning_rate": 4.239461909012647e-05, "loss": 0.0026, "step": 240070 }, { "epoch": 57.64, "learning_rate": 4.239107130707277e-05, "loss": 0.0042, "step": 240080 }, { "epoch": 57.64, "learning_rate": 4.238752356323558e-05, "loss": 0.0041, "step": 240090 }, { "epoch": 57.64, "learning_rate": 4.238397585863313e-05, "loss": 0.0051, "step": 240100 }, { "epoch": 57.64, "learning_rate": 4.238042819328375e-05, "loss": 0.0038, "step": 240110 }, { "epoch": 57.65, "learning_rate": 4.237688056720569e-05, "loss": 0.0087, "step": 240120 }, { "epoch": 57.65, "learning_rate": 4.237333298041727e-05, "loss": 0.0045, "step": 240130 }, { "epoch": 57.65, "learning_rate": 4.236978543293676e-05, "loss": 0.0034, "step": 240140 }, { "epoch": 57.65, "learning_rate": 4.2366237924782415e-05, "loss": 0.0036, "step": 240150 }, { "epoch": 57.66, "learning_rate": 4.2362690455972567e-05, "loss": 0.0032, "step": 240160 }, { "epoch": 57.66, "learning_rate": 4.235914302652545e-05, "loss": 0.0037, "step": 240170 }, { "epoch": 57.66, "learning_rate": 4.235559563645939e-05, "loss": 0.0029, "step": 240180 }, { "epoch": 57.66, "learning_rate": 4.235204828579265e-05, "loss": 0.0065, "step": 240190 }, { "epoch": 57.66, "learning_rate": 4.234850097454352e-05, "loss": 0.0042, "step": 240200 }, { "epoch": 57.67, "learning_rate": 4.2344953702730293e-05, "loss": 0.0036, "step": 240210 }, { "epoch": 57.67, "learning_rate": 4.2341406470371216e-05, "loss": 0.0027, "step": 240220 }, { "epoch": 57.67, "learning_rate": 4.2337859277484607e-05, "loss": 0.0039, "step": 240230 }, { "epoch": 57.67, "learning_rate": 4.233431212408872e-05, "loss": 0.006, "step": 240240 }, { "epoch": 57.68, "learning_rate": 4.233076501020188e-05, "loss": 0.0065, "step": 240250 }, { "epoch": 57.68, "learning_rate": 4.232721793584231e-05, "loss": 0.0032, "step": 240260 }, { "epoch": 57.68, "learning_rate": 4.232367090102835e-05, "loss": 0.0052, "step": 240270 }, { "epoch": 57.68, "learning_rate": 4.232012390577825e-05, "loss": 0.0035, "step": 240280 }, { "epoch": 57.69, "learning_rate": 4.231657695011028e-05, "loss": 0.0023, "step": 240290 }, { "epoch": 57.69, "learning_rate": 4.231303003404276e-05, "loss": 0.0079, "step": 240300 }, { "epoch": 57.69, "learning_rate": 4.230948315759391e-05, "loss": 0.0032, "step": 240310 }, { "epoch": 57.69, "learning_rate": 4.2305936320782086e-05, "loss": 0.0029, "step": 240320 }, { "epoch": 57.69, "learning_rate": 4.23023895236255e-05, "loss": 0.0041, "step": 240330 }, { "epoch": 57.7, "learning_rate": 4.229884276614248e-05, "loss": 0.0042, "step": 240340 }, { "epoch": 57.7, "learning_rate": 4.2295296048351294e-05, "loss": 0.0034, "step": 240350 }, { "epoch": 57.7, "learning_rate": 4.2291749370270195e-05, "loss": 0.0072, "step": 240360 }, { "epoch": 57.7, "learning_rate": 4.228820273191751e-05, "loss": 0.0083, "step": 240370 }, { "epoch": 57.71, "learning_rate": 4.2284656133311464e-05, "loss": 0.0036, "step": 240380 }, { "epoch": 57.71, "learning_rate": 4.22811095744704e-05, "loss": 0.0074, "step": 240390 }, { "epoch": 57.71, "learning_rate": 4.2277563055412525e-05, "loss": 0.0076, "step": 240400 }, { "epoch": 57.71, "learning_rate": 4.227401657615618e-05, "loss": 0.0033, "step": 240410 }, { "epoch": 57.72, "learning_rate": 4.227047013671963e-05, "loss": 0.0089, "step": 240420 }, { "epoch": 57.72, "learning_rate": 4.226692373712111e-05, "loss": 0.0069, "step": 240430 }, { "epoch": 57.72, "learning_rate": 4.226337737737895e-05, "loss": 0.0033, "step": 240440 }, { "epoch": 57.72, "learning_rate": 4.225983105751139e-05, "loss": 0.0077, "step": 240450 }, { "epoch": 57.72, "learning_rate": 4.225628477753675e-05, "loss": 0.0043, "step": 240460 }, { "epoch": 57.73, "learning_rate": 4.225273853747325e-05, "loss": 0.0054, "step": 240470 }, { "epoch": 57.73, "learning_rate": 4.2249192337339226e-05, "loss": 0.0066, "step": 240480 }, { "epoch": 57.73, "learning_rate": 4.224564617715292e-05, "loss": 0.0031, "step": 240490 }, { "epoch": 57.73, "learning_rate": 4.2242100056932615e-05, "loss": 0.009, "step": 240500 }, { "epoch": 57.74, "learning_rate": 4.2238553976696606e-05, "loss": 0.0049, "step": 240510 }, { "epoch": 57.74, "learning_rate": 4.223500793646313e-05, "loss": 0.0035, "step": 240520 }, { "epoch": 57.74, "learning_rate": 4.223146193625052e-05, "loss": 0.0031, "step": 240530 }, { "epoch": 57.74, "learning_rate": 4.2227915976076984e-05, "loss": 0.0027, "step": 240540 }, { "epoch": 57.74, "learning_rate": 4.222437005596087e-05, "loss": 0.0034, "step": 240550 }, { "epoch": 57.75, "learning_rate": 4.222082417592041e-05, "loss": 0.0024, "step": 240560 }, { "epoch": 57.75, "learning_rate": 4.221727833597386e-05, "loss": 0.0021, "step": 240570 }, { "epoch": 57.75, "learning_rate": 4.221373253613955e-05, "loss": 0.0024, "step": 240580 }, { "epoch": 57.75, "learning_rate": 4.221018677643571e-05, "loss": 0.0053, "step": 240590 }, { "epoch": 57.76, "learning_rate": 4.220664105688066e-05, "loss": 0.0024, "step": 240600 }, { "epoch": 57.76, "learning_rate": 4.2203095377492615e-05, "loss": 0.0034, "step": 240610 }, { "epoch": 57.76, "learning_rate": 4.21995497382899e-05, "loss": 0.0024, "step": 240620 }, { "epoch": 57.76, "learning_rate": 4.2196004139290765e-05, "loss": 0.0082, "step": 240630 }, { "epoch": 57.77, "learning_rate": 4.2192458580513486e-05, "loss": 0.0039, "step": 240640 }, { "epoch": 57.77, "learning_rate": 4.218891306197635e-05, "loss": 0.0027, "step": 240650 }, { "epoch": 57.77, "learning_rate": 4.218536758369761e-05, "loss": 0.0033, "step": 240660 }, { "epoch": 57.77, "learning_rate": 4.218182214569556e-05, "loss": 0.0118, "step": 240670 }, { "epoch": 57.77, "learning_rate": 4.2178276747988446e-05, "loss": 0.0025, "step": 240680 }, { "epoch": 57.78, "learning_rate": 4.217473139059459e-05, "loss": 0.0078, "step": 240690 }, { "epoch": 57.78, "learning_rate": 4.2171186073532227e-05, "loss": 0.0033, "step": 240700 }, { "epoch": 57.78, "learning_rate": 4.2167640796819616e-05, "loss": 0.0031, "step": 240710 }, { "epoch": 57.78, "learning_rate": 4.216409556047507e-05, "loss": 0.0024, "step": 240720 }, { "epoch": 57.79, "learning_rate": 4.216055036451682e-05, "loss": 0.003, "step": 240730 }, { "epoch": 57.79, "learning_rate": 4.215700520896319e-05, "loss": 0.0027, "step": 240740 }, { "epoch": 57.79, "learning_rate": 4.2153460093832385e-05, "loss": 0.0038, "step": 240750 }, { "epoch": 57.79, "learning_rate": 4.214991501914274e-05, "loss": 0.0041, "step": 240760 }, { "epoch": 57.8, "learning_rate": 4.2146369984912485e-05, "loss": 0.0066, "step": 240770 }, { "epoch": 57.8, "learning_rate": 4.2142824991159904e-05, "loss": 0.0028, "step": 240780 }, { "epoch": 57.8, "learning_rate": 4.213928003790327e-05, "loss": 0.0032, "step": 240790 }, { "epoch": 57.8, "learning_rate": 4.213573512516086e-05, "loss": 0.0034, "step": 240800 }, { "epoch": 57.8, "learning_rate": 4.213219025295093e-05, "loss": 0.0028, "step": 240810 }, { "epoch": 57.81, "learning_rate": 4.212864542129174e-05, "loss": 0.0026, "step": 240820 }, { "epoch": 57.81, "learning_rate": 4.2125100630201614e-05, "loss": 0.0042, "step": 240830 }, { "epoch": 57.81, "learning_rate": 4.2121555879698777e-05, "loss": 0.003, "step": 240840 }, { "epoch": 57.81, "learning_rate": 4.2118011169801485e-05, "loss": 0.0023, "step": 240850 }, { "epoch": 57.82, "learning_rate": 4.211446650052806e-05, "loss": 0.0062, "step": 240860 }, { "epoch": 57.82, "learning_rate": 4.21109218718967e-05, "loss": 0.0032, "step": 240870 }, { "epoch": 57.82, "learning_rate": 4.2107377283925755e-05, "loss": 0.0023, "step": 240880 }, { "epoch": 57.82, "learning_rate": 4.210383273663342e-05, "loss": 0.0027, "step": 240890 }, { "epoch": 57.82, "learning_rate": 4.210028823003802e-05, "loss": 0.0032, "step": 240900 }, { "epoch": 57.83, "learning_rate": 4.209674376415779e-05, "loss": 0.0057, "step": 240910 }, { "epoch": 57.83, "learning_rate": 4.2093199339011015e-05, "loss": 0.0027, "step": 240920 }, { "epoch": 57.83, "learning_rate": 4.2089654954615956e-05, "loss": 0.0027, "step": 240930 }, { "epoch": 57.83, "learning_rate": 4.208611061099087e-05, "loss": 0.0029, "step": 240940 }, { "epoch": 57.84, "learning_rate": 4.2082566308154045e-05, "loss": 0.0023, "step": 240950 }, { "epoch": 57.84, "learning_rate": 4.207902204612373e-05, "loss": 0.0023, "step": 240960 }, { "epoch": 57.84, "learning_rate": 4.207547782491822e-05, "loss": 0.0021, "step": 240970 }, { "epoch": 57.84, "learning_rate": 4.207193364455574e-05, "loss": 0.0045, "step": 240980 }, { "epoch": 57.85, "learning_rate": 4.2068389505054605e-05, "loss": 0.0026, "step": 240990 }, { "epoch": 57.85, "learning_rate": 4.206484540643306e-05, "loss": 0.0021, "step": 241000 }, { "epoch": 57.85, "learning_rate": 4.2061301348709335e-05, "loss": 0.0031, "step": 241010 }, { "epoch": 57.85, "learning_rate": 4.205775733190177e-05, "loss": 0.0064, "step": 241020 }, { "epoch": 57.85, "learning_rate": 4.205421335602855e-05, "loss": 0.0026, "step": 241030 }, { "epoch": 57.86, "learning_rate": 4.2050669421108016e-05, "loss": 0.003, "step": 241040 }, { "epoch": 57.86, "learning_rate": 4.204712552715836e-05, "loss": 0.0072, "step": 241050 }, { "epoch": 57.86, "learning_rate": 4.204358167419792e-05, "loss": 0.0027, "step": 241060 }, { "epoch": 57.86, "learning_rate": 4.204003786224491e-05, "loss": 0.0041, "step": 241070 }, { "epoch": 57.87, "learning_rate": 4.203649409131762e-05, "loss": 0.0087, "step": 241080 }, { "epoch": 57.87, "learning_rate": 4.20329503614343e-05, "loss": 0.0027, "step": 241090 }, { "epoch": 57.87, "learning_rate": 4.202940667261322e-05, "loss": 0.0052, "step": 241100 }, { "epoch": 57.87, "learning_rate": 4.202586302487265e-05, "loss": 0.0029, "step": 241110 }, { "epoch": 57.88, "learning_rate": 4.202231941823083e-05, "loss": 0.0051, "step": 241120 }, { "epoch": 57.88, "learning_rate": 4.2018775852706065e-05, "loss": 0.0032, "step": 241130 }, { "epoch": 57.88, "learning_rate": 4.20152323283166e-05, "loss": 0.0036, "step": 241140 }, { "epoch": 57.88, "learning_rate": 4.201168884508067e-05, "loss": 0.0025, "step": 241150 }, { "epoch": 57.88, "learning_rate": 4.200814540301659e-05, "loss": 0.0042, "step": 241160 }, { "epoch": 57.89, "learning_rate": 4.200460200214256e-05, "loss": 0.0027, "step": 241170 }, { "epoch": 57.89, "learning_rate": 4.200105864247691e-05, "loss": 0.0036, "step": 241180 }, { "epoch": 57.89, "learning_rate": 4.199751532403785e-05, "loss": 0.004, "step": 241190 }, { "epoch": 57.89, "learning_rate": 4.199397204684368e-05, "loss": 0.0028, "step": 241200 }, { "epoch": 57.9, "learning_rate": 4.199042881091265e-05, "loss": 0.0041, "step": 241210 }, { "epoch": 57.9, "learning_rate": 4.1986885616263e-05, "loss": 0.0029, "step": 241220 }, { "epoch": 57.9, "learning_rate": 4.1983342462913e-05, "loss": 0.0022, "step": 241230 }, { "epoch": 57.9, "learning_rate": 4.197979935088093e-05, "loss": 0.0023, "step": 241240 }, { "epoch": 57.9, "learning_rate": 4.197625628018505e-05, "loss": 0.0122, "step": 241250 }, { "epoch": 57.91, "learning_rate": 4.1972713250843604e-05, "loss": 0.0032, "step": 241260 }, { "epoch": 57.91, "learning_rate": 4.1969170262874855e-05, "loss": 0.0031, "step": 241270 }, { "epoch": 57.91, "learning_rate": 4.196562731629709e-05, "loss": 0.0027, "step": 241280 }, { "epoch": 57.91, "learning_rate": 4.196208441112853e-05, "loss": 0.0024, "step": 241290 }, { "epoch": 57.92, "learning_rate": 4.195854154738747e-05, "loss": 0.0042, "step": 241300 }, { "epoch": 57.92, "learning_rate": 4.1954998725092134e-05, "loss": 0.0023, "step": 241310 }, { "epoch": 57.92, "learning_rate": 4.195145594426082e-05, "loss": 0.0044, "step": 241320 }, { "epoch": 57.92, "learning_rate": 4.194791320491175e-05, "loss": 0.0025, "step": 241330 }, { "epoch": 57.93, "learning_rate": 4.1944370507063225e-05, "loss": 0.0029, "step": 241340 }, { "epoch": 57.93, "learning_rate": 4.1940827850733475e-05, "loss": 0.0038, "step": 241350 }, { "epoch": 57.93, "learning_rate": 4.193728523594075e-05, "loss": 0.0023, "step": 241360 }, { "epoch": 57.93, "learning_rate": 4.1933742662703355e-05, "loss": 0.0029, "step": 241370 }, { "epoch": 57.93, "learning_rate": 4.193020013103948e-05, "loss": 0.0026, "step": 241380 }, { "epoch": 57.94, "learning_rate": 4.1926657640967445e-05, "loss": 0.0032, "step": 241390 }, { "epoch": 57.94, "learning_rate": 4.1923115192505476e-05, "loss": 0.0021, "step": 241400 }, { "epoch": 57.94, "learning_rate": 4.191957278567184e-05, "loss": 0.0027, "step": 241410 }, { "epoch": 57.94, "learning_rate": 4.1916030420484806e-05, "loss": 0.0024, "step": 241420 }, { "epoch": 57.95, "learning_rate": 4.1912488096962595e-05, "loss": 0.0032, "step": 241430 }, { "epoch": 57.95, "learning_rate": 4.190894581512351e-05, "loss": 0.0044, "step": 241440 }, { "epoch": 57.95, "learning_rate": 4.190540357498576e-05, "loss": 0.0021, "step": 241450 }, { "epoch": 58.0, "learning_rate": 4.190186137656766e-05, "loss": 0.0036, "step": 241460 }, { "epoch": 58.0, "learning_rate": 4.1898319219887405e-05, "loss": 0.0034, "step": 241470 }, { "epoch": 58.01, "learning_rate": 4.18947771049633e-05, "loss": 0.004, "step": 241480 }, { "epoch": 58.01, "learning_rate": 4.1891235031813594e-05, "loss": 0.0072, "step": 241490 }, { "epoch": 58.01, "learning_rate": 4.188769300045649e-05, "loss": 0.0029, "step": 241500 }, { "epoch": 58.01, "learning_rate": 4.188415101091032e-05, "loss": 0.003, "step": 241510 }, { "epoch": 58.02, "learning_rate": 4.188060906319328e-05, "loss": 0.0034, "step": 241520 }, { "epoch": 58.02, "learning_rate": 4.187706715732366e-05, "loss": 0.0041, "step": 241530 }, { "epoch": 58.02, "learning_rate": 4.1873525293319696e-05, "loss": 0.0036, "step": 241540 }, { "epoch": 58.02, "learning_rate": 4.1869983471199655e-05, "loss": 0.0026, "step": 241550 }, { "epoch": 58.02, "learning_rate": 4.18664416909818e-05, "loss": 0.0069, "step": 241560 }, { "epoch": 58.03, "learning_rate": 4.1862899952684355e-05, "loss": 0.0063, "step": 241570 }, { "epoch": 58.03, "learning_rate": 4.185935825632561e-05, "loss": 0.0026, "step": 241580 }, { "epoch": 58.03, "learning_rate": 4.185581660192377e-05, "loss": 0.0029, "step": 241590 }, { "epoch": 58.03, "learning_rate": 4.185227498949715e-05, "loss": 0.0023, "step": 241600 }, { "epoch": 58.04, "learning_rate": 4.184873341906395e-05, "loss": 0.0028, "step": 241610 }, { "epoch": 58.04, "learning_rate": 4.1845191890642465e-05, "loss": 0.0023, "step": 241620 }, { "epoch": 58.04, "learning_rate": 4.184165040425093e-05, "loss": 0.0021, "step": 241630 }, { "epoch": 58.04, "learning_rate": 4.183810895990757e-05, "loss": 0.0083, "step": 241640 }, { "epoch": 58.04, "learning_rate": 4.18345675576307e-05, "loss": 0.0026, "step": 241650 }, { "epoch": 58.05, "learning_rate": 4.1831026197438505e-05, "loss": 0.0041, "step": 241660 }, { "epoch": 58.05, "learning_rate": 4.1827484879349296e-05, "loss": 0.0028, "step": 241670 }, { "epoch": 58.05, "learning_rate": 4.182394360338127e-05, "loss": 0.0033, "step": 241680 }, { "epoch": 58.05, "learning_rate": 4.1820402369552725e-05, "loss": 0.0028, "step": 241690 }, { "epoch": 58.06, "learning_rate": 4.18168611778819e-05, "loss": 0.0042, "step": 241700 }, { "epoch": 58.06, "learning_rate": 4.1813320028387025e-05, "loss": 0.0048, "step": 241710 }, { "epoch": 58.06, "learning_rate": 4.180977892108638e-05, "loss": 0.003, "step": 241720 }, { "epoch": 58.06, "learning_rate": 4.1806237855998196e-05, "loss": 0.0031, "step": 241730 }, { "epoch": 58.07, "learning_rate": 4.1802696833140734e-05, "loss": 0.0031, "step": 241740 }, { "epoch": 58.07, "learning_rate": 4.179915585253223e-05, "loss": 0.0073, "step": 241750 }, { "epoch": 58.07, "learning_rate": 4.1795614914190966e-05, "loss": 0.0048, "step": 241760 }, { "epoch": 58.07, "learning_rate": 4.179207401813515e-05, "loss": 0.0041, "step": 241770 }, { "epoch": 58.07, "learning_rate": 4.178853316438307e-05, "loss": 0.0028, "step": 241780 }, { "epoch": 58.08, "learning_rate": 4.178499235295297e-05, "loss": 0.0021, "step": 241790 }, { "epoch": 58.08, "learning_rate": 4.1781451583863055e-05, "loss": 0.0048, "step": 241800 }, { "epoch": 58.08, "learning_rate": 4.177791085713163e-05, "loss": 0.0026, "step": 241810 }, { "epoch": 58.08, "learning_rate": 4.177437017277691e-05, "loss": 0.009, "step": 241820 }, { "epoch": 58.09, "learning_rate": 4.177082953081716e-05, "loss": 0.003, "step": 241830 }, { "epoch": 58.09, "learning_rate": 4.1767288931270614e-05, "loss": 0.0046, "step": 241840 }, { "epoch": 58.09, "learning_rate": 4.176374837415554e-05, "loss": 0.0048, "step": 241850 }, { "epoch": 58.09, "learning_rate": 4.176020785949018e-05, "loss": 0.0067, "step": 241860 }, { "epoch": 58.1, "learning_rate": 4.175666738729276e-05, "loss": 0.0035, "step": 241870 }, { "epoch": 58.1, "learning_rate": 4.1753126957581565e-05, "loss": 0.0038, "step": 241880 }, { "epoch": 58.1, "learning_rate": 4.17495865703748e-05, "loss": 0.0042, "step": 241890 }, { "epoch": 58.1, "learning_rate": 4.174604622569076e-05, "loss": 0.0023, "step": 241900 }, { "epoch": 58.1, "learning_rate": 4.1742505923547645e-05, "loss": 0.0055, "step": 241910 }, { "epoch": 58.11, "learning_rate": 4.173896566396375e-05, "loss": 0.0036, "step": 241920 }, { "epoch": 58.11, "learning_rate": 4.1735425446957286e-05, "loss": 0.0031, "step": 241930 }, { "epoch": 58.11, "learning_rate": 4.173188527254649e-05, "loss": 0.0028, "step": 241940 }, { "epoch": 58.11, "learning_rate": 4.172834514074965e-05, "loss": 0.0051, "step": 241950 }, { "epoch": 58.12, "learning_rate": 4.172480505158496e-05, "loss": 0.0033, "step": 241960 }, { "epoch": 58.12, "learning_rate": 4.172126500507072e-05, "loss": 0.0056, "step": 241970 }, { "epoch": 58.12, "learning_rate": 4.1717725001225125e-05, "loss": 0.0035, "step": 241980 }, { "epoch": 58.12, "learning_rate": 4.1714185040066475e-05, "loss": 0.0145, "step": 241990 }, { "epoch": 58.12, "learning_rate": 4.171064512161296e-05, "loss": 0.0023, "step": 242000 }, { "epoch": 58.13, "learning_rate": 4.170710524588285e-05, "loss": 0.0048, "step": 242010 }, { "epoch": 58.13, "learning_rate": 4.1703565412894405e-05, "loss": 0.003, "step": 242020 }, { "epoch": 58.13, "learning_rate": 4.170002562266583e-05, "loss": 0.0035, "step": 242030 }, { "epoch": 58.13, "learning_rate": 4.1696485875215416e-05, "loss": 0.0024, "step": 242040 }, { "epoch": 58.14, "learning_rate": 4.169294617056137e-05, "loss": 0.0032, "step": 242050 }, { "epoch": 58.14, "learning_rate": 4.168940650872196e-05, "loss": 0.0047, "step": 242060 }, { "epoch": 58.14, "learning_rate": 4.1685866889715426e-05, "loss": 0.0136, "step": 242070 }, { "epoch": 58.14, "learning_rate": 4.1682327313559975e-05, "loss": 0.0041, "step": 242080 }, { "epoch": 58.15, "learning_rate": 4.1678787780273906e-05, "loss": 0.0055, "step": 242090 }, { "epoch": 58.15, "learning_rate": 4.1675248289875405e-05, "loss": 0.0052, "step": 242100 }, { "epoch": 58.15, "learning_rate": 4.1671708842382775e-05, "loss": 0.0037, "step": 242110 }, { "epoch": 58.15, "learning_rate": 4.16681694378142e-05, "loss": 0.0035, "step": 242120 }, { "epoch": 58.15, "learning_rate": 4.166463007618797e-05, "loss": 0.0043, "step": 242130 }, { "epoch": 58.16, "learning_rate": 4.166109075752229e-05, "loss": 0.0023, "step": 242140 }, { "epoch": 58.16, "learning_rate": 4.165755148183543e-05, "loss": 0.0033, "step": 242150 }, { "epoch": 58.16, "learning_rate": 4.165401224914561e-05, "loss": 0.0092, "step": 242160 }, { "epoch": 58.16, "learning_rate": 4.165047305947108e-05, "loss": 0.0035, "step": 242170 }, { "epoch": 58.17, "learning_rate": 4.1646933912830093e-05, "loss": 0.0031, "step": 242180 }, { "epoch": 58.17, "learning_rate": 4.164339480924086e-05, "loss": 0.0051, "step": 242190 }, { "epoch": 58.17, "learning_rate": 4.1639855748721666e-05, "loss": 0.0035, "step": 242200 }, { "epoch": 58.17, "learning_rate": 4.1636316731290717e-05, "loss": 0.0027, "step": 242210 }, { "epoch": 58.18, "learning_rate": 4.163277775696625e-05, "loss": 0.0028, "step": 242220 }, { "epoch": 58.18, "learning_rate": 4.1629238825766533e-05, "loss": 0.0034, "step": 242230 }, { "epoch": 58.18, "learning_rate": 4.162569993770977e-05, "loss": 0.0031, "step": 242240 }, { "epoch": 58.18, "learning_rate": 4.162216109281424e-05, "loss": 0.0074, "step": 242250 }, { "epoch": 58.18, "learning_rate": 4.161862229109813e-05, "loss": 0.0029, "step": 242260 }, { "epoch": 58.19, "learning_rate": 4.1615083532579746e-05, "loss": 0.0025, "step": 242270 }, { "epoch": 58.19, "learning_rate": 4.1611544817277276e-05, "loss": 0.0043, "step": 242280 }, { "epoch": 58.19, "learning_rate": 4.1608006145208974e-05, "loss": 0.0042, "step": 242290 }, { "epoch": 58.19, "learning_rate": 4.1604467516393075e-05, "loss": 0.0031, "step": 242300 }, { "epoch": 58.2, "learning_rate": 4.1600928930847826e-05, "loss": 0.004, "step": 242310 }, { "epoch": 58.2, "learning_rate": 4.159739038859146e-05, "loss": 0.0024, "step": 242320 }, { "epoch": 58.2, "learning_rate": 4.15938518896422e-05, "loss": 0.0036, "step": 242330 }, { "epoch": 58.2, "learning_rate": 4.1590313434018316e-05, "loss": 0.0026, "step": 242340 }, { "epoch": 58.2, "learning_rate": 4.1586775021738035e-05, "loss": 0.0061, "step": 242350 }, { "epoch": 58.21, "learning_rate": 4.158323665281956e-05, "loss": 0.0034, "step": 242360 }, { "epoch": 58.21, "learning_rate": 4.1579698327281177e-05, "loss": 0.0035, "step": 242370 }, { "epoch": 58.21, "learning_rate": 4.157616004514107e-05, "loss": 0.0041, "step": 242380 }, { "epoch": 58.21, "learning_rate": 4.1572621806417534e-05, "loss": 0.0025, "step": 242390 }, { "epoch": 58.22, "learning_rate": 4.156908361112876e-05, "loss": 0.0042, "step": 242400 }, { "epoch": 58.22, "learning_rate": 4.156554545929301e-05, "loss": 0.0069, "step": 242410 }, { "epoch": 58.22, "learning_rate": 4.15620073509285e-05, "loss": 0.006, "step": 242420 }, { "epoch": 58.22, "learning_rate": 4.1558469286053476e-05, "loss": 0.0025, "step": 242430 }, { "epoch": 58.23, "learning_rate": 4.155493126468617e-05, "loss": 0.0028, "step": 242440 }, { "epoch": 58.23, "learning_rate": 4.155139328684482e-05, "loss": 0.0027, "step": 242450 }, { "epoch": 58.23, "learning_rate": 4.154785535254767e-05, "loss": 0.0047, "step": 242460 }, { "epoch": 58.23, "learning_rate": 4.1544317461812935e-05, "loss": 0.0032, "step": 242470 }, { "epoch": 58.23, "learning_rate": 4.154077961465885e-05, "loss": 0.0071, "step": 242480 }, { "epoch": 58.24, "learning_rate": 4.153724181110368e-05, "loss": 0.0057, "step": 242490 }, { "epoch": 58.24, "learning_rate": 4.153370405116561e-05, "loss": 0.0029, "step": 242500 }, { "epoch": 58.24, "learning_rate": 4.153016633486293e-05, "loss": 0.0085, "step": 242510 }, { "epoch": 58.24, "learning_rate": 4.152662866221381e-05, "loss": 0.0047, "step": 242520 }, { "epoch": 58.25, "learning_rate": 4.152309103323655e-05, "loss": 0.0032, "step": 242530 }, { "epoch": 58.25, "learning_rate": 4.151955344794931e-05, "loss": 0.0047, "step": 242540 }, { "epoch": 58.25, "learning_rate": 4.15160159063704e-05, "loss": 0.0036, "step": 242550 }, { "epoch": 58.25, "learning_rate": 4.151247840851799e-05, "loss": 0.0042, "step": 242560 }, { "epoch": 58.26, "learning_rate": 4.150894095441036e-05, "loss": 0.005, "step": 242570 }, { "epoch": 58.26, "learning_rate": 4.15054035440657e-05, "loss": 0.0054, "step": 242580 }, { "epoch": 58.26, "learning_rate": 4.150186617750227e-05, "loss": 0.0042, "step": 242590 }, { "epoch": 58.26, "learning_rate": 4.149832885473829e-05, "loss": 0.0034, "step": 242600 }, { "epoch": 58.26, "learning_rate": 4.1494791575791994e-05, "loss": 0.0023, "step": 242610 }, { "epoch": 58.27, "learning_rate": 4.149125434068162e-05, "loss": 0.0022, "step": 242620 }, { "epoch": 58.27, "learning_rate": 4.148771714942538e-05, "loss": 0.0029, "step": 242630 }, { "epoch": 58.27, "learning_rate": 4.148418000204152e-05, "loss": 0.0036, "step": 242640 }, { "epoch": 58.27, "learning_rate": 4.1480642898548284e-05, "loss": 0.0054, "step": 242650 }, { "epoch": 58.28, "learning_rate": 4.147710583896386e-05, "loss": 0.0025, "step": 242660 }, { "epoch": 58.28, "learning_rate": 4.147356882330653e-05, "loss": 0.0034, "step": 242670 }, { "epoch": 58.28, "learning_rate": 4.147003185159447e-05, "loss": 0.003, "step": 242680 }, { "epoch": 58.28, "learning_rate": 4.146649492384596e-05, "loss": 0.005, "step": 242690 }, { "epoch": 58.28, "learning_rate": 4.1462958040079184e-05, "loss": 0.0085, "step": 242700 }, { "epoch": 58.29, "learning_rate": 4.145942120031242e-05, "loss": 0.0024, "step": 242710 }, { "epoch": 58.29, "learning_rate": 4.1455884404563874e-05, "loss": 0.0027, "step": 242720 }, { "epoch": 58.29, "learning_rate": 4.145234765285174e-05, "loss": 0.0027, "step": 242730 }, { "epoch": 58.29, "learning_rate": 4.144881094519429e-05, "loss": 0.0031, "step": 242740 }, { "epoch": 58.3, "learning_rate": 4.144527428160974e-05, "loss": 0.0023, "step": 242750 }, { "epoch": 58.3, "learning_rate": 4.144173766211632e-05, "loss": 0.0029, "step": 242760 }, { "epoch": 58.3, "learning_rate": 4.143820108673226e-05, "loss": 0.0034, "step": 242770 }, { "epoch": 58.3, "learning_rate": 4.143466455547578e-05, "loss": 0.0024, "step": 242780 }, { "epoch": 58.31, "learning_rate": 4.1431128068365114e-05, "loss": 0.0072, "step": 242790 }, { "epoch": 58.31, "learning_rate": 4.142759162541847e-05, "loss": 0.0025, "step": 242800 }, { "epoch": 58.31, "learning_rate": 4.142405522665411e-05, "loss": 0.0021, "step": 242810 }, { "epoch": 58.31, "learning_rate": 4.1420518872090225e-05, "loss": 0.0022, "step": 242820 }, { "epoch": 58.31, "learning_rate": 4.141698256174508e-05, "loss": 0.0023, "step": 242830 }, { "epoch": 58.32, "learning_rate": 4.141344629563685e-05, "loss": 0.0037, "step": 242840 }, { "epoch": 58.32, "learning_rate": 4.1409910073783805e-05, "loss": 0.0036, "step": 242850 }, { "epoch": 58.32, "learning_rate": 4.140637389620417e-05, "loss": 0.0035, "step": 242860 }, { "epoch": 58.32, "learning_rate": 4.140283776291612e-05, "loss": 0.0024, "step": 242870 }, { "epoch": 58.33, "learning_rate": 4.1399301673937954e-05, "loss": 0.0032, "step": 242880 }, { "epoch": 58.33, "learning_rate": 4.1395765629287826e-05, "loss": 0.0029, "step": 242890 }, { "epoch": 58.33, "learning_rate": 4.1392229628984006e-05, "loss": 0.0025, "step": 242900 }, { "epoch": 58.33, "learning_rate": 4.138869367304471e-05, "loss": 0.0045, "step": 242910 }, { "epoch": 58.34, "learning_rate": 4.1385157761488156e-05, "loss": 0.0021, "step": 242920 }, { "epoch": 58.34, "learning_rate": 4.138162189433258e-05, "loss": 0.0031, "step": 242930 }, { "epoch": 58.34, "learning_rate": 4.1378086071596176e-05, "loss": 0.005, "step": 242940 }, { "epoch": 58.34, "learning_rate": 4.137455029329722e-05, "loss": 0.0036, "step": 242950 }, { "epoch": 58.34, "learning_rate": 4.137101455945387e-05, "loss": 0.0024, "step": 242960 }, { "epoch": 58.35, "learning_rate": 4.1367478870084407e-05, "loss": 0.0031, "step": 242970 }, { "epoch": 58.35, "learning_rate": 4.1363943225207016e-05, "loss": 0.0027, "step": 242980 }, { "epoch": 58.35, "learning_rate": 4.1360407624839946e-05, "loss": 0.0042, "step": 242990 }, { "epoch": 58.35, "learning_rate": 4.135687206900141e-05, "loss": 0.0023, "step": 243000 }, { "epoch": 58.36, "learning_rate": 4.135333655770961e-05, "loss": 0.0024, "step": 243010 }, { "epoch": 58.36, "learning_rate": 4.13498010909828e-05, "loss": 0.0042, "step": 243020 }, { "epoch": 58.36, "learning_rate": 4.1346265668839175e-05, "loss": 0.0042, "step": 243030 }, { "epoch": 58.36, "learning_rate": 4.1342730291296984e-05, "loss": 0.0038, "step": 243040 }, { "epoch": 58.36, "learning_rate": 4.1339194958374414e-05, "loss": 0.0023, "step": 243050 }, { "epoch": 58.37, "learning_rate": 4.1335659670089715e-05, "loss": 0.0034, "step": 243060 }, { "epoch": 58.37, "learning_rate": 4.133212442646111e-05, "loss": 0.0043, "step": 243070 }, { "epoch": 58.37, "learning_rate": 4.132858922750679e-05, "loss": 0.0032, "step": 243080 }, { "epoch": 58.37, "learning_rate": 4.132505407324501e-05, "loss": 0.0021, "step": 243090 }, { "epoch": 58.38, "learning_rate": 4.132151896369395e-05, "loss": 0.0027, "step": 243100 }, { "epoch": 58.38, "learning_rate": 4.131798389887188e-05, "loss": 0.0028, "step": 243110 }, { "epoch": 58.38, "learning_rate": 4.131444887879697e-05, "loss": 0.0035, "step": 243120 }, { "epoch": 58.38, "learning_rate": 4.131091390348749e-05, "loss": 0.0025, "step": 243130 }, { "epoch": 58.39, "learning_rate": 4.130737897296163e-05, "loss": 0.0037, "step": 243140 }, { "epoch": 58.39, "learning_rate": 4.1303844087237586e-05, "loss": 0.0033, "step": 243150 }, { "epoch": 58.39, "learning_rate": 4.130030924633363e-05, "loss": 0.0038, "step": 243160 }, { "epoch": 58.39, "learning_rate": 4.1296774450267925e-05, "loss": 0.0028, "step": 243170 }, { "epoch": 58.39, "learning_rate": 4.129323969905874e-05, "loss": 0.0076, "step": 243180 }, { "epoch": 58.4, "learning_rate": 4.128970499272426e-05, "loss": 0.0036, "step": 243190 }, { "epoch": 58.4, "learning_rate": 4.128617033128271e-05, "loss": 0.0029, "step": 243200 }, { "epoch": 58.4, "learning_rate": 4.128263571475232e-05, "loss": 0.007, "step": 243210 }, { "epoch": 58.4, "learning_rate": 4.127910114315129e-05, "loss": 0.0024, "step": 243220 }, { "epoch": 58.41, "learning_rate": 4.1275566616497856e-05, "loss": 0.0028, "step": 243230 }, { "epoch": 58.41, "learning_rate": 4.127203213481021e-05, "loss": 0.0099, "step": 243240 }, { "epoch": 58.41, "learning_rate": 4.12684976981066e-05, "loss": 0.0028, "step": 243250 }, { "epoch": 58.41, "learning_rate": 4.12649633064052e-05, "loss": 0.0029, "step": 243260 }, { "epoch": 58.41, "learning_rate": 4.1261428959724285e-05, "loss": 0.0067, "step": 243270 }, { "epoch": 58.42, "learning_rate": 4.125789465808203e-05, "loss": 0.0024, "step": 243280 }, { "epoch": 58.42, "learning_rate": 4.1254360401496646e-05, "loss": 0.0053, "step": 243290 }, { "epoch": 58.42, "learning_rate": 4.125082618998637e-05, "loss": 0.0035, "step": 243300 }, { "epoch": 58.42, "learning_rate": 4.12472920235694e-05, "loss": 0.0027, "step": 243310 }, { "epoch": 58.43, "learning_rate": 4.124375790226398e-05, "loss": 0.0036, "step": 243320 }, { "epoch": 58.43, "learning_rate": 4.124022382608828e-05, "loss": 0.002, "step": 243330 }, { "epoch": 58.43, "learning_rate": 4.123668979506056e-05, "loss": 0.0023, "step": 243340 }, { "epoch": 58.43, "learning_rate": 4.1233155809198995e-05, "loss": 0.0038, "step": 243350 }, { "epoch": 58.44, "learning_rate": 4.122962186852182e-05, "loss": 0.0028, "step": 243360 }, { "epoch": 58.44, "learning_rate": 4.1226087973047265e-05, "loss": 0.003, "step": 243370 }, { "epoch": 58.44, "learning_rate": 4.1222554122793514e-05, "loss": 0.0025, "step": 243380 }, { "epoch": 58.44, "learning_rate": 4.12190203177788e-05, "loss": 0.0044, "step": 243390 }, { "epoch": 58.44, "learning_rate": 4.1215486558021315e-05, "loss": 0.0076, "step": 243400 }, { "epoch": 58.45, "learning_rate": 4.12119528435393e-05, "loss": 0.0033, "step": 243410 }, { "epoch": 58.45, "learning_rate": 4.120841917435094e-05, "loss": 0.0044, "step": 243420 }, { "epoch": 58.45, "learning_rate": 4.120488555047448e-05, "loss": 0.004, "step": 243430 }, { "epoch": 58.45, "learning_rate": 4.120135197192811e-05, "loss": 0.0029, "step": 243440 }, { "epoch": 58.46, "learning_rate": 4.119781843873003e-05, "loss": 0.0026, "step": 243450 }, { "epoch": 58.46, "learning_rate": 4.119428495089848e-05, "loss": 0.0024, "step": 243460 }, { "epoch": 58.46, "learning_rate": 4.119075150845165e-05, "loss": 0.0021, "step": 243470 }, { "epoch": 58.46, "learning_rate": 4.118721811140777e-05, "loss": 0.0022, "step": 243480 }, { "epoch": 58.47, "learning_rate": 4.118368475978502e-05, "loss": 0.0037, "step": 243490 }, { "epoch": 58.47, "learning_rate": 4.118015145360166e-05, "loss": 0.0034, "step": 243500 }, { "epoch": 58.47, "learning_rate": 4.1176618192875864e-05, "loss": 0.0069, "step": 243510 }, { "epoch": 58.47, "learning_rate": 4.1173084977625834e-05, "loss": 0.0027, "step": 243520 }, { "epoch": 58.47, "learning_rate": 4.116955180786983e-05, "loss": 0.0043, "step": 243530 }, { "epoch": 58.48, "learning_rate": 4.1166018683625995e-05, "loss": 0.004, "step": 243540 }, { "epoch": 58.48, "learning_rate": 4.11624856049126e-05, "loss": 0.0028, "step": 243550 }, { "epoch": 58.48, "learning_rate": 4.1158952571747814e-05, "loss": 0.0029, "step": 243560 }, { "epoch": 58.48, "learning_rate": 4.1155419584149876e-05, "loss": 0.0026, "step": 243570 }, { "epoch": 58.49, "learning_rate": 4.1151886642136975e-05, "loss": 0.0032, "step": 243580 }, { "epoch": 58.49, "learning_rate": 4.114835374572731e-05, "loss": 0.0024, "step": 243590 }, { "epoch": 58.49, "learning_rate": 4.1144820894939126e-05, "loss": 0.0027, "step": 243600 }, { "epoch": 58.49, "learning_rate": 4.114128808979058e-05, "loss": 0.0031, "step": 243610 }, { "epoch": 58.49, "learning_rate": 4.113775533029993e-05, "loss": 0.007, "step": 243620 }, { "epoch": 58.5, "learning_rate": 4.1134222616485355e-05, "loss": 0.0023, "step": 243630 }, { "epoch": 58.5, "learning_rate": 4.1130689948365077e-05, "loss": 0.0026, "step": 243640 }, { "epoch": 58.5, "learning_rate": 4.1127157325957296e-05, "loss": 0.005, "step": 243650 }, { "epoch": 58.5, "learning_rate": 4.1123624749280215e-05, "loss": 0.0025, "step": 243660 }, { "epoch": 58.51, "learning_rate": 4.112009221835205e-05, "loss": 0.0037, "step": 243670 }, { "epoch": 58.51, "learning_rate": 4.111655973319099e-05, "loss": 0.0045, "step": 243680 }, { "epoch": 58.51, "learning_rate": 4.111302729381528e-05, "loss": 0.0042, "step": 243690 }, { "epoch": 58.51, "learning_rate": 4.1109494900243076e-05, "loss": 0.0031, "step": 243700 }, { "epoch": 58.52, "learning_rate": 4.1105962552492634e-05, "loss": 0.0021, "step": 243710 }, { "epoch": 58.52, "learning_rate": 4.110243025058214e-05, "loss": 0.0021, "step": 243720 }, { "epoch": 58.52, "learning_rate": 4.109889799452976e-05, "loss": 0.0048, "step": 243730 }, { "epoch": 58.52, "learning_rate": 4.109536578435377e-05, "loss": 0.0031, "step": 243740 }, { "epoch": 58.52, "learning_rate": 4.109183362007231e-05, "loss": 0.0041, "step": 243750 }, { "epoch": 58.53, "learning_rate": 4.108830150170363e-05, "loss": 0.0032, "step": 243760 }, { "epoch": 58.53, "learning_rate": 4.1084769429265915e-05, "loss": 0.003, "step": 243770 }, { "epoch": 58.53, "learning_rate": 4.108123740277738e-05, "loss": 0.0043, "step": 243780 }, { "epoch": 58.53, "learning_rate": 4.107770542225621e-05, "loss": 0.003, "step": 243790 }, { "epoch": 58.54, "learning_rate": 4.107417348772063e-05, "loss": 0.0033, "step": 243800 }, { "epoch": 58.54, "learning_rate": 4.107064159918883e-05, "loss": 0.003, "step": 243810 }, { "epoch": 58.54, "learning_rate": 4.106710975667902e-05, "loss": 0.018, "step": 243820 }, { "epoch": 58.54, "learning_rate": 4.10635779602094e-05, "loss": 0.004, "step": 243830 }, { "epoch": 58.55, "learning_rate": 4.106004620979816e-05, "loss": 0.0045, "step": 243840 }, { "epoch": 58.55, "learning_rate": 4.105651450546354e-05, "loss": 0.0043, "step": 243850 }, { "epoch": 58.55, "learning_rate": 4.105298284722372e-05, "loss": 0.0036, "step": 243860 }, { "epoch": 58.55, "learning_rate": 4.1049451235096874e-05, "loss": 0.0038, "step": 243870 }, { "epoch": 58.55, "learning_rate": 4.104591966910126e-05, "loss": 0.0052, "step": 243880 }, { "epoch": 58.56, "learning_rate": 4.104238814925503e-05, "loss": 0.0026, "step": 243890 }, { "epoch": 58.56, "learning_rate": 4.103885667557642e-05, "loss": 0.0052, "step": 243900 }, { "epoch": 58.56, "learning_rate": 4.10353252480836e-05, "loss": 0.0037, "step": 243910 }, { "epoch": 58.56, "learning_rate": 4.103179386679481e-05, "loss": 0.0059, "step": 243920 }, { "epoch": 58.57, "learning_rate": 4.1028262531728223e-05, "loss": 0.0053, "step": 243930 }, { "epoch": 58.57, "learning_rate": 4.1024731242902044e-05, "loss": 0.0036, "step": 243940 }, { "epoch": 58.57, "learning_rate": 4.102120000033447e-05, "loss": 0.0068, "step": 243950 }, { "epoch": 58.57, "learning_rate": 4.101766880404371e-05, "loss": 0.0056, "step": 243960 }, { "epoch": 58.57, "learning_rate": 4.101413765404796e-05, "loss": 0.0045, "step": 243970 }, { "epoch": 58.58, "learning_rate": 4.1010606550365424e-05, "loss": 0.0102, "step": 243980 }, { "epoch": 58.58, "learning_rate": 4.100707549301429e-05, "loss": 0.004, "step": 243990 }, { "epoch": 58.58, "learning_rate": 4.100354448201278e-05, "loss": 0.003, "step": 244000 }, { "epoch": 58.58, "learning_rate": 4.100001351737905e-05, "loss": 0.0028, "step": 244010 }, { "epoch": 58.59, "learning_rate": 4.0996482599131344e-05, "loss": 0.0033, "step": 244020 }, { "epoch": 58.59, "learning_rate": 4.099295172728783e-05, "loss": 0.0044, "step": 244030 }, { "epoch": 58.59, "learning_rate": 4.0989420901866735e-05, "loss": 0.0051, "step": 244040 }, { "epoch": 58.59, "learning_rate": 4.098589012288622e-05, "loss": 0.0026, "step": 244050 }, { "epoch": 58.6, "learning_rate": 4.098235939036452e-05, "loss": 0.0029, "step": 244060 }, { "epoch": 58.6, "learning_rate": 4.0978828704319827e-05, "loss": 0.0033, "step": 244070 }, { "epoch": 58.6, "learning_rate": 4.0975298064770294e-05, "loss": 0.0061, "step": 244080 }, { "epoch": 58.6, "learning_rate": 4.0971767471734166e-05, "loss": 0.003, "step": 244090 }, { "epoch": 58.6, "learning_rate": 4.0968236925229616e-05, "loss": 0.0028, "step": 244100 }, { "epoch": 58.61, "learning_rate": 4.0964706425274854e-05, "loss": 0.0047, "step": 244110 }, { "epoch": 58.61, "learning_rate": 4.096117597188807e-05, "loss": 0.0045, "step": 244120 }, { "epoch": 58.61, "learning_rate": 4.095764556508746e-05, "loss": 0.0037, "step": 244130 }, { "epoch": 58.61, "learning_rate": 4.095411520489123e-05, "loss": 0.006, "step": 244140 }, { "epoch": 58.62, "learning_rate": 4.095058489131755e-05, "loss": 0.007, "step": 244150 }, { "epoch": 58.62, "learning_rate": 4.094705462438465e-05, "loss": 0.0028, "step": 244160 }, { "epoch": 58.62, "learning_rate": 4.094352440411068e-05, "loss": 0.0023, "step": 244170 }, { "epoch": 58.62, "learning_rate": 4.093999423051389e-05, "loss": 0.0035, "step": 244180 }, { "epoch": 58.63, "learning_rate": 4.0936464103612416e-05, "loss": 0.0035, "step": 244190 }, { "epoch": 58.63, "learning_rate": 4.093293402342451e-05, "loss": 0.0035, "step": 244200 }, { "epoch": 58.63, "learning_rate": 4.092940398996831e-05, "loss": 0.0048, "step": 244210 }, { "epoch": 58.63, "learning_rate": 4.092587400326207e-05, "loss": 0.0036, "step": 244220 }, { "epoch": 58.63, "learning_rate": 4.092234406332394e-05, "loss": 0.0039, "step": 244230 }, { "epoch": 58.64, "learning_rate": 4.09188141701721e-05, "loss": 0.0069, "step": 244240 }, { "epoch": 58.64, "learning_rate": 4.0915284323824796e-05, "loss": 0.0032, "step": 244250 }, { "epoch": 58.64, "learning_rate": 4.091175452430018e-05, "loss": 0.0041, "step": 244260 }, { "epoch": 58.64, "learning_rate": 4.0908224771616455e-05, "loss": 0.0036, "step": 244270 }, { "epoch": 58.65, "learning_rate": 4.090469506579182e-05, "loss": 0.0049, "step": 244280 }, { "epoch": 58.65, "learning_rate": 4.0901165406844465e-05, "loss": 0.0021, "step": 244290 }, { "epoch": 58.65, "learning_rate": 4.0897635794792585e-05, "loss": 0.0051, "step": 244300 }, { "epoch": 58.65, "learning_rate": 4.089410622965435e-05, "loss": 0.0044, "step": 244310 }, { "epoch": 58.65, "learning_rate": 4.089057671144798e-05, "loss": 0.0025, "step": 244320 }, { "epoch": 58.66, "learning_rate": 4.088704724019165e-05, "loss": 0.0052, "step": 244330 }, { "epoch": 58.66, "learning_rate": 4.088351781590356e-05, "loss": 0.0048, "step": 244340 }, { "epoch": 58.66, "learning_rate": 4.087998843860188e-05, "loss": 0.0037, "step": 244350 }, { "epoch": 58.66, "learning_rate": 4.087645910830483e-05, "loss": 0.0026, "step": 244360 }, { "epoch": 58.67, "learning_rate": 4.0872929825030595e-05, "loss": 0.0058, "step": 244370 }, { "epoch": 58.67, "learning_rate": 4.086940058879733e-05, "loss": 0.0035, "step": 244380 }, { "epoch": 58.67, "learning_rate": 4.086587139962327e-05, "loss": 0.009, "step": 244390 }, { "epoch": 58.67, "learning_rate": 4.086234225752657e-05, "loss": 0.0031, "step": 244400 }, { "epoch": 58.68, "learning_rate": 4.085881316252545e-05, "loss": 0.0036, "step": 244410 }, { "epoch": 58.68, "learning_rate": 4.085528411463807e-05, "loss": 0.0033, "step": 244420 }, { "epoch": 58.68, "learning_rate": 4.085175511388264e-05, "loss": 0.0028, "step": 244430 }, { "epoch": 58.68, "learning_rate": 4.084822616027735e-05, "loss": 0.0049, "step": 244440 }, { "epoch": 58.68, "learning_rate": 4.0844697253840355e-05, "loss": 0.0024, "step": 244450 }, { "epoch": 58.69, "learning_rate": 4.084116839458989e-05, "loss": 0.0036, "step": 244460 }, { "epoch": 58.69, "learning_rate": 4.0837639582544094e-05, "loss": 0.004, "step": 244470 }, { "epoch": 58.69, "learning_rate": 4.083411081772121e-05, "loss": 0.0037, "step": 244480 }, { "epoch": 58.69, "learning_rate": 4.083058210013937e-05, "loss": 0.0033, "step": 244490 }, { "epoch": 58.7, "learning_rate": 4.0827053429816805e-05, "loss": 0.0066, "step": 244500 }, { "epoch": 58.7, "learning_rate": 4.082352480677169e-05, "loss": 0.0041, "step": 244510 }, { "epoch": 58.7, "learning_rate": 4.081999623102218e-05, "loss": 0.008, "step": 244520 }, { "epoch": 58.7, "learning_rate": 4.08164677025865e-05, "loss": 0.0023, "step": 244530 }, { "epoch": 58.71, "learning_rate": 4.0812939221482816e-05, "loss": 0.0039, "step": 244540 }, { "epoch": 58.71, "learning_rate": 4.080941078772933e-05, "loss": 0.0046, "step": 244550 }, { "epoch": 58.71, "learning_rate": 4.08058824013442e-05, "loss": 0.0028, "step": 244560 }, { "epoch": 58.71, "learning_rate": 4.080235406234564e-05, "loss": 0.0048, "step": 244570 }, { "epoch": 58.71, "learning_rate": 4.079882577075183e-05, "loss": 0.0026, "step": 244580 }, { "epoch": 58.72, "learning_rate": 4.079529752658093e-05, "loss": 0.0035, "step": 244590 }, { "epoch": 58.72, "learning_rate": 4.079176932985117e-05, "loss": 0.0026, "step": 244600 }, { "epoch": 58.72, "learning_rate": 4.0788241180580684e-05, "loss": 0.0027, "step": 244610 }, { "epoch": 58.72, "learning_rate": 4.07847130787877e-05, "loss": 0.003, "step": 244620 }, { "epoch": 58.73, "learning_rate": 4.078118502449036e-05, "loss": 0.0097, "step": 244630 }, { "epoch": 58.73, "learning_rate": 4.0777657017706895e-05, "loss": 0.0035, "step": 244640 }, { "epoch": 58.73, "learning_rate": 4.077412905845546e-05, "loss": 0.0053, "step": 244650 }, { "epoch": 58.73, "learning_rate": 4.077060114675422e-05, "loss": 0.0024, "step": 244660 }, { "epoch": 58.73, "learning_rate": 4.076707328262139e-05, "loss": 0.0475, "step": 244670 }, { "epoch": 58.74, "learning_rate": 4.076354546607513e-05, "loss": 0.003, "step": 244680 }, { "epoch": 58.74, "learning_rate": 4.076001769713366e-05, "loss": 0.0028, "step": 244690 }, { "epoch": 58.74, "learning_rate": 4.07564899758151e-05, "loss": 0.006, "step": 244700 }, { "epoch": 58.74, "learning_rate": 4.0752962302137706e-05, "loss": 0.0023, "step": 244710 }, { "epoch": 58.75, "learning_rate": 4.07494346761196e-05, "loss": 0.004, "step": 244720 }, { "epoch": 58.75, "learning_rate": 4.074590709777898e-05, "loss": 0.0024, "step": 244730 }, { "epoch": 58.75, "learning_rate": 4.074237956713405e-05, "loss": 0.0043, "step": 244740 }, { "epoch": 58.75, "learning_rate": 4.073885208420295e-05, "loss": 0.0028, "step": 244750 }, { "epoch": 58.76, "learning_rate": 4.073532464900391e-05, "loss": 0.0035, "step": 244760 }, { "epoch": 58.76, "learning_rate": 4.073179726155506e-05, "loss": 0.006, "step": 244770 }, { "epoch": 58.76, "learning_rate": 4.0728269921874627e-05, "loss": 0.0087, "step": 244780 }, { "epoch": 58.76, "learning_rate": 4.072474262998077e-05, "loss": 0.0064, "step": 244790 }, { "epoch": 58.76, "learning_rate": 4.072121538589164e-05, "loss": 0.0041, "step": 244800 }, { "epoch": 58.77, "learning_rate": 4.071768818962547e-05, "loss": 0.0037, "step": 244810 }, { "epoch": 58.77, "learning_rate": 4.071416104120039e-05, "loss": 0.0047, "step": 244820 }, { "epoch": 58.77, "learning_rate": 4.071063394063462e-05, "loss": 0.0049, "step": 244830 }, { "epoch": 58.77, "learning_rate": 4.0707106887946304e-05, "loss": 0.0024, "step": 244840 }, { "epoch": 58.78, "learning_rate": 4.0703579883153655e-05, "loss": 0.0033, "step": 244850 }, { "epoch": 58.78, "learning_rate": 4.0700052926274826e-05, "loss": 0.0038, "step": 244860 }, { "epoch": 58.78, "learning_rate": 4.0696526017327994e-05, "loss": 0.004, "step": 244870 }, { "epoch": 58.78, "learning_rate": 4.069299915633135e-05, "loss": 0.0035, "step": 244880 }, { "epoch": 58.79, "learning_rate": 4.068947234330306e-05, "loss": 0.0026, "step": 244890 }, { "epoch": 58.79, "learning_rate": 4.068594557826132e-05, "loss": 0.0036, "step": 244900 }, { "epoch": 58.79, "learning_rate": 4.068241886122428e-05, "loss": 0.0053, "step": 244910 }, { "epoch": 58.79, "learning_rate": 4.067889219221015e-05, "loss": 0.0138, "step": 244920 }, { "epoch": 58.79, "learning_rate": 4.0675365571237086e-05, "loss": 0.0033, "step": 244930 }, { "epoch": 58.8, "learning_rate": 4.067183899832324e-05, "loss": 0.0023, "step": 244940 }, { "epoch": 58.8, "learning_rate": 4.066831247348684e-05, "loss": 0.0035, "step": 244950 }, { "epoch": 58.8, "learning_rate": 4.066478599674602e-05, "loss": 0.0035, "step": 244960 }, { "epoch": 58.8, "learning_rate": 4.066125956811898e-05, "loss": 0.0027, "step": 244970 }, { "epoch": 58.81, "learning_rate": 4.0657733187623875e-05, "loss": 0.0033, "step": 244980 }, { "epoch": 58.81, "learning_rate": 4.065420685527891e-05, "loss": 0.003, "step": 244990 }, { "epoch": 58.81, "learning_rate": 4.065068057110222e-05, "loss": 0.0026, "step": 245000 }, { "epoch": 58.81, "learning_rate": 4.064715433511202e-05, "loss": 0.0029, "step": 245010 }, { "epoch": 58.81, "learning_rate": 4.0643628147326455e-05, "loss": 0.0029, "step": 245020 }, { "epoch": 58.82, "learning_rate": 4.06401020077637e-05, "loss": 0.0034, "step": 245030 }, { "epoch": 58.82, "learning_rate": 4.063657591644195e-05, "loss": 0.0058, "step": 245040 }, { "epoch": 58.82, "learning_rate": 4.063304987337936e-05, "loss": 0.0172, "step": 245050 }, { "epoch": 58.82, "learning_rate": 4.062952387859412e-05, "loss": 0.0024, "step": 245060 }, { "epoch": 58.83, "learning_rate": 4.062599793210437e-05, "loss": 0.0039, "step": 245070 }, { "epoch": 58.83, "learning_rate": 4.062247203392833e-05, "loss": 0.0055, "step": 245080 }, { "epoch": 58.83, "learning_rate": 4.061894618408415e-05, "loss": 0.0035, "step": 245090 }, { "epoch": 58.83, "learning_rate": 4.0615420382589975e-05, "loss": 0.0032, "step": 245100 }, { "epoch": 58.84, "learning_rate": 4.061189462946402e-05, "loss": 0.0047, "step": 245110 }, { "epoch": 58.84, "learning_rate": 4.0608368924724423e-05, "loss": 0.0025, "step": 245120 }, { "epoch": 58.84, "learning_rate": 4.060484326838939e-05, "loss": 0.003, "step": 245130 }, { "epoch": 58.84, "learning_rate": 4.060131766047705e-05, "loss": 0.0029, "step": 245140 }, { "epoch": 58.84, "learning_rate": 4.059779210100562e-05, "loss": 0.0023, "step": 245150 }, { "epoch": 58.85, "learning_rate": 4.059426658999324e-05, "loss": 0.003, "step": 245160 }, { "epoch": 58.85, "learning_rate": 4.0590741127458085e-05, "loss": 0.004, "step": 245170 }, { "epoch": 58.85, "learning_rate": 4.058721571341833e-05, "loss": 0.0058, "step": 245180 }, { "epoch": 58.85, "learning_rate": 4.0583690347892134e-05, "loss": 0.0028, "step": 245190 }, { "epoch": 58.86, "learning_rate": 4.05801650308977e-05, "loss": 0.0032, "step": 245200 }, { "epoch": 58.86, "learning_rate": 4.057663976245315e-05, "loss": 0.0042, "step": 245210 }, { "epoch": 58.86, "learning_rate": 4.0573114542576696e-05, "loss": 0.0029, "step": 245220 }, { "epoch": 58.86, "learning_rate": 4.056958937128649e-05, "loss": 0.0022, "step": 245230 }, { "epoch": 58.87, "learning_rate": 4.056606424860068e-05, "loss": 0.0026, "step": 245240 }, { "epoch": 58.87, "learning_rate": 4.056253917453748e-05, "loss": 0.0027, "step": 245250 }, { "epoch": 58.87, "learning_rate": 4.0559014149115e-05, "loss": 0.003, "step": 245260 }, { "epoch": 58.87, "learning_rate": 4.055548917235147e-05, "loss": 0.0034, "step": 245270 }, { "epoch": 58.87, "learning_rate": 4.0551964244265005e-05, "loss": 0.0024, "step": 245280 }, { "epoch": 58.88, "learning_rate": 4.0548439364873814e-05, "loss": 0.0033, "step": 245290 }, { "epoch": 58.88, "learning_rate": 4.054491453419603e-05, "loss": 0.003, "step": 245300 }, { "epoch": 58.88, "learning_rate": 4.0541389752249846e-05, "loss": 0.0035, "step": 245310 }, { "epoch": 58.88, "learning_rate": 4.053786501905341e-05, "loss": 0.0031, "step": 245320 }, { "epoch": 58.89, "learning_rate": 4.0534340334624904e-05, "loss": 0.0034, "step": 245330 }, { "epoch": 58.89, "learning_rate": 4.053081569898248e-05, "loss": 0.0026, "step": 245340 }, { "epoch": 58.89, "learning_rate": 4.0527291112144305e-05, "loss": 0.003, "step": 245350 }, { "epoch": 58.89, "learning_rate": 4.0523766574128574e-05, "loss": 0.0024, "step": 245360 }, { "epoch": 58.89, "learning_rate": 4.052024208495343e-05, "loss": 0.0064, "step": 245370 }, { "epoch": 58.9, "learning_rate": 4.0516717644637004e-05, "loss": 0.003, "step": 245380 }, { "epoch": 58.9, "learning_rate": 4.0513193253197526e-05, "loss": 0.0025, "step": 245390 }, { "epoch": 58.9, "learning_rate": 4.0509668910653106e-05, "loss": 0.0029, "step": 245400 }, { "epoch": 58.9, "learning_rate": 4.050614461702195e-05, "loss": 0.0029, "step": 245410 }, { "epoch": 58.91, "learning_rate": 4.0502620372322184e-05, "loss": 0.0028, "step": 245420 }, { "epoch": 58.91, "learning_rate": 4.049909617657202e-05, "loss": 0.0044, "step": 245430 }, { "epoch": 58.91, "learning_rate": 4.049557202978959e-05, "loss": 0.0025, "step": 245440 }, { "epoch": 58.91, "learning_rate": 4.0492047931993035e-05, "loss": 0.0026, "step": 245450 }, { "epoch": 58.92, "learning_rate": 4.048852388320056e-05, "loss": 0.0038, "step": 245460 }, { "epoch": 58.92, "learning_rate": 4.048499988343031e-05, "loss": 0.0027, "step": 245470 }, { "epoch": 58.92, "learning_rate": 4.048147593270045e-05, "loss": 0.0025, "step": 245480 }, { "epoch": 58.92, "learning_rate": 4.047795203102915e-05, "loss": 0.0046, "step": 245490 }, { "epoch": 58.92, "learning_rate": 4.0474428178434554e-05, "loss": 0.003, "step": 245500 }, { "epoch": 58.93, "learning_rate": 4.0470904374934855e-05, "loss": 0.0083, "step": 245510 }, { "epoch": 58.93, "learning_rate": 4.0467380620548165e-05, "loss": 0.0026, "step": 245520 }, { "epoch": 58.93, "learning_rate": 4.04638569152927e-05, "loss": 0.0045, "step": 245530 }, { "epoch": 58.93, "learning_rate": 4.046033325918658e-05, "loss": 0.0029, "step": 245540 }, { "epoch": 58.94, "learning_rate": 4.0456809652248e-05, "loss": 0.0028, "step": 245550 }, { "epoch": 58.94, "learning_rate": 4.045328609449507e-05, "loss": 0.0046, "step": 245560 }, { "epoch": 58.94, "learning_rate": 4.0449762585946015e-05, "loss": 0.0084, "step": 245570 }, { "epoch": 58.94, "learning_rate": 4.044623912661896e-05, "loss": 0.0027, "step": 245580 }, { "epoch": 58.95, "learning_rate": 4.044271571653205e-05, "loss": 0.0056, "step": 245590 }, { "epoch": 58.95, "learning_rate": 4.043919235570348e-05, "loss": 0.0067, "step": 245600 }, { "epoch": 58.95, "learning_rate": 4.043566904415138e-05, "loss": 0.0026, "step": 245610 }, { "epoch": 59.0, "learning_rate": 4.043214578189393e-05, "loss": 0.0037, "step": 245620 }, { "epoch": 59.0, "learning_rate": 4.042862256894928e-05, "loss": 0.0038, "step": 245630 }, { "epoch": 59.01, "learning_rate": 4.0425099405335587e-05, "loss": 0.0264, "step": 245640 }, { "epoch": 59.01, "learning_rate": 4.042157629107102e-05, "loss": 0.0028, "step": 245650 }, { "epoch": 59.01, "learning_rate": 4.041805322617371e-05, "loss": 0.0034, "step": 245660 }, { "epoch": 59.01, "learning_rate": 4.041453021066186e-05, "loss": 0.004, "step": 245670 }, { "epoch": 59.01, "learning_rate": 4.041100724455357e-05, "loss": 0.0053, "step": 245680 }, { "epoch": 59.02, "learning_rate": 4.040748432786706e-05, "loss": 0.0036, "step": 245690 }, { "epoch": 59.02, "learning_rate": 4.040396146062043e-05, "loss": 0.0078, "step": 245700 }, { "epoch": 59.02, "learning_rate": 4.040043864283188e-05, "loss": 0.0044, "step": 245710 }, { "epoch": 59.02, "learning_rate": 4.039691587451956e-05, "loss": 0.0025, "step": 245720 }, { "epoch": 59.03, "learning_rate": 4.039339315570159e-05, "loss": 0.0033, "step": 245730 }, { "epoch": 59.03, "learning_rate": 4.038987048639616e-05, "loss": 0.0028, "step": 245740 }, { "epoch": 59.03, "learning_rate": 4.0386347866621416e-05, "loss": 0.0033, "step": 245750 }, { "epoch": 59.03, "learning_rate": 4.0382825296395515e-05, "loss": 0.0055, "step": 245760 }, { "epoch": 59.03, "learning_rate": 4.037930277573662e-05, "loss": 0.0032, "step": 245770 }, { "epoch": 59.04, "learning_rate": 4.0375780304662876e-05, "loss": 0.0042, "step": 245780 }, { "epoch": 59.04, "learning_rate": 4.037225788319244e-05, "loss": 0.003, "step": 245790 }, { "epoch": 59.04, "learning_rate": 4.0368735511343464e-05, "loss": 0.0022, "step": 245800 }, { "epoch": 59.04, "learning_rate": 4.036521318913412e-05, "loss": 0.0023, "step": 245810 }, { "epoch": 59.05, "learning_rate": 4.036169091658253e-05, "loss": 0.0047, "step": 245820 }, { "epoch": 59.05, "learning_rate": 4.035816869370688e-05, "loss": 0.0037, "step": 245830 }, { "epoch": 59.05, "learning_rate": 4.0354646520525294e-05, "loss": 0.0025, "step": 245840 }, { "epoch": 59.05, "learning_rate": 4.035112439705595e-05, "loss": 0.0028, "step": 245850 }, { "epoch": 59.06, "learning_rate": 4.034760232331698e-05, "loss": 0.0037, "step": 245860 }, { "epoch": 59.06, "learning_rate": 4.034408029932657e-05, "loss": 0.0028, "step": 245870 }, { "epoch": 59.06, "learning_rate": 4.034055832510285e-05, "loss": 0.0034, "step": 245880 }, { "epoch": 59.06, "learning_rate": 4.0337036400663954e-05, "loss": 0.0037, "step": 245890 }, { "epoch": 59.06, "learning_rate": 4.033351452602807e-05, "loss": 0.0045, "step": 245900 }, { "epoch": 59.07, "learning_rate": 4.032999270121331e-05, "loss": 0.0039, "step": 245910 }, { "epoch": 59.07, "learning_rate": 4.0326470926237865e-05, "loss": 0.0042, "step": 245920 }, { "epoch": 59.07, "learning_rate": 4.032294920111986e-05, "loss": 0.0047, "step": 245930 }, { "epoch": 59.07, "learning_rate": 4.031942752587747e-05, "loss": 0.0027, "step": 245940 }, { "epoch": 59.08, "learning_rate": 4.0315905900528836e-05, "loss": 0.0028, "step": 245950 }, { "epoch": 59.08, "learning_rate": 4.031238432509208e-05, "loss": 0.0046, "step": 245960 }, { "epoch": 59.08, "learning_rate": 4.030886279958539e-05, "loss": 0.004, "step": 245970 }, { "epoch": 59.08, "learning_rate": 4.03053413240269e-05, "loss": 0.0023, "step": 245980 }, { "epoch": 59.09, "learning_rate": 4.030181989843477e-05, "loss": 0.0027, "step": 245990 }, { "epoch": 59.09, "learning_rate": 4.0298298522827124e-05, "loss": 0.0039, "step": 246000 }, { "epoch": 59.09, "learning_rate": 4.0294777197222145e-05, "loss": 0.0081, "step": 246010 }, { "epoch": 59.09, "learning_rate": 4.029125592163797e-05, "loss": 0.0023, "step": 246020 }, { "epoch": 59.09, "learning_rate": 4.028773469609272e-05, "loss": 0.0062, "step": 246030 }, { "epoch": 59.1, "learning_rate": 4.028421352060459e-05, "loss": 0.0044, "step": 246040 }, { "epoch": 59.1, "learning_rate": 4.0280692395191685e-05, "loss": 0.0025, "step": 246050 }, { "epoch": 59.1, "learning_rate": 4.027717131987219e-05, "loss": 0.0031, "step": 246060 }, { "epoch": 59.1, "learning_rate": 4.027365029466421e-05, "loss": 0.0161, "step": 246070 }, { "epoch": 59.11, "learning_rate": 4.0270129319585936e-05, "loss": 0.0168, "step": 246080 }, { "epoch": 59.11, "learning_rate": 4.02666083946555e-05, "loss": 0.0027, "step": 246090 }, { "epoch": 59.11, "learning_rate": 4.026308751989104e-05, "loss": 0.0031, "step": 246100 }, { "epoch": 59.11, "learning_rate": 4.0259566695310715e-05, "loss": 0.0028, "step": 246110 }, { "epoch": 59.11, "learning_rate": 4.025604592093265e-05, "loss": 0.0023, "step": 246120 }, { "epoch": 59.12, "learning_rate": 4.025252519677502e-05, "loss": 0.0023, "step": 246130 }, { "epoch": 59.12, "learning_rate": 4.024900452285594e-05, "loss": 0.0021, "step": 246140 }, { "epoch": 59.12, "learning_rate": 4.0245483899193595e-05, "loss": 0.0022, "step": 246150 }, { "epoch": 59.12, "learning_rate": 4.0241963325806104e-05, "loss": 0.0022, "step": 246160 }, { "epoch": 59.13, "learning_rate": 4.0238442802711595e-05, "loss": 0.0021, "step": 246170 }, { "epoch": 59.13, "learning_rate": 4.0234922329928254e-05, "loss": 0.0109, "step": 246180 }, { "epoch": 59.13, "learning_rate": 4.023140190747419e-05, "loss": 0.0024, "step": 246190 }, { "epoch": 59.13, "learning_rate": 4.022788153536757e-05, "loss": 0.003, "step": 246200 }, { "epoch": 59.14, "learning_rate": 4.022436121362652e-05, "loss": 0.0029, "step": 246210 }, { "epoch": 59.14, "learning_rate": 4.0220840942269214e-05, "loss": 0.0035, "step": 246220 }, { "epoch": 59.14, "learning_rate": 4.021732072131377e-05, "loss": 0.0036, "step": 246230 }, { "epoch": 59.14, "learning_rate": 4.021380055077831e-05, "loss": 0.0035, "step": 246240 }, { "epoch": 59.14, "learning_rate": 4.021028043068104e-05, "loss": 0.0028, "step": 246250 }, { "epoch": 59.15, "learning_rate": 4.020676036104004e-05, "loss": 0.0049, "step": 246260 }, { "epoch": 59.15, "learning_rate": 4.02032403418735e-05, "loss": 0.0036, "step": 246270 }, { "epoch": 59.15, "learning_rate": 4.019972037319952e-05, "loss": 0.0027, "step": 246280 }, { "epoch": 59.15, "learning_rate": 4.0196200455036284e-05, "loss": 0.0022, "step": 246290 }, { "epoch": 59.16, "learning_rate": 4.019268058740192e-05, "loss": 0.0047, "step": 246300 }, { "epoch": 59.16, "learning_rate": 4.018916077031453e-05, "loss": 0.0032, "step": 246310 }, { "epoch": 59.16, "learning_rate": 4.018564100379231e-05, "loss": 0.0072, "step": 246320 }, { "epoch": 59.16, "learning_rate": 4.0182121287853366e-05, "loss": 0.0039, "step": 246330 }, { "epoch": 59.17, "learning_rate": 4.0178601622515865e-05, "loss": 0.0029, "step": 246340 }, { "epoch": 59.17, "learning_rate": 4.017508200779791e-05, "loss": 0.0027, "step": 246350 }, { "epoch": 59.17, "learning_rate": 4.017156244371769e-05, "loss": 0.0028, "step": 246360 }, { "epoch": 59.17, "learning_rate": 4.016804293029331e-05, "loss": 0.0024, "step": 246370 }, { "epoch": 59.17, "learning_rate": 4.0164523467542916e-05, "loss": 0.0041, "step": 246380 }, { "epoch": 59.18, "learning_rate": 4.016100405548465e-05, "loss": 0.0034, "step": 246390 }, { "epoch": 59.18, "learning_rate": 4.015748469413664e-05, "loss": 0.0037, "step": 246400 }, { "epoch": 59.18, "learning_rate": 4.0153965383517064e-05, "loss": 0.0023, "step": 246410 }, { "epoch": 59.18, "learning_rate": 4.0150446123644e-05, "loss": 0.0025, "step": 246420 }, { "epoch": 59.19, "learning_rate": 4.014692691453566e-05, "loss": 0.0023, "step": 246430 }, { "epoch": 59.19, "learning_rate": 4.014340775621012e-05, "loss": 0.0023, "step": 246440 }, { "epoch": 59.19, "learning_rate": 4.0139888648685524e-05, "loss": 0.0049, "step": 246450 }, { "epoch": 59.19, "learning_rate": 4.013636959198005e-05, "loss": 0.0028, "step": 246460 }, { "epoch": 59.19, "learning_rate": 4.0132850586111786e-05, "loss": 0.0031, "step": 246470 }, { "epoch": 59.2, "learning_rate": 4.012933163109891e-05, "loss": 0.0024, "step": 246480 }, { "epoch": 59.2, "learning_rate": 4.012581272695952e-05, "loss": 0.0019, "step": 246490 }, { "epoch": 59.2, "learning_rate": 4.01222938737118e-05, "loss": 0.0045, "step": 246500 }, { "epoch": 59.2, "learning_rate": 4.011877507137385e-05, "loss": 0.0022, "step": 246510 }, { "epoch": 59.21, "learning_rate": 4.0115256319963814e-05, "loss": 0.0022, "step": 246520 }, { "epoch": 59.21, "learning_rate": 4.011173761949983e-05, "loss": 0.0018, "step": 246530 }, { "epoch": 59.21, "learning_rate": 4.010821897000003e-05, "loss": 0.0028, "step": 246540 }, { "epoch": 59.21, "learning_rate": 4.010470037148256e-05, "loss": 0.0049, "step": 246550 }, { "epoch": 59.22, "learning_rate": 4.0101181823965526e-05, "loss": 0.0025, "step": 246560 }, { "epoch": 59.22, "learning_rate": 4.009766332746711e-05, "loss": 0.0029, "step": 246570 }, { "epoch": 59.22, "learning_rate": 4.00941448820054e-05, "loss": 0.0037, "step": 246580 }, { "epoch": 59.22, "learning_rate": 4.0090626487598565e-05, "loss": 0.0032, "step": 246590 }, { "epoch": 59.22, "learning_rate": 4.008710814426473e-05, "loss": 0.0028, "step": 246600 }, { "epoch": 59.23, "learning_rate": 4.0083589852022e-05, "loss": 0.0033, "step": 246610 }, { "epoch": 59.23, "learning_rate": 4.0080071610888554e-05, "loss": 0.0025, "step": 246620 }, { "epoch": 59.23, "learning_rate": 4.007655342088247e-05, "loss": 0.003, "step": 246630 }, { "epoch": 59.23, "learning_rate": 4.007303528202195e-05, "loss": 0.0021, "step": 246640 }, { "epoch": 59.24, "learning_rate": 4.006951719432506e-05, "loss": 0.0041, "step": 246650 }, { "epoch": 59.24, "learning_rate": 4.006599915780998e-05, "loss": 0.0022, "step": 246660 }, { "epoch": 59.24, "learning_rate": 4.006248117249482e-05, "loss": 0.003, "step": 246670 }, { "epoch": 59.24, "learning_rate": 4.0058963238397703e-05, "loss": 0.0035, "step": 246680 }, { "epoch": 59.25, "learning_rate": 4.005544535553678e-05, "loss": 0.0026, "step": 246690 }, { "epoch": 59.25, "learning_rate": 4.005192752393018e-05, "loss": 0.0046, "step": 246700 }, { "epoch": 59.25, "learning_rate": 4.004840974359602e-05, "loss": 0.0029, "step": 246710 }, { "epoch": 59.25, "learning_rate": 4.004489201455243e-05, "loss": 0.002, "step": 246720 }, { "epoch": 59.25, "learning_rate": 4.004137433681758e-05, "loss": 0.0031, "step": 246730 }, { "epoch": 59.26, "learning_rate": 4.003785671040956e-05, "loss": 0.0028, "step": 246740 }, { "epoch": 59.26, "learning_rate": 4.003433913534649e-05, "loss": 0.0037, "step": 246750 }, { "epoch": 59.26, "learning_rate": 4.0030821611646544e-05, "loss": 0.0027, "step": 246760 }, { "epoch": 59.26, "learning_rate": 4.0027304139327805e-05, "loss": 0.0028, "step": 246770 }, { "epoch": 59.27, "learning_rate": 4.002378671840844e-05, "loss": 0.0033, "step": 246780 }, { "epoch": 59.27, "learning_rate": 4.002026934890655e-05, "loss": 0.0021, "step": 246790 }, { "epoch": 59.27, "learning_rate": 4.001675203084029e-05, "loss": 0.0019, "step": 246800 }, { "epoch": 59.27, "learning_rate": 4.0013234764227756e-05, "loss": 0.0025, "step": 246810 }, { "epoch": 59.27, "learning_rate": 4.0009717549087106e-05, "loss": 0.0024, "step": 246820 }, { "epoch": 59.28, "learning_rate": 4.000620038543645e-05, "loss": 0.0102, "step": 246830 }, { "epoch": 59.28, "learning_rate": 4.0002683273293916e-05, "loss": 0.0029, "step": 246840 }, { "epoch": 59.28, "learning_rate": 3.999916621267765e-05, "loss": 0.0022, "step": 246850 }, { "epoch": 59.28, "learning_rate": 3.999564920360574e-05, "loss": 0.0026, "step": 246860 }, { "epoch": 59.29, "learning_rate": 3.999213224609636e-05, "loss": 0.0027, "step": 246870 }, { "epoch": 59.29, "learning_rate": 3.9988615340167625e-05, "loss": 0.0042, "step": 246880 }, { "epoch": 59.29, "learning_rate": 3.998509848583762e-05, "loss": 0.0023, "step": 246890 }, { "epoch": 59.29, "learning_rate": 3.998158168312453e-05, "loss": 0.0053, "step": 246900 }, { "epoch": 59.3, "learning_rate": 3.997806493204642e-05, "loss": 0.0027, "step": 246910 }, { "epoch": 59.3, "learning_rate": 3.997454823262147e-05, "loss": 0.0052, "step": 246920 }, { "epoch": 59.3, "learning_rate": 3.997103158486777e-05, "loss": 0.0065, "step": 246930 }, { "epoch": 59.3, "learning_rate": 3.9967514988803465e-05, "loss": 0.0027, "step": 246940 }, { "epoch": 59.3, "learning_rate": 3.9963998444446685e-05, "loss": 0.0022, "step": 246950 }, { "epoch": 59.31, "learning_rate": 3.9960481951815516e-05, "loss": 0.0018, "step": 246960 }, { "epoch": 59.31, "learning_rate": 3.9956965510928114e-05, "loss": 0.0027, "step": 246970 }, { "epoch": 59.31, "learning_rate": 3.99534491218026e-05, "loss": 0.0035, "step": 246980 }, { "epoch": 59.31, "learning_rate": 3.994993278445709e-05, "loss": 0.0035, "step": 246990 }, { "epoch": 59.32, "learning_rate": 3.994641649890971e-05, "loss": 0.002, "step": 247000 }, { "epoch": 59.32, "learning_rate": 3.9942900265178586e-05, "loss": 0.0102, "step": 247010 }, { "epoch": 59.32, "learning_rate": 3.993938408328185e-05, "loss": 0.0028, "step": 247020 }, { "epoch": 59.32, "learning_rate": 3.9935867953237585e-05, "loss": 0.0045, "step": 247030 }, { "epoch": 59.33, "learning_rate": 3.993235187506396e-05, "loss": 0.0024, "step": 247040 }, { "epoch": 59.33, "learning_rate": 3.992883584877906e-05, "loss": 0.0023, "step": 247050 }, { "epoch": 59.33, "learning_rate": 3.992531987440105e-05, "loss": 0.0024, "step": 247060 }, { "epoch": 59.33, "learning_rate": 3.9921803951948e-05, "loss": 0.003, "step": 247070 }, { "epoch": 59.33, "learning_rate": 3.9918288081438085e-05, "loss": 0.0031, "step": 247080 }, { "epoch": 59.34, "learning_rate": 3.991477226288939e-05, "loss": 0.0041, "step": 247090 }, { "epoch": 59.34, "learning_rate": 3.991125649632002e-05, "loss": 0.0027, "step": 247100 }, { "epoch": 59.34, "learning_rate": 3.990774078174814e-05, "loss": 0.0023, "step": 247110 }, { "epoch": 59.34, "learning_rate": 3.990422511919183e-05, "loss": 0.0032, "step": 247120 }, { "epoch": 59.35, "learning_rate": 3.9900709508669245e-05, "loss": 0.0021, "step": 247130 }, { "epoch": 59.35, "learning_rate": 3.989719395019848e-05, "loss": 0.0032, "step": 247140 }, { "epoch": 59.35, "learning_rate": 3.989367844379767e-05, "loss": 0.0041, "step": 247150 }, { "epoch": 59.35, "learning_rate": 3.9890162989484925e-05, "loss": 0.0019, "step": 247160 }, { "epoch": 59.35, "learning_rate": 3.988664758727835e-05, "loss": 0.0022, "step": 247170 }, { "epoch": 59.36, "learning_rate": 3.98831322371961e-05, "loss": 0.0026, "step": 247180 }, { "epoch": 59.36, "learning_rate": 3.987961693925624e-05, "loss": 0.0028, "step": 247190 }, { "epoch": 59.36, "learning_rate": 3.9876101693476945e-05, "loss": 0.0025, "step": 247200 }, { "epoch": 59.36, "learning_rate": 3.9872586499876294e-05, "loss": 0.0026, "step": 247210 }, { "epoch": 59.37, "learning_rate": 3.986907135847243e-05, "loss": 0.0023, "step": 247220 }, { "epoch": 59.37, "learning_rate": 3.9865556269283456e-05, "loss": 0.0057, "step": 247230 }, { "epoch": 59.37, "learning_rate": 3.9862041232327474e-05, "loss": 0.0024, "step": 247240 }, { "epoch": 59.37, "learning_rate": 3.985852624762263e-05, "loss": 0.0021, "step": 247250 }, { "epoch": 59.38, "learning_rate": 3.9855011315187005e-05, "loss": 0.003, "step": 247260 }, { "epoch": 59.38, "learning_rate": 3.985149643503877e-05, "loss": 0.006, "step": 247270 }, { "epoch": 59.38, "learning_rate": 3.984798160719598e-05, "loss": 0.0022, "step": 247280 }, { "epoch": 59.38, "learning_rate": 3.9844466831676783e-05, "loss": 0.0022, "step": 247290 }, { "epoch": 59.38, "learning_rate": 3.9840952108499305e-05, "loss": 0.0023, "step": 247300 }, { "epoch": 59.39, "learning_rate": 3.9837437437681616e-05, "loss": 0.0043, "step": 247310 }, { "epoch": 59.39, "learning_rate": 3.983392281924189e-05, "loss": 0.0027, "step": 247320 }, { "epoch": 59.39, "learning_rate": 3.9830408253198185e-05, "loss": 0.0023, "step": 247330 }, { "epoch": 59.39, "learning_rate": 3.982689373956866e-05, "loss": 0.0134, "step": 247340 }, { "epoch": 59.4, "learning_rate": 3.982337927837139e-05, "loss": 0.0034, "step": 247350 }, { "epoch": 59.4, "learning_rate": 3.981986486962453e-05, "loss": 0.0022, "step": 247360 }, { "epoch": 59.4, "learning_rate": 3.981635051334616e-05, "loss": 0.0117, "step": 247370 }, { "epoch": 59.4, "learning_rate": 3.981283620955441e-05, "loss": 0.0044, "step": 247380 }, { "epoch": 59.41, "learning_rate": 3.98093219582674e-05, "loss": 0.0025, "step": 247390 }, { "epoch": 59.41, "learning_rate": 3.98058077595032e-05, "loss": 0.0043, "step": 247400 }, { "epoch": 59.41, "learning_rate": 3.980229361327997e-05, "loss": 0.0027, "step": 247410 }, { "epoch": 59.41, "learning_rate": 3.979877951961579e-05, "loss": 0.0032, "step": 247420 }, { "epoch": 59.41, "learning_rate": 3.9795265478528796e-05, "loss": 0.0031, "step": 247430 }, { "epoch": 59.42, "learning_rate": 3.979175149003709e-05, "loss": 0.0031, "step": 247440 }, { "epoch": 59.42, "learning_rate": 3.978823755415878e-05, "loss": 0.0066, "step": 247450 }, { "epoch": 59.42, "learning_rate": 3.978472367091199e-05, "loss": 0.0021, "step": 247460 }, { "epoch": 59.42, "learning_rate": 3.97812098403148e-05, "loss": 0.0021, "step": 247470 }, { "epoch": 59.43, "learning_rate": 3.977769606238536e-05, "loss": 0.0026, "step": 247480 }, { "epoch": 59.43, "learning_rate": 3.977418233714173e-05, "loss": 0.0039, "step": 247490 }, { "epoch": 59.43, "learning_rate": 3.977066866460208e-05, "loss": 0.0025, "step": 247500 }, { "epoch": 59.43, "learning_rate": 3.976715504478447e-05, "loss": 0.0025, "step": 247510 }, { "epoch": 59.43, "learning_rate": 3.9763641477707045e-05, "loss": 0.003, "step": 247520 }, { "epoch": 59.44, "learning_rate": 3.97601279633879e-05, "loss": 0.0035, "step": 247530 }, { "epoch": 59.44, "learning_rate": 3.975661450184512e-05, "loss": 0.0024, "step": 247540 }, { "epoch": 59.44, "learning_rate": 3.9753101093096856e-05, "loss": 0.002, "step": 247550 }, { "epoch": 59.44, "learning_rate": 3.974958773716117e-05, "loss": 0.003, "step": 247560 }, { "epoch": 59.45, "learning_rate": 3.974607443405622e-05, "loss": 0.0041, "step": 247570 }, { "epoch": 59.45, "learning_rate": 3.9742561183800066e-05, "loss": 0.0048, "step": 247580 }, { "epoch": 59.45, "learning_rate": 3.9739047986410845e-05, "loss": 0.0042, "step": 247590 }, { "epoch": 59.45, "learning_rate": 3.973553484190666e-05, "loss": 0.0025, "step": 247600 }, { "epoch": 59.46, "learning_rate": 3.97320217503056e-05, "loss": 0.003, "step": 247610 }, { "epoch": 59.46, "learning_rate": 3.972850871162582e-05, "loss": 0.0044, "step": 247620 }, { "epoch": 59.46, "learning_rate": 3.972499572588536e-05, "loss": 0.003, "step": 247630 }, { "epoch": 59.46, "learning_rate": 3.972148279310237e-05, "loss": 0.0034, "step": 247640 }, { "epoch": 59.46, "learning_rate": 3.9717969913294935e-05, "loss": 0.0048, "step": 247650 }, { "epoch": 59.47, "learning_rate": 3.971445708648118e-05, "loss": 0.0022, "step": 247660 }, { "epoch": 59.47, "learning_rate": 3.971094431267921e-05, "loss": 0.002, "step": 247670 }, { "epoch": 59.47, "learning_rate": 3.970743159190709e-05, "loss": 0.0048, "step": 247680 }, { "epoch": 59.47, "learning_rate": 3.970391892418298e-05, "loss": 0.0035, "step": 247690 }, { "epoch": 59.48, "learning_rate": 3.9700406309524934e-05, "loss": 0.0021, "step": 247700 }, { "epoch": 59.48, "learning_rate": 3.96968937479511e-05, "loss": 0.002, "step": 247710 }, { "epoch": 59.48, "learning_rate": 3.969338123947954e-05, "loss": 0.0023, "step": 247720 }, { "epoch": 59.48, "learning_rate": 3.9689868784128405e-05, "loss": 0.0025, "step": 247730 }, { "epoch": 59.49, "learning_rate": 3.968635638191576e-05, "loss": 0.0091, "step": 247740 }, { "epoch": 59.49, "learning_rate": 3.9682844032859714e-05, "loss": 0.0026, "step": 247750 }, { "epoch": 59.49, "learning_rate": 3.9679331736978386e-05, "loss": 0.0228, "step": 247760 }, { "epoch": 59.49, "learning_rate": 3.967581949428985e-05, "loss": 0.0049, "step": 247770 }, { "epoch": 59.49, "learning_rate": 3.9672307304812255e-05, "loss": 0.0021, "step": 247780 }, { "epoch": 59.5, "learning_rate": 3.966879516856366e-05, "loss": 0.002, "step": 247790 }, { "epoch": 59.5, "learning_rate": 3.966528308556218e-05, "loss": 0.0029, "step": 247800 }, { "epoch": 59.5, "learning_rate": 3.966177105582594e-05, "loss": 0.0026, "step": 247810 }, { "epoch": 59.5, "learning_rate": 3.9658259079372985e-05, "loss": 0.0027, "step": 247820 }, { "epoch": 59.51, "learning_rate": 3.9654747156221465e-05, "loss": 0.0033, "step": 247830 }, { "epoch": 59.51, "learning_rate": 3.9651235286389456e-05, "loss": 0.0064, "step": 247840 }, { "epoch": 59.51, "learning_rate": 3.9647723469895084e-05, "loss": 0.0032, "step": 247850 }, { "epoch": 59.51, "learning_rate": 3.964421170675641e-05, "loss": 0.0035, "step": 247860 }, { "epoch": 59.51, "learning_rate": 3.964069999699157e-05, "loss": 0.0031, "step": 247870 }, { "epoch": 59.52, "learning_rate": 3.963718834061865e-05, "loss": 0.0048, "step": 247880 }, { "epoch": 59.52, "learning_rate": 3.963367673765573e-05, "loss": 0.0029, "step": 247890 }, { "epoch": 59.52, "learning_rate": 3.9630165188120945e-05, "loss": 0.0032, "step": 247900 }, { "epoch": 59.52, "learning_rate": 3.962665369203236e-05, "loss": 0.0031, "step": 247910 }, { "epoch": 59.53, "learning_rate": 3.9623142249408104e-05, "loss": 0.0027, "step": 247920 }, { "epoch": 59.53, "learning_rate": 3.961963086026624e-05, "loss": 0.0037, "step": 247930 }, { "epoch": 59.53, "learning_rate": 3.961611952462491e-05, "loss": 0.0041, "step": 247940 }, { "epoch": 59.53, "learning_rate": 3.9612608242502195e-05, "loss": 0.0054, "step": 247950 }, { "epoch": 59.54, "learning_rate": 3.960909701391615e-05, "loss": 0.0046, "step": 247960 }, { "epoch": 59.54, "learning_rate": 3.960558583888493e-05, "loss": 0.0071, "step": 247970 }, { "epoch": 59.54, "learning_rate": 3.9602074717426586e-05, "loss": 0.0067, "step": 247980 }, { "epoch": 59.54, "learning_rate": 3.959856364955925e-05, "loss": 0.0027, "step": 247990 }, { "epoch": 59.54, "learning_rate": 3.9595052635301e-05, "loss": 0.0025, "step": 248000 }, { "epoch": 59.55, "learning_rate": 3.959154167466994e-05, "loss": 0.0031, "step": 248010 }, { "epoch": 59.55, "learning_rate": 3.958803076768416e-05, "loss": 0.0069, "step": 248020 }, { "epoch": 59.55, "learning_rate": 3.958451991436176e-05, "loss": 0.0033, "step": 248030 }, { "epoch": 59.55, "learning_rate": 3.9581009114720825e-05, "loss": 0.0048, "step": 248040 }, { "epoch": 59.56, "learning_rate": 3.9577498368779456e-05, "loss": 0.0046, "step": 248050 }, { "epoch": 59.56, "learning_rate": 3.9573987676555744e-05, "loss": 0.0027, "step": 248060 }, { "epoch": 59.56, "learning_rate": 3.957047703806778e-05, "loss": 0.0055, "step": 248070 }, { "epoch": 59.56, "learning_rate": 3.956696645333369e-05, "loss": 0.0027, "step": 248080 }, { "epoch": 59.57, "learning_rate": 3.956345592237154e-05, "loss": 0.0038, "step": 248090 }, { "epoch": 59.57, "learning_rate": 3.9559945445199396e-05, "loss": 0.0044, "step": 248100 }, { "epoch": 59.57, "learning_rate": 3.9556435021835414e-05, "loss": 0.007, "step": 248110 }, { "epoch": 59.57, "learning_rate": 3.9552924652297624e-05, "loss": 0.0051, "step": 248120 }, { "epoch": 59.57, "learning_rate": 3.9549414336604174e-05, "loss": 0.0069, "step": 248130 }, { "epoch": 59.58, "learning_rate": 3.95459040747731e-05, "loss": 0.0043, "step": 248140 }, { "epoch": 59.58, "learning_rate": 3.9542393866822554e-05, "loss": 0.0036, "step": 248150 }, { "epoch": 59.58, "learning_rate": 3.9538883712770584e-05, "loss": 0.0026, "step": 248160 }, { "epoch": 59.58, "learning_rate": 3.9535373612635296e-05, "loss": 0.0041, "step": 248170 }, { "epoch": 59.59, "learning_rate": 3.9531863566434776e-05, "loss": 0.0048, "step": 248180 }, { "epoch": 59.59, "learning_rate": 3.952835357418712e-05, "loss": 0.004, "step": 248190 }, { "epoch": 59.59, "learning_rate": 3.952484363591042e-05, "loss": 0.0025, "step": 248200 }, { "epoch": 59.59, "learning_rate": 3.952133375162276e-05, "loss": 0.004, "step": 248210 }, { "epoch": 59.59, "learning_rate": 3.951782392134223e-05, "loss": 0.0033, "step": 248220 }, { "epoch": 59.6, "learning_rate": 3.9514314145086925e-05, "loss": 0.0049, "step": 248230 }, { "epoch": 59.6, "learning_rate": 3.951080442287495e-05, "loss": 0.0084, "step": 248240 }, { "epoch": 59.6, "learning_rate": 3.9507294754724365e-05, "loss": 0.0025, "step": 248250 }, { "epoch": 59.6, "learning_rate": 3.950378514065326e-05, "loss": 0.0033, "step": 248260 }, { "epoch": 59.61, "learning_rate": 3.9500275580679754e-05, "loss": 0.0088, "step": 248270 }, { "epoch": 59.61, "learning_rate": 3.949676607482189e-05, "loss": 0.0035, "step": 248280 }, { "epoch": 59.61, "learning_rate": 3.949325662309781e-05, "loss": 0.0034, "step": 248290 }, { "epoch": 59.61, "learning_rate": 3.948974722552554e-05, "loss": 0.0024, "step": 248300 }, { "epoch": 59.62, "learning_rate": 3.9486237882123235e-05, "loss": 0.0027, "step": 248310 }, { "epoch": 59.62, "learning_rate": 3.948272859290893e-05, "loss": 0.0032, "step": 248320 }, { "epoch": 59.62, "learning_rate": 3.947921935790073e-05, "loss": 0.0042, "step": 248330 }, { "epoch": 59.62, "learning_rate": 3.947571017711672e-05, "loss": 0.0067, "step": 248340 }, { "epoch": 59.62, "learning_rate": 3.9472201050574996e-05, "loss": 0.0023, "step": 248350 }, { "epoch": 59.63, "learning_rate": 3.9468691978293624e-05, "loss": 0.0058, "step": 248360 }, { "epoch": 59.63, "learning_rate": 3.946518296029071e-05, "loss": 0.0081, "step": 248370 }, { "epoch": 59.63, "learning_rate": 3.9461673996584334e-05, "loss": 0.0021, "step": 248380 }, { "epoch": 59.63, "learning_rate": 3.945816508719258e-05, "loss": 0.0025, "step": 248390 }, { "epoch": 59.64, "learning_rate": 3.945465623213351e-05, "loss": 0.0036, "step": 248400 }, { "epoch": 59.64, "learning_rate": 3.945114743142526e-05, "loss": 0.0041, "step": 248410 }, { "epoch": 59.64, "learning_rate": 3.944763868508586e-05, "loss": 0.0027, "step": 248420 }, { "epoch": 59.64, "learning_rate": 3.9444129993133435e-05, "loss": 0.0059, "step": 248430 }, { "epoch": 59.65, "learning_rate": 3.944062135558603e-05, "loss": 0.0037, "step": 248440 }, { "epoch": 59.65, "learning_rate": 3.943711277246178e-05, "loss": 0.006, "step": 248450 }, { "epoch": 59.65, "learning_rate": 3.943360424377873e-05, "loss": 0.004, "step": 248460 }, { "epoch": 59.65, "learning_rate": 3.943009576955496e-05, "loss": 0.0036, "step": 248470 }, { "epoch": 59.65, "learning_rate": 3.942658734980857e-05, "loss": 0.0033, "step": 248480 }, { "epoch": 59.66, "learning_rate": 3.9423078984557635e-05, "loss": 0.003, "step": 248490 }, { "epoch": 59.66, "learning_rate": 3.941957067382025e-05, "loss": 0.0022, "step": 248500 }, { "epoch": 59.66, "learning_rate": 3.9416062417614476e-05, "loss": 0.0043, "step": 248510 }, { "epoch": 59.66, "learning_rate": 3.9412554215958406e-05, "loss": 0.0023, "step": 248520 }, { "epoch": 59.67, "learning_rate": 3.940904606887013e-05, "loss": 0.0026, "step": 248530 }, { "epoch": 59.67, "learning_rate": 3.9405537976367704e-05, "loss": 0.0039, "step": 248540 }, { "epoch": 59.67, "learning_rate": 3.9402029938469245e-05, "loss": 0.0054, "step": 248550 }, { "epoch": 59.67, "learning_rate": 3.939852195519278e-05, "loss": 0.0031, "step": 248560 }, { "epoch": 59.67, "learning_rate": 3.939501402655645e-05, "loss": 0.0023, "step": 248570 }, { "epoch": 59.68, "learning_rate": 3.939150615257828e-05, "loss": 0.0086, "step": 248580 }, { "epoch": 59.68, "learning_rate": 3.938799833327641e-05, "loss": 0.0028, "step": 248590 }, { "epoch": 59.68, "learning_rate": 3.938449056866887e-05, "loss": 0.0022, "step": 248600 }, { "epoch": 59.68, "learning_rate": 3.9380982858773744e-05, "loss": 0.0027, "step": 248610 }, { "epoch": 59.69, "learning_rate": 3.937747520360914e-05, "loss": 0.0029, "step": 248620 }, { "epoch": 59.69, "learning_rate": 3.9373967603193096e-05, "loss": 0.0032, "step": 248630 }, { "epoch": 59.69, "learning_rate": 3.937046005754372e-05, "loss": 0.0025, "step": 248640 }, { "epoch": 59.69, "learning_rate": 3.936695256667908e-05, "loss": 0.0037, "step": 248650 }, { "epoch": 59.7, "learning_rate": 3.936344513061726e-05, "loss": 0.0022, "step": 248660 }, { "epoch": 59.7, "learning_rate": 3.935993774937635e-05, "loss": 0.0123, "step": 248670 }, { "epoch": 59.7, "learning_rate": 3.9356430422974376e-05, "loss": 0.0033, "step": 248680 }, { "epoch": 59.7, "learning_rate": 3.935292315142948e-05, "loss": 0.0027, "step": 248690 }, { "epoch": 59.7, "learning_rate": 3.9349415934759676e-05, "loss": 0.0029, "step": 248700 }, { "epoch": 59.71, "learning_rate": 3.93459087729831e-05, "loss": 0.005, "step": 248710 }, { "epoch": 59.71, "learning_rate": 3.934240166611777e-05, "loss": 0.0031, "step": 248720 }, { "epoch": 59.71, "learning_rate": 3.9338894614181815e-05, "loss": 0.0064, "step": 248730 }, { "epoch": 59.71, "learning_rate": 3.933538761719329e-05, "loss": 0.005, "step": 248740 }, { "epoch": 59.72, "learning_rate": 3.933188067517024e-05, "loss": 0.0041, "step": 248750 }, { "epoch": 59.72, "learning_rate": 3.93283737881308e-05, "loss": 0.003, "step": 248760 }, { "epoch": 59.72, "learning_rate": 3.932486695609297e-05, "loss": 0.0029, "step": 248770 }, { "epoch": 59.72, "learning_rate": 3.93213601790749e-05, "loss": 0.0054, "step": 248780 }, { "epoch": 59.73, "learning_rate": 3.9317853457094604e-05, "loss": 0.004, "step": 248790 }, { "epoch": 59.73, "learning_rate": 3.931434679017019e-05, "loss": 0.0063, "step": 248800 }, { "epoch": 59.73, "learning_rate": 3.931084017831973e-05, "loss": 0.0029, "step": 248810 }, { "epoch": 59.73, "learning_rate": 3.930733362156127e-05, "loss": 0.0046, "step": 248820 }, { "epoch": 59.73, "learning_rate": 3.930382711991293e-05, "loss": 0.0031, "step": 248830 }, { "epoch": 59.74, "learning_rate": 3.930032067339273e-05, "loss": 0.0028, "step": 248840 }, { "epoch": 59.74, "learning_rate": 3.9296814282018784e-05, "loss": 0.0021, "step": 248850 }, { "epoch": 59.74, "learning_rate": 3.929330794580913e-05, "loss": 0.0057, "step": 248860 }, { "epoch": 59.74, "learning_rate": 3.928980166478187e-05, "loss": 0.0026, "step": 248870 }, { "epoch": 59.75, "learning_rate": 3.928629543895507e-05, "loss": 0.0023, "step": 248880 }, { "epoch": 59.75, "learning_rate": 3.9282789268346766e-05, "loss": 0.0024, "step": 248890 }, { "epoch": 59.75, "learning_rate": 3.9279283152975074e-05, "loss": 0.0033, "step": 248900 }, { "epoch": 59.75, "learning_rate": 3.927577709285804e-05, "loss": 0.0024, "step": 248910 }, { "epoch": 59.75, "learning_rate": 3.9272271088013744e-05, "loss": 0.0031, "step": 248920 }, { "epoch": 59.76, "learning_rate": 3.926876513846024e-05, "loss": 0.0038, "step": 248930 }, { "epoch": 59.76, "learning_rate": 3.926525924421564e-05, "loss": 0.0024, "step": 248940 }, { "epoch": 59.76, "learning_rate": 3.9261753405297956e-05, "loss": 0.0024, "step": 248950 }, { "epoch": 59.76, "learning_rate": 3.925824762172528e-05, "loss": 0.0034, "step": 248960 }, { "epoch": 59.77, "learning_rate": 3.925474189351571e-05, "loss": 0.0028, "step": 248970 }, { "epoch": 59.77, "learning_rate": 3.925123622068727e-05, "loss": 0.0041, "step": 248980 }, { "epoch": 59.77, "learning_rate": 3.924773060325807e-05, "loss": 0.005, "step": 248990 }, { "epoch": 59.77, "learning_rate": 3.924422504124612e-05, "loss": 0.008, "step": 249000 }, { "epoch": 59.78, "learning_rate": 3.924071953466956e-05, "loss": 0.0031, "step": 249010 }, { "epoch": 59.78, "learning_rate": 3.9237214083546406e-05, "loss": 0.0022, "step": 249020 }, { "epoch": 59.78, "learning_rate": 3.923370868789475e-05, "loss": 0.0037, "step": 249030 }, { "epoch": 59.78, "learning_rate": 3.923020334773265e-05, "loss": 0.0074, "step": 249040 }, { "epoch": 59.78, "learning_rate": 3.9226698063078153e-05, "loss": 0.0025, "step": 249050 }, { "epoch": 59.79, "learning_rate": 3.922319283394937e-05, "loss": 0.0031, "step": 249060 }, { "epoch": 59.79, "learning_rate": 3.921968766036431e-05, "loss": 0.0023, "step": 249070 }, { "epoch": 59.79, "learning_rate": 3.92161825423411e-05, "loss": 0.0056, "step": 249080 }, { "epoch": 59.79, "learning_rate": 3.921267747989775e-05, "loss": 0.0024, "step": 249090 }, { "epoch": 59.8, "learning_rate": 3.9209172473052364e-05, "loss": 0.0027, "step": 249100 }, { "epoch": 59.8, "learning_rate": 3.9205667521822995e-05, "loss": 0.0046, "step": 249110 }, { "epoch": 59.8, "learning_rate": 3.920216262622769e-05, "loss": 0.0037, "step": 249120 }, { "epoch": 59.8, "learning_rate": 3.919865778628456e-05, "loss": 0.0028, "step": 249130 }, { "epoch": 59.81, "learning_rate": 3.919515300201161e-05, "loss": 0.0027, "step": 249140 }, { "epoch": 59.81, "learning_rate": 3.919164827342695e-05, "loss": 0.0038, "step": 249150 }, { "epoch": 59.81, "learning_rate": 3.9188143600548605e-05, "loss": 0.0026, "step": 249160 }, { "epoch": 59.81, "learning_rate": 3.9184638983394676e-05, "loss": 0.0026, "step": 249170 }, { "epoch": 59.81, "learning_rate": 3.918113442198322e-05, "loss": 0.0037, "step": 249180 }, { "epoch": 59.82, "learning_rate": 3.917762991633225e-05, "loss": 0.0034, "step": 249190 }, { "epoch": 59.82, "learning_rate": 3.91741254664599e-05, "loss": 0.0026, "step": 249200 }, { "epoch": 59.82, "learning_rate": 3.9170621072384174e-05, "loss": 0.0031, "step": 249210 }, { "epoch": 59.82, "learning_rate": 3.9167116734123174e-05, "loss": 0.0033, "step": 249220 }, { "epoch": 59.83, "learning_rate": 3.9163612451694934e-05, "loss": 0.0029, "step": 249230 }, { "epoch": 59.83, "learning_rate": 3.916010822511753e-05, "loss": 0.0022, "step": 249240 }, { "epoch": 59.83, "learning_rate": 3.915660405440902e-05, "loss": 0.0029, "step": 249250 }, { "epoch": 59.83, "learning_rate": 3.915309993958745e-05, "loss": 0.0054, "step": 249260 }, { "epoch": 59.83, "learning_rate": 3.914959588067092e-05, "loss": 0.004, "step": 249270 }, { "epoch": 59.84, "learning_rate": 3.914609187767744e-05, "loss": 0.0045, "step": 249280 }, { "epoch": 59.84, "learning_rate": 3.914258793062511e-05, "loss": 0.0037, "step": 249290 }, { "epoch": 59.84, "learning_rate": 3.913908403953195e-05, "loss": 0.0028, "step": 249300 }, { "epoch": 59.84, "learning_rate": 3.9135580204416064e-05, "loss": 0.0051, "step": 249310 }, { "epoch": 59.85, "learning_rate": 3.913207642529549e-05, "loss": 0.0068, "step": 249320 }, { "epoch": 59.85, "learning_rate": 3.9128572702188274e-05, "loss": 0.0034, "step": 249330 }, { "epoch": 59.85, "learning_rate": 3.9125069035112495e-05, "loss": 0.0099, "step": 249340 }, { "epoch": 59.85, "learning_rate": 3.912156542408618e-05, "loss": 0.0043, "step": 249350 }, { "epoch": 59.86, "learning_rate": 3.911806186912743e-05, "loss": 0.0022, "step": 249360 }, { "epoch": 59.86, "learning_rate": 3.911455837025426e-05, "loss": 0.0028, "step": 249370 }, { "epoch": 59.86, "learning_rate": 3.9111054927484767e-05, "loss": 0.0024, "step": 249380 }, { "epoch": 59.86, "learning_rate": 3.910755154083698e-05, "loss": 0.0023, "step": 249390 }, { "epoch": 59.86, "learning_rate": 3.910404821032896e-05, "loss": 0.0025, "step": 249400 }, { "epoch": 59.87, "learning_rate": 3.9100544935978776e-05, "loss": 0.0028, "step": 249410 }, { "epoch": 59.87, "learning_rate": 3.909704171780445e-05, "loss": 0.0026, "step": 249420 }, { "epoch": 59.87, "learning_rate": 3.909353855582409e-05, "loss": 0.0024, "step": 249430 }, { "epoch": 59.87, "learning_rate": 3.90900354500557e-05, "loss": 0.0024, "step": 249440 }, { "epoch": 59.88, "learning_rate": 3.908653240051738e-05, "loss": 0.0029, "step": 249450 }, { "epoch": 59.88, "learning_rate": 3.908302940722717e-05, "loss": 0.0043, "step": 249460 }, { "epoch": 59.88, "learning_rate": 3.907952647020309e-05, "loss": 0.0032, "step": 249470 }, { "epoch": 59.88, "learning_rate": 3.9076023589463245e-05, "loss": 0.0027, "step": 249480 }, { "epoch": 59.89, "learning_rate": 3.907252076502565e-05, "loss": 0.0025, "step": 249490 }, { "epoch": 59.89, "learning_rate": 3.906901799690839e-05, "loss": 0.0019, "step": 249500 }, { "epoch": 59.89, "learning_rate": 3.906551528512947e-05, "loss": 0.003, "step": 249510 }, { "epoch": 59.89, "learning_rate": 3.906201262970701e-05, "loss": 0.0026, "step": 249520 }, { "epoch": 59.89, "learning_rate": 3.905851003065902e-05, "loss": 0.0074, "step": 249530 }, { "epoch": 59.9, "learning_rate": 3.9055007488003556e-05, "loss": 0.0023, "step": 249540 }, { "epoch": 59.9, "learning_rate": 3.905150500175867e-05, "loss": 0.0021, "step": 249550 }, { "epoch": 59.9, "learning_rate": 3.9048002571942425e-05, "loss": 0.0029, "step": 249560 }, { "epoch": 59.9, "learning_rate": 3.904450019857286e-05, "loss": 0.0026, "step": 249570 }, { "epoch": 59.91, "learning_rate": 3.904099788166803e-05, "loss": 0.0022, "step": 249580 }, { "epoch": 59.91, "learning_rate": 3.9037495621246015e-05, "loss": 0.0063, "step": 249590 }, { "epoch": 59.91, "learning_rate": 3.9033993417324826e-05, "loss": 0.0049, "step": 249600 }, { "epoch": 59.91, "learning_rate": 3.9030491269922506e-05, "loss": 0.0045, "step": 249610 }, { "epoch": 59.91, "learning_rate": 3.9026989179057155e-05, "loss": 0.0028, "step": 249620 }, { "epoch": 59.92, "learning_rate": 3.9023487144746765e-05, "loss": 0.0078, "step": 249630 }, { "epoch": 59.92, "learning_rate": 3.901998516700944e-05, "loss": 0.0023, "step": 249640 }, { "epoch": 59.92, "learning_rate": 3.901648324586319e-05, "loss": 0.0022, "step": 249650 }, { "epoch": 59.92, "learning_rate": 3.901298138132608e-05, "loss": 0.0053, "step": 249660 }, { "epoch": 59.93, "learning_rate": 3.900947957341616e-05, "loss": 0.0058, "step": 249670 }, { "epoch": 59.93, "learning_rate": 3.9005977822151466e-05, "loss": 0.0025, "step": 249680 }, { "epoch": 59.93, "learning_rate": 3.9002476127550056e-05, "loss": 0.006, "step": 249690 }, { "epoch": 59.93, "learning_rate": 3.8998974489629976e-05, "loss": 0.0029, "step": 249700 }, { "epoch": 59.94, "learning_rate": 3.899547290840927e-05, "loss": 0.0022, "step": 249710 }, { "epoch": 59.94, "learning_rate": 3.8991971383906e-05, "loss": 0.0036, "step": 249720 }, { "epoch": 59.94, "learning_rate": 3.8988469916138194e-05, "loss": 0.003, "step": 249730 }, { "epoch": 59.94, "learning_rate": 3.8984968505123917e-05, "loss": 0.0028, "step": 249740 }, { "epoch": 59.94, "learning_rate": 3.898146715088118e-05, "loss": 0.0033, "step": 249750 }, { "epoch": 59.95, "learning_rate": 3.8977965853428076e-05, "loss": 0.0043, "step": 249760 }, { "epoch": 59.95, "learning_rate": 3.897446461278261e-05, "loss": 0.0035, "step": 249770 }, { "epoch": 59.95, "learning_rate": 3.8970963428962864e-05, "loss": 0.0033, "step": 249780 }, { "epoch": 60.0, "learning_rate": 3.896746230198685e-05, "loss": 0.0027, "step": 249790 }, { "epoch": 60.0, "learning_rate": 3.8963961231872635e-05, "loss": 0.0022, "step": 249800 }, { "epoch": 60.01, "learning_rate": 3.896046021863825e-05, "loss": 0.0036, "step": 249810 }, { "epoch": 60.01, "learning_rate": 3.895695926230176e-05, "loss": 0.0025, "step": 249820 }, { "epoch": 60.01, "learning_rate": 3.895345836288118e-05, "loss": 0.0022, "step": 249830 }, { "epoch": 60.01, "learning_rate": 3.894995752039457e-05, "loss": 0.002, "step": 249840 }, { "epoch": 60.02, "learning_rate": 3.894645673485998e-05, "loss": 0.0079, "step": 249850 }, { "epoch": 60.02, "learning_rate": 3.8942956006295436e-05, "loss": 0.0028, "step": 249860 }, { "epoch": 60.02, "learning_rate": 3.8939455334718987e-05, "loss": 0.0021, "step": 249870 }, { "epoch": 60.02, "learning_rate": 3.893595472014868e-05, "loss": 0.0053, "step": 249880 }, { "epoch": 60.03, "learning_rate": 3.893245416260256e-05, "loss": 0.0028, "step": 249890 }, { "epoch": 60.03, "learning_rate": 3.892895366209867e-05, "loss": 0.0027, "step": 249900 }, { "epoch": 60.03, "learning_rate": 3.892545321865502e-05, "loss": 0.0026, "step": 249910 }, { "epoch": 60.03, "learning_rate": 3.89219528322897e-05, "loss": 0.0024, "step": 249920 }, { "epoch": 60.03, "learning_rate": 3.891845250302071e-05, "loss": 0.0038, "step": 249930 }, { "epoch": 60.04, "learning_rate": 3.891495223086613e-05, "loss": 0.0024, "step": 249940 }, { "epoch": 60.04, "learning_rate": 3.891145201584396e-05, "loss": 0.0032, "step": 249950 }, { "epoch": 60.04, "learning_rate": 3.8907951857972276e-05, "loss": 0.006, "step": 249960 }, { "epoch": 60.04, "learning_rate": 3.89044517572691e-05, "loss": 0.0024, "step": 249970 }, { "epoch": 60.05, "learning_rate": 3.890095171375245e-05, "loss": 0.0041, "step": 249980 }, { "epoch": 60.05, "learning_rate": 3.8897451727440404e-05, "loss": 0.0041, "step": 249990 }, { "epoch": 60.05, "learning_rate": 3.889395179835098e-05, "loss": 0.0046, "step": 250000 }, { "epoch": 60.05, "learning_rate": 3.889045192650222e-05, "loss": 0.0028, "step": 250010 }, { "epoch": 60.05, "learning_rate": 3.8886952111912166e-05, "loss": 0.003, "step": 250020 }, { "epoch": 60.06, "learning_rate": 3.8883452354598854e-05, "loss": 0.0066, "step": 250030 }, { "epoch": 60.06, "learning_rate": 3.887995265458033e-05, "loss": 0.0023, "step": 250040 }, { "epoch": 60.06, "learning_rate": 3.88764530118746e-05, "loss": 0.0031, "step": 250050 }, { "epoch": 60.06, "learning_rate": 3.8872953426499754e-05, "loss": 0.0025, "step": 250060 }, { "epoch": 60.07, "learning_rate": 3.8869453898473776e-05, "loss": 0.002, "step": 250070 }, { "epoch": 60.07, "learning_rate": 3.886595442781474e-05, "loss": 0.0021, "step": 250080 }, { "epoch": 60.07, "learning_rate": 3.886245501454065e-05, "loss": 0.0085, "step": 250090 }, { "epoch": 60.07, "learning_rate": 3.885895565866958e-05, "loss": 0.0034, "step": 250100 }, { "epoch": 60.08, "learning_rate": 3.885545636021955e-05, "loss": 0.0042, "step": 250110 }, { "epoch": 60.08, "learning_rate": 3.885195711920857e-05, "loss": 0.0026, "step": 250120 }, { "epoch": 60.08, "learning_rate": 3.884845793565471e-05, "loss": 0.0046, "step": 250130 }, { "epoch": 60.08, "learning_rate": 3.8844958809575975e-05, "loss": 0.0055, "step": 250140 }, { "epoch": 60.08, "learning_rate": 3.8841459740990425e-05, "loss": 0.0022, "step": 250150 }, { "epoch": 60.09, "learning_rate": 3.883796072991609e-05, "loss": 0.0027, "step": 250160 }, { "epoch": 60.09, "learning_rate": 3.883446177637099e-05, "loss": 0.0044, "step": 250170 }, { "epoch": 60.09, "learning_rate": 3.883096288037318e-05, "loss": 0.0023, "step": 250180 }, { "epoch": 60.09, "learning_rate": 3.882746404194066e-05, "loss": 0.0038, "step": 250190 }, { "epoch": 60.1, "learning_rate": 3.882396526109151e-05, "loss": 0.0037, "step": 250200 }, { "epoch": 60.1, "learning_rate": 3.882046653784371e-05, "loss": 0.0031, "step": 250210 }, { "epoch": 60.1, "learning_rate": 3.8816967872215346e-05, "loss": 0.0033, "step": 250220 }, { "epoch": 60.1, "learning_rate": 3.881346926422439e-05, "loss": 0.0029, "step": 250230 }, { "epoch": 60.11, "learning_rate": 3.880997071388894e-05, "loss": 0.0027, "step": 250240 }, { "epoch": 60.11, "learning_rate": 3.8806472221226986e-05, "loss": 0.0027, "step": 250250 }, { "epoch": 60.11, "learning_rate": 3.880297378625655e-05, "loss": 0.002, "step": 250260 }, { "epoch": 60.11, "learning_rate": 3.8799475408995705e-05, "loss": 0.0026, "step": 250270 }, { "epoch": 60.11, "learning_rate": 3.879597708946243e-05, "loss": 0.0052, "step": 250280 }, { "epoch": 60.12, "learning_rate": 3.8792478827674814e-05, "loss": 0.0022, "step": 250290 }, { "epoch": 60.12, "learning_rate": 3.8788980623650826e-05, "loss": 0.0075, "step": 250300 }, { "epoch": 60.12, "learning_rate": 3.878548247740854e-05, "loss": 0.0026, "step": 250310 }, { "epoch": 60.12, "learning_rate": 3.878198438896598e-05, "loss": 0.0042, "step": 250320 }, { "epoch": 60.13, "learning_rate": 3.877848635834114e-05, "loss": 0.0021, "step": 250330 }, { "epoch": 60.13, "learning_rate": 3.8774988385552106e-05, "loss": 0.0023, "step": 250340 }, { "epoch": 60.13, "learning_rate": 3.8771490470616844e-05, "loss": 0.0024, "step": 250350 }, { "epoch": 60.13, "learning_rate": 3.876799261355344e-05, "loss": 0.0054, "step": 250360 }, { "epoch": 60.13, "learning_rate": 3.876449481437988e-05, "loss": 0.0031, "step": 250370 }, { "epoch": 60.14, "learning_rate": 3.8760997073114226e-05, "loss": 0.0034, "step": 250380 }, { "epoch": 60.14, "learning_rate": 3.875749938977449e-05, "loss": 0.0027, "step": 250390 }, { "epoch": 60.14, "learning_rate": 3.8754001764378664e-05, "loss": 0.0023, "step": 250400 }, { "epoch": 60.14, "learning_rate": 3.8750504196944835e-05, "loss": 0.0024, "step": 250410 }, { "epoch": 60.15, "learning_rate": 3.8747006687490975e-05, "loss": 0.002, "step": 250420 }, { "epoch": 60.15, "learning_rate": 3.874350923603517e-05, "loss": 0.0021, "step": 250430 }, { "epoch": 60.15, "learning_rate": 3.874001184259538e-05, "loss": 0.0024, "step": 250440 }, { "epoch": 60.15, "learning_rate": 3.873651450718969e-05, "loss": 0.0025, "step": 250450 }, { "epoch": 60.16, "learning_rate": 3.873301722983609e-05, "loss": 0.0022, "step": 250460 }, { "epoch": 60.16, "learning_rate": 3.87295200105526e-05, "loss": 0.0022, "step": 250470 }, { "epoch": 60.16, "learning_rate": 3.872602284935727e-05, "loss": 0.003, "step": 250480 }, { "epoch": 60.16, "learning_rate": 3.87225257462681e-05, "loss": 0.0031, "step": 250490 }, { "epoch": 60.16, "learning_rate": 3.871902870130315e-05, "loss": 0.0024, "step": 250500 }, { "epoch": 60.17, "learning_rate": 3.871553171448039e-05, "loss": 0.0092, "step": 250510 }, { "epoch": 60.17, "learning_rate": 3.871203478581791e-05, "loss": 0.0033, "step": 250520 }, { "epoch": 60.17, "learning_rate": 3.8708537915333684e-05, "loss": 0.0077, "step": 250530 }, { "epoch": 60.17, "learning_rate": 3.870504110304573e-05, "loss": 0.0029, "step": 250540 }, { "epoch": 60.18, "learning_rate": 3.8701544348972115e-05, "loss": 0.003, "step": 250550 }, { "epoch": 60.18, "learning_rate": 3.869804765313081e-05, "loss": 0.0033, "step": 250560 }, { "epoch": 60.18, "learning_rate": 3.869455101553988e-05, "loss": 0.0024, "step": 250570 }, { "epoch": 60.18, "learning_rate": 3.869105443621731e-05, "loss": 0.0032, "step": 250580 }, { "epoch": 60.19, "learning_rate": 3.868755791518116e-05, "loss": 0.0021, "step": 250590 }, { "epoch": 60.19, "learning_rate": 3.868406145244941e-05, "loss": 0.0025, "step": 250600 }, { "epoch": 60.19, "learning_rate": 3.8680565048040125e-05, "loss": 0.0032, "step": 250610 }, { "epoch": 60.19, "learning_rate": 3.867706870197129e-05, "loss": 0.0027, "step": 250620 }, { "epoch": 60.19, "learning_rate": 3.867357241426093e-05, "loss": 0.0025, "step": 250630 }, { "epoch": 60.2, "learning_rate": 3.867007618492709e-05, "loss": 0.0045, "step": 250640 }, { "epoch": 60.2, "learning_rate": 3.866658001398775e-05, "loss": 0.0065, "step": 250650 }, { "epoch": 60.2, "learning_rate": 3.866308390146098e-05, "loss": 0.0026, "step": 250660 }, { "epoch": 60.2, "learning_rate": 3.865958784736474e-05, "loss": 0.0065, "step": 250670 }, { "epoch": 60.21, "learning_rate": 3.86560918517171e-05, "loss": 0.005, "step": 250680 }, { "epoch": 60.21, "learning_rate": 3.865259591453607e-05, "loss": 0.0049, "step": 250690 }, { "epoch": 60.21, "learning_rate": 3.8649100035839627e-05, "loss": 0.0037, "step": 250700 }, { "epoch": 60.21, "learning_rate": 3.864560421564583e-05, "loss": 0.0029, "step": 250710 }, { "epoch": 60.21, "learning_rate": 3.864210845397267e-05, "loss": 0.0024, "step": 250720 }, { "epoch": 60.22, "learning_rate": 3.86386127508382e-05, "loss": 0.0036, "step": 250730 }, { "epoch": 60.22, "learning_rate": 3.863511710626039e-05, "loss": 0.0091, "step": 250740 }, { "epoch": 60.22, "learning_rate": 3.863162152025731e-05, "loss": 0.0037, "step": 250750 }, { "epoch": 60.22, "learning_rate": 3.862812599284693e-05, "loss": 0.0022, "step": 250760 }, { "epoch": 60.23, "learning_rate": 3.862463052404729e-05, "loss": 0.0035, "step": 250770 }, { "epoch": 60.23, "learning_rate": 3.8621135113876395e-05, "loss": 0.002, "step": 250780 }, { "epoch": 60.23, "learning_rate": 3.861763976235225e-05, "loss": 0.0041, "step": 250790 }, { "epoch": 60.23, "learning_rate": 3.8614144469492914e-05, "loss": 0.0055, "step": 250800 }, { "epoch": 60.24, "learning_rate": 3.861064923531635e-05, "loss": 0.002, "step": 250810 }, { "epoch": 60.24, "learning_rate": 3.8607154059840614e-05, "loss": 0.0032, "step": 250820 }, { "epoch": 60.24, "learning_rate": 3.86036589430837e-05, "loss": 0.0025, "step": 250830 }, { "epoch": 60.24, "learning_rate": 3.86001638850636e-05, "loss": 0.0029, "step": 250840 }, { "epoch": 60.24, "learning_rate": 3.859666888579838e-05, "loss": 0.0021, "step": 250850 }, { "epoch": 60.25, "learning_rate": 3.8593173945305996e-05, "loss": 0.0032, "step": 250860 }, { "epoch": 60.25, "learning_rate": 3.8589679063604514e-05, "loss": 0.0039, "step": 250870 }, { "epoch": 60.25, "learning_rate": 3.85861842407119e-05, "loss": 0.0038, "step": 250880 }, { "epoch": 60.25, "learning_rate": 3.8582689476646204e-05, "loss": 0.0025, "step": 250890 }, { "epoch": 60.26, "learning_rate": 3.857919477142541e-05, "loss": 0.0084, "step": 250900 }, { "epoch": 60.26, "learning_rate": 3.857570012506755e-05, "loss": 0.0089, "step": 250910 }, { "epoch": 60.26, "learning_rate": 3.857220553759062e-05, "loss": 0.0022, "step": 250920 }, { "epoch": 60.26, "learning_rate": 3.856871100901264e-05, "loss": 0.0021, "step": 250930 }, { "epoch": 60.27, "learning_rate": 3.856521653935162e-05, "loss": 0.0053, "step": 250940 }, { "epoch": 60.27, "learning_rate": 3.8561722128625565e-05, "loss": 0.0024, "step": 250950 }, { "epoch": 60.27, "learning_rate": 3.855822777685251e-05, "loss": 0.004, "step": 250960 }, { "epoch": 60.27, "learning_rate": 3.855473348405044e-05, "loss": 0.0022, "step": 250970 }, { "epoch": 60.27, "learning_rate": 3.855123925023734e-05, "loss": 0.0038, "step": 250980 }, { "epoch": 60.28, "learning_rate": 3.854774507543128e-05, "loss": 0.0022, "step": 250990 }, { "epoch": 60.28, "learning_rate": 3.854425095965021e-05, "loss": 0.002, "step": 251000 }, { "epoch": 60.28, "learning_rate": 3.8540756902912194e-05, "loss": 0.0029, "step": 251010 }, { "epoch": 60.28, "learning_rate": 3.8537262905235194e-05, "loss": 0.0045, "step": 251020 }, { "epoch": 60.29, "learning_rate": 3.853376896663725e-05, "loss": 0.0036, "step": 251030 }, { "epoch": 60.29, "learning_rate": 3.853027508713635e-05, "loss": 0.0028, "step": 251040 }, { "epoch": 60.29, "learning_rate": 3.852678126675051e-05, "loss": 0.0023, "step": 251050 }, { "epoch": 60.29, "learning_rate": 3.852328750549773e-05, "loss": 0.0026, "step": 251060 }, { "epoch": 60.29, "learning_rate": 3.851979380339602e-05, "loss": 0.0022, "step": 251070 }, { "epoch": 60.3, "learning_rate": 3.8516300160463395e-05, "loss": 0.0023, "step": 251080 }, { "epoch": 60.3, "learning_rate": 3.851280657671785e-05, "loss": 0.0021, "step": 251090 }, { "epoch": 60.3, "learning_rate": 3.850931305217741e-05, "loss": 0.0125, "step": 251100 }, { "epoch": 60.3, "learning_rate": 3.850581958686007e-05, "loss": 0.002, "step": 251110 }, { "epoch": 60.31, "learning_rate": 3.85023261807838e-05, "loss": 0.0032, "step": 251120 }, { "epoch": 60.31, "learning_rate": 3.8498832833966663e-05, "loss": 0.0022, "step": 251130 }, { "epoch": 60.31, "learning_rate": 3.849533954642662e-05, "loss": 0.004, "step": 251140 }, { "epoch": 60.31, "learning_rate": 3.8491846318181715e-05, "loss": 0.0039, "step": 251150 }, { "epoch": 60.32, "learning_rate": 3.848835314924991e-05, "loss": 0.0026, "step": 251160 }, { "epoch": 60.32, "learning_rate": 3.8484860039649245e-05, "loss": 0.0033, "step": 251170 }, { "epoch": 60.32, "learning_rate": 3.848136698939771e-05, "loss": 0.0031, "step": 251180 }, { "epoch": 60.32, "learning_rate": 3.847787399851328e-05, "loss": 0.0031, "step": 251190 }, { "epoch": 60.32, "learning_rate": 3.8474381067014e-05, "loss": 0.0031, "step": 251200 }, { "epoch": 60.33, "learning_rate": 3.847088819491786e-05, "loss": 0.0025, "step": 251210 }, { "epoch": 60.33, "learning_rate": 3.846739538224285e-05, "loss": 0.0031, "step": 251220 }, { "epoch": 60.33, "learning_rate": 3.846390262900699e-05, "loss": 0.0021, "step": 251230 }, { "epoch": 60.33, "learning_rate": 3.846040993522827e-05, "loss": 0.0071, "step": 251240 }, { "epoch": 60.34, "learning_rate": 3.845691730092469e-05, "loss": 0.0024, "step": 251250 }, { "epoch": 60.34, "learning_rate": 3.845342472611425e-05, "loss": 0.0033, "step": 251260 }, { "epoch": 60.34, "learning_rate": 3.844993221081497e-05, "loss": 0.005, "step": 251270 }, { "epoch": 60.34, "learning_rate": 3.8446439755044815e-05, "loss": 0.0024, "step": 251280 }, { "epoch": 60.35, "learning_rate": 3.844294735882183e-05, "loss": 0.0046, "step": 251290 }, { "epoch": 60.35, "learning_rate": 3.8439455022163966e-05, "loss": 0.0031, "step": 251300 }, { "epoch": 60.35, "learning_rate": 3.843596274508927e-05, "loss": 0.0042, "step": 251310 }, { "epoch": 60.35, "learning_rate": 3.8432470527615725e-05, "loss": 0.0022, "step": 251320 }, { "epoch": 60.35, "learning_rate": 3.842897836976129e-05, "loss": 0.0022, "step": 251330 }, { "epoch": 60.36, "learning_rate": 3.842548627154403e-05, "loss": 0.0024, "step": 251340 }, { "epoch": 60.36, "learning_rate": 3.842199423298188e-05, "loss": 0.0029, "step": 251350 }, { "epoch": 60.36, "learning_rate": 3.8418502254092886e-05, "loss": 0.0023, "step": 251360 }, { "epoch": 60.36, "learning_rate": 3.841501033489503e-05, "loss": 0.0048, "step": 251370 }, { "epoch": 60.37, "learning_rate": 3.84115184754063e-05, "loss": 0.0039, "step": 251380 }, { "epoch": 60.37, "learning_rate": 3.84080266756447e-05, "loss": 0.0034, "step": 251390 }, { "epoch": 60.37, "learning_rate": 3.840453493562823e-05, "loss": 0.0042, "step": 251400 }, { "epoch": 60.37, "learning_rate": 3.84010432553749e-05, "loss": 0.0074, "step": 251410 }, { "epoch": 60.37, "learning_rate": 3.8397551634902666e-05, "loss": 0.0027, "step": 251420 }, { "epoch": 60.38, "learning_rate": 3.8394060074229566e-05, "loss": 0.0019, "step": 251430 }, { "epoch": 60.38, "learning_rate": 3.839056857337356e-05, "loss": 0.0023, "step": 251440 }, { "epoch": 60.38, "learning_rate": 3.838707713235268e-05, "loss": 0.0027, "step": 251450 }, { "epoch": 60.38, "learning_rate": 3.838358575118488e-05, "loss": 0.002, "step": 251460 }, { "epoch": 60.39, "learning_rate": 3.83800944298882e-05, "loss": 0.0018, "step": 251470 }, { "epoch": 60.39, "learning_rate": 3.837660316848061e-05, "loss": 0.0021, "step": 251480 }, { "epoch": 60.39, "learning_rate": 3.837311196698008e-05, "loss": 0.0022, "step": 251490 }, { "epoch": 60.39, "learning_rate": 3.836962082540463e-05, "loss": 0.0027, "step": 251500 }, { "epoch": 60.4, "learning_rate": 3.836612974377227e-05, "loss": 0.0034, "step": 251510 }, { "epoch": 60.4, "learning_rate": 3.836263872210096e-05, "loss": 0.0024, "step": 251520 }, { "epoch": 60.4, "learning_rate": 3.8359147760408716e-05, "loss": 0.0025, "step": 251530 }, { "epoch": 60.4, "learning_rate": 3.835565685871352e-05, "loss": 0.0045, "step": 251540 }, { "epoch": 60.4, "learning_rate": 3.8352166017033374e-05, "loss": 0.0029, "step": 251550 }, { "epoch": 60.41, "learning_rate": 3.834867523538625e-05, "loss": 0.0032, "step": 251560 }, { "epoch": 60.41, "learning_rate": 3.834518451379016e-05, "loss": 0.002, "step": 251570 }, { "epoch": 60.41, "learning_rate": 3.8341693852263064e-05, "loss": 0.0022, "step": 251580 }, { "epoch": 60.41, "learning_rate": 3.8338203250823e-05, "loss": 0.0052, "step": 251590 }, { "epoch": 60.42, "learning_rate": 3.833471270948792e-05, "loss": 0.0023, "step": 251600 }, { "epoch": 60.42, "learning_rate": 3.8331222228275844e-05, "loss": 0.0023, "step": 251610 }, { "epoch": 60.42, "learning_rate": 3.832773180720475e-05, "loss": 0.0021, "step": 251620 }, { "epoch": 60.42, "learning_rate": 3.83242414462926e-05, "loss": 0.0022, "step": 251630 }, { "epoch": 60.43, "learning_rate": 3.832075114555742e-05, "loss": 0.0028, "step": 251640 }, { "epoch": 60.43, "learning_rate": 3.8317260905017174e-05, "loss": 0.0023, "step": 251650 }, { "epoch": 60.43, "learning_rate": 3.831377072468988e-05, "loss": 0.0052, "step": 251660 }, { "epoch": 60.43, "learning_rate": 3.831028060459349e-05, "loss": 0.0033, "step": 251670 }, { "epoch": 60.43, "learning_rate": 3.830679054474602e-05, "loss": 0.0088, "step": 251680 }, { "epoch": 60.44, "learning_rate": 3.8303300545165465e-05, "loss": 0.0062, "step": 251690 }, { "epoch": 60.44, "learning_rate": 3.829981060586978e-05, "loss": 0.0023, "step": 251700 }, { "epoch": 60.44, "learning_rate": 3.8296320726876976e-05, "loss": 0.002, "step": 251710 }, { "epoch": 60.44, "learning_rate": 3.8292830908205025e-05, "loss": 0.0022, "step": 251720 }, { "epoch": 60.45, "learning_rate": 3.8289341149871934e-05, "loss": 0.003, "step": 251730 }, { "epoch": 60.45, "learning_rate": 3.828585145189566e-05, "loss": 0.0021, "step": 251740 }, { "epoch": 60.45, "learning_rate": 3.828236181429422e-05, "loss": 0.0022, "step": 251750 }, { "epoch": 60.45, "learning_rate": 3.827887223708559e-05, "loss": 0.0028, "step": 251760 }, { "epoch": 60.45, "learning_rate": 3.8275382720287735e-05, "loss": 0.0032, "step": 251770 }, { "epoch": 60.46, "learning_rate": 3.827189326391867e-05, "loss": 0.0024, "step": 251780 }, { "epoch": 60.46, "learning_rate": 3.826840386799634e-05, "loss": 0.0029, "step": 251790 }, { "epoch": 60.46, "learning_rate": 3.826491453253878e-05, "loss": 0.0021, "step": 251800 }, { "epoch": 60.46, "learning_rate": 3.826142525756393e-05, "loss": 0.003, "step": 251810 }, { "epoch": 60.47, "learning_rate": 3.82579360430898e-05, "loss": 0.0026, "step": 251820 }, { "epoch": 60.47, "learning_rate": 3.825444688913438e-05, "loss": 0.0034, "step": 251830 }, { "epoch": 60.47, "learning_rate": 3.825095779571561e-05, "loss": 0.0089, "step": 251840 }, { "epoch": 60.47, "learning_rate": 3.824746876285153e-05, "loss": 0.0023, "step": 251850 }, { "epoch": 60.48, "learning_rate": 3.824397979056007e-05, "loss": 0.0061, "step": 251860 }, { "epoch": 60.48, "learning_rate": 3.824049087885926e-05, "loss": 0.0029, "step": 251870 }, { "epoch": 60.48, "learning_rate": 3.823700202776703e-05, "loss": 0.0023, "step": 251880 }, { "epoch": 60.48, "learning_rate": 3.8233513237301425e-05, "loss": 0.0024, "step": 251890 }, { "epoch": 60.48, "learning_rate": 3.823002450748038e-05, "loss": 0.004, "step": 251900 }, { "epoch": 60.49, "learning_rate": 3.8226535838321864e-05, "loss": 0.0044, "step": 251910 }, { "epoch": 60.49, "learning_rate": 3.822304722984391e-05, "loss": 0.0021, "step": 251920 }, { "epoch": 60.49, "learning_rate": 3.8219558682064445e-05, "loss": 0.0033, "step": 251930 }, { "epoch": 60.49, "learning_rate": 3.821607019500149e-05, "loss": 0.0033, "step": 251940 }, { "epoch": 60.5, "learning_rate": 3.8212581768672996e-05, "loss": 0.0027, "step": 251950 }, { "epoch": 60.5, "learning_rate": 3.820909340309696e-05, "loss": 0.0034, "step": 251960 }, { "epoch": 60.5, "learning_rate": 3.8205605098291356e-05, "loss": 0.0035, "step": 251970 }, { "epoch": 60.5, "learning_rate": 3.820211685427415e-05, "loss": 0.0074, "step": 251980 }, { "epoch": 60.51, "learning_rate": 3.819862867106336e-05, "loss": 0.005, "step": 251990 }, { "epoch": 60.51, "learning_rate": 3.819514054867691e-05, "loss": 0.0023, "step": 252000 }, { "epoch": 60.51, "learning_rate": 3.819165248713282e-05, "loss": 0.0021, "step": 252010 }, { "epoch": 60.51, "learning_rate": 3.818816448644903e-05, "loss": 0.0024, "step": 252020 }, { "epoch": 60.51, "learning_rate": 3.818467654664357e-05, "loss": 0.0026, "step": 252030 }, { "epoch": 60.52, "learning_rate": 3.8181188667734375e-05, "loss": 0.007, "step": 252040 }, { "epoch": 60.52, "learning_rate": 3.817770084973942e-05, "loss": 0.0059, "step": 252050 }, { "epoch": 60.52, "learning_rate": 3.817421309267671e-05, "loss": 0.0026, "step": 252060 }, { "epoch": 60.52, "learning_rate": 3.817072539656418e-05, "loss": 0.0025, "step": 252070 }, { "epoch": 60.53, "learning_rate": 3.816723776141986e-05, "loss": 0.0031, "step": 252080 }, { "epoch": 60.53, "learning_rate": 3.816375018726167e-05, "loss": 0.0034, "step": 252090 }, { "epoch": 60.53, "learning_rate": 3.8160262674107624e-05, "loss": 0.0028, "step": 252100 }, { "epoch": 60.53, "learning_rate": 3.815677522197569e-05, "loss": 0.0026, "step": 252110 }, { "epoch": 60.53, "learning_rate": 3.815328783088382e-05, "loss": 0.0039, "step": 252120 }, { "epoch": 60.54, "learning_rate": 3.814980050085001e-05, "loss": 0.0031, "step": 252130 }, { "epoch": 60.54, "learning_rate": 3.814631323189222e-05, "loss": 0.0029, "step": 252140 }, { "epoch": 60.54, "learning_rate": 3.814282602402844e-05, "loss": 0.0036, "step": 252150 }, { "epoch": 60.54, "learning_rate": 3.8139338877276624e-05, "loss": 0.0033, "step": 252160 }, { "epoch": 60.55, "learning_rate": 3.8135851791654775e-05, "loss": 0.0034, "step": 252170 }, { "epoch": 60.55, "learning_rate": 3.8132364767180836e-05, "loss": 0.0032, "step": 252180 }, { "epoch": 60.55, "learning_rate": 3.812887780387278e-05, "loss": 0.0063, "step": 252190 }, { "epoch": 60.55, "learning_rate": 3.8125390901748604e-05, "loss": 0.0037, "step": 252200 }, { "epoch": 60.56, "learning_rate": 3.812190406082624e-05, "loss": 0.0038, "step": 252210 }, { "epoch": 60.56, "learning_rate": 3.81184172811237e-05, "loss": 0.0095, "step": 252220 }, { "epoch": 60.56, "learning_rate": 3.811493056265891e-05, "loss": 0.0023, "step": 252230 }, { "epoch": 60.56, "learning_rate": 3.81114439054499e-05, "loss": 0.008, "step": 252240 }, { "epoch": 60.56, "learning_rate": 3.8107957309514584e-05, "loss": 0.0032, "step": 252250 }, { "epoch": 60.57, "learning_rate": 3.810447077487097e-05, "loss": 0.003, "step": 252260 }, { "epoch": 60.57, "learning_rate": 3.810098430153701e-05, "loss": 0.0024, "step": 252270 }, { "epoch": 60.57, "learning_rate": 3.8097497889530675e-05, "loss": 0.0033, "step": 252280 }, { "epoch": 60.57, "learning_rate": 3.8094011538869935e-05, "loss": 0.0031, "step": 252290 }, { "epoch": 60.58, "learning_rate": 3.809052524957275e-05, "loss": 0.0046, "step": 252300 }, { "epoch": 60.58, "learning_rate": 3.808703902165711e-05, "loss": 0.0027, "step": 252310 }, { "epoch": 60.58, "learning_rate": 3.808355285514096e-05, "loss": 0.003, "step": 252320 }, { "epoch": 60.58, "learning_rate": 3.808006675004229e-05, "loss": 0.0059, "step": 252330 }, { "epoch": 60.59, "learning_rate": 3.807658070637906e-05, "loss": 0.0033, "step": 252340 }, { "epoch": 60.59, "learning_rate": 3.807309472416921e-05, "loss": 0.0046, "step": 252350 }, { "epoch": 60.59, "learning_rate": 3.8069608803430755e-05, "loss": 0.0068, "step": 252360 }, { "epoch": 60.59, "learning_rate": 3.8066122944181614e-05, "loss": 0.0029, "step": 252370 }, { "epoch": 60.59, "learning_rate": 3.80626371464398e-05, "loss": 0.0033, "step": 252380 }, { "epoch": 60.6, "learning_rate": 3.805915141022322e-05, "loss": 0.0036, "step": 252390 }, { "epoch": 60.6, "learning_rate": 3.80556657355499e-05, "loss": 0.004, "step": 252400 }, { "epoch": 60.6, "learning_rate": 3.805218012243777e-05, "loss": 0.0041, "step": 252410 }, { "epoch": 60.6, "learning_rate": 3.8048694570904805e-05, "loss": 0.0037, "step": 252420 }, { "epoch": 60.61, "learning_rate": 3.804520908096897e-05, "loss": 0.0095, "step": 252430 }, { "epoch": 60.61, "learning_rate": 3.804172365264822e-05, "loss": 0.0029, "step": 252440 }, { "epoch": 60.61, "learning_rate": 3.803823828596053e-05, "loss": 0.0032, "step": 252450 }, { "epoch": 60.61, "learning_rate": 3.803475298092385e-05, "loss": 0.0042, "step": 252460 }, { "epoch": 60.61, "learning_rate": 3.803126773755617e-05, "loss": 0.0032, "step": 252470 }, { "epoch": 60.62, "learning_rate": 3.802778255587544e-05, "loss": 0.0059, "step": 252480 }, { "epoch": 60.62, "learning_rate": 3.80242974358996e-05, "loss": 0.0063, "step": 252490 }, { "epoch": 60.62, "learning_rate": 3.8020812377646644e-05, "loss": 0.0035, "step": 252500 }, { "epoch": 60.62, "learning_rate": 3.801732738113451e-05, "loss": 0.0038, "step": 252510 }, { "epoch": 60.63, "learning_rate": 3.8013842446381186e-05, "loss": 0.003, "step": 252520 }, { "epoch": 60.63, "learning_rate": 3.80103575734046e-05, "loss": 0.0058, "step": 252530 }, { "epoch": 60.63, "learning_rate": 3.800687276222275e-05, "loss": 0.0033, "step": 252540 }, { "epoch": 60.63, "learning_rate": 3.800338801285357e-05, "loss": 0.0027, "step": 252550 }, { "epoch": 60.64, "learning_rate": 3.799990332531503e-05, "loss": 0.0035, "step": 252560 }, { "epoch": 60.64, "learning_rate": 3.799641869962508e-05, "loss": 0.0054, "step": 252570 }, { "epoch": 60.64, "learning_rate": 3.7992934135801695e-05, "loss": 0.0039, "step": 252580 }, { "epoch": 60.64, "learning_rate": 3.798944963386283e-05, "loss": 0.0032, "step": 252590 }, { "epoch": 60.64, "learning_rate": 3.7985965193826423e-05, "loss": 0.0029, "step": 252600 }, { "epoch": 60.65, "learning_rate": 3.798248081571048e-05, "loss": 0.003, "step": 252610 }, { "epoch": 60.65, "learning_rate": 3.797899649953293e-05, "loss": 0.0049, "step": 252620 }, { "epoch": 60.65, "learning_rate": 3.7975512245311714e-05, "loss": 0.0036, "step": 252630 }, { "epoch": 60.65, "learning_rate": 3.7972028053064823e-05, "loss": 0.0023, "step": 252640 }, { "epoch": 60.66, "learning_rate": 3.796854392281019e-05, "loss": 0.0035, "step": 252650 }, { "epoch": 60.66, "learning_rate": 3.796505985456579e-05, "loss": 0.003, "step": 252660 }, { "epoch": 60.66, "learning_rate": 3.796157584834956e-05, "loss": 0.0029, "step": 252670 }, { "epoch": 60.66, "learning_rate": 3.795809190417948e-05, "loss": 0.0023, "step": 252680 }, { "epoch": 60.66, "learning_rate": 3.79546080220735e-05, "loss": 0.0113, "step": 252690 }, { "epoch": 60.67, "learning_rate": 3.7951124202049554e-05, "loss": 0.004, "step": 252700 }, { "epoch": 60.67, "learning_rate": 3.7947640444125624e-05, "loss": 0.0023, "step": 252710 }, { "epoch": 60.67, "learning_rate": 3.794415674831965e-05, "loss": 0.003, "step": 252720 }, { "epoch": 60.67, "learning_rate": 3.79406731146496e-05, "loss": 0.0032, "step": 252730 }, { "epoch": 60.68, "learning_rate": 3.793718954313342e-05, "loss": 0.0052, "step": 252740 }, { "epoch": 60.68, "learning_rate": 3.793370603378906e-05, "loss": 0.0032, "step": 252750 }, { "epoch": 60.68, "learning_rate": 3.793022258663449e-05, "loss": 0.0028, "step": 252760 }, { "epoch": 60.68, "learning_rate": 3.792673920168764e-05, "loss": 0.003, "step": 252770 }, { "epoch": 60.69, "learning_rate": 3.79232558789665e-05, "loss": 0.0022, "step": 252780 }, { "epoch": 60.69, "learning_rate": 3.7919772618488976e-05, "loss": 0.0038, "step": 252790 }, { "epoch": 60.69, "learning_rate": 3.791628942027307e-05, "loss": 0.0027, "step": 252800 }, { "epoch": 60.69, "learning_rate": 3.791280628433668e-05, "loss": 0.0042, "step": 252810 }, { "epoch": 60.69, "learning_rate": 3.790932321069781e-05, "loss": 0.0036, "step": 252820 }, { "epoch": 60.7, "learning_rate": 3.7905840199374386e-05, "loss": 0.0044, "step": 252830 }, { "epoch": 60.7, "learning_rate": 3.790235725038435e-05, "loss": 0.015, "step": 252840 }, { "epoch": 60.7, "learning_rate": 3.789887436374568e-05, "loss": 0.0051, "step": 252850 }, { "epoch": 60.7, "learning_rate": 3.78953915394763e-05, "loss": 0.0028, "step": 252860 }, { "epoch": 60.71, "learning_rate": 3.789190877759417e-05, "loss": 0.0036, "step": 252870 }, { "epoch": 60.71, "learning_rate": 3.7888426078117254e-05, "loss": 0.0049, "step": 252880 }, { "epoch": 60.71, "learning_rate": 3.788494344106349e-05, "loss": 0.0039, "step": 252890 }, { "epoch": 60.71, "learning_rate": 3.788146086645084e-05, "loss": 0.0027, "step": 252900 }, { "epoch": 60.72, "learning_rate": 3.7877978354297224e-05, "loss": 0.0025, "step": 252910 }, { "epoch": 60.72, "learning_rate": 3.787449590462062e-05, "loss": 0.0026, "step": 252920 }, { "epoch": 60.72, "learning_rate": 3.7871013517438956e-05, "loss": 0.0024, "step": 252930 }, { "epoch": 60.72, "learning_rate": 3.78675311927702e-05, "loss": 0.0024, "step": 252940 }, { "epoch": 60.72, "learning_rate": 3.7864048930632273e-05, "loss": 0.0046, "step": 252950 }, { "epoch": 60.73, "learning_rate": 3.7860566731043164e-05, "loss": 0.0032, "step": 252960 }, { "epoch": 60.73, "learning_rate": 3.7857084594020794e-05, "loss": 0.0036, "step": 252970 }, { "epoch": 60.73, "learning_rate": 3.7853602519583086e-05, "loss": 0.0029, "step": 252980 }, { "epoch": 60.73, "learning_rate": 3.785012050774803e-05, "loss": 0.0036, "step": 252990 }, { "epoch": 60.74, "learning_rate": 3.784663855853354e-05, "loss": 0.0023, "step": 253000 }, { "epoch": 60.74, "learning_rate": 3.7843156671957603e-05, "loss": 0.0022, "step": 253010 }, { "epoch": 60.74, "learning_rate": 3.783967484803811e-05, "loss": 0.0052, "step": 253020 }, { "epoch": 60.74, "learning_rate": 3.783619308679304e-05, "loss": 0.0026, "step": 253030 }, { "epoch": 60.74, "learning_rate": 3.783271138824034e-05, "loss": 0.0066, "step": 253040 }, { "epoch": 60.75, "learning_rate": 3.782922975239795e-05, "loss": 0.0026, "step": 253050 }, { "epoch": 60.75, "learning_rate": 3.782574817928382e-05, "loss": 0.0024, "step": 253060 }, { "epoch": 60.75, "learning_rate": 3.7822266668915856e-05, "loss": 0.0049, "step": 253070 }, { "epoch": 60.75, "learning_rate": 3.781878522131206e-05, "loss": 0.007, "step": 253080 }, { "epoch": 60.76, "learning_rate": 3.7815303836490326e-05, "loss": 0.0037, "step": 253090 }, { "epoch": 60.76, "learning_rate": 3.781182251446864e-05, "loss": 0.0038, "step": 253100 }, { "epoch": 60.76, "learning_rate": 3.780834125526489e-05, "loss": 0.006, "step": 253110 }, { "epoch": 60.76, "learning_rate": 3.7804860058897086e-05, "loss": 0.0031, "step": 253120 }, { "epoch": 60.77, "learning_rate": 3.780137892538313e-05, "loss": 0.0027, "step": 253130 }, { "epoch": 60.77, "learning_rate": 3.779789785474095e-05, "loss": 0.0032, "step": 253140 }, { "epoch": 60.77, "learning_rate": 3.7794416846988524e-05, "loss": 0.0029, "step": 253150 }, { "epoch": 60.77, "learning_rate": 3.779093590214376e-05, "loss": 0.0027, "step": 253160 }, { "epoch": 60.77, "learning_rate": 3.778745502022461e-05, "loss": 0.0026, "step": 253170 }, { "epoch": 60.78, "learning_rate": 3.7783974201249036e-05, "loss": 0.0024, "step": 253180 }, { "epoch": 60.78, "learning_rate": 3.778049344523496e-05, "loss": 0.0023, "step": 253190 }, { "epoch": 60.78, "learning_rate": 3.7777012752200325e-05, "loss": 0.0073, "step": 253200 }, { "epoch": 60.78, "learning_rate": 3.777353212216305e-05, "loss": 0.0026, "step": 253210 }, { "epoch": 60.79, "learning_rate": 3.777005155514111e-05, "loss": 0.0028, "step": 253220 }, { "epoch": 60.79, "learning_rate": 3.7766571051152414e-05, "loss": 0.0026, "step": 253230 }, { "epoch": 60.79, "learning_rate": 3.776309061021493e-05, "loss": 0.0034, "step": 253240 }, { "epoch": 60.79, "learning_rate": 3.775961023234656e-05, "loss": 0.0031, "step": 253250 }, { "epoch": 60.8, "learning_rate": 3.7756129917565274e-05, "loss": 0.0023, "step": 253260 }, { "epoch": 60.8, "learning_rate": 3.7752649665889004e-05, "loss": 0.0017, "step": 253270 }, { "epoch": 60.8, "learning_rate": 3.774916947733566e-05, "loss": 0.0019, "step": 253280 }, { "epoch": 60.8, "learning_rate": 3.774568935192322e-05, "loss": 0.0019, "step": 253290 }, { "epoch": 60.8, "learning_rate": 3.774220928966958e-05, "loss": 0.0021, "step": 253300 }, { "epoch": 60.81, "learning_rate": 3.773872929059271e-05, "loss": 0.002, "step": 253310 }, { "epoch": 60.81, "learning_rate": 3.773524935471051e-05, "loss": 0.0021, "step": 253320 }, { "epoch": 60.81, "learning_rate": 3.773176948204096e-05, "loss": 0.0027, "step": 253330 }, { "epoch": 60.81, "learning_rate": 3.7728289672601974e-05, "loss": 0.0019, "step": 253340 }, { "epoch": 60.82, "learning_rate": 3.772480992641147e-05, "loss": 0.0027, "step": 253350 }, { "epoch": 60.82, "learning_rate": 3.772133024348741e-05, "loss": 0.0023, "step": 253360 }, { "epoch": 60.82, "learning_rate": 3.77178506238477e-05, "loss": 0.0026, "step": 253370 }, { "epoch": 60.82, "learning_rate": 3.7714371067510315e-05, "loss": 0.0034, "step": 253380 }, { "epoch": 60.82, "learning_rate": 3.771089157449314e-05, "loss": 0.0026, "step": 253390 }, { "epoch": 60.83, "learning_rate": 3.770741214481415e-05, "loss": 0.0022, "step": 253400 }, { "epoch": 60.83, "learning_rate": 3.770393277849127e-05, "loss": 0.0029, "step": 253410 }, { "epoch": 60.83, "learning_rate": 3.770045347554239e-05, "loss": 0.002, "step": 253420 }, { "epoch": 60.83, "learning_rate": 3.7696974235985504e-05, "loss": 0.0025, "step": 253430 }, { "epoch": 60.84, "learning_rate": 3.7693495059838494e-05, "loss": 0.0024, "step": 253440 }, { "epoch": 60.84, "learning_rate": 3.769001594711933e-05, "loss": 0.0045, "step": 253450 }, { "epoch": 60.84, "learning_rate": 3.7686536897845916e-05, "loss": 0.0039, "step": 253460 }, { "epoch": 60.84, "learning_rate": 3.768305791203621e-05, "loss": 0.003, "step": 253470 }, { "epoch": 60.85, "learning_rate": 3.7679578989708116e-05, "loss": 0.0023, "step": 253480 }, { "epoch": 60.85, "learning_rate": 3.7676100130879563e-05, "loss": 0.0024, "step": 253490 }, { "epoch": 60.85, "learning_rate": 3.7672621335568514e-05, "loss": 0.003, "step": 253500 }, { "epoch": 60.85, "learning_rate": 3.766914260379285e-05, "loss": 0.0025, "step": 253510 }, { "epoch": 60.85, "learning_rate": 3.766566393557056e-05, "loss": 0.0021, "step": 253520 }, { "epoch": 60.86, "learning_rate": 3.7662185330919515e-05, "loss": 0.0028, "step": 253530 }, { "epoch": 60.86, "learning_rate": 3.765870678985769e-05, "loss": 0.002, "step": 253540 }, { "epoch": 60.86, "learning_rate": 3.7655228312403e-05, "loss": 0.002, "step": 253550 }, { "epoch": 60.86, "learning_rate": 3.765174989857334e-05, "loss": 0.0029, "step": 253560 }, { "epoch": 60.87, "learning_rate": 3.7648271548386685e-05, "loss": 0.0026, "step": 253570 }, { "epoch": 60.87, "learning_rate": 3.7644793261860923e-05, "loss": 0.0027, "step": 253580 }, { "epoch": 60.87, "learning_rate": 3.764131503901402e-05, "loss": 0.0027, "step": 253590 }, { "epoch": 60.87, "learning_rate": 3.7637836879863855e-05, "loss": 0.0026, "step": 253600 }, { "epoch": 60.88, "learning_rate": 3.7634358784428415e-05, "loss": 0.0028, "step": 253610 }, { "epoch": 60.88, "learning_rate": 3.763088075272557e-05, "loss": 0.0021, "step": 253620 }, { "epoch": 60.88, "learning_rate": 3.762740278477328e-05, "loss": 0.0018, "step": 253630 }, { "epoch": 60.88, "learning_rate": 3.7623924880589455e-05, "loss": 0.0026, "step": 253640 }, { "epoch": 60.88, "learning_rate": 3.762044704019202e-05, "loss": 0.0048, "step": 253650 }, { "epoch": 60.89, "learning_rate": 3.7616969263598914e-05, "loss": 0.0025, "step": 253660 }, { "epoch": 60.89, "learning_rate": 3.7613491550828037e-05, "loss": 0.0027, "step": 253670 }, { "epoch": 60.89, "learning_rate": 3.761001390189735e-05, "loss": 0.0024, "step": 253680 }, { "epoch": 60.89, "learning_rate": 3.760653631682475e-05, "loss": 0.002, "step": 253690 }, { "epoch": 60.9, "learning_rate": 3.760305879562815e-05, "loss": 0.0025, "step": 253700 }, { "epoch": 60.9, "learning_rate": 3.7599581338325504e-05, "loss": 0.0035, "step": 253710 }, { "epoch": 60.9, "learning_rate": 3.759610394493471e-05, "loss": 0.0024, "step": 253720 }, { "epoch": 60.9, "learning_rate": 3.759262661547371e-05, "loss": 0.0277, "step": 253730 }, { "epoch": 60.9, "learning_rate": 3.758914934996039e-05, "loss": 0.0046, "step": 253740 }, { "epoch": 60.91, "learning_rate": 3.7585672148412734e-05, "loss": 0.0024, "step": 253750 }, { "epoch": 60.91, "learning_rate": 3.758219501084861e-05, "loss": 0.0029, "step": 253760 }, { "epoch": 60.91, "learning_rate": 3.7578717937285954e-05, "loss": 0.0028, "step": 253770 }, { "epoch": 60.91, "learning_rate": 3.7575240927742693e-05, "loss": 0.0028, "step": 253780 }, { "epoch": 60.92, "learning_rate": 3.757176398223674e-05, "loss": 0.0044, "step": 253790 }, { "epoch": 60.92, "learning_rate": 3.756828710078603e-05, "loss": 0.003, "step": 253800 }, { "epoch": 60.92, "learning_rate": 3.756481028340845e-05, "loss": 0.0035, "step": 253810 }, { "epoch": 60.92, "learning_rate": 3.756133353012197e-05, "loss": 0.002, "step": 253820 }, { "epoch": 60.93, "learning_rate": 3.755785684094446e-05, "loss": 0.0026, "step": 253830 }, { "epoch": 60.93, "learning_rate": 3.755438021589388e-05, "loss": 0.0061, "step": 253840 }, { "epoch": 60.93, "learning_rate": 3.755090365498812e-05, "loss": 0.0022, "step": 253850 }, { "epoch": 60.93, "learning_rate": 3.7547427158245094e-05, "loss": 0.0022, "step": 253860 }, { "epoch": 60.93, "learning_rate": 3.754395072568275e-05, "loss": 0.0018, "step": 253870 }, { "epoch": 60.94, "learning_rate": 3.754047435731897e-05, "loss": 0.0023, "step": 253880 }, { "epoch": 60.94, "learning_rate": 3.753699805317171e-05, "loss": 0.0026, "step": 253890 }, { "epoch": 60.94, "learning_rate": 3.753352181325884e-05, "loss": 0.0055, "step": 253900 }, { "epoch": 60.94, "learning_rate": 3.753004563759833e-05, "loss": 0.0021, "step": 253910 }, { "epoch": 60.95, "learning_rate": 3.752656952620806e-05, "loss": 0.0026, "step": 253920 }, { "epoch": 60.95, "learning_rate": 3.752309347910595e-05, "loss": 0.0024, "step": 253930 }, { "epoch": 60.95, "learning_rate": 3.751961749630992e-05, "loss": 0.0019, "step": 253940 }, { "epoch": 61.0, "learning_rate": 3.751614157783789e-05, "loss": 0.0049, "step": 253950 }, { "epoch": 61.0, "learning_rate": 3.751266572370777e-05, "loss": 0.0027, "step": 253960 }, { "epoch": 61.01, "learning_rate": 3.7509189933937464e-05, "loss": 0.0024, "step": 253970 }, { "epoch": 61.01, "learning_rate": 3.750571420854492e-05, "loss": 0.005, "step": 253980 }, { "epoch": 61.01, "learning_rate": 3.750223854754802e-05, "loss": 0.0032, "step": 253990 }, { "epoch": 61.01, "learning_rate": 3.749876295096468e-05, "loss": 0.0047, "step": 254000 }, { "epoch": 61.02, "learning_rate": 3.749528741881283e-05, "loss": 0.0023, "step": 254010 }, { "epoch": 61.02, "learning_rate": 3.7491811951110355e-05, "loss": 0.0029, "step": 254020 }, { "epoch": 61.02, "learning_rate": 3.748833654787521e-05, "loss": 0.0024, "step": 254030 }, { "epoch": 61.02, "learning_rate": 3.748486120912526e-05, "loss": 0.0029, "step": 254040 }, { "epoch": 61.02, "learning_rate": 3.7481385934878465e-05, "loss": 0.0038, "step": 254050 }, { "epoch": 61.03, "learning_rate": 3.7477910725152695e-05, "loss": 0.0022, "step": 254060 }, { "epoch": 61.03, "learning_rate": 3.747443557996588e-05, "loss": 0.0053, "step": 254070 }, { "epoch": 61.03, "learning_rate": 3.747096049933593e-05, "loss": 0.0022, "step": 254080 }, { "epoch": 61.03, "learning_rate": 3.746748548328075e-05, "loss": 0.0023, "step": 254090 }, { "epoch": 61.04, "learning_rate": 3.746401053181826e-05, "loss": 0.0027, "step": 254100 }, { "epoch": 61.04, "learning_rate": 3.746053564496636e-05, "loss": 0.0023, "step": 254110 }, { "epoch": 61.04, "learning_rate": 3.7457060822742964e-05, "loss": 0.0019, "step": 254120 }, { "epoch": 61.04, "learning_rate": 3.7453586065166004e-05, "loss": 0.002, "step": 254130 }, { "epoch": 61.05, "learning_rate": 3.745011137225333e-05, "loss": 0.0027, "step": 254140 }, { "epoch": 61.05, "learning_rate": 3.744663674402291e-05, "loss": 0.0024, "step": 254150 }, { "epoch": 61.05, "learning_rate": 3.7443162180492615e-05, "loss": 0.0024, "step": 254160 }, { "epoch": 61.05, "learning_rate": 3.743968768168038e-05, "loss": 0.0038, "step": 254170 }, { "epoch": 61.05, "learning_rate": 3.743621324760408e-05, "loss": 0.0025, "step": 254180 }, { "epoch": 61.06, "learning_rate": 3.743273887828167e-05, "loss": 0.0035, "step": 254190 }, { "epoch": 61.06, "learning_rate": 3.7429264573731024e-05, "loss": 0.0078, "step": 254200 }, { "epoch": 61.06, "learning_rate": 3.742579033397004e-05, "loss": 0.0058, "step": 254210 }, { "epoch": 61.06, "learning_rate": 3.742231615901663e-05, "loss": 0.0021, "step": 254220 }, { "epoch": 61.07, "learning_rate": 3.7418842048888726e-05, "loss": 0.0109, "step": 254230 }, { "epoch": 61.07, "learning_rate": 3.741536800360421e-05, "loss": 0.0034, "step": 254240 }, { "epoch": 61.07, "learning_rate": 3.741189402318099e-05, "loss": 0.0025, "step": 254250 }, { "epoch": 61.07, "learning_rate": 3.7408420107636977e-05, "loss": 0.003, "step": 254260 }, { "epoch": 61.07, "learning_rate": 3.740494625699008e-05, "loss": 0.0029, "step": 254270 }, { "epoch": 61.08, "learning_rate": 3.740147247125817e-05, "loss": 0.0025, "step": 254280 }, { "epoch": 61.08, "learning_rate": 3.739799875045921e-05, "loss": 0.0021, "step": 254290 }, { "epoch": 61.08, "learning_rate": 3.739452509461103e-05, "loss": 0.0045, "step": 254300 }, { "epoch": 61.08, "learning_rate": 3.739105150373161e-05, "loss": 0.0017, "step": 254310 }, { "epoch": 61.09, "learning_rate": 3.7387577977838786e-05, "loss": 0.0037, "step": 254320 }, { "epoch": 61.09, "learning_rate": 3.7384104516950514e-05, "loss": 0.0066, "step": 254330 }, { "epoch": 61.09, "learning_rate": 3.738063112108467e-05, "loss": 0.0019, "step": 254340 }, { "epoch": 61.09, "learning_rate": 3.737715779025915e-05, "loss": 0.002, "step": 254350 }, { "epoch": 61.1, "learning_rate": 3.7373684524491875e-05, "loss": 0.0034, "step": 254360 }, { "epoch": 61.1, "learning_rate": 3.737021132380071e-05, "loss": 0.0021, "step": 254370 }, { "epoch": 61.1, "learning_rate": 3.7366738188203606e-05, "loss": 0.0054, "step": 254380 }, { "epoch": 61.1, "learning_rate": 3.736326511771843e-05, "loss": 0.0034, "step": 254390 }, { "epoch": 61.1, "learning_rate": 3.735979211236309e-05, "loss": 0.0037, "step": 254400 }, { "epoch": 61.11, "learning_rate": 3.7356319172155495e-05, "loss": 0.0024, "step": 254410 }, { "epoch": 61.11, "learning_rate": 3.735284629711353e-05, "loss": 0.002, "step": 254420 }, { "epoch": 61.11, "learning_rate": 3.7349373487255105e-05, "loss": 0.0063, "step": 254430 }, { "epoch": 61.11, "learning_rate": 3.7345900742598106e-05, "loss": 0.0021, "step": 254440 }, { "epoch": 61.12, "learning_rate": 3.734242806316045e-05, "loss": 0.0027, "step": 254450 }, { "epoch": 61.12, "learning_rate": 3.733895544896001e-05, "loss": 0.0019, "step": 254460 }, { "epoch": 61.12, "learning_rate": 3.733548290001473e-05, "loss": 0.0031, "step": 254470 }, { "epoch": 61.12, "learning_rate": 3.7332010416342465e-05, "loss": 0.0022, "step": 254480 }, { "epoch": 61.12, "learning_rate": 3.732853799796111e-05, "loss": 0.0038, "step": 254490 }, { "epoch": 61.13, "learning_rate": 3.732506564488859e-05, "loss": 0.0021, "step": 254500 }, { "epoch": 61.13, "learning_rate": 3.732159335714277e-05, "loss": 0.0024, "step": 254510 }, { "epoch": 61.13, "learning_rate": 3.7318121134741585e-05, "loss": 0.0047, "step": 254520 }, { "epoch": 61.13, "learning_rate": 3.7314648977702885e-05, "loss": 0.0028, "step": 254530 }, { "epoch": 61.14, "learning_rate": 3.7311176886044605e-05, "loss": 0.0031, "step": 254540 }, { "epoch": 61.14, "learning_rate": 3.7307704859784635e-05, "loss": 0.0025, "step": 254550 }, { "epoch": 61.14, "learning_rate": 3.7304232898940836e-05, "loss": 0.004, "step": 254560 }, { "epoch": 61.14, "learning_rate": 3.730076100353116e-05, "loss": 0.0028, "step": 254570 }, { "epoch": 61.15, "learning_rate": 3.729728917357344e-05, "loss": 0.0024, "step": 254580 }, { "epoch": 61.15, "learning_rate": 3.729381740908561e-05, "loss": 0.0018, "step": 254590 }, { "epoch": 61.15, "learning_rate": 3.729034571008554e-05, "loss": 0.0045, "step": 254600 }, { "epoch": 61.15, "learning_rate": 3.728687407659115e-05, "loss": 0.0132, "step": 254610 }, { "epoch": 61.15, "learning_rate": 3.72834025086203e-05, "loss": 0.002, "step": 254620 }, { "epoch": 61.16, "learning_rate": 3.727993100619092e-05, "loss": 0.0035, "step": 254630 }, { "epoch": 61.16, "learning_rate": 3.7276459569320886e-05, "loss": 0.0029, "step": 254640 }, { "epoch": 61.16, "learning_rate": 3.727298819802806e-05, "loss": 0.0019, "step": 254650 }, { "epoch": 61.16, "learning_rate": 3.726951689233038e-05, "loss": 0.0033, "step": 254660 }, { "epoch": 61.17, "learning_rate": 3.7266045652245695e-05, "loss": 0.0029, "step": 254670 }, { "epoch": 61.17, "learning_rate": 3.726257447779194e-05, "loss": 0.0312, "step": 254680 }, { "epoch": 61.17, "learning_rate": 3.725910336898696e-05, "loss": 0.0055, "step": 254690 }, { "epoch": 61.17, "learning_rate": 3.725563232584868e-05, "loss": 0.0022, "step": 254700 }, { "epoch": 61.18, "learning_rate": 3.725216134839499e-05, "loss": 0.0027, "step": 254710 }, { "epoch": 61.18, "learning_rate": 3.7248690436643743e-05, "loss": 0.0024, "step": 254720 }, { "epoch": 61.18, "learning_rate": 3.7245219590612864e-05, "loss": 0.0019, "step": 254730 }, { "epoch": 61.18, "learning_rate": 3.724174881032022e-05, "loss": 0.0024, "step": 254740 }, { "epoch": 61.18, "learning_rate": 3.723827809578373e-05, "loss": 0.0064, "step": 254750 }, { "epoch": 61.19, "learning_rate": 3.7234807447021235e-05, "loss": 0.0022, "step": 254760 }, { "epoch": 61.19, "learning_rate": 3.723133686405068e-05, "loss": 0.0076, "step": 254770 }, { "epoch": 61.19, "learning_rate": 3.722786634688992e-05, "loss": 0.0022, "step": 254780 }, { "epoch": 61.19, "learning_rate": 3.722439589555681e-05, "loss": 0.0021, "step": 254790 }, { "epoch": 61.2, "learning_rate": 3.72209255100693e-05, "loss": 0.0025, "step": 254800 }, { "epoch": 61.2, "learning_rate": 3.7217455190445225e-05, "loss": 0.0026, "step": 254810 }, { "epoch": 61.2, "learning_rate": 3.7213984936702514e-05, "loss": 0.0021, "step": 254820 }, { "epoch": 61.2, "learning_rate": 3.721051474885901e-05, "loss": 0.0024, "step": 254830 }, { "epoch": 61.2, "learning_rate": 3.720704462693264e-05, "loss": 0.0023, "step": 254840 }, { "epoch": 61.21, "learning_rate": 3.720357457094126e-05, "loss": 0.0031, "step": 254850 }, { "epoch": 61.21, "learning_rate": 3.720010458090275e-05, "loss": 0.0024, "step": 254860 }, { "epoch": 61.21, "learning_rate": 3.7196634656835035e-05, "loss": 0.0035, "step": 254870 }, { "epoch": 61.21, "learning_rate": 3.719316479875595e-05, "loss": 0.003, "step": 254880 }, { "epoch": 61.22, "learning_rate": 3.7189695006683416e-05, "loss": 0.0022, "step": 254890 }, { "epoch": 61.22, "learning_rate": 3.7186225280635285e-05, "loss": 0.0025, "step": 254900 }, { "epoch": 61.22, "learning_rate": 3.718275562062947e-05, "loss": 0.003, "step": 254910 }, { "epoch": 61.22, "learning_rate": 3.717928602668385e-05, "loss": 0.0074, "step": 254920 }, { "epoch": 61.23, "learning_rate": 3.7175816498816274e-05, "loss": 0.0026, "step": 254930 }, { "epoch": 61.23, "learning_rate": 3.7172347037044666e-05, "loss": 0.0024, "step": 254940 }, { "epoch": 61.23, "learning_rate": 3.716887764138686e-05, "loss": 0.0046, "step": 254950 }, { "epoch": 61.23, "learning_rate": 3.71654083118608e-05, "loss": 0.0019, "step": 254960 }, { "epoch": 61.23, "learning_rate": 3.71619390484843e-05, "loss": 0.0021, "step": 254970 }, { "epoch": 61.24, "learning_rate": 3.7158469851275304e-05, "loss": 0.0024, "step": 254980 }, { "epoch": 61.24, "learning_rate": 3.7155000720251643e-05, "loss": 0.0022, "step": 254990 }, { "epoch": 61.24, "learning_rate": 3.7151531655431204e-05, "loss": 0.0055, "step": 255000 }, { "epoch": 61.24, "learning_rate": 3.71480626568319e-05, "loss": 0.0019, "step": 255010 }, { "epoch": 61.25, "learning_rate": 3.714459372447158e-05, "loss": 0.0035, "step": 255020 }, { "epoch": 61.25, "learning_rate": 3.714112485836815e-05, "loss": 0.0025, "step": 255030 }, { "epoch": 61.25, "learning_rate": 3.713765605853944e-05, "loss": 0.0035, "step": 255040 }, { "epoch": 61.25, "learning_rate": 3.7134187325003376e-05, "loss": 0.0031, "step": 255050 }, { "epoch": 61.26, "learning_rate": 3.713071865777783e-05, "loss": 0.0022, "step": 255060 }, { "epoch": 61.26, "learning_rate": 3.712725005688064e-05, "loss": 0.002, "step": 255070 }, { "epoch": 61.26, "learning_rate": 3.712378152232974e-05, "loss": 0.0022, "step": 255080 }, { "epoch": 61.26, "learning_rate": 3.712031305414294e-05, "loss": 0.0026, "step": 255090 }, { "epoch": 61.26, "learning_rate": 3.7116844652338186e-05, "loss": 0.0022, "step": 255100 }, { "epoch": 61.27, "learning_rate": 3.71133763169333e-05, "loss": 0.0032, "step": 255110 }, { "epoch": 61.27, "learning_rate": 3.71099080479462e-05, "loss": 0.0037, "step": 255120 }, { "epoch": 61.27, "learning_rate": 3.710643984539474e-05, "loss": 0.0036, "step": 255130 }, { "epoch": 61.27, "learning_rate": 3.7102971709296785e-05, "loss": 0.0033, "step": 255140 }, { "epoch": 61.28, "learning_rate": 3.709950363967022e-05, "loss": 0.003, "step": 255150 }, { "epoch": 61.28, "learning_rate": 3.709603563653292e-05, "loss": 0.0069, "step": 255160 }, { "epoch": 61.28, "learning_rate": 3.709256769990278e-05, "loss": 0.0036, "step": 255170 }, { "epoch": 61.28, "learning_rate": 3.708909982979763e-05, "loss": 0.0028, "step": 255180 }, { "epoch": 61.28, "learning_rate": 3.7085632026235386e-05, "loss": 0.0042, "step": 255190 }, { "epoch": 61.29, "learning_rate": 3.708216428923391e-05, "loss": 0.0018, "step": 255200 }, { "epoch": 61.29, "learning_rate": 3.7078696618811036e-05, "loss": 0.0051, "step": 255210 }, { "epoch": 61.29, "learning_rate": 3.70752290149847e-05, "loss": 0.0024, "step": 255220 }, { "epoch": 61.29, "learning_rate": 3.7071761477772715e-05, "loss": 0.003, "step": 255230 }, { "epoch": 61.3, "learning_rate": 3.706829400719299e-05, "loss": 0.0031, "step": 255240 }, { "epoch": 61.3, "learning_rate": 3.706482660326338e-05, "loss": 0.0028, "step": 255250 }, { "epoch": 61.3, "learning_rate": 3.7061359266001785e-05, "loss": 0.0029, "step": 255260 }, { "epoch": 61.3, "learning_rate": 3.705789199542603e-05, "loss": 0.002, "step": 255270 }, { "epoch": 61.31, "learning_rate": 3.705442479155401e-05, "loss": 0.0029, "step": 255280 }, { "epoch": 61.31, "learning_rate": 3.70509576544036e-05, "loss": 0.0034, "step": 255290 }, { "epoch": 61.31, "learning_rate": 3.704749058399266e-05, "loss": 0.0024, "step": 255300 }, { "epoch": 61.31, "learning_rate": 3.704402358033906e-05, "loss": 0.0026, "step": 255310 }, { "epoch": 61.31, "learning_rate": 3.704055664346065e-05, "loss": 0.0018, "step": 255320 }, { "epoch": 61.32, "learning_rate": 3.703708977337536e-05, "loss": 0.0024, "step": 255330 }, { "epoch": 61.32, "learning_rate": 3.7033622970101004e-05, "loss": 0.0024, "step": 255340 }, { "epoch": 61.32, "learning_rate": 3.703015623365545e-05, "loss": 0.0028, "step": 255350 }, { "epoch": 61.32, "learning_rate": 3.702668956405659e-05, "loss": 0.0022, "step": 255360 }, { "epoch": 61.33, "learning_rate": 3.702322296132227e-05, "loss": 0.0023, "step": 255370 }, { "epoch": 61.33, "learning_rate": 3.701975642547039e-05, "loss": 0.002, "step": 255380 }, { "epoch": 61.33, "learning_rate": 3.701628995651877e-05, "loss": 0.0042, "step": 255390 }, { "epoch": 61.33, "learning_rate": 3.701282355448531e-05, "loss": 0.0022, "step": 255400 }, { "epoch": 61.34, "learning_rate": 3.7009357219387856e-05, "loss": 0.0021, "step": 255410 }, { "epoch": 61.34, "learning_rate": 3.70058909512443e-05, "loss": 0.0026, "step": 255420 }, { "epoch": 61.34, "learning_rate": 3.7002424750072485e-05, "loss": 0.0027, "step": 255430 }, { "epoch": 61.34, "learning_rate": 3.699895861589028e-05, "loss": 0.0024, "step": 255440 }, { "epoch": 61.34, "learning_rate": 3.6995492548715546e-05, "loss": 0.0032, "step": 255450 }, { "epoch": 61.35, "learning_rate": 3.699202654856616e-05, "loss": 0.0027, "step": 255460 }, { "epoch": 61.35, "learning_rate": 3.698856061545997e-05, "loss": 0.0021, "step": 255470 }, { "epoch": 61.35, "learning_rate": 3.698509474941484e-05, "loss": 0.0022, "step": 255480 }, { "epoch": 61.35, "learning_rate": 3.6981628950448665e-05, "loss": 0.0023, "step": 255490 }, { "epoch": 61.36, "learning_rate": 3.697816321857928e-05, "loss": 0.002, "step": 255500 }, { "epoch": 61.36, "learning_rate": 3.697469755382453e-05, "loss": 0.0027, "step": 255510 }, { "epoch": 61.36, "learning_rate": 3.6971231956202315e-05, "loss": 0.0027, "step": 255520 }, { "epoch": 61.36, "learning_rate": 3.6967766425730464e-05, "loss": 0.0018, "step": 255530 }, { "epoch": 61.36, "learning_rate": 3.6964300962426876e-05, "loss": 0.0033, "step": 255540 }, { "epoch": 61.37, "learning_rate": 3.6960835566309365e-05, "loss": 0.0032, "step": 255550 }, { "epoch": 61.37, "learning_rate": 3.695737023739584e-05, "loss": 0.0021, "step": 255560 }, { "epoch": 61.37, "learning_rate": 3.6953904975704126e-05, "loss": 0.0028, "step": 255570 }, { "epoch": 61.37, "learning_rate": 3.695043978125209e-05, "loss": 0.0071, "step": 255580 }, { "epoch": 61.38, "learning_rate": 3.69469746540576e-05, "loss": 0.0028, "step": 255590 }, { "epoch": 61.38, "learning_rate": 3.6943509594138516e-05, "loss": 0.0036, "step": 255600 }, { "epoch": 61.38, "learning_rate": 3.6940044601512684e-05, "loss": 0.0024, "step": 255610 }, { "epoch": 61.38, "learning_rate": 3.693657967619798e-05, "loss": 0.0028, "step": 255620 }, { "epoch": 61.39, "learning_rate": 3.693311481821225e-05, "loss": 0.0054, "step": 255630 }, { "epoch": 61.39, "learning_rate": 3.6929650027573365e-05, "loss": 0.0028, "step": 255640 }, { "epoch": 61.39, "learning_rate": 3.692618530429915e-05, "loss": 0.0056, "step": 255650 }, { "epoch": 61.39, "learning_rate": 3.692272064840751e-05, "loss": 0.003, "step": 255660 }, { "epoch": 61.39, "learning_rate": 3.6919256059916255e-05, "loss": 0.0034, "step": 255670 }, { "epoch": 61.4, "learning_rate": 3.691579153884329e-05, "loss": 0.0023, "step": 255680 }, { "epoch": 61.4, "learning_rate": 3.691232708520641e-05, "loss": 0.0028, "step": 255690 }, { "epoch": 61.4, "learning_rate": 3.690886269902354e-05, "loss": 0.0028, "step": 255700 }, { "epoch": 61.4, "learning_rate": 3.6905398380312496e-05, "loss": 0.003, "step": 255710 }, { "epoch": 61.41, "learning_rate": 3.690193412909112e-05, "loss": 0.002, "step": 255720 }, { "epoch": 61.41, "learning_rate": 3.689846994537729e-05, "loss": 0.0026, "step": 255730 }, { "epoch": 61.41, "learning_rate": 3.6895005829188855e-05, "loss": 0.0028, "step": 255740 }, { "epoch": 61.41, "learning_rate": 3.6891541780543676e-05, "loss": 0.0021, "step": 255750 }, { "epoch": 61.42, "learning_rate": 3.68880777994596e-05, "loss": 0.0021, "step": 255760 }, { "epoch": 61.42, "learning_rate": 3.6884613885954475e-05, "loss": 0.002, "step": 255770 }, { "epoch": 61.42, "learning_rate": 3.688115004004618e-05, "loss": 0.0041, "step": 255780 }, { "epoch": 61.42, "learning_rate": 3.687768626175251e-05, "loss": 0.006, "step": 255790 }, { "epoch": 61.42, "learning_rate": 3.6874222551091386e-05, "loss": 0.0023, "step": 255800 }, { "epoch": 61.43, "learning_rate": 3.68707589080806e-05, "loss": 0.0028, "step": 255810 }, { "epoch": 61.43, "learning_rate": 3.686729533273807e-05, "loss": 0.0023, "step": 255820 }, { "epoch": 61.43, "learning_rate": 3.6863831825081576e-05, "loss": 0.0028, "step": 255830 }, { "epoch": 61.43, "learning_rate": 3.686036838512903e-05, "loss": 0.0029, "step": 255840 }, { "epoch": 61.44, "learning_rate": 3.685690501289825e-05, "loss": 0.0025, "step": 255850 }, { "epoch": 61.44, "learning_rate": 3.685344170840707e-05, "loss": 0.0024, "step": 255860 }, { "epoch": 61.44, "learning_rate": 3.684997847167339e-05, "loss": 0.002, "step": 255870 }, { "epoch": 61.44, "learning_rate": 3.6846515302714994e-05, "loss": 0.0026, "step": 255880 }, { "epoch": 61.44, "learning_rate": 3.684305220154979e-05, "loss": 0.003, "step": 255890 }, { "epoch": 61.45, "learning_rate": 3.6839589168195605e-05, "loss": 0.0126, "step": 255900 }, { "epoch": 61.45, "learning_rate": 3.683612620267029e-05, "loss": 0.0039, "step": 255910 }, { "epoch": 61.45, "learning_rate": 3.683266330499169e-05, "loss": 0.0022, "step": 255920 }, { "epoch": 61.45, "learning_rate": 3.682920047517764e-05, "loss": 0.0023, "step": 255930 }, { "epoch": 61.46, "learning_rate": 3.682573771324602e-05, "loss": 0.0028, "step": 255940 }, { "epoch": 61.46, "learning_rate": 3.682227501921464e-05, "loss": 0.0023, "step": 255950 }, { "epoch": 61.46, "learning_rate": 3.6818812393101384e-05, "loss": 0.0146, "step": 255960 }, { "epoch": 61.46, "learning_rate": 3.6815349834924056e-05, "loss": 0.003, "step": 255970 }, { "epoch": 61.47, "learning_rate": 3.681188734470055e-05, "loss": 0.0034, "step": 255980 }, { "epoch": 61.47, "learning_rate": 3.680842492244868e-05, "loss": 0.0019, "step": 255990 }, { "epoch": 61.47, "learning_rate": 3.6804962568186286e-05, "loss": 0.0038, "step": 256000 }, { "epoch": 61.47, "learning_rate": 3.680150028193125e-05, "loss": 0.0028, "step": 256010 }, { "epoch": 61.47, "learning_rate": 3.6798038063701356e-05, "loss": 0.0029, "step": 256020 }, { "epoch": 61.48, "learning_rate": 3.679457591351451e-05, "loss": 0.0021, "step": 256030 }, { "epoch": 61.48, "learning_rate": 3.6791113831388516e-05, "loss": 0.0021, "step": 256040 }, { "epoch": 61.48, "learning_rate": 3.678765181734124e-05, "loss": 0.0032, "step": 256050 }, { "epoch": 61.48, "learning_rate": 3.678418987139052e-05, "loss": 0.0019, "step": 256060 }, { "epoch": 61.49, "learning_rate": 3.6780727993554176e-05, "loss": 0.0047, "step": 256070 }, { "epoch": 61.49, "learning_rate": 3.67772661838501e-05, "loss": 0.0032, "step": 256080 }, { "epoch": 61.49, "learning_rate": 3.6773804442296076e-05, "loss": 0.0022, "step": 256090 }, { "epoch": 61.49, "learning_rate": 3.6770342768910005e-05, "loss": 0.006, "step": 256100 }, { "epoch": 61.5, "learning_rate": 3.6766881163709666e-05, "loss": 0.0029, "step": 256110 }, { "epoch": 61.5, "learning_rate": 3.6763419626712955e-05, "loss": 0.0031, "step": 256120 }, { "epoch": 61.5, "learning_rate": 3.6759958157937694e-05, "loss": 0.0021, "step": 256130 }, { "epoch": 61.5, "learning_rate": 3.67564967574017e-05, "loss": 0.0031, "step": 256140 }, { "epoch": 61.5, "learning_rate": 3.675303542512285e-05, "loss": 0.0027, "step": 256150 }, { "epoch": 61.51, "learning_rate": 3.674957416111894e-05, "loss": 0.0042, "step": 256160 }, { "epoch": 61.51, "learning_rate": 3.6746112965407865e-05, "loss": 0.0032, "step": 256170 }, { "epoch": 61.51, "learning_rate": 3.6742651838007414e-05, "loss": 0.0039, "step": 256180 }, { "epoch": 61.51, "learning_rate": 3.6739190778935464e-05, "loss": 0.002, "step": 256190 }, { "epoch": 61.52, "learning_rate": 3.673572978820982e-05, "loss": 0.0028, "step": 256200 }, { "epoch": 61.52, "learning_rate": 3.673226886584833e-05, "loss": 0.0028, "step": 256210 }, { "epoch": 61.52, "learning_rate": 3.672880801186886e-05, "loss": 0.0031, "step": 256220 }, { "epoch": 61.52, "learning_rate": 3.6725347226289196e-05, "loss": 0.004, "step": 256230 }, { "epoch": 61.52, "learning_rate": 3.672188650912723e-05, "loss": 0.0039, "step": 256240 }, { "epoch": 61.53, "learning_rate": 3.671842586040075e-05, "loss": 0.002, "step": 256250 }, { "epoch": 61.53, "learning_rate": 3.671496528012765e-05, "loss": 0.0031, "step": 256260 }, { "epoch": 61.53, "learning_rate": 3.671150476832569e-05, "loss": 0.0036, "step": 256270 }, { "epoch": 61.53, "learning_rate": 3.670804432501277e-05, "loss": 0.0029, "step": 256280 }, { "epoch": 61.54, "learning_rate": 3.67045839502067e-05, "loss": 0.0028, "step": 256290 }, { "epoch": 61.54, "learning_rate": 3.670112364392529e-05, "loss": 0.0032, "step": 256300 }, { "epoch": 61.54, "learning_rate": 3.6697663406186435e-05, "loss": 0.0033, "step": 256310 }, { "epoch": 61.54, "learning_rate": 3.66942032370079e-05, "loss": 0.0039, "step": 256320 }, { "epoch": 61.55, "learning_rate": 3.669074313640758e-05, "loss": 0.0038, "step": 256330 }, { "epoch": 61.55, "learning_rate": 3.668728310440326e-05, "loss": 0.0042, "step": 256340 }, { "epoch": 61.55, "learning_rate": 3.668382314101282e-05, "loss": 0.0026, "step": 256350 }, { "epoch": 61.55, "learning_rate": 3.668036324625405e-05, "loss": 0.0026, "step": 256360 }, { "epoch": 61.55, "learning_rate": 3.6676903420144784e-05, "loss": 0.0057, "step": 256370 }, { "epoch": 61.56, "learning_rate": 3.66734436627029e-05, "loss": 0.0024, "step": 256380 }, { "epoch": 61.56, "learning_rate": 3.666998397394617e-05, "loss": 0.0037, "step": 256390 }, { "epoch": 61.56, "learning_rate": 3.666652435389248e-05, "loss": 0.0024, "step": 256400 }, { "epoch": 61.56, "learning_rate": 3.666306480255961e-05, "loss": 0.0024, "step": 256410 }, { "epoch": 61.57, "learning_rate": 3.665960531996544e-05, "loss": 0.0033, "step": 256420 }, { "epoch": 61.57, "learning_rate": 3.665614590612777e-05, "loss": 0.0036, "step": 256430 }, { "epoch": 61.57, "learning_rate": 3.665268656106442e-05, "loss": 0.0025, "step": 256440 }, { "epoch": 61.57, "learning_rate": 3.6649227284793255e-05, "loss": 0.0065, "step": 256450 }, { "epoch": 61.58, "learning_rate": 3.664576807733207e-05, "loss": 0.0074, "step": 256460 }, { "epoch": 61.58, "learning_rate": 3.664230893869872e-05, "loss": 0.0027, "step": 256470 }, { "epoch": 61.58, "learning_rate": 3.6638849868910995e-05, "loss": 0.0024, "step": 256480 }, { "epoch": 61.58, "learning_rate": 3.6635390867986785e-05, "loss": 0.0021, "step": 256490 }, { "epoch": 61.58, "learning_rate": 3.6631931935943863e-05, "loss": 0.0048, "step": 256500 }, { "epoch": 61.59, "learning_rate": 3.662847307280007e-05, "loss": 0.0042, "step": 256510 }, { "epoch": 61.59, "learning_rate": 3.662501427857325e-05, "loss": 0.0024, "step": 256520 }, { "epoch": 61.59, "learning_rate": 3.662155555328121e-05, "loss": 0.0031, "step": 256530 }, { "epoch": 61.59, "learning_rate": 3.661809689694179e-05, "loss": 0.0026, "step": 256540 }, { "epoch": 61.6, "learning_rate": 3.66146383095728e-05, "loss": 0.0024, "step": 256550 }, { "epoch": 61.6, "learning_rate": 3.66111797911921e-05, "loss": 0.0059, "step": 256560 }, { "epoch": 61.6, "learning_rate": 3.660772134181748e-05, "loss": 0.0034, "step": 256570 }, { "epoch": 61.6, "learning_rate": 3.660426296146676e-05, "loss": 0.0048, "step": 256580 }, { "epoch": 61.6, "learning_rate": 3.6600804650157806e-05, "loss": 0.0027, "step": 256590 }, { "epoch": 61.61, "learning_rate": 3.6597346407908396e-05, "loss": 0.0032, "step": 256600 }, { "epoch": 61.61, "learning_rate": 3.6593888234736393e-05, "loss": 0.0021, "step": 256610 }, { "epoch": 61.61, "learning_rate": 3.659043013065958e-05, "loss": 0.0031, "step": 256620 }, { "epoch": 61.61, "learning_rate": 3.658697209569583e-05, "loss": 0.0033, "step": 256630 }, { "epoch": 61.62, "learning_rate": 3.6583514129862915e-05, "loss": 0.0045, "step": 256640 }, { "epoch": 61.62, "learning_rate": 3.658005623317869e-05, "loss": 0.0037, "step": 256650 }, { "epoch": 61.62, "learning_rate": 3.6576598405660964e-05, "loss": 0.0033, "step": 256660 }, { "epoch": 61.62, "learning_rate": 3.6573140647327556e-05, "loss": 0.0026, "step": 256670 }, { "epoch": 61.63, "learning_rate": 3.6569682958196305e-05, "loss": 0.0023, "step": 256680 }, { "epoch": 61.63, "learning_rate": 3.656622533828501e-05, "loss": 0.0022, "step": 256690 }, { "epoch": 61.63, "learning_rate": 3.656276778761151e-05, "loss": 0.003, "step": 256700 }, { "epoch": 61.63, "learning_rate": 3.655931030619363e-05, "loss": 0.0037, "step": 256710 }, { "epoch": 61.63, "learning_rate": 3.6555852894049146e-05, "loss": 0.0023, "step": 256720 }, { "epoch": 61.64, "learning_rate": 3.6552395551195935e-05, "loss": 0.0029, "step": 256730 }, { "epoch": 61.64, "learning_rate": 3.6548938277651765e-05, "loss": 0.0022, "step": 256740 }, { "epoch": 61.64, "learning_rate": 3.654548107343451e-05, "loss": 0.0027, "step": 256750 }, { "epoch": 61.64, "learning_rate": 3.6542023938561925e-05, "loss": 0.0025, "step": 256760 }, { "epoch": 61.65, "learning_rate": 3.6538566873051885e-05, "loss": 0.0024, "step": 256770 }, { "epoch": 61.65, "learning_rate": 3.653510987692218e-05, "loss": 0.0054, "step": 256780 }, { "epoch": 61.65, "learning_rate": 3.653165295019063e-05, "loss": 0.0019, "step": 256790 }, { "epoch": 61.65, "learning_rate": 3.6528196092875044e-05, "loss": 0.0043, "step": 256800 }, { "epoch": 61.66, "learning_rate": 3.6524739304993253e-05, "loss": 0.0019, "step": 256810 }, { "epoch": 61.66, "learning_rate": 3.652128258656307e-05, "loss": 0.0032, "step": 256820 }, { "epoch": 61.66, "learning_rate": 3.6517825937602304e-05, "loss": 0.0038, "step": 256830 }, { "epoch": 61.66, "learning_rate": 3.651436935812879e-05, "loss": 0.0051, "step": 256840 }, { "epoch": 61.66, "learning_rate": 3.651091284816033e-05, "loss": 0.0032, "step": 256850 }, { "epoch": 61.67, "learning_rate": 3.650745640771471e-05, "loss": 0.002, "step": 256860 }, { "epoch": 61.67, "learning_rate": 3.6504000036809804e-05, "loss": 0.003, "step": 256870 }, { "epoch": 61.67, "learning_rate": 3.650054373546337e-05, "loss": 0.0024, "step": 256880 }, { "epoch": 61.67, "learning_rate": 3.649708750369327e-05, "loss": 0.0027, "step": 256890 }, { "epoch": 61.68, "learning_rate": 3.649363134151727e-05, "loss": 0.003, "step": 256900 }, { "epoch": 61.68, "learning_rate": 3.649017524895323e-05, "loss": 0.0025, "step": 256910 }, { "epoch": 61.68, "learning_rate": 3.648671922601894e-05, "loss": 0.0023, "step": 256920 }, { "epoch": 61.68, "learning_rate": 3.6483263272732184e-05, "loss": 0.0029, "step": 256930 }, { "epoch": 61.68, "learning_rate": 3.6479807389110824e-05, "loss": 0.0025, "step": 256940 }, { "epoch": 61.69, "learning_rate": 3.647635157517264e-05, "loss": 0.0047, "step": 256950 }, { "epoch": 61.69, "learning_rate": 3.647289583093545e-05, "loss": 0.003, "step": 256960 }, { "epoch": 61.69, "learning_rate": 3.646944015641708e-05, "loss": 0.0024, "step": 256970 }, { "epoch": 61.69, "learning_rate": 3.6465984551635325e-05, "loss": 0.0024, "step": 256980 }, { "epoch": 61.7, "learning_rate": 3.6462529016608e-05, "loss": 0.0036, "step": 256990 }, { "epoch": 61.7, "learning_rate": 3.6459073551352906e-05, "loss": 0.0024, "step": 257000 }, { "epoch": 61.7, "learning_rate": 3.645561815588787e-05, "loss": 0.0058, "step": 257010 }, { "epoch": 61.7, "learning_rate": 3.645216283023067e-05, "loss": 0.0022, "step": 257020 }, { "epoch": 61.71, "learning_rate": 3.644870757439917e-05, "loss": 0.0028, "step": 257030 }, { "epoch": 61.71, "learning_rate": 3.6445252388411115e-05, "loss": 0.0023, "step": 257040 }, { "epoch": 61.71, "learning_rate": 3.6441797272284364e-05, "loss": 0.0024, "step": 257050 }, { "epoch": 61.71, "learning_rate": 3.643834222603668e-05, "loss": 0.0021, "step": 257060 }, { "epoch": 61.71, "learning_rate": 3.643488724968592e-05, "loss": 0.0025, "step": 257070 }, { "epoch": 61.72, "learning_rate": 3.643143234324986e-05, "loss": 0.0022, "step": 257080 }, { "epoch": 61.72, "learning_rate": 3.642797750674629e-05, "loss": 0.002, "step": 257090 }, { "epoch": 61.72, "learning_rate": 3.642452274019305e-05, "loss": 0.002, "step": 257100 }, { "epoch": 61.72, "learning_rate": 3.642106804360793e-05, "loss": 0.0031, "step": 257110 }, { "epoch": 61.73, "learning_rate": 3.6417613417008744e-05, "loss": 0.0043, "step": 257120 }, { "epoch": 61.73, "learning_rate": 3.6414158860413296e-05, "loss": 0.0033, "step": 257130 }, { "epoch": 61.73, "learning_rate": 3.641070437383938e-05, "loss": 0.0031, "step": 257140 }, { "epoch": 61.73, "learning_rate": 3.640724995730481e-05, "loss": 0.0019, "step": 257150 }, { "epoch": 61.74, "learning_rate": 3.640379561082737e-05, "loss": 0.0027, "step": 257160 }, { "epoch": 61.74, "learning_rate": 3.6400341334424915e-05, "loss": 0.0018, "step": 257170 }, { "epoch": 61.74, "learning_rate": 3.6396887128115185e-05, "loss": 0.0048, "step": 257180 }, { "epoch": 61.74, "learning_rate": 3.639343299191603e-05, "loss": 0.0025, "step": 257190 }, { "epoch": 61.74, "learning_rate": 3.638997892584522e-05, "loss": 0.003, "step": 257200 }, { "epoch": 61.75, "learning_rate": 3.638652492992059e-05, "loss": 0.0023, "step": 257210 }, { "epoch": 61.75, "learning_rate": 3.638307100415992e-05, "loss": 0.0048, "step": 257220 }, { "epoch": 61.75, "learning_rate": 3.6379617148581e-05, "loss": 0.0026, "step": 257230 }, { "epoch": 61.75, "learning_rate": 3.637616336320167e-05, "loss": 0.0096, "step": 257240 }, { "epoch": 61.76, "learning_rate": 3.637270964803969e-05, "loss": 0.0024, "step": 257250 }, { "epoch": 61.76, "learning_rate": 3.6369256003112884e-05, "loss": 0.0027, "step": 257260 }, { "epoch": 61.76, "learning_rate": 3.6365802428439045e-05, "loss": 0.0023, "step": 257270 }, { "epoch": 61.76, "learning_rate": 3.6362348924035974e-05, "loss": 0.0037, "step": 257280 }, { "epoch": 61.76, "learning_rate": 3.6358895489921486e-05, "loss": 0.0025, "step": 257290 }, { "epoch": 61.77, "learning_rate": 3.6355442126113335e-05, "loss": 0.0021, "step": 257300 }, { "epoch": 61.77, "learning_rate": 3.635198883262938e-05, "loss": 0.0025, "step": 257310 }, { "epoch": 61.77, "learning_rate": 3.6348535609487357e-05, "loss": 0.0023, "step": 257320 }, { "epoch": 61.77, "learning_rate": 3.6345082456705125e-05, "loss": 0.0023, "step": 257330 }, { "epoch": 61.78, "learning_rate": 3.634162937430043e-05, "loss": 0.0022, "step": 257340 }, { "epoch": 61.78, "learning_rate": 3.633817636229111e-05, "loss": 0.0037, "step": 257350 }, { "epoch": 61.78, "learning_rate": 3.6334723420694945e-05, "loss": 0.0025, "step": 257360 }, { "epoch": 61.78, "learning_rate": 3.633127054952971e-05, "loss": 0.0027, "step": 257370 }, { "epoch": 61.79, "learning_rate": 3.6327817748813244e-05, "loss": 0.0022, "step": 257380 }, { "epoch": 61.79, "learning_rate": 3.632436501856329e-05, "loss": 0.002, "step": 257390 }, { "epoch": 61.79, "learning_rate": 3.632091235879769e-05, "loss": 0.0022, "step": 257400 }, { "epoch": 61.79, "learning_rate": 3.631745976953422e-05, "loss": 0.0025, "step": 257410 }, { "epoch": 61.79, "learning_rate": 3.631400725079067e-05, "loss": 0.0023, "step": 257420 }, { "epoch": 61.8, "learning_rate": 3.6310554802584865e-05, "loss": 0.0085, "step": 257430 }, { "epoch": 61.8, "learning_rate": 3.6307102424934545e-05, "loss": 0.0051, "step": 257440 }, { "epoch": 61.8, "learning_rate": 3.630365011785756e-05, "loss": 0.002, "step": 257450 }, { "epoch": 61.8, "learning_rate": 3.630019788137165e-05, "loss": 0.0057, "step": 257460 }, { "epoch": 61.81, "learning_rate": 3.6296745715494664e-05, "loss": 0.0026, "step": 257470 }, { "epoch": 61.81, "learning_rate": 3.629329362024433e-05, "loss": 0.0017, "step": 257480 }, { "epoch": 61.81, "learning_rate": 3.6289841595638507e-05, "loss": 0.0026, "step": 257490 }, { "epoch": 61.81, "learning_rate": 3.628638964169495e-05, "loss": 0.0117, "step": 257500 }, { "epoch": 61.82, "learning_rate": 3.628293775843144e-05, "loss": 0.0023, "step": 257510 }, { "epoch": 61.82, "learning_rate": 3.62794859458658e-05, "loss": 0.0027, "step": 257520 }, { "epoch": 61.82, "learning_rate": 3.627603420401578e-05, "loss": 0.0032, "step": 257530 }, { "epoch": 61.82, "learning_rate": 3.6272582532899225e-05, "loss": 0.002, "step": 257540 }, { "epoch": 61.82, "learning_rate": 3.6269130932533866e-05, "loss": 0.0031, "step": 257550 }, { "epoch": 61.83, "learning_rate": 3.6265679402937534e-05, "loss": 0.003, "step": 257560 }, { "epoch": 61.83, "learning_rate": 3.626222794412802e-05, "loss": 0.0028, "step": 257570 }, { "epoch": 61.83, "learning_rate": 3.625877655612307e-05, "loss": 0.0025, "step": 257580 }, { "epoch": 61.83, "learning_rate": 3.625532523894053e-05, "loss": 0.0029, "step": 257590 }, { "epoch": 61.84, "learning_rate": 3.625187399259813e-05, "loss": 0.0022, "step": 257600 }, { "epoch": 61.84, "learning_rate": 3.624842281711371e-05, "loss": 0.0022, "step": 257610 }, { "epoch": 61.84, "learning_rate": 3.624497171250501e-05, "loss": 0.0031, "step": 257620 }, { "epoch": 61.84, "learning_rate": 3.6241520678789866e-05, "loss": 0.0026, "step": 257630 }, { "epoch": 61.84, "learning_rate": 3.623806971598604e-05, "loss": 0.0027, "step": 257640 }, { "epoch": 61.85, "learning_rate": 3.623461882411129e-05, "loss": 0.0024, "step": 257650 }, { "epoch": 61.85, "learning_rate": 3.6231168003183454e-05, "loss": 0.0022, "step": 257660 }, { "epoch": 61.85, "learning_rate": 3.6227717253220275e-05, "loss": 0.0022, "step": 257670 }, { "epoch": 61.85, "learning_rate": 3.6224266574239575e-05, "loss": 0.0025, "step": 257680 }, { "epoch": 61.86, "learning_rate": 3.6220815966259094e-05, "loss": 0.0029, "step": 257690 }, { "epoch": 61.86, "learning_rate": 3.621736542929667e-05, "loss": 0.0026, "step": 257700 }, { "epoch": 61.86, "learning_rate": 3.621391496337005e-05, "loss": 0.0028, "step": 257710 }, { "epoch": 61.86, "learning_rate": 3.6210464568497015e-05, "loss": 0.007, "step": 257720 }, { "epoch": 61.87, "learning_rate": 3.620701424469538e-05, "loss": 0.0022, "step": 257730 }, { "epoch": 61.87, "learning_rate": 3.620356399198289e-05, "loss": 0.003, "step": 257740 }, { "epoch": 61.87, "learning_rate": 3.620011381037737e-05, "loss": 0.0026, "step": 257750 }, { "epoch": 61.87, "learning_rate": 3.619666369989655e-05, "loss": 0.003, "step": 257760 }, { "epoch": 61.87, "learning_rate": 3.6193213660558264e-05, "loss": 0.0055, "step": 257770 }, { "epoch": 61.88, "learning_rate": 3.618976369238028e-05, "loss": 0.0046, "step": 257780 }, { "epoch": 61.88, "learning_rate": 3.618631379538034e-05, "loss": 0.0022, "step": 257790 }, { "epoch": 61.88, "learning_rate": 3.6182863969576274e-05, "loss": 0.0022, "step": 257800 }, { "epoch": 61.88, "learning_rate": 3.617941421498583e-05, "loss": 0.0089, "step": 257810 }, { "epoch": 61.89, "learning_rate": 3.6175964531626814e-05, "loss": 0.0073, "step": 257820 }, { "epoch": 61.89, "learning_rate": 3.6172514919516977e-05, "loss": 0.0023, "step": 257830 }, { "epoch": 61.89, "learning_rate": 3.6169065378674126e-05, "loss": 0.0039, "step": 257840 }, { "epoch": 61.89, "learning_rate": 3.6165615909116016e-05, "loss": 0.0023, "step": 257850 }, { "epoch": 61.9, "learning_rate": 3.616216651086045e-05, "loss": 0.0021, "step": 257860 }, { "epoch": 61.9, "learning_rate": 3.615871718392519e-05, "loss": 0.0042, "step": 257870 }, { "epoch": 61.9, "learning_rate": 3.6155267928328004e-05, "loss": 0.0038, "step": 257880 }, { "epoch": 61.9, "learning_rate": 3.61518187440867e-05, "loss": 0.0038, "step": 257890 }, { "epoch": 61.9, "learning_rate": 3.614836963121902e-05, "loss": 0.0025, "step": 257900 }, { "epoch": 61.91, "learning_rate": 3.614492058974278e-05, "loss": 0.0027, "step": 257910 }, { "epoch": 61.91, "learning_rate": 3.614147161967572e-05, "loss": 0.0027, "step": 257920 }, { "epoch": 61.91, "learning_rate": 3.613802272103564e-05, "loss": 0.0021, "step": 257930 }, { "epoch": 61.91, "learning_rate": 3.613457389384032e-05, "loss": 0.0054, "step": 257940 }, { "epoch": 61.92, "learning_rate": 3.6131125138107494e-05, "loss": 0.0061, "step": 257950 }, { "epoch": 61.92, "learning_rate": 3.612767645385498e-05, "loss": 0.0037, "step": 257960 }, { "epoch": 61.92, "learning_rate": 3.612422784110052e-05, "loss": 0.0026, "step": 257970 }, { "epoch": 61.92, "learning_rate": 3.612077929986193e-05, "loss": 0.0028, "step": 257980 }, { "epoch": 61.92, "learning_rate": 3.611733083015694e-05, "loss": 0.0025, "step": 257990 }, { "epoch": 61.93, "learning_rate": 3.611388243200337e-05, "loss": 0.0018, "step": 258000 }, { "epoch": 61.93, "learning_rate": 3.611043410541894e-05, "loss": 0.0022, "step": 258010 }, { "epoch": 61.93, "learning_rate": 3.610698585042146e-05, "loss": 0.0034, "step": 258020 }, { "epoch": 61.93, "learning_rate": 3.610353766702869e-05, "loss": 0.002, "step": 258030 }, { "epoch": 61.94, "learning_rate": 3.610008955525838e-05, "loss": 0.0022, "step": 258040 }, { "epoch": 61.94, "learning_rate": 3.609664151512836e-05, "loss": 0.0025, "step": 258050 }, { "epoch": 61.94, "learning_rate": 3.609319354665634e-05, "loss": 0.0039, "step": 258060 }, { "epoch": 61.94, "learning_rate": 3.6089745649860134e-05, "loss": 0.0026, "step": 258070 }, { "epoch": 61.95, "learning_rate": 3.60862978247575e-05, "loss": 0.0025, "step": 258080 }, { "epoch": 61.95, "learning_rate": 3.608285007136618e-05, "loss": 0.0024, "step": 258090 }, { "epoch": 61.95, "learning_rate": 3.6079402389703993e-05, "loss": 0.0021, "step": 258100 }, { "epoch": 62.0, "learning_rate": 3.6075954779788654e-05, "loss": 0.0024, "step": 258110 }, { "epoch": 62.0, "learning_rate": 3.6072507241637984e-05, "loss": 0.0019, "step": 258120 }, { "epoch": 62.01, "learning_rate": 3.606905977526971e-05, "loss": 0.0023, "step": 258130 }, { "epoch": 62.01, "learning_rate": 3.6065612380701643e-05, "loss": 0.0034, "step": 258140 }, { "epoch": 62.01, "learning_rate": 3.60621650579515e-05, "loss": 0.0028, "step": 258150 }, { "epoch": 62.01, "learning_rate": 3.605871780703709e-05, "loss": 0.0025, "step": 258160 }, { "epoch": 62.01, "learning_rate": 3.6055270627976164e-05, "loss": 0.0031, "step": 258170 }, { "epoch": 62.02, "learning_rate": 3.605182352078649e-05, "loss": 0.0039, "step": 258180 }, { "epoch": 62.02, "learning_rate": 3.6048376485485824e-05, "loss": 0.0025, "step": 258190 }, { "epoch": 62.02, "learning_rate": 3.604492952209194e-05, "loss": 0.0039, "step": 258200 }, { "epoch": 62.02, "learning_rate": 3.6041482630622624e-05, "loss": 0.003, "step": 258210 }, { "epoch": 62.03, "learning_rate": 3.603803581109562e-05, "loss": 0.0033, "step": 258220 }, { "epoch": 62.03, "learning_rate": 3.6034589063528676e-05, "loss": 0.0034, "step": 258230 }, { "epoch": 62.03, "learning_rate": 3.603114238793961e-05, "loss": 0.0027, "step": 258240 }, { "epoch": 62.03, "learning_rate": 3.602769578434611e-05, "loss": 0.0025, "step": 258250 }, { "epoch": 62.04, "learning_rate": 3.602424925276602e-05, "loss": 0.0068, "step": 258260 }, { "epoch": 62.04, "learning_rate": 3.6020802793217046e-05, "loss": 0.0019, "step": 258270 }, { "epoch": 62.04, "learning_rate": 3.601735640571698e-05, "loss": 0.0036, "step": 258280 }, { "epoch": 62.04, "learning_rate": 3.601391009028358e-05, "loss": 0.0025, "step": 258290 }, { "epoch": 62.04, "learning_rate": 3.601046384693459e-05, "loss": 0.0034, "step": 258300 }, { "epoch": 62.05, "learning_rate": 3.600701767568781e-05, "loss": 0.0057, "step": 258310 }, { "epoch": 62.05, "learning_rate": 3.600357157656096e-05, "loss": 0.0024, "step": 258320 }, { "epoch": 62.05, "learning_rate": 3.600012554957182e-05, "loss": 0.0052, "step": 258330 }, { "epoch": 62.05, "learning_rate": 3.599667959473815e-05, "loss": 0.0021, "step": 258340 }, { "epoch": 62.06, "learning_rate": 3.5993233712077705e-05, "loss": 0.0023, "step": 258350 }, { "epoch": 62.06, "learning_rate": 3.5989787901608266e-05, "loss": 0.002, "step": 258360 }, { "epoch": 62.06, "learning_rate": 3.598634216334756e-05, "loss": 0.0022, "step": 258370 }, { "epoch": 62.06, "learning_rate": 3.598289649731338e-05, "loss": 0.0019, "step": 258380 }, { "epoch": 62.06, "learning_rate": 3.597945090352345e-05, "loss": 0.0033, "step": 258390 }, { "epoch": 62.07, "learning_rate": 3.597600538199557e-05, "loss": 0.0019, "step": 258400 }, { "epoch": 62.07, "learning_rate": 3.597255993274745e-05, "loss": 0.0044, "step": 258410 }, { "epoch": 62.07, "learning_rate": 3.5969114555796903e-05, "loss": 0.0021, "step": 258420 }, { "epoch": 62.07, "learning_rate": 3.596566925116165e-05, "loss": 0.0036, "step": 258430 }, { "epoch": 62.08, "learning_rate": 3.596222401885943e-05, "loss": 0.0032, "step": 258440 }, { "epoch": 62.08, "learning_rate": 3.5958778858908036e-05, "loss": 0.0028, "step": 258450 }, { "epoch": 62.08, "learning_rate": 3.595533377132522e-05, "loss": 0.0032, "step": 258460 }, { "epoch": 62.08, "learning_rate": 3.5951888756128725e-05, "loss": 0.0021, "step": 258470 }, { "epoch": 62.09, "learning_rate": 3.594844381333632e-05, "loss": 0.0019, "step": 258480 }, { "epoch": 62.09, "learning_rate": 3.594499894296575e-05, "loss": 0.0024, "step": 258490 }, { "epoch": 62.09, "learning_rate": 3.5941554145034784e-05, "loss": 0.0021, "step": 258500 }, { "epoch": 62.09, "learning_rate": 3.593810941956114e-05, "loss": 0.0081, "step": 258510 }, { "epoch": 62.09, "learning_rate": 3.593466476656262e-05, "loss": 0.005, "step": 258520 }, { "epoch": 62.1, "learning_rate": 3.5931220186056933e-05, "loss": 0.0065, "step": 258530 }, { "epoch": 62.1, "learning_rate": 3.592777567806188e-05, "loss": 0.0026, "step": 258540 }, { "epoch": 62.1, "learning_rate": 3.5924331242595165e-05, "loss": 0.0031, "step": 258550 }, { "epoch": 62.1, "learning_rate": 3.592088687967459e-05, "loss": 0.0037, "step": 258560 }, { "epoch": 62.11, "learning_rate": 3.591744258931788e-05, "loss": 0.0039, "step": 258570 }, { "epoch": 62.11, "learning_rate": 3.5913998371542766e-05, "loss": 0.0027, "step": 258580 }, { "epoch": 62.11, "learning_rate": 3.5910554226367043e-05, "loss": 0.0025, "step": 258590 }, { "epoch": 62.11, "learning_rate": 3.590711015380842e-05, "loss": 0.0024, "step": 258600 }, { "epoch": 62.12, "learning_rate": 3.590366615388468e-05, "loss": 0.0051, "step": 258610 }, { "epoch": 62.12, "learning_rate": 3.590022222661356e-05, "loss": 0.0027, "step": 258620 }, { "epoch": 62.12, "learning_rate": 3.5896778372012816e-05, "loss": 0.0025, "step": 258630 }, { "epoch": 62.12, "learning_rate": 3.589333459010019e-05, "loss": 0.0025, "step": 258640 }, { "epoch": 62.12, "learning_rate": 3.588989088089344e-05, "loss": 0.0023, "step": 258650 }, { "epoch": 62.13, "learning_rate": 3.588644724441032e-05, "loss": 0.0024, "step": 258660 }, { "epoch": 62.13, "learning_rate": 3.5883003680668544e-05, "loss": 0.0026, "step": 258670 }, { "epoch": 62.13, "learning_rate": 3.587956018968591e-05, "loss": 0.003, "step": 258680 }, { "epoch": 62.13, "learning_rate": 3.587611677148012e-05, "loss": 0.0022, "step": 258690 }, { "epoch": 62.14, "learning_rate": 3.587267342606896e-05, "loss": 0.0024, "step": 258700 }, { "epoch": 62.14, "learning_rate": 3.5869230153470146e-05, "loss": 0.002, "step": 258710 }, { "epoch": 62.14, "learning_rate": 3.586578695370145e-05, "loss": 0.0036, "step": 258720 }, { "epoch": 62.14, "learning_rate": 3.586234382678061e-05, "loss": 0.0023, "step": 258730 }, { "epoch": 62.14, "learning_rate": 3.5858900772725345e-05, "loss": 0.0058, "step": 258740 }, { "epoch": 62.15, "learning_rate": 3.5855457791553446e-05, "loss": 0.0021, "step": 258750 }, { "epoch": 62.15, "learning_rate": 3.585201488328262e-05, "loss": 0.0023, "step": 258760 }, { "epoch": 62.15, "learning_rate": 3.584857204793063e-05, "loss": 0.0019, "step": 258770 }, { "epoch": 62.15, "learning_rate": 3.584512928551522e-05, "loss": 0.0029, "step": 258780 }, { "epoch": 62.16, "learning_rate": 3.584168659605414e-05, "loss": 0.0024, "step": 258790 }, { "epoch": 62.16, "learning_rate": 3.5838243979565126e-05, "loss": 0.0023, "step": 258800 }, { "epoch": 62.16, "learning_rate": 3.5834801436065904e-05, "loss": 0.0032, "step": 258810 }, { "epoch": 62.16, "learning_rate": 3.5831358965574255e-05, "loss": 0.0023, "step": 258820 }, { "epoch": 62.17, "learning_rate": 3.582791656810788e-05, "loss": 0.0021, "step": 258830 }, { "epoch": 62.17, "learning_rate": 3.582447424368456e-05, "loss": 0.002, "step": 258840 }, { "epoch": 62.17, "learning_rate": 3.5821031992321994e-05, "loss": 0.0017, "step": 258850 }, { "epoch": 62.17, "learning_rate": 3.5817589814037975e-05, "loss": 0.003, "step": 258860 }, { "epoch": 62.17, "learning_rate": 3.581414770885021e-05, "loss": 0.0027, "step": 258870 }, { "epoch": 62.18, "learning_rate": 3.581070567677644e-05, "loss": 0.0023, "step": 258880 }, { "epoch": 62.18, "learning_rate": 3.580726371783441e-05, "loss": 0.0021, "step": 258890 }, { "epoch": 62.18, "learning_rate": 3.5803821832041855e-05, "loss": 0.0027, "step": 258900 }, { "epoch": 62.18, "learning_rate": 3.580038001941654e-05, "loss": 0.0104, "step": 258910 }, { "epoch": 62.19, "learning_rate": 3.579693827997617e-05, "loss": 0.0027, "step": 258920 }, { "epoch": 62.19, "learning_rate": 3.5793496613738496e-05, "loss": 0.0027, "step": 258930 }, { "epoch": 62.19, "learning_rate": 3.579005502072128e-05, "loss": 0.0029, "step": 258940 }, { "epoch": 62.19, "learning_rate": 3.578661350094221e-05, "loss": 0.0019, "step": 258950 }, { "epoch": 62.2, "learning_rate": 3.578317205441908e-05, "loss": 0.0023, "step": 258960 }, { "epoch": 62.2, "learning_rate": 3.577973068116958e-05, "loss": 0.0026, "step": 258970 }, { "epoch": 62.2, "learning_rate": 3.577628938121148e-05, "loss": 0.0021, "step": 258980 }, { "epoch": 62.2, "learning_rate": 3.5772848154562495e-05, "loss": 0.0019, "step": 258990 }, { "epoch": 62.2, "learning_rate": 3.5769407001240384e-05, "loss": 0.0029, "step": 259000 }, { "epoch": 62.21, "learning_rate": 3.576596592126287e-05, "loss": 0.0025, "step": 259010 }, { "epoch": 62.21, "learning_rate": 3.576252491464766e-05, "loss": 0.0019, "step": 259020 }, { "epoch": 62.21, "learning_rate": 3.575908398141254e-05, "loss": 0.0023, "step": 259030 }, { "epoch": 62.21, "learning_rate": 3.57556431215752e-05, "loss": 0.0024, "step": 259040 }, { "epoch": 62.22, "learning_rate": 3.575220233515341e-05, "loss": 0.002, "step": 259050 }, { "epoch": 62.22, "learning_rate": 3.5748761622164876e-05, "loss": 0.0027, "step": 259060 }, { "epoch": 62.22, "learning_rate": 3.574532098262735e-05, "loss": 0.0028, "step": 259070 }, { "epoch": 62.22, "learning_rate": 3.574188041655857e-05, "loss": 0.0026, "step": 259080 }, { "epoch": 62.22, "learning_rate": 3.573843992397623e-05, "loss": 0.0019, "step": 259090 }, { "epoch": 62.23, "learning_rate": 3.573499950489812e-05, "loss": 0.0086, "step": 259100 }, { "epoch": 62.23, "learning_rate": 3.5731559159341923e-05, "loss": 0.0026, "step": 259110 }, { "epoch": 62.23, "learning_rate": 3.57281188873254e-05, "loss": 0.0023, "step": 259120 }, { "epoch": 62.23, "learning_rate": 3.5724678688866255e-05, "loss": 0.003, "step": 259130 }, { "epoch": 62.24, "learning_rate": 3.5721238563982255e-05, "loss": 0.0026, "step": 259140 }, { "epoch": 62.24, "learning_rate": 3.571779851269111e-05, "loss": 0.0031, "step": 259150 }, { "epoch": 62.24, "learning_rate": 3.5714358535010536e-05, "loss": 0.0033, "step": 259160 }, { "epoch": 62.24, "learning_rate": 3.57109186309583e-05, "loss": 0.0028, "step": 259170 }, { "epoch": 62.25, "learning_rate": 3.570747880055208e-05, "loss": 0.0018, "step": 259180 }, { "epoch": 62.25, "learning_rate": 3.570403904380966e-05, "loss": 0.0025, "step": 259190 }, { "epoch": 62.25, "learning_rate": 3.5700599360748716e-05, "loss": 0.0027, "step": 259200 }, { "epoch": 62.25, "learning_rate": 3.569715975138702e-05, "loss": 0.0023, "step": 259210 }, { "epoch": 62.25, "learning_rate": 3.569372021574228e-05, "loss": 0.0037, "step": 259220 }, { "epoch": 62.26, "learning_rate": 3.5690280753832216e-05, "loss": 0.004, "step": 259230 }, { "epoch": 62.26, "learning_rate": 3.568684136567458e-05, "loss": 0.0028, "step": 259240 }, { "epoch": 62.26, "learning_rate": 3.568340205128707e-05, "loss": 0.0022, "step": 259250 }, { "epoch": 62.26, "learning_rate": 3.567996281068744e-05, "loss": 0.0045, "step": 259260 }, { "epoch": 62.27, "learning_rate": 3.567652364389338e-05, "loss": 0.0027, "step": 259270 }, { "epoch": 62.27, "learning_rate": 3.567308455092266e-05, "loss": 0.0022, "step": 259280 }, { "epoch": 62.27, "learning_rate": 3.5669645531792985e-05, "loss": 0.0026, "step": 259290 }, { "epoch": 62.27, "learning_rate": 3.566620658652205e-05, "loss": 0.0033, "step": 259300 }, { "epoch": 62.28, "learning_rate": 3.5662767715127633e-05, "loss": 0.0114, "step": 259310 }, { "epoch": 62.28, "learning_rate": 3.56593289176274e-05, "loss": 0.0022, "step": 259320 }, { "epoch": 62.28, "learning_rate": 3.565589019403913e-05, "loss": 0.0037, "step": 259330 }, { "epoch": 62.28, "learning_rate": 3.56524515443805e-05, "loss": 0.0044, "step": 259340 }, { "epoch": 62.28, "learning_rate": 3.564901296866929e-05, "loss": 0.0027, "step": 259350 }, { "epoch": 62.29, "learning_rate": 3.5645574466923163e-05, "loss": 0.0016, "step": 259360 }, { "epoch": 62.29, "learning_rate": 3.5642136039159865e-05, "loss": 0.0031, "step": 259370 }, { "epoch": 62.29, "learning_rate": 3.5638697685397126e-05, "loss": 0.0022, "step": 259380 }, { "epoch": 62.29, "learning_rate": 3.5635259405652646e-05, "loss": 0.0061, "step": 259390 }, { "epoch": 62.3, "learning_rate": 3.563182119994417e-05, "loss": 0.005, "step": 259400 }, { "epoch": 62.3, "learning_rate": 3.56283830682894e-05, "loss": 0.005, "step": 259410 }, { "epoch": 62.3, "learning_rate": 3.562494501070608e-05, "loss": 0.0018, "step": 259420 }, { "epoch": 62.3, "learning_rate": 3.5621507027211886e-05, "loss": 0.0025, "step": 259430 }, { "epoch": 62.3, "learning_rate": 3.561806911782459e-05, "loss": 0.0022, "step": 259440 }, { "epoch": 62.31, "learning_rate": 3.561463128256189e-05, "loss": 0.0026, "step": 259450 }, { "epoch": 62.31, "learning_rate": 3.561119352144148e-05, "loss": 0.002, "step": 259460 }, { "epoch": 62.31, "learning_rate": 3.560775583448112e-05, "loss": 0.0032, "step": 259470 }, { "epoch": 62.31, "learning_rate": 3.5604318221698483e-05, "loss": 0.0034, "step": 259480 }, { "epoch": 62.32, "learning_rate": 3.560088068311133e-05, "loss": 0.0019, "step": 259490 }, { "epoch": 62.32, "learning_rate": 3.559744321873734e-05, "loss": 0.0019, "step": 259500 }, { "epoch": 62.32, "learning_rate": 3.5594005828594265e-05, "loss": 0.002, "step": 259510 }, { "epoch": 62.32, "learning_rate": 3.55905685126998e-05, "loss": 0.003, "step": 259520 }, { "epoch": 62.33, "learning_rate": 3.558713127107166e-05, "loss": 0.002, "step": 259530 }, { "epoch": 62.33, "learning_rate": 3.558369410372757e-05, "loss": 0.0129, "step": 259540 }, { "epoch": 62.33, "learning_rate": 3.5580257010685224e-05, "loss": 0.0036, "step": 259550 }, { "epoch": 62.33, "learning_rate": 3.5576819991962385e-05, "loss": 0.0021, "step": 259560 }, { "epoch": 62.33, "learning_rate": 3.55733830475767e-05, "loss": 0.0022, "step": 259570 }, { "epoch": 62.34, "learning_rate": 3.556994617754595e-05, "loss": 0.0018, "step": 259580 }, { "epoch": 62.34, "learning_rate": 3.5566509381887823e-05, "loss": 0.0033, "step": 259590 }, { "epoch": 62.34, "learning_rate": 3.556307266062e-05, "loss": 0.0022, "step": 259600 }, { "epoch": 62.34, "learning_rate": 3.555963601376024e-05, "loss": 0.002, "step": 259610 }, { "epoch": 62.35, "learning_rate": 3.555619944132622e-05, "loss": 0.0021, "step": 259620 }, { "epoch": 62.35, "learning_rate": 3.555276294333569e-05, "loss": 0.0021, "step": 259630 }, { "epoch": 62.35, "learning_rate": 3.5549326519806325e-05, "loss": 0.0019, "step": 259640 }, { "epoch": 62.35, "learning_rate": 3.5545890170755866e-05, "loss": 0.0022, "step": 259650 }, { "epoch": 62.36, "learning_rate": 3.5542453896202e-05, "loss": 0.0019, "step": 259660 }, { "epoch": 62.36, "learning_rate": 3.553901769616245e-05, "loss": 0.0022, "step": 259670 }, { "epoch": 62.36, "learning_rate": 3.553558157065492e-05, "loss": 0.0022, "step": 259680 }, { "epoch": 62.36, "learning_rate": 3.553214551969712e-05, "loss": 0.003, "step": 259690 }, { "epoch": 62.36, "learning_rate": 3.552870954330677e-05, "loss": 0.0033, "step": 259700 }, { "epoch": 62.37, "learning_rate": 3.552527364150156e-05, "loss": 0.0021, "step": 259710 }, { "epoch": 62.37, "learning_rate": 3.552183781429923e-05, "loss": 0.0022, "step": 259720 }, { "epoch": 62.37, "learning_rate": 3.5518402061717464e-05, "loss": 0.0033, "step": 259730 }, { "epoch": 62.37, "learning_rate": 3.551496638377396e-05, "loss": 0.0023, "step": 259740 }, { "epoch": 62.38, "learning_rate": 3.551153078048646e-05, "loss": 0.0064, "step": 259750 }, { "epoch": 62.38, "learning_rate": 3.550809525187263e-05, "loss": 0.0025, "step": 259760 }, { "epoch": 62.38, "learning_rate": 3.550465979795022e-05, "loss": 0.0023, "step": 259770 }, { "epoch": 62.38, "learning_rate": 3.5501224418736894e-05, "loss": 0.0023, "step": 259780 }, { "epoch": 62.38, "learning_rate": 3.54977891142504e-05, "loss": 0.0022, "step": 259790 }, { "epoch": 62.39, "learning_rate": 3.549435388450841e-05, "loss": 0.0028, "step": 259800 }, { "epoch": 62.39, "learning_rate": 3.5490918729528646e-05, "loss": 0.003, "step": 259810 }, { "epoch": 62.39, "learning_rate": 3.54874836493288e-05, "loss": 0.0022, "step": 259820 }, { "epoch": 62.39, "learning_rate": 3.5484048643926595e-05, "loss": 0.002, "step": 259830 }, { "epoch": 62.4, "learning_rate": 3.5480613713339716e-05, "loss": 0.0034, "step": 259840 }, { "epoch": 62.4, "learning_rate": 3.547717885758588e-05, "loss": 0.0026, "step": 259850 }, { "epoch": 62.4, "learning_rate": 3.547374407668278e-05, "loss": 0.0034, "step": 259860 }, { "epoch": 62.4, "learning_rate": 3.5470309370648136e-05, "loss": 0.0024, "step": 259870 }, { "epoch": 62.41, "learning_rate": 3.546687473949962e-05, "loss": 0.0026, "step": 259880 }, { "epoch": 62.41, "learning_rate": 3.546344018325498e-05, "loss": 0.0026, "step": 259890 }, { "epoch": 62.41, "learning_rate": 3.546000570193186e-05, "loss": 0.0021, "step": 259900 }, { "epoch": 62.41, "learning_rate": 3.545657129554802e-05, "loss": 0.0024, "step": 259910 }, { "epoch": 62.41, "learning_rate": 3.545313696412111e-05, "loss": 0.0058, "step": 259920 }, { "epoch": 62.42, "learning_rate": 3.5449702707668874e-05, "loss": 0.0018, "step": 259930 }, { "epoch": 62.42, "learning_rate": 3.544626852620899e-05, "loss": 0.0024, "step": 259940 }, { "epoch": 62.42, "learning_rate": 3.544283441975914e-05, "loss": 0.0024, "step": 259950 }, { "epoch": 62.42, "learning_rate": 3.543940038833705e-05, "loss": 0.0061, "step": 259960 }, { "epoch": 62.43, "learning_rate": 3.543596643196042e-05, "loss": 0.0022, "step": 259970 }, { "epoch": 62.43, "learning_rate": 3.5432532550646935e-05, "loss": 0.0072, "step": 259980 }, { "epoch": 62.43, "learning_rate": 3.54290987444143e-05, "loss": 0.0021, "step": 259990 }, { "epoch": 62.43, "learning_rate": 3.5425665013280216e-05, "loss": 0.0024, "step": 260000 }, { "epoch": 62.44, "learning_rate": 3.542223135726239e-05, "loss": 0.0031, "step": 260010 }, { "epoch": 62.44, "learning_rate": 3.541879777637848e-05, "loss": 0.0023, "step": 260020 }, { "epoch": 62.44, "learning_rate": 3.5415364270646225e-05, "loss": 0.0046, "step": 260030 }, { "epoch": 62.44, "learning_rate": 3.541193084008329e-05, "loss": 0.0021, "step": 260040 }, { "epoch": 62.44, "learning_rate": 3.540849748470739e-05, "loss": 0.002, "step": 260050 }, { "epoch": 62.45, "learning_rate": 3.540506420453621e-05, "loss": 0.0018, "step": 260060 }, { "epoch": 62.45, "learning_rate": 3.540163099958747e-05, "loss": 0.0023, "step": 260070 }, { "epoch": 62.45, "learning_rate": 3.539819786987884e-05, "loss": 0.0023, "step": 260080 }, { "epoch": 62.45, "learning_rate": 3.539476481542801e-05, "loss": 0.0028, "step": 260090 }, { "epoch": 62.46, "learning_rate": 3.53913318362527e-05, "loss": 0.0032, "step": 260100 }, { "epoch": 62.46, "learning_rate": 3.538789893237057e-05, "loss": 0.0029, "step": 260110 }, { "epoch": 62.46, "learning_rate": 3.5384466103799334e-05, "loss": 0.0023, "step": 260120 }, { "epoch": 62.46, "learning_rate": 3.5381033350556683e-05, "loss": 0.0036, "step": 260130 }, { "epoch": 62.46, "learning_rate": 3.537760067266032e-05, "loss": 0.0026, "step": 260140 }, { "epoch": 62.47, "learning_rate": 3.537416807012792e-05, "loss": 0.0017, "step": 260150 }, { "epoch": 62.47, "learning_rate": 3.537073554297716e-05, "loss": 0.0019, "step": 260160 }, { "epoch": 62.47, "learning_rate": 3.5367303091225785e-05, "loss": 0.0025, "step": 260170 }, { "epoch": 62.47, "learning_rate": 3.536387071489142e-05, "loss": 0.0041, "step": 260180 }, { "epoch": 62.48, "learning_rate": 3.536043841399182e-05, "loss": 0.0026, "step": 260190 }, { "epoch": 62.48, "learning_rate": 3.535700618854461e-05, "loss": 0.0039, "step": 260200 }, { "epoch": 62.48, "learning_rate": 3.535357403856754e-05, "loss": 0.0021, "step": 260210 }, { "epoch": 62.48, "learning_rate": 3.535014196407827e-05, "loss": 0.0026, "step": 260220 }, { "epoch": 62.49, "learning_rate": 3.534670996509447e-05, "loss": 0.002, "step": 260230 }, { "epoch": 62.49, "learning_rate": 3.534327804163387e-05, "loss": 0.0041, "step": 260240 }, { "epoch": 62.49, "learning_rate": 3.533984619371412e-05, "loss": 0.0021, "step": 260250 }, { "epoch": 62.49, "learning_rate": 3.533641442135294e-05, "loss": 0.0029, "step": 260260 }, { "epoch": 62.49, "learning_rate": 3.533298272456799e-05, "loss": 0.0023, "step": 260270 }, { "epoch": 62.5, "learning_rate": 3.532955110337697e-05, "loss": 0.0057, "step": 260280 }, { "epoch": 62.5, "learning_rate": 3.532611955779757e-05, "loss": 0.0028, "step": 260290 }, { "epoch": 62.5, "learning_rate": 3.5322688087847475e-05, "loss": 0.003, "step": 260300 }, { "epoch": 62.5, "learning_rate": 3.5319256693544376e-05, "loss": 0.0027, "step": 260310 }, { "epoch": 62.51, "learning_rate": 3.531582537490593e-05, "loss": 0.0021, "step": 260320 }, { "epoch": 62.51, "learning_rate": 3.5312394131949865e-05, "loss": 0.0029, "step": 260330 }, { "epoch": 62.51, "learning_rate": 3.5308962964693826e-05, "loss": 0.0048, "step": 260340 }, { "epoch": 62.51, "learning_rate": 3.5305531873155525e-05, "loss": 0.002, "step": 260350 }, { "epoch": 62.52, "learning_rate": 3.530210085735263e-05, "loss": 0.0026, "step": 260360 }, { "epoch": 62.52, "learning_rate": 3.529866991730284e-05, "loss": 0.0025, "step": 260370 }, { "epoch": 62.52, "learning_rate": 3.529523905302383e-05, "loss": 0.0046, "step": 260380 }, { "epoch": 62.52, "learning_rate": 3.529180826453326e-05, "loss": 0.0027, "step": 260390 }, { "epoch": 62.52, "learning_rate": 3.528837755184885e-05, "loss": 0.0037, "step": 260400 }, { "epoch": 62.53, "learning_rate": 3.528494691498826e-05, "loss": 0.0034, "step": 260410 }, { "epoch": 62.53, "learning_rate": 3.528151635396918e-05, "loss": 0.0052, "step": 260420 }, { "epoch": 62.53, "learning_rate": 3.527808586880927e-05, "loss": 0.0042, "step": 260430 }, { "epoch": 62.53, "learning_rate": 3.527465545952624e-05, "loss": 0.0027, "step": 260440 }, { "epoch": 62.54, "learning_rate": 3.527122512613777e-05, "loss": 0.0025, "step": 260450 }, { "epoch": 62.54, "learning_rate": 3.526779486866152e-05, "loss": 0.0047, "step": 260460 }, { "epoch": 62.54, "learning_rate": 3.526436468711518e-05, "loss": 0.0026, "step": 260470 }, { "epoch": 62.54, "learning_rate": 3.526093458151642e-05, "loss": 0.0023, "step": 260480 }, { "epoch": 62.54, "learning_rate": 3.5257504551882945e-05, "loss": 0.0032, "step": 260490 }, { "epoch": 62.55, "learning_rate": 3.525407459823239e-05, "loss": 0.0081, "step": 260500 }, { "epoch": 62.55, "learning_rate": 3.525064472058248e-05, "loss": 0.0032, "step": 260510 }, { "epoch": 62.55, "learning_rate": 3.5247214918950864e-05, "loss": 0.0034, "step": 260520 }, { "epoch": 62.55, "learning_rate": 3.5243785193355215e-05, "loss": 0.0023, "step": 260530 }, { "epoch": 62.56, "learning_rate": 3.5240355543813244e-05, "loss": 0.0037, "step": 260540 }, { "epoch": 62.56, "learning_rate": 3.523692597034257e-05, "loss": 0.0051, "step": 260550 }, { "epoch": 62.56, "learning_rate": 3.5233496472960934e-05, "loss": 0.0023, "step": 260560 }, { "epoch": 62.56, "learning_rate": 3.5230067051685954e-05, "loss": 0.0024, "step": 260570 }, { "epoch": 62.57, "learning_rate": 3.5226637706535355e-05, "loss": 0.0057, "step": 260580 }, { "epoch": 62.57, "learning_rate": 3.522320843752678e-05, "loss": 0.0035, "step": 260590 }, { "epoch": 62.57, "learning_rate": 3.5219779244677895e-05, "loss": 0.0033, "step": 260600 }, { "epoch": 62.57, "learning_rate": 3.521635012800641e-05, "loss": 0.0031, "step": 260610 }, { "epoch": 62.57, "learning_rate": 3.521292108752997e-05, "loss": 0.0034, "step": 260620 }, { "epoch": 62.58, "learning_rate": 3.520949212326628e-05, "loss": 0.0103, "step": 260630 }, { "epoch": 62.58, "learning_rate": 3.520606323523297e-05, "loss": 0.0033, "step": 260640 }, { "epoch": 62.58, "learning_rate": 3.520263442344774e-05, "loss": 0.0121, "step": 260650 }, { "epoch": 62.58, "learning_rate": 3.519920568792827e-05, "loss": 0.0025, "step": 260660 }, { "epoch": 62.59, "learning_rate": 3.5195777028692194e-05, "loss": 0.0024, "step": 260670 }, { "epoch": 62.59, "learning_rate": 3.519234844575723e-05, "loss": 0.0034, "step": 260680 }, { "epoch": 62.59, "learning_rate": 3.5188919939140994e-05, "loss": 0.0064, "step": 260690 }, { "epoch": 62.59, "learning_rate": 3.518549150886122e-05, "loss": 0.0031, "step": 260700 }, { "epoch": 62.6, "learning_rate": 3.518206315493552e-05, "loss": 0.002, "step": 260710 }, { "epoch": 62.6, "learning_rate": 3.5178634877381625e-05, "loss": 0.004, "step": 260720 }, { "epoch": 62.6, "learning_rate": 3.5175206676217144e-05, "loss": 0.005, "step": 260730 }, { "epoch": 62.6, "learning_rate": 3.5171778551459764e-05, "loss": 0.0019, "step": 260740 }, { "epoch": 62.6, "learning_rate": 3.5168350503127186e-05, "loss": 0.0055, "step": 260750 }, { "epoch": 62.61, "learning_rate": 3.516492253123703e-05, "loss": 0.0036, "step": 260760 }, { "epoch": 62.61, "learning_rate": 3.516149463580701e-05, "loss": 0.006, "step": 260770 }, { "epoch": 62.61, "learning_rate": 3.515806681685475e-05, "loss": 0.0023, "step": 260780 }, { "epoch": 62.61, "learning_rate": 3.515463907439796e-05, "loss": 0.0025, "step": 260790 }, { "epoch": 62.62, "learning_rate": 3.5151211408454276e-05, "loss": 0.0021, "step": 260800 }, { "epoch": 62.62, "learning_rate": 3.514778381904136e-05, "loss": 0.0068, "step": 260810 }, { "epoch": 62.62, "learning_rate": 3.51443563061769e-05, "loss": 0.0027, "step": 260820 }, { "epoch": 62.62, "learning_rate": 3.514092886987854e-05, "loss": 0.0023, "step": 260830 }, { "epoch": 62.62, "learning_rate": 3.5137501510163976e-05, "loss": 0.0027, "step": 260840 }, { "epoch": 62.63, "learning_rate": 3.5134074227050836e-05, "loss": 0.0036, "step": 260850 }, { "epoch": 62.63, "learning_rate": 3.513064702055682e-05, "loss": 0.0026, "step": 260860 }, { "epoch": 62.63, "learning_rate": 3.512721989069956e-05, "loss": 0.0033, "step": 260870 }, { "epoch": 62.63, "learning_rate": 3.512379283749674e-05, "loss": 0.0025, "step": 260880 }, { "epoch": 62.64, "learning_rate": 3.512036586096601e-05, "loss": 0.0026, "step": 260890 }, { "epoch": 62.64, "learning_rate": 3.5116938961125026e-05, "loss": 0.0036, "step": 260900 }, { "epoch": 62.64, "learning_rate": 3.511351213799149e-05, "loss": 0.0025, "step": 260910 }, { "epoch": 62.64, "learning_rate": 3.511008539158301e-05, "loss": 0.0025, "step": 260920 }, { "epoch": 62.65, "learning_rate": 3.510665872191731e-05, "loss": 0.0037, "step": 260930 }, { "epoch": 62.65, "learning_rate": 3.5103232129011995e-05, "loss": 0.0021, "step": 260940 }, { "epoch": 62.65, "learning_rate": 3.509980561288474e-05, "loss": 0.0032, "step": 260950 }, { "epoch": 62.65, "learning_rate": 3.509637917355323e-05, "loss": 0.0036, "step": 260960 }, { "epoch": 62.65, "learning_rate": 3.509295281103508e-05, "loss": 0.002, "step": 260970 }, { "epoch": 62.66, "learning_rate": 3.5089526525347995e-05, "loss": 0.003, "step": 260980 }, { "epoch": 62.66, "learning_rate": 3.5086100316509605e-05, "loss": 0.002, "step": 260990 }, { "epoch": 62.66, "learning_rate": 3.508267418453759e-05, "loss": 0.0321, "step": 261000 }, { "epoch": 62.66, "learning_rate": 3.507924812944959e-05, "loss": 0.0031, "step": 261010 }, { "epoch": 62.67, "learning_rate": 3.507582215126327e-05, "loss": 0.0028, "step": 261020 }, { "epoch": 62.67, "learning_rate": 3.507239624999629e-05, "loss": 0.0051, "step": 261030 }, { "epoch": 62.67, "learning_rate": 3.5068970425666295e-05, "loss": 0.0025, "step": 261040 }, { "epoch": 62.67, "learning_rate": 3.5065544678290966e-05, "loss": 0.0031, "step": 261050 }, { "epoch": 62.68, "learning_rate": 3.506211900788792e-05, "loss": 0.0052, "step": 261060 }, { "epoch": 62.68, "learning_rate": 3.505869341447486e-05, "loss": 0.0021, "step": 261070 }, { "epoch": 62.68, "learning_rate": 3.5055267898069406e-05, "loss": 0.002, "step": 261080 }, { "epoch": 62.68, "learning_rate": 3.505184245868924e-05, "loss": 0.0025, "step": 261090 }, { "epoch": 62.68, "learning_rate": 3.504841709635201e-05, "loss": 0.0038, "step": 261100 }, { "epoch": 62.69, "learning_rate": 3.504499181107533e-05, "loss": 0.0049, "step": 261110 }, { "epoch": 62.69, "learning_rate": 3.504156660287693e-05, "loss": 0.0021, "step": 261120 }, { "epoch": 62.69, "learning_rate": 3.503814147177438e-05, "loss": 0.0024, "step": 261130 }, { "epoch": 62.69, "learning_rate": 3.5034716417785404e-05, "loss": 0.002, "step": 261140 }, { "epoch": 62.7, "learning_rate": 3.5031291440927595e-05, "loss": 0.0034, "step": 261150 }, { "epoch": 62.7, "learning_rate": 3.5027866541218665e-05, "loss": 0.0027, "step": 261160 }, { "epoch": 62.7, "learning_rate": 3.5024441718676226e-05, "loss": 0.0033, "step": 261170 }, { "epoch": 62.7, "learning_rate": 3.5021016973317936e-05, "loss": 0.0022, "step": 261180 }, { "epoch": 62.7, "learning_rate": 3.501759230516145e-05, "loss": 0.0019, "step": 261190 }, { "epoch": 62.71, "learning_rate": 3.501416771422441e-05, "loss": 0.0025, "step": 261200 }, { "epoch": 62.71, "learning_rate": 3.501074320052449e-05, "loss": 0.0022, "step": 261210 }, { "epoch": 62.71, "learning_rate": 3.5007318764079306e-05, "loss": 0.0042, "step": 261220 }, { "epoch": 62.71, "learning_rate": 3.5003894404906545e-05, "loss": 0.0025, "step": 261230 }, { "epoch": 62.72, "learning_rate": 3.500047012302384e-05, "loss": 0.0022, "step": 261240 }, { "epoch": 62.72, "learning_rate": 3.499704591844882e-05, "loss": 0.0028, "step": 261250 }, { "epoch": 62.72, "learning_rate": 3.499362179119917e-05, "loss": 0.0018, "step": 261260 }, { "epoch": 62.72, "learning_rate": 3.49901977412925e-05, "loss": 0.0024, "step": 261270 }, { "epoch": 62.73, "learning_rate": 3.49867737687465e-05, "loss": 0.0027, "step": 261280 }, { "epoch": 62.73, "learning_rate": 3.4983349873578765e-05, "loss": 0.0026, "step": 261290 }, { "epoch": 62.73, "learning_rate": 3.497992605580699e-05, "loss": 0.0019, "step": 261300 }, { "epoch": 62.73, "learning_rate": 3.49765023154488e-05, "loss": 0.0088, "step": 261310 }, { "epoch": 62.73, "learning_rate": 3.497307865252183e-05, "loss": 0.0025, "step": 261320 }, { "epoch": 62.74, "learning_rate": 3.496965506704375e-05, "loss": 0.0033, "step": 261330 }, { "epoch": 62.74, "learning_rate": 3.496623155903218e-05, "loss": 0.0041, "step": 261340 }, { "epoch": 62.74, "learning_rate": 3.496280812850479e-05, "loss": 0.0021, "step": 261350 }, { "epoch": 62.74, "learning_rate": 3.495938477547921e-05, "loss": 0.0023, "step": 261360 }, { "epoch": 62.75, "learning_rate": 3.495596149997309e-05, "loss": 0.0039, "step": 261370 }, { "epoch": 62.75, "learning_rate": 3.495253830200407e-05, "loss": 0.0022, "step": 261380 }, { "epoch": 62.75, "learning_rate": 3.4949115181589784e-05, "loss": 0.0021, "step": 261390 }, { "epoch": 62.75, "learning_rate": 3.49456921387479e-05, "loss": 0.0028, "step": 261400 }, { "epoch": 62.76, "learning_rate": 3.4942269173496025e-05, "loss": 0.002, "step": 261410 }, { "epoch": 62.76, "learning_rate": 3.493884628585184e-05, "loss": 0.0021, "step": 261420 }, { "epoch": 62.76, "learning_rate": 3.493542347583294e-05, "loss": 0.0058, "step": 261430 }, { "epoch": 62.76, "learning_rate": 3.493200074345703e-05, "loss": 0.0021, "step": 261440 }, { "epoch": 62.76, "learning_rate": 3.492857808874171e-05, "loss": 0.0032, "step": 261450 }, { "epoch": 62.77, "learning_rate": 3.492515551170459e-05, "loss": 0.0027, "step": 261460 }, { "epoch": 62.77, "learning_rate": 3.4921733012363366e-05, "loss": 0.0022, "step": 261470 }, { "epoch": 62.77, "learning_rate": 3.4918310590735646e-05, "loss": 0.0021, "step": 261480 }, { "epoch": 62.77, "learning_rate": 3.4914888246839096e-05, "loss": 0.0033, "step": 261490 }, { "epoch": 62.78, "learning_rate": 3.491146598069133e-05, "loss": 0.0024, "step": 261500 }, { "epoch": 62.78, "learning_rate": 3.490804379230999e-05, "loss": 0.0053, "step": 261510 }, { "epoch": 62.78, "learning_rate": 3.490462168171273e-05, "loss": 0.0023, "step": 261520 }, { "epoch": 62.78, "learning_rate": 3.490119964891716e-05, "loss": 0.0033, "step": 261530 }, { "epoch": 62.78, "learning_rate": 3.4897777693940944e-05, "loss": 0.0022, "step": 261540 }, { "epoch": 62.79, "learning_rate": 3.4894355816801704e-05, "loss": 0.0033, "step": 261550 }, { "epoch": 62.79, "learning_rate": 3.489093401751709e-05, "loss": 0.002, "step": 261560 }, { "epoch": 62.79, "learning_rate": 3.488751229610471e-05, "loss": 0.0023, "step": 261570 }, { "epoch": 62.79, "learning_rate": 3.4884090652582236e-05, "loss": 0.0205, "step": 261580 }, { "epoch": 62.8, "learning_rate": 3.4880669086967287e-05, "loss": 0.0023, "step": 261590 }, { "epoch": 62.8, "learning_rate": 3.487724759927747e-05, "loss": 0.002, "step": 261600 }, { "epoch": 62.8, "learning_rate": 3.4873826189530475e-05, "loss": 0.0026, "step": 261610 }, { "epoch": 62.8, "learning_rate": 3.487040485774389e-05, "loss": 0.0157, "step": 261620 }, { "epoch": 62.81, "learning_rate": 3.486698360393537e-05, "loss": 0.0029, "step": 261630 }, { "epoch": 62.81, "learning_rate": 3.486356242812253e-05, "loss": 0.0025, "step": 261640 }, { "epoch": 62.81, "learning_rate": 3.486014133032303e-05, "loss": 0.0043, "step": 261650 }, { "epoch": 62.81, "learning_rate": 3.485672031055449e-05, "loss": 0.0021, "step": 261660 }, { "epoch": 62.81, "learning_rate": 3.4853299368834525e-05, "loss": 0.0032, "step": 261670 }, { "epoch": 62.82, "learning_rate": 3.4849878505180804e-05, "loss": 0.002, "step": 261680 }, { "epoch": 62.82, "learning_rate": 3.4846457719610916e-05, "loss": 0.0029, "step": 261690 }, { "epoch": 62.82, "learning_rate": 3.484303701214253e-05, "loss": 0.0025, "step": 261700 }, { "epoch": 62.82, "learning_rate": 3.4839616382793225e-05, "loss": 0.002, "step": 261710 }, { "epoch": 62.83, "learning_rate": 3.48361958315807e-05, "loss": 0.0031, "step": 261720 }, { "epoch": 62.83, "learning_rate": 3.4832775358522546e-05, "loss": 0.0021, "step": 261730 }, { "epoch": 62.83, "learning_rate": 3.482935496363637e-05, "loss": 0.0025, "step": 261740 }, { "epoch": 62.83, "learning_rate": 3.482593464693985e-05, "loss": 0.0019, "step": 261750 }, { "epoch": 62.84, "learning_rate": 3.482251440845057e-05, "loss": 0.0019, "step": 261760 }, { "epoch": 62.84, "learning_rate": 3.4819094248186193e-05, "loss": 0.0031, "step": 261770 }, { "epoch": 62.84, "learning_rate": 3.481567416616431e-05, "loss": 0.0018, "step": 261780 }, { "epoch": 62.84, "learning_rate": 3.481225416240258e-05, "loss": 0.0045, "step": 261790 }, { "epoch": 62.84, "learning_rate": 3.480883423691863e-05, "loss": 0.0021, "step": 261800 }, { "epoch": 62.85, "learning_rate": 3.480541438973006e-05, "loss": 0.0019, "step": 261810 }, { "epoch": 62.85, "learning_rate": 3.480199462085453e-05, "loss": 0.0024, "step": 261820 }, { "epoch": 62.85, "learning_rate": 3.4798574930309626e-05, "loss": 0.0029, "step": 261830 }, { "epoch": 62.85, "learning_rate": 3.479515531811301e-05, "loss": 0.0021, "step": 261840 }, { "epoch": 62.86, "learning_rate": 3.479173578428228e-05, "loss": 0.0037, "step": 261850 }, { "epoch": 62.86, "learning_rate": 3.4788316328835074e-05, "loss": 0.0018, "step": 261860 }, { "epoch": 62.86, "learning_rate": 3.4784896951789004e-05, "loss": 0.0054, "step": 261870 }, { "epoch": 62.86, "learning_rate": 3.478147765316172e-05, "loss": 0.0021, "step": 261880 }, { "epoch": 62.86, "learning_rate": 3.477805843297083e-05, "loss": 0.0023, "step": 261890 }, { "epoch": 62.87, "learning_rate": 3.477463929123393e-05, "loss": 0.0026, "step": 261900 }, { "epoch": 62.87, "learning_rate": 3.477122022796869e-05, "loss": 0.0025, "step": 261910 }, { "epoch": 62.87, "learning_rate": 3.4767801243192685e-05, "loss": 0.005, "step": 261920 }, { "epoch": 62.87, "learning_rate": 3.4764382336923583e-05, "loss": 0.0021, "step": 261930 }, { "epoch": 62.88, "learning_rate": 3.476096350917896e-05, "loss": 0.0032, "step": 261940 }, { "epoch": 62.88, "learning_rate": 3.475754475997647e-05, "loss": 0.0053, "step": 261950 }, { "epoch": 62.88, "learning_rate": 3.475412608933373e-05, "loss": 0.0048, "step": 261960 }, { "epoch": 62.88, "learning_rate": 3.475070749726833e-05, "loss": 0.0031, "step": 261970 }, { "epoch": 62.89, "learning_rate": 3.4747288983797935e-05, "loss": 0.002, "step": 261980 }, { "epoch": 62.89, "learning_rate": 3.4743870548940114e-05, "loss": 0.0023, "step": 261990 }, { "epoch": 62.89, "learning_rate": 3.4740452192712544e-05, "loss": 0.0019, "step": 262000 }, { "epoch": 62.89, "learning_rate": 3.4737033915132777e-05, "loss": 0.0037, "step": 262010 }, { "epoch": 62.89, "learning_rate": 3.473361571621849e-05, "loss": 0.0026, "step": 262020 }, { "epoch": 62.9, "learning_rate": 3.473019759598728e-05, "loss": 0.004, "step": 262030 }, { "epoch": 62.9, "learning_rate": 3.472677955445673e-05, "loss": 0.0025, "step": 262040 }, { "epoch": 62.9, "learning_rate": 3.472336159164452e-05, "loss": 0.003, "step": 262050 }, { "epoch": 62.9, "learning_rate": 3.4719943707568204e-05, "loss": 0.0024, "step": 262060 }, { "epoch": 62.91, "learning_rate": 3.471652590224544e-05, "loss": 0.0035, "step": 262070 }, { "epoch": 62.91, "learning_rate": 3.471310817569382e-05, "loss": 0.0026, "step": 262080 }, { "epoch": 62.91, "learning_rate": 3.4709690527930974e-05, "loss": 0.0025, "step": 262090 }, { "epoch": 62.91, "learning_rate": 3.470627295897452e-05, "loss": 0.002, "step": 262100 }, { "epoch": 62.91, "learning_rate": 3.470285546884203e-05, "loss": 0.0035, "step": 262110 }, { "epoch": 62.92, "learning_rate": 3.469943805755119e-05, "loss": 0.0019, "step": 262120 }, { "epoch": 62.92, "learning_rate": 3.469602072511955e-05, "loss": 0.002, "step": 262130 }, { "epoch": 62.92, "learning_rate": 3.469260347156476e-05, "loss": 0.0018, "step": 262140 }, { "epoch": 62.92, "learning_rate": 3.46891862969044e-05, "loss": 0.0022, "step": 262150 }, { "epoch": 62.93, "learning_rate": 3.468576920115613e-05, "loss": 0.0017, "step": 262160 }, { "epoch": 62.93, "learning_rate": 3.468235218433753e-05, "loss": 0.003, "step": 262170 }, { "epoch": 62.93, "learning_rate": 3.467893524646619e-05, "loss": 0.0024, "step": 262180 }, { "epoch": 62.93, "learning_rate": 3.4675518387559775e-05, "loss": 0.0017, "step": 262190 }, { "epoch": 62.94, "learning_rate": 3.467210160763584e-05, "loss": 0.0018, "step": 262200 }, { "epoch": 62.94, "learning_rate": 3.466868490671205e-05, "loss": 0.0032, "step": 262210 }, { "epoch": 62.94, "learning_rate": 3.466526828480595e-05, "loss": 0.0027, "step": 262220 }, { "epoch": 62.94, "learning_rate": 3.4661851741935214e-05, "loss": 0.0025, "step": 262230 }, { "epoch": 62.94, "learning_rate": 3.465843527811741e-05, "loss": 0.0059, "step": 262240 }, { "epoch": 62.95, "learning_rate": 3.4655018893370164e-05, "loss": 0.0019, "step": 262250 }, { "epoch": 62.95, "learning_rate": 3.465160258771108e-05, "loss": 0.0021, "step": 262260 }, { "epoch": 63.0, "learning_rate": 3.4648186361157745e-05, "loss": 0.0021, "step": 262270 }, { "epoch": 63.0, "learning_rate": 3.4644770213727814e-05, "loss": 0.0031, "step": 262280 }, { "epoch": 63.0, "learning_rate": 3.464135414543884e-05, "loss": 0.0021, "step": 262290 }, { "epoch": 63.01, "learning_rate": 3.463793815630848e-05, "loss": 0.0034, "step": 262300 }, { "epoch": 63.01, "learning_rate": 3.463452224635432e-05, "loss": 0.003, "step": 262310 }, { "epoch": 63.01, "learning_rate": 3.463110641559393e-05, "loss": 0.0039, "step": 262320 }, { "epoch": 63.01, "learning_rate": 3.462769066404497e-05, "loss": 0.0021, "step": 262330 }, { "epoch": 63.02, "learning_rate": 3.4624274991725e-05, "loss": 0.0019, "step": 262340 }, { "epoch": 63.02, "learning_rate": 3.462085939865167e-05, "loss": 0.0018, "step": 262350 }, { "epoch": 63.02, "learning_rate": 3.4617443884842536e-05, "loss": 0.0022, "step": 262360 }, { "epoch": 63.02, "learning_rate": 3.461402845031524e-05, "loss": 0.0036, "step": 262370 }, { "epoch": 63.03, "learning_rate": 3.461061309508737e-05, "loss": 0.0046, "step": 262380 }, { "epoch": 63.03, "learning_rate": 3.4607197819176515e-05, "loss": 0.0021, "step": 262390 }, { "epoch": 63.03, "learning_rate": 3.4603782622600305e-05, "loss": 0.0016, "step": 262400 }, { "epoch": 63.03, "learning_rate": 3.460036750537632e-05, "loss": 0.0022, "step": 262410 }, { "epoch": 63.03, "learning_rate": 3.4596952467522176e-05, "loss": 0.0022, "step": 262420 }, { "epoch": 63.04, "learning_rate": 3.459353750905545e-05, "loss": 0.0025, "step": 262430 }, { "epoch": 63.04, "learning_rate": 3.4590122629993785e-05, "loss": 0.0021, "step": 262440 }, { "epoch": 63.04, "learning_rate": 3.458670783035476e-05, "loss": 0.0033, "step": 262450 }, { "epoch": 63.04, "learning_rate": 3.458329311015594e-05, "loss": 0.003, "step": 262460 }, { "epoch": 63.05, "learning_rate": 3.457987846941499e-05, "loss": 0.0128, "step": 262470 }, { "epoch": 63.05, "learning_rate": 3.4576463908149446e-05, "loss": 0.0021, "step": 262480 }, { "epoch": 63.05, "learning_rate": 3.4573049426376955e-05, "loss": 0.0061, "step": 262490 }, { "epoch": 63.05, "learning_rate": 3.4569635024115087e-05, "loss": 0.0025, "step": 262500 }, { "epoch": 63.06, "learning_rate": 3.456622070138146e-05, "loss": 0.0021, "step": 262510 }, { "epoch": 63.06, "learning_rate": 3.4562806458193654e-05, "loss": 0.0036, "step": 262520 }, { "epoch": 63.06, "learning_rate": 3.455939229456927e-05, "loss": 0.003, "step": 262530 }, { "epoch": 63.06, "learning_rate": 3.4555978210525904e-05, "loss": 0.0019, "step": 262540 }, { "epoch": 63.06, "learning_rate": 3.4552564206081165e-05, "loss": 0.0023, "step": 262550 }, { "epoch": 63.07, "learning_rate": 3.4549150281252636e-05, "loss": 0.0021, "step": 262560 }, { "epoch": 63.07, "learning_rate": 3.45457364360579e-05, "loss": 0.0026, "step": 262570 }, { "epoch": 63.07, "learning_rate": 3.454232267051459e-05, "loss": 0.0019, "step": 262580 }, { "epoch": 63.07, "learning_rate": 3.4538908984640284e-05, "loss": 0.0062, "step": 262590 }, { "epoch": 63.08, "learning_rate": 3.453549537845254e-05, "loss": 0.0022, "step": 262600 }, { "epoch": 63.08, "learning_rate": 3.453208185196901e-05, "loss": 0.0022, "step": 262610 }, { "epoch": 63.08, "learning_rate": 3.4528668405207246e-05, "loss": 0.0019, "step": 262620 }, { "epoch": 63.08, "learning_rate": 3.452525503818486e-05, "loss": 0.0021, "step": 262630 }, { "epoch": 63.08, "learning_rate": 3.4521841750919425e-05, "loss": 0.0029, "step": 262640 }, { "epoch": 63.09, "learning_rate": 3.4518428543428564e-05, "loss": 0.002, "step": 262650 }, { "epoch": 63.09, "learning_rate": 3.4515015415729834e-05, "loss": 0.0023, "step": 262660 }, { "epoch": 63.09, "learning_rate": 3.4511602367840865e-05, "loss": 0.0021, "step": 262670 }, { "epoch": 63.09, "learning_rate": 3.4508189399779215e-05, "loss": 0.0021, "step": 262680 }, { "epoch": 63.1, "learning_rate": 3.450477651156249e-05, "loss": 0.0019, "step": 262690 }, { "epoch": 63.1, "learning_rate": 3.450136370320827e-05, "loss": 0.0028, "step": 262700 }, { "epoch": 63.1, "learning_rate": 3.449795097473415e-05, "loss": 0.0019, "step": 262710 }, { "epoch": 63.1, "learning_rate": 3.449453832615773e-05, "loss": 0.0045, "step": 262720 }, { "epoch": 63.11, "learning_rate": 3.449112575749658e-05, "loss": 0.002, "step": 262730 }, { "epoch": 63.11, "learning_rate": 3.4487713268768305e-05, "loss": 0.0019, "step": 262740 }, { "epoch": 63.11, "learning_rate": 3.4484300859990496e-05, "loss": 0.0019, "step": 262750 }, { "epoch": 63.11, "learning_rate": 3.448088853118071e-05, "loss": 0.0054, "step": 262760 }, { "epoch": 63.11, "learning_rate": 3.447747628235657e-05, "loss": 0.0354, "step": 262770 }, { "epoch": 63.12, "learning_rate": 3.447406411353562e-05, "loss": 0.0021, "step": 262780 }, { "epoch": 63.12, "learning_rate": 3.447065202473551e-05, "loss": 0.0023, "step": 262790 }, { "epoch": 63.12, "learning_rate": 3.446724001597375e-05, "loss": 0.0022, "step": 262800 }, { "epoch": 63.12, "learning_rate": 3.4463828087268e-05, "loss": 0.002, "step": 262810 }, { "epoch": 63.13, "learning_rate": 3.446041623863581e-05, "loss": 0.0024, "step": 262820 }, { "epoch": 63.13, "learning_rate": 3.445700447009473e-05, "loss": 0.002, "step": 262830 }, { "epoch": 63.13, "learning_rate": 3.44535927816624e-05, "loss": 0.0018, "step": 262840 }, { "epoch": 63.13, "learning_rate": 3.445018117335638e-05, "loss": 0.0023, "step": 262850 }, { "epoch": 63.14, "learning_rate": 3.444676964519426e-05, "loss": 0.0025, "step": 262860 }, { "epoch": 63.14, "learning_rate": 3.444335819719361e-05, "loss": 0.003, "step": 262870 }, { "epoch": 63.14, "learning_rate": 3.443994682937203e-05, "loss": 0.0023, "step": 262880 }, { "epoch": 63.14, "learning_rate": 3.4436535541747105e-05, "loss": 0.004, "step": 262890 }, { "epoch": 63.14, "learning_rate": 3.443312433433638e-05, "loss": 0.0028, "step": 262900 }, { "epoch": 63.15, "learning_rate": 3.442971320715749e-05, "loss": 0.0027, "step": 262910 }, { "epoch": 63.15, "learning_rate": 3.442630216022796e-05, "loss": 0.0021, "step": 262920 }, { "epoch": 63.15, "learning_rate": 3.442289119356542e-05, "loss": 0.0023, "step": 262930 }, { "epoch": 63.15, "learning_rate": 3.441948030718741e-05, "loss": 0.0038, "step": 262940 }, { "epoch": 63.16, "learning_rate": 3.441606950111156e-05, "loss": 0.0204, "step": 262950 }, { "epoch": 63.16, "learning_rate": 3.441265877535541e-05, "loss": 0.0019, "step": 262960 }, { "epoch": 63.16, "learning_rate": 3.440924812993652e-05, "loss": 0.0028, "step": 262970 }, { "epoch": 63.16, "learning_rate": 3.440583756487252e-05, "loss": 0.002, "step": 262980 }, { "epoch": 63.16, "learning_rate": 3.440242708018094e-05, "loss": 0.0026, "step": 262990 }, { "epoch": 63.17, "learning_rate": 3.43990166758794e-05, "loss": 0.0021, "step": 263000 }, { "epoch": 63.17, "learning_rate": 3.439560635198545e-05, "loss": 0.0021, "step": 263010 }, { "epoch": 63.17, "learning_rate": 3.4392196108516686e-05, "loss": 0.0024, "step": 263020 }, { "epoch": 63.17, "learning_rate": 3.438878594549068e-05, "loss": 0.0025, "step": 263030 }, { "epoch": 63.18, "learning_rate": 3.4385375862924975e-05, "loss": 0.0045, "step": 263040 }, { "epoch": 63.18, "learning_rate": 3.4381965860837194e-05, "loss": 0.0023, "step": 263050 }, { "epoch": 63.18, "learning_rate": 3.437855593924487e-05, "loss": 0.0025, "step": 263060 }, { "epoch": 63.18, "learning_rate": 3.437514609816563e-05, "loss": 0.0021, "step": 263070 }, { "epoch": 63.19, "learning_rate": 3.4371736337616985e-05, "loss": 0.002, "step": 263080 }, { "epoch": 63.19, "learning_rate": 3.436832665761657e-05, "loss": 0.0021, "step": 263090 }, { "epoch": 63.19, "learning_rate": 3.4364917058181934e-05, "loss": 0.003, "step": 263100 }, { "epoch": 63.19, "learning_rate": 3.4361507539330616e-05, "loss": 0.0024, "step": 263110 }, { "epoch": 63.19, "learning_rate": 3.435809810108025e-05, "loss": 0.0023, "step": 263120 }, { "epoch": 63.2, "learning_rate": 3.435468874344835e-05, "loss": 0.0025, "step": 263130 }, { "epoch": 63.2, "learning_rate": 3.4351279466452526e-05, "loss": 0.002, "step": 263140 }, { "epoch": 63.2, "learning_rate": 3.434787027011033e-05, "loss": 0.0046, "step": 263150 }, { "epoch": 63.2, "learning_rate": 3.434446115443935e-05, "loss": 0.0021, "step": 263160 }, { "epoch": 63.21, "learning_rate": 3.434105211945716e-05, "loss": 0.0023, "step": 263170 }, { "epoch": 63.21, "learning_rate": 3.43376431651813e-05, "loss": 0.002, "step": 263180 }, { "epoch": 63.21, "learning_rate": 3.433423429162937e-05, "loss": 0.0022, "step": 263190 }, { "epoch": 63.21, "learning_rate": 3.433082549881891e-05, "loss": 0.002, "step": 263200 }, { "epoch": 63.22, "learning_rate": 3.432741678676753e-05, "loss": 0.002, "step": 263210 }, { "epoch": 63.22, "learning_rate": 3.4324008155492746e-05, "loss": 0.0019, "step": 263220 }, { "epoch": 63.22, "learning_rate": 3.4320599605012184e-05, "loss": 0.0021, "step": 263230 }, { "epoch": 63.22, "learning_rate": 3.431719113534338e-05, "loss": 0.0022, "step": 263240 }, { "epoch": 63.22, "learning_rate": 3.4313782746503886e-05, "loss": 0.0033, "step": 263250 }, { "epoch": 63.23, "learning_rate": 3.4310374438511306e-05, "loss": 0.002, "step": 263260 }, { "epoch": 63.23, "learning_rate": 3.430696621138316e-05, "loss": 0.0037, "step": 263270 }, { "epoch": 63.23, "learning_rate": 3.430355806513707e-05, "loss": 0.0049, "step": 263280 }, { "epoch": 63.23, "learning_rate": 3.430014999979055e-05, "loss": 0.0038, "step": 263290 }, { "epoch": 63.24, "learning_rate": 3.4296742015361195e-05, "loss": 0.0019, "step": 263300 }, { "epoch": 63.24, "learning_rate": 3.429333411186658e-05, "loss": 0.0024, "step": 263310 }, { "epoch": 63.24, "learning_rate": 3.4289926289324225e-05, "loss": 0.0023, "step": 263320 }, { "epoch": 63.24, "learning_rate": 3.4286518547751745e-05, "loss": 0.0034, "step": 263330 }, { "epoch": 63.24, "learning_rate": 3.428311088716666e-05, "loss": 0.0026, "step": 263340 }, { "epoch": 63.25, "learning_rate": 3.4279703307586575e-05, "loss": 0.0021, "step": 263350 }, { "epoch": 63.25, "learning_rate": 3.4276295809029e-05, "loss": 0.0104, "step": 263360 }, { "epoch": 63.25, "learning_rate": 3.427288839151156e-05, "loss": 0.0028, "step": 263370 }, { "epoch": 63.25, "learning_rate": 3.4269481055051784e-05, "loss": 0.0028, "step": 263380 }, { "epoch": 63.26, "learning_rate": 3.426607379966721e-05, "loss": 0.005, "step": 263390 }, { "epoch": 63.26, "learning_rate": 3.4262666625375436e-05, "loss": 0.0051, "step": 263400 }, { "epoch": 63.26, "learning_rate": 3.4259259532194006e-05, "loss": 0.0058, "step": 263410 }, { "epoch": 63.26, "learning_rate": 3.42558525201405e-05, "loss": 0.0022, "step": 263420 }, { "epoch": 63.27, "learning_rate": 3.4252445589232426e-05, "loss": 0.0019, "step": 263430 }, { "epoch": 63.27, "learning_rate": 3.424903873948742e-05, "loss": 0.0022, "step": 263440 }, { "epoch": 63.27, "learning_rate": 3.424563197092296e-05, "loss": 0.0022, "step": 263450 }, { "epoch": 63.27, "learning_rate": 3.424222528355667e-05, "loss": 0.0042, "step": 263460 }, { "epoch": 63.27, "learning_rate": 3.4238818677406086e-05, "loss": 0.0022, "step": 263470 }, { "epoch": 63.28, "learning_rate": 3.4235412152488747e-05, "loss": 0.0024, "step": 263480 }, { "epoch": 63.28, "learning_rate": 3.423200570882224e-05, "loss": 0.0062, "step": 263490 }, { "epoch": 63.28, "learning_rate": 3.422859934642409e-05, "loss": 0.002, "step": 263500 }, { "epoch": 63.28, "learning_rate": 3.422519306531189e-05, "loss": 0.0028, "step": 263510 }, { "epoch": 63.29, "learning_rate": 3.422178686550316e-05, "loss": 0.0042, "step": 263520 }, { "epoch": 63.29, "learning_rate": 3.421838074701549e-05, "loss": 0.0073, "step": 263530 }, { "epoch": 63.29, "learning_rate": 3.421497470986641e-05, "loss": 0.0028, "step": 263540 }, { "epoch": 63.29, "learning_rate": 3.4211568754073475e-05, "loss": 0.0034, "step": 263550 }, { "epoch": 63.3, "learning_rate": 3.420816287965426e-05, "loss": 0.0019, "step": 263560 }, { "epoch": 63.3, "learning_rate": 3.420475708662628e-05, "loss": 0.0019, "step": 263570 }, { "epoch": 63.3, "learning_rate": 3.420135137500715e-05, "loss": 0.0029, "step": 263580 }, { "epoch": 63.3, "learning_rate": 3.419794574481435e-05, "loss": 0.003, "step": 263590 }, { "epoch": 63.3, "learning_rate": 3.41945401960655e-05, "loss": 0.0017, "step": 263600 }, { "epoch": 63.31, "learning_rate": 3.4191134728778107e-05, "loss": 0.0023, "step": 263610 }, { "epoch": 63.31, "learning_rate": 3.418772934296973e-05, "loss": 0.003, "step": 263620 }, { "epoch": 63.31, "learning_rate": 3.418432403865795e-05, "loss": 0.002, "step": 263630 }, { "epoch": 63.31, "learning_rate": 3.418091881586028e-05, "loss": 0.0019, "step": 263640 }, { "epoch": 63.32, "learning_rate": 3.4177513674594297e-05, "loss": 0.0018, "step": 263650 }, { "epoch": 63.32, "learning_rate": 3.417410861487752e-05, "loss": 0.0039, "step": 263660 }, { "epoch": 63.32, "learning_rate": 3.4170703636727544e-05, "loss": 0.0023, "step": 263670 }, { "epoch": 63.32, "learning_rate": 3.4167298740161894e-05, "loss": 0.0019, "step": 263680 }, { "epoch": 63.32, "learning_rate": 3.41638939251981e-05, "loss": 0.0023, "step": 263690 }, { "epoch": 63.33, "learning_rate": 3.416048919185375e-05, "loss": 0.003, "step": 263700 }, { "epoch": 63.33, "learning_rate": 3.4157084540146346e-05, "loss": 0.0022, "step": 263710 }, { "epoch": 63.33, "learning_rate": 3.4153679970093486e-05, "loss": 0.0018, "step": 263720 }, { "epoch": 63.33, "learning_rate": 3.415027548171267e-05, "loss": 0.0021, "step": 263730 }, { "epoch": 63.34, "learning_rate": 3.414687107502148e-05, "loss": 0.0018, "step": 263740 }, { "epoch": 63.34, "learning_rate": 3.4143466750037446e-05, "loss": 0.0031, "step": 263750 }, { "epoch": 63.34, "learning_rate": 3.4140062506778116e-05, "loss": 0.0019, "step": 263760 }, { "epoch": 63.34, "learning_rate": 3.4136658345261044e-05, "loss": 0.002, "step": 263770 }, { "epoch": 63.35, "learning_rate": 3.4133254265503746e-05, "loss": 0.0018, "step": 263780 }, { "epoch": 63.35, "learning_rate": 3.412985026752381e-05, "loss": 0.005, "step": 263790 }, { "epoch": 63.35, "learning_rate": 3.4126446351338734e-05, "loss": 0.004, "step": 263800 }, { "epoch": 63.35, "learning_rate": 3.412304251696612e-05, "loss": 0.0023, "step": 263810 }, { "epoch": 63.35, "learning_rate": 3.4119638764423465e-05, "loss": 0.0021, "step": 263820 }, { "epoch": 63.36, "learning_rate": 3.411623509372831e-05, "loss": 0.0023, "step": 263830 }, { "epoch": 63.36, "learning_rate": 3.4112831504898235e-05, "loss": 0.0019, "step": 263840 }, { "epoch": 63.36, "learning_rate": 3.4109427997950735e-05, "loss": 0.0036, "step": 263850 }, { "epoch": 63.36, "learning_rate": 3.410602457290339e-05, "loss": 0.004, "step": 263860 }, { "epoch": 63.37, "learning_rate": 3.4102621229773725e-05, "loss": 0.002, "step": 263870 }, { "epoch": 63.37, "learning_rate": 3.409921796857929e-05, "loss": 0.0036, "step": 263880 }, { "epoch": 63.37, "learning_rate": 3.409581478933761e-05, "loss": 0.005, "step": 263890 }, { "epoch": 63.37, "learning_rate": 3.4092411692066226e-05, "loss": 0.0026, "step": 263900 }, { "epoch": 63.38, "learning_rate": 3.40890086767827e-05, "loss": 0.002, "step": 263910 }, { "epoch": 63.38, "learning_rate": 3.4085605743504547e-05, "loss": 0.0033, "step": 263920 }, { "epoch": 63.38, "learning_rate": 3.408220289224932e-05, "loss": 0.0027, "step": 263930 }, { "epoch": 63.38, "learning_rate": 3.407880012303454e-05, "loss": 0.0023, "step": 263940 }, { "epoch": 63.38, "learning_rate": 3.4075397435877775e-05, "loss": 0.0043, "step": 263950 }, { "epoch": 63.39, "learning_rate": 3.407199483079655e-05, "loss": 0.0034, "step": 263960 }, { "epoch": 63.39, "learning_rate": 3.406859230780837e-05, "loss": 0.0023, "step": 263970 }, { "epoch": 63.39, "learning_rate": 3.4065189866930826e-05, "loss": 0.0019, "step": 263980 }, { "epoch": 63.39, "learning_rate": 3.40617875081814e-05, "loss": 0.0022, "step": 263990 }, { "epoch": 63.4, "learning_rate": 3.4058385231577674e-05, "loss": 0.0037, "step": 264000 }, { "epoch": 63.4, "learning_rate": 3.405498303713715e-05, "loss": 0.0025, "step": 264010 }, { "epoch": 63.4, "learning_rate": 3.405158092487739e-05, "loss": 0.0032, "step": 264020 }, { "epoch": 63.4, "learning_rate": 3.4048178894815916e-05, "loss": 0.0018, "step": 264030 }, { "epoch": 63.4, "learning_rate": 3.404477694697025e-05, "loss": 0.0017, "step": 264040 }, { "epoch": 63.41, "learning_rate": 3.404137508135794e-05, "loss": 0.0017, "step": 264050 }, { "epoch": 63.41, "learning_rate": 3.403797329799652e-05, "loss": 0.0046, "step": 264060 }, { "epoch": 63.41, "learning_rate": 3.4034571596903517e-05, "loss": 0.0026, "step": 264070 }, { "epoch": 63.41, "learning_rate": 3.403116997809646e-05, "loss": 0.0024, "step": 264080 }, { "epoch": 63.42, "learning_rate": 3.402776844159289e-05, "loss": 0.0039, "step": 264090 }, { "epoch": 63.42, "learning_rate": 3.402436698741035e-05, "loss": 0.0026, "step": 264100 }, { "epoch": 63.42, "learning_rate": 3.402096561556633e-05, "loss": 0.0024, "step": 264110 }, { "epoch": 63.42, "learning_rate": 3.401756432607841e-05, "loss": 0.002, "step": 264120 }, { "epoch": 63.43, "learning_rate": 3.401416311896408e-05, "loss": 0.0025, "step": 264130 }, { "epoch": 63.43, "learning_rate": 3.40107619942409e-05, "loss": 0.0022, "step": 264140 }, { "epoch": 63.43, "learning_rate": 3.400736095192637e-05, "loss": 0.002, "step": 264150 }, { "epoch": 63.43, "learning_rate": 3.400395999203805e-05, "loss": 0.0022, "step": 264160 }, { "epoch": 63.43, "learning_rate": 3.400055911459346e-05, "loss": 0.0019, "step": 264170 }, { "epoch": 63.44, "learning_rate": 3.39971583196101e-05, "loss": 0.0021, "step": 264180 }, { "epoch": 63.44, "learning_rate": 3.3993757607105534e-05, "loss": 0.007, "step": 264190 }, { "epoch": 63.44, "learning_rate": 3.3990356977097274e-05, "loss": 0.0096, "step": 264200 }, { "epoch": 63.44, "learning_rate": 3.398695642960284e-05, "loss": 0.002, "step": 264210 }, { "epoch": 63.45, "learning_rate": 3.398355596463977e-05, "loss": 0.002, "step": 264220 }, { "epoch": 63.45, "learning_rate": 3.398015558222559e-05, "loss": 0.0021, "step": 264230 }, { "epoch": 63.45, "learning_rate": 3.397675528237783e-05, "loss": 0.0052, "step": 264240 }, { "epoch": 63.45, "learning_rate": 3.397335506511399e-05, "loss": 0.0025, "step": 264250 }, { "epoch": 63.45, "learning_rate": 3.396995493045163e-05, "loss": 0.0028, "step": 264260 }, { "epoch": 63.46, "learning_rate": 3.396655487840823e-05, "loss": 0.0024, "step": 264270 }, { "epoch": 63.46, "learning_rate": 3.396315490900137e-05, "loss": 0.0019, "step": 264280 }, { "epoch": 63.46, "learning_rate": 3.3959755022248516e-05, "loss": 0.0024, "step": 264290 }, { "epoch": 63.46, "learning_rate": 3.395635521816724e-05, "loss": 0.0017, "step": 264300 }, { "epoch": 63.47, "learning_rate": 3.395295549677503e-05, "loss": 0.0017, "step": 264310 }, { "epoch": 63.47, "learning_rate": 3.394955585808944e-05, "loss": 0.0017, "step": 264320 }, { "epoch": 63.47, "learning_rate": 3.394615630212797e-05, "loss": 0.0021, "step": 264330 }, { "epoch": 63.47, "learning_rate": 3.3942756828908125e-05, "loss": 0.0046, "step": 264340 }, { "epoch": 63.48, "learning_rate": 3.393935743844745e-05, "loss": 0.0023, "step": 264350 }, { "epoch": 63.48, "learning_rate": 3.393595813076347e-05, "loss": 0.0022, "step": 264360 }, { "epoch": 63.48, "learning_rate": 3.393255890587369e-05, "loss": 0.0018, "step": 264370 }, { "epoch": 63.48, "learning_rate": 3.392915976379564e-05, "loss": 0.0032, "step": 264380 }, { "epoch": 63.48, "learning_rate": 3.392576070454683e-05, "loss": 0.0185, "step": 264390 }, { "epoch": 63.49, "learning_rate": 3.3922361728144804e-05, "loss": 0.0023, "step": 264400 }, { "epoch": 63.49, "learning_rate": 3.391896283460703e-05, "loss": 0.0081, "step": 264410 }, { "epoch": 63.49, "learning_rate": 3.3915564023951075e-05, "loss": 0.0042, "step": 264420 }, { "epoch": 63.49, "learning_rate": 3.391216529619442e-05, "loss": 0.0027, "step": 264430 }, { "epoch": 63.5, "learning_rate": 3.3908766651354625e-05, "loss": 0.0039, "step": 264440 }, { "epoch": 63.5, "learning_rate": 3.3905368089449154e-05, "loss": 0.0021, "step": 264450 }, { "epoch": 63.5, "learning_rate": 3.390196961049558e-05, "loss": 0.0021, "step": 264460 }, { "epoch": 63.5, "learning_rate": 3.3898571214511373e-05, "loss": 0.0022, "step": 264470 }, { "epoch": 63.51, "learning_rate": 3.389517290151406e-05, "loss": 0.0018, "step": 264480 }, { "epoch": 63.51, "learning_rate": 3.389177467152117e-05, "loss": 0.0019, "step": 264490 }, { "epoch": 63.51, "learning_rate": 3.38883765245502e-05, "loss": 0.0023, "step": 264500 }, { "epoch": 63.51, "learning_rate": 3.388497846061867e-05, "loss": 0.0045, "step": 264510 }, { "epoch": 63.51, "learning_rate": 3.38815804797441e-05, "loss": 0.0024, "step": 264520 }, { "epoch": 63.52, "learning_rate": 3.3878182581944e-05, "loss": 0.0022, "step": 264530 }, { "epoch": 63.52, "learning_rate": 3.387478476723589e-05, "loss": 0.0022, "step": 264540 }, { "epoch": 63.52, "learning_rate": 3.387138703563726e-05, "loss": 0.0036, "step": 264550 }, { "epoch": 63.52, "learning_rate": 3.3867989387165646e-05, "loss": 0.0024, "step": 264560 }, { "epoch": 63.53, "learning_rate": 3.386459182183854e-05, "loss": 0.0019, "step": 264570 }, { "epoch": 63.53, "learning_rate": 3.386119433967348e-05, "loss": 0.005, "step": 264580 }, { "epoch": 63.53, "learning_rate": 3.385779694068793e-05, "loss": 0.0019, "step": 264590 }, { "epoch": 63.53, "learning_rate": 3.385439962489946e-05, "loss": 0.0065, "step": 264600 }, { "epoch": 63.53, "learning_rate": 3.385100239232554e-05, "loss": 0.0024, "step": 264610 }, { "epoch": 63.54, "learning_rate": 3.384760524298368e-05, "loss": 0.0019, "step": 264620 }, { "epoch": 63.54, "learning_rate": 3.3844208176891405e-05, "loss": 0.0052, "step": 264630 }, { "epoch": 63.54, "learning_rate": 3.3840811194066205e-05, "loss": 0.003, "step": 264640 }, { "epoch": 63.54, "learning_rate": 3.3837414294525615e-05, "loss": 0.0022, "step": 264650 }, { "epoch": 63.55, "learning_rate": 3.383401747828711e-05, "loss": 0.0018, "step": 264660 }, { "epoch": 63.55, "learning_rate": 3.383062074536823e-05, "loss": 0.0023, "step": 264670 }, { "epoch": 63.55, "learning_rate": 3.3827224095786456e-05, "loss": 0.0022, "step": 264680 }, { "epoch": 63.55, "learning_rate": 3.382382752955931e-05, "loss": 0.0023, "step": 264690 }, { "epoch": 63.56, "learning_rate": 3.3820431046704296e-05, "loss": 0.003, "step": 264700 }, { "epoch": 63.56, "learning_rate": 3.381703464723889e-05, "loss": 0.0034, "step": 264710 }, { "epoch": 63.56, "learning_rate": 3.3813638331180655e-05, "loss": 0.0032, "step": 264720 }, { "epoch": 63.56, "learning_rate": 3.381024209854704e-05, "loss": 0.0032, "step": 264730 }, { "epoch": 63.56, "learning_rate": 3.380684594935559e-05, "loss": 0.002, "step": 264740 }, { "epoch": 63.57, "learning_rate": 3.38034498836238e-05, "loss": 0.0045, "step": 264750 }, { "epoch": 63.57, "learning_rate": 3.3800053901369135e-05, "loss": 0.0033, "step": 264760 }, { "epoch": 63.57, "learning_rate": 3.379665800260915e-05, "loss": 0.0022, "step": 264770 }, { "epoch": 63.57, "learning_rate": 3.3793262187361306e-05, "loss": 0.0019, "step": 264780 }, { "epoch": 63.58, "learning_rate": 3.3789866455643146e-05, "loss": 0.0021, "step": 264790 }, { "epoch": 63.58, "learning_rate": 3.378647080747213e-05, "loss": 0.0024, "step": 264800 }, { "epoch": 63.58, "learning_rate": 3.378307524286578e-05, "loss": 0.0026, "step": 264810 }, { "epoch": 63.58, "learning_rate": 3.377967976184161e-05, "loss": 0.0021, "step": 264820 }, { "epoch": 63.59, "learning_rate": 3.3776284364417094e-05, "loss": 0.0021, "step": 264830 }, { "epoch": 63.59, "learning_rate": 3.377288905060976e-05, "loss": 0.0026, "step": 264840 }, { "epoch": 63.59, "learning_rate": 3.376949382043707e-05, "loss": 0.0026, "step": 264850 }, { "epoch": 63.59, "learning_rate": 3.376609867391656e-05, "loss": 0.0036, "step": 264860 }, { "epoch": 63.59, "learning_rate": 3.37627036110657e-05, "loss": 0.0032, "step": 264870 }, { "epoch": 63.6, "learning_rate": 3.375930863190202e-05, "loss": 0.0027, "step": 264880 }, { "epoch": 63.6, "learning_rate": 3.3755913736443e-05, "loss": 0.0042, "step": 264890 }, { "epoch": 63.6, "learning_rate": 3.3752518924706114e-05, "loss": 0.0032, "step": 264900 }, { "epoch": 63.6, "learning_rate": 3.37491241967089e-05, "loss": 0.0021, "step": 264910 }, { "epoch": 63.61, "learning_rate": 3.374572955246882e-05, "loss": 0.0034, "step": 264920 }, { "epoch": 63.61, "learning_rate": 3.37423349920034e-05, "loss": 0.0025, "step": 264930 }, { "epoch": 63.61, "learning_rate": 3.37389405153301e-05, "loss": 0.0024, "step": 264940 }, { "epoch": 63.61, "learning_rate": 3.3735546122466465e-05, "loss": 0.0033, "step": 264950 }, { "epoch": 63.61, "learning_rate": 3.3732151813429945e-05, "loss": 0.0024, "step": 264960 }, { "epoch": 63.62, "learning_rate": 3.3728757588238046e-05, "loss": 0.003, "step": 264970 }, { "epoch": 63.62, "learning_rate": 3.3725363446908284e-05, "loss": 0.0024, "step": 264980 }, { "epoch": 63.62, "learning_rate": 3.372196938945811e-05, "loss": 0.0021, "step": 264990 }, { "epoch": 63.62, "learning_rate": 3.371857541590507e-05, "loss": 0.0021, "step": 265000 }, { "epoch": 63.63, "learning_rate": 3.3715181526266605e-05, "loss": 0.0031, "step": 265010 }, { "epoch": 63.63, "learning_rate": 3.371178772056025e-05, "loss": 0.0037, "step": 265020 }, { "epoch": 63.63, "learning_rate": 3.3708393998803475e-05, "loss": 0.0035, "step": 265030 }, { "epoch": 63.63, "learning_rate": 3.370500036101375e-05, "loss": 0.0052, "step": 265040 }, { "epoch": 63.64, "learning_rate": 3.370160680720862e-05, "loss": 0.002, "step": 265050 }, { "epoch": 63.64, "learning_rate": 3.3698213337405516e-05, "loss": 0.0022, "step": 265060 }, { "epoch": 63.64, "learning_rate": 3.369481995162198e-05, "loss": 0.0027, "step": 265070 }, { "epoch": 63.64, "learning_rate": 3.369142664987546e-05, "loss": 0.003, "step": 265080 }, { "epoch": 63.64, "learning_rate": 3.368803343218349e-05, "loss": 0.0031, "step": 265090 }, { "epoch": 63.65, "learning_rate": 3.36846402985635e-05, "loss": 0.0021, "step": 265100 }, { "epoch": 63.65, "learning_rate": 3.3681247249033034e-05, "loss": 0.0027, "step": 265110 }, { "epoch": 63.65, "learning_rate": 3.367785428360955e-05, "loss": 0.0052, "step": 265120 }, { "epoch": 63.65, "learning_rate": 3.367446140231052e-05, "loss": 0.0018, "step": 265130 }, { "epoch": 63.66, "learning_rate": 3.367106860515348e-05, "loss": 0.002, "step": 265140 }, { "epoch": 63.66, "learning_rate": 3.366767589215587e-05, "loss": 0.002, "step": 265150 }, { "epoch": 63.66, "learning_rate": 3.3664283263335214e-05, "loss": 0.0023, "step": 265160 }, { "epoch": 63.66, "learning_rate": 3.366089071870896e-05, "loss": 0.0029, "step": 265170 }, { "epoch": 63.67, "learning_rate": 3.365749825829463e-05, "loss": 0.0021, "step": 265180 }, { "epoch": 63.67, "learning_rate": 3.3654105882109693e-05, "loss": 0.002, "step": 265190 }, { "epoch": 63.67, "learning_rate": 3.365071359017161e-05, "loss": 0.0023, "step": 265200 }, { "epoch": 63.67, "learning_rate": 3.36473213824979e-05, "loss": 0.0021, "step": 265210 }, { "epoch": 63.67, "learning_rate": 3.364392925910602e-05, "loss": 0.0023, "step": 265220 }, { "epoch": 63.68, "learning_rate": 3.364053722001348e-05, "loss": 0.0072, "step": 265230 }, { "epoch": 63.68, "learning_rate": 3.3637145265237735e-05, "loss": 0.0028, "step": 265240 }, { "epoch": 63.68, "learning_rate": 3.36337533947963e-05, "loss": 0.0022, "step": 265250 }, { "epoch": 63.68, "learning_rate": 3.3630361608706616e-05, "loss": 0.0023, "step": 265260 }, { "epoch": 63.69, "learning_rate": 3.3626969906986194e-05, "loss": 0.0026, "step": 265270 }, { "epoch": 63.69, "learning_rate": 3.36235782896525e-05, "loss": 0.0023, "step": 265280 }, { "epoch": 63.69, "learning_rate": 3.3620186756723015e-05, "loss": 0.0025, "step": 265290 }, { "epoch": 63.69, "learning_rate": 3.3616795308215245e-05, "loss": 0.0023, "step": 265300 }, { "epoch": 63.69, "learning_rate": 3.3613403944146624e-05, "loss": 0.002, "step": 265310 }, { "epoch": 63.7, "learning_rate": 3.361001266453468e-05, "loss": 0.0035, "step": 265320 }, { "epoch": 63.7, "learning_rate": 3.360662146939687e-05, "loss": 0.0021, "step": 265330 }, { "epoch": 63.7, "learning_rate": 3.360323035875064e-05, "loss": 0.0021, "step": 265340 }, { "epoch": 63.7, "learning_rate": 3.3599839332613524e-05, "loss": 0.005, "step": 265350 }, { "epoch": 63.71, "learning_rate": 3.359644839100295e-05, "loss": 0.0022, "step": 265360 }, { "epoch": 63.71, "learning_rate": 3.3593057533936445e-05, "loss": 0.0028, "step": 265370 }, { "epoch": 63.71, "learning_rate": 3.358966676143144e-05, "loss": 0.0023, "step": 265380 }, { "epoch": 63.71, "learning_rate": 3.358627607350544e-05, "loss": 0.0046, "step": 265390 }, { "epoch": 63.72, "learning_rate": 3.3582885470175906e-05, "loss": 0.011, "step": 265400 }, { "epoch": 63.72, "learning_rate": 3.357949495146032e-05, "loss": 0.0021, "step": 265410 }, { "epoch": 63.72, "learning_rate": 3.357610451737615e-05, "loss": 0.002, "step": 265420 }, { "epoch": 63.72, "learning_rate": 3.357271416794088e-05, "loss": 0.0023, "step": 265430 }, { "epoch": 63.72, "learning_rate": 3.356932390317197e-05, "loss": 0.0035, "step": 265440 }, { "epoch": 63.73, "learning_rate": 3.3565933723086894e-05, "loss": 0.0024, "step": 265450 }, { "epoch": 63.73, "learning_rate": 3.356254362770316e-05, "loss": 0.0028, "step": 265460 }, { "epoch": 63.73, "learning_rate": 3.3559153617038207e-05, "loss": 0.0026, "step": 265470 }, { "epoch": 63.73, "learning_rate": 3.3555763691109496e-05, "loss": 0.0022, "step": 265480 }, { "epoch": 63.74, "learning_rate": 3.355237384993454e-05, "loss": 0.0036, "step": 265490 }, { "epoch": 63.74, "learning_rate": 3.354898409353076e-05, "loss": 0.0022, "step": 265500 }, { "epoch": 63.74, "learning_rate": 3.354559442191567e-05, "loss": 0.0047, "step": 265510 }, { "epoch": 63.74, "learning_rate": 3.354220483510672e-05, "loss": 0.0023, "step": 265520 }, { "epoch": 63.75, "learning_rate": 3.353881533312139e-05, "loss": 0.002, "step": 265530 }, { "epoch": 63.75, "learning_rate": 3.353542591597714e-05, "loss": 0.002, "step": 265540 }, { "epoch": 63.75, "learning_rate": 3.3532036583691436e-05, "loss": 0.0021, "step": 265550 }, { "epoch": 63.75, "learning_rate": 3.3528647336281755e-05, "loss": 0.002, "step": 265560 }, { "epoch": 63.75, "learning_rate": 3.3525258173765564e-05, "loss": 0.0033, "step": 265570 }, { "epoch": 63.76, "learning_rate": 3.352186909616033e-05, "loss": 0.002, "step": 265580 }, { "epoch": 63.76, "learning_rate": 3.3518480103483526e-05, "loss": 0.0036, "step": 265590 }, { "epoch": 63.76, "learning_rate": 3.35150911957526e-05, "loss": 0.0021, "step": 265600 }, { "epoch": 63.76, "learning_rate": 3.3511702372985055e-05, "loss": 0.0022, "step": 265610 }, { "epoch": 63.77, "learning_rate": 3.350831363519831e-05, "loss": 0.0111, "step": 265620 }, { "epoch": 63.77, "learning_rate": 3.350492498240988e-05, "loss": 0.0022, "step": 265630 }, { "epoch": 63.77, "learning_rate": 3.350153641463717e-05, "loss": 0.0021, "step": 265640 }, { "epoch": 63.77, "learning_rate": 3.3498147931897706e-05, "loss": 0.004, "step": 265650 }, { "epoch": 63.77, "learning_rate": 3.3494759534208905e-05, "loss": 0.0052, "step": 265660 }, { "epoch": 63.78, "learning_rate": 3.3491371221588274e-05, "loss": 0.0021, "step": 265670 }, { "epoch": 63.78, "learning_rate": 3.3487982994053255e-05, "loss": 0.0043, "step": 265680 }, { "epoch": 63.78, "learning_rate": 3.348459485162129e-05, "loss": 0.002, "step": 265690 }, { "epoch": 63.78, "learning_rate": 3.348120679430987e-05, "loss": 0.0021, "step": 265700 }, { "epoch": 63.79, "learning_rate": 3.347781882213644e-05, "loss": 0.0049, "step": 265710 }, { "epoch": 63.79, "learning_rate": 3.3474430935118487e-05, "loss": 0.0026, "step": 265720 }, { "epoch": 63.79, "learning_rate": 3.347104313327344e-05, "loss": 0.002, "step": 265730 }, { "epoch": 63.79, "learning_rate": 3.346765541661878e-05, "loss": 0.0021, "step": 265740 }, { "epoch": 63.8, "learning_rate": 3.346426778517197e-05, "loss": 0.002, "step": 265750 }, { "epoch": 63.8, "learning_rate": 3.346088023895044e-05, "loss": 0.0018, "step": 265760 }, { "epoch": 63.8, "learning_rate": 3.34574927779717e-05, "loss": 0.0033, "step": 265770 }, { "epoch": 63.8, "learning_rate": 3.345410540225316e-05, "loss": 0.0023, "step": 265780 }, { "epoch": 63.8, "learning_rate": 3.345071811181231e-05, "loss": 0.0034, "step": 265790 }, { "epoch": 63.81, "learning_rate": 3.3447330906666584e-05, "loss": 0.0023, "step": 265800 }, { "epoch": 63.81, "learning_rate": 3.344394378683347e-05, "loss": 0.0024, "step": 265810 }, { "epoch": 63.81, "learning_rate": 3.344055675233041e-05, "loss": 0.002, "step": 265820 }, { "epoch": 63.81, "learning_rate": 3.343716980317484e-05, "loss": 0.003, "step": 265830 }, { "epoch": 63.82, "learning_rate": 3.343378293938425e-05, "loss": 0.0019, "step": 265840 }, { "epoch": 63.82, "learning_rate": 3.343039616097607e-05, "loss": 0.0023, "step": 265850 }, { "epoch": 63.82, "learning_rate": 3.342700946796777e-05, "loss": 0.0021, "step": 265860 }, { "epoch": 63.82, "learning_rate": 3.34236228603768e-05, "loss": 0.0019, "step": 265870 }, { "epoch": 63.83, "learning_rate": 3.342023633822062e-05, "loss": 0.0044, "step": 265880 }, { "epoch": 63.83, "learning_rate": 3.341684990151668e-05, "loss": 0.0023, "step": 265890 }, { "epoch": 63.83, "learning_rate": 3.3413463550282435e-05, "loss": 0.0018, "step": 265900 }, { "epoch": 63.83, "learning_rate": 3.3410077284535346e-05, "loss": 0.0031, "step": 265910 }, { "epoch": 63.83, "learning_rate": 3.3406691104292844e-05, "loss": 0.0022, "step": 265920 }, { "epoch": 63.84, "learning_rate": 3.340330500957241e-05, "loss": 0.002, "step": 265930 }, { "epoch": 63.84, "learning_rate": 3.3399919000391455e-05, "loss": 0.0025, "step": 265940 }, { "epoch": 63.84, "learning_rate": 3.339653307676748e-05, "loss": 0.0019, "step": 265950 }, { "epoch": 63.84, "learning_rate": 3.339314723871789e-05, "loss": 0.002, "step": 265960 }, { "epoch": 63.85, "learning_rate": 3.3389761486260185e-05, "loss": 0.0023, "step": 265970 }, { "epoch": 63.85, "learning_rate": 3.338637581941179e-05, "loss": 0.0019, "step": 265980 }, { "epoch": 63.85, "learning_rate": 3.338299023819012e-05, "loss": 0.0019, "step": 265990 }, { "epoch": 63.85, "learning_rate": 3.337960474261268e-05, "loss": 0.0023, "step": 266000 }, { "epoch": 63.85, "learning_rate": 3.337621933269688e-05, "loss": 0.0027, "step": 266010 }, { "epoch": 63.86, "learning_rate": 3.33728340084602e-05, "loss": 0.0021, "step": 266020 }, { "epoch": 63.86, "learning_rate": 3.336944876992006e-05, "loss": 0.002, "step": 266030 }, { "epoch": 63.86, "learning_rate": 3.336606361709393e-05, "loss": 0.0073, "step": 266040 }, { "epoch": 63.86, "learning_rate": 3.336267854999926e-05, "loss": 0.0072, "step": 266050 }, { "epoch": 63.87, "learning_rate": 3.335929356865345e-05, "loss": 0.0019, "step": 266060 }, { "epoch": 63.87, "learning_rate": 3.335590867307401e-05, "loss": 0.0022, "step": 266070 }, { "epoch": 63.87, "learning_rate": 3.335252386327834e-05, "loss": 0.0027, "step": 266080 }, { "epoch": 63.87, "learning_rate": 3.334913913928391e-05, "loss": 0.002, "step": 266090 }, { "epoch": 63.88, "learning_rate": 3.3345754501108143e-05, "loss": 0.0024, "step": 266100 }, { "epoch": 63.88, "learning_rate": 3.334236994876851e-05, "loss": 0.0021, "step": 266110 }, { "epoch": 63.88, "learning_rate": 3.3338985482282453e-05, "loss": 0.002, "step": 266120 }, { "epoch": 63.88, "learning_rate": 3.333560110166738e-05, "loss": 0.0019, "step": 266130 }, { "epoch": 63.88, "learning_rate": 3.333221680694077e-05, "loss": 0.0022, "step": 266140 }, { "epoch": 63.89, "learning_rate": 3.332883259812004e-05, "loss": 0.0056, "step": 266150 }, { "epoch": 63.89, "learning_rate": 3.332544847522267e-05, "loss": 0.0023, "step": 266160 }, { "epoch": 63.89, "learning_rate": 3.3322064438266054e-05, "loss": 0.0026, "step": 266170 }, { "epoch": 63.89, "learning_rate": 3.3318680487267665e-05, "loss": 0.0023, "step": 266180 }, { "epoch": 63.9, "learning_rate": 3.331529662224495e-05, "loss": 0.002, "step": 266190 }, { "epoch": 63.9, "learning_rate": 3.331191284321531e-05, "loss": 0.0035, "step": 266200 }, { "epoch": 63.9, "learning_rate": 3.3308529150196235e-05, "loss": 0.0021, "step": 266210 }, { "epoch": 63.9, "learning_rate": 3.330514554320512e-05, "loss": 0.002, "step": 266220 }, { "epoch": 63.91, "learning_rate": 3.3301762022259446e-05, "loss": 0.0019, "step": 266230 }, { "epoch": 63.91, "learning_rate": 3.329837858737661e-05, "loss": 0.002, "step": 266240 }, { "epoch": 63.91, "learning_rate": 3.329499523857409e-05, "loss": 0.002, "step": 266250 }, { "epoch": 63.91, "learning_rate": 3.3291611975869296e-05, "loss": 0.0021, "step": 266260 }, { "epoch": 63.91, "learning_rate": 3.328822879927966e-05, "loss": 0.005, "step": 266270 }, { "epoch": 63.92, "learning_rate": 3.3284845708822656e-05, "loss": 0.0023, "step": 266280 }, { "epoch": 63.92, "learning_rate": 3.3281462704515675e-05, "loss": 0.002, "step": 266290 }, { "epoch": 63.92, "learning_rate": 3.327807978637619e-05, "loss": 0.0021, "step": 266300 }, { "epoch": 63.92, "learning_rate": 3.327469695442161e-05, "loss": 0.0019, "step": 266310 }, { "epoch": 63.93, "learning_rate": 3.32713142086694e-05, "loss": 0.0021, "step": 266320 }, { "epoch": 63.93, "learning_rate": 3.326793154913696e-05, "loss": 0.0022, "step": 266330 }, { "epoch": 63.93, "learning_rate": 3.326454897584173e-05, "loss": 0.0021, "step": 266340 }, { "epoch": 63.93, "learning_rate": 3.3261166488801185e-05, "loss": 0.0019, "step": 266350 }, { "epoch": 63.93, "learning_rate": 3.32577840880327e-05, "loss": 0.0021, "step": 266360 }, { "epoch": 63.94, "learning_rate": 3.3254401773553755e-05, "loss": 0.002, "step": 266370 }, { "epoch": 63.94, "learning_rate": 3.325101954538174e-05, "loss": 0.002, "step": 266380 }, { "epoch": 63.94, "learning_rate": 3.3247637403534144e-05, "loss": 0.002, "step": 266390 }, { "epoch": 63.94, "learning_rate": 3.3244255348028355e-05, "loss": 0.002, "step": 266400 }, { "epoch": 63.95, "learning_rate": 3.3240873378881796e-05, "loss": 0.0031, "step": 266410 }, { "epoch": 63.95, "learning_rate": 3.323749149611193e-05, "loss": 0.0018, "step": 266420 }, { "epoch": 63.95, "learning_rate": 3.323410969973616e-05, "loss": 0.003, "step": 266430 }, { "epoch": 64.0, "learning_rate": 3.3230727989771945e-05, "loss": 0.0027, "step": 266440 }, { "epoch": 64.0, "learning_rate": 3.322734636623668e-05, "loss": 0.0023, "step": 266450 }, { "epoch": 64.01, "learning_rate": 3.3223964829147834e-05, "loss": 0.0038, "step": 266460 }, { "epoch": 64.01, "learning_rate": 3.322058337852281e-05, "loss": 0.0031, "step": 266470 }, { "epoch": 64.01, "learning_rate": 3.3217202014379024e-05, "loss": 0.0019, "step": 266480 }, { "epoch": 64.01, "learning_rate": 3.321382073673393e-05, "loss": 0.0028, "step": 266490 }, { "epoch": 64.02, "learning_rate": 3.3210439545604926e-05, "loss": 0.002, "step": 266500 }, { "epoch": 64.02, "learning_rate": 3.320705844100948e-05, "loss": 0.0046, "step": 266510 }, { "epoch": 64.02, "learning_rate": 3.320367742296498e-05, "loss": 0.0029, "step": 266520 }, { "epoch": 64.02, "learning_rate": 3.320029649148888e-05, "loss": 0.002, "step": 266530 }, { "epoch": 64.02, "learning_rate": 3.31969156465986e-05, "loss": 0.0017, "step": 266540 }, { "epoch": 64.03, "learning_rate": 3.3193534888311525e-05, "loss": 0.0025, "step": 266550 }, { "epoch": 64.03, "learning_rate": 3.319015421664514e-05, "loss": 0.0024, "step": 266560 }, { "epoch": 64.03, "learning_rate": 3.318677363161683e-05, "loss": 0.0031, "step": 266570 }, { "epoch": 64.03, "learning_rate": 3.3183393133244035e-05, "loss": 0.002, "step": 266580 }, { "epoch": 64.04, "learning_rate": 3.318001272154416e-05, "loss": 0.0028, "step": 266590 }, { "epoch": 64.04, "learning_rate": 3.317663239653466e-05, "loss": 0.0028, "step": 266600 }, { "epoch": 64.04, "learning_rate": 3.3173252158232915e-05, "loss": 0.0037, "step": 266610 }, { "epoch": 64.04, "learning_rate": 3.316987200665638e-05, "loss": 0.0024, "step": 266620 }, { "epoch": 64.05, "learning_rate": 3.316649194182246e-05, "loss": 0.0025, "step": 266630 }, { "epoch": 64.05, "learning_rate": 3.3163111963748576e-05, "loss": 0.0029, "step": 266640 }, { "epoch": 64.05, "learning_rate": 3.315973207245218e-05, "loss": 0.0022, "step": 266650 }, { "epoch": 64.05, "learning_rate": 3.315635226795063e-05, "loss": 0.0028, "step": 266660 }, { "epoch": 64.05, "learning_rate": 3.315297255026141e-05, "loss": 0.0024, "step": 266670 }, { "epoch": 64.06, "learning_rate": 3.3149592919401894e-05, "loss": 0.0023, "step": 266680 }, { "epoch": 64.06, "learning_rate": 3.314621337538953e-05, "loss": 0.0024, "step": 266690 }, { "epoch": 64.06, "learning_rate": 3.314283391824173e-05, "loss": 0.0031, "step": 266700 }, { "epoch": 64.06, "learning_rate": 3.313945454797588e-05, "loss": 0.0026, "step": 266710 }, { "epoch": 64.07, "learning_rate": 3.313607526460944e-05, "loss": 0.0022, "step": 266720 }, { "epoch": 64.07, "learning_rate": 3.313269606815979e-05, "loss": 0.0019, "step": 266730 }, { "epoch": 64.07, "learning_rate": 3.312931695864439e-05, "loss": 0.0032, "step": 266740 }, { "epoch": 64.07, "learning_rate": 3.312593793608061e-05, "loss": 0.002, "step": 266750 }, { "epoch": 64.07, "learning_rate": 3.31225590004859e-05, "loss": 0.0041, "step": 266760 }, { "epoch": 64.08, "learning_rate": 3.311918015187766e-05, "loss": 0.0024, "step": 266770 }, { "epoch": 64.08, "learning_rate": 3.3115801390273305e-05, "loss": 0.0026, "step": 266780 }, { "epoch": 64.08, "learning_rate": 3.311242271569025e-05, "loss": 0.0021, "step": 266790 }, { "epoch": 64.08, "learning_rate": 3.31090441281459e-05, "loss": 0.0022, "step": 266800 }, { "epoch": 64.09, "learning_rate": 3.3105665627657704e-05, "loss": 0.0022, "step": 266810 }, { "epoch": 64.09, "learning_rate": 3.310228721424301e-05, "loss": 0.0018, "step": 266820 }, { "epoch": 64.09, "learning_rate": 3.309890888791931e-05, "loss": 0.0016, "step": 266830 }, { "epoch": 64.09, "learning_rate": 3.309553064870397e-05, "loss": 0.0028, "step": 266840 }, { "epoch": 64.1, "learning_rate": 3.309215249661437e-05, "loss": 0.0027, "step": 266850 }, { "epoch": 64.1, "learning_rate": 3.308877443166799e-05, "loss": 0.0038, "step": 266860 }, { "epoch": 64.1, "learning_rate": 3.308539645388219e-05, "loss": 0.0066, "step": 266870 }, { "epoch": 64.1, "learning_rate": 3.308201856327441e-05, "loss": 0.0019, "step": 266880 }, { "epoch": 64.1, "learning_rate": 3.307864075986204e-05, "loss": 0.0022, "step": 266890 }, { "epoch": 64.11, "learning_rate": 3.3075263043662506e-05, "loss": 0.0023, "step": 266900 }, { "epoch": 64.11, "learning_rate": 3.3071885414693206e-05, "loss": 0.0038, "step": 266910 }, { "epoch": 64.11, "learning_rate": 3.3068507872971545e-05, "loss": 0.003, "step": 266920 }, { "epoch": 64.11, "learning_rate": 3.306513041851493e-05, "loss": 0.0023, "step": 266930 }, { "epoch": 64.12, "learning_rate": 3.306175305134078e-05, "loss": 0.0021, "step": 266940 }, { "epoch": 64.12, "learning_rate": 3.30583757714665e-05, "loss": 0.0025, "step": 266950 }, { "epoch": 64.12, "learning_rate": 3.305499857890948e-05, "loss": 0.0026, "step": 266960 }, { "epoch": 64.12, "learning_rate": 3.305162147368717e-05, "loss": 0.0045, "step": 266970 }, { "epoch": 64.13, "learning_rate": 3.304824445581692e-05, "loss": 0.0028, "step": 266980 }, { "epoch": 64.13, "learning_rate": 3.304486752531616e-05, "loss": 0.0247, "step": 266990 }, { "epoch": 64.13, "learning_rate": 3.3041490682202306e-05, "loss": 0.0028, "step": 267000 }, { "epoch": 64.13, "learning_rate": 3.3038113926492736e-05, "loss": 0.0056, "step": 267010 }, { "epoch": 64.13, "learning_rate": 3.303473725820489e-05, "loss": 0.0026, "step": 267020 }, { "epoch": 64.14, "learning_rate": 3.303136067735612e-05, "loss": 0.0033, "step": 267030 }, { "epoch": 64.14, "learning_rate": 3.3027984183963887e-05, "loss": 0.0023, "step": 267040 }, { "epoch": 64.14, "learning_rate": 3.302460777804556e-05, "loss": 0.0024, "step": 267050 }, { "epoch": 64.14, "learning_rate": 3.302123145961853e-05, "loss": 0.0026, "step": 267060 }, { "epoch": 64.15, "learning_rate": 3.301785522870022e-05, "loss": 0.0065, "step": 267070 }, { "epoch": 64.15, "learning_rate": 3.301447908530804e-05, "loss": 0.0053, "step": 267080 }, { "epoch": 64.15, "learning_rate": 3.301110302945936e-05, "loss": 0.0023, "step": 267090 }, { "epoch": 64.15, "learning_rate": 3.300772706117161e-05, "loss": 0.0025, "step": 267100 }, { "epoch": 64.15, "learning_rate": 3.300435118046217e-05, "loss": 0.0043, "step": 267110 }, { "epoch": 64.16, "learning_rate": 3.3000975387348454e-05, "loss": 0.0028, "step": 267120 }, { "epoch": 64.16, "learning_rate": 3.2997599681847836e-05, "loss": 0.0019, "step": 267130 }, { "epoch": 64.16, "learning_rate": 3.299422406397775e-05, "loss": 0.0024, "step": 267140 }, { "epoch": 64.16, "learning_rate": 3.2990848533755556e-05, "loss": 0.0022, "step": 267150 }, { "epoch": 64.17, "learning_rate": 3.29874730911987e-05, "loss": 0.0052, "step": 267160 }, { "epoch": 64.17, "learning_rate": 3.2984097736324515e-05, "loss": 0.0021, "step": 267170 }, { "epoch": 64.17, "learning_rate": 3.298072246915046e-05, "loss": 0.0018, "step": 267180 }, { "epoch": 64.17, "learning_rate": 3.2977347289693896e-05, "loss": 0.0027, "step": 267190 }, { "epoch": 64.18, "learning_rate": 3.2973972197972216e-05, "loss": 0.002, "step": 267200 }, { "epoch": 64.18, "learning_rate": 3.297059719400283e-05, "loss": 0.0019, "step": 267210 }, { "epoch": 64.18, "learning_rate": 3.2967222277803136e-05, "loss": 0.0034, "step": 267220 }, { "epoch": 64.18, "learning_rate": 3.296384744939051e-05, "loss": 0.0027, "step": 267230 }, { "epoch": 64.18, "learning_rate": 3.2960472708782365e-05, "loss": 0.002, "step": 267240 }, { "epoch": 64.19, "learning_rate": 3.2957098055996086e-05, "loss": 0.0022, "step": 267250 }, { "epoch": 64.19, "learning_rate": 3.2953723491049074e-05, "loss": 0.002, "step": 267260 }, { "epoch": 64.19, "learning_rate": 3.295034901395869e-05, "loss": 0.0021, "step": 267270 }, { "epoch": 64.19, "learning_rate": 3.2946974624742374e-05, "loss": 0.0024, "step": 267280 }, { "epoch": 64.2, "learning_rate": 3.294360032341747e-05, "loss": 0.0028, "step": 267290 }, { "epoch": 64.2, "learning_rate": 3.2940226110001416e-05, "loss": 0.0018, "step": 267300 }, { "epoch": 64.2, "learning_rate": 3.293685198451155e-05, "loss": 0.0028, "step": 267310 }, { "epoch": 64.2, "learning_rate": 3.293347794696532e-05, "loss": 0.0017, "step": 267320 }, { "epoch": 64.21, "learning_rate": 3.293010399738009e-05, "loss": 0.0024, "step": 267330 }, { "epoch": 64.21, "learning_rate": 3.292673013577322e-05, "loss": 0.0022, "step": 267340 }, { "epoch": 64.21, "learning_rate": 3.292335636216215e-05, "loss": 0.0027, "step": 267350 }, { "epoch": 64.21, "learning_rate": 3.2919982676564227e-05, "loss": 0.002, "step": 267360 }, { "epoch": 64.21, "learning_rate": 3.291660907899686e-05, "loss": 0.0039, "step": 267370 }, { "epoch": 64.22, "learning_rate": 3.291323556947743e-05, "loss": 0.0019, "step": 267380 }, { "epoch": 64.22, "learning_rate": 3.290986214802334e-05, "loss": 0.0023, "step": 267390 }, { "epoch": 64.22, "learning_rate": 3.2906488814651956e-05, "loss": 0.0017, "step": 267400 }, { "epoch": 64.22, "learning_rate": 3.2903115569380664e-05, "loss": 0.0019, "step": 267410 }, { "epoch": 64.23, "learning_rate": 3.2899742412226874e-05, "loss": 0.0023, "step": 267420 }, { "epoch": 64.23, "learning_rate": 3.289636934320793e-05, "loss": 0.0019, "step": 267430 }, { "epoch": 64.23, "learning_rate": 3.289299636234127e-05, "loss": 0.002, "step": 267440 }, { "epoch": 64.23, "learning_rate": 3.288962346964423e-05, "loss": 0.0027, "step": 267450 }, { "epoch": 64.23, "learning_rate": 3.288625066513422e-05, "loss": 0.002, "step": 267460 }, { "epoch": 64.24, "learning_rate": 3.288287794882861e-05, "loss": 0.0026, "step": 267470 }, { "epoch": 64.24, "learning_rate": 3.287950532074481e-05, "loss": 0.0022, "step": 267480 }, { "epoch": 64.24, "learning_rate": 3.287613278090017e-05, "loss": 0.0024, "step": 267490 }, { "epoch": 64.24, "learning_rate": 3.287276032931208e-05, "loss": 0.0017, "step": 267500 }, { "epoch": 64.25, "learning_rate": 3.286938796599793e-05, "loss": 0.0022, "step": 267510 }, { "epoch": 64.25, "learning_rate": 3.28660156909751e-05, "loss": 0.0063, "step": 267520 }, { "epoch": 64.25, "learning_rate": 3.286264350426096e-05, "loss": 0.0025, "step": 267530 }, { "epoch": 64.25, "learning_rate": 3.2859271405872906e-05, "loss": 0.0031, "step": 267540 }, { "epoch": 64.26, "learning_rate": 3.2855899395828304e-05, "loss": 0.0019, "step": 267550 }, { "epoch": 64.26, "learning_rate": 3.285252747414456e-05, "loss": 0.0017, "step": 267560 }, { "epoch": 64.26, "learning_rate": 3.2849155640839e-05, "loss": 0.0018, "step": 267570 }, { "epoch": 64.26, "learning_rate": 3.2845783895929066e-05, "loss": 0.0023, "step": 267580 }, { "epoch": 64.26, "learning_rate": 3.2842412239432086e-05, "loss": 0.0022, "step": 267590 }, { "epoch": 64.27, "learning_rate": 3.2839040671365474e-05, "loss": 0.002, "step": 267600 }, { "epoch": 64.27, "learning_rate": 3.2835669191746565e-05, "loss": 0.0025, "step": 267610 }, { "epoch": 64.27, "learning_rate": 3.283229780059278e-05, "loss": 0.002, "step": 267620 }, { "epoch": 64.27, "learning_rate": 3.282892649792148e-05, "loss": 0.0022, "step": 267630 }, { "epoch": 64.28, "learning_rate": 3.282555528375002e-05, "loss": 0.0019, "step": 267640 }, { "epoch": 64.28, "learning_rate": 3.28221841580958e-05, "loss": 0.0041, "step": 267650 }, { "epoch": 64.28, "learning_rate": 3.281881312097618e-05, "loss": 0.0026, "step": 267660 }, { "epoch": 64.28, "learning_rate": 3.281544217240855e-05, "loss": 0.0024, "step": 267670 }, { "epoch": 64.29, "learning_rate": 3.2812071312410265e-05, "loss": 0.0102, "step": 267680 }, { "epoch": 64.29, "learning_rate": 3.280870054099871e-05, "loss": 0.0019, "step": 267690 }, { "epoch": 64.29, "learning_rate": 3.2805329858191266e-05, "loss": 0.0022, "step": 267700 }, { "epoch": 64.29, "learning_rate": 3.280195926400528e-05, "loss": 0.0036, "step": 267710 }, { "epoch": 64.29, "learning_rate": 3.279858875845816e-05, "loss": 0.0034, "step": 267720 }, { "epoch": 64.3, "learning_rate": 3.279521834156724e-05, "loss": 0.0019, "step": 267730 }, { "epoch": 64.3, "learning_rate": 3.2791848013349915e-05, "loss": 0.0026, "step": 267740 }, { "epoch": 64.3, "learning_rate": 3.278847777382354e-05, "loss": 0.0023, "step": 267750 }, { "epoch": 64.3, "learning_rate": 3.278510762300551e-05, "loss": 0.0017, "step": 267760 }, { "epoch": 64.31, "learning_rate": 3.2781737560913186e-05, "loss": 0.0027, "step": 267770 }, { "epoch": 64.31, "learning_rate": 3.27783675875639e-05, "loss": 0.0017, "step": 267780 }, { "epoch": 64.31, "learning_rate": 3.277499770297508e-05, "loss": 0.0039, "step": 267790 }, { "epoch": 64.31, "learning_rate": 3.2771627907164043e-05, "loss": 0.0044, "step": 267800 }, { "epoch": 64.31, "learning_rate": 3.27682582001482e-05, "loss": 0.0022, "step": 267810 }, { "epoch": 64.32, "learning_rate": 3.2764888581944875e-05, "loss": 0.0019, "step": 267820 }, { "epoch": 64.32, "learning_rate": 3.2761519052571486e-05, "loss": 0.0084, "step": 267830 }, { "epoch": 64.32, "learning_rate": 3.2758149612045355e-05, "loss": 0.0033, "step": 267840 }, { "epoch": 64.32, "learning_rate": 3.2754780260383856e-05, "loss": 0.0018, "step": 267850 }, { "epoch": 64.33, "learning_rate": 3.2751410997604384e-05, "loss": 0.0039, "step": 267860 }, { "epoch": 64.33, "learning_rate": 3.2748041823724265e-05, "loss": 0.0026, "step": 267870 }, { "epoch": 64.33, "learning_rate": 3.274467273876091e-05, "loss": 0.0019, "step": 267880 }, { "epoch": 64.33, "learning_rate": 3.274130374273162e-05, "loss": 0.0071, "step": 267890 }, { "epoch": 64.34, "learning_rate": 3.273793483565383e-05, "loss": 0.0024, "step": 267900 }, { "epoch": 64.34, "learning_rate": 3.273456601754486e-05, "loss": 0.0027, "step": 267910 }, { "epoch": 64.34, "learning_rate": 3.2731197288422065e-05, "loss": 0.0045, "step": 267920 }, { "epoch": 64.34, "learning_rate": 3.272782864830284e-05, "loss": 0.0023, "step": 267930 }, { "epoch": 64.34, "learning_rate": 3.272446009720451e-05, "loss": 0.0019, "step": 267940 }, { "epoch": 64.35, "learning_rate": 3.272109163514448e-05, "loss": 0.0021, "step": 267950 }, { "epoch": 64.35, "learning_rate": 3.2717723262140065e-05, "loss": 0.0017, "step": 267960 }, { "epoch": 64.35, "learning_rate": 3.271435497820867e-05, "loss": 0.0035, "step": 267970 }, { "epoch": 64.35, "learning_rate": 3.271098678336763e-05, "loss": 0.002, "step": 267980 }, { "epoch": 64.36, "learning_rate": 3.27076186776343e-05, "loss": 0.0019, "step": 267990 }, { "epoch": 64.36, "learning_rate": 3.2704250661026045e-05, "loss": 0.0026, "step": 268000 }, { "epoch": 64.36, "learning_rate": 3.270088273356023e-05, "loss": 0.0026, "step": 268010 }, { "epoch": 64.36, "learning_rate": 3.269751489525422e-05, "loss": 0.0023, "step": 268020 }, { "epoch": 64.37, "learning_rate": 3.2694147146125345e-05, "loss": 0.0057, "step": 268030 }, { "epoch": 64.37, "learning_rate": 3.2690779486191e-05, "loss": 0.0037, "step": 268040 }, { "epoch": 64.37, "learning_rate": 3.2687411915468525e-05, "loss": 0.0019, "step": 268050 }, { "epoch": 64.37, "learning_rate": 3.268404443397525e-05, "loss": 0.0018, "step": 268060 }, { "epoch": 64.37, "learning_rate": 3.268067704172858e-05, "loss": 0.0022, "step": 268070 }, { "epoch": 64.38, "learning_rate": 3.267730973874582e-05, "loss": 0.0022, "step": 268080 }, { "epoch": 64.38, "learning_rate": 3.267394252504438e-05, "loss": 0.004, "step": 268090 }, { "epoch": 64.38, "learning_rate": 3.2670575400641546e-05, "loss": 0.0023, "step": 268100 }, { "epoch": 64.38, "learning_rate": 3.266720836555475e-05, "loss": 0.0017, "step": 268110 }, { "epoch": 64.39, "learning_rate": 3.266384141980129e-05, "loss": 0.0029, "step": 268120 }, { "epoch": 64.39, "learning_rate": 3.266047456339853e-05, "loss": 0.0026, "step": 268130 }, { "epoch": 64.39, "learning_rate": 3.265710779636384e-05, "loss": 0.0028, "step": 268140 }, { "epoch": 64.39, "learning_rate": 3.2653741118714555e-05, "loss": 0.0019, "step": 268150 }, { "epoch": 64.39, "learning_rate": 3.265037453046803e-05, "loss": 0.0044, "step": 268160 }, { "epoch": 64.4, "learning_rate": 3.264700803164161e-05, "loss": 0.0026, "step": 268170 }, { "epoch": 64.4, "learning_rate": 3.264364162225268e-05, "loss": 0.0018, "step": 268180 }, { "epoch": 64.4, "learning_rate": 3.2640275302318566e-05, "loss": 0.0025, "step": 268190 }, { "epoch": 64.4, "learning_rate": 3.26369090718566e-05, "loss": 0.0031, "step": 268200 }, { "epoch": 64.41, "learning_rate": 3.263354293088417e-05, "loss": 0.0018, "step": 268210 }, { "epoch": 64.41, "learning_rate": 3.263017687941858e-05, "loss": 0.0024, "step": 268220 }, { "epoch": 64.41, "learning_rate": 3.2626810917477226e-05, "loss": 0.0019, "step": 268230 }, { "epoch": 64.41, "learning_rate": 3.262344504507742e-05, "loss": 0.0018, "step": 268240 }, { "epoch": 64.42, "learning_rate": 3.2620079262236534e-05, "loss": 0.0044, "step": 268250 }, { "epoch": 64.42, "learning_rate": 3.26167135689719e-05, "loss": 0.002, "step": 268260 }, { "epoch": 64.42, "learning_rate": 3.261334796530087e-05, "loss": 0.0022, "step": 268270 }, { "epoch": 64.42, "learning_rate": 3.260998245124078e-05, "loss": 0.0021, "step": 268280 }, { "epoch": 64.42, "learning_rate": 3.260661702680899e-05, "loss": 0.0019, "step": 268290 }, { "epoch": 64.43, "learning_rate": 3.2603251692022854e-05, "loss": 0.0019, "step": 268300 }, { "epoch": 64.43, "learning_rate": 3.2599886446899687e-05, "loss": 0.0025, "step": 268310 }, { "epoch": 64.43, "learning_rate": 3.2596521291456864e-05, "loss": 0.0031, "step": 268320 }, { "epoch": 64.43, "learning_rate": 3.25931562257117e-05, "loss": 0.0034, "step": 268330 }, { "epoch": 64.44, "learning_rate": 3.2589791249681575e-05, "loss": 0.0021, "step": 268340 }, { "epoch": 64.44, "learning_rate": 3.258642636338382e-05, "loss": 0.0018, "step": 268350 }, { "epoch": 64.44, "learning_rate": 3.258306156683573e-05, "loss": 0.0025, "step": 268360 }, { "epoch": 64.44, "learning_rate": 3.257969686005472e-05, "loss": 0.0027, "step": 268370 }, { "epoch": 64.45, "learning_rate": 3.257633224305807e-05, "loss": 0.0069, "step": 268380 }, { "epoch": 64.45, "learning_rate": 3.257296771586318e-05, "loss": 0.0019, "step": 268390 }, { "epoch": 64.45, "learning_rate": 3.256960327848733e-05, "loss": 0.0021, "step": 268400 }, { "epoch": 64.45, "learning_rate": 3.256623893094791e-05, "loss": 0.0038, "step": 268410 }, { "epoch": 64.45, "learning_rate": 3.2562874673262236e-05, "loss": 0.0017, "step": 268420 }, { "epoch": 64.46, "learning_rate": 3.255951050544765e-05, "loss": 0.002, "step": 268430 }, { "epoch": 64.46, "learning_rate": 3.2556146427521493e-05, "loss": 0.0018, "step": 268440 }, { "epoch": 64.46, "learning_rate": 3.2552782439501105e-05, "loss": 0.0023, "step": 268450 }, { "epoch": 64.46, "learning_rate": 3.254941854140382e-05, "loss": 0.0054, "step": 268460 }, { "epoch": 64.47, "learning_rate": 3.2546054733246963e-05, "loss": 0.0028, "step": 268470 }, { "epoch": 64.47, "learning_rate": 3.254269101504792e-05, "loss": 0.0045, "step": 268480 }, { "epoch": 64.47, "learning_rate": 3.253932738682398e-05, "loss": 0.002, "step": 268490 }, { "epoch": 64.47, "learning_rate": 3.253596384859248e-05, "loss": 0.0023, "step": 268500 }, { "epoch": 64.47, "learning_rate": 3.2532600400370784e-05, "loss": 0.0019, "step": 268510 }, { "epoch": 64.48, "learning_rate": 3.2529237042176184e-05, "loss": 0.0024, "step": 268520 }, { "epoch": 64.48, "learning_rate": 3.252587377402608e-05, "loss": 0.003, "step": 268530 }, { "epoch": 64.48, "learning_rate": 3.252251059593774e-05, "loss": 0.0019, "step": 268540 }, { "epoch": 64.48, "learning_rate": 3.2519147507928545e-05, "loss": 0.0024, "step": 268550 }, { "epoch": 64.49, "learning_rate": 3.251578451001581e-05, "loss": 0.0027, "step": 268560 }, { "epoch": 64.49, "learning_rate": 3.2512421602216846e-05, "loss": 0.0033, "step": 268570 }, { "epoch": 64.49, "learning_rate": 3.2509058784549016e-05, "loss": 0.0021, "step": 268580 }, { "epoch": 64.49, "learning_rate": 3.250569605702965e-05, "loss": 0.0018, "step": 268590 }, { "epoch": 64.5, "learning_rate": 3.2502333419676066e-05, "loss": 0.0016, "step": 268600 }, { "epoch": 64.5, "learning_rate": 3.2498970872505606e-05, "loss": 0.0019, "step": 268610 }, { "epoch": 64.5, "learning_rate": 3.24956084155356e-05, "loss": 0.0035, "step": 268620 }, { "epoch": 64.5, "learning_rate": 3.249224604878338e-05, "loss": 0.0026, "step": 268630 }, { "epoch": 64.5, "learning_rate": 3.248888377226626e-05, "loss": 0.0024, "step": 268640 }, { "epoch": 64.51, "learning_rate": 3.248552158600158e-05, "loss": 0.0016, "step": 268650 }, { "epoch": 64.51, "learning_rate": 3.2482159490006656e-05, "loss": 0.002, "step": 268660 }, { "epoch": 64.51, "learning_rate": 3.247879748429885e-05, "loss": 0.0022, "step": 268670 }, { "epoch": 64.51, "learning_rate": 3.247543556889545e-05, "loss": 0.0019, "step": 268680 }, { "epoch": 64.52, "learning_rate": 3.247207374381383e-05, "loss": 0.0022, "step": 268690 }, { "epoch": 64.52, "learning_rate": 3.246871200907127e-05, "loss": 0.002, "step": 268700 }, { "epoch": 64.52, "learning_rate": 3.246535036468511e-05, "loss": 0.0023, "step": 268710 }, { "epoch": 64.52, "learning_rate": 3.246198881067269e-05, "loss": 0.0025, "step": 268720 }, { "epoch": 64.53, "learning_rate": 3.245862734705131e-05, "loss": 0.0045, "step": 268730 }, { "epoch": 64.53, "learning_rate": 3.2455265973838325e-05, "loss": 0.0018, "step": 268740 }, { "epoch": 64.53, "learning_rate": 3.2451904691051035e-05, "loss": 0.0031, "step": 268750 }, { "epoch": 64.53, "learning_rate": 3.2448543498706786e-05, "loss": 0.0029, "step": 268760 }, { "epoch": 64.53, "learning_rate": 3.2445182396822904e-05, "loss": 0.002, "step": 268770 }, { "epoch": 64.54, "learning_rate": 3.244182138541667e-05, "loss": 0.0018, "step": 268780 }, { "epoch": 64.54, "learning_rate": 3.243846046450546e-05, "loss": 0.0026, "step": 268790 }, { "epoch": 64.54, "learning_rate": 3.2435099634106545e-05, "loss": 0.0026, "step": 268800 }, { "epoch": 64.54, "learning_rate": 3.2431738894237294e-05, "loss": 0.0021, "step": 268810 }, { "epoch": 64.55, "learning_rate": 3.242837824491499e-05, "loss": 0.0025, "step": 268820 }, { "epoch": 64.55, "learning_rate": 3.242501768615699e-05, "loss": 0.0019, "step": 268830 }, { "epoch": 64.55, "learning_rate": 3.2421657217980606e-05, "loss": 0.0031, "step": 268840 }, { "epoch": 64.55, "learning_rate": 3.2418296840403115e-05, "loss": 0.0022, "step": 268850 }, { "epoch": 64.55, "learning_rate": 3.24149365534419e-05, "loss": 0.0034, "step": 268860 }, { "epoch": 64.56, "learning_rate": 3.2411576357114214e-05, "loss": 0.0021, "step": 268870 }, { "epoch": 64.56, "learning_rate": 3.240821625143743e-05, "loss": 0.0065, "step": 268880 }, { "epoch": 64.56, "learning_rate": 3.240485623642885e-05, "loss": 0.0016, "step": 268890 }, { "epoch": 64.56, "learning_rate": 3.240149631210578e-05, "loss": 0.0031, "step": 268900 }, { "epoch": 64.57, "learning_rate": 3.239813647848556e-05, "loss": 0.003, "step": 268910 }, { "epoch": 64.57, "learning_rate": 3.2394776735585466e-05, "loss": 0.0036, "step": 268920 }, { "epoch": 64.57, "learning_rate": 3.239141708342287e-05, "loss": 0.0022, "step": 268930 }, { "epoch": 64.57, "learning_rate": 3.238805752201503e-05, "loss": 0.0024, "step": 268940 }, { "epoch": 64.58, "learning_rate": 3.2384698051379314e-05, "loss": 0.0023, "step": 268950 }, { "epoch": 64.58, "learning_rate": 3.2381338671532984e-05, "loss": 0.0023, "step": 268960 }, { "epoch": 64.58, "learning_rate": 3.2377979382493404e-05, "loss": 0.0018, "step": 268970 }, { "epoch": 64.58, "learning_rate": 3.2374620184277874e-05, "loss": 0.002, "step": 268980 }, { "epoch": 64.58, "learning_rate": 3.237126107690367e-05, "loss": 0.0026, "step": 268990 }, { "epoch": 64.59, "learning_rate": 3.2367902060388155e-05, "loss": 0.0033, "step": 269000 }, { "epoch": 64.59, "learning_rate": 3.2364543134748606e-05, "loss": 0.0041, "step": 269010 }, { "epoch": 64.59, "learning_rate": 3.2361184300002354e-05, "loss": 0.0019, "step": 269020 }, { "epoch": 64.59, "learning_rate": 3.23578255561667e-05, "loss": 0.0198, "step": 269030 }, { "epoch": 64.6, "learning_rate": 3.235446690325897e-05, "loss": 0.0043, "step": 269040 }, { "epoch": 64.6, "learning_rate": 3.235110834129647e-05, "loss": 0.0024, "step": 269050 }, { "epoch": 64.6, "learning_rate": 3.2347749870296486e-05, "loss": 0.0024, "step": 269060 }, { "epoch": 64.6, "learning_rate": 3.234439149027637e-05, "loss": 0.0035, "step": 269070 }, { "epoch": 64.61, "learning_rate": 3.234103320125338e-05, "loss": 0.003, "step": 269080 }, { "epoch": 64.61, "learning_rate": 3.233767500324488e-05, "loss": 0.0021, "step": 269090 }, { "epoch": 64.61, "learning_rate": 3.233431689626812e-05, "loss": 0.0031, "step": 269100 }, { "epoch": 64.61, "learning_rate": 3.2330958880340476e-05, "loss": 0.0025, "step": 269110 }, { "epoch": 64.61, "learning_rate": 3.2327600955479184e-05, "loss": 0.0019, "step": 269120 }, { "epoch": 64.62, "learning_rate": 3.2324243121701615e-05, "loss": 0.0026, "step": 269130 }, { "epoch": 64.62, "learning_rate": 3.2320885379025034e-05, "loss": 0.0021, "step": 269140 }, { "epoch": 64.62, "learning_rate": 3.231752772746674e-05, "loss": 0.0042, "step": 269150 }, { "epoch": 64.62, "learning_rate": 3.231417016704408e-05, "loss": 0.0015, "step": 269160 }, { "epoch": 64.63, "learning_rate": 3.231081269777431e-05, "loss": 0.0028, "step": 269170 }, { "epoch": 64.63, "learning_rate": 3.230745531967479e-05, "loss": 0.0024, "step": 269180 }, { "epoch": 64.63, "learning_rate": 3.2304098032762756e-05, "loss": 0.0025, "step": 269190 }, { "epoch": 64.63, "learning_rate": 3.2300740837055567e-05, "loss": 0.0029, "step": 269200 }, { "epoch": 64.63, "learning_rate": 3.229738373257052e-05, "loss": 0.0042, "step": 269210 }, { "epoch": 64.64, "learning_rate": 3.2294026719324886e-05, "loss": 0.0024, "step": 269220 }, { "epoch": 64.64, "learning_rate": 3.229066979733601e-05, "loss": 0.0028, "step": 269230 }, { "epoch": 64.64, "learning_rate": 3.2287312966621136e-05, "loss": 0.0019, "step": 269240 }, { "epoch": 64.64, "learning_rate": 3.2283956227197626e-05, "loss": 0.003, "step": 269250 }, { "epoch": 64.65, "learning_rate": 3.2280599579082736e-05, "loss": 0.002, "step": 269260 }, { "epoch": 64.65, "learning_rate": 3.22772430222938e-05, "loss": 0.0017, "step": 269270 }, { "epoch": 64.65, "learning_rate": 3.2273886556848104e-05, "loss": 0.0037, "step": 269280 }, { "epoch": 64.65, "learning_rate": 3.227053018276293e-05, "loss": 0.002, "step": 269290 }, { "epoch": 64.66, "learning_rate": 3.2267173900055605e-05, "loss": 0.0025, "step": 269300 }, { "epoch": 64.66, "learning_rate": 3.2263817708743395e-05, "loss": 0.0233, "step": 269310 }, { "epoch": 64.66, "learning_rate": 3.226046160884364e-05, "loss": 0.0024, "step": 269320 }, { "epoch": 64.66, "learning_rate": 3.2257105600373585e-05, "loss": 0.0027, "step": 269330 }, { "epoch": 64.66, "learning_rate": 3.2253749683350586e-05, "loss": 0.0022, "step": 269340 }, { "epoch": 64.67, "learning_rate": 3.225039385779189e-05, "loss": 0.0028, "step": 269350 }, { "epoch": 64.67, "learning_rate": 3.2247038123714815e-05, "loss": 0.0022, "step": 269360 }, { "epoch": 64.67, "learning_rate": 3.2243682481136664e-05, "loss": 0.0024, "step": 269370 }, { "epoch": 64.67, "learning_rate": 3.2240326930074704e-05, "loss": 0.0017, "step": 269380 }, { "epoch": 64.68, "learning_rate": 3.223697147054627e-05, "loss": 0.0021, "step": 269390 }, { "epoch": 64.68, "learning_rate": 3.223361610256861e-05, "loss": 0.0023, "step": 269400 }, { "epoch": 64.68, "learning_rate": 3.2230260826159066e-05, "loss": 0.0021, "step": 269410 }, { "epoch": 64.68, "learning_rate": 3.22269056413349e-05, "loss": 0.0025, "step": 269420 }, { "epoch": 64.69, "learning_rate": 3.222355054811339e-05, "loss": 0.0021, "step": 269430 }, { "epoch": 64.69, "learning_rate": 3.222019554651188e-05, "loss": 0.0027, "step": 269440 }, { "epoch": 64.69, "learning_rate": 3.22168406365476e-05, "loss": 0.0019, "step": 269450 }, { "epoch": 64.69, "learning_rate": 3.22134858182379e-05, "loss": 0.0018, "step": 269460 }, { "epoch": 64.69, "learning_rate": 3.2210131091600016e-05, "loss": 0.0019, "step": 269470 }, { "epoch": 64.7, "learning_rate": 3.220677645665129e-05, "loss": 0.0024, "step": 269480 }, { "epoch": 64.7, "learning_rate": 3.220342191340897e-05, "loss": 0.0023, "step": 269490 }, { "epoch": 64.7, "learning_rate": 3.220006746189037e-05, "loss": 0.0025, "step": 269500 }, { "epoch": 64.7, "learning_rate": 3.219671310211277e-05, "loss": 0.002, "step": 269510 }, { "epoch": 64.71, "learning_rate": 3.219335883409344e-05, "loss": 0.002, "step": 269520 }, { "epoch": 64.71, "learning_rate": 3.2190004657849724e-05, "loss": 0.0023, "step": 269530 }, { "epoch": 64.71, "learning_rate": 3.2186650573398836e-05, "loss": 0.0019, "step": 269540 }, { "epoch": 64.71, "learning_rate": 3.2183296580758135e-05, "loss": 0.0027, "step": 269550 }, { "epoch": 64.71, "learning_rate": 3.2179942679944865e-05, "loss": 0.007, "step": 269560 }, { "epoch": 64.72, "learning_rate": 3.21765888709763e-05, "loss": 0.0031, "step": 269570 }, { "epoch": 64.72, "learning_rate": 3.2173235153869764e-05, "loss": 0.0032, "step": 269580 }, { "epoch": 64.72, "learning_rate": 3.21698815286425e-05, "loss": 0.0022, "step": 269590 }, { "epoch": 64.72, "learning_rate": 3.2166527995311836e-05, "loss": 0.0023, "step": 269600 }, { "epoch": 64.73, "learning_rate": 3.2163174553895023e-05, "loss": 0.0027, "step": 269610 }, { "epoch": 64.73, "learning_rate": 3.2159821204409366e-05, "loss": 0.0024, "step": 269620 }, { "epoch": 64.73, "learning_rate": 3.2156467946872144e-05, "loss": 0.0018, "step": 269630 }, { "epoch": 64.73, "learning_rate": 3.215311478130062e-05, "loss": 0.0021, "step": 269640 }, { "epoch": 64.74, "learning_rate": 3.214976170771211e-05, "loss": 0.0029, "step": 269650 }, { "epoch": 64.74, "learning_rate": 3.214640872612387e-05, "loss": 0.0032, "step": 269660 }, { "epoch": 64.74, "learning_rate": 3.214305583655318e-05, "loss": 0.0027, "step": 269670 }, { "epoch": 64.74, "learning_rate": 3.213970303901732e-05, "loss": 0.0023, "step": 269680 }, { "epoch": 64.74, "learning_rate": 3.2136350333533605e-05, "loss": 0.0024, "step": 269690 }, { "epoch": 64.75, "learning_rate": 3.2132997720119294e-05, "loss": 0.002, "step": 269700 }, { "epoch": 64.75, "learning_rate": 3.2129645198791634e-05, "loss": 0.0021, "step": 269710 }, { "epoch": 64.75, "learning_rate": 3.212629276956796e-05, "loss": 0.0023, "step": 269720 }, { "epoch": 64.75, "learning_rate": 3.21229404324655e-05, "loss": 0.0025, "step": 269730 }, { "epoch": 64.76, "learning_rate": 3.211958818750157e-05, "loss": 0.0018, "step": 269740 }, { "epoch": 64.76, "learning_rate": 3.2116236034693413e-05, "loss": 0.0021, "step": 269750 }, { "epoch": 64.76, "learning_rate": 3.211288397405835e-05, "loss": 0.002, "step": 269760 }, { "epoch": 64.76, "learning_rate": 3.210953200561362e-05, "loss": 0.0025, "step": 269770 }, { "epoch": 64.77, "learning_rate": 3.21061801293765e-05, "loss": 0.002, "step": 269780 }, { "epoch": 64.77, "learning_rate": 3.21028283453643e-05, "loss": 0.0026, "step": 269790 }, { "epoch": 64.77, "learning_rate": 3.209947665359426e-05, "loss": 0.0018, "step": 269800 }, { "epoch": 64.77, "learning_rate": 3.2096125054083665e-05, "loss": 0.0023, "step": 269810 }, { "epoch": 64.77, "learning_rate": 3.209277354684979e-05, "loss": 0.0026, "step": 269820 }, { "epoch": 64.78, "learning_rate": 3.2089422131909916e-05, "loss": 0.0019, "step": 269830 }, { "epoch": 64.78, "learning_rate": 3.2086070809281314e-05, "loss": 0.0022, "step": 269840 }, { "epoch": 64.78, "learning_rate": 3.2082719578981235e-05, "loss": 0.0025, "step": 269850 }, { "epoch": 64.78, "learning_rate": 3.207936844102699e-05, "loss": 0.0018, "step": 269860 }, { "epoch": 64.79, "learning_rate": 3.2076017395435816e-05, "loss": 0.0023, "step": 269870 }, { "epoch": 64.79, "learning_rate": 3.207266644222501e-05, "loss": 0.0018, "step": 269880 }, { "epoch": 64.79, "learning_rate": 3.206931558141181e-05, "loss": 0.002, "step": 269890 }, { "epoch": 64.79, "learning_rate": 3.206596481301353e-05, "loss": 0.0022, "step": 269900 }, { "epoch": 64.79, "learning_rate": 3.2062614137047395e-05, "loss": 0.0019, "step": 269910 }, { "epoch": 64.8, "learning_rate": 3.205926355353073e-05, "loss": 0.003, "step": 269920 }, { "epoch": 64.8, "learning_rate": 3.205591306248075e-05, "loss": 0.0019, "step": 269930 }, { "epoch": 64.8, "learning_rate": 3.2052562663914746e-05, "loss": 0.0023, "step": 269940 }, { "epoch": 64.8, "learning_rate": 3.204921235784998e-05, "loss": 0.0022, "step": 269950 }, { "epoch": 64.81, "learning_rate": 3.204586214430372e-05, "loss": 0.0047, "step": 269960 }, { "epoch": 64.81, "learning_rate": 3.204251202329324e-05, "loss": 0.0021, "step": 269970 }, { "epoch": 64.81, "learning_rate": 3.203916199483581e-05, "loss": 0.002, "step": 269980 }, { "epoch": 64.81, "learning_rate": 3.2035812058948684e-05, "loss": 0.0019, "step": 269990 }, { "epoch": 64.82, "learning_rate": 3.203246221564914e-05, "loss": 0.0025, "step": 270000 }, { "epoch": 64.82, "learning_rate": 3.2029112464954424e-05, "loss": 0.0042, "step": 270010 }, { "epoch": 64.82, "learning_rate": 3.202576280688183e-05, "loss": 0.0017, "step": 270020 }, { "epoch": 64.82, "learning_rate": 3.202241324144858e-05, "loss": 0.0025, "step": 270030 }, { "epoch": 64.82, "learning_rate": 3.201906376867198e-05, "loss": 0.0022, "step": 270040 }, { "epoch": 64.83, "learning_rate": 3.201571438856926e-05, "loss": 0.0019, "step": 270050 }, { "epoch": 64.83, "learning_rate": 3.2012365101157726e-05, "loss": 0.002, "step": 270060 }, { "epoch": 64.83, "learning_rate": 3.2009015906454605e-05, "loss": 0.0022, "step": 270070 }, { "epoch": 64.83, "learning_rate": 3.200566680447714e-05, "loss": 0.0043, "step": 270080 }, { "epoch": 64.84, "learning_rate": 3.200231779524264e-05, "loss": 0.0018, "step": 270090 }, { "epoch": 64.84, "learning_rate": 3.199896887876834e-05, "loss": 0.003, "step": 270100 }, { "epoch": 64.84, "learning_rate": 3.1995620055071504e-05, "loss": 0.0017, "step": 270110 }, { "epoch": 64.84, "learning_rate": 3.19922713241694e-05, "loss": 0.0022, "step": 270120 }, { "epoch": 64.85, "learning_rate": 3.198892268607927e-05, "loss": 0.0059, "step": 270130 }, { "epoch": 64.85, "learning_rate": 3.19855741408184e-05, "loss": 0.0017, "step": 270140 }, { "epoch": 64.85, "learning_rate": 3.198222568840401e-05, "loss": 0.0019, "step": 270150 }, { "epoch": 64.85, "learning_rate": 3.1978877328853396e-05, "loss": 0.0022, "step": 270160 }, { "epoch": 64.85, "learning_rate": 3.197552906218377e-05, "loss": 0.0022, "step": 270170 }, { "epoch": 64.86, "learning_rate": 3.1972180888412455e-05, "loss": 0.0018, "step": 270180 }, { "epoch": 64.86, "learning_rate": 3.196883280755665e-05, "loss": 0.0018, "step": 270190 }, { "epoch": 64.86, "learning_rate": 3.196548481963364e-05, "loss": 0.0018, "step": 270200 }, { "epoch": 64.86, "learning_rate": 3.196213692466068e-05, "loss": 0.0017, "step": 270210 }, { "epoch": 64.87, "learning_rate": 3.195878912265499e-05, "loss": 0.0019, "step": 270220 }, { "epoch": 64.87, "learning_rate": 3.195544141363388e-05, "loss": 0.0021, "step": 270230 }, { "epoch": 64.87, "learning_rate": 3.1952093797614554e-05, "loss": 0.0017, "step": 270240 }, { "epoch": 64.87, "learning_rate": 3.1948746274614296e-05, "loss": 0.0119, "step": 270250 }, { "epoch": 64.87, "learning_rate": 3.194539884465034e-05, "loss": 0.0022, "step": 270260 }, { "epoch": 64.88, "learning_rate": 3.194205150773997e-05, "loss": 0.0029, "step": 270270 }, { "epoch": 64.88, "learning_rate": 3.193870426390041e-05, "loss": 0.0022, "step": 270280 }, { "epoch": 64.88, "learning_rate": 3.1935357113148906e-05, "loss": 0.0021, "step": 270290 }, { "epoch": 64.88, "learning_rate": 3.193201005550275e-05, "loss": 0.0023, "step": 270300 }, { "epoch": 64.89, "learning_rate": 3.192866309097913e-05, "loss": 0.0026, "step": 270310 }, { "epoch": 64.89, "learning_rate": 3.192531621959536e-05, "loss": 0.0017, "step": 270320 }, { "epoch": 64.89, "learning_rate": 3.192196944136864e-05, "loss": 0.0022, "step": 270330 }, { "epoch": 64.89, "learning_rate": 3.1918622756316264e-05, "loss": 0.004, "step": 270340 }, { "epoch": 64.9, "learning_rate": 3.1915276164455455e-05, "loss": 0.006, "step": 270350 }, { "epoch": 64.9, "learning_rate": 3.191192966580344e-05, "loss": 0.0019, "step": 270360 }, { "epoch": 64.9, "learning_rate": 3.190858326037751e-05, "loss": 0.0261, "step": 270370 }, { "epoch": 64.9, "learning_rate": 3.1905236948194884e-05, "loss": 0.0017, "step": 270380 }, { "epoch": 64.9, "learning_rate": 3.190189072927283e-05, "loss": 0.0018, "step": 270390 }, { "epoch": 64.91, "learning_rate": 3.1898544603628563e-05, "loss": 0.0018, "step": 270400 }, { "epoch": 64.91, "learning_rate": 3.189519857127936e-05, "loss": 0.0018, "step": 270410 }, { "epoch": 64.91, "learning_rate": 3.1891852632242455e-05, "loss": 0.002, "step": 270420 }, { "epoch": 64.91, "learning_rate": 3.188850678653509e-05, "loss": 0.0019, "step": 270430 }, { "epoch": 64.92, "learning_rate": 3.1885161034174524e-05, "loss": 0.002, "step": 270440 }, { "epoch": 64.92, "learning_rate": 3.188181537517797e-05, "loss": 0.0024, "step": 270450 }, { "epoch": 64.92, "learning_rate": 3.187846980956271e-05, "loss": 0.0017, "step": 270460 }, { "epoch": 64.92, "learning_rate": 3.187512433734594e-05, "loss": 0.0047, "step": 270470 }, { "epoch": 64.93, "learning_rate": 3.1871778958544965e-05, "loss": 0.0016, "step": 270480 }, { "epoch": 64.93, "learning_rate": 3.186843367317699e-05, "loss": 0.0019, "step": 270490 }, { "epoch": 64.93, "learning_rate": 3.186508848125923e-05, "loss": 0.0019, "step": 270500 }, { "epoch": 64.93, "learning_rate": 3.186174338280898e-05, "loss": 0.0021, "step": 270510 }, { "epoch": 64.93, "learning_rate": 3.185839837784345e-05, "loss": 0.0019, "step": 270520 }, { "epoch": 64.94, "learning_rate": 3.185505346637989e-05, "loss": 0.0184, "step": 270530 }, { "epoch": 64.94, "learning_rate": 3.1851708648435516e-05, "loss": 0.0016, "step": 270540 }, { "epoch": 64.94, "learning_rate": 3.1848363924027616e-05, "loss": 0.0019, "step": 270550 }, { "epoch": 64.94, "learning_rate": 3.1845019293173386e-05, "loss": 0.0017, "step": 270560 }, { "epoch": 64.95, "learning_rate": 3.184167475589007e-05, "loss": 0.002, "step": 270570 }, { "epoch": 64.95, "learning_rate": 3.183833031219493e-05, "loss": 0.0024, "step": 270580 }, { "epoch": 64.95, "learning_rate": 3.1834985962105167e-05, "loss": 0.0018, "step": 270590 }, { "epoch": 65.0, "learning_rate": 3.183164170563806e-05, "loss": 0.0017, "step": 270600 }, { "epoch": 65.0, "learning_rate": 3.182829754281081e-05, "loss": 0.0017, "step": 270610 }, { "epoch": 65.01, "learning_rate": 3.182495347364068e-05, "loss": 0.0019, "step": 270620 }, { "epoch": 65.01, "learning_rate": 3.1821609498144886e-05, "loss": 0.0016, "step": 270630 }, { "epoch": 65.01, "learning_rate": 3.181826561634066e-05, "loss": 0.0022, "step": 270640 }, { "epoch": 65.01, "learning_rate": 3.181492182824526e-05, "loss": 0.0021, "step": 270650 }, { "epoch": 65.01, "learning_rate": 3.181157813387589e-05, "loss": 0.0018, "step": 270660 }, { "epoch": 65.02, "learning_rate": 3.180823453324981e-05, "loss": 0.0018, "step": 270670 }, { "epoch": 65.02, "learning_rate": 3.180489102638423e-05, "loss": 0.0017, "step": 270680 }, { "epoch": 65.02, "learning_rate": 3.18015476132964e-05, "loss": 0.0021, "step": 270690 }, { "epoch": 65.02, "learning_rate": 3.179820429400354e-05, "loss": 0.0019, "step": 270700 }, { "epoch": 65.03, "learning_rate": 3.179486106852289e-05, "loss": 0.003, "step": 270710 }, { "epoch": 65.03, "learning_rate": 3.179151793687169e-05, "loss": 0.0023, "step": 270720 }, { "epoch": 65.03, "learning_rate": 3.1788174899067134e-05, "loss": 0.0066, "step": 270730 }, { "epoch": 65.03, "learning_rate": 3.178483195512651e-05, "loss": 0.0019, "step": 270740 }, { "epoch": 65.04, "learning_rate": 3.178148910506698e-05, "loss": 0.0026, "step": 270750 }, { "epoch": 65.04, "learning_rate": 3.177814634890583e-05, "loss": 0.0023, "step": 270760 }, { "epoch": 65.04, "learning_rate": 3.177480368666025e-05, "loss": 0.0026, "step": 270770 }, { "epoch": 65.04, "learning_rate": 3.17714611183475e-05, "loss": 0.002, "step": 270780 }, { "epoch": 65.04, "learning_rate": 3.17681186439848e-05, "loss": 0.003, "step": 270790 }, { "epoch": 65.05, "learning_rate": 3.176477626358935e-05, "loss": 0.0033, "step": 270800 }, { "epoch": 65.05, "learning_rate": 3.17614339771784e-05, "loss": 0.0021, "step": 270810 }, { "epoch": 65.05, "learning_rate": 3.175809178476916e-05, "loss": 0.002, "step": 270820 }, { "epoch": 65.05, "learning_rate": 3.1754749686378895e-05, "loss": 0.002, "step": 270830 }, { "epoch": 65.06, "learning_rate": 3.175140768202477e-05, "loss": 0.0019, "step": 270840 }, { "epoch": 65.06, "learning_rate": 3.1748065771724074e-05, "loss": 0.0073, "step": 270850 }, { "epoch": 65.06, "learning_rate": 3.174472395549398e-05, "loss": 0.0029, "step": 270860 }, { "epoch": 65.06, "learning_rate": 3.174138223335173e-05, "loss": 0.0064, "step": 270870 }, { "epoch": 65.07, "learning_rate": 3.173804060531456e-05, "loss": 0.0021, "step": 270880 }, { "epoch": 65.07, "learning_rate": 3.173469907139966e-05, "loss": 0.0018, "step": 270890 }, { "epoch": 65.07, "learning_rate": 3.1731357631624305e-05, "loss": 0.0025, "step": 270900 }, { "epoch": 65.07, "learning_rate": 3.172801628600566e-05, "loss": 0.0027, "step": 270910 }, { "epoch": 65.07, "learning_rate": 3.1724675034560994e-05, "loss": 0.002, "step": 270920 }, { "epoch": 65.08, "learning_rate": 3.1721333877307505e-05, "loss": 0.0024, "step": 270930 }, { "epoch": 65.08, "learning_rate": 3.171799281426239e-05, "loss": 0.002, "step": 270940 }, { "epoch": 65.08, "learning_rate": 3.171465184544291e-05, "loss": 0.0021, "step": 270950 }, { "epoch": 65.08, "learning_rate": 3.1711310970866254e-05, "loss": 0.0028, "step": 270960 }, { "epoch": 65.09, "learning_rate": 3.170797019054968e-05, "loss": 0.0019, "step": 270970 }, { "epoch": 65.09, "learning_rate": 3.170462950451034e-05, "loss": 0.0017, "step": 270980 }, { "epoch": 65.09, "learning_rate": 3.170128891276553e-05, "loss": 0.0017, "step": 270990 }, { "epoch": 65.09, "learning_rate": 3.169794841533241e-05, "loss": 0.0022, "step": 271000 }, { "epoch": 65.09, "learning_rate": 3.169460801222823e-05, "loss": 0.0033, "step": 271010 }, { "epoch": 65.1, "learning_rate": 3.169126770347018e-05, "loss": 0.0021, "step": 271020 }, { "epoch": 65.1, "learning_rate": 3.168792748907549e-05, "loss": 0.0018, "step": 271030 }, { "epoch": 65.1, "learning_rate": 3.1684587369061385e-05, "loss": 0.0018, "step": 271040 }, { "epoch": 65.1, "learning_rate": 3.168124734344505e-05, "loss": 0.0022, "step": 271050 }, { "epoch": 65.11, "learning_rate": 3.167790741224375e-05, "loss": 0.0022, "step": 271060 }, { "epoch": 65.11, "learning_rate": 3.167456757547466e-05, "loss": 0.0029, "step": 271070 }, { "epoch": 65.11, "learning_rate": 3.167122783315498e-05, "loss": 0.0022, "step": 271080 }, { "epoch": 65.11, "learning_rate": 3.166788818530197e-05, "loss": 0.0023, "step": 271090 }, { "epoch": 65.12, "learning_rate": 3.16645486319328e-05, "loss": 0.0018, "step": 271100 }, { "epoch": 65.12, "learning_rate": 3.166120917306471e-05, "loss": 0.0029, "step": 271110 }, { "epoch": 65.12, "learning_rate": 3.1657869808714894e-05, "loss": 0.0019, "step": 271120 }, { "epoch": 65.12, "learning_rate": 3.165453053890058e-05, "loss": 0.0021, "step": 271130 }, { "epoch": 65.12, "learning_rate": 3.165119136363896e-05, "loss": 0.0024, "step": 271140 }, { "epoch": 65.13, "learning_rate": 3.164785228294726e-05, "loss": 0.0022, "step": 271150 }, { "epoch": 65.13, "learning_rate": 3.164451329684267e-05, "loss": 0.0043, "step": 271160 }, { "epoch": 65.13, "learning_rate": 3.164117440534242e-05, "loss": 0.002, "step": 271170 }, { "epoch": 65.13, "learning_rate": 3.163783560846372e-05, "loss": 0.0022, "step": 271180 }, { "epoch": 65.14, "learning_rate": 3.1634496906223744e-05, "loss": 0.0043, "step": 271190 }, { "epoch": 65.14, "learning_rate": 3.163115829863975e-05, "loss": 0.002, "step": 271200 }, { "epoch": 65.14, "learning_rate": 3.162781978572892e-05, "loss": 0.002, "step": 271210 }, { "epoch": 65.14, "learning_rate": 3.162448136750844e-05, "loss": 0.0017, "step": 271220 }, { "epoch": 65.15, "learning_rate": 3.1621143043995554e-05, "loss": 0.002, "step": 271230 }, { "epoch": 65.15, "learning_rate": 3.161780481520743e-05, "loss": 0.0027, "step": 271240 }, { "epoch": 65.15, "learning_rate": 3.161446668116132e-05, "loss": 0.002, "step": 271250 }, { "epoch": 65.15, "learning_rate": 3.1611128641874374e-05, "loss": 0.0021, "step": 271260 }, { "epoch": 65.15, "learning_rate": 3.160779069736386e-05, "loss": 0.0019, "step": 271270 }, { "epoch": 65.16, "learning_rate": 3.160445284764692e-05, "loss": 0.0023, "step": 271280 }, { "epoch": 65.16, "learning_rate": 3.160111509274079e-05, "loss": 0.0019, "step": 271290 }, { "epoch": 65.16, "learning_rate": 3.159777743266267e-05, "loss": 0.0333, "step": 271300 }, { "epoch": 65.16, "learning_rate": 3.159443986742975e-05, "loss": 0.002, "step": 271310 }, { "epoch": 65.17, "learning_rate": 3.1591102397059246e-05, "loss": 0.0032, "step": 271320 }, { "epoch": 65.17, "learning_rate": 3.158776502156835e-05, "loss": 0.0024, "step": 271330 }, { "epoch": 65.17, "learning_rate": 3.1584427740974274e-05, "loss": 0.0035, "step": 271340 }, { "epoch": 65.17, "learning_rate": 3.158109055529422e-05, "loss": 0.0024, "step": 271350 }, { "epoch": 65.17, "learning_rate": 3.157775346454536e-05, "loss": 0.002, "step": 271360 }, { "epoch": 65.18, "learning_rate": 3.157441646874493e-05, "loss": 0.0035, "step": 271370 }, { "epoch": 65.18, "learning_rate": 3.157107956791009e-05, "loss": 0.0019, "step": 271380 }, { "epoch": 65.18, "learning_rate": 3.156774276205808e-05, "loss": 0.0029, "step": 271390 }, { "epoch": 65.18, "learning_rate": 3.1564406051206064e-05, "loss": 0.0038, "step": 271400 }, { "epoch": 65.19, "learning_rate": 3.156106943537127e-05, "loss": 0.0037, "step": 271410 }, { "epoch": 65.19, "learning_rate": 3.1557732914570874e-05, "loss": 0.0017, "step": 271420 }, { "epoch": 65.19, "learning_rate": 3.1554396488822056e-05, "loss": 0.0018, "step": 271430 }, { "epoch": 65.19, "learning_rate": 3.1551060158142055e-05, "loss": 0.0022, "step": 271440 }, { "epoch": 65.2, "learning_rate": 3.1547723922548034e-05, "loss": 0.0021, "step": 271450 }, { "epoch": 65.2, "learning_rate": 3.154438778205719e-05, "loss": 0.0017, "step": 271460 }, { "epoch": 65.2, "learning_rate": 3.154105173668674e-05, "loss": 0.0019, "step": 271470 }, { "epoch": 65.2, "learning_rate": 3.153771578645386e-05, "loss": 0.0024, "step": 271480 }, { "epoch": 65.2, "learning_rate": 3.153437993137575e-05, "loss": 0.0024, "step": 271490 }, { "epoch": 65.21, "learning_rate": 3.153104417146959e-05, "loss": 0.0018, "step": 271500 }, { "epoch": 65.21, "learning_rate": 3.152770850675261e-05, "loss": 0.0019, "step": 271510 }, { "epoch": 65.21, "learning_rate": 3.152437293724194e-05, "loss": 0.002, "step": 271520 }, { "epoch": 65.21, "learning_rate": 3.152103746295483e-05, "loss": 0.0019, "step": 271530 }, { "epoch": 65.22, "learning_rate": 3.151770208390843e-05, "loss": 0.002, "step": 271540 }, { "epoch": 65.22, "learning_rate": 3.1514366800119964e-05, "loss": 0.0017, "step": 271550 }, { "epoch": 65.22, "learning_rate": 3.151103161160659e-05, "loss": 0.002, "step": 271560 }, { "epoch": 65.22, "learning_rate": 3.1507696518385525e-05, "loss": 0.0019, "step": 271570 }, { "epoch": 65.23, "learning_rate": 3.150436152047396e-05, "loss": 0.0027, "step": 271580 }, { "epoch": 65.23, "learning_rate": 3.150102661788904e-05, "loss": 0.0028, "step": 271590 }, { "epoch": 65.23, "learning_rate": 3.1497691810647993e-05, "loss": 0.0021, "step": 271600 }, { "epoch": 65.23, "learning_rate": 3.1494357098768e-05, "loss": 0.0018, "step": 271610 }, { "epoch": 65.23, "learning_rate": 3.149102248226625e-05, "loss": 0.0022, "step": 271620 }, { "epoch": 65.24, "learning_rate": 3.1487687961159915e-05, "loss": 0.0017, "step": 271630 }, { "epoch": 65.24, "learning_rate": 3.148435353546621e-05, "loss": 0.0019, "step": 271640 }, { "epoch": 65.24, "learning_rate": 3.148101920520229e-05, "loss": 0.0021, "step": 271650 }, { "epoch": 65.24, "learning_rate": 3.147768497038534e-05, "loss": 0.0023, "step": 271660 }, { "epoch": 65.25, "learning_rate": 3.147435083103258e-05, "loss": 0.0019, "step": 271670 }, { "epoch": 65.25, "learning_rate": 3.147101678716114e-05, "loss": 0.0026, "step": 271680 }, { "epoch": 65.25, "learning_rate": 3.146768283878827e-05, "loss": 0.0019, "step": 271690 }, { "epoch": 65.25, "learning_rate": 3.1464348985931085e-05, "loss": 0.0029, "step": 271700 }, { "epoch": 65.25, "learning_rate": 3.146101522860683e-05, "loss": 0.0018, "step": 271710 }, { "epoch": 65.26, "learning_rate": 3.1457681566832656e-05, "loss": 0.0018, "step": 271720 }, { "epoch": 65.26, "learning_rate": 3.145434800062572e-05, "loss": 0.002, "step": 271730 }, { "epoch": 65.26, "learning_rate": 3.1451014530003246e-05, "loss": 0.0017, "step": 271740 }, { "epoch": 65.26, "learning_rate": 3.1447681154982386e-05, "loss": 0.0019, "step": 271750 }, { "epoch": 65.27, "learning_rate": 3.144434787558034e-05, "loss": 0.0016, "step": 271760 }, { "epoch": 65.27, "learning_rate": 3.144101469181428e-05, "loss": 0.0015, "step": 271770 }, { "epoch": 65.27, "learning_rate": 3.143768160370139e-05, "loss": 0.0017, "step": 271780 }, { "epoch": 65.27, "learning_rate": 3.143434861125885e-05, "loss": 0.0019, "step": 271790 }, { "epoch": 65.28, "learning_rate": 3.1431015714503806e-05, "loss": 0.0028, "step": 271800 }, { "epoch": 65.28, "learning_rate": 3.142768291345349e-05, "loss": 0.0097, "step": 271810 }, { "epoch": 65.28, "learning_rate": 3.142435020812503e-05, "loss": 0.0018, "step": 271820 }, { "epoch": 65.28, "learning_rate": 3.142101759853565e-05, "loss": 0.0021, "step": 271830 }, { "epoch": 65.28, "learning_rate": 3.141768508470247e-05, "loss": 0.0019, "step": 271840 }, { "epoch": 65.29, "learning_rate": 3.141435266664272e-05, "loss": 0.0017, "step": 271850 }, { "epoch": 65.29, "learning_rate": 3.141102034437355e-05, "loss": 0.0021, "step": 271860 }, { "epoch": 65.29, "learning_rate": 3.1407688117912124e-05, "loss": 0.0084, "step": 271870 }, { "epoch": 65.29, "learning_rate": 3.140435598727565e-05, "loss": 0.0025, "step": 271880 }, { "epoch": 65.3, "learning_rate": 3.1401023952481254e-05, "loss": 0.0018, "step": 271890 }, { "epoch": 65.3, "learning_rate": 3.1397692013546155e-05, "loss": 0.0018, "step": 271900 }, { "epoch": 65.3, "learning_rate": 3.1394360170487494e-05, "loss": 0.0018, "step": 271910 }, { "epoch": 65.3, "learning_rate": 3.139102842332246e-05, "loss": 0.0019, "step": 271920 }, { "epoch": 65.31, "learning_rate": 3.1387696772068234e-05, "loss": 0.0019, "step": 271930 }, { "epoch": 65.31, "learning_rate": 3.138436521674195e-05, "loss": 0.0017, "step": 271940 }, { "epoch": 65.31, "learning_rate": 3.138103375736082e-05, "loss": 0.0033, "step": 271950 }, { "epoch": 65.31, "learning_rate": 3.137770239394199e-05, "loss": 0.002, "step": 271960 }, { "epoch": 65.31, "learning_rate": 3.1374371126502646e-05, "loss": 0.0017, "step": 271970 }, { "epoch": 65.32, "learning_rate": 3.137103995505993e-05, "loss": 0.0018, "step": 271980 }, { "epoch": 65.32, "learning_rate": 3.136770887963106e-05, "loss": 0.0017, "step": 271990 }, { "epoch": 65.32, "learning_rate": 3.136437790023317e-05, "loss": 0.0034, "step": 272000 }, { "epoch": 65.32, "learning_rate": 3.13610470168834e-05, "loss": 0.0025, "step": 272010 }, { "epoch": 65.33, "learning_rate": 3.135771622959899e-05, "loss": 0.0019, "step": 272020 }, { "epoch": 65.33, "learning_rate": 3.1354385538397036e-05, "loss": 0.0017, "step": 272030 }, { "epoch": 65.33, "learning_rate": 3.135105494329476e-05, "loss": 0.0042, "step": 272040 }, { "epoch": 65.33, "learning_rate": 3.1347724444309266e-05, "loss": 0.0019, "step": 272050 }, { "epoch": 65.33, "learning_rate": 3.134439404145779e-05, "loss": 0.0018, "step": 272060 }, { "epoch": 65.34, "learning_rate": 3.134106373475745e-05, "loss": 0.0019, "step": 272070 }, { "epoch": 65.34, "learning_rate": 3.133773352422542e-05, "loss": 0.0018, "step": 272080 }, { "epoch": 65.34, "learning_rate": 3.1334403409878875e-05, "loss": 0.0034, "step": 272090 }, { "epoch": 65.34, "learning_rate": 3.133107339173496e-05, "loss": 0.002, "step": 272100 }, { "epoch": 65.35, "learning_rate": 3.132774346981087e-05, "loss": 0.0019, "step": 272110 }, { "epoch": 65.35, "learning_rate": 3.132441364412372e-05, "loss": 0.0044, "step": 272120 }, { "epoch": 65.35, "learning_rate": 3.132108391469072e-05, "loss": 0.002, "step": 272130 }, { "epoch": 65.35, "learning_rate": 3.131775428152901e-05, "loss": 0.0041, "step": 272140 }, { "epoch": 65.36, "learning_rate": 3.131442474465573e-05, "loss": 0.0019, "step": 272150 }, { "epoch": 65.36, "learning_rate": 3.1311095304088086e-05, "loss": 0.0057, "step": 272160 }, { "epoch": 65.36, "learning_rate": 3.130776595984318e-05, "loss": 0.0037, "step": 272170 }, { "epoch": 65.36, "learning_rate": 3.130443671193824e-05, "loss": 0.0036, "step": 272180 }, { "epoch": 65.36, "learning_rate": 3.130110756039036e-05, "loss": 0.0018, "step": 272190 }, { "epoch": 65.37, "learning_rate": 3.1297778505216756e-05, "loss": 0.0018, "step": 272200 }, { "epoch": 65.37, "learning_rate": 3.129444954643454e-05, "loss": 0.0018, "step": 272210 }, { "epoch": 65.37, "learning_rate": 3.129112068406089e-05, "loss": 0.0032, "step": 272220 }, { "epoch": 65.37, "learning_rate": 3.128779191811296e-05, "loss": 0.002, "step": 272230 }, { "epoch": 65.38, "learning_rate": 3.12844632486079e-05, "loss": 0.0019, "step": 272240 }, { "epoch": 65.38, "learning_rate": 3.128113467556289e-05, "loss": 0.0029, "step": 272250 }, { "epoch": 65.38, "learning_rate": 3.1277806198995046e-05, "loss": 0.0024, "step": 272260 }, { "epoch": 65.38, "learning_rate": 3.127447781892157e-05, "loss": 0.002, "step": 272270 }, { "epoch": 65.39, "learning_rate": 3.127114953535959e-05, "loss": 0.0019, "step": 272280 }, { "epoch": 65.39, "learning_rate": 3.126782134832624e-05, "loss": 0.0019, "step": 272290 }, { "epoch": 65.39, "learning_rate": 3.126449325783872e-05, "loss": 0.0022, "step": 272300 }, { "epoch": 65.39, "learning_rate": 3.126116526391413e-05, "loss": 0.0021, "step": 272310 }, { "epoch": 65.39, "learning_rate": 3.1257837366569675e-05, "loss": 0.0017, "step": 272320 }, { "epoch": 65.4, "learning_rate": 3.125450956582246e-05, "loss": 0.0019, "step": 272330 }, { "epoch": 65.4, "learning_rate": 3.125118186168969e-05, "loss": 0.002, "step": 272340 }, { "epoch": 65.4, "learning_rate": 3.124785425418846e-05, "loss": 0.0022, "step": 272350 }, { "epoch": 65.4, "learning_rate": 3.124452674333597e-05, "loss": 0.0017, "step": 272360 }, { "epoch": 65.41, "learning_rate": 3.124119932914933e-05, "loss": 0.0022, "step": 272370 }, { "epoch": 65.41, "learning_rate": 3.123787201164569e-05, "loss": 0.0016, "step": 272380 }, { "epoch": 65.41, "learning_rate": 3.1234544790842246e-05, "loss": 0.0017, "step": 272390 }, { "epoch": 65.41, "learning_rate": 3.1231217666756086e-05, "loss": 0.0028, "step": 272400 }, { "epoch": 65.41, "learning_rate": 3.122789063940441e-05, "loss": 0.0021, "step": 272410 }, { "epoch": 65.42, "learning_rate": 3.1224563708804324e-05, "loss": 0.003, "step": 272420 }, { "epoch": 65.42, "learning_rate": 3.122123687497302e-05, "loss": 0.0022, "step": 272430 }, { "epoch": 65.42, "learning_rate": 3.1217910137927605e-05, "loss": 0.0027, "step": 272440 }, { "epoch": 65.42, "learning_rate": 3.1214583497685224e-05, "loss": 0.0042, "step": 272450 }, { "epoch": 65.43, "learning_rate": 3.121125695426306e-05, "loss": 0.0026, "step": 272460 }, { "epoch": 65.43, "learning_rate": 3.120793050767821e-05, "loss": 0.0019, "step": 272470 }, { "epoch": 65.43, "learning_rate": 3.120460415794786e-05, "loss": 0.0026, "step": 272480 }, { "epoch": 65.43, "learning_rate": 3.120127790508912e-05, "loss": 0.0018, "step": 272490 }, { "epoch": 65.44, "learning_rate": 3.119795174911917e-05, "loss": 0.0017, "step": 272500 }, { "epoch": 65.44, "learning_rate": 3.119462569005513e-05, "loss": 0.0017, "step": 272510 }, { "epoch": 65.44, "learning_rate": 3.1191299727914146e-05, "loss": 0.0032, "step": 272520 }, { "epoch": 65.44, "learning_rate": 3.118797386271336e-05, "loss": 0.0018, "step": 272530 }, { "epoch": 65.44, "learning_rate": 3.11846480944699e-05, "loss": 0.0023, "step": 272540 }, { "epoch": 65.45, "learning_rate": 3.118132242320094e-05, "loss": 0.0016, "step": 272550 }, { "epoch": 65.45, "learning_rate": 3.117799684892359e-05, "loss": 0.0018, "step": 272560 }, { "epoch": 65.45, "learning_rate": 3.1174671371655e-05, "loss": 0.0032, "step": 272570 }, { "epoch": 65.45, "learning_rate": 3.1171345991412336e-05, "loss": 0.0028, "step": 272580 }, { "epoch": 65.46, "learning_rate": 3.116802070821269e-05, "loss": 0.0027, "step": 272590 }, { "epoch": 65.46, "learning_rate": 3.1164695522073226e-05, "loss": 0.0019, "step": 272600 }, { "epoch": 65.46, "learning_rate": 3.116137043301107e-05, "loss": 0.0024, "step": 272610 }, { "epoch": 65.46, "learning_rate": 3.1158045441043386e-05, "loss": 0.005, "step": 272620 }, { "epoch": 65.47, "learning_rate": 3.115472054618728e-05, "loss": 0.0025, "step": 272630 }, { "epoch": 65.47, "learning_rate": 3.115139574845991e-05, "loss": 0.0018, "step": 272640 }, { "epoch": 65.47, "learning_rate": 3.11480710478784e-05, "loss": 0.003, "step": 272650 }, { "epoch": 65.47, "learning_rate": 3.114474644445989e-05, "loss": 0.0028, "step": 272660 }, { "epoch": 65.47, "learning_rate": 3.114142193822151e-05, "loss": 0.0023, "step": 272670 }, { "epoch": 65.48, "learning_rate": 3.11380975291804e-05, "loss": 0.0026, "step": 272680 }, { "epoch": 65.48, "learning_rate": 3.1134773217353694e-05, "loss": 0.0024, "step": 272690 }, { "epoch": 65.48, "learning_rate": 3.1131449002758514e-05, "loss": 0.0017, "step": 272700 }, { "epoch": 65.48, "learning_rate": 3.112812488541203e-05, "loss": 0.0018, "step": 272710 }, { "epoch": 65.49, "learning_rate": 3.112480086533134e-05, "loss": 0.0017, "step": 272720 }, { "epoch": 65.49, "learning_rate": 3.112147694253357e-05, "loss": 0.002, "step": 272730 }, { "epoch": 65.49, "learning_rate": 3.1118153117035885e-05, "loss": 0.0032, "step": 272740 }, { "epoch": 65.49, "learning_rate": 3.111482938885537e-05, "loss": 0.0024, "step": 272750 }, { "epoch": 65.49, "learning_rate": 3.111150575800921e-05, "loss": 0.0026, "step": 272760 }, { "epoch": 65.5, "learning_rate": 3.1108182224514484e-05, "loss": 0.0019, "step": 272770 }, { "epoch": 65.5, "learning_rate": 3.110485878838837e-05, "loss": 0.0033, "step": 272780 }, { "epoch": 65.5, "learning_rate": 3.1101535449647965e-05, "loss": 0.0021, "step": 272790 }, { "epoch": 65.5, "learning_rate": 3.1098212208310385e-05, "loss": 0.0018, "step": 272800 }, { "epoch": 65.51, "learning_rate": 3.109488906439278e-05, "loss": 0.0022, "step": 272810 }, { "epoch": 65.51, "learning_rate": 3.1091566017912286e-05, "loss": 0.0016, "step": 272820 }, { "epoch": 65.51, "learning_rate": 3.108824306888602e-05, "loss": 0.0024, "step": 272830 }, { "epoch": 65.51, "learning_rate": 3.10849202173311e-05, "loss": 0.002, "step": 272840 }, { "epoch": 65.52, "learning_rate": 3.108159746326467e-05, "loss": 0.0023, "step": 272850 }, { "epoch": 65.52, "learning_rate": 3.1078274806703844e-05, "loss": 0.0022, "step": 272860 }, { "epoch": 65.52, "learning_rate": 3.107495224766573e-05, "loss": 0.0029, "step": 272870 }, { "epoch": 65.52, "learning_rate": 3.1071629786167486e-05, "loss": 0.0017, "step": 272880 }, { "epoch": 65.52, "learning_rate": 3.1068307422226206e-05, "loss": 0.0025, "step": 272890 }, { "epoch": 65.53, "learning_rate": 3.106498515585905e-05, "loss": 0.0022, "step": 272900 }, { "epoch": 65.53, "learning_rate": 3.106166298708309e-05, "loss": 0.0019, "step": 272910 }, { "epoch": 65.53, "learning_rate": 3.1058340915915506e-05, "loss": 0.0185, "step": 272920 }, { "epoch": 65.53, "learning_rate": 3.105501894237339e-05, "loss": 0.0036, "step": 272930 }, { "epoch": 65.54, "learning_rate": 3.105169706647384e-05, "loss": 0.0094, "step": 272940 }, { "epoch": 65.54, "learning_rate": 3.104837528823402e-05, "loss": 0.0037, "step": 272950 }, { "epoch": 65.54, "learning_rate": 3.104505360767103e-05, "loss": 0.0022, "step": 272960 }, { "epoch": 65.54, "learning_rate": 3.1041732024801984e-05, "loss": 0.0026, "step": 272970 }, { "epoch": 65.55, "learning_rate": 3.103841053964402e-05, "loss": 0.0023, "step": 272980 }, { "epoch": 65.55, "learning_rate": 3.103508915221423e-05, "loss": 0.0022, "step": 272990 }, { "epoch": 65.55, "learning_rate": 3.103176786252978e-05, "loss": 0.0065, "step": 273000 }, { "epoch": 65.55, "learning_rate": 3.102844667060772e-05, "loss": 0.0023, "step": 273010 }, { "epoch": 65.55, "learning_rate": 3.1025125576465244e-05, "loss": 0.002, "step": 273020 }, { "epoch": 65.56, "learning_rate": 3.1021804580119394e-05, "loss": 0.0019, "step": 273030 }, { "epoch": 65.56, "learning_rate": 3.101848368158734e-05, "loss": 0.0021, "step": 273040 }, { "epoch": 65.56, "learning_rate": 3.1015162880886174e-05, "loss": 0.0021, "step": 273050 }, { "epoch": 65.56, "learning_rate": 3.1011842178033025e-05, "loss": 0.0034, "step": 273060 }, { "epoch": 65.57, "learning_rate": 3.1008521573045e-05, "loss": 0.0018, "step": 273070 }, { "epoch": 65.57, "learning_rate": 3.10052010659392e-05, "loss": 0.0019, "step": 273080 }, { "epoch": 65.57, "learning_rate": 3.100188065673277e-05, "loss": 0.0024, "step": 273090 }, { "epoch": 65.57, "learning_rate": 3.0998560345442786e-05, "loss": 0.0025, "step": 273100 }, { "epoch": 65.57, "learning_rate": 3.099524013208639e-05, "loss": 0.0016, "step": 273110 }, { "epoch": 65.58, "learning_rate": 3.0991920016680686e-05, "loss": 0.002, "step": 273120 }, { "epoch": 65.58, "learning_rate": 3.098859999924278e-05, "loss": 0.0016, "step": 273130 }, { "epoch": 65.58, "learning_rate": 3.0985280079789794e-05, "loss": 0.0022, "step": 273140 }, { "epoch": 65.58, "learning_rate": 3.0981960258338835e-05, "loss": 0.0039, "step": 273150 }, { "epoch": 65.59, "learning_rate": 3.0978640534907016e-05, "loss": 0.0021, "step": 273160 }, { "epoch": 65.59, "learning_rate": 3.097532090951143e-05, "loss": 0.005, "step": 273170 }, { "epoch": 65.59, "learning_rate": 3.0972001382169215e-05, "loss": 0.0051, "step": 273180 }, { "epoch": 65.59, "learning_rate": 3.096868195289744e-05, "loss": 0.0019, "step": 273190 }, { "epoch": 65.6, "learning_rate": 3.096536262171326e-05, "loss": 0.0022, "step": 273200 }, { "epoch": 65.6, "learning_rate": 3.096204338863374e-05, "loss": 0.0028, "step": 273210 }, { "epoch": 65.6, "learning_rate": 3.095872425367603e-05, "loss": 0.0025, "step": 273220 }, { "epoch": 65.6, "learning_rate": 3.095540521685721e-05, "loss": 0.002, "step": 273230 }, { "epoch": 65.6, "learning_rate": 3.095208627819438e-05, "loss": 0.0018, "step": 273240 }, { "epoch": 65.61, "learning_rate": 3.094876743770467e-05, "loss": 0.0036, "step": 273250 }, { "epoch": 65.61, "learning_rate": 3.094544869540515e-05, "loss": 0.0022, "step": 273260 }, { "epoch": 65.61, "learning_rate": 3.0942130051312956e-05, "loss": 0.0041, "step": 273270 }, { "epoch": 65.61, "learning_rate": 3.0938811505445186e-05, "loss": 0.0025, "step": 273280 }, { "epoch": 65.62, "learning_rate": 3.093549305781894e-05, "loss": 0.0036, "step": 273290 }, { "epoch": 65.62, "learning_rate": 3.0932174708451334e-05, "loss": 0.0018, "step": 273300 }, { "epoch": 65.62, "learning_rate": 3.092885645735944e-05, "loss": 0.0072, "step": 273310 }, { "epoch": 65.62, "learning_rate": 3.09255383045604e-05, "loss": 0.0045, "step": 273320 }, { "epoch": 65.62, "learning_rate": 3.0922220250071267e-05, "loss": 0.0023, "step": 273330 }, { "epoch": 65.63, "learning_rate": 3.0918902293909196e-05, "loss": 0.0022, "step": 273340 }, { "epoch": 65.63, "learning_rate": 3.0915584436091236e-05, "loss": 0.0021, "step": 273350 }, { "epoch": 65.63, "learning_rate": 3.091226667663455e-05, "loss": 0.0026, "step": 273360 }, { "epoch": 65.63, "learning_rate": 3.0908949015556186e-05, "loss": 0.0054, "step": 273370 }, { "epoch": 65.64, "learning_rate": 3.090563145287324e-05, "loss": 0.005, "step": 273380 }, { "epoch": 65.64, "learning_rate": 3.090231398860285e-05, "loss": 0.0023, "step": 273390 }, { "epoch": 65.64, "learning_rate": 3.0898996622762075e-05, "loss": 0.002, "step": 273400 }, { "epoch": 65.64, "learning_rate": 3.089567935536806e-05, "loss": 0.0022, "step": 273410 }, { "epoch": 65.65, "learning_rate": 3.089236218643784e-05, "loss": 0.003, "step": 273420 }, { "epoch": 65.65, "learning_rate": 3.0889045115988557e-05, "loss": 0.0281, "step": 273430 }, { "epoch": 65.65, "learning_rate": 3.088572814403731e-05, "loss": 0.0027, "step": 273440 }, { "epoch": 65.65, "learning_rate": 3.088241127060115e-05, "loss": 0.0023, "step": 273450 }, { "epoch": 65.65, "learning_rate": 3.087909449569724e-05, "loss": 0.0021, "step": 273460 }, { "epoch": 65.66, "learning_rate": 3.08757778193426e-05, "loss": 0.0025, "step": 273470 }, { "epoch": 65.66, "learning_rate": 3.087246124155438e-05, "loss": 0.0025, "step": 273480 }, { "epoch": 65.66, "learning_rate": 3.086914476234964e-05, "loss": 0.0022, "step": 273490 }, { "epoch": 65.66, "learning_rate": 3.086582838174551e-05, "loss": 0.0023, "step": 273500 }, { "epoch": 65.67, "learning_rate": 3.0862512099759066e-05, "loss": 0.0017, "step": 273510 }, { "epoch": 65.67, "learning_rate": 3.085919591640737e-05, "loss": 0.0042, "step": 273520 }, { "epoch": 65.67, "learning_rate": 3.085587983170756e-05, "loss": 0.0028, "step": 273530 }, { "epoch": 65.67, "learning_rate": 3.0852563845676673e-05, "loss": 0.0019, "step": 273540 }, { "epoch": 65.68, "learning_rate": 3.084924795833187e-05, "loss": 0.0059, "step": 273550 }, { "epoch": 65.68, "learning_rate": 3.084593216969017e-05, "loss": 0.0064, "step": 273560 }, { "epoch": 65.68, "learning_rate": 3.084261647976872e-05, "loss": 0.0018, "step": 273570 }, { "epoch": 65.68, "learning_rate": 3.083930088858458e-05, "loss": 0.0027, "step": 273580 }, { "epoch": 65.68, "learning_rate": 3.083598539615482e-05, "loss": 0.0019, "step": 273590 }, { "epoch": 65.69, "learning_rate": 3.0832670002496584e-05, "loss": 0.0019, "step": 273600 }, { "epoch": 65.69, "learning_rate": 3.0829354707626904e-05, "loss": 0.0018, "step": 273610 }, { "epoch": 65.69, "learning_rate": 3.0826039511562905e-05, "loss": 0.0017, "step": 273620 }, { "epoch": 65.69, "learning_rate": 3.0822724414321644e-05, "loss": 0.0127, "step": 273630 }, { "epoch": 65.7, "learning_rate": 3.0819409415920245e-05, "loss": 0.0024, "step": 273640 }, { "epoch": 65.7, "learning_rate": 3.081609451637576e-05, "loss": 0.002, "step": 273650 }, { "epoch": 65.7, "learning_rate": 3.0812779715705266e-05, "loss": 0.0025, "step": 273660 }, { "epoch": 65.7, "learning_rate": 3.0809465013925894e-05, "loss": 0.0019, "step": 273670 }, { "epoch": 65.7, "learning_rate": 3.080615041105467e-05, "loss": 0.0021, "step": 273680 }, { "epoch": 65.71, "learning_rate": 3.080283590710874e-05, "loss": 0.0019, "step": 273690 }, { "epoch": 65.71, "learning_rate": 3.0799521502105125e-05, "loss": 0.0017, "step": 273700 }, { "epoch": 65.71, "learning_rate": 3.0796207196060955e-05, "loss": 0.0019, "step": 273710 }, { "epoch": 65.71, "learning_rate": 3.079289298899328e-05, "loss": 0.002, "step": 273720 }, { "epoch": 65.72, "learning_rate": 3.0789578880919206e-05, "loss": 0.0021, "step": 273730 }, { "epoch": 65.72, "learning_rate": 3.07862648718558e-05, "loss": 0.0018, "step": 273740 }, { "epoch": 65.72, "learning_rate": 3.078295096182013e-05, "loss": 0.0014, "step": 273750 }, { "epoch": 65.72, "learning_rate": 3.077963715082932e-05, "loss": 0.0018, "step": 273760 }, { "epoch": 65.73, "learning_rate": 3.077632343890039e-05, "loss": 0.0018, "step": 273770 }, { "epoch": 65.73, "learning_rate": 3.077300982605048e-05, "loss": 0.0022, "step": 273780 }, { "epoch": 65.73, "learning_rate": 3.0769696312296637e-05, "loss": 0.0123, "step": 273790 }, { "epoch": 65.73, "learning_rate": 3.076638289765591e-05, "loss": 0.0022, "step": 273800 }, { "epoch": 65.73, "learning_rate": 3.0763069582145435e-05, "loss": 0.0021, "step": 273810 }, { "epoch": 65.74, "learning_rate": 3.075975636578224e-05, "loss": 0.0018, "step": 273820 }, { "epoch": 65.74, "learning_rate": 3.075644324858344e-05, "loss": 0.0017, "step": 273830 }, { "epoch": 65.74, "learning_rate": 3.075313023056607e-05, "loss": 0.0017, "step": 273840 }, { "epoch": 65.74, "learning_rate": 3.074981731174725e-05, "loss": 0.0021, "step": 273850 }, { "epoch": 65.75, "learning_rate": 3.0746504492144024e-05, "loss": 0.002, "step": 273860 }, { "epoch": 65.75, "learning_rate": 3.074319177177347e-05, "loss": 0.0018, "step": 273870 }, { "epoch": 65.75, "learning_rate": 3.073987915065267e-05, "loss": 0.0019, "step": 273880 }, { "epoch": 65.75, "learning_rate": 3.0736566628798696e-05, "loss": 0.0023, "step": 273890 }, { "epoch": 65.76, "learning_rate": 3.0733254206228616e-05, "loss": 0.0022, "step": 273900 }, { "epoch": 65.76, "learning_rate": 3.0729941882959495e-05, "loss": 0.002, "step": 273910 }, { "epoch": 65.76, "learning_rate": 3.0726629659008436e-05, "loss": 0.0031, "step": 273920 }, { "epoch": 65.76, "learning_rate": 3.072331753439247e-05, "loss": 0.0021, "step": 273930 }, { "epoch": 65.76, "learning_rate": 3.07200055091287e-05, "loss": 0.0019, "step": 273940 }, { "epoch": 65.77, "learning_rate": 3.071669358323419e-05, "loss": 0.0018, "step": 273950 }, { "epoch": 65.77, "learning_rate": 3.071338175672598e-05, "loss": 0.0031, "step": 273960 }, { "epoch": 65.77, "learning_rate": 3.0710070029621176e-05, "loss": 0.0019, "step": 273970 }, { "epoch": 65.77, "learning_rate": 3.070675840193682e-05, "loss": 0.0048, "step": 273980 }, { "epoch": 65.78, "learning_rate": 3.070344687369001e-05, "loss": 0.0059, "step": 273990 }, { "epoch": 65.78, "learning_rate": 3.070013544489778e-05, "loss": 0.0042, "step": 274000 }, { "epoch": 65.78, "learning_rate": 3.0696824115577225e-05, "loss": 0.0034, "step": 274010 }, { "epoch": 65.78, "learning_rate": 3.069351288574539e-05, "loss": 0.0021, "step": 274020 }, { "epoch": 65.78, "learning_rate": 3.069020175541936e-05, "loss": 0.0018, "step": 274030 }, { "epoch": 65.79, "learning_rate": 3.068689072461619e-05, "loss": 0.002, "step": 274040 }, { "epoch": 65.79, "learning_rate": 3.0683579793352934e-05, "loss": 0.0018, "step": 274050 }, { "epoch": 65.79, "learning_rate": 3.068026896164669e-05, "loss": 0.0017, "step": 274060 }, { "epoch": 65.79, "learning_rate": 3.0676958229514476e-05, "loss": 0.002, "step": 274070 }, { "epoch": 65.8, "learning_rate": 3.06736475969734e-05, "loss": 0.0029, "step": 274080 }, { "epoch": 65.8, "learning_rate": 3.0670337064040513e-05, "loss": 0.0035, "step": 274090 }, { "epoch": 65.8, "learning_rate": 3.066702663073284e-05, "loss": 0.0017, "step": 274100 }, { "epoch": 65.8, "learning_rate": 3.0663716297067505e-05, "loss": 0.0019, "step": 274110 }, { "epoch": 65.81, "learning_rate": 3.066040606306151e-05, "loss": 0.0025, "step": 274120 }, { "epoch": 65.81, "learning_rate": 3.065709592873197e-05, "loss": 0.0022, "step": 274130 }, { "epoch": 65.81, "learning_rate": 3.06537858940959e-05, "loss": 0.0024, "step": 274140 }, { "epoch": 65.81, "learning_rate": 3.065047595917039e-05, "loss": 0.0053, "step": 274150 }, { "epoch": 65.81, "learning_rate": 3.0647166123972495e-05, "loss": 0.0029, "step": 274160 }, { "epoch": 65.82, "learning_rate": 3.0643856388519254e-05, "loss": 0.002, "step": 274170 }, { "epoch": 65.82, "learning_rate": 3.064054675282774e-05, "loss": 0.0032, "step": 274180 }, { "epoch": 65.82, "learning_rate": 3.0637237216915014e-05, "loss": 0.0017, "step": 274190 }, { "epoch": 65.82, "learning_rate": 3.063392778079812e-05, "loss": 0.0018, "step": 274200 }, { "epoch": 65.83, "learning_rate": 3.063061844449413e-05, "loss": 0.002, "step": 274210 }, { "epoch": 65.83, "learning_rate": 3.0627309208020106e-05, "loss": 0.002, "step": 274220 }, { "epoch": 65.83, "learning_rate": 3.062400007139309e-05, "loss": 0.0022, "step": 274230 }, { "epoch": 65.83, "learning_rate": 3.062069103463012e-05, "loss": 0.0019, "step": 274240 }, { "epoch": 65.84, "learning_rate": 3.061738209774829e-05, "loss": 0.002, "step": 274250 }, { "epoch": 65.84, "learning_rate": 3.061407326076462e-05, "loss": 0.0029, "step": 274260 }, { "epoch": 65.84, "learning_rate": 3.0610764523696195e-05, "loss": 0.0017, "step": 274270 }, { "epoch": 65.84, "learning_rate": 3.060745588656003e-05, "loss": 0.0027, "step": 274280 }, { "epoch": 65.84, "learning_rate": 3.060414734937322e-05, "loss": 0.002, "step": 274290 }, { "epoch": 65.85, "learning_rate": 3.06008389121528e-05, "loss": 0.002, "step": 274300 }, { "epoch": 65.85, "learning_rate": 3.05975305749158e-05, "loss": 0.0018, "step": 274310 }, { "epoch": 65.85, "learning_rate": 3.059422233767929e-05, "loss": 0.0016, "step": 274320 }, { "epoch": 65.85, "learning_rate": 3.059091420046033e-05, "loss": 0.0021, "step": 274330 }, { "epoch": 65.86, "learning_rate": 3.0587606163275956e-05, "loss": 0.0019, "step": 274340 }, { "epoch": 65.86, "learning_rate": 3.058429822614322e-05, "loss": 0.0019, "step": 274350 }, { "epoch": 65.86, "learning_rate": 3.058099038907918e-05, "loss": 0.0016, "step": 274360 }, { "epoch": 65.86, "learning_rate": 3.057768265210088e-05, "loss": 0.0025, "step": 274370 }, { "epoch": 65.86, "learning_rate": 3.057437501522535e-05, "loss": 0.0018, "step": 274380 }, { "epoch": 65.87, "learning_rate": 3.057106747846967e-05, "loss": 0.0025, "step": 274390 }, { "epoch": 65.87, "learning_rate": 3.0567760041850854e-05, "loss": 0.0018, "step": 274400 }, { "epoch": 65.87, "learning_rate": 3.0564452705385996e-05, "loss": 0.0017, "step": 274410 }, { "epoch": 65.87, "learning_rate": 3.056114546909208e-05, "loss": 0.0019, "step": 274420 }, { "epoch": 65.88, "learning_rate": 3.05578383329862e-05, "loss": 0.0019, "step": 274430 }, { "epoch": 65.88, "learning_rate": 3.055453129708539e-05, "loss": 0.002, "step": 274440 }, { "epoch": 65.88, "learning_rate": 3.0551224361406663e-05, "loss": 0.002, "step": 274450 }, { "epoch": 65.88, "learning_rate": 3.054791752596711e-05, "loss": 0.0019, "step": 274460 }, { "epoch": 65.89, "learning_rate": 3.054461079078373e-05, "loss": 0.0017, "step": 274470 }, { "epoch": 65.89, "learning_rate": 3.05413041558736e-05, "loss": 0.0016, "step": 274480 }, { "epoch": 65.89, "learning_rate": 3.053799762125376e-05, "loss": 0.002, "step": 274490 }, { "epoch": 65.89, "learning_rate": 3.0534691186941235e-05, "loss": 0.0123, "step": 274500 }, { "epoch": 65.89, "learning_rate": 3.0531384852953084e-05, "loss": 0.002, "step": 274510 }, { "epoch": 65.9, "learning_rate": 3.052807861930631e-05, "loss": 0.0021, "step": 274520 }, { "epoch": 65.9, "learning_rate": 3.052477248601802e-05, "loss": 0.0021, "step": 274530 }, { "epoch": 65.9, "learning_rate": 3.052146645310519e-05, "loss": 0.0019, "step": 274540 }, { "epoch": 65.9, "learning_rate": 3.051816052058489e-05, "loss": 0.0019, "step": 274550 }, { "epoch": 65.91, "learning_rate": 3.051485468847415e-05, "loss": 0.0021, "step": 274560 }, { "epoch": 65.91, "learning_rate": 3.0511548956790025e-05, "loss": 0.0017, "step": 274570 }, { "epoch": 65.91, "learning_rate": 3.050824332554954e-05, "loss": 0.002, "step": 274580 }, { "epoch": 65.91, "learning_rate": 3.050493779476971e-05, "loss": 0.0018, "step": 274590 }, { "epoch": 65.92, "learning_rate": 3.050163236446762e-05, "loss": 0.0019, "step": 274600 }, { "epoch": 65.92, "learning_rate": 3.0498327034660256e-05, "loss": 0.0019, "step": 274610 }, { "epoch": 65.92, "learning_rate": 3.04950218053647e-05, "loss": 0.0022, "step": 274620 }, { "epoch": 65.92, "learning_rate": 3.0491716676597936e-05, "loss": 0.0021, "step": 274630 }, { "epoch": 65.92, "learning_rate": 3.0488411648377047e-05, "loss": 0.0019, "step": 274640 }, { "epoch": 65.93, "learning_rate": 3.0485106720719047e-05, "loss": 0.0025, "step": 274650 }, { "epoch": 65.93, "learning_rate": 3.048180189364096e-05, "loss": 0.0018, "step": 274660 }, { "epoch": 65.93, "learning_rate": 3.0478497167159846e-05, "loss": 0.0016, "step": 274670 }, { "epoch": 65.93, "learning_rate": 3.0475192541292702e-05, "loss": 0.0017, "step": 274680 }, { "epoch": 65.94, "learning_rate": 3.04718880160566e-05, "loss": 0.0017, "step": 274690 }, { "epoch": 65.94, "learning_rate": 3.0468583591468526e-05, "loss": 0.0019, "step": 274700 }, { "epoch": 65.94, "learning_rate": 3.0465279267545555e-05, "loss": 0.002, "step": 274710 }, { "epoch": 65.94, "learning_rate": 3.046197504430468e-05, "loss": 0.0031, "step": 274720 }, { "epoch": 65.94, "learning_rate": 3.0458670921762973e-05, "loss": 0.0018, "step": 274730 }, { "epoch": 65.95, "learning_rate": 3.0455366899937433e-05, "loss": 0.0019, "step": 274740 }, { "epoch": 65.95, "learning_rate": 3.045206297884508e-05, "loss": 0.0018, "step": 274750 }, { "epoch": 66.0, "learning_rate": 3.0448759158502975e-05, "loss": 0.0017, "step": 274760 }, { "epoch": 66.0, "learning_rate": 3.044545543892811e-05, "loss": 0.0029, "step": 274770 }, { "epoch": 66.01, "learning_rate": 3.0442151820137544e-05, "loss": 0.0019, "step": 274780 }, { "epoch": 66.01, "learning_rate": 3.0438848302148282e-05, "loss": 0.0018, "step": 274790 }, { "epoch": 66.01, "learning_rate": 3.0435544884977368e-05, "loss": 0.0019, "step": 274800 }, { "epoch": 66.01, "learning_rate": 3.043224156864183e-05, "loss": 0.0022, "step": 274810 }, { "epoch": 66.01, "learning_rate": 3.0428938353158654e-05, "loss": 0.0019, "step": 274820 }, { "epoch": 66.02, "learning_rate": 3.042563523854492e-05, "loss": 0.0017, "step": 274830 }, { "epoch": 66.02, "learning_rate": 3.0422332224817607e-05, "loss": 0.003, "step": 274840 }, { "epoch": 66.02, "learning_rate": 3.0419029311993775e-05, "loss": 0.0019, "step": 274850 }, { "epoch": 66.02, "learning_rate": 3.0415726500090402e-05, "loss": 0.002, "step": 274860 }, { "epoch": 66.03, "learning_rate": 3.0412423789124567e-05, "loss": 0.0025, "step": 274870 }, { "epoch": 66.03, "learning_rate": 3.0409121179113266e-05, "loss": 0.0017, "step": 274880 }, { "epoch": 66.03, "learning_rate": 3.040581867007349e-05, "loss": 0.0021, "step": 274890 }, { "epoch": 66.03, "learning_rate": 3.0402516262022313e-05, "loss": 0.002, "step": 274900 }, { "epoch": 66.03, "learning_rate": 3.0399213954976706e-05, "loss": 0.0025, "step": 274910 }, { "epoch": 66.04, "learning_rate": 3.0395911748953743e-05, "loss": 0.0017, "step": 274920 }, { "epoch": 66.04, "learning_rate": 3.0392609643970387e-05, "loss": 0.0022, "step": 274930 }, { "epoch": 66.04, "learning_rate": 3.0389307640043695e-05, "loss": 0.0019, "step": 274940 }, { "epoch": 66.04, "learning_rate": 3.038600573719069e-05, "loss": 0.0016, "step": 274950 }, { "epoch": 66.05, "learning_rate": 3.0382703935428358e-05, "loss": 0.0026, "step": 274960 }, { "epoch": 66.05, "learning_rate": 3.0379402234773746e-05, "loss": 0.0021, "step": 274970 }, { "epoch": 66.05, "learning_rate": 3.0376100635243843e-05, "loss": 0.002, "step": 274980 }, { "epoch": 66.05, "learning_rate": 3.0372799136855702e-05, "loss": 0.002, "step": 274990 }, { "epoch": 66.06, "learning_rate": 3.0369497739626296e-05, "loss": 0.0023, "step": 275000 }, { "epoch": 66.06, "learning_rate": 3.0366196443572682e-05, "loss": 0.0028, "step": 275010 }, { "epoch": 66.06, "learning_rate": 3.036289524871186e-05, "loss": 0.0021, "step": 275020 }, { "epoch": 66.06, "learning_rate": 3.0359594155060813e-05, "loss": 0.0019, "step": 275030 }, { "epoch": 66.06, "learning_rate": 3.0356293162636608e-05, "loss": 0.0025, "step": 275040 }, { "epoch": 66.07, "learning_rate": 3.035299227145621e-05, "loss": 0.0028, "step": 275050 }, { "epoch": 66.07, "learning_rate": 3.0349691481536672e-05, "loss": 0.0018, "step": 275060 }, { "epoch": 66.07, "learning_rate": 3.0346390792894973e-05, "loss": 0.0019, "step": 275070 }, { "epoch": 66.07, "learning_rate": 3.0343090205548157e-05, "loss": 0.0019, "step": 275080 }, { "epoch": 66.08, "learning_rate": 3.033978971951321e-05, "loss": 0.0018, "step": 275090 }, { "epoch": 66.08, "learning_rate": 3.033648933480714e-05, "loss": 0.0022, "step": 275100 }, { "epoch": 66.08, "learning_rate": 3.0333189051446985e-05, "loss": 0.0019, "step": 275110 }, { "epoch": 66.08, "learning_rate": 3.0329888869449728e-05, "loss": 0.0071, "step": 275120 }, { "epoch": 66.09, "learning_rate": 3.03265887888324e-05, "loss": 0.0021, "step": 275130 }, { "epoch": 66.09, "learning_rate": 3.0323288809611982e-05, "loss": 0.004, "step": 275140 }, { "epoch": 66.09, "learning_rate": 3.0319988931805514e-05, "loss": 0.0018, "step": 275150 }, { "epoch": 66.09, "learning_rate": 3.031668915542999e-05, "loss": 0.0027, "step": 275160 }, { "epoch": 66.09, "learning_rate": 3.0313389480502397e-05, "loss": 0.0019, "step": 275170 }, { "epoch": 66.1, "learning_rate": 3.0310089907039773e-05, "loss": 0.002, "step": 275180 }, { "epoch": 66.1, "learning_rate": 3.0306790435059095e-05, "loss": 0.0016, "step": 275190 }, { "epoch": 66.1, "learning_rate": 3.03034910645774e-05, "loss": 0.0247, "step": 275200 }, { "epoch": 66.1, "learning_rate": 3.030019179561166e-05, "loss": 0.0065, "step": 275210 }, { "epoch": 66.11, "learning_rate": 3.0296892628178915e-05, "loss": 0.0022, "step": 275220 }, { "epoch": 66.11, "learning_rate": 3.0293593562296142e-05, "loss": 0.0019, "step": 275230 }, { "epoch": 66.11, "learning_rate": 3.0290294597980352e-05, "loss": 0.0022, "step": 275240 }, { "epoch": 66.11, "learning_rate": 3.028699573524854e-05, "loss": 0.0026, "step": 275250 }, { "epoch": 66.11, "learning_rate": 3.0283696974117714e-05, "loss": 0.002, "step": 275260 }, { "epoch": 66.12, "learning_rate": 3.0280398314604896e-05, "loss": 0.0018, "step": 275270 }, { "epoch": 66.12, "learning_rate": 3.0277099756727057e-05, "loss": 0.0029, "step": 275280 }, { "epoch": 66.12, "learning_rate": 3.0273801300501226e-05, "loss": 0.0019, "step": 275290 }, { "epoch": 66.12, "learning_rate": 3.027050294594439e-05, "loss": 0.0019, "step": 275300 }, { "epoch": 66.13, "learning_rate": 3.026720469307352e-05, "loss": 0.0018, "step": 275310 }, { "epoch": 66.13, "learning_rate": 3.026390654190567e-05, "loss": 0.0021, "step": 275320 }, { "epoch": 66.13, "learning_rate": 3.0260608492457788e-05, "loss": 0.0018, "step": 275330 }, { "epoch": 66.13, "learning_rate": 3.025731054474691e-05, "loss": 0.0017, "step": 275340 }, { "epoch": 66.14, "learning_rate": 3.0254012698790003e-05, "loss": 0.0019, "step": 275350 }, { "epoch": 66.14, "learning_rate": 3.02507149546041e-05, "loss": 0.002, "step": 275360 }, { "epoch": 66.14, "learning_rate": 3.0247417312206167e-05, "loss": 0.002, "step": 275370 }, { "epoch": 66.14, "learning_rate": 3.024411977161321e-05, "loss": 0.002, "step": 275380 }, { "epoch": 66.14, "learning_rate": 3.0240822332842224e-05, "loss": 0.0019, "step": 275390 }, { "epoch": 66.15, "learning_rate": 3.0237524995910205e-05, "loss": 0.0016, "step": 275400 }, { "epoch": 66.15, "learning_rate": 3.0234227760834145e-05, "loss": 0.0021, "step": 275410 }, { "epoch": 66.15, "learning_rate": 3.0230930627631032e-05, "loss": 0.002, "step": 275420 }, { "epoch": 66.15, "learning_rate": 3.022763359631789e-05, "loss": 0.0018, "step": 275430 }, { "epoch": 66.16, "learning_rate": 3.022433666691169e-05, "loss": 0.0021, "step": 275440 }, { "epoch": 66.16, "learning_rate": 3.0221039839429398e-05, "loss": 0.0017, "step": 275450 }, { "epoch": 66.16, "learning_rate": 3.0217743113888064e-05, "loss": 0.0023, "step": 275460 }, { "epoch": 66.16, "learning_rate": 3.0214446490304614e-05, "loss": 0.0019, "step": 275470 }, { "epoch": 66.16, "learning_rate": 3.02111499686961e-05, "loss": 0.0031, "step": 275480 }, { "epoch": 66.17, "learning_rate": 3.0207853549079463e-05, "loss": 0.0019, "step": 275490 }, { "epoch": 66.17, "learning_rate": 3.020455723147173e-05, "loss": 0.0221, "step": 275500 }, { "epoch": 66.17, "learning_rate": 3.020126101588987e-05, "loss": 0.0035, "step": 275510 }, { "epoch": 66.17, "learning_rate": 3.0197964902350873e-05, "loss": 0.0019, "step": 275520 }, { "epoch": 66.18, "learning_rate": 3.0194668890871737e-05, "loss": 0.0016, "step": 275530 }, { "epoch": 66.18, "learning_rate": 3.0191372981469436e-05, "loss": 0.002, "step": 275540 }, { "epoch": 66.18, "learning_rate": 3.0188077174160965e-05, "loss": 0.0019, "step": 275550 }, { "epoch": 66.18, "learning_rate": 3.018478146896331e-05, "loss": 0.0027, "step": 275560 }, { "epoch": 66.19, "learning_rate": 3.0181485865893462e-05, "loss": 0.0034, "step": 275570 }, { "epoch": 66.19, "learning_rate": 3.0178190364968385e-05, "loss": 0.0023, "step": 275580 }, { "epoch": 66.19, "learning_rate": 3.0174894966205104e-05, "loss": 0.0027, "step": 275590 }, { "epoch": 66.19, "learning_rate": 3.0171599669620577e-05, "loss": 0.0031, "step": 275600 }, { "epoch": 66.19, "learning_rate": 3.0168304475231774e-05, "loss": 0.0023, "step": 275610 }, { "epoch": 66.2, "learning_rate": 3.0165009383055713e-05, "loss": 0.0019, "step": 275620 }, { "epoch": 66.2, "learning_rate": 3.016171439310934e-05, "loss": 0.0044, "step": 275630 }, { "epoch": 66.2, "learning_rate": 3.0158419505409687e-05, "loss": 0.0026, "step": 275640 }, { "epoch": 66.2, "learning_rate": 3.015512471997367e-05, "loss": 0.0019, "step": 275650 }, { "epoch": 66.21, "learning_rate": 3.0151830036818334e-05, "loss": 0.0031, "step": 275660 }, { "epoch": 66.21, "learning_rate": 3.014853545596062e-05, "loss": 0.0035, "step": 275670 }, { "epoch": 66.21, "learning_rate": 3.0145240977417522e-05, "loss": 0.0074, "step": 275680 }, { "epoch": 66.21, "learning_rate": 3.0141946601206018e-05, "loss": 0.0021, "step": 275690 }, { "epoch": 66.22, "learning_rate": 3.0138652327343088e-05, "loss": 0.0018, "step": 275700 }, { "epoch": 66.22, "learning_rate": 3.0135358155845705e-05, "loss": 0.0017, "step": 275710 }, { "epoch": 66.22, "learning_rate": 3.0132064086730855e-05, "loss": 0.0022, "step": 275720 }, { "epoch": 66.22, "learning_rate": 3.0128770120015515e-05, "loss": 0.0017, "step": 275730 }, { "epoch": 66.22, "learning_rate": 3.0125476255716668e-05, "loss": 0.0024, "step": 275740 }, { "epoch": 66.23, "learning_rate": 3.012218249385126e-05, "loss": 0.0019, "step": 275750 }, { "epoch": 66.23, "learning_rate": 3.0118888834436308e-05, "loss": 0.002, "step": 275760 }, { "epoch": 66.23, "learning_rate": 3.0115595277488752e-05, "loss": 0.0014, "step": 275770 }, { "epoch": 66.23, "learning_rate": 3.0112301823025607e-05, "loss": 0.0053, "step": 275780 }, { "epoch": 66.24, "learning_rate": 3.0109008471063805e-05, "loss": 0.0029, "step": 275790 }, { "epoch": 66.24, "learning_rate": 3.0105715221620356e-05, "loss": 0.0018, "step": 275800 }, { "epoch": 66.24, "learning_rate": 3.010242207471222e-05, "loss": 0.0025, "step": 275810 }, { "epoch": 66.24, "learning_rate": 3.0099129030356343e-05, "loss": 0.0029, "step": 275820 }, { "epoch": 66.24, "learning_rate": 3.0095836088569735e-05, "loss": 0.0018, "step": 275830 }, { "epoch": 66.25, "learning_rate": 3.0092543249369354e-05, "loss": 0.0021, "step": 275840 }, { "epoch": 66.25, "learning_rate": 3.008925051277217e-05, "loss": 0.0021, "step": 275850 }, { "epoch": 66.25, "learning_rate": 3.0085957878795157e-05, "loss": 0.0037, "step": 275860 }, { "epoch": 66.25, "learning_rate": 3.0082665347455273e-05, "loss": 0.0024, "step": 275870 }, { "epoch": 66.26, "learning_rate": 3.007937291876952e-05, "loss": 0.0028, "step": 275880 }, { "epoch": 66.26, "learning_rate": 3.007608059275483e-05, "loss": 0.0016, "step": 275890 }, { "epoch": 66.26, "learning_rate": 3.0072788369428194e-05, "loss": 0.0018, "step": 275900 }, { "epoch": 66.26, "learning_rate": 3.006949624880656e-05, "loss": 0.005, "step": 275910 }, { "epoch": 66.27, "learning_rate": 3.006620423090693e-05, "loss": 0.0019, "step": 275920 }, { "epoch": 66.27, "learning_rate": 3.0062912315746228e-05, "loss": 0.0017, "step": 275930 }, { "epoch": 66.27, "learning_rate": 3.0059620503341462e-05, "loss": 0.0021, "step": 275940 }, { "epoch": 66.27, "learning_rate": 3.0056328793709576e-05, "loss": 0.008, "step": 275950 }, { "epoch": 66.27, "learning_rate": 3.0053037186867526e-05, "loss": 0.0034, "step": 275960 }, { "epoch": 66.28, "learning_rate": 3.0049745682832305e-05, "loss": 0.0026, "step": 275970 }, { "epoch": 66.28, "learning_rate": 3.004645428162084e-05, "loss": 0.0017, "step": 275980 }, { "epoch": 66.28, "learning_rate": 3.004316298325013e-05, "loss": 0.0017, "step": 275990 }, { "epoch": 66.28, "learning_rate": 3.0039871787737118e-05, "loss": 0.0015, "step": 276000 }, { "epoch": 66.29, "learning_rate": 3.0036580695098782e-05, "loss": 0.0019, "step": 276010 }, { "epoch": 66.29, "learning_rate": 3.003328970535208e-05, "loss": 0.002, "step": 276020 }, { "epoch": 66.29, "learning_rate": 3.0029998818513948e-05, "loss": 0.0019, "step": 276030 }, { "epoch": 66.29, "learning_rate": 3.0026708034601398e-05, "loss": 0.0017, "step": 276040 }, { "epoch": 66.3, "learning_rate": 3.0023417353631334e-05, "loss": 0.0215, "step": 276050 }, { "epoch": 66.3, "learning_rate": 3.0020126775620767e-05, "loss": 0.002, "step": 276060 }, { "epoch": 66.3, "learning_rate": 3.0016836300586615e-05, "loss": 0.0017, "step": 276070 }, { "epoch": 66.3, "learning_rate": 3.001354592854587e-05, "loss": 0.0017, "step": 276080 }, { "epoch": 66.3, "learning_rate": 3.0010255659515485e-05, "loss": 0.0019, "step": 276090 }, { "epoch": 66.31, "learning_rate": 3.0006965493512383e-05, "loss": 0.0018, "step": 276100 }, { "epoch": 66.31, "learning_rate": 3.000367543055357e-05, "loss": 0.0022, "step": 276110 }, { "epoch": 66.31, "learning_rate": 3.0000385470655955e-05, "loss": 0.0017, "step": 276120 }, { "epoch": 66.31, "learning_rate": 2.9997095613836545e-05, "loss": 0.0021, "step": 276130 }, { "epoch": 66.32, "learning_rate": 2.9993805860112255e-05, "loss": 0.0024, "step": 276140 }, { "epoch": 66.32, "learning_rate": 2.9990516209500065e-05, "loss": 0.0016, "step": 276150 }, { "epoch": 66.32, "learning_rate": 2.998722666201693e-05, "loss": 0.0021, "step": 276160 }, { "epoch": 66.32, "learning_rate": 2.998393721767978e-05, "loss": 0.0021, "step": 276170 }, { "epoch": 66.32, "learning_rate": 2.9980647876505595e-05, "loss": 0.0026, "step": 276180 }, { "epoch": 66.33, "learning_rate": 2.9977358638511312e-05, "loss": 0.0014, "step": 276190 }, { "epoch": 66.33, "learning_rate": 2.99740695037139e-05, "loss": 0.0079, "step": 276200 }, { "epoch": 66.33, "learning_rate": 2.997078047213029e-05, "loss": 0.0032, "step": 276210 }, { "epoch": 66.33, "learning_rate": 2.9967491543777455e-05, "loss": 0.002, "step": 276220 }, { "epoch": 66.34, "learning_rate": 2.996420271867234e-05, "loss": 0.0025, "step": 276230 }, { "epoch": 66.34, "learning_rate": 2.9960913996831875e-05, "loss": 0.0019, "step": 276240 }, { "epoch": 66.34, "learning_rate": 2.9957625378273036e-05, "loss": 0.0018, "step": 276250 }, { "epoch": 66.34, "learning_rate": 2.9954336863012756e-05, "loss": 0.0023, "step": 276260 }, { "epoch": 66.35, "learning_rate": 2.9951048451068002e-05, "loss": 0.0034, "step": 276270 }, { "epoch": 66.35, "learning_rate": 2.9947760142455694e-05, "loss": 0.0016, "step": 276280 }, { "epoch": 66.35, "learning_rate": 2.994447193719282e-05, "loss": 0.002, "step": 276290 }, { "epoch": 66.35, "learning_rate": 2.99411838352963e-05, "loss": 0.0015, "step": 276300 }, { "epoch": 66.35, "learning_rate": 2.993789583678307e-05, "loss": 0.0018, "step": 276310 }, { "epoch": 66.36, "learning_rate": 2.993460794167011e-05, "loss": 0.0015, "step": 276320 }, { "epoch": 66.36, "learning_rate": 2.9931320149974333e-05, "loss": 0.0018, "step": 276330 }, { "epoch": 66.36, "learning_rate": 2.992803246171272e-05, "loss": 0.0023, "step": 276340 }, { "epoch": 66.36, "learning_rate": 2.9924744876902177e-05, "loss": 0.0017, "step": 276350 }, { "epoch": 66.37, "learning_rate": 2.992145739555968e-05, "loss": 0.0019, "step": 276360 }, { "epoch": 66.37, "learning_rate": 2.9918170017702147e-05, "loss": 0.0017, "step": 276370 }, { "epoch": 66.37, "learning_rate": 2.991488274334655e-05, "loss": 0.0028, "step": 276380 }, { "epoch": 66.37, "learning_rate": 2.9911595572509816e-05, "loss": 0.0031, "step": 276390 }, { "epoch": 66.38, "learning_rate": 2.9908308505208866e-05, "loss": 0.0017, "step": 276400 }, { "epoch": 66.38, "learning_rate": 2.9905021541460675e-05, "loss": 0.0014, "step": 276410 }, { "epoch": 66.38, "learning_rate": 2.990173468128216e-05, "loss": 0.0017, "step": 276420 }, { "epoch": 66.38, "learning_rate": 2.9898447924690293e-05, "loss": 0.0026, "step": 276430 }, { "epoch": 66.38, "learning_rate": 2.9895161271701967e-05, "loss": 0.0018, "step": 276440 }, { "epoch": 66.39, "learning_rate": 2.989187472233417e-05, "loss": 0.0018, "step": 276450 }, { "epoch": 66.39, "learning_rate": 2.9888588276603814e-05, "loss": 0.0021, "step": 276460 }, { "epoch": 66.39, "learning_rate": 2.988530193452783e-05, "loss": 0.0018, "step": 276470 }, { "epoch": 66.39, "learning_rate": 2.9882015696123183e-05, "loss": 0.0015, "step": 276480 }, { "epoch": 66.4, "learning_rate": 2.987872956140678e-05, "loss": 0.0044, "step": 276490 }, { "epoch": 66.4, "learning_rate": 2.9875443530395592e-05, "loss": 0.0039, "step": 276500 }, { "epoch": 66.4, "learning_rate": 2.9872157603106514e-05, "loss": 0.0017, "step": 276510 }, { "epoch": 66.4, "learning_rate": 2.986887177955653e-05, "loss": 0.002, "step": 276520 }, { "epoch": 66.4, "learning_rate": 2.986558605976254e-05, "loss": 0.0018, "step": 276530 }, { "epoch": 66.41, "learning_rate": 2.9862300443741476e-05, "loss": 0.0018, "step": 276540 }, { "epoch": 66.41, "learning_rate": 2.98590149315103e-05, "loss": 0.0019, "step": 276550 }, { "epoch": 66.41, "learning_rate": 2.9855729523085907e-05, "loss": 0.0015, "step": 276560 }, { "epoch": 66.41, "learning_rate": 2.9852444218485277e-05, "loss": 0.0016, "step": 276570 }, { "epoch": 66.42, "learning_rate": 2.9849159017725293e-05, "loss": 0.0018, "step": 276580 }, { "epoch": 66.42, "learning_rate": 2.9845873920822935e-05, "loss": 0.0016, "step": 276590 }, { "epoch": 66.42, "learning_rate": 2.98425889277951e-05, "loss": 0.002, "step": 276600 }, { "epoch": 66.42, "learning_rate": 2.983930403865872e-05, "loss": 0.0015, "step": 276610 }, { "epoch": 66.43, "learning_rate": 2.983601925343076e-05, "loss": 0.0018, "step": 276620 }, { "epoch": 66.43, "learning_rate": 2.9832734572128102e-05, "loss": 0.0016, "step": 276630 }, { "epoch": 66.43, "learning_rate": 2.982944999476772e-05, "loss": 0.0021, "step": 276640 }, { "epoch": 66.43, "learning_rate": 2.98261655213665e-05, "loss": 0.0018, "step": 276650 }, { "epoch": 66.43, "learning_rate": 2.9822881151941407e-05, "loss": 0.0018, "step": 276660 }, { "epoch": 66.44, "learning_rate": 2.981959688650936e-05, "loss": 0.0016, "step": 276670 }, { "epoch": 66.44, "learning_rate": 2.9816312725087258e-05, "loss": 0.0022, "step": 276680 }, { "epoch": 66.44, "learning_rate": 2.9813028667692068e-05, "loss": 0.0016, "step": 276690 }, { "epoch": 66.44, "learning_rate": 2.9809744714340676e-05, "loss": 0.0019, "step": 276700 }, { "epoch": 66.45, "learning_rate": 2.980646086505005e-05, "loss": 0.0018, "step": 276710 }, { "epoch": 66.45, "learning_rate": 2.9803177119837073e-05, "loss": 0.0017, "step": 276720 }, { "epoch": 66.45, "learning_rate": 2.979989347871871e-05, "loss": 0.0055, "step": 276730 }, { "epoch": 66.45, "learning_rate": 2.9796609941711857e-05, "loss": 0.0017, "step": 276740 }, { "epoch": 66.46, "learning_rate": 2.979332650883344e-05, "loss": 0.0018, "step": 276750 }, { "epoch": 66.46, "learning_rate": 2.9790043180100393e-05, "loss": 0.0016, "step": 276760 }, { "epoch": 66.46, "learning_rate": 2.978675995552962e-05, "loss": 0.0015, "step": 276770 }, { "epoch": 66.46, "learning_rate": 2.978347683513807e-05, "loss": 0.0019, "step": 276780 }, { "epoch": 66.46, "learning_rate": 2.9780193818942635e-05, "loss": 0.0015, "step": 276790 }, { "epoch": 66.47, "learning_rate": 2.977691090696027e-05, "loss": 0.0019, "step": 276800 }, { "epoch": 66.47, "learning_rate": 2.9773628099207872e-05, "loss": 0.0018, "step": 276810 }, { "epoch": 66.47, "learning_rate": 2.977034539570235e-05, "loss": 0.0017, "step": 276820 }, { "epoch": 66.47, "learning_rate": 2.9767062796460653e-05, "loss": 0.0017, "step": 276830 }, { "epoch": 66.48, "learning_rate": 2.976378030149966e-05, "loss": 0.0021, "step": 276840 }, { "epoch": 66.48, "learning_rate": 2.9760497910836337e-05, "loss": 0.0018, "step": 276850 }, { "epoch": 66.48, "learning_rate": 2.9757215624487554e-05, "loss": 0.0018, "step": 276860 }, { "epoch": 66.48, "learning_rate": 2.9753933442470273e-05, "loss": 0.0023, "step": 276870 }, { "epoch": 66.48, "learning_rate": 2.9750651364801385e-05, "loss": 0.002, "step": 276880 }, { "epoch": 66.49, "learning_rate": 2.97473693914978e-05, "loss": 0.0018, "step": 276890 }, { "epoch": 66.49, "learning_rate": 2.974408752257644e-05, "loss": 0.0018, "step": 276900 }, { "epoch": 66.49, "learning_rate": 2.974080575805423e-05, "loss": 0.0025, "step": 276910 }, { "epoch": 66.49, "learning_rate": 2.973752409794807e-05, "loss": 0.0019, "step": 276920 }, { "epoch": 66.5, "learning_rate": 2.9734242542274876e-05, "loss": 0.0135, "step": 276930 }, { "epoch": 66.5, "learning_rate": 2.9730961091051583e-05, "loss": 0.0017, "step": 276940 }, { "epoch": 66.5, "learning_rate": 2.972767974429509e-05, "loss": 0.0018, "step": 276950 }, { "epoch": 66.5, "learning_rate": 2.9724398502022276e-05, "loss": 0.0032, "step": 276960 }, { "epoch": 66.51, "learning_rate": 2.9721117364250106e-05, "loss": 0.0071, "step": 276970 }, { "epoch": 66.51, "learning_rate": 2.971783633099545e-05, "loss": 0.0018, "step": 276980 }, { "epoch": 66.51, "learning_rate": 2.971455540227525e-05, "loss": 0.0019, "step": 276990 }, { "epoch": 66.51, "learning_rate": 2.9711274578106383e-05, "loss": 0.0018, "step": 277000 }, { "epoch": 66.51, "learning_rate": 2.97079938585058e-05, "loss": 0.0021, "step": 277010 }, { "epoch": 66.52, "learning_rate": 2.9704713243490367e-05, "loss": 0.0043, "step": 277020 }, { "epoch": 66.52, "learning_rate": 2.9701432733077018e-05, "loss": 0.002, "step": 277030 }, { "epoch": 66.52, "learning_rate": 2.9698152327282657e-05, "loss": 0.0015, "step": 277040 }, { "epoch": 66.52, "learning_rate": 2.9694872026124186e-05, "loss": 0.0016, "step": 277050 }, { "epoch": 66.53, "learning_rate": 2.9691591829618513e-05, "loss": 0.0016, "step": 277060 }, { "epoch": 66.53, "learning_rate": 2.9688311737782548e-05, "loss": 0.0054, "step": 277070 }, { "epoch": 66.53, "learning_rate": 2.968503175063319e-05, "loss": 0.0023, "step": 277080 }, { "epoch": 66.53, "learning_rate": 2.9681751868187358e-05, "loss": 0.0046, "step": 277090 }, { "epoch": 66.54, "learning_rate": 2.9678472090461927e-05, "loss": 0.0018, "step": 277100 }, { "epoch": 66.54, "learning_rate": 2.9675192417473847e-05, "loss": 0.0021, "step": 277110 }, { "epoch": 66.54, "learning_rate": 2.967191284923997e-05, "loss": 0.0023, "step": 277120 }, { "epoch": 66.54, "learning_rate": 2.9668633385777245e-05, "loss": 0.002, "step": 277130 }, { "epoch": 66.54, "learning_rate": 2.9665354027102533e-05, "loss": 0.0021, "step": 277140 }, { "epoch": 66.55, "learning_rate": 2.966207477323278e-05, "loss": 0.0035, "step": 277150 }, { "epoch": 66.55, "learning_rate": 2.9658795624184845e-05, "loss": 0.0019, "step": 277160 }, { "epoch": 66.55, "learning_rate": 2.9655516579975658e-05, "loss": 0.0019, "step": 277170 }, { "epoch": 66.55, "learning_rate": 2.9652237640622106e-05, "loss": 0.0023, "step": 277180 }, { "epoch": 66.56, "learning_rate": 2.9648958806141085e-05, "loss": 0.0024, "step": 277190 }, { "epoch": 66.56, "learning_rate": 2.9645680076549503e-05, "loss": 0.0022, "step": 277200 }, { "epoch": 66.56, "learning_rate": 2.9642401451864256e-05, "loss": 0.0079, "step": 277210 }, { "epoch": 66.56, "learning_rate": 2.9639122932102247e-05, "loss": 0.0031, "step": 277220 }, { "epoch": 66.56, "learning_rate": 2.9635844517280363e-05, "loss": 0.0025, "step": 277230 }, { "epoch": 66.57, "learning_rate": 2.9632566207415514e-05, "loss": 0.0017, "step": 277240 }, { "epoch": 66.57, "learning_rate": 2.962928800252459e-05, "loss": 0.0021, "step": 277250 }, { "epoch": 66.57, "learning_rate": 2.962600990262447e-05, "loss": 0.0026, "step": 277260 }, { "epoch": 66.57, "learning_rate": 2.9622731907732082e-05, "loss": 0.0021, "step": 277270 }, { "epoch": 66.58, "learning_rate": 2.961945401786429e-05, "loss": 0.0027, "step": 277280 }, { "epoch": 66.58, "learning_rate": 2.961617623303802e-05, "loss": 0.0018, "step": 277290 }, { "epoch": 66.58, "learning_rate": 2.9612898553270124e-05, "loss": 0.002, "step": 277300 }, { "epoch": 66.58, "learning_rate": 2.9609620978577547e-05, "loss": 0.0017, "step": 277310 }, { "epoch": 66.59, "learning_rate": 2.960634350897714e-05, "loss": 0.0024, "step": 277320 }, { "epoch": 66.59, "learning_rate": 2.9603066144485804e-05, "loss": 0.0023, "step": 277330 }, { "epoch": 66.59, "learning_rate": 2.959978888512044e-05, "loss": 0.0037, "step": 277340 }, { "epoch": 66.59, "learning_rate": 2.9596511730897934e-05, "loss": 0.002, "step": 277350 }, { "epoch": 66.59, "learning_rate": 2.959323468183518e-05, "loss": 0.002, "step": 277360 }, { "epoch": 66.6, "learning_rate": 2.9589957737949058e-05, "loss": 0.0025, "step": 277370 }, { "epoch": 66.6, "learning_rate": 2.958668089925647e-05, "loss": 0.0029, "step": 277380 }, { "epoch": 66.6, "learning_rate": 2.958340416577431e-05, "loss": 0.0017, "step": 277390 }, { "epoch": 66.6, "learning_rate": 2.958012753751943e-05, "loss": 0.002, "step": 277400 }, { "epoch": 66.61, "learning_rate": 2.9576851014508767e-05, "loss": 0.0019, "step": 277410 }, { "epoch": 66.61, "learning_rate": 2.9573574596759167e-05, "loss": 0.0018, "step": 277420 }, { "epoch": 66.61, "learning_rate": 2.9570298284287556e-05, "loss": 0.0025, "step": 277430 }, { "epoch": 66.61, "learning_rate": 2.9567022077110773e-05, "loss": 0.0023, "step": 277440 }, { "epoch": 66.62, "learning_rate": 2.956374597524575e-05, "loss": 0.002, "step": 277450 }, { "epoch": 66.62, "learning_rate": 2.956046997870935e-05, "loss": 0.0022, "step": 277460 }, { "epoch": 66.62, "learning_rate": 2.9557194087518442e-05, "loss": 0.0043, "step": 277470 }, { "epoch": 66.62, "learning_rate": 2.955391830168994e-05, "loss": 0.0017, "step": 277480 }, { "epoch": 66.62, "learning_rate": 2.95506426212407e-05, "loss": 0.0024, "step": 277490 }, { "epoch": 66.63, "learning_rate": 2.954736704618763e-05, "loss": 0.0019, "step": 277500 }, { "epoch": 66.63, "learning_rate": 2.9544091576547595e-05, "loss": 0.0047, "step": 277510 }, { "epoch": 66.63, "learning_rate": 2.954081621233749e-05, "loss": 0.0017, "step": 277520 }, { "epoch": 66.63, "learning_rate": 2.9537540953574194e-05, "loss": 0.0021, "step": 277530 }, { "epoch": 66.64, "learning_rate": 2.9534265800274564e-05, "loss": 0.0039, "step": 277540 }, { "epoch": 66.64, "learning_rate": 2.9530990752455523e-05, "loss": 0.0067, "step": 277550 }, { "epoch": 66.64, "learning_rate": 2.9527715810133905e-05, "loss": 0.0019, "step": 277560 }, { "epoch": 66.64, "learning_rate": 2.9524440973326628e-05, "loss": 0.0022, "step": 277570 }, { "epoch": 66.64, "learning_rate": 2.9521166242050535e-05, "loss": 0.0034, "step": 277580 }, { "epoch": 66.65, "learning_rate": 2.9517891616322548e-05, "loss": 0.0023, "step": 277590 }, { "epoch": 66.65, "learning_rate": 2.9514617096159507e-05, "loss": 0.002, "step": 277600 }, { "epoch": 66.65, "learning_rate": 2.951134268157829e-05, "loss": 0.0017, "step": 277610 }, { "epoch": 66.65, "learning_rate": 2.95080683725958e-05, "loss": 0.0119, "step": 277620 }, { "epoch": 66.66, "learning_rate": 2.9504794169228878e-05, "loss": 0.0033, "step": 277630 }, { "epoch": 66.66, "learning_rate": 2.9501520071494436e-05, "loss": 0.0027, "step": 277640 }, { "epoch": 66.66, "learning_rate": 2.9498246079409312e-05, "loss": 0.004, "step": 277650 }, { "epoch": 66.66, "learning_rate": 2.949497219299041e-05, "loss": 0.0024, "step": 277660 }, { "epoch": 66.67, "learning_rate": 2.949169841225461e-05, "loss": 0.0017, "step": 277670 }, { "epoch": 66.67, "learning_rate": 2.9488424737218733e-05, "loss": 0.0083, "step": 277680 }, { "epoch": 66.67, "learning_rate": 2.9485151167899717e-05, "loss": 0.0019, "step": 277690 }, { "epoch": 66.67, "learning_rate": 2.948187770431438e-05, "loss": 0.0023, "step": 277700 }, { "epoch": 66.67, "learning_rate": 2.9478604346479637e-05, "loss": 0.002, "step": 277710 }, { "epoch": 66.68, "learning_rate": 2.947533109441232e-05, "loss": 0.0024, "step": 277720 }, { "epoch": 66.68, "learning_rate": 2.947205794812934e-05, "loss": 0.0025, "step": 277730 }, { "epoch": 66.68, "learning_rate": 2.946878490764754e-05, "loss": 0.0021, "step": 277740 }, { "epoch": 66.68, "learning_rate": 2.9465511972983773e-05, "loss": 0.0049, "step": 277750 }, { "epoch": 66.69, "learning_rate": 2.9462239144154956e-05, "loss": 0.0041, "step": 277760 }, { "epoch": 66.69, "learning_rate": 2.94589664211779e-05, "loss": 0.0019, "step": 277770 }, { "epoch": 66.69, "learning_rate": 2.9455693804069533e-05, "loss": 0.0026, "step": 277780 }, { "epoch": 66.69, "learning_rate": 2.9452421292846666e-05, "loss": 0.0033, "step": 277790 }, { "epoch": 66.7, "learning_rate": 2.944914888752621e-05, "loss": 0.0019, "step": 277800 }, { "epoch": 66.7, "learning_rate": 2.944587658812501e-05, "loss": 0.003, "step": 277810 }, { "epoch": 66.7, "learning_rate": 2.9442604394659924e-05, "loss": 0.0023, "step": 277820 }, { "epoch": 66.7, "learning_rate": 2.9439332307147837e-05, "loss": 0.0039, "step": 277830 }, { "epoch": 66.7, "learning_rate": 2.9436060325605585e-05, "loss": 0.0033, "step": 277840 }, { "epoch": 66.71, "learning_rate": 2.9432788450050076e-05, "loss": 0.0018, "step": 277850 }, { "epoch": 66.71, "learning_rate": 2.9429516680498125e-05, "loss": 0.0021, "step": 277860 }, { "epoch": 66.71, "learning_rate": 2.9426245016966635e-05, "loss": 0.0021, "step": 277870 }, { "epoch": 66.71, "learning_rate": 2.942297345947246e-05, "loss": 0.002, "step": 277880 }, { "epoch": 66.72, "learning_rate": 2.9419702008032418e-05, "loss": 0.0022, "step": 277890 }, { "epoch": 66.72, "learning_rate": 2.941643066266343e-05, "loss": 0.0016, "step": 277900 }, { "epoch": 66.72, "learning_rate": 2.941315942338231e-05, "loss": 0.0018, "step": 277910 }, { "epoch": 66.72, "learning_rate": 2.9409888290205954e-05, "loss": 0.0034, "step": 277920 }, { "epoch": 66.72, "learning_rate": 2.9406617263151192e-05, "loss": 0.0021, "step": 277930 }, { "epoch": 66.73, "learning_rate": 2.9403346342234917e-05, "loss": 0.0018, "step": 277940 }, { "epoch": 66.73, "learning_rate": 2.9400075527473947e-05, "loss": 0.0018, "step": 277950 }, { "epoch": 66.73, "learning_rate": 2.9396804818885176e-05, "loss": 0.0022, "step": 277960 }, { "epoch": 66.73, "learning_rate": 2.9393534216485435e-05, "loss": 0.003, "step": 277970 }, { "epoch": 66.74, "learning_rate": 2.9390263720291584e-05, "loss": 0.0024, "step": 277980 }, { "epoch": 66.74, "learning_rate": 2.9386993330320507e-05, "loss": 0.0051, "step": 277990 }, { "epoch": 66.74, "learning_rate": 2.938372304658902e-05, "loss": 0.0019, "step": 278000 }, { "epoch": 66.74, "learning_rate": 2.9380452869114005e-05, "loss": 0.0024, "step": 278010 }, { "epoch": 66.75, "learning_rate": 2.9377182797912302e-05, "loss": 0.0021, "step": 278020 }, { "epoch": 66.75, "learning_rate": 2.9373912833000782e-05, "loss": 0.0027, "step": 278030 }, { "epoch": 66.75, "learning_rate": 2.9370642974396295e-05, "loss": 0.0028, "step": 278040 }, { "epoch": 66.75, "learning_rate": 2.9367373222115663e-05, "loss": 0.003, "step": 278050 }, { "epoch": 66.75, "learning_rate": 2.9364103576175782e-05, "loss": 0.0026, "step": 278060 }, { "epoch": 66.76, "learning_rate": 2.9360834036593465e-05, "loss": 0.002, "step": 278070 }, { "epoch": 66.76, "learning_rate": 2.93575646033856e-05, "loss": 0.0018, "step": 278080 }, { "epoch": 66.76, "learning_rate": 2.9354295276569e-05, "loss": 0.0019, "step": 278090 }, { "epoch": 66.76, "learning_rate": 2.9351026056160553e-05, "loss": 0.0018, "step": 278100 }, { "epoch": 66.77, "learning_rate": 2.9347756942177085e-05, "loss": 0.0021, "step": 278110 }, { "epoch": 66.77, "learning_rate": 2.9344487934635444e-05, "loss": 0.0019, "step": 278120 }, { "epoch": 66.77, "learning_rate": 2.934121903355249e-05, "loss": 0.0042, "step": 278130 }, { "epoch": 66.77, "learning_rate": 2.9337950238945056e-05, "loss": 0.0021, "step": 278140 }, { "epoch": 66.78, "learning_rate": 2.9334681550830012e-05, "loss": 0.0032, "step": 278150 }, { "epoch": 66.78, "learning_rate": 2.933141296922418e-05, "loss": 0.0019, "step": 278160 }, { "epoch": 66.78, "learning_rate": 2.9328144494144437e-05, "loss": 0.0018, "step": 278170 }, { "epoch": 66.78, "learning_rate": 2.932487612560761e-05, "loss": 0.0019, "step": 278180 }, { "epoch": 66.78, "learning_rate": 2.9321607863630517e-05, "loss": 0.0021, "step": 278190 }, { "epoch": 66.79, "learning_rate": 2.9318339708230058e-05, "loss": 0.0023, "step": 278200 }, { "epoch": 66.79, "learning_rate": 2.931507165942303e-05, "loss": 0.0021, "step": 278210 }, { "epoch": 66.79, "learning_rate": 2.931180371722631e-05, "loss": 0.0025, "step": 278220 }, { "epoch": 66.79, "learning_rate": 2.9308535881656708e-05, "loss": 0.0018, "step": 278230 }, { "epoch": 66.8, "learning_rate": 2.9305268152731107e-05, "loss": 0.0024, "step": 278240 }, { "epoch": 66.8, "learning_rate": 2.9302000530466318e-05, "loss": 0.002, "step": 278250 }, { "epoch": 66.8, "learning_rate": 2.9298733014879186e-05, "loss": 0.0049, "step": 278260 }, { "epoch": 66.8, "learning_rate": 2.929546560598656e-05, "loss": 0.0024, "step": 278270 }, { "epoch": 66.8, "learning_rate": 2.9292198303805275e-05, "loss": 0.0027, "step": 278280 }, { "epoch": 66.81, "learning_rate": 2.928893110835218e-05, "loss": 0.0017, "step": 278290 }, { "epoch": 66.81, "learning_rate": 2.9285664019644095e-05, "loss": 0.0028, "step": 278300 }, { "epoch": 66.81, "learning_rate": 2.9282397037697884e-05, "loss": 0.0019, "step": 278310 }, { "epoch": 66.81, "learning_rate": 2.9279130162530377e-05, "loss": 0.0019, "step": 278320 }, { "epoch": 66.82, "learning_rate": 2.9275863394158387e-05, "loss": 0.0022, "step": 278330 }, { "epoch": 66.82, "learning_rate": 2.927259673259879e-05, "loss": 0.0017, "step": 278340 }, { "epoch": 66.82, "learning_rate": 2.926933017786838e-05, "loss": 0.0025, "step": 278350 }, { "epoch": 66.82, "learning_rate": 2.926606372998404e-05, "loss": 0.0018, "step": 278360 }, { "epoch": 66.83, "learning_rate": 2.926279738896256e-05, "loss": 0.0022, "step": 278370 }, { "epoch": 66.83, "learning_rate": 2.9259531154820812e-05, "loss": 0.0028, "step": 278380 }, { "epoch": 66.83, "learning_rate": 2.925626502757561e-05, "loss": 0.0019, "step": 278390 }, { "epoch": 66.83, "learning_rate": 2.9252999007243785e-05, "loss": 0.0026, "step": 278400 }, { "epoch": 66.83, "learning_rate": 2.924973309384218e-05, "loss": 0.002, "step": 278410 }, { "epoch": 66.84, "learning_rate": 2.9246467287387618e-05, "loss": 0.0016, "step": 278420 }, { "epoch": 66.84, "learning_rate": 2.924320158789694e-05, "loss": 0.0022, "step": 278430 }, { "epoch": 66.84, "learning_rate": 2.923993599538697e-05, "loss": 0.0017, "step": 278440 }, { "epoch": 66.84, "learning_rate": 2.9236670509874558e-05, "loss": 0.0024, "step": 278450 }, { "epoch": 66.85, "learning_rate": 2.9233405131376522e-05, "loss": 0.002, "step": 278460 }, { "epoch": 66.85, "learning_rate": 2.9230139859909667e-05, "loss": 0.0019, "step": 278470 }, { "epoch": 66.85, "learning_rate": 2.9226874695490867e-05, "loss": 0.0017, "step": 278480 }, { "epoch": 66.85, "learning_rate": 2.9223609638136913e-05, "loss": 0.0038, "step": 278490 }, { "epoch": 66.86, "learning_rate": 2.9220344687864664e-05, "loss": 0.0019, "step": 278500 }, { "epoch": 66.86, "learning_rate": 2.921707984469091e-05, "loss": 0.002, "step": 278510 }, { "epoch": 66.86, "learning_rate": 2.9213815108632527e-05, "loss": 0.0018, "step": 278520 }, { "epoch": 66.86, "learning_rate": 2.9210550479706306e-05, "loss": 0.0022, "step": 278530 }, { "epoch": 66.86, "learning_rate": 2.9207285957929065e-05, "loss": 0.002, "step": 278540 }, { "epoch": 66.87, "learning_rate": 2.9204021543317657e-05, "loss": 0.0021, "step": 278550 }, { "epoch": 66.87, "learning_rate": 2.9200757235888897e-05, "loss": 0.0018, "step": 278560 }, { "epoch": 66.87, "learning_rate": 2.9197493035659606e-05, "loss": 0.0018, "step": 278570 }, { "epoch": 66.87, "learning_rate": 2.9194228942646608e-05, "loss": 0.0019, "step": 278580 }, { "epoch": 66.88, "learning_rate": 2.9190964956866727e-05, "loss": 0.0019, "step": 278590 }, { "epoch": 66.88, "learning_rate": 2.9187701078336803e-05, "loss": 0.0021, "step": 278600 }, { "epoch": 66.88, "learning_rate": 2.918443730707362e-05, "loss": 0.002, "step": 278610 }, { "epoch": 66.88, "learning_rate": 2.9181173643094038e-05, "loss": 0.0019, "step": 278620 }, { "epoch": 66.88, "learning_rate": 2.9177910086414838e-05, "loss": 0.0019, "step": 278630 }, { "epoch": 66.89, "learning_rate": 2.9174646637052893e-05, "loss": 0.0055, "step": 278640 }, { "epoch": 66.89, "learning_rate": 2.9171383295024967e-05, "loss": 0.0027, "step": 278650 }, { "epoch": 66.89, "learning_rate": 2.9168120060347927e-05, "loss": 0.002, "step": 278660 }, { "epoch": 66.89, "learning_rate": 2.9164856933038564e-05, "loss": 0.0024, "step": 278670 }, { "epoch": 66.9, "learning_rate": 2.9161593913113694e-05, "loss": 0.0019, "step": 278680 }, { "epoch": 66.9, "learning_rate": 2.9158331000590155e-05, "loss": 0.0022, "step": 278690 }, { "epoch": 66.9, "learning_rate": 2.9155068195484735e-05, "loss": 0.002, "step": 278700 }, { "epoch": 66.9, "learning_rate": 2.915180549781429e-05, "loss": 0.0017, "step": 278710 }, { "epoch": 66.91, "learning_rate": 2.9148542907595588e-05, "loss": 0.0017, "step": 278720 }, { "epoch": 66.91, "learning_rate": 2.91452804248455e-05, "loss": 0.0019, "step": 278730 }, { "epoch": 66.91, "learning_rate": 2.9142018049580778e-05, "loss": 0.0018, "step": 278740 }, { "epoch": 66.91, "learning_rate": 2.9138755781818298e-05, "loss": 0.0018, "step": 278750 }, { "epoch": 66.91, "learning_rate": 2.9135493621574844e-05, "loss": 0.0018, "step": 278760 }, { "epoch": 66.92, "learning_rate": 2.913223156886721e-05, "loss": 0.0016, "step": 278770 }, { "epoch": 66.92, "learning_rate": 2.9128969623712227e-05, "loss": 0.0017, "step": 278780 }, { "epoch": 66.92, "learning_rate": 2.9125707786126732e-05, "loss": 0.002, "step": 278790 }, { "epoch": 66.92, "learning_rate": 2.912244605612749e-05, "loss": 0.0024, "step": 278800 }, { "epoch": 66.93, "learning_rate": 2.9119184433731363e-05, "loss": 0.0025, "step": 278810 }, { "epoch": 66.93, "learning_rate": 2.91159229189551e-05, "loss": 0.0018, "step": 278820 }, { "epoch": 66.93, "learning_rate": 2.9112661511815576e-05, "loss": 0.002, "step": 278830 }, { "epoch": 66.93, "learning_rate": 2.9109400212329546e-05, "loss": 0.0017, "step": 278840 }, { "epoch": 66.94, "learning_rate": 2.9106139020513863e-05, "loss": 0.0018, "step": 278850 }, { "epoch": 66.94, "learning_rate": 2.9102877936385293e-05, "loss": 0.0034, "step": 278860 }, { "epoch": 66.94, "learning_rate": 2.9099616959960686e-05, "loss": 0.0021, "step": 278870 }, { "epoch": 66.94, "learning_rate": 2.9096356091256803e-05, "loss": 0.0015, "step": 278880 }, { "epoch": 66.94, "learning_rate": 2.90930953302905e-05, "loss": 0.002, "step": 278890 }, { "epoch": 66.95, "learning_rate": 2.9089834677078558e-05, "loss": 0.0016, "step": 278900 }, { "epoch": 66.95, "learning_rate": 2.9086574131637766e-05, "loss": 0.0025, "step": 278910 }, { "epoch": 66.95, "learning_rate": 2.9083313693984958e-05, "loss": 0.002, "step": 278920 }, { "epoch": 67.0, "learning_rate": 2.9080053364136917e-05, "loss": 0.0018, "step": 278930 }, { "epoch": 67.0, "learning_rate": 2.9076793142110465e-05, "loss": 0.0016, "step": 278940 }, { "epoch": 67.01, "learning_rate": 2.9073533027922382e-05, "loss": 0.0036, "step": 278950 }, { "epoch": 67.01, "learning_rate": 2.90702730215895e-05, "loss": 0.002, "step": 278960 }, { "epoch": 67.01, "learning_rate": 2.9067013123128613e-05, "loss": 0.0021, "step": 278970 }, { "epoch": 67.01, "learning_rate": 2.9063753332556488e-05, "loss": 0.0031, "step": 278980 }, { "epoch": 67.02, "learning_rate": 2.9060493649889974e-05, "loss": 0.0018, "step": 278990 }, { "epoch": 67.02, "learning_rate": 2.9057234075145832e-05, "loss": 0.002, "step": 279000 }, { "epoch": 67.02, "learning_rate": 2.9053974608340905e-05, "loss": 0.0026, "step": 279010 }, { "epoch": 67.02, "learning_rate": 2.9050715249491946e-05, "loss": 0.0016, "step": 279020 }, { "epoch": 67.02, "learning_rate": 2.904745599861579e-05, "loss": 0.0022, "step": 279030 }, { "epoch": 67.03, "learning_rate": 2.9044196855729232e-05, "loss": 0.0015, "step": 279040 }, { "epoch": 67.03, "learning_rate": 2.904093782084903e-05, "loss": 0.0051, "step": 279050 }, { "epoch": 67.03, "learning_rate": 2.903767889399203e-05, "loss": 0.0018, "step": 279060 }, { "epoch": 67.03, "learning_rate": 2.9034420075174996e-05, "loss": 0.0016, "step": 279070 }, { "epoch": 67.04, "learning_rate": 2.903116136441475e-05, "loss": 0.0016, "step": 279080 }, { "epoch": 67.04, "learning_rate": 2.9027902761728048e-05, "loss": 0.007, "step": 279090 }, { "epoch": 67.04, "learning_rate": 2.902464426713172e-05, "loss": 0.0025, "step": 279100 }, { "epoch": 67.04, "learning_rate": 2.9021385880642566e-05, "loss": 0.0066, "step": 279110 }, { "epoch": 67.05, "learning_rate": 2.9018127602277346e-05, "loss": 0.0017, "step": 279120 }, { "epoch": 67.05, "learning_rate": 2.901486943205289e-05, "loss": 0.0017, "step": 279130 }, { "epoch": 67.05, "learning_rate": 2.901161136998595e-05, "loss": 0.002, "step": 279140 }, { "epoch": 67.05, "learning_rate": 2.900835341609337e-05, "loss": 0.002, "step": 279150 }, { "epoch": 67.05, "learning_rate": 2.9005095570391882e-05, "loss": 0.0027, "step": 279160 }, { "epoch": 67.06, "learning_rate": 2.900183783289833e-05, "loss": 0.0017, "step": 279170 }, { "epoch": 67.06, "learning_rate": 2.8998580203629484e-05, "loss": 0.0021, "step": 279180 }, { "epoch": 67.06, "learning_rate": 2.899532268260211e-05, "loss": 0.0022, "step": 279190 }, { "epoch": 67.06, "learning_rate": 2.8992065269833036e-05, "loss": 0.0018, "step": 279200 }, { "epoch": 67.07, "learning_rate": 2.8988807965339017e-05, "loss": 0.0025, "step": 279210 }, { "epoch": 67.07, "learning_rate": 2.8985550769136872e-05, "loss": 0.0027, "step": 279220 }, { "epoch": 67.07, "learning_rate": 2.8982293681243354e-05, "loss": 0.0025, "step": 279230 }, { "epoch": 67.07, "learning_rate": 2.89790367016753e-05, "loss": 0.002, "step": 279240 }, { "epoch": 67.08, "learning_rate": 2.8975779830449456e-05, "loss": 0.0016, "step": 279250 }, { "epoch": 67.08, "learning_rate": 2.89725230675826e-05, "loss": 0.0019, "step": 279260 }, { "epoch": 67.08, "learning_rate": 2.8969266413091566e-05, "loss": 0.002, "step": 279270 }, { "epoch": 67.08, "learning_rate": 2.8966009866993084e-05, "loss": 0.0017, "step": 279280 }, { "epoch": 67.08, "learning_rate": 2.8962753429303973e-05, "loss": 0.0018, "step": 279290 }, { "epoch": 67.09, "learning_rate": 2.8959497100040996e-05, "loss": 0.0021, "step": 279300 }, { "epoch": 67.09, "learning_rate": 2.8956240879220963e-05, "loss": 0.0016, "step": 279310 }, { "epoch": 67.09, "learning_rate": 2.895298476686064e-05, "loss": 0.0017, "step": 279320 }, { "epoch": 67.09, "learning_rate": 2.894972876297679e-05, "loss": 0.0017, "step": 279330 }, { "epoch": 67.1, "learning_rate": 2.8946472867586237e-05, "loss": 0.002, "step": 279340 }, { "epoch": 67.1, "learning_rate": 2.894321708070572e-05, "loss": 0.0024, "step": 279350 }, { "epoch": 67.1, "learning_rate": 2.8939961402352055e-05, "loss": 0.0015, "step": 279360 }, { "epoch": 67.1, "learning_rate": 2.893670583254199e-05, "loss": 0.0023, "step": 279370 }, { "epoch": 67.1, "learning_rate": 2.8933450371292325e-05, "loss": 0.0026, "step": 279380 }, { "epoch": 67.11, "learning_rate": 2.8930195018619826e-05, "loss": 0.0018, "step": 279390 }, { "epoch": 67.11, "learning_rate": 2.892693977454127e-05, "loss": 0.0024, "step": 279400 }, { "epoch": 67.11, "learning_rate": 2.892368463907347e-05, "loss": 0.0023, "step": 279410 }, { "epoch": 67.11, "learning_rate": 2.892042961223316e-05, "loss": 0.0019, "step": 279420 }, { "epoch": 67.12, "learning_rate": 2.891717469403714e-05, "loss": 0.0023, "step": 279430 }, { "epoch": 67.12, "learning_rate": 2.891391988450216e-05, "loss": 0.0029, "step": 279440 }, { "epoch": 67.12, "learning_rate": 2.8910665183645036e-05, "loss": 0.0017, "step": 279450 }, { "epoch": 67.12, "learning_rate": 2.890741059148252e-05, "loss": 0.0023, "step": 279460 }, { "epoch": 67.13, "learning_rate": 2.8904156108031365e-05, "loss": 0.0019, "step": 279470 }, { "epoch": 67.13, "learning_rate": 2.8900901733308382e-05, "loss": 0.0018, "step": 279480 }, { "epoch": 67.13, "learning_rate": 2.8897647467330314e-05, "loss": 0.0017, "step": 279490 }, { "epoch": 67.13, "learning_rate": 2.8894393310113964e-05, "loss": 0.0019, "step": 279500 }, { "epoch": 67.13, "learning_rate": 2.889113926167607e-05, "loss": 0.0018, "step": 279510 }, { "epoch": 67.14, "learning_rate": 2.8887885322033437e-05, "loss": 0.0017, "step": 279520 }, { "epoch": 67.14, "learning_rate": 2.888463149120283e-05, "loss": 0.002, "step": 279530 }, { "epoch": 67.14, "learning_rate": 2.888137776920098e-05, "loss": 0.002, "step": 279540 }, { "epoch": 67.14, "learning_rate": 2.8878124156044705e-05, "loss": 0.002, "step": 279550 }, { "epoch": 67.15, "learning_rate": 2.887487065175073e-05, "loss": 0.0016, "step": 279560 }, { "epoch": 67.15, "learning_rate": 2.8871617256335876e-05, "loss": 0.0026, "step": 279570 }, { "epoch": 67.15, "learning_rate": 2.886836396981686e-05, "loss": 0.0018, "step": 279580 }, { "epoch": 67.15, "learning_rate": 2.886511079221049e-05, "loss": 0.0024, "step": 279590 }, { "epoch": 67.16, "learning_rate": 2.8861857723533502e-05, "loss": 0.0017, "step": 279600 }, { "epoch": 67.16, "learning_rate": 2.88586047638027e-05, "loss": 0.0018, "step": 279610 }, { "epoch": 67.16, "learning_rate": 2.8855351913034816e-05, "loss": 0.0016, "step": 279620 }, { "epoch": 67.16, "learning_rate": 2.8852099171246604e-05, "loss": 0.0016, "step": 279630 }, { "epoch": 67.16, "learning_rate": 2.8848846538454877e-05, "loss": 0.0037, "step": 279640 }, { "epoch": 67.17, "learning_rate": 2.8845594014676347e-05, "loss": 0.0026, "step": 279650 }, { "epoch": 67.17, "learning_rate": 2.8842341599927824e-05, "loss": 0.0034, "step": 279660 }, { "epoch": 67.17, "learning_rate": 2.8839089294226028e-05, "loss": 0.0018, "step": 279670 }, { "epoch": 67.17, "learning_rate": 2.883583709758777e-05, "loss": 0.0021, "step": 279680 }, { "epoch": 67.18, "learning_rate": 2.8832585010029756e-05, "loss": 0.0027, "step": 279690 }, { "epoch": 67.18, "learning_rate": 2.88293330315688e-05, "loss": 0.0017, "step": 279700 }, { "epoch": 67.18, "learning_rate": 2.882608116222162e-05, "loss": 0.0021, "step": 279710 }, { "epoch": 67.18, "learning_rate": 2.882282940200499e-05, "loss": 0.002, "step": 279720 }, { "epoch": 67.18, "learning_rate": 2.8819577750935695e-05, "loss": 0.002, "step": 279730 }, { "epoch": 67.19, "learning_rate": 2.8816326209030454e-05, "loss": 0.0018, "step": 279740 }, { "epoch": 67.19, "learning_rate": 2.8813074776306058e-05, "loss": 0.0026, "step": 279750 }, { "epoch": 67.19, "learning_rate": 2.8809823452779262e-05, "loss": 0.002, "step": 279760 }, { "epoch": 67.19, "learning_rate": 2.8806572238466788e-05, "loss": 0.0018, "step": 279770 }, { "epoch": 67.2, "learning_rate": 2.8803321133385443e-05, "loss": 0.0018, "step": 279780 }, { "epoch": 67.2, "learning_rate": 2.8800070137551937e-05, "loss": 0.002, "step": 279790 }, { "epoch": 67.2, "learning_rate": 2.8796819250983066e-05, "loss": 0.0017, "step": 279800 }, { "epoch": 67.2, "learning_rate": 2.8793568473695543e-05, "loss": 0.0017, "step": 279810 }, { "epoch": 67.21, "learning_rate": 2.8790317805706163e-05, "loss": 0.002, "step": 279820 }, { "epoch": 67.21, "learning_rate": 2.8787067247031664e-05, "loss": 0.0019, "step": 279830 }, { "epoch": 67.21, "learning_rate": 2.878381679768878e-05, "loss": 0.0018, "step": 279840 }, { "epoch": 67.21, "learning_rate": 2.87805664576943e-05, "loss": 0.0016, "step": 279850 }, { "epoch": 67.21, "learning_rate": 2.8777316227064942e-05, "loss": 0.0015, "step": 279860 }, { "epoch": 67.22, "learning_rate": 2.8774066105817488e-05, "loss": 0.0016, "step": 279870 }, { "epoch": 67.22, "learning_rate": 2.8770816093968656e-05, "loss": 0.0024, "step": 279880 }, { "epoch": 67.22, "learning_rate": 2.8767566191535233e-05, "loss": 0.0018, "step": 279890 }, { "epoch": 67.22, "learning_rate": 2.8764316398533957e-05, "loss": 0.0016, "step": 279900 }, { "epoch": 67.23, "learning_rate": 2.8761066714981556e-05, "loss": 0.0017, "step": 279910 }, { "epoch": 67.23, "learning_rate": 2.8757817140894804e-05, "loss": 0.0014, "step": 279920 }, { "epoch": 67.23, "learning_rate": 2.875456767629042e-05, "loss": 0.002, "step": 279930 }, { "epoch": 67.23, "learning_rate": 2.87513183211852e-05, "loss": 0.0041, "step": 279940 }, { "epoch": 67.24, "learning_rate": 2.874806907559584e-05, "loss": 0.0019, "step": 279950 }, { "epoch": 67.24, "learning_rate": 2.8744819939539125e-05, "loss": 0.0017, "step": 279960 }, { "epoch": 67.24, "learning_rate": 2.8741570913031766e-05, "loss": 0.0016, "step": 279970 }, { "epoch": 67.24, "learning_rate": 2.8738321996090556e-05, "loss": 0.0016, "step": 279980 }, { "epoch": 67.24, "learning_rate": 2.8735073188732186e-05, "loss": 0.0017, "step": 279990 }, { "epoch": 67.25, "learning_rate": 2.8731824490973446e-05, "loss": 0.0033, "step": 280000 }, { "epoch": 67.25, "learning_rate": 2.8728575902831046e-05, "loss": 0.0016, "step": 280010 }, { "epoch": 67.25, "learning_rate": 2.8725327424321756e-05, "loss": 0.0021, "step": 280020 }, { "epoch": 67.25, "learning_rate": 2.872207905546229e-05, "loss": 0.0017, "step": 280030 }, { "epoch": 67.26, "learning_rate": 2.8718830796269435e-05, "loss": 0.0039, "step": 280040 }, { "epoch": 67.26, "learning_rate": 2.8715582646759875e-05, "loss": 0.0019, "step": 280050 }, { "epoch": 67.26, "learning_rate": 2.87123346069504e-05, "loss": 0.0018, "step": 280060 }, { "epoch": 67.26, "learning_rate": 2.870908667685771e-05, "loss": 0.0015, "step": 280070 }, { "epoch": 67.26, "learning_rate": 2.8705838856498584e-05, "loss": 0.0024, "step": 280080 }, { "epoch": 67.27, "learning_rate": 2.8702591145889723e-05, "loss": 0.0019, "step": 280090 }, { "epoch": 67.27, "learning_rate": 2.8699343545047906e-05, "loss": 0.0019, "step": 280100 }, { "epoch": 67.27, "learning_rate": 2.8696096053989853e-05, "loss": 0.0029, "step": 280110 }, { "epoch": 67.27, "learning_rate": 2.869284867273228e-05, "loss": 0.0018, "step": 280120 }, { "epoch": 67.28, "learning_rate": 2.868960140129196e-05, "loss": 0.0016, "step": 280130 }, { "epoch": 67.28, "learning_rate": 2.8686354239685592e-05, "loss": 0.0016, "step": 280140 }, { "epoch": 67.28, "learning_rate": 2.868310718792996e-05, "loss": 0.002, "step": 280150 }, { "epoch": 67.28, "learning_rate": 2.867986024604174e-05, "loss": 0.0016, "step": 280160 }, { "epoch": 67.29, "learning_rate": 2.8676613414037722e-05, "loss": 0.0018, "step": 280170 }, { "epoch": 67.29, "learning_rate": 2.867336669193462e-05, "loss": 0.0018, "step": 280180 }, { "epoch": 67.29, "learning_rate": 2.867012007974914e-05, "loss": 0.0014, "step": 280190 }, { "epoch": 67.29, "learning_rate": 2.8666873577498066e-05, "loss": 0.0018, "step": 280200 }, { "epoch": 67.29, "learning_rate": 2.8663627185198077e-05, "loss": 0.0017, "step": 280210 }, { "epoch": 67.3, "learning_rate": 2.8660380902865957e-05, "loss": 0.0016, "step": 280220 }, { "epoch": 67.3, "learning_rate": 2.865713473051839e-05, "loss": 0.0021, "step": 280230 }, { "epoch": 67.3, "learning_rate": 2.8653888668172146e-05, "loss": 0.0016, "step": 280240 }, { "epoch": 67.3, "learning_rate": 2.8650642715843944e-05, "loss": 0.0074, "step": 280250 }, { "epoch": 67.31, "learning_rate": 2.8647396873550485e-05, "loss": 0.0018, "step": 280260 }, { "epoch": 67.31, "learning_rate": 2.864415114130854e-05, "loss": 0.0025, "step": 280270 }, { "epoch": 67.31, "learning_rate": 2.8640905519134797e-05, "loss": 0.0021, "step": 280280 }, { "epoch": 67.31, "learning_rate": 2.8637660007046012e-05, "loss": 0.0019, "step": 280290 }, { "epoch": 67.32, "learning_rate": 2.8634414605058924e-05, "loss": 0.0016, "step": 280300 }, { "epoch": 67.32, "learning_rate": 2.8631169313190222e-05, "loss": 0.0016, "step": 280310 }, { "epoch": 67.32, "learning_rate": 2.8627924131456664e-05, "loss": 0.0016, "step": 280320 }, { "epoch": 67.32, "learning_rate": 2.862467905987495e-05, "loss": 0.0017, "step": 280330 }, { "epoch": 67.32, "learning_rate": 2.862143409846184e-05, "loss": 0.0027, "step": 280340 }, { "epoch": 67.33, "learning_rate": 2.8618189247234016e-05, "loss": 0.0015, "step": 280350 }, { "epoch": 67.33, "learning_rate": 2.861494450620824e-05, "loss": 0.0018, "step": 280360 }, { "epoch": 67.33, "learning_rate": 2.86116998754012e-05, "loss": 0.002, "step": 280370 }, { "epoch": 67.33, "learning_rate": 2.8608455354829666e-05, "loss": 0.0022, "step": 280380 }, { "epoch": 67.34, "learning_rate": 2.86052109445103e-05, "loss": 0.002, "step": 280390 }, { "epoch": 67.34, "learning_rate": 2.8601966644459883e-05, "loss": 0.002, "step": 280400 }, { "epoch": 67.34, "learning_rate": 2.8598722454695104e-05, "loss": 0.0016, "step": 280410 }, { "epoch": 67.34, "learning_rate": 2.8595478375232676e-05, "loss": 0.0017, "step": 280420 }, { "epoch": 67.34, "learning_rate": 2.8592234406089347e-05, "loss": 0.0014, "step": 280430 }, { "epoch": 67.35, "learning_rate": 2.8588990547281797e-05, "loss": 0.0015, "step": 280440 }, { "epoch": 67.35, "learning_rate": 2.858574679882679e-05, "loss": 0.0016, "step": 280450 }, { "epoch": 67.35, "learning_rate": 2.8582503160741003e-05, "loss": 0.0016, "step": 280460 }, { "epoch": 67.35, "learning_rate": 2.85792596330412e-05, "loss": 0.0016, "step": 280470 }, { "epoch": 67.36, "learning_rate": 2.8576016215744068e-05, "loss": 0.0019, "step": 280480 }, { "epoch": 67.36, "learning_rate": 2.8572772908866307e-05, "loss": 0.0017, "step": 280490 }, { "epoch": 67.36, "learning_rate": 2.856952971242467e-05, "loss": 0.0017, "step": 280500 }, { "epoch": 67.36, "learning_rate": 2.856628662643584e-05, "loss": 0.0019, "step": 280510 }, { "epoch": 67.37, "learning_rate": 2.8563043650916565e-05, "loss": 0.0027, "step": 280520 }, { "epoch": 67.37, "learning_rate": 2.855980078588353e-05, "loss": 0.0055, "step": 280530 }, { "epoch": 67.37, "learning_rate": 2.8556558031353476e-05, "loss": 0.0015, "step": 280540 }, { "epoch": 67.37, "learning_rate": 2.85533153873431e-05, "loss": 0.0024, "step": 280550 }, { "epoch": 67.37, "learning_rate": 2.8550072853869092e-05, "loss": 0.0025, "step": 280560 }, { "epoch": 67.38, "learning_rate": 2.8546830430948213e-05, "loss": 0.0021, "step": 280570 }, { "epoch": 67.38, "learning_rate": 2.854358811859713e-05, "loss": 0.0023, "step": 280580 }, { "epoch": 67.38, "learning_rate": 2.854034591683259e-05, "loss": 0.0021, "step": 280590 }, { "epoch": 67.38, "learning_rate": 2.8537103825671267e-05, "loss": 0.0019, "step": 280600 }, { "epoch": 67.39, "learning_rate": 2.8533861845129896e-05, "loss": 0.0018, "step": 280610 }, { "epoch": 67.39, "learning_rate": 2.8530619975225193e-05, "loss": 0.0024, "step": 280620 }, { "epoch": 67.39, "learning_rate": 2.852737821597384e-05, "loss": 0.0059, "step": 280630 }, { "epoch": 67.39, "learning_rate": 2.8524136567392577e-05, "loss": 0.0019, "step": 280640 }, { "epoch": 67.4, "learning_rate": 2.8520895029498074e-05, "loss": 0.0018, "step": 280650 }, { "epoch": 67.4, "learning_rate": 2.851765360230707e-05, "loss": 0.0022, "step": 280660 }, { "epoch": 67.4, "learning_rate": 2.8514412285836244e-05, "loss": 0.0016, "step": 280670 }, { "epoch": 67.4, "learning_rate": 2.851117108010234e-05, "loss": 0.002, "step": 280680 }, { "epoch": 67.4, "learning_rate": 2.850792998512204e-05, "loss": 0.0024, "step": 280690 }, { "epoch": 67.41, "learning_rate": 2.8504689000912026e-05, "loss": 0.0017, "step": 280700 }, { "epoch": 67.41, "learning_rate": 2.8501448127489046e-05, "loss": 0.002, "step": 280710 }, { "epoch": 67.41, "learning_rate": 2.8498207364869762e-05, "loss": 0.0014, "step": 280720 }, { "epoch": 67.41, "learning_rate": 2.8494966713070913e-05, "loss": 0.0017, "step": 280730 }, { "epoch": 67.42, "learning_rate": 2.8491726172109168e-05, "loss": 0.0022, "step": 280740 }, { "epoch": 67.42, "learning_rate": 2.848848574200127e-05, "loss": 0.0016, "step": 280750 }, { "epoch": 67.42, "learning_rate": 2.848524542276389e-05, "loss": 0.0037, "step": 280760 }, { "epoch": 67.42, "learning_rate": 2.8482005214413722e-05, "loss": 0.0026, "step": 280770 }, { "epoch": 67.42, "learning_rate": 2.8478765116967488e-05, "loss": 0.0018, "step": 280780 }, { "epoch": 67.43, "learning_rate": 2.847552513044187e-05, "loss": 0.0018, "step": 280790 }, { "epoch": 67.43, "learning_rate": 2.8472285254853593e-05, "loss": 0.0018, "step": 280800 }, { "epoch": 67.43, "learning_rate": 2.8469045490219316e-05, "loss": 0.0019, "step": 280810 }, { "epoch": 67.43, "learning_rate": 2.846580583655577e-05, "loss": 0.0025, "step": 280820 }, { "epoch": 67.44, "learning_rate": 2.846256629387965e-05, "loss": 0.0019, "step": 280830 }, { "epoch": 67.44, "learning_rate": 2.8459326862207625e-05, "loss": 0.0021, "step": 280840 }, { "epoch": 67.44, "learning_rate": 2.8456087541556418e-05, "loss": 0.0017, "step": 280850 }, { "epoch": 67.44, "learning_rate": 2.845284833194271e-05, "loss": 0.0017, "step": 280860 }, { "epoch": 67.45, "learning_rate": 2.8449609233383212e-05, "loss": 0.0019, "step": 280870 }, { "epoch": 67.45, "learning_rate": 2.8446370245894593e-05, "loss": 0.0029, "step": 280880 }, { "epoch": 67.45, "learning_rate": 2.844313136949358e-05, "loss": 0.0016, "step": 280890 }, { "epoch": 67.45, "learning_rate": 2.8439892604196834e-05, "loss": 0.0025, "step": 280900 }, { "epoch": 67.45, "learning_rate": 2.8436653950021074e-05, "loss": 0.0033, "step": 280910 }, { "epoch": 67.46, "learning_rate": 2.8433415406982965e-05, "loss": 0.0037, "step": 280920 }, { "epoch": 67.46, "learning_rate": 2.843017697509921e-05, "loss": 0.004, "step": 280930 }, { "epoch": 67.46, "learning_rate": 2.8426938654386526e-05, "loss": 0.0014, "step": 280940 }, { "epoch": 67.46, "learning_rate": 2.8423700444861555e-05, "loss": 0.0023, "step": 280950 }, { "epoch": 67.47, "learning_rate": 2.842046234654104e-05, "loss": 0.0022, "step": 280960 }, { "epoch": 67.47, "learning_rate": 2.8417224359441635e-05, "loss": 0.0017, "step": 280970 }, { "epoch": 67.47, "learning_rate": 2.8413986483580018e-05, "loss": 0.0015, "step": 280980 }, { "epoch": 67.47, "learning_rate": 2.841074871897292e-05, "loss": 0.0016, "step": 280990 }, { "epoch": 67.48, "learning_rate": 2.8407511065636978e-05, "loss": 0.0028, "step": 281000 }, { "epoch": 67.48, "learning_rate": 2.8404273523588925e-05, "loss": 0.0018, "step": 281010 }, { "epoch": 67.48, "learning_rate": 2.8401036092845412e-05, "loss": 0.0046, "step": 281020 }, { "epoch": 67.48, "learning_rate": 2.8397798773423157e-05, "loss": 0.0022, "step": 281030 }, { "epoch": 67.48, "learning_rate": 2.8394561565338823e-05, "loss": 0.0018, "step": 281040 }, { "epoch": 67.49, "learning_rate": 2.8391324468609082e-05, "loss": 0.0023, "step": 281050 }, { "epoch": 67.49, "learning_rate": 2.8388087483250658e-05, "loss": 0.0017, "step": 281060 }, { "epoch": 67.49, "learning_rate": 2.838485060928019e-05, "loss": 0.0029, "step": 281070 }, { "epoch": 67.49, "learning_rate": 2.83816138467144e-05, "loss": 0.0025, "step": 281080 }, { "epoch": 67.5, "learning_rate": 2.837837719556994e-05, "loss": 0.002, "step": 281090 }, { "epoch": 67.5, "learning_rate": 2.8375140655863518e-05, "loss": 0.0037, "step": 281100 }, { "epoch": 67.5, "learning_rate": 2.83719042276118e-05, "loss": 0.0015, "step": 281110 }, { "epoch": 67.5, "learning_rate": 2.8368667910831453e-05, "loss": 0.0024, "step": 281120 }, { "epoch": 67.5, "learning_rate": 2.8365431705539193e-05, "loss": 0.002, "step": 281130 }, { "epoch": 67.51, "learning_rate": 2.836219561175165e-05, "loss": 0.0017, "step": 281140 }, { "epoch": 67.51, "learning_rate": 2.8358959629485564e-05, "loss": 0.0028, "step": 281150 }, { "epoch": 67.51, "learning_rate": 2.835572375875756e-05, "loss": 0.0018, "step": 281160 }, { "epoch": 67.51, "learning_rate": 2.8352487999584348e-05, "loss": 0.005, "step": 281170 }, { "epoch": 67.52, "learning_rate": 2.834925235198258e-05, "loss": 0.0016, "step": 281180 }, { "epoch": 67.52, "learning_rate": 2.834601681596897e-05, "loss": 0.0019, "step": 281190 }, { "epoch": 67.52, "learning_rate": 2.834278139156014e-05, "loss": 0.0021, "step": 281200 }, { "epoch": 67.52, "learning_rate": 2.8339546078772822e-05, "loss": 0.0015, "step": 281210 }, { "epoch": 67.53, "learning_rate": 2.833631087762364e-05, "loss": 0.0026, "step": 281220 }, { "epoch": 67.53, "learning_rate": 2.83330757881293e-05, "loss": 0.0017, "step": 281230 }, { "epoch": 67.53, "learning_rate": 2.8329840810306483e-05, "loss": 0.0043, "step": 281240 }, { "epoch": 67.53, "learning_rate": 2.832660594417183e-05, "loss": 0.0016, "step": 281250 }, { "epoch": 67.53, "learning_rate": 2.8323371189742053e-05, "loss": 0.0027, "step": 281260 }, { "epoch": 67.54, "learning_rate": 2.8320136547033795e-05, "loss": 0.0022, "step": 281270 }, { "epoch": 67.54, "learning_rate": 2.8316902016063718e-05, "loss": 0.0028, "step": 281280 }, { "epoch": 67.54, "learning_rate": 2.8313667596848535e-05, "loss": 0.0023, "step": 281290 }, { "epoch": 67.54, "learning_rate": 2.8310433289404866e-05, "loss": 0.0024, "step": 281300 }, { "epoch": 67.55, "learning_rate": 2.8307199093749427e-05, "loss": 0.0022, "step": 281310 }, { "epoch": 67.55, "learning_rate": 2.8303965009898837e-05, "loss": 0.0123, "step": 281320 }, { "epoch": 67.55, "learning_rate": 2.830073103786982e-05, "loss": 0.0029, "step": 281330 }, { "epoch": 67.55, "learning_rate": 2.8297497177679018e-05, "loss": 0.0032, "step": 281340 }, { "epoch": 67.56, "learning_rate": 2.829426342934307e-05, "loss": 0.0023, "step": 281350 }, { "epoch": 67.56, "learning_rate": 2.82910297928787e-05, "loss": 0.002, "step": 281360 }, { "epoch": 67.56, "learning_rate": 2.8287796268302514e-05, "loss": 0.0023, "step": 281370 }, { "epoch": 67.56, "learning_rate": 2.828456285563123e-05, "loss": 0.0016, "step": 281380 }, { "epoch": 67.56, "learning_rate": 2.8281329554881474e-05, "loss": 0.0022, "step": 281390 }, { "epoch": 67.57, "learning_rate": 2.8278096366069946e-05, "loss": 0.0048, "step": 281400 }, { "epoch": 67.57, "learning_rate": 2.827486328921329e-05, "loss": 0.002, "step": 281410 }, { "epoch": 67.57, "learning_rate": 2.8271630324328147e-05, "loss": 0.0022, "step": 281420 }, { "epoch": 67.57, "learning_rate": 2.826839747143123e-05, "loss": 0.0024, "step": 281430 }, { "epoch": 67.58, "learning_rate": 2.826516473053915e-05, "loss": 0.0025, "step": 281440 }, { "epoch": 67.58, "learning_rate": 2.8261932101668608e-05, "loss": 0.0022, "step": 281450 }, { "epoch": 67.58, "learning_rate": 2.8258699584836234e-05, "loss": 0.0023, "step": 281460 }, { "epoch": 67.58, "learning_rate": 2.8255467180058727e-05, "loss": 0.0019, "step": 281470 }, { "epoch": 67.58, "learning_rate": 2.8252234887352725e-05, "loss": 0.0021, "step": 281480 }, { "epoch": 67.59, "learning_rate": 2.824900270673486e-05, "loss": 0.002, "step": 281490 }, { "epoch": 67.59, "learning_rate": 2.824577063822182e-05, "loss": 0.0021, "step": 281500 }, { "epoch": 67.59, "learning_rate": 2.8242538681830277e-05, "loss": 0.0028, "step": 281510 }, { "epoch": 67.59, "learning_rate": 2.8239306837576857e-05, "loss": 0.0027, "step": 281520 }, { "epoch": 67.6, "learning_rate": 2.8236075105478242e-05, "loss": 0.0018, "step": 281530 }, { "epoch": 67.6, "learning_rate": 2.823284348555107e-05, "loss": 0.0019, "step": 281540 }, { "epoch": 67.6, "learning_rate": 2.822961197781202e-05, "loss": 0.0023, "step": 281550 }, { "epoch": 67.6, "learning_rate": 2.8226380582277712e-05, "loss": 0.0021, "step": 281560 }, { "epoch": 67.61, "learning_rate": 2.8223149298964834e-05, "loss": 0.0019, "step": 281570 }, { "epoch": 67.61, "learning_rate": 2.821991812789001e-05, "loss": 0.0019, "step": 281580 }, { "epoch": 67.61, "learning_rate": 2.8216687069069934e-05, "loss": 0.0017, "step": 281590 }, { "epoch": 67.61, "learning_rate": 2.8213456122521215e-05, "loss": 0.003, "step": 281600 }, { "epoch": 67.61, "learning_rate": 2.821022528826054e-05, "loss": 0.003, "step": 281610 }, { "epoch": 67.62, "learning_rate": 2.820699456630455e-05, "loss": 0.0027, "step": 281620 }, { "epoch": 67.62, "learning_rate": 2.820376395666987e-05, "loss": 0.0017, "step": 281630 }, { "epoch": 67.62, "learning_rate": 2.8200533459373197e-05, "loss": 0.0018, "step": 281640 }, { "epoch": 67.62, "learning_rate": 2.819730307443113e-05, "loss": 0.002, "step": 281650 }, { "epoch": 67.63, "learning_rate": 2.819407280186037e-05, "loss": 0.0017, "step": 281660 }, { "epoch": 67.63, "learning_rate": 2.8190842641677517e-05, "loss": 0.0018, "step": 281670 }, { "epoch": 67.63, "learning_rate": 2.8187612593899272e-05, "loss": 0.0019, "step": 281680 }, { "epoch": 67.63, "learning_rate": 2.8184382658542246e-05, "loss": 0.0019, "step": 281690 }, { "epoch": 67.64, "learning_rate": 2.8181152835623077e-05, "loss": 0.0021, "step": 281700 }, { "epoch": 67.64, "learning_rate": 2.8177923125158445e-05, "loss": 0.0021, "step": 281710 }, { "epoch": 67.64, "learning_rate": 2.8174693527164965e-05, "loss": 0.0021, "step": 281720 }, { "epoch": 67.64, "learning_rate": 2.817146404165931e-05, "loss": 0.0019, "step": 281730 }, { "epoch": 67.64, "learning_rate": 2.81682346686581e-05, "loss": 0.0021, "step": 281740 }, { "epoch": 67.65, "learning_rate": 2.8165005408178007e-05, "loss": 0.0018, "step": 281750 }, { "epoch": 67.65, "learning_rate": 2.816177626023566e-05, "loss": 0.0026, "step": 281760 }, { "epoch": 67.65, "learning_rate": 2.8158547224847674e-05, "loss": 0.0019, "step": 281770 }, { "epoch": 67.65, "learning_rate": 2.8155318302030753e-05, "loss": 0.0072, "step": 281780 }, { "epoch": 67.66, "learning_rate": 2.815208949180147e-05, "loss": 0.002, "step": 281790 }, { "epoch": 67.66, "learning_rate": 2.8148860794176507e-05, "loss": 0.0029, "step": 281800 }, { "epoch": 67.66, "learning_rate": 2.814563220917251e-05, "loss": 0.0022, "step": 281810 }, { "epoch": 67.66, "learning_rate": 2.81424037368061e-05, "loss": 0.002, "step": 281820 }, { "epoch": 67.66, "learning_rate": 2.813917537709394e-05, "loss": 0.0019, "step": 281830 }, { "epoch": 67.67, "learning_rate": 2.813594713005263e-05, "loss": 0.0025, "step": 281840 }, { "epoch": 67.67, "learning_rate": 2.813271899569885e-05, "loss": 0.0016, "step": 281850 }, { "epoch": 67.67, "learning_rate": 2.81294909740492e-05, "loss": 0.0018, "step": 281860 }, { "epoch": 67.67, "learning_rate": 2.8126263065120355e-05, "loss": 0.0017, "step": 281870 }, { "epoch": 67.68, "learning_rate": 2.8123035268928923e-05, "loss": 0.0018, "step": 281880 }, { "epoch": 67.68, "learning_rate": 2.8119807585491552e-05, "loss": 0.0017, "step": 281890 }, { "epoch": 67.68, "learning_rate": 2.811658001482489e-05, "loss": 0.0015, "step": 281900 }, { "epoch": 67.68, "learning_rate": 2.811335255694553e-05, "loss": 0.0018, "step": 281910 }, { "epoch": 67.69, "learning_rate": 2.8110125211870163e-05, "loss": 0.002, "step": 281920 }, { "epoch": 67.69, "learning_rate": 2.8106897979615364e-05, "loss": 0.0021, "step": 281930 }, { "epoch": 67.69, "learning_rate": 2.8103670860197816e-05, "loss": 0.0018, "step": 281940 }, { "epoch": 67.69, "learning_rate": 2.8100443853634116e-05, "loss": 0.0021, "step": 281950 }, { "epoch": 67.69, "learning_rate": 2.809721695994093e-05, "loss": 0.002, "step": 281960 }, { "epoch": 67.7, "learning_rate": 2.8093990179134856e-05, "loss": 0.0024, "step": 281970 }, { "epoch": 67.7, "learning_rate": 2.8090763511232554e-05, "loss": 0.0253, "step": 281980 }, { "epoch": 67.7, "learning_rate": 2.8087536956250636e-05, "loss": 0.0019, "step": 281990 }, { "epoch": 67.7, "learning_rate": 2.8084310514205725e-05, "loss": 0.0019, "step": 282000 }, { "epoch": 67.71, "learning_rate": 2.8081084185114474e-05, "loss": 0.0019, "step": 282010 }, { "epoch": 67.71, "learning_rate": 2.807785796899348e-05, "loss": 0.0018, "step": 282020 }, { "epoch": 67.71, "learning_rate": 2.8074631865859412e-05, "loss": 0.0022, "step": 282030 }, { "epoch": 67.71, "learning_rate": 2.8071405875728852e-05, "loss": 0.0065, "step": 282040 }, { "epoch": 67.72, "learning_rate": 2.806817999861847e-05, "loss": 0.0019, "step": 282050 }, { "epoch": 67.72, "learning_rate": 2.806495423454487e-05, "loss": 0.0018, "step": 282060 }, { "epoch": 67.72, "learning_rate": 2.8061728583524666e-05, "loss": 0.002, "step": 282070 }, { "epoch": 67.72, "learning_rate": 2.8058503045574514e-05, "loss": 0.0042, "step": 282080 }, { "epoch": 67.72, "learning_rate": 2.8055277620710995e-05, "loss": 0.0016, "step": 282090 }, { "epoch": 67.73, "learning_rate": 2.8052052308950782e-05, "loss": 0.0017, "step": 282100 }, { "epoch": 67.73, "learning_rate": 2.8048827110310448e-05, "loss": 0.018, "step": 282110 }, { "epoch": 67.73, "learning_rate": 2.804560202480665e-05, "loss": 0.002, "step": 282120 }, { "epoch": 67.73, "learning_rate": 2.8042377052456027e-05, "loss": 0.0024, "step": 282130 }, { "epoch": 67.74, "learning_rate": 2.8039152193275147e-05, "loss": 0.0019, "step": 282140 }, { "epoch": 67.74, "learning_rate": 2.8035927447280685e-05, "loss": 0.0022, "step": 282150 }, { "epoch": 67.74, "learning_rate": 2.803270281448922e-05, "loss": 0.0017, "step": 282160 }, { "epoch": 67.74, "learning_rate": 2.80294782949174e-05, "loss": 0.0016, "step": 282170 }, { "epoch": 67.74, "learning_rate": 2.8026253888581815e-05, "loss": 0.0019, "step": 282180 }, { "epoch": 67.75, "learning_rate": 2.8023029595499123e-05, "loss": 0.0016, "step": 282190 }, { "epoch": 67.75, "learning_rate": 2.8019805415685918e-05, "loss": 0.0027, "step": 282200 }, { "epoch": 67.75, "learning_rate": 2.8016581349158806e-05, "loss": 0.002, "step": 282210 }, { "epoch": 67.75, "learning_rate": 2.8013357395934432e-05, "loss": 0.0018, "step": 282220 }, { "epoch": 67.76, "learning_rate": 2.801013355602938e-05, "loss": 0.002, "step": 282230 }, { "epoch": 67.76, "learning_rate": 2.80069098294603e-05, "loss": 0.0017, "step": 282240 }, { "epoch": 67.76, "learning_rate": 2.8003686216243774e-05, "loss": 0.002, "step": 282250 }, { "epoch": 67.76, "learning_rate": 2.800046271639645e-05, "loss": 0.0029, "step": 282260 }, { "epoch": 67.77, "learning_rate": 2.7997239329934922e-05, "loss": 0.0016, "step": 282270 }, { "epoch": 67.77, "learning_rate": 2.7994016056875793e-05, "loss": 0.002, "step": 282280 }, { "epoch": 67.77, "learning_rate": 2.7990792897235707e-05, "loss": 0.0017, "step": 282290 }, { "epoch": 67.77, "learning_rate": 2.7987569851031236e-05, "loss": 0.0028, "step": 282300 }, { "epoch": 67.77, "learning_rate": 2.7984346918279035e-05, "loss": 0.0019, "step": 282310 }, { "epoch": 67.78, "learning_rate": 2.7981124098995683e-05, "loss": 0.002, "step": 282320 }, { "epoch": 67.78, "learning_rate": 2.7977901393197815e-05, "loss": 0.0017, "step": 282330 }, { "epoch": 67.78, "learning_rate": 2.797467880090202e-05, "loss": 0.0017, "step": 282340 }, { "epoch": 67.78, "learning_rate": 2.79714563221249e-05, "loss": 0.0021, "step": 282350 }, { "epoch": 67.79, "learning_rate": 2.7968233956883106e-05, "loss": 0.0017, "step": 282360 }, { "epoch": 67.79, "learning_rate": 2.7965011705193188e-05, "loss": 0.0033, "step": 282370 }, { "epoch": 67.79, "learning_rate": 2.7961789567071804e-05, "loss": 0.0019, "step": 282380 }, { "epoch": 67.79, "learning_rate": 2.795856754253553e-05, "loss": 0.0017, "step": 282390 }, { "epoch": 67.8, "learning_rate": 2.7955345631600993e-05, "loss": 0.0018, "step": 282400 }, { "epoch": 67.8, "learning_rate": 2.7952123834284772e-05, "loss": 0.0017, "step": 282410 }, { "epoch": 67.8, "learning_rate": 2.7948902150603513e-05, "loss": 0.0016, "step": 282420 }, { "epoch": 67.8, "learning_rate": 2.7945680580573774e-05, "loss": 0.0018, "step": 282430 }, { "epoch": 67.8, "learning_rate": 2.7942459124212184e-05, "loss": 0.0017, "step": 282440 }, { "epoch": 67.81, "learning_rate": 2.793923778153536e-05, "loss": 0.0017, "step": 282450 }, { "epoch": 67.81, "learning_rate": 2.7936016552559868e-05, "loss": 0.0018, "step": 282460 }, { "epoch": 67.81, "learning_rate": 2.7932795437302356e-05, "loss": 0.0019, "step": 282470 }, { "epoch": 67.81, "learning_rate": 2.7929574435779393e-05, "loss": 0.0033, "step": 282480 }, { "epoch": 67.82, "learning_rate": 2.7926353548007578e-05, "loss": 0.0023, "step": 282490 }, { "epoch": 67.82, "learning_rate": 2.7923132774003536e-05, "loss": 0.0017, "step": 282500 }, { "epoch": 67.82, "learning_rate": 2.791991211378383e-05, "loss": 0.0018, "step": 282510 }, { "epoch": 67.82, "learning_rate": 2.7916691567365106e-05, "loss": 0.0018, "step": 282520 }, { "epoch": 67.82, "learning_rate": 2.7913471134763915e-05, "loss": 0.0019, "step": 282530 }, { "epoch": 67.83, "learning_rate": 2.7910250815996904e-05, "loss": 0.0016, "step": 282540 }, { "epoch": 67.83, "learning_rate": 2.790703061108064e-05, "loss": 0.0015, "step": 282550 }, { "epoch": 67.83, "learning_rate": 2.7903810520031703e-05, "loss": 0.0018, "step": 282560 }, { "epoch": 67.83, "learning_rate": 2.7900590542866734e-05, "loss": 0.0027, "step": 282570 }, { "epoch": 67.84, "learning_rate": 2.7897370679602285e-05, "loss": 0.0017, "step": 282580 }, { "epoch": 67.84, "learning_rate": 2.7894150930254993e-05, "loss": 0.002, "step": 282590 }, { "epoch": 67.84, "learning_rate": 2.7890931294841417e-05, "loss": 0.0017, "step": 282600 }, { "epoch": 67.84, "learning_rate": 2.7887711773378178e-05, "loss": 0.0016, "step": 282610 }, { "epoch": 67.85, "learning_rate": 2.788449236588186e-05, "loss": 0.0033, "step": 282620 }, { "epoch": 67.85, "learning_rate": 2.788127307236903e-05, "loss": 0.0023, "step": 282630 }, { "epoch": 67.85, "learning_rate": 2.7878053892856333e-05, "loss": 0.0017, "step": 282640 }, { "epoch": 67.85, "learning_rate": 2.78748348273603e-05, "loss": 0.0019, "step": 282650 }, { "epoch": 67.85, "learning_rate": 2.7871615875897584e-05, "loss": 0.0015, "step": 282660 }, { "epoch": 67.86, "learning_rate": 2.7868397038484716e-05, "loss": 0.0016, "step": 282670 }, { "epoch": 67.86, "learning_rate": 2.786517831513834e-05, "loss": 0.0019, "step": 282680 }, { "epoch": 67.86, "learning_rate": 2.7861959705874994e-05, "loss": 0.0095, "step": 282690 }, { "epoch": 67.86, "learning_rate": 2.7858741210711315e-05, "loss": 0.0017, "step": 282700 }, { "epoch": 67.87, "learning_rate": 2.7855522829663854e-05, "loss": 0.0017, "step": 282710 }, { "epoch": 67.87, "learning_rate": 2.785230456274923e-05, "loss": 0.0033, "step": 282720 }, { "epoch": 67.87, "learning_rate": 2.7849086409983993e-05, "loss": 0.0021, "step": 282730 }, { "epoch": 67.87, "learning_rate": 2.784586837138477e-05, "loss": 0.0016, "step": 282740 }, { "epoch": 67.88, "learning_rate": 2.784265044696811e-05, "loss": 0.0022, "step": 282750 }, { "epoch": 67.88, "learning_rate": 2.7839432636750605e-05, "loss": 0.0015, "step": 282760 }, { "epoch": 67.88, "learning_rate": 2.7836214940748877e-05, "loss": 0.0019, "step": 282770 }, { "epoch": 67.88, "learning_rate": 2.7832997358979486e-05, "loss": 0.0017, "step": 282780 }, { "epoch": 67.88, "learning_rate": 2.7829779891458983e-05, "loss": 0.0027, "step": 282790 }, { "epoch": 67.89, "learning_rate": 2.7826562538204004e-05, "loss": 0.0017, "step": 282800 }, { "epoch": 67.89, "learning_rate": 2.7823345299231083e-05, "loss": 0.0017, "step": 282810 }, { "epoch": 67.89, "learning_rate": 2.782012817455686e-05, "loss": 0.0015, "step": 282820 }, { "epoch": 67.89, "learning_rate": 2.7816911164197846e-05, "loss": 0.0017, "step": 282830 }, { "epoch": 67.9, "learning_rate": 2.7813694268170687e-05, "loss": 0.0018, "step": 282840 }, { "epoch": 67.9, "learning_rate": 2.7810477486491924e-05, "loss": 0.0018, "step": 282850 }, { "epoch": 67.9, "learning_rate": 2.780726081917813e-05, "loss": 0.0018, "step": 282860 }, { "epoch": 67.9, "learning_rate": 2.7804044266245922e-05, "loss": 0.0016, "step": 282870 }, { "epoch": 67.9, "learning_rate": 2.7800827827711828e-05, "loss": 0.0018, "step": 282880 }, { "epoch": 67.91, "learning_rate": 2.779761150359248e-05, "loss": 0.0019, "step": 282890 }, { "epoch": 67.91, "learning_rate": 2.7794395293904406e-05, "loss": 0.0017, "step": 282900 }, { "epoch": 67.91, "learning_rate": 2.779117919866423e-05, "loss": 0.0019, "step": 282910 }, { "epoch": 67.91, "learning_rate": 2.778796321788849e-05, "loss": 0.0016, "step": 282920 }, { "epoch": 67.92, "learning_rate": 2.7784747351593765e-05, "loss": 0.0016, "step": 282930 }, { "epoch": 67.92, "learning_rate": 2.778153159979665e-05, "loss": 0.0016, "step": 282940 }, { "epoch": 67.92, "learning_rate": 2.777831596251369e-05, "loss": 0.0018, "step": 282950 }, { "epoch": 67.92, "learning_rate": 2.7775100439761493e-05, "loss": 0.0015, "step": 282960 }, { "epoch": 67.93, "learning_rate": 2.77718850315566e-05, "loss": 0.0018, "step": 282970 }, { "epoch": 67.93, "learning_rate": 2.7768669737915607e-05, "loss": 0.0018, "step": 282980 }, { "epoch": 67.93, "learning_rate": 2.7765454558855087e-05, "loss": 0.0016, "step": 282990 }, { "epoch": 67.93, "learning_rate": 2.7762239494391573e-05, "loss": 0.0046, "step": 283000 }, { "epoch": 67.93, "learning_rate": 2.775902454454166e-05, "loss": 0.0016, "step": 283010 }, { "epoch": 67.94, "learning_rate": 2.7755809709321945e-05, "loss": 0.0016, "step": 283020 }, { "epoch": 67.94, "learning_rate": 2.775259498874896e-05, "loss": 0.0032, "step": 283030 }, { "epoch": 67.94, "learning_rate": 2.7749380382839296e-05, "loss": 0.0016, "step": 283040 }, { "epoch": 67.94, "learning_rate": 2.7746165891609492e-05, "loss": 0.0017, "step": 283050 }, { "epoch": 67.95, "learning_rate": 2.7742951515076156e-05, "loss": 0.0017, "step": 283060 }, { "epoch": 67.95, "learning_rate": 2.7739737253255817e-05, "loss": 0.0017, "step": 283070 }, { "epoch": 67.95, "learning_rate": 2.773652310616508e-05, "loss": 0.0028, "step": 283080 }, { "epoch": 68.0, "learning_rate": 2.7733309073820462e-05, "loss": 0.0018, "step": 283090 }, { "epoch": 68.0, "learning_rate": 2.773009515623858e-05, "loss": 0.002, "step": 283100 }, { "epoch": 68.01, "learning_rate": 2.772688135343595e-05, "loss": 0.0019, "step": 283110 }, { "epoch": 68.01, "learning_rate": 2.772366766542919e-05, "loss": 0.0018, "step": 283120 }, { "epoch": 68.01, "learning_rate": 2.7720454092234814e-05, "loss": 0.0015, "step": 283130 }, { "epoch": 68.01, "learning_rate": 2.77172406338694e-05, "loss": 0.0022, "step": 283140 }, { "epoch": 68.02, "learning_rate": 2.771402729034953e-05, "loss": 0.0016, "step": 283150 }, { "epoch": 68.02, "learning_rate": 2.7710814061691724e-05, "loss": 0.0029, "step": 283160 }, { "epoch": 68.02, "learning_rate": 2.7707600947912595e-05, "loss": 0.0022, "step": 283170 }, { "epoch": 68.02, "learning_rate": 2.7704387949028653e-05, "loss": 0.0028, "step": 283180 }, { "epoch": 68.02, "learning_rate": 2.7701175065056504e-05, "loss": 0.0028, "step": 283190 }, { "epoch": 68.03, "learning_rate": 2.7697962296012693e-05, "loss": 0.0019, "step": 283200 }, { "epoch": 68.03, "learning_rate": 2.7694749641913743e-05, "loss": 0.0019, "step": 283210 }, { "epoch": 68.03, "learning_rate": 2.7691537102776256e-05, "loss": 0.0016, "step": 283220 }, { "epoch": 68.03, "learning_rate": 2.7688324678616762e-05, "loss": 0.0021, "step": 283230 }, { "epoch": 68.04, "learning_rate": 2.7685112369451838e-05, "loss": 0.0021, "step": 283240 }, { "epoch": 68.04, "learning_rate": 2.768190017529802e-05, "loss": 0.0021, "step": 283250 }, { "epoch": 68.04, "learning_rate": 2.767868809617189e-05, "loss": 0.0023, "step": 283260 }, { "epoch": 68.04, "learning_rate": 2.7675476132089995e-05, "loss": 0.0018, "step": 283270 }, { "epoch": 68.04, "learning_rate": 2.767226428306886e-05, "loss": 0.0019, "step": 283280 }, { "epoch": 68.05, "learning_rate": 2.7669052549125074e-05, "loss": 0.0026, "step": 283290 }, { "epoch": 68.05, "learning_rate": 2.7665840930275166e-05, "loss": 0.0018, "step": 283300 }, { "epoch": 68.05, "learning_rate": 2.766262942653572e-05, "loss": 0.0024, "step": 283310 }, { "epoch": 68.05, "learning_rate": 2.7659418037923245e-05, "loss": 0.0021, "step": 283320 }, { "epoch": 68.06, "learning_rate": 2.7656206764454317e-05, "loss": 0.0082, "step": 283330 }, { "epoch": 68.06, "learning_rate": 2.765299560614551e-05, "loss": 0.0022, "step": 283340 }, { "epoch": 68.06, "learning_rate": 2.7649784563013327e-05, "loss": 0.0025, "step": 283350 }, { "epoch": 68.06, "learning_rate": 2.7646573635074363e-05, "loss": 0.002, "step": 283360 }, { "epoch": 68.07, "learning_rate": 2.764336282234512e-05, "loss": 0.0019, "step": 283370 }, { "epoch": 68.07, "learning_rate": 2.76401521248422e-05, "loss": 0.0015, "step": 283380 }, { "epoch": 68.07, "learning_rate": 2.7636941542582094e-05, "loss": 0.0016, "step": 283390 }, { "epoch": 68.07, "learning_rate": 2.7633731075581405e-05, "loss": 0.0019, "step": 283400 }, { "epoch": 68.07, "learning_rate": 2.7630520723856658e-05, "loss": 0.0021, "step": 283410 }, { "epoch": 68.08, "learning_rate": 2.7627310487424364e-05, "loss": 0.0016, "step": 283420 }, { "epoch": 68.08, "learning_rate": 2.762410036630112e-05, "loss": 0.0016, "step": 283430 }, { "epoch": 68.08, "learning_rate": 2.762089036050343e-05, "loss": 0.0018, "step": 283440 }, { "epoch": 68.08, "learning_rate": 2.761768047004788e-05, "loss": 0.0019, "step": 283450 }, { "epoch": 68.09, "learning_rate": 2.761447069495098e-05, "loss": 0.0027, "step": 283460 }, { "epoch": 68.09, "learning_rate": 2.761126103522929e-05, "loss": 0.0016, "step": 283470 }, { "epoch": 68.09, "learning_rate": 2.7608051490899358e-05, "loss": 0.0018, "step": 283480 }, { "epoch": 68.09, "learning_rate": 2.7604842061977687e-05, "loss": 0.002, "step": 283490 }, { "epoch": 68.1, "learning_rate": 2.760163274848088e-05, "loss": 0.002, "step": 283500 }, { "epoch": 68.1, "learning_rate": 2.759842355042541e-05, "loss": 0.0019, "step": 283510 }, { "epoch": 68.1, "learning_rate": 2.7595214467827885e-05, "loss": 0.0018, "step": 283520 }, { "epoch": 68.1, "learning_rate": 2.7592005500704787e-05, "loss": 0.002, "step": 283530 }, { "epoch": 68.1, "learning_rate": 2.7588796649072703e-05, "loss": 0.0034, "step": 283540 }, { "epoch": 68.11, "learning_rate": 2.758558791294814e-05, "loss": 0.0018, "step": 283550 }, { "epoch": 68.11, "learning_rate": 2.7582379292347633e-05, "loss": 0.0018, "step": 283560 }, { "epoch": 68.11, "learning_rate": 2.7579170787287746e-05, "loss": 0.0019, "step": 283570 }, { "epoch": 68.11, "learning_rate": 2.7575962397784982e-05, "loss": 0.0057, "step": 283580 }, { "epoch": 68.12, "learning_rate": 2.7572754123855914e-05, "loss": 0.0016, "step": 283590 }, { "epoch": 68.12, "learning_rate": 2.756954596551704e-05, "loss": 0.0017, "step": 283600 }, { "epoch": 68.12, "learning_rate": 2.7566337922784935e-05, "loss": 0.0022, "step": 283610 }, { "epoch": 68.12, "learning_rate": 2.7563129995676086e-05, "loss": 0.0025, "step": 283620 }, { "epoch": 68.12, "learning_rate": 2.7559922184207054e-05, "loss": 0.0019, "step": 283630 }, { "epoch": 68.13, "learning_rate": 2.7556714488394398e-05, "loss": 0.0017, "step": 283640 }, { "epoch": 68.13, "learning_rate": 2.7553506908254594e-05, "loss": 0.0017, "step": 283650 }, { "epoch": 68.13, "learning_rate": 2.7550299443804227e-05, "loss": 0.0019, "step": 283660 }, { "epoch": 68.13, "learning_rate": 2.754709209505979e-05, "loss": 0.0019, "step": 283670 }, { "epoch": 68.14, "learning_rate": 2.754388486203784e-05, "loss": 0.0019, "step": 283680 }, { "epoch": 68.14, "learning_rate": 2.7540677744754873e-05, "loss": 0.0018, "step": 283690 }, { "epoch": 68.14, "learning_rate": 2.7537470743227467e-05, "loss": 0.0015, "step": 283700 }, { "epoch": 68.14, "learning_rate": 2.753426385747212e-05, "loss": 0.0017, "step": 283710 }, { "epoch": 68.15, "learning_rate": 2.753105708750535e-05, "loss": 0.0019, "step": 283720 }, { "epoch": 68.15, "learning_rate": 2.7527850433343717e-05, "loss": 0.0017, "step": 283730 }, { "epoch": 68.15, "learning_rate": 2.752464389500371e-05, "loss": 0.0068, "step": 283740 }, { "epoch": 68.15, "learning_rate": 2.75214374725019e-05, "loss": 0.0017, "step": 283750 }, { "epoch": 68.15, "learning_rate": 2.751823116585477e-05, "loss": 0.0015, "step": 283760 }, { "epoch": 68.16, "learning_rate": 2.7515024975078873e-05, "loss": 0.0017, "step": 283770 }, { "epoch": 68.16, "learning_rate": 2.7511818900190735e-05, "loss": 0.0019, "step": 283780 }, { "epoch": 68.16, "learning_rate": 2.7508612941206845e-05, "loss": 0.002, "step": 283790 }, { "epoch": 68.16, "learning_rate": 2.7505407098143775e-05, "loss": 0.0018, "step": 283800 }, { "epoch": 68.17, "learning_rate": 2.750220137101801e-05, "loss": 0.0014, "step": 283810 }, { "epoch": 68.17, "learning_rate": 2.7498995759846103e-05, "loss": 0.002, "step": 283820 }, { "epoch": 68.17, "learning_rate": 2.749579026464454e-05, "loss": 0.003, "step": 283830 }, { "epoch": 68.17, "learning_rate": 2.7492584885429877e-05, "loss": 0.0019, "step": 283840 }, { "epoch": 68.18, "learning_rate": 2.7489379622218627e-05, "loss": 0.0017, "step": 283850 }, { "epoch": 68.18, "learning_rate": 2.7486174475027278e-05, "loss": 0.0018, "step": 283860 }, { "epoch": 68.18, "learning_rate": 2.7482969443872396e-05, "loss": 0.0018, "step": 283870 }, { "epoch": 68.18, "learning_rate": 2.7479764528770457e-05, "loss": 0.0018, "step": 283880 }, { "epoch": 68.18, "learning_rate": 2.7476559729738015e-05, "loss": 0.0018, "step": 283890 }, { "epoch": 68.19, "learning_rate": 2.747335504679156e-05, "loss": 0.002, "step": 283900 }, { "epoch": 68.19, "learning_rate": 2.747015047994764e-05, "loss": 0.0017, "step": 283910 }, { "epoch": 68.19, "learning_rate": 2.746694602922273e-05, "loss": 0.0017, "step": 283920 }, { "epoch": 68.19, "learning_rate": 2.7463741694633395e-05, "loss": 0.0018, "step": 283930 }, { "epoch": 68.2, "learning_rate": 2.7460537476196096e-05, "loss": 0.0016, "step": 283940 }, { "epoch": 68.2, "learning_rate": 2.7457333373927373e-05, "loss": 0.0017, "step": 283950 }, { "epoch": 68.2, "learning_rate": 2.7454129387843774e-05, "loss": 0.0019, "step": 283960 }, { "epoch": 68.2, "learning_rate": 2.7450925517961752e-05, "loss": 0.0018, "step": 283970 }, { "epoch": 68.2, "learning_rate": 2.7447721764297875e-05, "loss": 0.0016, "step": 283980 }, { "epoch": 68.21, "learning_rate": 2.744451812686862e-05, "loss": 0.0018, "step": 283990 }, { "epoch": 68.21, "learning_rate": 2.7441314605690488e-05, "loss": 0.0022, "step": 284000 }, { "epoch": 68.21, "learning_rate": 2.7438111200780037e-05, "loss": 0.0018, "step": 284010 }, { "epoch": 68.21, "learning_rate": 2.7434907912153717e-05, "loss": 0.0015, "step": 284020 }, { "epoch": 68.22, "learning_rate": 2.74317047398281e-05, "loss": 0.002, "step": 284030 }, { "epoch": 68.22, "learning_rate": 2.7428501683819642e-05, "loss": 0.0016, "step": 284040 }, { "epoch": 68.22, "learning_rate": 2.74252987441449e-05, "loss": 0.0016, "step": 284050 }, { "epoch": 68.22, "learning_rate": 2.742209592082035e-05, "loss": 0.0019, "step": 284060 }, { "epoch": 68.23, "learning_rate": 2.741889321386249e-05, "loss": 0.002, "step": 284070 }, { "epoch": 68.23, "learning_rate": 2.741569062328786e-05, "loss": 0.0024, "step": 284080 }, { "epoch": 68.23, "learning_rate": 2.7412488149112936e-05, "loss": 0.0025, "step": 284090 }, { "epoch": 68.23, "learning_rate": 2.740928579135425e-05, "loss": 0.0016, "step": 284100 }, { "epoch": 68.23, "learning_rate": 2.7406083550028276e-05, "loss": 0.0023, "step": 284110 }, { "epoch": 68.24, "learning_rate": 2.7402881425151562e-05, "loss": 0.0036, "step": 284120 }, { "epoch": 68.24, "learning_rate": 2.7399679416740576e-05, "loss": 0.0018, "step": 284130 }, { "epoch": 68.24, "learning_rate": 2.7396477524811814e-05, "loss": 0.0017, "step": 284140 }, { "epoch": 68.24, "learning_rate": 2.7393275749381818e-05, "loss": 0.0023, "step": 284150 }, { "epoch": 68.25, "learning_rate": 2.739007409046705e-05, "loss": 0.0066, "step": 284160 }, { "epoch": 68.25, "learning_rate": 2.7386872548084043e-05, "loss": 0.0024, "step": 284170 }, { "epoch": 68.25, "learning_rate": 2.7383671122249268e-05, "loss": 0.0018, "step": 284180 }, { "epoch": 68.25, "learning_rate": 2.738046981297926e-05, "loss": 0.0017, "step": 284190 }, { "epoch": 68.26, "learning_rate": 2.7377268620290486e-05, "loss": 0.0016, "step": 284200 }, { "epoch": 68.26, "learning_rate": 2.7374067544199467e-05, "loss": 0.002, "step": 284210 }, { "epoch": 68.26, "learning_rate": 2.7370866584722682e-05, "loss": 0.0021, "step": 284220 }, { "epoch": 68.26, "learning_rate": 2.736766574187666e-05, "loss": 0.0017, "step": 284230 }, { "epoch": 68.26, "learning_rate": 2.7364465015677854e-05, "loss": 0.0037, "step": 284240 }, { "epoch": 68.27, "learning_rate": 2.73612644061428e-05, "loss": 0.0061, "step": 284250 }, { "epoch": 68.27, "learning_rate": 2.7358063913287966e-05, "loss": 0.0019, "step": 284260 }, { "epoch": 68.27, "learning_rate": 2.7354863537129877e-05, "loss": 0.0025, "step": 284270 }, { "epoch": 68.27, "learning_rate": 2.7351663277684993e-05, "loss": 0.0029, "step": 284280 }, { "epoch": 68.28, "learning_rate": 2.7348463134969838e-05, "loss": 0.0036, "step": 284290 }, { "epoch": 68.28, "learning_rate": 2.7345263109000885e-05, "loss": 0.005, "step": 284300 }, { "epoch": 68.28, "learning_rate": 2.7342063199794644e-05, "loss": 0.0017, "step": 284310 }, { "epoch": 68.28, "learning_rate": 2.7338863407367586e-05, "loss": 0.0016, "step": 284320 }, { "epoch": 68.28, "learning_rate": 2.7335663731736234e-05, "loss": 0.0017, "step": 284330 }, { "epoch": 68.29, "learning_rate": 2.733246417291706e-05, "loss": 0.0036, "step": 284340 }, { "epoch": 68.29, "learning_rate": 2.7329264730926534e-05, "loss": 0.0018, "step": 284350 }, { "epoch": 68.29, "learning_rate": 2.7326065405781186e-05, "loss": 0.0017, "step": 284360 }, { "epoch": 68.29, "learning_rate": 2.732286619749747e-05, "loss": 0.0017, "step": 284370 }, { "epoch": 68.3, "learning_rate": 2.7319667106091912e-05, "loss": 0.0018, "step": 284380 }, { "epoch": 68.3, "learning_rate": 2.731646813158096e-05, "loss": 0.002, "step": 284390 }, { "epoch": 68.3, "learning_rate": 2.7313269273981135e-05, "loss": 0.0017, "step": 284400 }, { "epoch": 68.3, "learning_rate": 2.7310070533308897e-05, "loss": 0.0017, "step": 284410 }, { "epoch": 68.31, "learning_rate": 2.7306871909580755e-05, "loss": 0.0025, "step": 284420 }, { "epoch": 68.31, "learning_rate": 2.730367340281319e-05, "loss": 0.0025, "step": 284430 }, { "epoch": 68.31, "learning_rate": 2.7300475013022663e-05, "loss": 0.0018, "step": 284440 }, { "epoch": 68.31, "learning_rate": 2.7297276740225696e-05, "loss": 0.0023, "step": 284450 }, { "epoch": 68.31, "learning_rate": 2.7294078584438744e-05, "loss": 0.0018, "step": 284460 }, { "epoch": 68.32, "learning_rate": 2.729088054567831e-05, "loss": 0.0022, "step": 284470 }, { "epoch": 68.32, "learning_rate": 2.7287682623960848e-05, "loss": 0.0037, "step": 284480 }, { "epoch": 68.32, "learning_rate": 2.728448481930288e-05, "loss": 0.0019, "step": 284490 }, { "epoch": 68.32, "learning_rate": 2.7281287131720867e-05, "loss": 0.0016, "step": 284500 }, { "epoch": 68.33, "learning_rate": 2.7278089561231273e-05, "loss": 0.0024, "step": 284510 }, { "epoch": 68.33, "learning_rate": 2.7274892107850598e-05, "loss": 0.0017, "step": 284520 }, { "epoch": 68.33, "learning_rate": 2.7271694771595334e-05, "loss": 0.0018, "step": 284530 }, { "epoch": 68.33, "learning_rate": 2.7268497552481926e-05, "loss": 0.0017, "step": 284540 }, { "epoch": 68.34, "learning_rate": 2.726530045052689e-05, "loss": 0.0015, "step": 284550 }, { "epoch": 68.34, "learning_rate": 2.726210346574667e-05, "loss": 0.0019, "step": 284560 }, { "epoch": 68.34, "learning_rate": 2.7258906598157775e-05, "loss": 0.0021, "step": 284570 }, { "epoch": 68.34, "learning_rate": 2.7255709847776644e-05, "loss": 0.0018, "step": 284580 }, { "epoch": 68.34, "learning_rate": 2.72525132146198e-05, "loss": 0.0023, "step": 284590 }, { "epoch": 68.35, "learning_rate": 2.724931669870367e-05, "loss": 0.0018, "step": 284600 }, { "epoch": 68.35, "learning_rate": 2.7246120300044774e-05, "loss": 0.0016, "step": 284610 }, { "epoch": 68.35, "learning_rate": 2.7242924018659545e-05, "loss": 0.003, "step": 284620 }, { "epoch": 68.35, "learning_rate": 2.723972785456449e-05, "loss": 0.0017, "step": 284630 }, { "epoch": 68.36, "learning_rate": 2.7236531807776068e-05, "loss": 0.0014, "step": 284640 }, { "epoch": 68.36, "learning_rate": 2.7233335878310738e-05, "loss": 0.0024, "step": 284650 }, { "epoch": 68.36, "learning_rate": 2.7230140066185e-05, "loss": 0.0018, "step": 284660 }, { "epoch": 68.36, "learning_rate": 2.7226944371415293e-05, "loss": 0.0018, "step": 284670 }, { "epoch": 68.36, "learning_rate": 2.7223748794018124e-05, "loss": 0.0016, "step": 284680 }, { "epoch": 68.37, "learning_rate": 2.7220553334009922e-05, "loss": 0.0022, "step": 284690 }, { "epoch": 68.37, "learning_rate": 2.72173579914072e-05, "loss": 0.0016, "step": 284700 }, { "epoch": 68.37, "learning_rate": 2.7214162766226404e-05, "loss": 0.0014, "step": 284710 }, { "epoch": 68.37, "learning_rate": 2.7210967658483986e-05, "loss": 0.0018, "step": 284720 }, { "epoch": 68.38, "learning_rate": 2.7207772668196453e-05, "loss": 0.0018, "step": 284730 }, { "epoch": 68.38, "learning_rate": 2.7204577795380225e-05, "loss": 0.002, "step": 284740 }, { "epoch": 68.38, "learning_rate": 2.720138304005182e-05, "loss": 0.0019, "step": 284750 }, { "epoch": 68.38, "learning_rate": 2.7198188402227653e-05, "loss": 0.0016, "step": 284760 }, { "epoch": 68.39, "learning_rate": 2.7194993881924237e-05, "loss": 0.0017, "step": 284770 }, { "epoch": 68.39, "learning_rate": 2.719179947915801e-05, "loss": 0.0018, "step": 284780 }, { "epoch": 68.39, "learning_rate": 2.7188605193945415e-05, "loss": 0.0017, "step": 284790 }, { "epoch": 68.39, "learning_rate": 2.7185411026302964e-05, "loss": 0.0016, "step": 284800 }, { "epoch": 68.39, "learning_rate": 2.7182216976247077e-05, "loss": 0.0017, "step": 284810 }, { "epoch": 68.4, "learning_rate": 2.7179023043794254e-05, "loss": 0.0019, "step": 284820 }, { "epoch": 68.4, "learning_rate": 2.7175829228960914e-05, "loss": 0.0018, "step": 284830 }, { "epoch": 68.4, "learning_rate": 2.7172635531763548e-05, "loss": 0.0018, "step": 284840 }, { "epoch": 68.4, "learning_rate": 2.716944195221862e-05, "loss": 0.0018, "step": 284850 }, { "epoch": 68.41, "learning_rate": 2.7166248490342568e-05, "loss": 0.0015, "step": 284860 }, { "epoch": 68.41, "learning_rate": 2.7163055146151874e-05, "loss": 0.0016, "step": 284870 }, { "epoch": 68.41, "learning_rate": 2.7159861919662967e-05, "loss": 0.0019, "step": 284880 }, { "epoch": 68.41, "learning_rate": 2.7156668810892345e-05, "loss": 0.0017, "step": 284890 }, { "epoch": 68.41, "learning_rate": 2.7153475819856422e-05, "loss": 0.0018, "step": 284900 }, { "epoch": 68.42, "learning_rate": 2.7150282946571693e-05, "loss": 0.0021, "step": 284910 }, { "epoch": 68.42, "learning_rate": 2.7147090191054602e-05, "loss": 0.0016, "step": 284920 }, { "epoch": 68.42, "learning_rate": 2.7143897553321574e-05, "loss": 0.0017, "step": 284930 }, { "epoch": 68.42, "learning_rate": 2.7140705033389113e-05, "loss": 0.0032, "step": 284940 }, { "epoch": 68.43, "learning_rate": 2.7137512631273627e-05, "loss": 0.0018, "step": 284950 }, { "epoch": 68.43, "learning_rate": 2.713432034699161e-05, "loss": 0.0018, "step": 284960 }, { "epoch": 68.43, "learning_rate": 2.7131128180559484e-05, "loss": 0.0017, "step": 284970 }, { "epoch": 68.43, "learning_rate": 2.7127936131993727e-05, "loss": 0.0016, "step": 284980 }, { "epoch": 68.44, "learning_rate": 2.7124744201310782e-05, "loss": 0.0021, "step": 284990 }, { "epoch": 68.44, "learning_rate": 2.712155238852707e-05, "loss": 0.0016, "step": 285000 }, { "epoch": 68.44, "learning_rate": 2.7118360693659094e-05, "loss": 0.0036, "step": 285010 }, { "epoch": 68.44, "learning_rate": 2.711516911672326e-05, "loss": 0.0019, "step": 285020 }, { "epoch": 68.44, "learning_rate": 2.7111977657736053e-05, "loss": 0.0016, "step": 285030 }, { "epoch": 68.45, "learning_rate": 2.7108786316713885e-05, "loss": 0.0019, "step": 285040 }, { "epoch": 68.45, "learning_rate": 2.7105595093673248e-05, "loss": 0.0016, "step": 285050 }, { "epoch": 68.45, "learning_rate": 2.710240398863056e-05, "loss": 0.0016, "step": 285060 }, { "epoch": 68.45, "learning_rate": 2.7099213001602253e-05, "loss": 0.0017, "step": 285070 }, { "epoch": 68.46, "learning_rate": 2.7096022132604813e-05, "loss": 0.0035, "step": 285080 }, { "epoch": 68.46, "learning_rate": 2.7092831381654653e-05, "loss": 0.0016, "step": 285090 }, { "epoch": 68.46, "learning_rate": 2.7089640748768247e-05, "loss": 0.0037, "step": 285100 }, { "epoch": 68.46, "learning_rate": 2.7086450233962e-05, "loss": 0.0017, "step": 285110 }, { "epoch": 68.47, "learning_rate": 2.7083259837252407e-05, "loss": 0.002, "step": 285120 }, { "epoch": 68.47, "learning_rate": 2.7080069558655864e-05, "loss": 0.0018, "step": 285130 }, { "epoch": 68.47, "learning_rate": 2.707687939818883e-05, "loss": 0.0017, "step": 285140 }, { "epoch": 68.47, "learning_rate": 2.7073689355867772e-05, "loss": 0.003, "step": 285150 }, { "epoch": 68.47, "learning_rate": 2.7070499431709097e-05, "loss": 0.002, "step": 285160 }, { "epoch": 68.48, "learning_rate": 2.706730962572927e-05, "loss": 0.0024, "step": 285170 }, { "epoch": 68.48, "learning_rate": 2.7064119937944705e-05, "loss": 0.0021, "step": 285180 }, { "epoch": 68.48, "learning_rate": 2.706093036837188e-05, "loss": 0.0019, "step": 285190 }, { "epoch": 68.48, "learning_rate": 2.7057740917027186e-05, "loss": 0.002, "step": 285200 }, { "epoch": 68.49, "learning_rate": 2.7054551583927112e-05, "loss": 0.0024, "step": 285210 }, { "epoch": 68.49, "learning_rate": 2.7051362369088067e-05, "loss": 0.0018, "step": 285220 }, { "epoch": 68.49, "learning_rate": 2.7048173272526477e-05, "loss": 0.002, "step": 285230 }, { "epoch": 68.49, "learning_rate": 2.704498429425881e-05, "loss": 0.0019, "step": 285240 }, { "epoch": 68.49, "learning_rate": 2.7041795434301465e-05, "loss": 0.0019, "step": 285250 }, { "epoch": 68.5, "learning_rate": 2.703860669267092e-05, "loss": 0.0025, "step": 285260 }, { "epoch": 68.5, "learning_rate": 2.7035418069383567e-05, "loss": 0.0016, "step": 285270 }, { "epoch": 68.5, "learning_rate": 2.7032229564455886e-05, "loss": 0.0025, "step": 285280 }, { "epoch": 68.5, "learning_rate": 2.702904117790428e-05, "loss": 0.0032, "step": 285290 }, { "epoch": 68.51, "learning_rate": 2.7025852909745176e-05, "loss": 0.0016, "step": 285300 }, { "epoch": 68.51, "learning_rate": 2.7022664759995033e-05, "loss": 0.0019, "step": 285310 }, { "epoch": 68.51, "learning_rate": 2.7019476728670246e-05, "loss": 0.0033, "step": 285320 }, { "epoch": 68.51, "learning_rate": 2.7016288815787282e-05, "loss": 0.0017, "step": 285330 }, { "epoch": 68.52, "learning_rate": 2.7013101021362547e-05, "loss": 0.0021, "step": 285340 }, { "epoch": 68.52, "learning_rate": 2.7009913345412497e-05, "loss": 0.0017, "step": 285350 }, { "epoch": 68.52, "learning_rate": 2.7006725787953546e-05, "loss": 0.0016, "step": 285360 }, { "epoch": 68.52, "learning_rate": 2.700353834900211e-05, "loss": 0.0016, "step": 285370 }, { "epoch": 68.52, "learning_rate": 2.7000351028574645e-05, "loss": 0.0017, "step": 285380 }, { "epoch": 68.53, "learning_rate": 2.6997163826687543e-05, "loss": 0.0015, "step": 285390 }, { "epoch": 68.53, "learning_rate": 2.6993976743357264e-05, "loss": 0.0016, "step": 285400 }, { "epoch": 68.53, "learning_rate": 2.6990789778600213e-05, "loss": 0.0021, "step": 285410 }, { "epoch": 68.53, "learning_rate": 2.6987602932432833e-05, "loss": 0.0021, "step": 285420 }, { "epoch": 68.54, "learning_rate": 2.6984416204871526e-05, "loss": 0.0016, "step": 285430 }, { "epoch": 68.54, "learning_rate": 2.698122959593275e-05, "loss": 0.0016, "step": 285440 }, { "epoch": 68.54, "learning_rate": 2.697804310563289e-05, "loss": 0.0027, "step": 285450 }, { "epoch": 68.54, "learning_rate": 2.6974856733988385e-05, "loss": 0.0018, "step": 285460 }, { "epoch": 68.55, "learning_rate": 2.697167048101568e-05, "loss": 0.0018, "step": 285470 }, { "epoch": 68.55, "learning_rate": 2.696848434673116e-05, "loss": 0.0022, "step": 285480 }, { "epoch": 68.55, "learning_rate": 2.6965298331151283e-05, "loss": 0.0018, "step": 285490 }, { "epoch": 68.55, "learning_rate": 2.6962112434292454e-05, "loss": 0.0024, "step": 285500 }, { "epoch": 68.55, "learning_rate": 2.695892665617107e-05, "loss": 0.0016, "step": 285510 }, { "epoch": 68.56, "learning_rate": 2.695574099680359e-05, "loss": 0.0018, "step": 285520 }, { "epoch": 68.56, "learning_rate": 2.6952555456206393e-05, "loss": 0.0017, "step": 285530 }, { "epoch": 68.56, "learning_rate": 2.694937003439594e-05, "loss": 0.0021, "step": 285540 }, { "epoch": 68.56, "learning_rate": 2.6946184731388602e-05, "loss": 0.0021, "step": 285550 }, { "epoch": 68.57, "learning_rate": 2.6942999547200838e-05, "loss": 0.0015, "step": 285560 }, { "epoch": 68.57, "learning_rate": 2.6939814481849052e-05, "loss": 0.0153, "step": 285570 }, { "epoch": 68.57, "learning_rate": 2.6936629535349632e-05, "loss": 0.0018, "step": 285580 }, { "epoch": 68.57, "learning_rate": 2.6933444707719042e-05, "loss": 0.0052, "step": 285590 }, { "epoch": 68.57, "learning_rate": 2.6930259998973646e-05, "loss": 0.0021, "step": 285600 }, { "epoch": 68.58, "learning_rate": 2.6927075409129904e-05, "loss": 0.0021, "step": 285610 }, { "epoch": 68.58, "learning_rate": 2.692389093820419e-05, "loss": 0.0022, "step": 285620 }, { "epoch": 68.58, "learning_rate": 2.692070658621295e-05, "loss": 0.0023, "step": 285630 }, { "epoch": 68.58, "learning_rate": 2.6917522353172587e-05, "loss": 0.0024, "step": 285640 }, { "epoch": 68.59, "learning_rate": 2.691433823909948e-05, "loss": 0.0021, "step": 285650 }, { "epoch": 68.59, "learning_rate": 2.6911154244010095e-05, "loss": 0.0034, "step": 285660 }, { "epoch": 68.59, "learning_rate": 2.6907970367920787e-05, "loss": 0.0028, "step": 285670 }, { "epoch": 68.59, "learning_rate": 2.6904786610848014e-05, "loss": 0.0025, "step": 285680 }, { "epoch": 68.6, "learning_rate": 2.690160297280815e-05, "loss": 0.0028, "step": 285690 }, { "epoch": 68.6, "learning_rate": 2.689841945381763e-05, "loss": 0.0019, "step": 285700 }, { "epoch": 68.6, "learning_rate": 2.6895236053892852e-05, "loss": 0.0021, "step": 285710 }, { "epoch": 68.6, "learning_rate": 2.68920527730502e-05, "loss": 0.0029, "step": 285720 }, { "epoch": 68.6, "learning_rate": 2.68888696113061e-05, "loss": 0.0019, "step": 285730 }, { "epoch": 68.61, "learning_rate": 2.6885686568676983e-05, "loss": 0.0041, "step": 285740 }, { "epoch": 68.61, "learning_rate": 2.688250364517921e-05, "loss": 0.002, "step": 285750 }, { "epoch": 68.61, "learning_rate": 2.6879320840829224e-05, "loss": 0.0027, "step": 285760 }, { "epoch": 68.61, "learning_rate": 2.6876138155643394e-05, "loss": 0.0336, "step": 285770 }, { "epoch": 68.62, "learning_rate": 2.687295558963816e-05, "loss": 0.0025, "step": 285780 }, { "epoch": 68.62, "learning_rate": 2.6869773142829885e-05, "loss": 0.0033, "step": 285790 }, { "epoch": 68.62, "learning_rate": 2.6866590815235016e-05, "loss": 0.0021, "step": 285800 }, { "epoch": 68.62, "learning_rate": 2.6863408606869904e-05, "loss": 0.002, "step": 285810 }, { "epoch": 68.63, "learning_rate": 2.686022651775101e-05, "loss": 0.0025, "step": 285820 }, { "epoch": 68.63, "learning_rate": 2.685704454789467e-05, "loss": 0.0022, "step": 285830 }, { "epoch": 68.63, "learning_rate": 2.685386269731734e-05, "loss": 0.0024, "step": 285840 }, { "epoch": 68.63, "learning_rate": 2.685068096603539e-05, "loss": 0.0019, "step": 285850 }, { "epoch": 68.63, "learning_rate": 2.6847499354065207e-05, "loss": 0.0022, "step": 285860 }, { "epoch": 68.64, "learning_rate": 2.6844317861423234e-05, "loss": 0.0021, "step": 285870 }, { "epoch": 68.64, "learning_rate": 2.6841136488125817e-05, "loss": 0.0019, "step": 285880 }, { "epoch": 68.64, "learning_rate": 2.6837955234189394e-05, "loss": 0.004, "step": 285890 }, { "epoch": 68.64, "learning_rate": 2.683477409963032e-05, "loss": 0.0025, "step": 285900 }, { "epoch": 68.65, "learning_rate": 2.6831593084465034e-05, "loss": 0.0019, "step": 285910 }, { "epoch": 68.65, "learning_rate": 2.6828412188709916e-05, "loss": 0.0041, "step": 285920 }, { "epoch": 68.65, "learning_rate": 2.6825231412381335e-05, "loss": 0.0021, "step": 285930 }, { "epoch": 68.65, "learning_rate": 2.682205075549572e-05, "loss": 0.0035, "step": 285940 }, { "epoch": 68.65, "learning_rate": 2.681887021806943e-05, "loss": 0.0031, "step": 285950 }, { "epoch": 68.66, "learning_rate": 2.6815689800118897e-05, "loss": 0.0019, "step": 285960 }, { "epoch": 68.66, "learning_rate": 2.6812509501660476e-05, "loss": 0.0017, "step": 285970 }, { "epoch": 68.66, "learning_rate": 2.68093293227106e-05, "loss": 0.0034, "step": 285980 }, { "epoch": 68.66, "learning_rate": 2.68061492632856e-05, "loss": 0.0017, "step": 285990 }, { "epoch": 68.67, "learning_rate": 2.680296932340193e-05, "loss": 0.0022, "step": 286000 }, { "epoch": 68.67, "learning_rate": 2.6799789503075944e-05, "loss": 0.0018, "step": 286010 }, { "epoch": 68.67, "learning_rate": 2.6796609802324026e-05, "loss": 0.0028, "step": 286020 }, { "epoch": 68.67, "learning_rate": 2.6793430221162568e-05, "loss": 0.0019, "step": 286030 }, { "epoch": 68.68, "learning_rate": 2.6790250759607986e-05, "loss": 0.0019, "step": 286040 }, { "epoch": 68.68, "learning_rate": 2.6787071417676622e-05, "loss": 0.0018, "step": 286050 }, { "epoch": 68.68, "learning_rate": 2.6783892195384918e-05, "loss": 0.002, "step": 286060 }, { "epoch": 68.68, "learning_rate": 2.6780713092749198e-05, "loss": 0.002, "step": 286070 }, { "epoch": 68.68, "learning_rate": 2.6777534109785894e-05, "loss": 0.0017, "step": 286080 }, { "epoch": 68.69, "learning_rate": 2.677435524651136e-05, "loss": 0.0049, "step": 286090 }, { "epoch": 68.69, "learning_rate": 2.6771176502942007e-05, "loss": 0.0047, "step": 286100 }, { "epoch": 68.69, "learning_rate": 2.67679978790942e-05, "loss": 0.0021, "step": 286110 }, { "epoch": 68.69, "learning_rate": 2.676481937498433e-05, "loss": 0.0023, "step": 286120 }, { "epoch": 68.7, "learning_rate": 2.6761640990628756e-05, "loss": 0.0127, "step": 286130 }, { "epoch": 68.7, "learning_rate": 2.6758462726043904e-05, "loss": 0.0019, "step": 286140 }, { "epoch": 68.7, "learning_rate": 2.6755284581246132e-05, "loss": 0.0019, "step": 286150 }, { "epoch": 68.7, "learning_rate": 2.675210655625179e-05, "loss": 0.0022, "step": 286160 }, { "epoch": 68.71, "learning_rate": 2.674892865107731e-05, "loss": 0.0016, "step": 286170 }, { "epoch": 68.71, "learning_rate": 2.6745750865739023e-05, "loss": 0.0027, "step": 286180 }, { "epoch": 68.71, "learning_rate": 2.674257320025335e-05, "loss": 0.0031, "step": 286190 }, { "epoch": 68.71, "learning_rate": 2.6739395654636633e-05, "loss": 0.0023, "step": 286200 }, { "epoch": 68.71, "learning_rate": 2.6736218228905286e-05, "loss": 0.0027, "step": 286210 }, { "epoch": 68.72, "learning_rate": 2.6733040923075658e-05, "loss": 0.0017, "step": 286220 }, { "epoch": 68.72, "learning_rate": 2.672986373716412e-05, "loss": 0.0021, "step": 286230 }, { "epoch": 68.72, "learning_rate": 2.6726686671187072e-05, "loss": 0.0021, "step": 286240 }, { "epoch": 68.72, "learning_rate": 2.6723509725160855e-05, "loss": 0.0019, "step": 286250 }, { "epoch": 68.73, "learning_rate": 2.6720332899101885e-05, "loss": 0.0021, "step": 286260 }, { "epoch": 68.73, "learning_rate": 2.6717156193026495e-05, "loss": 0.0016, "step": 286270 }, { "epoch": 68.73, "learning_rate": 2.6713979606951102e-05, "loss": 0.0015, "step": 286280 }, { "epoch": 68.73, "learning_rate": 2.6710803140892042e-05, "loss": 0.0019, "step": 286290 }, { "epoch": 68.73, "learning_rate": 2.670762679486568e-05, "loss": 0.002, "step": 286300 }, { "epoch": 68.74, "learning_rate": 2.6704450568888427e-05, "loss": 0.002, "step": 286310 }, { "epoch": 68.74, "learning_rate": 2.6701274462976615e-05, "loss": 0.0027, "step": 286320 }, { "epoch": 68.74, "learning_rate": 2.6698098477146645e-05, "loss": 0.0018, "step": 286330 }, { "epoch": 68.74, "learning_rate": 2.669492261141485e-05, "loss": 0.0039, "step": 286340 }, { "epoch": 68.75, "learning_rate": 2.6691746865797617e-05, "loss": 0.0021, "step": 286350 }, { "epoch": 68.75, "learning_rate": 2.668857124031134e-05, "loss": 0.0019, "step": 286360 }, { "epoch": 68.75, "learning_rate": 2.668539573497234e-05, "loss": 0.0017, "step": 286370 }, { "epoch": 68.75, "learning_rate": 2.6682220349797023e-05, "loss": 0.0017, "step": 286380 }, { "epoch": 68.76, "learning_rate": 2.6679045084801713e-05, "loss": 0.0015, "step": 286390 }, { "epoch": 68.76, "learning_rate": 2.6675869940002828e-05, "loss": 0.0018, "step": 286400 }, { "epoch": 68.76, "learning_rate": 2.6672694915416678e-05, "loss": 0.0018, "step": 286410 }, { "epoch": 68.76, "learning_rate": 2.666952001105968e-05, "loss": 0.0015, "step": 286420 }, { "epoch": 68.76, "learning_rate": 2.6666345226948166e-05, "loss": 0.0016, "step": 286430 }, { "epoch": 68.77, "learning_rate": 2.6663170563098485e-05, "loss": 0.0017, "step": 286440 }, { "epoch": 68.77, "learning_rate": 2.6659996019527035e-05, "loss": 0.002, "step": 286450 }, { "epoch": 68.77, "learning_rate": 2.6656821596250147e-05, "loss": 0.0016, "step": 286460 }, { "epoch": 68.77, "learning_rate": 2.6653647293284213e-05, "loss": 0.002, "step": 286470 }, { "epoch": 68.78, "learning_rate": 2.6650473110645557e-05, "loss": 0.0025, "step": 286480 }, { "epoch": 68.78, "learning_rate": 2.664729904835057e-05, "loss": 0.0022, "step": 286490 }, { "epoch": 68.78, "learning_rate": 2.664412510641561e-05, "loss": 0.0025, "step": 286500 }, { "epoch": 68.78, "learning_rate": 2.6640951284856998e-05, "loss": 0.0017, "step": 286510 }, { "epoch": 68.79, "learning_rate": 2.6637777583691137e-05, "loss": 0.0018, "step": 286520 }, { "epoch": 68.79, "learning_rate": 2.6634604002934347e-05, "loss": 0.0019, "step": 286530 }, { "epoch": 68.79, "learning_rate": 2.6631430542603024e-05, "loss": 0.0026, "step": 286540 }, { "epoch": 68.79, "learning_rate": 2.6628257202713486e-05, "loss": 0.0018, "step": 286550 }, { "epoch": 68.79, "learning_rate": 2.6625083983282124e-05, "loss": 0.0016, "step": 286560 }, { "epoch": 68.8, "learning_rate": 2.6621910884325274e-05, "loss": 0.0134, "step": 286570 }, { "epoch": 68.8, "learning_rate": 2.661873790585927e-05, "loss": 0.0019, "step": 286580 }, { "epoch": 68.8, "learning_rate": 2.6615565047900503e-05, "loss": 0.0023, "step": 286590 }, { "epoch": 68.8, "learning_rate": 2.6612392310465294e-05, "loss": 0.0021, "step": 286600 }, { "epoch": 68.81, "learning_rate": 2.660921969357003e-05, "loss": 0.0018, "step": 286610 }, { "epoch": 68.81, "learning_rate": 2.6606047197231026e-05, "loss": 0.002, "step": 286620 }, { "epoch": 68.81, "learning_rate": 2.660287482146467e-05, "loss": 0.0018, "step": 286630 }, { "epoch": 68.81, "learning_rate": 2.6599702566287266e-05, "loss": 0.0023, "step": 286640 }, { "epoch": 68.81, "learning_rate": 2.6596530431715218e-05, "loss": 0.0017, "step": 286650 }, { "epoch": 68.82, "learning_rate": 2.6593358417764825e-05, "loss": 0.0017, "step": 286660 }, { "epoch": 68.82, "learning_rate": 2.6590186524452453e-05, "loss": 0.002, "step": 286670 }, { "epoch": 68.82, "learning_rate": 2.658701475179448e-05, "loss": 0.0022, "step": 286680 }, { "epoch": 68.82, "learning_rate": 2.658384309980721e-05, "loss": 0.0018, "step": 286690 }, { "epoch": 68.83, "learning_rate": 2.6580671568507032e-05, "loss": 0.0019, "step": 286700 }, { "epoch": 68.83, "learning_rate": 2.6577500157910263e-05, "loss": 0.0019, "step": 286710 }, { "epoch": 68.83, "learning_rate": 2.6574328868033226e-05, "loss": 0.0016, "step": 286720 }, { "epoch": 68.83, "learning_rate": 2.6571157698892322e-05, "loss": 0.0019, "step": 286730 }, { "epoch": 68.84, "learning_rate": 2.656798665050385e-05, "loss": 0.0016, "step": 286740 }, { "epoch": 68.84, "learning_rate": 2.656481572288419e-05, "loss": 0.0017, "step": 286750 }, { "epoch": 68.84, "learning_rate": 2.6561644916049643e-05, "loss": 0.0019, "step": 286760 }, { "epoch": 68.84, "learning_rate": 2.6558474230016593e-05, "loss": 0.0018, "step": 286770 }, { "epoch": 68.84, "learning_rate": 2.6555303664801345e-05, "loss": 0.0017, "step": 286780 }, { "epoch": 68.85, "learning_rate": 2.6552133220420283e-05, "loss": 0.0015, "step": 286790 }, { "epoch": 68.85, "learning_rate": 2.654896289688972e-05, "loss": 0.0017, "step": 286800 }, { "epoch": 68.85, "learning_rate": 2.6545792694225968e-05, "loss": 0.0017, "step": 286810 }, { "epoch": 68.85, "learning_rate": 2.6542622612445423e-05, "loss": 0.0017, "step": 286820 }, { "epoch": 68.86, "learning_rate": 2.6539452651564378e-05, "loss": 0.0016, "step": 286830 }, { "epoch": 68.86, "learning_rate": 2.653628281159921e-05, "loss": 0.0018, "step": 286840 }, { "epoch": 68.86, "learning_rate": 2.653311309256622e-05, "loss": 0.002, "step": 286850 }, { "epoch": 68.86, "learning_rate": 2.6529943494481774e-05, "loss": 0.0018, "step": 286860 }, { "epoch": 68.87, "learning_rate": 2.65267740173622e-05, "loss": 0.0041, "step": 286870 }, { "epoch": 68.87, "learning_rate": 2.652360466122381e-05, "loss": 0.0024, "step": 286880 }, { "epoch": 68.87, "learning_rate": 2.6520435426082973e-05, "loss": 0.0017, "step": 286890 }, { "epoch": 68.87, "learning_rate": 2.651726631195599e-05, "loss": 0.0015, "step": 286900 }, { "epoch": 68.87, "learning_rate": 2.6514097318859233e-05, "loss": 0.0022, "step": 286910 }, { "epoch": 68.88, "learning_rate": 2.6510928446808996e-05, "loss": 0.0033, "step": 286920 }, { "epoch": 68.88, "learning_rate": 2.650775969582165e-05, "loss": 0.0016, "step": 286930 }, { "epoch": 68.88, "learning_rate": 2.6504591065913487e-05, "loss": 0.0019, "step": 286940 }, { "epoch": 68.88, "learning_rate": 2.6501422557100874e-05, "loss": 0.0016, "step": 286950 }, { "epoch": 68.89, "learning_rate": 2.6498254169400112e-05, "loss": 0.0017, "step": 286960 }, { "epoch": 68.89, "learning_rate": 2.6495085902827545e-05, "loss": 0.0018, "step": 286970 }, { "epoch": 68.89, "learning_rate": 2.6491917757399514e-05, "loss": 0.0017, "step": 286980 }, { "epoch": 68.89, "learning_rate": 2.6488749733132322e-05, "loss": 0.0015, "step": 286990 }, { "epoch": 68.89, "learning_rate": 2.6485581830042328e-05, "loss": 0.0158, "step": 287000 }, { "epoch": 68.9, "learning_rate": 2.648241404814584e-05, "loss": 0.0017, "step": 287010 }, { "epoch": 68.9, "learning_rate": 2.6479246387459167e-05, "loss": 0.0017, "step": 287020 }, { "epoch": 68.9, "learning_rate": 2.6476078847998675e-05, "loss": 0.0024, "step": 287030 }, { "epoch": 68.9, "learning_rate": 2.647291142978065e-05, "loss": 0.0016, "step": 287040 }, { "epoch": 68.91, "learning_rate": 2.646974413282146e-05, "loss": 0.0018, "step": 287050 }, { "epoch": 68.91, "learning_rate": 2.646657695713738e-05, "loss": 0.002, "step": 287060 }, { "epoch": 68.91, "learning_rate": 2.646340990274478e-05, "loss": 0.0018, "step": 287070 }, { "epoch": 68.91, "learning_rate": 2.6460242969659966e-05, "loss": 0.002, "step": 287080 }, { "epoch": 68.92, "learning_rate": 2.645707615789923e-05, "loss": 0.0018, "step": 287090 }, { "epoch": 68.92, "learning_rate": 2.6453909467478943e-05, "loss": 0.0016, "step": 287100 }, { "epoch": 68.92, "learning_rate": 2.645074289841538e-05, "loss": 0.0018, "step": 287110 }, { "epoch": 68.92, "learning_rate": 2.6447576450724915e-05, "loss": 0.0015, "step": 287120 }, { "epoch": 68.92, "learning_rate": 2.644441012442381e-05, "loss": 0.0018, "step": 287130 }, { "epoch": 68.93, "learning_rate": 2.6441243919528435e-05, "loss": 0.0016, "step": 287140 }, { "epoch": 68.93, "learning_rate": 2.6438077836055086e-05, "loss": 0.0015, "step": 287150 }, { "epoch": 68.93, "learning_rate": 2.6434911874020057e-05, "loss": 0.0023, "step": 287160 }, { "epoch": 68.93, "learning_rate": 2.6431746033439714e-05, "loss": 0.0016, "step": 287170 }, { "epoch": 68.94, "learning_rate": 2.6428580314330327e-05, "loss": 0.0018, "step": 287180 }, { "epoch": 68.94, "learning_rate": 2.6425414716708252e-05, "loss": 0.0016, "step": 287190 }, { "epoch": 68.94, "learning_rate": 2.6422249240589768e-05, "loss": 0.0016, "step": 287200 }, { "epoch": 68.94, "learning_rate": 2.641908388599123e-05, "loss": 0.0015, "step": 287210 }, { "epoch": 68.95, "learning_rate": 2.641591865292893e-05, "loss": 0.0017, "step": 287220 }, { "epoch": 68.95, "learning_rate": 2.641275354141916e-05, "loss": 0.0016, "step": 287230 }, { "epoch": 68.95, "learning_rate": 2.640958855147826e-05, "loss": 0.0018, "step": 287240 }, { "epoch": 69.0, "learning_rate": 2.640642368312255e-05, "loss": 0.0017, "step": 287250 }, { "epoch": 69.0, "learning_rate": 2.640325893636832e-05, "loss": 0.0015, "step": 287260 }, { "epoch": 69.01, "learning_rate": 2.6400094311231904e-05, "loss": 0.0017, "step": 287270 }, { "epoch": 69.01, "learning_rate": 2.6396929807729582e-05, "loss": 0.0016, "step": 287280 }, { "epoch": 69.01, "learning_rate": 2.63937654258777e-05, "loss": 0.0013, "step": 287290 }, { "epoch": 69.01, "learning_rate": 2.639060116569253e-05, "loss": 0.0017, "step": 287300 }, { "epoch": 69.01, "learning_rate": 2.638743702719041e-05, "loss": 0.0015, "step": 287310 }, { "epoch": 69.02, "learning_rate": 2.638427301038763e-05, "loss": 0.0015, "step": 287320 }, { "epoch": 69.02, "learning_rate": 2.638110911530052e-05, "loss": 0.0034, "step": 287330 }, { "epoch": 69.02, "learning_rate": 2.6377945341945344e-05, "loss": 0.0021, "step": 287340 }, { "epoch": 69.02, "learning_rate": 2.6374781690338457e-05, "loss": 0.0018, "step": 287350 }, { "epoch": 69.03, "learning_rate": 2.6371618160496148e-05, "loss": 0.0018, "step": 287360 }, { "epoch": 69.03, "learning_rate": 2.6368454752434696e-05, "loss": 0.0054, "step": 287370 }, { "epoch": 69.03, "learning_rate": 2.6365291466170446e-05, "loss": 0.0022, "step": 287380 }, { "epoch": 69.03, "learning_rate": 2.6362128301719657e-05, "loss": 0.0019, "step": 287390 }, { "epoch": 69.03, "learning_rate": 2.635896525909868e-05, "loss": 0.0017, "step": 287400 }, { "epoch": 69.04, "learning_rate": 2.6355802338323775e-05, "loss": 0.0036, "step": 287410 }, { "epoch": 69.04, "learning_rate": 2.6352639539411278e-05, "loss": 0.0016, "step": 287420 }, { "epoch": 69.04, "learning_rate": 2.6349476862377474e-05, "loss": 0.0016, "step": 287430 }, { "epoch": 69.04, "learning_rate": 2.634631430723865e-05, "loss": 0.0016, "step": 287440 }, { "epoch": 69.05, "learning_rate": 2.6343151874011134e-05, "loss": 0.0018, "step": 287450 }, { "epoch": 69.05, "learning_rate": 2.6339989562711192e-05, "loss": 0.0017, "step": 287460 }, { "epoch": 69.05, "learning_rate": 2.6336827373355168e-05, "loss": 0.0016, "step": 287470 }, { "epoch": 69.05, "learning_rate": 2.6333665305959304e-05, "loss": 0.0016, "step": 287480 }, { "epoch": 69.06, "learning_rate": 2.633050336053995e-05, "loss": 0.0016, "step": 287490 }, { "epoch": 69.06, "learning_rate": 2.632734153711338e-05, "loss": 0.0013, "step": 287500 }, { "epoch": 69.06, "learning_rate": 2.6324179835695872e-05, "loss": 0.0015, "step": 287510 }, { "epoch": 69.06, "learning_rate": 2.6321018256303754e-05, "loss": 0.0015, "step": 287520 }, { "epoch": 69.06, "learning_rate": 2.6317856798953288e-05, "loss": 0.0013, "step": 287530 }, { "epoch": 69.07, "learning_rate": 2.6314695463660787e-05, "loss": 0.0018, "step": 287540 }, { "epoch": 69.07, "learning_rate": 2.631153425044257e-05, "loss": 0.0015, "step": 287550 }, { "epoch": 69.07, "learning_rate": 2.6308373159314876e-05, "loss": 0.0016, "step": 287560 }, { "epoch": 69.07, "learning_rate": 2.630521219029405e-05, "loss": 0.0016, "step": 287570 }, { "epoch": 69.08, "learning_rate": 2.6302051343396328e-05, "loss": 0.0016, "step": 287580 }, { "epoch": 69.08, "learning_rate": 2.629889061863806e-05, "loss": 0.0024, "step": 287590 }, { "epoch": 69.08, "learning_rate": 2.629573001603548e-05, "loss": 0.0015, "step": 287600 }, { "epoch": 69.08, "learning_rate": 2.6292569535604938e-05, "loss": 0.0017, "step": 287610 }, { "epoch": 69.09, "learning_rate": 2.6289409177362662e-05, "loss": 0.0017, "step": 287620 }, { "epoch": 69.09, "learning_rate": 2.6286248941324987e-05, "loss": 0.0015, "step": 287630 }, { "epoch": 69.09, "learning_rate": 2.6283088827508173e-05, "loss": 0.0017, "step": 287640 }, { "epoch": 69.09, "learning_rate": 2.627992883592853e-05, "loss": 0.0016, "step": 287650 }, { "epoch": 69.09, "learning_rate": 2.6276768966602332e-05, "loss": 0.0017, "step": 287660 }, { "epoch": 69.1, "learning_rate": 2.6273609219545847e-05, "loss": 0.0016, "step": 287670 }, { "epoch": 69.1, "learning_rate": 2.6270449594775405e-05, "loss": 0.0018, "step": 287680 }, { "epoch": 69.1, "learning_rate": 2.6267290092307233e-05, "loss": 0.0017, "step": 287690 }, { "epoch": 69.1, "learning_rate": 2.626413071215767e-05, "loss": 0.0015, "step": 287700 }, { "epoch": 69.11, "learning_rate": 2.6260971454342952e-05, "loss": 0.0016, "step": 287710 }, { "epoch": 69.11, "learning_rate": 2.6257812318879415e-05, "loss": 0.0045, "step": 287720 }, { "epoch": 69.11, "learning_rate": 2.6254653305783305e-05, "loss": 0.0019, "step": 287730 }, { "epoch": 69.11, "learning_rate": 2.6251494415070892e-05, "loss": 0.0016, "step": 287740 }, { "epoch": 69.11, "learning_rate": 2.624833564675849e-05, "loss": 0.0019, "step": 287750 }, { "epoch": 69.12, "learning_rate": 2.6245177000862352e-05, "loss": 0.0017, "step": 287760 }, { "epoch": 69.12, "learning_rate": 2.6242018477398794e-05, "loss": 0.0016, "step": 287770 }, { "epoch": 69.12, "learning_rate": 2.6238860076384043e-05, "loss": 0.0016, "step": 287780 }, { "epoch": 69.12, "learning_rate": 2.6235701797834434e-05, "loss": 0.0018, "step": 287790 }, { "epoch": 69.13, "learning_rate": 2.6232543641766206e-05, "loss": 0.009, "step": 287800 }, { "epoch": 69.13, "learning_rate": 2.6229385608195632e-05, "loss": 0.0026, "step": 287810 }, { "epoch": 69.13, "learning_rate": 2.622622769713903e-05, "loss": 0.003, "step": 287820 }, { "epoch": 69.13, "learning_rate": 2.622306990861262e-05, "loss": 0.0018, "step": 287830 }, { "epoch": 69.14, "learning_rate": 2.6219912242632726e-05, "loss": 0.0017, "step": 287840 }, { "epoch": 69.14, "learning_rate": 2.6216754699215585e-05, "loss": 0.0016, "step": 287850 }, { "epoch": 69.14, "learning_rate": 2.6213597278377488e-05, "loss": 0.0017, "step": 287860 }, { "epoch": 69.14, "learning_rate": 2.621043998013473e-05, "loss": 0.0018, "step": 287870 }, { "epoch": 69.14, "learning_rate": 2.6207282804503548e-05, "loss": 0.0018, "step": 287880 }, { "epoch": 69.15, "learning_rate": 2.6204125751500242e-05, "loss": 0.0143, "step": 287890 }, { "epoch": 69.15, "learning_rate": 2.620096882114106e-05, "loss": 0.0016, "step": 287900 }, { "epoch": 69.15, "learning_rate": 2.6197812013442296e-05, "loss": 0.0017, "step": 287910 }, { "epoch": 69.15, "learning_rate": 2.6194655328420192e-05, "loss": 0.0042, "step": 287920 }, { "epoch": 69.16, "learning_rate": 2.619149876609105e-05, "loss": 0.0016, "step": 287930 }, { "epoch": 69.16, "learning_rate": 2.6188342326471122e-05, "loss": 0.0018, "step": 287940 }, { "epoch": 69.16, "learning_rate": 2.6185186009576656e-05, "loss": 0.0016, "step": 287950 }, { "epoch": 69.16, "learning_rate": 2.618202981542397e-05, "loss": 0.0014, "step": 287960 }, { "epoch": 69.17, "learning_rate": 2.617887374402927e-05, "loss": 0.0016, "step": 287970 }, { "epoch": 69.17, "learning_rate": 2.6175717795408878e-05, "loss": 0.0016, "step": 287980 }, { "epoch": 69.17, "learning_rate": 2.6172561969579012e-05, "loss": 0.0016, "step": 287990 }, { "epoch": 69.17, "learning_rate": 2.6169406266555983e-05, "loss": 0.002, "step": 288000 }, { "epoch": 69.17, "learning_rate": 2.6166250686356042e-05, "loss": 0.0018, "step": 288010 }, { "epoch": 69.18, "learning_rate": 2.6163095228995415e-05, "loss": 0.0019, "step": 288020 }, { "epoch": 69.18, "learning_rate": 2.6159939894490414e-05, "loss": 0.002, "step": 288030 }, { "epoch": 69.18, "learning_rate": 2.6156784682857267e-05, "loss": 0.0032, "step": 288040 }, { "epoch": 69.18, "learning_rate": 2.6153629594112273e-05, "loss": 0.0034, "step": 288050 }, { "epoch": 69.19, "learning_rate": 2.6150474628271644e-05, "loss": 0.0022, "step": 288060 }, { "epoch": 69.19, "learning_rate": 2.6147319785351688e-05, "loss": 0.0032, "step": 288070 }, { "epoch": 69.19, "learning_rate": 2.6144165065368653e-05, "loss": 0.0021, "step": 288080 }, { "epoch": 69.19, "learning_rate": 2.614101046833876e-05, "loss": 0.0014, "step": 288090 }, { "epoch": 69.19, "learning_rate": 2.6137855994278325e-05, "loss": 0.0027, "step": 288100 }, { "epoch": 69.2, "learning_rate": 2.6134701643203564e-05, "loss": 0.0017, "step": 288110 }, { "epoch": 69.2, "learning_rate": 2.6131547415130763e-05, "loss": 0.0018, "step": 288120 }, { "epoch": 69.2, "learning_rate": 2.612839331007615e-05, "loss": 0.0014, "step": 288130 }, { "epoch": 69.2, "learning_rate": 2.612523932805601e-05, "loss": 0.0016, "step": 288140 }, { "epoch": 69.21, "learning_rate": 2.6122085469086576e-05, "loss": 0.002, "step": 288150 }, { "epoch": 69.21, "learning_rate": 2.6118931733184126e-05, "loss": 0.0016, "step": 288160 }, { "epoch": 69.21, "learning_rate": 2.6115778120364888e-05, "loss": 0.0019, "step": 288170 }, { "epoch": 69.21, "learning_rate": 2.611262463064512e-05, "loss": 0.0017, "step": 288180 }, { "epoch": 69.22, "learning_rate": 2.6109471264041114e-05, "loss": 0.0019, "step": 288190 }, { "epoch": 69.22, "learning_rate": 2.6106318020569064e-05, "loss": 0.0016, "step": 288200 }, { "epoch": 69.22, "learning_rate": 2.610316490024528e-05, "loss": 0.0016, "step": 288210 }, { "epoch": 69.22, "learning_rate": 2.6100011903085973e-05, "loss": 0.0016, "step": 288220 }, { "epoch": 69.22, "learning_rate": 2.6096859029107395e-05, "loss": 0.0016, "step": 288230 }, { "epoch": 69.23, "learning_rate": 2.6093706278325825e-05, "loss": 0.0028, "step": 288240 }, { "epoch": 69.23, "learning_rate": 2.6090553650757465e-05, "loss": 0.0016, "step": 288250 }, { "epoch": 69.23, "learning_rate": 2.6087401146418616e-05, "loss": 0.0018, "step": 288260 }, { "epoch": 69.23, "learning_rate": 2.608424876532548e-05, "loss": 0.0022, "step": 288270 }, { "epoch": 69.24, "learning_rate": 2.6081096507494345e-05, "loss": 0.0017, "step": 288280 }, { "epoch": 69.24, "learning_rate": 2.6077944372941444e-05, "loss": 0.0016, "step": 288290 }, { "epoch": 69.24, "learning_rate": 2.607479236168299e-05, "loss": 0.0018, "step": 288300 }, { "epoch": 69.24, "learning_rate": 2.607164047373528e-05, "loss": 0.003, "step": 288310 }, { "epoch": 69.25, "learning_rate": 2.6068488709114513e-05, "loss": 0.0019, "step": 288320 }, { "epoch": 69.25, "learning_rate": 2.6065337067836982e-05, "loss": 0.0019, "step": 288330 }, { "epoch": 69.25, "learning_rate": 2.6062185549918873e-05, "loss": 0.0277, "step": 288340 }, { "epoch": 69.25, "learning_rate": 2.6059034155376483e-05, "loss": 0.0016, "step": 288350 }, { "epoch": 69.25, "learning_rate": 2.6055882884226035e-05, "loss": 0.0023, "step": 288360 }, { "epoch": 69.26, "learning_rate": 2.605273173648375e-05, "loss": 0.0017, "step": 288370 }, { "epoch": 69.26, "learning_rate": 2.60495807121659e-05, "loss": 0.0017, "step": 288380 }, { "epoch": 69.26, "learning_rate": 2.6046429811288693e-05, "loss": 0.0017, "step": 288390 }, { "epoch": 69.26, "learning_rate": 2.6043279033868407e-05, "loss": 0.0018, "step": 288400 }, { "epoch": 69.27, "learning_rate": 2.6040128379921234e-05, "loss": 0.0016, "step": 288410 }, { "epoch": 69.27, "learning_rate": 2.6036977849463466e-05, "loss": 0.0016, "step": 288420 }, { "epoch": 69.27, "learning_rate": 2.6033827442511294e-05, "loss": 0.0024, "step": 288430 }, { "epoch": 69.27, "learning_rate": 2.6030677159080995e-05, "loss": 0.0015, "step": 288440 }, { "epoch": 69.27, "learning_rate": 2.6027526999188768e-05, "loss": 0.0016, "step": 288450 }, { "epoch": 69.28, "learning_rate": 2.6024376962850888e-05, "loss": 0.0019, "step": 288460 }, { "epoch": 69.28, "learning_rate": 2.6021227050083552e-05, "loss": 0.0019, "step": 288470 }, { "epoch": 69.28, "learning_rate": 2.601807726090303e-05, "loss": 0.0016, "step": 288480 }, { "epoch": 69.28, "learning_rate": 2.601492759532551e-05, "loss": 0.0018, "step": 288490 }, { "epoch": 69.29, "learning_rate": 2.6011778053367264e-05, "loss": 0.0015, "step": 288500 }, { "epoch": 69.29, "learning_rate": 2.600862863504453e-05, "loss": 0.0015, "step": 288510 }, { "epoch": 69.29, "learning_rate": 2.600547934037352e-05, "loss": 0.0016, "step": 288520 }, { "epoch": 69.29, "learning_rate": 2.600233016937046e-05, "loss": 0.0015, "step": 288530 }, { "epoch": 69.3, "learning_rate": 2.5999181122051608e-05, "loss": 0.0049, "step": 288540 }, { "epoch": 69.3, "learning_rate": 2.5996032198433152e-05, "loss": 0.0015, "step": 288550 }, { "epoch": 69.3, "learning_rate": 2.599288339853137e-05, "loss": 0.0018, "step": 288560 }, { "epoch": 69.3, "learning_rate": 2.5989734722362446e-05, "loss": 0.0017, "step": 288570 }, { "epoch": 69.3, "learning_rate": 2.598658616994265e-05, "loss": 0.0026, "step": 288580 }, { "epoch": 69.31, "learning_rate": 2.5983437741288196e-05, "loss": 0.0066, "step": 288590 }, { "epoch": 69.31, "learning_rate": 2.5980289436415277e-05, "loss": 0.0017, "step": 288600 }, { "epoch": 69.31, "learning_rate": 2.597714125534017e-05, "loss": 0.0017, "step": 288610 }, { "epoch": 69.31, "learning_rate": 2.597399319807906e-05, "loss": 0.0016, "step": 288620 }, { "epoch": 69.32, "learning_rate": 2.5970845264648202e-05, "loss": 0.0015, "step": 288630 }, { "epoch": 69.32, "learning_rate": 2.59676974550638e-05, "loss": 0.0017, "step": 288640 }, { "epoch": 69.32, "learning_rate": 2.5964549769342095e-05, "loss": 0.0019, "step": 288650 }, { "epoch": 69.32, "learning_rate": 2.596140220749931e-05, "loss": 0.0015, "step": 288660 }, { "epoch": 69.33, "learning_rate": 2.5958254769551638e-05, "loss": 0.0018, "step": 288670 }, { "epoch": 69.33, "learning_rate": 2.5955107455515336e-05, "loss": 0.0018, "step": 288680 }, { "epoch": 69.33, "learning_rate": 2.5951960265406595e-05, "loss": 0.0018, "step": 288690 }, { "epoch": 69.33, "learning_rate": 2.5948813199241672e-05, "loss": 0.0023, "step": 288700 }, { "epoch": 69.33, "learning_rate": 2.5945666257036744e-05, "loss": 0.0018, "step": 288710 }, { "epoch": 69.34, "learning_rate": 2.5942519438808078e-05, "loss": 0.0018, "step": 288720 }, { "epoch": 69.34, "learning_rate": 2.5939372744571862e-05, "loss": 0.0021, "step": 288730 }, { "epoch": 69.34, "learning_rate": 2.5936226174344302e-05, "loss": 0.0024, "step": 288740 }, { "epoch": 69.34, "learning_rate": 2.5933079728141634e-05, "loss": 0.0016, "step": 288750 }, { "epoch": 69.35, "learning_rate": 2.5929933405980094e-05, "loss": 0.0015, "step": 288760 }, { "epoch": 69.35, "learning_rate": 2.5926787207875856e-05, "loss": 0.0021, "step": 288770 }, { "epoch": 69.35, "learning_rate": 2.5923641133845188e-05, "loss": 0.0017, "step": 288780 }, { "epoch": 69.35, "learning_rate": 2.5920495183904246e-05, "loss": 0.0019, "step": 288790 }, { "epoch": 69.35, "learning_rate": 2.591734935806929e-05, "loss": 0.004, "step": 288800 }, { "epoch": 69.36, "learning_rate": 2.5914203656356505e-05, "loss": 0.0015, "step": 288810 }, { "epoch": 69.36, "learning_rate": 2.5911058078782136e-05, "loss": 0.0015, "step": 288820 }, { "epoch": 69.36, "learning_rate": 2.590791262536235e-05, "loss": 0.0016, "step": 288830 }, { "epoch": 69.36, "learning_rate": 2.5904767296113404e-05, "loss": 0.0015, "step": 288840 }, { "epoch": 69.37, "learning_rate": 2.590162209105147e-05, "loss": 0.0086, "step": 288850 }, { "epoch": 69.37, "learning_rate": 2.5898477010192795e-05, "loss": 0.0018, "step": 288860 }, { "epoch": 69.37, "learning_rate": 2.5895332053553577e-05, "loss": 0.0016, "step": 288870 }, { "epoch": 69.37, "learning_rate": 2.5892187221149993e-05, "loss": 0.0023, "step": 288880 }, { "epoch": 69.38, "learning_rate": 2.5889042512998295e-05, "loss": 0.0017, "step": 288890 }, { "epoch": 69.38, "learning_rate": 2.5885897929114662e-05, "loss": 0.0022, "step": 288900 }, { "epoch": 69.38, "learning_rate": 2.588275346951533e-05, "loss": 0.0018, "step": 288910 }, { "epoch": 69.38, "learning_rate": 2.5879609134216463e-05, "loss": 0.0017, "step": 288920 }, { "epoch": 69.38, "learning_rate": 2.5876464923234322e-05, "loss": 0.0016, "step": 288930 }, { "epoch": 69.39, "learning_rate": 2.587332083658507e-05, "loss": 0.0018, "step": 288940 }, { "epoch": 69.39, "learning_rate": 2.5870176874284914e-05, "loss": 0.0017, "step": 288950 }, { "epoch": 69.39, "learning_rate": 2.5867033036350085e-05, "loss": 0.0015, "step": 288960 }, { "epoch": 69.39, "learning_rate": 2.5863889322796746e-05, "loss": 0.0017, "step": 288970 }, { "epoch": 69.4, "learning_rate": 2.5860745733641146e-05, "loss": 0.0015, "step": 288980 }, { "epoch": 69.4, "learning_rate": 2.585760226889945e-05, "loss": 0.0017, "step": 288990 }, { "epoch": 69.4, "learning_rate": 2.5854458928587888e-05, "loss": 0.0016, "step": 289000 }, { "epoch": 69.4, "learning_rate": 2.5851315712722645e-05, "loss": 0.0017, "step": 289010 }, { "epoch": 69.41, "learning_rate": 2.5848172621319898e-05, "loss": 0.0172, "step": 289020 }, { "epoch": 69.41, "learning_rate": 2.5845029654395903e-05, "loss": 0.0017, "step": 289030 }, { "epoch": 69.41, "learning_rate": 2.58418868119668e-05, "loss": 0.0018, "step": 289040 }, { "epoch": 69.41, "learning_rate": 2.583874409404884e-05, "loss": 0.0025, "step": 289050 }, { "epoch": 69.41, "learning_rate": 2.583560150065817e-05, "loss": 0.0015, "step": 289060 }, { "epoch": 69.42, "learning_rate": 2.583245903181101e-05, "loss": 0.0017, "step": 289070 }, { "epoch": 69.42, "learning_rate": 2.5829316687523586e-05, "loss": 0.0018, "step": 289080 }, { "epoch": 69.42, "learning_rate": 2.5826174467812037e-05, "loss": 0.0016, "step": 289090 }, { "epoch": 69.42, "learning_rate": 2.5823032372692614e-05, "loss": 0.0015, "step": 289100 }, { "epoch": 69.43, "learning_rate": 2.5819890402181458e-05, "loss": 0.0014, "step": 289110 }, { "epoch": 69.43, "learning_rate": 2.581674855629481e-05, "loss": 0.0015, "step": 289120 }, { "epoch": 69.43, "learning_rate": 2.5813606835048826e-05, "loss": 0.0014, "step": 289130 }, { "epoch": 69.43, "learning_rate": 2.581046523845973e-05, "loss": 0.0018, "step": 289140 }, { "epoch": 69.43, "learning_rate": 2.58073237665437e-05, "loss": 0.0015, "step": 289150 }, { "epoch": 69.44, "learning_rate": 2.5804182419316908e-05, "loss": 0.0016, "step": 289160 }, { "epoch": 69.44, "learning_rate": 2.5801041196795584e-05, "loss": 0.0016, "step": 289170 }, { "epoch": 69.44, "learning_rate": 2.579790009899587e-05, "loss": 0.0022, "step": 289180 }, { "epoch": 69.44, "learning_rate": 2.5794759125934e-05, "loss": 0.0016, "step": 289190 }, { "epoch": 69.45, "learning_rate": 2.579161827762613e-05, "loss": 0.0017, "step": 289200 }, { "epoch": 69.45, "learning_rate": 2.5788477554088475e-05, "loss": 0.0015, "step": 289210 }, { "epoch": 69.45, "learning_rate": 2.5785336955337196e-05, "loss": 0.0022, "step": 289220 }, { "epoch": 69.45, "learning_rate": 2.578219648138851e-05, "loss": 0.0018, "step": 289230 }, { "epoch": 69.46, "learning_rate": 2.5779056132258582e-05, "loss": 0.0014, "step": 289240 }, { "epoch": 69.46, "learning_rate": 2.5775915907963587e-05, "loss": 0.0018, "step": 289250 }, { "epoch": 69.46, "learning_rate": 2.5772775808519745e-05, "loss": 0.003, "step": 289260 }, { "epoch": 69.46, "learning_rate": 2.5769635833943195e-05, "loss": 0.0018, "step": 289270 }, { "epoch": 69.46, "learning_rate": 2.576649598425016e-05, "loss": 0.0014, "step": 289280 }, { "epoch": 69.47, "learning_rate": 2.5763356259456794e-05, "loss": 0.0015, "step": 289290 }, { "epoch": 69.47, "learning_rate": 2.5760216659579313e-05, "loss": 0.0016, "step": 289300 }, { "epoch": 69.47, "learning_rate": 2.575707718463387e-05, "loss": 0.0017, "step": 289310 }, { "epoch": 69.47, "learning_rate": 2.5753937834636643e-05, "loss": 0.0017, "step": 289320 }, { "epoch": 69.48, "learning_rate": 2.5750798609603844e-05, "loss": 0.0017, "step": 289330 }, { "epoch": 69.48, "learning_rate": 2.5747659509551604e-05, "loss": 0.0052, "step": 289340 }, { "epoch": 69.48, "learning_rate": 2.5744520534496152e-05, "loss": 0.002, "step": 289350 }, { "epoch": 69.48, "learning_rate": 2.5741381684453625e-05, "loss": 0.0015, "step": 289360 }, { "epoch": 69.49, "learning_rate": 2.5738242959440218e-05, "loss": 0.0017, "step": 289370 }, { "epoch": 69.49, "learning_rate": 2.5735104359472134e-05, "loss": 0.002, "step": 289380 }, { "epoch": 69.49, "learning_rate": 2.57319658845655e-05, "loss": 0.0016, "step": 289390 }, { "epoch": 69.49, "learning_rate": 2.572882753473654e-05, "loss": 0.0018, "step": 289400 }, { "epoch": 69.49, "learning_rate": 2.5725689310001384e-05, "loss": 0.0057, "step": 289410 }, { "epoch": 69.5, "learning_rate": 2.5722551210376244e-05, "loss": 0.0024, "step": 289420 }, { "epoch": 69.5, "learning_rate": 2.5719413235877265e-05, "loss": 0.0017, "step": 289430 }, { "epoch": 69.5, "learning_rate": 2.571627538652065e-05, "loss": 0.0017, "step": 289440 }, { "epoch": 69.5, "learning_rate": 2.5713137662322557e-05, "loss": 0.0014, "step": 289450 }, { "epoch": 69.51, "learning_rate": 2.5710000063299134e-05, "loss": 0.0019, "step": 289460 }, { "epoch": 69.51, "learning_rate": 2.5706862589466595e-05, "loss": 0.0016, "step": 289470 }, { "epoch": 69.51, "learning_rate": 2.570372524084107e-05, "loss": 0.0015, "step": 289480 }, { "epoch": 69.51, "learning_rate": 2.5700588017438765e-05, "loss": 0.0017, "step": 289490 }, { "epoch": 69.51, "learning_rate": 2.569745091927581e-05, "loss": 0.0016, "step": 289500 }, { "epoch": 69.52, "learning_rate": 2.569431394636842e-05, "loss": 0.0017, "step": 289510 }, { "epoch": 69.52, "learning_rate": 2.5691177098732738e-05, "loss": 0.0019, "step": 289520 }, { "epoch": 69.52, "learning_rate": 2.5688040376384916e-05, "loss": 0.002, "step": 289530 }, { "epoch": 69.52, "learning_rate": 2.568490377934115e-05, "loss": 0.0028, "step": 289540 }, { "epoch": 69.53, "learning_rate": 2.5681767307617577e-05, "loss": 0.002, "step": 289550 }, { "epoch": 69.53, "learning_rate": 2.5678630961230397e-05, "loss": 0.0016, "step": 289560 }, { "epoch": 69.53, "learning_rate": 2.5675494740195745e-05, "loss": 0.0019, "step": 289570 }, { "epoch": 69.53, "learning_rate": 2.5672358644529803e-05, "loss": 0.0021, "step": 289580 }, { "epoch": 69.54, "learning_rate": 2.5669222674248738e-05, "loss": 0.0018, "step": 289590 }, { "epoch": 69.54, "learning_rate": 2.5666086829368678e-05, "loss": 0.0017, "step": 289600 }, { "epoch": 69.54, "learning_rate": 2.566295110990583e-05, "loss": 0.0017, "step": 289610 }, { "epoch": 69.54, "learning_rate": 2.5659815515876318e-05, "loss": 0.004, "step": 289620 }, { "epoch": 69.54, "learning_rate": 2.5656680047296338e-05, "loss": 0.0027, "step": 289630 }, { "epoch": 69.55, "learning_rate": 2.5653544704182014e-05, "loss": 0.0018, "step": 289640 }, { "epoch": 69.55, "learning_rate": 2.5650409486549544e-05, "loss": 0.0024, "step": 289650 }, { "epoch": 69.55, "learning_rate": 2.5647274394415044e-05, "loss": 0.0017, "step": 289660 }, { "epoch": 69.55, "learning_rate": 2.5644139427794723e-05, "loss": 0.0019, "step": 289670 }, { "epoch": 69.56, "learning_rate": 2.5641004586704688e-05, "loss": 0.0023, "step": 289680 }, { "epoch": 69.56, "learning_rate": 2.5637869871161114e-05, "loss": 0.0019, "step": 289690 }, { "epoch": 69.56, "learning_rate": 2.5634735281180182e-05, "loss": 0.0021, "step": 289700 }, { "epoch": 69.56, "learning_rate": 2.563160081677801e-05, "loss": 0.0022, "step": 289710 }, { "epoch": 69.57, "learning_rate": 2.5628466477970793e-05, "loss": 0.0017, "step": 289720 }, { "epoch": 69.57, "learning_rate": 2.5625332264774664e-05, "loss": 0.0017, "step": 289730 }, { "epoch": 69.57, "learning_rate": 2.562219817720576e-05, "loss": 0.0022, "step": 289740 }, { "epoch": 69.57, "learning_rate": 2.5619064215280262e-05, "loss": 0.0033, "step": 289750 }, { "epoch": 69.57, "learning_rate": 2.5615930379014296e-05, "loss": 0.0016, "step": 289760 }, { "epoch": 69.58, "learning_rate": 2.5612796668424045e-05, "loss": 0.0018, "step": 289770 }, { "epoch": 69.58, "learning_rate": 2.5609663083525626e-05, "loss": 0.002, "step": 289780 }, { "epoch": 69.58, "learning_rate": 2.5606529624335225e-05, "loss": 0.0019, "step": 289790 }, { "epoch": 69.58, "learning_rate": 2.5603396290868975e-05, "loss": 0.002, "step": 289800 }, { "epoch": 69.59, "learning_rate": 2.5600263083143004e-05, "loss": 0.0017, "step": 289810 }, { "epoch": 69.59, "learning_rate": 2.5597130001173508e-05, "loss": 0.0018, "step": 289820 }, { "epoch": 69.59, "learning_rate": 2.559399704497658e-05, "loss": 0.0019, "step": 289830 }, { "epoch": 69.59, "learning_rate": 2.5590864214568415e-05, "loss": 0.0019, "step": 289840 }, { "epoch": 69.59, "learning_rate": 2.5587731509965124e-05, "loss": 0.0017, "step": 289850 }, { "epoch": 69.6, "learning_rate": 2.558459893118289e-05, "loss": 0.0029, "step": 289860 }, { "epoch": 69.6, "learning_rate": 2.5581466478237837e-05, "loss": 0.002, "step": 289870 }, { "epoch": 69.6, "learning_rate": 2.5578334151146082e-05, "loss": 0.0018, "step": 289880 }, { "epoch": 69.6, "learning_rate": 2.5575201949923823e-05, "loss": 0.0037, "step": 289890 }, { "epoch": 69.61, "learning_rate": 2.5572069874587157e-05, "loss": 0.0041, "step": 289900 }, { "epoch": 69.61, "learning_rate": 2.556893792515227e-05, "loss": 0.0027, "step": 289910 }, { "epoch": 69.61, "learning_rate": 2.5565806101635258e-05, "loss": 0.0019, "step": 289920 }, { "epoch": 69.61, "learning_rate": 2.55626744040523e-05, "loss": 0.0021, "step": 289930 }, { "epoch": 69.62, "learning_rate": 2.5559542832419514e-05, "loss": 0.0024, "step": 289940 }, { "epoch": 69.62, "learning_rate": 2.555641138675306e-05, "loss": 0.0039, "step": 289950 }, { "epoch": 69.62, "learning_rate": 2.555328006706905e-05, "loss": 0.0017, "step": 289960 }, { "epoch": 69.62, "learning_rate": 2.5550148873383657e-05, "loss": 0.0017, "step": 289970 }, { "epoch": 69.62, "learning_rate": 2.554701780571298e-05, "loss": 0.004, "step": 289980 }, { "epoch": 69.63, "learning_rate": 2.5543886864073196e-05, "loss": 0.0029, "step": 289990 }, { "epoch": 69.63, "learning_rate": 2.554075604848041e-05, "loss": 0.0018, "step": 290000 }, { "epoch": 69.63, "learning_rate": 2.5537625358950766e-05, "loss": 0.0025, "step": 290010 }, { "epoch": 69.63, "learning_rate": 2.553449479550043e-05, "loss": 0.0017, "step": 290020 }, { "epoch": 69.64, "learning_rate": 2.553136435814551e-05, "loss": 0.0016, "step": 290030 }, { "epoch": 69.64, "learning_rate": 2.5528234046902122e-05, "loss": 0.0031, "step": 290040 }, { "epoch": 69.64, "learning_rate": 2.5525103861786444e-05, "loss": 0.0022, "step": 290050 }, { "epoch": 69.64, "learning_rate": 2.5521973802814558e-05, "loss": 0.0021, "step": 290060 }, { "epoch": 69.65, "learning_rate": 2.5518843870002653e-05, "loss": 0.0017, "step": 290070 }, { "epoch": 69.65, "learning_rate": 2.55157140633668e-05, "loss": 0.0017, "step": 290080 }, { "epoch": 69.65, "learning_rate": 2.551258438292319e-05, "loss": 0.0023, "step": 290090 }, { "epoch": 69.65, "learning_rate": 2.5509454828687922e-05, "loss": 0.0021, "step": 290100 }, { "epoch": 69.65, "learning_rate": 2.5506325400677113e-05, "loss": 0.0038, "step": 290110 }, { "epoch": 69.66, "learning_rate": 2.550319609890692e-05, "loss": 0.0022, "step": 290120 }, { "epoch": 69.66, "learning_rate": 2.550006692339344e-05, "loss": 0.0021, "step": 290130 }, { "epoch": 69.66, "learning_rate": 2.549693787415285e-05, "loss": 0.0031, "step": 290140 }, { "epoch": 69.66, "learning_rate": 2.5493808951201213e-05, "loss": 0.0027, "step": 290150 }, { "epoch": 69.67, "learning_rate": 2.5490680154554712e-05, "loss": 0.0016, "step": 290160 }, { "epoch": 69.67, "learning_rate": 2.5487551484229456e-05, "loss": 0.0052, "step": 290170 }, { "epoch": 69.67, "learning_rate": 2.5484422940241547e-05, "loss": 0.0021, "step": 290180 }, { "epoch": 69.67, "learning_rate": 2.548129452260714e-05, "loss": 0.002, "step": 290190 }, { "epoch": 69.67, "learning_rate": 2.5478166231342333e-05, "loss": 0.0021, "step": 290200 }, { "epoch": 69.68, "learning_rate": 2.5475038066463274e-05, "loss": 0.0017, "step": 290210 }, { "epoch": 69.68, "learning_rate": 2.5471910027986057e-05, "loss": 0.0019, "step": 290220 }, { "epoch": 69.68, "learning_rate": 2.5468782115926847e-05, "loss": 0.0031, "step": 290230 }, { "epoch": 69.68, "learning_rate": 2.546565433030173e-05, "loss": 0.0017, "step": 290240 }, { "epoch": 69.69, "learning_rate": 2.546252667112682e-05, "loss": 0.0017, "step": 290250 }, { "epoch": 69.69, "learning_rate": 2.545939913841825e-05, "loss": 0.0018, "step": 290260 }, { "epoch": 69.69, "learning_rate": 2.5456271732192166e-05, "loss": 0.0019, "step": 290270 }, { "epoch": 69.69, "learning_rate": 2.545314445246464e-05, "loss": 0.0021, "step": 290280 }, { "epoch": 69.7, "learning_rate": 2.545001729925184e-05, "loss": 0.0023, "step": 290290 }, { "epoch": 69.7, "learning_rate": 2.5446890272569823e-05, "loss": 0.0049, "step": 290300 }, { "epoch": 69.7, "learning_rate": 2.5443763372434763e-05, "loss": 0.002, "step": 290310 }, { "epoch": 69.7, "learning_rate": 2.544063659886274e-05, "loss": 0.0016, "step": 290320 }, { "epoch": 69.7, "learning_rate": 2.5437509951869893e-05, "loss": 0.0031, "step": 290330 }, { "epoch": 69.71, "learning_rate": 2.5434383431472307e-05, "loss": 0.0017, "step": 290340 }, { "epoch": 69.71, "learning_rate": 2.5431257037686136e-05, "loss": 0.0018, "step": 290350 }, { "epoch": 69.71, "learning_rate": 2.5428130770527448e-05, "loss": 0.0019, "step": 290360 }, { "epoch": 69.71, "learning_rate": 2.54250046300124e-05, "loss": 0.0017, "step": 290370 }, { "epoch": 69.72, "learning_rate": 2.5421878616157087e-05, "loss": 0.0017, "step": 290380 }, { "epoch": 69.72, "learning_rate": 2.541875272897759e-05, "loss": 0.0018, "step": 290390 }, { "epoch": 69.72, "learning_rate": 2.5415626968490074e-05, "loss": 0.0028, "step": 290400 }, { "epoch": 69.72, "learning_rate": 2.5412501334710602e-05, "loss": 0.0019, "step": 290410 }, { "epoch": 69.73, "learning_rate": 2.5409375827655323e-05, "loss": 0.002, "step": 290420 }, { "epoch": 69.73, "learning_rate": 2.5406250447340303e-05, "loss": 0.0022, "step": 290430 }, { "epoch": 69.73, "learning_rate": 2.5403125193781696e-05, "loss": 0.0014, "step": 290440 }, { "epoch": 69.73, "learning_rate": 2.5400000066995587e-05, "loss": 0.0018, "step": 290450 }, { "epoch": 69.73, "learning_rate": 2.539687506699806e-05, "loss": 0.0023, "step": 290460 }, { "epoch": 69.74, "learning_rate": 2.5393750193805272e-05, "loss": 0.0017, "step": 290470 }, { "epoch": 69.74, "learning_rate": 2.539062544743328e-05, "loss": 0.0101, "step": 290480 }, { "epoch": 69.74, "learning_rate": 2.5387500827898226e-05, "loss": 0.002, "step": 290490 }, { "epoch": 69.74, "learning_rate": 2.5384376335216177e-05, "loss": 0.0017, "step": 290500 }, { "epoch": 69.75, "learning_rate": 2.5381251969403282e-05, "loss": 0.0019, "step": 290510 }, { "epoch": 69.75, "learning_rate": 2.537812773047562e-05, "loss": 0.0016, "step": 290520 }, { "epoch": 69.75, "learning_rate": 2.5375003618449273e-05, "loss": 0.002, "step": 290530 }, { "epoch": 69.75, "learning_rate": 2.5371879633340378e-05, "loss": 0.0016, "step": 290540 }, { "epoch": 69.75, "learning_rate": 2.536875577516501e-05, "loss": 0.0019, "step": 290550 }, { "epoch": 69.76, "learning_rate": 2.5365632043939293e-05, "loss": 0.0016, "step": 290560 }, { "epoch": 69.76, "learning_rate": 2.53625084396793e-05, "loss": 0.0017, "step": 290570 }, { "epoch": 69.76, "learning_rate": 2.5359384962401145e-05, "loss": 0.0022, "step": 290580 }, { "epoch": 69.76, "learning_rate": 2.535626161212094e-05, "loss": 0.0015, "step": 290590 }, { "epoch": 69.77, "learning_rate": 2.5353138388854754e-05, "loss": 0.0017, "step": 290600 }, { "epoch": 69.77, "learning_rate": 2.5350015292618716e-05, "loss": 0.0018, "step": 290610 }, { "epoch": 69.77, "learning_rate": 2.5346892323428883e-05, "loss": 0.0017, "step": 290620 }, { "epoch": 69.77, "learning_rate": 2.5343769481301398e-05, "loss": 0.0016, "step": 290630 }, { "epoch": 69.78, "learning_rate": 2.5340646766252308e-05, "loss": 0.0022, "step": 290640 }, { "epoch": 69.78, "learning_rate": 2.5337524178297757e-05, "loss": 0.002, "step": 290650 }, { "epoch": 69.78, "learning_rate": 2.5334401717453805e-05, "loss": 0.0015, "step": 290660 }, { "epoch": 69.78, "learning_rate": 2.5331279383736535e-05, "loss": 0.0017, "step": 290670 }, { "epoch": 69.78, "learning_rate": 2.5328157177162076e-05, "loss": 0.0016, "step": 290680 }, { "epoch": 69.79, "learning_rate": 2.5325035097746485e-05, "loss": 0.0016, "step": 290690 }, { "epoch": 69.79, "learning_rate": 2.5321913145505882e-05, "loss": 0.0016, "step": 290700 }, { "epoch": 69.79, "learning_rate": 2.5318791320456336e-05, "loss": 0.0018, "step": 290710 }, { "epoch": 69.79, "learning_rate": 2.5315669622613957e-05, "loss": 0.0015, "step": 290720 }, { "epoch": 69.8, "learning_rate": 2.5312548051994823e-05, "loss": 0.0018, "step": 290730 }, { "epoch": 69.8, "learning_rate": 2.5309426608615005e-05, "loss": 0.0015, "step": 290740 }, { "epoch": 69.8, "learning_rate": 2.530630529249063e-05, "loss": 0.003, "step": 290750 }, { "epoch": 69.8, "learning_rate": 2.5303184103637745e-05, "loss": 0.0024, "step": 290760 }, { "epoch": 69.81, "learning_rate": 2.5300063042072476e-05, "loss": 0.002, "step": 290770 }, { "epoch": 69.81, "learning_rate": 2.529694210781086e-05, "loss": 0.0021, "step": 290780 }, { "epoch": 69.81, "learning_rate": 2.5293821300869036e-05, "loss": 0.0015, "step": 290790 }, { "epoch": 69.81, "learning_rate": 2.5290700621263046e-05, "loss": 0.0017, "step": 290800 }, { "epoch": 69.81, "learning_rate": 2.5287580069009008e-05, "loss": 0.0015, "step": 290810 }, { "epoch": 69.82, "learning_rate": 2.5284459644122992e-05, "loss": 0.0017, "step": 290820 }, { "epoch": 69.82, "learning_rate": 2.528133934662106e-05, "loss": 0.0016, "step": 290830 }, { "epoch": 69.82, "learning_rate": 2.5278219176519325e-05, "loss": 0.0015, "step": 290840 }, { "epoch": 69.82, "learning_rate": 2.527509913383384e-05, "loss": 0.0016, "step": 290850 }, { "epoch": 69.83, "learning_rate": 2.5271979218580722e-05, "loss": 0.0018, "step": 290860 }, { "epoch": 69.83, "learning_rate": 2.5268859430776002e-05, "loss": 0.0022, "step": 290870 }, { "epoch": 69.83, "learning_rate": 2.5265739770435813e-05, "loss": 0.0017, "step": 290880 }, { "epoch": 69.83, "learning_rate": 2.5262620237576183e-05, "loss": 0.0017, "step": 290890 }, { "epoch": 69.83, "learning_rate": 2.5259500832213223e-05, "loss": 0.0016, "step": 290900 }, { "epoch": 69.84, "learning_rate": 2.525638155436302e-05, "loss": 0.0016, "step": 290910 }, { "epoch": 69.84, "learning_rate": 2.525326240404161e-05, "loss": 0.0016, "step": 290920 }, { "epoch": 69.84, "learning_rate": 2.5250143381265113e-05, "loss": 0.0015, "step": 290930 }, { "epoch": 69.84, "learning_rate": 2.5247024486049565e-05, "loss": 0.0019, "step": 290940 }, { "epoch": 69.85, "learning_rate": 2.5243905718411083e-05, "loss": 0.0015, "step": 290950 }, { "epoch": 69.85, "learning_rate": 2.5240787078365715e-05, "loss": 0.0017, "step": 290960 }, { "epoch": 69.85, "learning_rate": 2.523766856592952e-05, "loss": 0.0017, "step": 290970 }, { "epoch": 69.85, "learning_rate": 2.52345501811186e-05, "loss": 0.0019, "step": 290980 }, { "epoch": 69.86, "learning_rate": 2.5231431923949e-05, "loss": 0.0019, "step": 290990 }, { "epoch": 69.86, "learning_rate": 2.5228313794436832e-05, "loss": 0.0114, "step": 291000 }, { "epoch": 69.86, "learning_rate": 2.522519579259811e-05, "loss": 0.0018, "step": 291010 }, { "epoch": 69.86, "learning_rate": 2.5222077918448966e-05, "loss": 0.0017, "step": 291020 }, { "epoch": 69.86, "learning_rate": 2.5218960172005433e-05, "loss": 0.0018, "step": 291030 }, { "epoch": 69.87, "learning_rate": 2.5215842553283576e-05, "loss": 0.0018, "step": 291040 }, { "epoch": 69.87, "learning_rate": 2.5212725062299482e-05, "loss": 0.0018, "step": 291050 }, { "epoch": 69.87, "learning_rate": 2.52096076990692e-05, "loss": 0.0017, "step": 291060 }, { "epoch": 69.87, "learning_rate": 2.5206490463608823e-05, "loss": 0.0016, "step": 291070 }, { "epoch": 69.88, "learning_rate": 2.5203373355934377e-05, "loss": 0.0016, "step": 291080 }, { "epoch": 69.88, "learning_rate": 2.520025637606198e-05, "loss": 0.0014, "step": 291090 }, { "epoch": 69.88, "learning_rate": 2.5197139524007663e-05, "loss": 0.0016, "step": 291100 }, { "epoch": 69.88, "learning_rate": 2.5194022799787482e-05, "loss": 0.0018, "step": 291110 }, { "epoch": 69.89, "learning_rate": 2.519090620341753e-05, "loss": 0.0019, "step": 291120 }, { "epoch": 69.89, "learning_rate": 2.5187789734913835e-05, "loss": 0.0017, "step": 291130 }, { "epoch": 69.89, "learning_rate": 2.51846733942925e-05, "loss": 0.0015, "step": 291140 }, { "epoch": 69.89, "learning_rate": 2.5181557181569548e-05, "loss": 0.0016, "step": 291150 }, { "epoch": 69.89, "learning_rate": 2.5178441096761075e-05, "loss": 0.0017, "step": 291160 }, { "epoch": 69.9, "learning_rate": 2.5175325139883105e-05, "loss": 0.0015, "step": 291170 }, { "epoch": 69.9, "learning_rate": 2.517220931095173e-05, "loss": 0.0016, "step": 291180 }, { "epoch": 69.9, "learning_rate": 2.5169093609982984e-05, "loss": 0.0016, "step": 291190 }, { "epoch": 69.9, "learning_rate": 2.5165978036992943e-05, "loss": 0.0016, "step": 291200 }, { "epoch": 69.91, "learning_rate": 2.516286259199767e-05, "loss": 0.0016, "step": 291210 }, { "epoch": 69.91, "learning_rate": 2.515974727501319e-05, "loss": 0.0015, "step": 291220 }, { "epoch": 69.91, "learning_rate": 2.5156632086055603e-05, "loss": 0.0016, "step": 291230 }, { "epoch": 69.91, "learning_rate": 2.515351702514094e-05, "loss": 0.0016, "step": 291240 }, { "epoch": 69.91, "learning_rate": 2.515040209228524e-05, "loss": 0.0017, "step": 291250 }, { "epoch": 69.92, "learning_rate": 2.5147287287504595e-05, "loss": 0.0016, "step": 291260 }, { "epoch": 69.92, "learning_rate": 2.514417261081502e-05, "loss": 0.0015, "step": 291270 }, { "epoch": 69.92, "learning_rate": 2.5141058062232602e-05, "loss": 0.0018, "step": 291280 }, { "epoch": 69.92, "learning_rate": 2.5137943641773364e-05, "loss": 0.0015, "step": 291290 }, { "epoch": 69.93, "learning_rate": 2.513482934945339e-05, "loss": 0.0016, "step": 291300 }, { "epoch": 69.93, "learning_rate": 2.513171518528871e-05, "loss": 0.0018, "step": 291310 }, { "epoch": 69.93, "learning_rate": 2.5128601149295362e-05, "loss": 0.0017, "step": 291320 }, { "epoch": 69.93, "learning_rate": 2.5125487241489432e-05, "loss": 0.0015, "step": 291330 }, { "epoch": 69.94, "learning_rate": 2.512237346188693e-05, "loss": 0.002, "step": 291340 }, { "epoch": 69.94, "learning_rate": 2.5119259810503936e-05, "loss": 0.0018, "step": 291350 }, { "epoch": 69.94, "learning_rate": 2.5116146287356474e-05, "loss": 0.0017, "step": 291360 }, { "epoch": 69.94, "learning_rate": 2.511303289246062e-05, "loss": 0.0014, "step": 291370 }, { "epoch": 69.94, "learning_rate": 2.51099196258324e-05, "loss": 0.0017, "step": 291380 }, { "epoch": 69.95, "learning_rate": 2.5106806487487845e-05, "loss": 0.0016, "step": 291390 }, { "epoch": 69.95, "learning_rate": 2.510369347744303e-05, "loss": 0.0016, "step": 291400 }, { "epoch": 69.95, "learning_rate": 2.5100580595713972e-05, "loss": 0.0015, "step": 291410 }, { "epoch": 70.0, "learning_rate": 2.5097467842316747e-05, "loss": 0.0019, "step": 291420 }, { "epoch": 70.0, "learning_rate": 2.5094355217267368e-05, "loss": 0.0019, "step": 291430 }, { "epoch": 70.01, "learning_rate": 2.5091242720581902e-05, "loss": 0.0031, "step": 291440 }, { "epoch": 70.01, "learning_rate": 2.5088130352276385e-05, "loss": 0.0024, "step": 291450 }, { "epoch": 70.01, "learning_rate": 2.5085018112366832e-05, "loss": 0.0015, "step": 291460 }, { "epoch": 70.01, "learning_rate": 2.5081906000869304e-05, "loss": 0.0015, "step": 291470 }, { "epoch": 70.02, "learning_rate": 2.5078794017799857e-05, "loss": 0.0015, "step": 291480 }, { "epoch": 70.02, "learning_rate": 2.5075682163174496e-05, "loss": 0.0017, "step": 291490 }, { "epoch": 70.02, "learning_rate": 2.50725704370093e-05, "loss": 0.0015, "step": 291500 }, { "epoch": 70.02, "learning_rate": 2.5069458839320258e-05, "loss": 0.0019, "step": 291510 }, { "epoch": 70.03, "learning_rate": 2.5066347370123456e-05, "loss": 0.002, "step": 291520 }, { "epoch": 70.03, "learning_rate": 2.5063236029434896e-05, "loss": 0.0014, "step": 291530 }, { "epoch": 70.03, "learning_rate": 2.5060124817270635e-05, "loss": 0.0016, "step": 291540 }, { "epoch": 70.03, "learning_rate": 2.5057013733646684e-05, "loss": 0.0016, "step": 291550 }, { "epoch": 70.03, "learning_rate": 2.5053902778579115e-05, "loss": 0.0016, "step": 291560 }, { "epoch": 70.04, "learning_rate": 2.5050791952083918e-05, "loss": 0.0017, "step": 291570 }, { "epoch": 70.04, "learning_rate": 2.5047681254177164e-05, "loss": 0.0015, "step": 291580 }, { "epoch": 70.04, "learning_rate": 2.5044570684874868e-05, "loss": 0.0015, "step": 291590 }, { "epoch": 70.04, "learning_rate": 2.5041460244193047e-05, "loss": 0.0016, "step": 291600 }, { "epoch": 70.05, "learning_rate": 2.5038349932147776e-05, "loss": 0.0017, "step": 291610 }, { "epoch": 70.05, "learning_rate": 2.503523974875503e-05, "loss": 0.0016, "step": 291620 }, { "epoch": 70.05, "learning_rate": 2.5032129694030885e-05, "loss": 0.0015, "step": 291630 }, { "epoch": 70.05, "learning_rate": 2.5029019767991335e-05, "loss": 0.0014, "step": 291640 }, { "epoch": 70.05, "learning_rate": 2.502590997065245e-05, "loss": 0.0015, "step": 291650 }, { "epoch": 70.06, "learning_rate": 2.5022800302030208e-05, "loss": 0.0015, "step": 291660 }, { "epoch": 70.06, "learning_rate": 2.5019690762140686e-05, "loss": 0.0021, "step": 291670 }, { "epoch": 70.06, "learning_rate": 2.5016581350999884e-05, "loss": 0.0014, "step": 291680 }, { "epoch": 70.06, "learning_rate": 2.501347206862381e-05, "loss": 0.0015, "step": 291690 }, { "epoch": 70.07, "learning_rate": 2.501036291502853e-05, "loss": 0.0016, "step": 291700 }, { "epoch": 70.07, "learning_rate": 2.500725389023003e-05, "loss": 0.0024, "step": 291710 }, { "epoch": 70.07, "learning_rate": 2.500414499424437e-05, "loss": 0.0026, "step": 291720 }, { "epoch": 70.07, "learning_rate": 2.5001036227087536e-05, "loss": 0.0017, "step": 291730 }, { "epoch": 70.08, "learning_rate": 2.4997927588775594e-05, "loss": 0.0017, "step": 291740 }, { "epoch": 70.08, "learning_rate": 2.4994819079324543e-05, "loss": 0.0016, "step": 291750 }, { "epoch": 70.08, "learning_rate": 2.499171069875038e-05, "loss": 0.0018, "step": 291760 }, { "epoch": 70.08, "learning_rate": 2.498860244706915e-05, "loss": 0.0014, "step": 291770 }, { "epoch": 70.08, "learning_rate": 2.4985494324296888e-05, "loss": 0.0017, "step": 291780 }, { "epoch": 70.09, "learning_rate": 2.498238633044958e-05, "loss": 0.0014, "step": 291790 }, { "epoch": 70.09, "learning_rate": 2.4979278465543287e-05, "loss": 0.0018, "step": 291800 }, { "epoch": 70.09, "learning_rate": 2.497617072959398e-05, "loss": 0.0016, "step": 291810 }, { "epoch": 70.09, "learning_rate": 2.497306312261771e-05, "loss": 0.0016, "step": 291820 }, { "epoch": 70.1, "learning_rate": 2.496995564463047e-05, "loss": 0.0016, "step": 291830 }, { "epoch": 70.1, "learning_rate": 2.4966848295648303e-05, "loss": 0.0015, "step": 291840 }, { "epoch": 70.1, "learning_rate": 2.4963741075687197e-05, "loss": 0.0015, "step": 291850 }, { "epoch": 70.1, "learning_rate": 2.4960633984763194e-05, "loss": 0.0019, "step": 291860 }, { "epoch": 70.11, "learning_rate": 2.4957527022892268e-05, "loss": 0.0032, "step": 291870 }, { "epoch": 70.11, "learning_rate": 2.4954420190090484e-05, "loss": 0.0019, "step": 291880 }, { "epoch": 70.11, "learning_rate": 2.495131348637382e-05, "loss": 0.0022, "step": 291890 }, { "epoch": 70.11, "learning_rate": 2.494820691175828e-05, "loss": 0.0015, "step": 291900 }, { "epoch": 70.11, "learning_rate": 2.4945100466259914e-05, "loss": 0.0016, "step": 291910 }, { "epoch": 70.12, "learning_rate": 2.4941994149894687e-05, "loss": 0.0015, "step": 291920 }, { "epoch": 70.12, "learning_rate": 2.4938887962678654e-05, "loss": 0.0016, "step": 291930 }, { "epoch": 70.12, "learning_rate": 2.493578190462778e-05, "loss": 0.0015, "step": 291940 }, { "epoch": 70.12, "learning_rate": 2.4932675975758114e-05, "loss": 0.0015, "step": 291950 }, { "epoch": 70.13, "learning_rate": 2.4929570176085648e-05, "loss": 0.0024, "step": 291960 }, { "epoch": 70.13, "learning_rate": 2.4926464505626368e-05, "loss": 0.0015, "step": 291970 }, { "epoch": 70.13, "learning_rate": 2.4923358964396316e-05, "loss": 0.0016, "step": 291980 }, { "epoch": 70.13, "learning_rate": 2.492025355241146e-05, "loss": 0.0019, "step": 291990 }, { "epoch": 70.13, "learning_rate": 2.491714826968785e-05, "loss": 0.0014, "step": 292000 }, { "epoch": 70.14, "learning_rate": 2.491404311624145e-05, "loss": 0.0017, "step": 292010 }, { "epoch": 70.14, "learning_rate": 2.4910938092088297e-05, "loss": 0.0015, "step": 292020 }, { "epoch": 70.14, "learning_rate": 2.490783319724438e-05, "loss": 0.0036, "step": 292030 }, { "epoch": 70.14, "learning_rate": 2.4904728431725682e-05, "loss": 0.002, "step": 292040 }, { "epoch": 70.15, "learning_rate": 2.490162379554824e-05, "loss": 0.0017, "step": 292050 }, { "epoch": 70.15, "learning_rate": 2.4898519288728023e-05, "loss": 0.0017, "step": 292060 }, { "epoch": 70.15, "learning_rate": 2.489541491128106e-05, "loss": 0.0018, "step": 292070 }, { "epoch": 70.15, "learning_rate": 2.4892310663223328e-05, "loss": 0.0016, "step": 292080 }, { "epoch": 70.16, "learning_rate": 2.488920654457083e-05, "loss": 0.0017, "step": 292090 }, { "epoch": 70.16, "learning_rate": 2.4886102555339596e-05, "loss": 0.0017, "step": 292100 }, { "epoch": 70.16, "learning_rate": 2.4882998695545577e-05, "loss": 0.0015, "step": 292110 }, { "epoch": 70.16, "learning_rate": 2.4879894965204813e-05, "loss": 0.0024, "step": 292120 }, { "epoch": 70.16, "learning_rate": 2.4876791364333263e-05, "loss": 0.0019, "step": 292130 }, { "epoch": 70.17, "learning_rate": 2.4873687892946958e-05, "loss": 0.0016, "step": 292140 }, { "epoch": 70.17, "learning_rate": 2.4870584551061853e-05, "loss": 0.002, "step": 292150 }, { "epoch": 70.17, "learning_rate": 2.4867481338693988e-05, "loss": 0.0016, "step": 292160 }, { "epoch": 70.17, "learning_rate": 2.4864378255859334e-05, "loss": 0.0015, "step": 292170 }, { "epoch": 70.18, "learning_rate": 2.486127530257386e-05, "loss": 0.0016, "step": 292180 }, { "epoch": 70.18, "learning_rate": 2.485817247885361e-05, "loss": 0.0258, "step": 292190 }, { "epoch": 70.18, "learning_rate": 2.4855069784714528e-05, "loss": 0.0017, "step": 292200 }, { "epoch": 70.18, "learning_rate": 2.4851967220172643e-05, "loss": 0.0015, "step": 292210 }, { "epoch": 70.19, "learning_rate": 2.4848864785243913e-05, "loss": 0.0015, "step": 292220 }, { "epoch": 70.19, "learning_rate": 2.4845762479944363e-05, "loss": 0.0016, "step": 292230 }, { "epoch": 70.19, "learning_rate": 2.484266030428996e-05, "loss": 0.0015, "step": 292240 }, { "epoch": 70.19, "learning_rate": 2.483955825829668e-05, "loss": 0.0014, "step": 292250 }, { "epoch": 70.19, "learning_rate": 2.4836456341980545e-05, "loss": 0.0015, "step": 292260 }, { "epoch": 70.2, "learning_rate": 2.4833354555357507e-05, "loss": 0.002, "step": 292270 }, { "epoch": 70.2, "learning_rate": 2.483025289844359e-05, "loss": 0.0023, "step": 292280 }, { "epoch": 70.2, "learning_rate": 2.4827151371254735e-05, "loss": 0.0019, "step": 292290 }, { "epoch": 70.2, "learning_rate": 2.4824049973806978e-05, "loss": 0.0016, "step": 292300 }, { "epoch": 70.21, "learning_rate": 2.4820948706116277e-05, "loss": 0.0027, "step": 292310 }, { "epoch": 70.21, "learning_rate": 2.4817847568198595e-05, "loss": 0.0017, "step": 292320 }, { "epoch": 70.21, "learning_rate": 2.4814746560069956e-05, "loss": 0.0017, "step": 292330 }, { "epoch": 70.21, "learning_rate": 2.4811645681746304e-05, "loss": 0.0019, "step": 292340 }, { "epoch": 70.21, "learning_rate": 2.480854493324366e-05, "loss": 0.0016, "step": 292350 }, { "epoch": 70.22, "learning_rate": 2.480544431457797e-05, "loss": 0.0015, "step": 292360 }, { "epoch": 70.22, "learning_rate": 2.4802343825765247e-05, "loss": 0.0017, "step": 292370 }, { "epoch": 70.22, "learning_rate": 2.4799243466821435e-05, "loss": 0.0015, "step": 292380 }, { "epoch": 70.22, "learning_rate": 2.4796143237762554e-05, "loss": 0.0018, "step": 292390 }, { "epoch": 70.23, "learning_rate": 2.4793043138604544e-05, "loss": 0.002, "step": 292400 }, { "epoch": 70.23, "learning_rate": 2.4789943169363393e-05, "loss": 0.0015, "step": 292410 }, { "epoch": 70.23, "learning_rate": 2.4786843330055115e-05, "loss": 0.0015, "step": 292420 }, { "epoch": 70.23, "learning_rate": 2.4783743620695632e-05, "loss": 0.0016, "step": 292430 }, { "epoch": 70.24, "learning_rate": 2.4780644041300966e-05, "loss": 0.0014, "step": 292440 }, { "epoch": 70.24, "learning_rate": 2.477754459188705e-05, "loss": 0.0017, "step": 292450 }, { "epoch": 70.24, "learning_rate": 2.4774445272469897e-05, "loss": 0.0016, "step": 292460 }, { "epoch": 70.24, "learning_rate": 2.4771346083065472e-05, "loss": 0.0014, "step": 292470 }, { "epoch": 70.24, "learning_rate": 2.4768247023689716e-05, "loss": 0.0018, "step": 292480 }, { "epoch": 70.25, "learning_rate": 2.4765148094358643e-05, "loss": 0.0017, "step": 292490 }, { "epoch": 70.25, "learning_rate": 2.476204929508819e-05, "loss": 0.0016, "step": 292500 }, { "epoch": 70.25, "learning_rate": 2.4758950625894367e-05, "loss": 0.0017, "step": 292510 }, { "epoch": 70.25, "learning_rate": 2.47558520867931e-05, "loss": 0.0019, "step": 292520 }, { "epoch": 70.26, "learning_rate": 2.4752753677800412e-05, "loss": 0.0053, "step": 292530 }, { "epoch": 70.26, "learning_rate": 2.474965539893223e-05, "loss": 0.0019, "step": 292540 }, { "epoch": 70.26, "learning_rate": 2.474655725020452e-05, "loss": 0.0019, "step": 292550 }, { "epoch": 70.26, "learning_rate": 2.4743459231633288e-05, "loss": 0.0047, "step": 292560 }, { "epoch": 70.27, "learning_rate": 2.4740361343234458e-05, "loss": 0.0016, "step": 292570 }, { "epoch": 70.27, "learning_rate": 2.4737263585024034e-05, "loss": 0.002, "step": 292580 }, { "epoch": 70.27, "learning_rate": 2.4734165957017945e-05, "loss": 0.0016, "step": 292590 }, { "epoch": 70.27, "learning_rate": 2.4731068459232197e-05, "loss": 0.0017, "step": 292600 }, { "epoch": 70.27, "learning_rate": 2.4727971091682733e-05, "loss": 0.0015, "step": 292610 }, { "epoch": 70.28, "learning_rate": 2.47248738543855e-05, "loss": 0.0028, "step": 292620 }, { "epoch": 70.28, "learning_rate": 2.472177674735649e-05, "loss": 0.0044, "step": 292630 }, { "epoch": 70.28, "learning_rate": 2.4718679770611643e-05, "loss": 0.0017, "step": 292640 }, { "epoch": 70.28, "learning_rate": 2.4715582924166947e-05, "loss": 0.0018, "step": 292650 }, { "epoch": 70.29, "learning_rate": 2.471248620803833e-05, "loss": 0.0016, "step": 292660 }, { "epoch": 70.29, "learning_rate": 2.470938962224179e-05, "loss": 0.0016, "step": 292670 }, { "epoch": 70.29, "learning_rate": 2.4706293166793244e-05, "loss": 0.0023, "step": 292680 }, { "epoch": 70.29, "learning_rate": 2.4703196841708698e-05, "loss": 0.0015, "step": 292690 }, { "epoch": 70.29, "learning_rate": 2.4700100647004064e-05, "loss": 0.0058, "step": 292700 }, { "epoch": 70.3, "learning_rate": 2.4697004582695325e-05, "loss": 0.0022, "step": 292710 }, { "epoch": 70.3, "learning_rate": 2.4693908648798458e-05, "loss": 0.0016, "step": 292720 }, { "epoch": 70.3, "learning_rate": 2.4690812845329375e-05, "loss": 0.0017, "step": 292730 }, { "epoch": 70.3, "learning_rate": 2.4687717172304076e-05, "loss": 0.0016, "step": 292740 }, { "epoch": 70.31, "learning_rate": 2.468462162973849e-05, "loss": 0.0015, "step": 292750 }, { "epoch": 70.31, "learning_rate": 2.468152621764856e-05, "loss": 0.0023, "step": 292760 }, { "epoch": 70.31, "learning_rate": 2.4678430936050272e-05, "loss": 0.0017, "step": 292770 }, { "epoch": 70.31, "learning_rate": 2.4675335784959547e-05, "loss": 0.0054, "step": 292780 }, { "epoch": 70.32, "learning_rate": 2.4672240764392368e-05, "loss": 0.0016, "step": 292790 }, { "epoch": 70.32, "learning_rate": 2.4669145874364658e-05, "loss": 0.0017, "step": 292800 }, { "epoch": 70.32, "learning_rate": 2.4666051114892396e-05, "loss": 0.0015, "step": 292810 }, { "epoch": 70.32, "learning_rate": 2.4662956485991517e-05, "loss": 0.0036, "step": 292820 }, { "epoch": 70.32, "learning_rate": 2.4659861987677958e-05, "loss": 0.0016, "step": 292830 }, { "epoch": 70.33, "learning_rate": 2.46567676199677e-05, "loss": 0.004, "step": 292840 }, { "epoch": 70.33, "learning_rate": 2.4653673382876653e-05, "loss": 0.0016, "step": 292850 }, { "epoch": 70.33, "learning_rate": 2.4650579276420803e-05, "loss": 0.0018, "step": 292860 }, { "epoch": 70.33, "learning_rate": 2.4647485300616062e-05, "loss": 0.0016, "step": 292870 }, { "epoch": 70.34, "learning_rate": 2.4644391455478418e-05, "loss": 0.0019, "step": 292880 }, { "epoch": 70.34, "learning_rate": 2.4641297741023785e-05, "loss": 0.0019, "step": 292890 }, { "epoch": 70.34, "learning_rate": 2.4638204157268097e-05, "loss": 0.0017, "step": 292900 }, { "epoch": 70.34, "learning_rate": 2.4635110704227337e-05, "loss": 0.0016, "step": 292910 }, { "epoch": 70.35, "learning_rate": 2.4632017381917412e-05, "loss": 0.0018, "step": 292920 }, { "epoch": 70.35, "learning_rate": 2.4628924190354297e-05, "loss": 0.0014, "step": 292930 }, { "epoch": 70.35, "learning_rate": 2.4625831129553905e-05, "loss": 0.0016, "step": 292940 }, { "epoch": 70.35, "learning_rate": 2.4622738199532202e-05, "loss": 0.006, "step": 292950 }, { "epoch": 70.35, "learning_rate": 2.4619645400305125e-05, "loss": 0.002, "step": 292960 }, { "epoch": 70.36, "learning_rate": 2.4616552731888586e-05, "loss": 0.0021, "step": 292970 }, { "epoch": 70.36, "learning_rate": 2.4613460194298548e-05, "loss": 0.0016, "step": 292980 }, { "epoch": 70.36, "learning_rate": 2.461036778755097e-05, "loss": 0.0016, "step": 292990 }, { "epoch": 70.36, "learning_rate": 2.4607275511661743e-05, "loss": 0.0015, "step": 293000 }, { "epoch": 70.37, "learning_rate": 2.4604183366646855e-05, "loss": 0.0016, "step": 293010 }, { "epoch": 70.37, "learning_rate": 2.4601091352522193e-05, "loss": 0.0015, "step": 293020 }, { "epoch": 70.37, "learning_rate": 2.4597999469303745e-05, "loss": 0.0018, "step": 293030 }, { "epoch": 70.37, "learning_rate": 2.4594907717007393e-05, "loss": 0.0016, "step": 293040 }, { "epoch": 70.37, "learning_rate": 2.4591816095649123e-05, "loss": 0.0016, "step": 293050 }, { "epoch": 70.38, "learning_rate": 2.4588724605244827e-05, "loss": 0.0017, "step": 293060 }, { "epoch": 70.38, "learning_rate": 2.4585633245810473e-05, "loss": 0.002, "step": 293070 }, { "epoch": 70.38, "learning_rate": 2.458254201736196e-05, "loss": 0.0016, "step": 293080 }, { "epoch": 70.38, "learning_rate": 2.4579450919915257e-05, "loss": 0.0014, "step": 293090 }, { "epoch": 70.39, "learning_rate": 2.4576359953486278e-05, "loss": 0.0015, "step": 293100 }, { "epoch": 70.39, "learning_rate": 2.457326911809093e-05, "loss": 0.0016, "step": 293110 }, { "epoch": 70.39, "learning_rate": 2.4570178413745187e-05, "loss": 0.0016, "step": 293120 }, { "epoch": 70.39, "learning_rate": 2.4567087840464937e-05, "loss": 0.0014, "step": 293130 }, { "epoch": 70.4, "learning_rate": 2.4563997398266146e-05, "loss": 0.0027, "step": 293140 }, { "epoch": 70.4, "learning_rate": 2.4560907087164708e-05, "loss": 0.0016, "step": 293150 }, { "epoch": 70.4, "learning_rate": 2.455781690717659e-05, "loss": 0.0015, "step": 293160 }, { "epoch": 70.4, "learning_rate": 2.4554726858317688e-05, "loss": 0.0016, "step": 293170 }, { "epoch": 70.4, "learning_rate": 2.4551636940603927e-05, "loss": 0.0014, "step": 293180 }, { "epoch": 70.41, "learning_rate": 2.4548547154051253e-05, "loss": 0.0015, "step": 293190 }, { "epoch": 70.41, "learning_rate": 2.4545457498675567e-05, "loss": 0.0015, "step": 293200 }, { "epoch": 70.41, "learning_rate": 2.454236797449282e-05, "loss": 0.0016, "step": 293210 }, { "epoch": 70.41, "learning_rate": 2.4539278581518903e-05, "loss": 0.0016, "step": 293220 }, { "epoch": 70.42, "learning_rate": 2.4536189319769775e-05, "loss": 0.0015, "step": 293230 }, { "epoch": 70.42, "learning_rate": 2.4533100189261327e-05, "loss": 0.0015, "step": 293240 }, { "epoch": 70.42, "learning_rate": 2.4530011190009504e-05, "loss": 0.0016, "step": 293250 }, { "epoch": 70.42, "learning_rate": 2.4526922322030228e-05, "loss": 0.0013, "step": 293260 }, { "epoch": 70.43, "learning_rate": 2.4523833585339378e-05, "loss": 0.0017, "step": 293270 }, { "epoch": 70.43, "learning_rate": 2.4520744979952926e-05, "loss": 0.0015, "step": 293280 }, { "epoch": 70.43, "learning_rate": 2.4517656505886745e-05, "loss": 0.0015, "step": 293290 }, { "epoch": 70.43, "learning_rate": 2.4514568163156777e-05, "loss": 0.0014, "step": 293300 }, { "epoch": 70.43, "learning_rate": 2.451147995177896e-05, "loss": 0.0014, "step": 293310 }, { "epoch": 70.44, "learning_rate": 2.4508391871769165e-05, "loss": 0.0015, "step": 293320 }, { "epoch": 70.44, "learning_rate": 2.4505303923143352e-05, "loss": 0.0014, "step": 293330 }, { "epoch": 70.44, "learning_rate": 2.45022161059174e-05, "loss": 0.0015, "step": 293340 }, { "epoch": 70.44, "learning_rate": 2.4499128420107255e-05, "loss": 0.0014, "step": 293350 }, { "epoch": 70.45, "learning_rate": 2.449604086572879e-05, "loss": 0.0015, "step": 293360 }, { "epoch": 70.45, "learning_rate": 2.449295344279797e-05, "loss": 0.0017, "step": 293370 }, { "epoch": 70.45, "learning_rate": 2.448986615133066e-05, "loss": 0.0014, "step": 293380 }, { "epoch": 70.45, "learning_rate": 2.448677899134281e-05, "loss": 0.0017, "step": 293390 }, { "epoch": 70.45, "learning_rate": 2.4483691962850326e-05, "loss": 0.0015, "step": 293400 }, { "epoch": 70.46, "learning_rate": 2.4480605065869078e-05, "loss": 0.0015, "step": 293410 }, { "epoch": 70.46, "learning_rate": 2.447751830041502e-05, "loss": 0.0016, "step": 293420 }, { "epoch": 70.46, "learning_rate": 2.447443166650403e-05, "loss": 0.0016, "step": 293430 }, { "epoch": 70.46, "learning_rate": 2.4471345164152058e-05, "loss": 0.0014, "step": 293440 }, { "epoch": 70.47, "learning_rate": 2.4468258793374964e-05, "loss": 0.0014, "step": 293450 }, { "epoch": 70.47, "learning_rate": 2.446517255418869e-05, "loss": 0.0016, "step": 293460 }, { "epoch": 70.47, "learning_rate": 2.446208644660914e-05, "loss": 0.0021, "step": 293470 }, { "epoch": 70.47, "learning_rate": 2.4459000470652188e-05, "loss": 0.0016, "step": 293480 }, { "epoch": 70.48, "learning_rate": 2.4455914626333775e-05, "loss": 0.0017, "step": 293490 }, { "epoch": 70.48, "learning_rate": 2.445282891366978e-05, "loss": 0.0019, "step": 293500 }, { "epoch": 70.48, "learning_rate": 2.4449743332676132e-05, "loss": 0.0015, "step": 293510 }, { "epoch": 70.48, "learning_rate": 2.4446657883368702e-05, "loss": 0.0016, "step": 293520 }, { "epoch": 70.48, "learning_rate": 2.4443572565763434e-05, "loss": 0.0013, "step": 293530 }, { "epoch": 70.49, "learning_rate": 2.4440487379876203e-05, "loss": 0.0014, "step": 293540 }, { "epoch": 70.49, "learning_rate": 2.443740232572289e-05, "loss": 0.0016, "step": 293550 }, { "epoch": 70.49, "learning_rate": 2.4434317403319445e-05, "loss": 0.0016, "step": 293560 }, { "epoch": 70.49, "learning_rate": 2.4431232612681724e-05, "loss": 0.0014, "step": 293570 }, { "epoch": 70.5, "learning_rate": 2.4428147953825658e-05, "loss": 0.0017, "step": 293580 }, { "epoch": 70.5, "learning_rate": 2.4425063426767115e-05, "loss": 0.0018, "step": 293590 }, { "epoch": 70.5, "learning_rate": 2.4421979031522006e-05, "loss": 0.0016, "step": 293600 }, { "epoch": 70.5, "learning_rate": 2.4418894768106252e-05, "loss": 0.0016, "step": 293610 }, { "epoch": 70.51, "learning_rate": 2.4415810636535714e-05, "loss": 0.0019, "step": 293620 }, { "epoch": 70.51, "learning_rate": 2.441272663682631e-05, "loss": 0.0023, "step": 293630 }, { "epoch": 70.51, "learning_rate": 2.4409642768993917e-05, "loss": 0.0016, "step": 293640 }, { "epoch": 70.51, "learning_rate": 2.4406559033054453e-05, "loss": 0.0013, "step": 293650 }, { "epoch": 70.51, "learning_rate": 2.440347542902378e-05, "loss": 0.0015, "step": 293660 }, { "epoch": 70.52, "learning_rate": 2.440039195691783e-05, "loss": 0.0014, "step": 293670 }, { "epoch": 70.52, "learning_rate": 2.4397308616752475e-05, "loss": 0.0041, "step": 293680 }, { "epoch": 70.52, "learning_rate": 2.439422540854358e-05, "loss": 0.0015, "step": 293690 }, { "epoch": 70.52, "learning_rate": 2.439114233230708e-05, "loss": 0.0016, "step": 293700 }, { "epoch": 70.53, "learning_rate": 2.4388059388058833e-05, "loss": 0.0016, "step": 293710 }, { "epoch": 70.53, "learning_rate": 2.438497657581476e-05, "loss": 0.002, "step": 293720 }, { "epoch": 70.53, "learning_rate": 2.4381893895590712e-05, "loss": 0.0014, "step": 293730 }, { "epoch": 70.53, "learning_rate": 2.4378811347402613e-05, "loss": 0.0018, "step": 293740 }, { "epoch": 70.53, "learning_rate": 2.437572893126634e-05, "loss": 0.0016, "step": 293750 }, { "epoch": 70.54, "learning_rate": 2.437264664719775e-05, "loss": 0.0018, "step": 293760 }, { "epoch": 70.54, "learning_rate": 2.4369564495212777e-05, "loss": 0.0016, "step": 293770 }, { "epoch": 70.54, "learning_rate": 2.4366482475327262e-05, "loss": 0.0021, "step": 293780 }, { "epoch": 70.54, "learning_rate": 2.4363400587557128e-05, "loss": 0.0017, "step": 293790 }, { "epoch": 70.55, "learning_rate": 2.4360318831918228e-05, "loss": 0.0017, "step": 293800 }, { "epoch": 70.55, "learning_rate": 2.435723720842647e-05, "loss": 0.0017, "step": 293810 }, { "epoch": 70.55, "learning_rate": 2.4354155717097732e-05, "loss": 0.0016, "step": 293820 }, { "epoch": 70.55, "learning_rate": 2.4351074357947867e-05, "loss": 0.0015, "step": 293830 }, { "epoch": 70.56, "learning_rate": 2.4347993130992804e-05, "loss": 0.0033, "step": 293840 }, { "epoch": 70.56, "learning_rate": 2.4344912036248373e-05, "loss": 0.0018, "step": 293850 }, { "epoch": 70.56, "learning_rate": 2.4341831073730497e-05, "loss": 0.0017, "step": 293860 }, { "epoch": 70.56, "learning_rate": 2.4338750243455028e-05, "loss": 0.0018, "step": 293870 }, { "epoch": 70.56, "learning_rate": 2.4335669545437867e-05, "loss": 0.0023, "step": 293880 }, { "epoch": 70.57, "learning_rate": 2.4332588979694863e-05, "loss": 0.0018, "step": 293890 }, { "epoch": 70.57, "learning_rate": 2.432950854624193e-05, "loss": 0.0016, "step": 293900 }, { "epoch": 70.57, "learning_rate": 2.43264282450949e-05, "loss": 0.0016, "step": 293910 }, { "epoch": 70.57, "learning_rate": 2.4323348076269682e-05, "loss": 0.0018, "step": 293920 }, { "epoch": 70.58, "learning_rate": 2.4320268039782157e-05, "loss": 0.0021, "step": 293930 }, { "epoch": 70.58, "learning_rate": 2.4317188135648168e-05, "loss": 0.002, "step": 293940 }, { "epoch": 70.58, "learning_rate": 2.431410836388362e-05, "loss": 0.0016, "step": 293950 }, { "epoch": 70.58, "learning_rate": 2.4311028724504375e-05, "loss": 0.0017, "step": 293960 }, { "epoch": 70.59, "learning_rate": 2.430794921752629e-05, "loss": 0.0027, "step": 293970 }, { "epoch": 70.59, "learning_rate": 2.430486984296526e-05, "loss": 0.0019, "step": 293980 }, { "epoch": 70.59, "learning_rate": 2.4301790600837133e-05, "loss": 0.0016, "step": 293990 }, { "epoch": 70.59, "learning_rate": 2.4298711491157806e-05, "loss": 0.0025, "step": 294000 }, { "epoch": 70.59, "learning_rate": 2.4295632513943118e-05, "loss": 0.002, "step": 294010 }, { "epoch": 70.6, "learning_rate": 2.429255366920897e-05, "loss": 0.0019, "step": 294020 }, { "epoch": 70.6, "learning_rate": 2.4289474956971204e-05, "loss": 0.0024, "step": 294030 }, { "epoch": 70.6, "learning_rate": 2.4286396377245714e-05, "loss": 0.002, "step": 294040 }, { "epoch": 70.6, "learning_rate": 2.428331793004835e-05, "loss": 0.0019, "step": 294050 }, { "epoch": 70.61, "learning_rate": 2.428023961539496e-05, "loss": 0.002, "step": 294060 }, { "epoch": 70.61, "learning_rate": 2.4277161433301454e-05, "loss": 0.0016, "step": 294070 }, { "epoch": 70.61, "learning_rate": 2.427408338378365e-05, "loss": 0.0076, "step": 294080 }, { "epoch": 70.61, "learning_rate": 2.427100546685746e-05, "loss": 0.0018, "step": 294090 }, { "epoch": 70.61, "learning_rate": 2.42679276825387e-05, "loss": 0.0039, "step": 294100 }, { "epoch": 70.62, "learning_rate": 2.4264850030843274e-05, "loss": 0.0017, "step": 294110 }, { "epoch": 70.62, "learning_rate": 2.4261772511787023e-05, "loss": 0.0018, "step": 294120 }, { "epoch": 70.62, "learning_rate": 2.42586951253858e-05, "loss": 0.0016, "step": 294130 }, { "epoch": 70.62, "learning_rate": 2.4255617871655496e-05, "loss": 0.0016, "step": 294140 }, { "epoch": 70.63, "learning_rate": 2.425254075061193e-05, "loss": 0.0017, "step": 294150 }, { "epoch": 70.63, "learning_rate": 2.4249463762271e-05, "loss": 0.0023, "step": 294160 }, { "epoch": 70.63, "learning_rate": 2.4246386906648533e-05, "loss": 0.0049, "step": 294170 }, { "epoch": 70.63, "learning_rate": 2.4243310183760426e-05, "loss": 0.0032, "step": 294180 }, { "epoch": 70.64, "learning_rate": 2.424023359362249e-05, "loss": 0.0022, "step": 294190 }, { "epoch": 70.64, "learning_rate": 2.4237157136250628e-05, "loss": 0.0018, "step": 294200 }, { "epoch": 70.64, "learning_rate": 2.4234080811660652e-05, "loss": 0.0035, "step": 294210 }, { "epoch": 70.64, "learning_rate": 2.423100461986846e-05, "loss": 0.0018, "step": 294220 }, { "epoch": 70.64, "learning_rate": 2.422792856088986e-05, "loss": 0.0018, "step": 294230 }, { "epoch": 70.65, "learning_rate": 2.4224852634740742e-05, "loss": 0.002, "step": 294240 }, { "epoch": 70.65, "learning_rate": 2.422177684143696e-05, "loss": 0.002, "step": 294250 }, { "epoch": 70.65, "learning_rate": 2.4218701180994358e-05, "loss": 0.0017, "step": 294260 }, { "epoch": 70.65, "learning_rate": 2.421562565342877e-05, "loss": 0.002, "step": 294270 }, { "epoch": 70.66, "learning_rate": 2.421255025875608e-05, "loss": 0.0018, "step": 294280 }, { "epoch": 70.66, "learning_rate": 2.42094749969921e-05, "loss": 0.0017, "step": 294290 }, { "epoch": 70.66, "learning_rate": 2.4206399868152717e-05, "loss": 0.0022, "step": 294300 }, { "epoch": 70.66, "learning_rate": 2.420332487225375e-05, "loss": 0.0019, "step": 294310 }, { "epoch": 70.66, "learning_rate": 2.4200250009311083e-05, "loss": 0.0017, "step": 294320 }, { "epoch": 70.67, "learning_rate": 2.4197175279340544e-05, "loss": 0.002, "step": 294330 }, { "epoch": 70.67, "learning_rate": 2.4194100682357958e-05, "loss": 0.003, "step": 294340 }, { "epoch": 70.67, "learning_rate": 2.419102621837921e-05, "loss": 0.0016, "step": 294350 }, { "epoch": 70.67, "learning_rate": 2.4187951887420114e-05, "loss": 0.0021, "step": 294360 }, { "epoch": 70.68, "learning_rate": 2.4184877689496542e-05, "loss": 0.0022, "step": 294370 }, { "epoch": 70.68, "learning_rate": 2.4181803624624312e-05, "loss": 0.002, "step": 294380 }, { "epoch": 70.68, "learning_rate": 2.4178729692819302e-05, "loss": 0.0024, "step": 294390 }, { "epoch": 70.68, "learning_rate": 2.4175655894097333e-05, "loss": 0.0032, "step": 294400 }, { "epoch": 70.69, "learning_rate": 2.4172582228474233e-05, "loss": 0.0024, "step": 294410 }, { "epoch": 70.69, "learning_rate": 2.4169508695965876e-05, "loss": 0.0033, "step": 294420 }, { "epoch": 70.69, "learning_rate": 2.416643529658807e-05, "loss": 0.002, "step": 294430 }, { "epoch": 70.69, "learning_rate": 2.416336203035669e-05, "loss": 0.0022, "step": 294440 }, { "epoch": 70.69, "learning_rate": 2.4160288897287538e-05, "loss": 0.0019, "step": 294450 }, { "epoch": 70.7, "learning_rate": 2.415721589739649e-05, "loss": 0.0027, "step": 294460 }, { "epoch": 70.7, "learning_rate": 2.415414303069937e-05, "loss": 0.0018, "step": 294470 }, { "epoch": 70.7, "learning_rate": 2.4151070297211997e-05, "loss": 0.0025, "step": 294480 }, { "epoch": 70.7, "learning_rate": 2.414799769695022e-05, "loss": 0.0015, "step": 294490 }, { "epoch": 70.71, "learning_rate": 2.41449252299299e-05, "loss": 0.0031, "step": 294500 }, { "epoch": 70.71, "learning_rate": 2.4141852896166834e-05, "loss": 0.0018, "step": 294510 }, { "epoch": 70.71, "learning_rate": 2.413878069567689e-05, "loss": 0.0019, "step": 294520 }, { "epoch": 70.71, "learning_rate": 2.4135708628475867e-05, "loss": 0.0017, "step": 294530 }, { "epoch": 70.72, "learning_rate": 2.4132636694579636e-05, "loss": 0.0015, "step": 294540 }, { "epoch": 70.72, "learning_rate": 2.4129564894004e-05, "loss": 0.0015, "step": 294550 }, { "epoch": 70.72, "learning_rate": 2.4126493226764812e-05, "loss": 0.0016, "step": 294560 }, { "epoch": 70.72, "learning_rate": 2.4123421692877878e-05, "loss": 0.0016, "step": 294570 }, { "epoch": 70.72, "learning_rate": 2.4120350292359067e-05, "loss": 0.0018, "step": 294580 }, { "epoch": 70.73, "learning_rate": 2.411727902522417e-05, "loss": 0.0017, "step": 294590 }, { "epoch": 70.73, "learning_rate": 2.4114207891489047e-05, "loss": 0.0019, "step": 294600 }, { "epoch": 70.73, "learning_rate": 2.4111136891169515e-05, "loss": 0.0028, "step": 294610 }, { "epoch": 70.73, "learning_rate": 2.4108066024281383e-05, "loss": 0.0016, "step": 294620 }, { "epoch": 70.74, "learning_rate": 2.410499529084051e-05, "loss": 0.0018, "step": 294630 }, { "epoch": 70.74, "learning_rate": 2.4101924690862694e-05, "loss": 0.0036, "step": 294640 }, { "epoch": 70.74, "learning_rate": 2.4098854224363786e-05, "loss": 0.0015, "step": 294650 }, { "epoch": 70.74, "learning_rate": 2.4095783891359585e-05, "loss": 0.0018, "step": 294660 }, { "epoch": 70.74, "learning_rate": 2.4092713691865954e-05, "loss": 0.0017, "step": 294670 }, { "epoch": 70.75, "learning_rate": 2.4089643625898684e-05, "loss": 0.0016, "step": 294680 }, { "epoch": 70.75, "learning_rate": 2.4086573693473596e-05, "loss": 0.0022, "step": 294690 }, { "epoch": 70.75, "learning_rate": 2.408350389460654e-05, "loss": 0.0018, "step": 294700 }, { "epoch": 70.75, "learning_rate": 2.4080434229313297e-05, "loss": 0.0018, "step": 294710 }, { "epoch": 70.76, "learning_rate": 2.4077364697609738e-05, "loss": 0.0018, "step": 294720 }, { "epoch": 70.76, "learning_rate": 2.407429529951164e-05, "loss": 0.0017, "step": 294730 }, { "epoch": 70.76, "learning_rate": 2.407122603503486e-05, "loss": 0.0017, "step": 294740 }, { "epoch": 70.76, "learning_rate": 2.4068156904195193e-05, "loss": 0.0024, "step": 294750 }, { "epoch": 70.77, "learning_rate": 2.4065087907008442e-05, "loss": 0.0018, "step": 294760 }, { "epoch": 70.77, "learning_rate": 2.406201904349047e-05, "loss": 0.0017, "step": 294770 }, { "epoch": 70.77, "learning_rate": 2.4058950313657047e-05, "loss": 0.0025, "step": 294780 }, { "epoch": 70.77, "learning_rate": 2.405588171752403e-05, "loss": 0.0015, "step": 294790 }, { "epoch": 70.77, "learning_rate": 2.4052813255107198e-05, "loss": 0.0017, "step": 294800 }, { "epoch": 70.78, "learning_rate": 2.404974492642238e-05, "loss": 0.0014, "step": 294810 }, { "epoch": 70.78, "learning_rate": 2.404667673148541e-05, "loss": 0.0132, "step": 294820 }, { "epoch": 70.78, "learning_rate": 2.4043608670312072e-05, "loss": 0.0021, "step": 294830 }, { "epoch": 70.78, "learning_rate": 2.404054074291821e-05, "loss": 0.0051, "step": 294840 }, { "epoch": 70.79, "learning_rate": 2.40374729493196e-05, "loss": 0.0045, "step": 294850 }, { "epoch": 70.79, "learning_rate": 2.4034405289532092e-05, "loss": 0.0028, "step": 294860 }, { "epoch": 70.79, "learning_rate": 2.403133776357145e-05, "loss": 0.0019, "step": 294870 }, { "epoch": 70.79, "learning_rate": 2.4028270371453532e-05, "loss": 0.0019, "step": 294880 }, { "epoch": 70.8, "learning_rate": 2.4025203113194112e-05, "loss": 0.0069, "step": 294890 }, { "epoch": 70.8, "learning_rate": 2.4022135988809025e-05, "loss": 0.0016, "step": 294900 }, { "epoch": 70.8, "learning_rate": 2.4019068998314066e-05, "loss": 0.002, "step": 294910 }, { "epoch": 70.8, "learning_rate": 2.4016002141725025e-05, "loss": 0.0017, "step": 294920 }, { "epoch": 70.8, "learning_rate": 2.4012935419057747e-05, "loss": 0.0018, "step": 294930 }, { "epoch": 70.81, "learning_rate": 2.4009868830328e-05, "loss": 0.002, "step": 294940 }, { "epoch": 70.81, "learning_rate": 2.4006802375551618e-05, "loss": 0.0026, "step": 294950 }, { "epoch": 70.81, "learning_rate": 2.400373605474438e-05, "loss": 0.0017, "step": 294960 }, { "epoch": 70.81, "learning_rate": 2.4000669867922122e-05, "loss": 0.0017, "step": 294970 }, { "epoch": 70.82, "learning_rate": 2.399760381510063e-05, "loss": 0.0017, "step": 294980 }, { "epoch": 70.82, "learning_rate": 2.3994537896295682e-05, "loss": 0.0052, "step": 294990 }, { "epoch": 70.82, "learning_rate": 2.399147211152313e-05, "loss": 0.0027, "step": 295000 }, { "epoch": 70.82, "learning_rate": 2.398840646079872e-05, "loss": 0.0016, "step": 295010 }, { "epoch": 70.82, "learning_rate": 2.39853409441383e-05, "loss": 0.0014, "step": 295020 }, { "epoch": 70.83, "learning_rate": 2.3982275561557637e-05, "loss": 0.0017, "step": 295030 }, { "epoch": 70.83, "learning_rate": 2.397921031307256e-05, "loss": 0.0019, "step": 295040 }, { "epoch": 70.83, "learning_rate": 2.397614519869885e-05, "loss": 0.0021, "step": 295050 }, { "epoch": 70.83, "learning_rate": 2.397308021845229e-05, "loss": 0.0015, "step": 295060 }, { "epoch": 70.84, "learning_rate": 2.3970015372348708e-05, "loss": 0.0017, "step": 295070 }, { "epoch": 70.84, "learning_rate": 2.3966950660403863e-05, "loss": 0.0016, "step": 295080 }, { "epoch": 70.84, "learning_rate": 2.396388608263359e-05, "loss": 0.0024, "step": 295090 }, { "epoch": 70.84, "learning_rate": 2.3960821639053653e-05, "loss": 0.0016, "step": 295100 }, { "epoch": 70.85, "learning_rate": 2.395775732967986e-05, "loss": 0.0015, "step": 295110 }, { "epoch": 70.85, "learning_rate": 2.3954693154528012e-05, "loss": 0.0018, "step": 295120 }, { "epoch": 70.85, "learning_rate": 2.3951629113613883e-05, "loss": 0.002, "step": 295130 }, { "epoch": 70.85, "learning_rate": 2.3948565206953287e-05, "loss": 0.0017, "step": 295140 }, { "epoch": 70.85, "learning_rate": 2.3945501434561996e-05, "loss": 0.0016, "step": 295150 }, { "epoch": 70.86, "learning_rate": 2.3942437796455818e-05, "loss": 0.0019, "step": 295160 }, { "epoch": 70.86, "learning_rate": 2.393937429265052e-05, "loss": 0.0016, "step": 295170 }, { "epoch": 70.86, "learning_rate": 2.393631092316192e-05, "loss": 0.0017, "step": 295180 }, { "epoch": 70.86, "learning_rate": 2.393324768800579e-05, "loss": 0.0016, "step": 295190 }, { "epoch": 70.87, "learning_rate": 2.3930184587197903e-05, "loss": 0.0016, "step": 295200 }, { "epoch": 70.87, "learning_rate": 2.392712162075408e-05, "loss": 0.0017, "step": 295210 }, { "epoch": 70.87, "learning_rate": 2.3924058788690072e-05, "loss": 0.0015, "step": 295220 }, { "epoch": 70.87, "learning_rate": 2.3920996091021702e-05, "loss": 0.0055, "step": 295230 }, { "epoch": 70.88, "learning_rate": 2.391793352776472e-05, "loss": 0.0018, "step": 295240 }, { "epoch": 70.88, "learning_rate": 2.3914871098934937e-05, "loss": 0.0017, "step": 295250 }, { "epoch": 70.88, "learning_rate": 2.3911808804548135e-05, "loss": 0.0015, "step": 295260 }, { "epoch": 70.88, "learning_rate": 2.390874664462007e-05, "loss": 0.0015, "step": 295270 }, { "epoch": 70.88, "learning_rate": 2.3905684619166556e-05, "loss": 0.0016, "step": 295280 }, { "epoch": 70.89, "learning_rate": 2.3902622728203343e-05, "loss": 0.0016, "step": 295290 }, { "epoch": 70.89, "learning_rate": 2.3899560971746254e-05, "loss": 0.0029, "step": 295300 }, { "epoch": 70.89, "learning_rate": 2.3896499349811025e-05, "loss": 0.0245, "step": 295310 }, { "epoch": 70.89, "learning_rate": 2.3893437862413475e-05, "loss": 0.0017, "step": 295320 }, { "epoch": 70.9, "learning_rate": 2.389037650956936e-05, "loss": 0.0023, "step": 295330 }, { "epoch": 70.9, "learning_rate": 2.3887315291294453e-05, "loss": 0.0015, "step": 295340 }, { "epoch": 70.9, "learning_rate": 2.3884254207604555e-05, "loss": 0.0015, "step": 295350 }, { "epoch": 70.9, "learning_rate": 2.388119325851541e-05, "loss": 0.0017, "step": 295360 }, { "epoch": 70.9, "learning_rate": 2.3878132444042835e-05, "loss": 0.0018, "step": 295370 }, { "epoch": 70.91, "learning_rate": 2.3875071764202563e-05, "loss": 0.0015, "step": 295380 }, { "epoch": 70.91, "learning_rate": 2.3872011219010405e-05, "loss": 0.0017, "step": 295390 }, { "epoch": 70.91, "learning_rate": 2.3868950808482104e-05, "loss": 0.0014, "step": 295400 }, { "epoch": 70.91, "learning_rate": 2.3865890532633468e-05, "loss": 0.0017, "step": 295410 }, { "epoch": 70.92, "learning_rate": 2.3862830391480234e-05, "loss": 0.0017, "step": 295420 }, { "epoch": 70.92, "learning_rate": 2.385977038503819e-05, "loss": 0.0017, "step": 295430 }, { "epoch": 70.92, "learning_rate": 2.385671051332312e-05, "loss": 0.0017, "step": 295440 }, { "epoch": 70.92, "learning_rate": 2.3853650776350773e-05, "loss": 0.0026, "step": 295450 }, { "epoch": 70.93, "learning_rate": 2.3850591174136937e-05, "loss": 0.0021, "step": 295460 }, { "epoch": 70.93, "learning_rate": 2.384753170669738e-05, "loss": 0.0021, "step": 295470 }, { "epoch": 70.93, "learning_rate": 2.3844472374047844e-05, "loss": 0.0149, "step": 295480 }, { "epoch": 70.93, "learning_rate": 2.3841413176204135e-05, "loss": 0.0016, "step": 295490 }, { "epoch": 70.93, "learning_rate": 2.3838354113181982e-05, "loss": 0.0014, "step": 295500 }, { "epoch": 70.94, "learning_rate": 2.3835295184997185e-05, "loss": 0.0017, "step": 295510 }, { "epoch": 70.94, "learning_rate": 2.383223639166548e-05, "loss": 0.0016, "step": 295520 }, { "epoch": 70.94, "learning_rate": 2.382917773320267e-05, "loss": 0.0027, "step": 295530 }, { "epoch": 70.94, "learning_rate": 2.3826119209624494e-05, "loss": 0.0019, "step": 295540 }, { "epoch": 70.95, "learning_rate": 2.3823060820946697e-05, "loss": 0.0016, "step": 295550 }, { "epoch": 70.95, "learning_rate": 2.3820002567185084e-05, "loss": 0.0016, "step": 295560 }, { "epoch": 70.95, "learning_rate": 2.381694444835538e-05, "loss": 0.0017, "step": 295570 }, { "epoch": 71.0, "learning_rate": 2.3813886464473374e-05, "loss": 0.0018, "step": 295580 }, { "epoch": 71.0, "learning_rate": 2.3810828615554803e-05, "loss": 0.0015, "step": 295590 }, { "epoch": 71.01, "learning_rate": 2.3807770901615463e-05, "loss": 0.0019, "step": 295600 }, { "epoch": 71.01, "learning_rate": 2.3804713322671084e-05, "loss": 0.0013, "step": 295610 }, { "epoch": 71.01, "learning_rate": 2.380165587873741e-05, "loss": 0.0017, "step": 295620 }, { "epoch": 71.01, "learning_rate": 2.379859856983025e-05, "loss": 0.0017, "step": 295630 }, { "epoch": 71.02, "learning_rate": 2.3795541395965306e-05, "loss": 0.0017, "step": 295640 }, { "epoch": 71.02, "learning_rate": 2.379248435715838e-05, "loss": 0.0014, "step": 295650 }, { "epoch": 71.02, "learning_rate": 2.378942745342519e-05, "loss": 0.0016, "step": 295660 }, { "epoch": 71.02, "learning_rate": 2.3786370684781534e-05, "loss": 0.0021, "step": 295670 }, { "epoch": 71.02, "learning_rate": 2.3783314051243116e-05, "loss": 0.003, "step": 295680 }, { "epoch": 71.03, "learning_rate": 2.3780257552825742e-05, "loss": 0.0017, "step": 295690 }, { "epoch": 71.03, "learning_rate": 2.377720118954512e-05, "loss": 0.0018, "step": 295700 }, { "epoch": 71.03, "learning_rate": 2.3774144961417032e-05, "loss": 0.0016, "step": 295710 }, { "epoch": 71.03, "learning_rate": 2.377108886845721e-05, "loss": 0.0016, "step": 295720 }, { "epoch": 71.04, "learning_rate": 2.376803291068143e-05, "loss": 0.0014, "step": 295730 }, { "epoch": 71.04, "learning_rate": 2.376497708810541e-05, "loss": 0.0015, "step": 295740 }, { "epoch": 71.04, "learning_rate": 2.3761921400744926e-05, "loss": 0.0019, "step": 295750 }, { "epoch": 71.04, "learning_rate": 2.3758865848615725e-05, "loss": 0.0017, "step": 295760 }, { "epoch": 71.05, "learning_rate": 2.3755810431733555e-05, "loss": 0.0015, "step": 295770 }, { "epoch": 71.05, "learning_rate": 2.3752755150114138e-05, "loss": 0.0016, "step": 295780 }, { "epoch": 71.05, "learning_rate": 2.3749700003773258e-05, "loss": 0.0024, "step": 295790 }, { "epoch": 71.05, "learning_rate": 2.3746644992726623e-05, "loss": 0.0015, "step": 295800 }, { "epoch": 71.05, "learning_rate": 2.3743590116990022e-05, "loss": 0.0018, "step": 295810 }, { "epoch": 71.06, "learning_rate": 2.3740535376579152e-05, "loss": 0.0016, "step": 295820 }, { "epoch": 71.06, "learning_rate": 2.3737480771509805e-05, "loss": 0.0016, "step": 295830 }, { "epoch": 71.06, "learning_rate": 2.3734426301797702e-05, "loss": 0.0014, "step": 295840 }, { "epoch": 71.06, "learning_rate": 2.3731371967458564e-05, "loss": 0.0015, "step": 295850 }, { "epoch": 71.07, "learning_rate": 2.372831776850818e-05, "loss": 0.0017, "step": 295860 }, { "epoch": 71.07, "learning_rate": 2.3725263704962242e-05, "loss": 0.0017, "step": 295870 }, { "epoch": 71.07, "learning_rate": 2.3722209776836534e-05, "loss": 0.0015, "step": 295880 }, { "epoch": 71.07, "learning_rate": 2.3719155984146756e-05, "loss": 0.0014, "step": 295890 }, { "epoch": 71.07, "learning_rate": 2.371610232690869e-05, "loss": 0.0017, "step": 295900 }, { "epoch": 71.08, "learning_rate": 2.371304880513805e-05, "loss": 0.002, "step": 295910 }, { "epoch": 71.08, "learning_rate": 2.3709995418850557e-05, "loss": 0.0018, "step": 295920 }, { "epoch": 71.08, "learning_rate": 2.3706942168061985e-05, "loss": 0.0016, "step": 295930 }, { "epoch": 71.08, "learning_rate": 2.3703889052788037e-05, "loss": 0.0018, "step": 295940 }, { "epoch": 71.09, "learning_rate": 2.3700836073044486e-05, "loss": 0.0016, "step": 295950 }, { "epoch": 71.09, "learning_rate": 2.369778322884702e-05, "loss": 0.002, "step": 295960 }, { "epoch": 71.09, "learning_rate": 2.369473052021142e-05, "loss": 0.0087, "step": 295970 }, { "epoch": 71.09, "learning_rate": 2.36916779471534e-05, "loss": 0.0018, "step": 295980 }, { "epoch": 71.1, "learning_rate": 2.3688625509688673e-05, "loss": 0.0017, "step": 295990 }, { "epoch": 71.1, "learning_rate": 2.368557320783299e-05, "loss": 0.0021, "step": 296000 }, { "epoch": 71.1, "learning_rate": 2.36825210416021e-05, "loss": 0.0018, "step": 296010 }, { "epoch": 71.1, "learning_rate": 2.36794690110117e-05, "loss": 0.0016, "step": 296020 }, { "epoch": 71.1, "learning_rate": 2.3676417116077553e-05, "loss": 0.0017, "step": 296030 }, { "epoch": 71.11, "learning_rate": 2.3673365356815357e-05, "loss": 0.0018, "step": 296040 }, { "epoch": 71.11, "learning_rate": 2.3670313733240872e-05, "loss": 0.0017, "step": 296050 }, { "epoch": 71.11, "learning_rate": 2.3667262245369794e-05, "loss": 0.0019, "step": 296060 }, { "epoch": 71.11, "learning_rate": 2.3664210893217886e-05, "loss": 0.0016, "step": 296070 }, { "epoch": 71.12, "learning_rate": 2.366115967680083e-05, "loss": 0.0025, "step": 296080 }, { "epoch": 71.12, "learning_rate": 2.3658108596134404e-05, "loss": 0.0017, "step": 296090 }, { "epoch": 71.12, "learning_rate": 2.365505765123428e-05, "loss": 0.0021, "step": 296100 }, { "epoch": 71.12, "learning_rate": 2.3652006842116232e-05, "loss": 0.0016, "step": 296110 }, { "epoch": 71.12, "learning_rate": 2.364895616879596e-05, "loss": 0.0016, "step": 296120 }, { "epoch": 71.13, "learning_rate": 2.3645905631289173e-05, "loss": 0.0017, "step": 296130 }, { "epoch": 71.13, "learning_rate": 2.364285522961162e-05, "loss": 0.0015, "step": 296140 }, { "epoch": 71.13, "learning_rate": 2.3639804963778998e-05, "loss": 0.0016, "step": 296150 }, { "epoch": 71.13, "learning_rate": 2.363675483380706e-05, "loss": 0.0015, "step": 296160 }, { "epoch": 71.14, "learning_rate": 2.363370483971149e-05, "loss": 0.0015, "step": 296170 }, { "epoch": 71.14, "learning_rate": 2.363065498150804e-05, "loss": 0.0016, "step": 296180 }, { "epoch": 71.14, "learning_rate": 2.3627605259212422e-05, "loss": 0.0016, "step": 296190 }, { "epoch": 71.14, "learning_rate": 2.362455567284032e-05, "loss": 0.0016, "step": 296200 }, { "epoch": 71.15, "learning_rate": 2.36215062224075e-05, "loss": 0.0016, "step": 296210 }, { "epoch": 71.15, "learning_rate": 2.3618456907929643e-05, "loss": 0.0015, "step": 296220 }, { "epoch": 71.15, "learning_rate": 2.361540772942249e-05, "loss": 0.0016, "step": 296230 }, { "epoch": 71.15, "learning_rate": 2.3612358686901737e-05, "loss": 0.0016, "step": 296240 }, { "epoch": 71.15, "learning_rate": 2.3609309780383122e-05, "loss": 0.0014, "step": 296250 }, { "epoch": 71.16, "learning_rate": 2.360626100988234e-05, "loss": 0.0014, "step": 296260 }, { "epoch": 71.16, "learning_rate": 2.3603212375415096e-05, "loss": 0.0015, "step": 296270 }, { "epoch": 71.16, "learning_rate": 2.3600163876997134e-05, "loss": 0.0014, "step": 296280 }, { "epoch": 71.16, "learning_rate": 2.359711551464413e-05, "loss": 0.0015, "step": 296290 }, { "epoch": 71.17, "learning_rate": 2.3594067288371836e-05, "loss": 0.0014, "step": 296300 }, { "epoch": 71.17, "learning_rate": 2.359101919819591e-05, "loss": 0.0014, "step": 296310 }, { "epoch": 71.17, "learning_rate": 2.35879712441321e-05, "loss": 0.0017, "step": 296320 }, { "epoch": 71.17, "learning_rate": 2.3584923426196125e-05, "loss": 0.0014, "step": 296330 }, { "epoch": 71.18, "learning_rate": 2.3581875744403657e-05, "loss": 0.0112, "step": 296340 }, { "epoch": 71.18, "learning_rate": 2.3578828198770442e-05, "loss": 0.0015, "step": 296350 }, { "epoch": 71.18, "learning_rate": 2.3575780789312145e-05, "loss": 0.002, "step": 296360 }, { "epoch": 71.18, "learning_rate": 2.3572733516044515e-05, "loss": 0.0015, "step": 296370 }, { "epoch": 71.18, "learning_rate": 2.356968637898322e-05, "loss": 0.0018, "step": 296380 }, { "epoch": 71.19, "learning_rate": 2.3566639378144e-05, "loss": 0.0023, "step": 296390 }, { "epoch": 71.19, "learning_rate": 2.3563592513542544e-05, "loss": 0.0019, "step": 296400 }, { "epoch": 71.19, "learning_rate": 2.3560545785194527e-05, "loss": 0.0015, "step": 296410 }, { "epoch": 71.19, "learning_rate": 2.3557499193115702e-05, "loss": 0.0016, "step": 296420 }, { "epoch": 71.2, "learning_rate": 2.355445273732173e-05, "loss": 0.0018, "step": 296430 }, { "epoch": 71.2, "learning_rate": 2.355140641782835e-05, "loss": 0.0015, "step": 296440 }, { "epoch": 71.2, "learning_rate": 2.3548360234651217e-05, "loss": 0.0018, "step": 296450 }, { "epoch": 71.2, "learning_rate": 2.3545314187806078e-05, "loss": 0.002, "step": 296460 }, { "epoch": 71.2, "learning_rate": 2.3542268277308588e-05, "loss": 0.0016, "step": 296470 }, { "epoch": 71.21, "learning_rate": 2.3539222503174495e-05, "loss": 0.0016, "step": 296480 }, { "epoch": 71.21, "learning_rate": 2.353617686541947e-05, "loss": 0.0015, "step": 296490 }, { "epoch": 71.21, "learning_rate": 2.3533131364059187e-05, "loss": 0.0016, "step": 296500 }, { "epoch": 71.21, "learning_rate": 2.3530085999109387e-05, "loss": 0.0024, "step": 296510 }, { "epoch": 71.22, "learning_rate": 2.3527040770585723e-05, "loss": 0.0014, "step": 296520 }, { "epoch": 71.22, "learning_rate": 2.3523995678503935e-05, "loss": 0.0015, "step": 296530 }, { "epoch": 71.22, "learning_rate": 2.3520950722879676e-05, "loss": 0.0018, "step": 296540 }, { "epoch": 71.22, "learning_rate": 2.351790590372867e-05, "loss": 0.0015, "step": 296550 }, { "epoch": 71.23, "learning_rate": 2.3514861221066608e-05, "loss": 0.0015, "step": 296560 }, { "epoch": 71.23, "learning_rate": 2.351181667490915e-05, "loss": 0.0015, "step": 296570 }, { "epoch": 71.23, "learning_rate": 2.3508772265272028e-05, "loss": 0.0016, "step": 296580 }, { "epoch": 71.23, "learning_rate": 2.35057279921709e-05, "loss": 0.0016, "step": 296590 }, { "epoch": 71.23, "learning_rate": 2.3502683855621487e-05, "loss": 0.0017, "step": 296600 }, { "epoch": 71.24, "learning_rate": 2.3499639855639444e-05, "loss": 0.0016, "step": 296610 }, { "epoch": 71.24, "learning_rate": 2.34965959922405e-05, "loss": 0.0014, "step": 296620 }, { "epoch": 71.24, "learning_rate": 2.34935522654403e-05, "loss": 0.0014, "step": 296630 }, { "epoch": 71.24, "learning_rate": 2.3490508675254554e-05, "loss": 0.0014, "step": 296640 }, { "epoch": 71.25, "learning_rate": 2.3487465221698967e-05, "loss": 0.0014, "step": 296650 }, { "epoch": 71.25, "learning_rate": 2.3484421904789182e-05, "loss": 0.0014, "step": 296660 }, { "epoch": 71.25, "learning_rate": 2.3481378724540936e-05, "loss": 0.0015, "step": 296670 }, { "epoch": 71.25, "learning_rate": 2.3478335680969865e-05, "loss": 0.0016, "step": 296680 }, { "epoch": 71.26, "learning_rate": 2.347529277409169e-05, "loss": 0.0015, "step": 296690 }, { "epoch": 71.26, "learning_rate": 2.3472250003922076e-05, "loss": 0.0014, "step": 296700 }, { "epoch": 71.26, "learning_rate": 2.346920737047669e-05, "loss": 0.0016, "step": 296710 }, { "epoch": 71.26, "learning_rate": 2.346616487377125e-05, "loss": 0.0016, "step": 296720 }, { "epoch": 71.26, "learning_rate": 2.34631225138214e-05, "loss": 0.0015, "step": 296730 }, { "epoch": 71.27, "learning_rate": 2.3460080290642857e-05, "loss": 0.0017, "step": 296740 }, { "epoch": 71.27, "learning_rate": 2.3457038204251265e-05, "loss": 0.0014, "step": 296750 }, { "epoch": 71.27, "learning_rate": 2.3453996254662334e-05, "loss": 0.0013, "step": 296760 }, { "epoch": 71.27, "learning_rate": 2.3450954441891732e-05, "loss": 0.0016, "step": 296770 }, { "epoch": 71.28, "learning_rate": 2.344791276595511e-05, "loss": 0.0015, "step": 296780 }, { "epoch": 71.28, "learning_rate": 2.3444871226868194e-05, "loss": 0.0015, "step": 296790 }, { "epoch": 71.28, "learning_rate": 2.3441829824646604e-05, "loss": 0.0016, "step": 296800 }, { "epoch": 71.28, "learning_rate": 2.3438788559306074e-05, "loss": 0.0015, "step": 296810 }, { "epoch": 71.28, "learning_rate": 2.3435747430862226e-05, "loss": 0.0014, "step": 296820 }, { "epoch": 71.29, "learning_rate": 2.3432706439330775e-05, "loss": 0.0015, "step": 296830 }, { "epoch": 71.29, "learning_rate": 2.3429665584727384e-05, "loss": 0.0015, "step": 296840 }, { "epoch": 71.29, "learning_rate": 2.342662486706769e-05, "loss": 0.0013, "step": 296850 }, { "epoch": 71.29, "learning_rate": 2.3423584286367423e-05, "loss": 0.0015, "step": 296860 }, { "epoch": 71.3, "learning_rate": 2.34205438426422e-05, "loss": 0.0015, "step": 296870 }, { "epoch": 71.3, "learning_rate": 2.3417503535907736e-05, "loss": 0.0015, "step": 296880 }, { "epoch": 71.3, "learning_rate": 2.341446336617966e-05, "loss": 0.0176, "step": 296890 }, { "epoch": 71.3, "learning_rate": 2.341142333347368e-05, "loss": 0.0014, "step": 296900 }, { "epoch": 71.31, "learning_rate": 2.3408383437805433e-05, "loss": 0.0064, "step": 296910 }, { "epoch": 71.31, "learning_rate": 2.3405343679190616e-05, "loss": 0.0021, "step": 296920 }, { "epoch": 71.31, "learning_rate": 2.340230405764486e-05, "loss": 0.0014, "step": 296930 }, { "epoch": 71.31, "learning_rate": 2.3399264573183854e-05, "loss": 0.0016, "step": 296940 }, { "epoch": 71.31, "learning_rate": 2.3396225225823276e-05, "loss": 0.0014, "step": 296950 }, { "epoch": 71.32, "learning_rate": 2.3393186015578762e-05, "loss": 0.0014, "step": 296960 }, { "epoch": 71.32, "learning_rate": 2.3390146942466002e-05, "loss": 0.0014, "step": 296970 }, { "epoch": 71.32, "learning_rate": 2.3387108006500653e-05, "loss": 0.0217, "step": 296980 }, { "epoch": 71.32, "learning_rate": 2.338406920769835e-05, "loss": 0.0015, "step": 296990 }, { "epoch": 71.33, "learning_rate": 2.3381030546074796e-05, "loss": 0.0015, "step": 297000 }, { "epoch": 71.33, "learning_rate": 2.3377992021645612e-05, "loss": 0.0013, "step": 297010 }, { "epoch": 71.33, "learning_rate": 2.33749536344265e-05, "loss": 0.0015, "step": 297020 }, { "epoch": 71.33, "learning_rate": 2.3371915384433086e-05, "loss": 0.0015, "step": 297030 }, { "epoch": 71.34, "learning_rate": 2.3368877271681057e-05, "loss": 0.0015, "step": 297040 }, { "epoch": 71.34, "learning_rate": 2.3365839296186055e-05, "loss": 0.0014, "step": 297050 }, { "epoch": 71.34, "learning_rate": 2.3362801457963723e-05, "loss": 0.0016, "step": 297060 }, { "epoch": 71.34, "learning_rate": 2.3359763757029752e-05, "loss": 0.0017, "step": 297070 }, { "epoch": 71.34, "learning_rate": 2.3356726193399764e-05, "loss": 0.0018, "step": 297080 }, { "epoch": 71.35, "learning_rate": 2.3353688767089453e-05, "loss": 0.002, "step": 297090 }, { "epoch": 71.35, "learning_rate": 2.335065147811443e-05, "loss": 0.0015, "step": 297100 }, { "epoch": 71.35, "learning_rate": 2.3347614326490393e-05, "loss": 0.0014, "step": 297110 }, { "epoch": 71.35, "learning_rate": 2.3344577312232974e-05, "loss": 0.0015, "step": 297120 }, { "epoch": 71.36, "learning_rate": 2.3341540435357807e-05, "loss": 0.0015, "step": 297130 }, { "epoch": 71.36, "learning_rate": 2.3338503695880587e-05, "loss": 0.0015, "step": 297140 }, { "epoch": 71.36, "learning_rate": 2.3335467093816915e-05, "loss": 0.0014, "step": 297150 }, { "epoch": 71.36, "learning_rate": 2.3332430629182493e-05, "loss": 0.0016, "step": 297160 }, { "epoch": 71.36, "learning_rate": 2.3329394301992925e-05, "loss": 0.0013, "step": 297170 }, { "epoch": 71.37, "learning_rate": 2.3326358112263903e-05, "loss": 0.0017, "step": 297180 }, { "epoch": 71.37, "learning_rate": 2.3323322060011055e-05, "loss": 0.0019, "step": 297190 }, { "epoch": 71.37, "learning_rate": 2.3320286145250002e-05, "loss": 0.0014, "step": 297200 }, { "epoch": 71.37, "learning_rate": 2.3317250367996423e-05, "loss": 0.0017, "step": 297210 }, { "epoch": 71.38, "learning_rate": 2.3314214728265975e-05, "loss": 0.0019, "step": 297220 }, { "epoch": 71.38, "learning_rate": 2.3311179226074277e-05, "loss": 0.0014, "step": 297230 }, { "epoch": 71.38, "learning_rate": 2.3308143861436992e-05, "loss": 0.0015, "step": 297240 }, { "epoch": 71.38, "learning_rate": 2.3305108634369744e-05, "loss": 0.0015, "step": 297250 }, { "epoch": 71.39, "learning_rate": 2.3302073544888185e-05, "loss": 0.0016, "step": 297260 }, { "epoch": 71.39, "learning_rate": 2.329903859300799e-05, "loss": 0.002, "step": 297270 }, { "epoch": 71.39, "learning_rate": 2.329600377874476e-05, "loss": 0.0016, "step": 297280 }, { "epoch": 71.39, "learning_rate": 2.3292969102114142e-05, "loss": 0.0016, "step": 297290 }, { "epoch": 71.39, "learning_rate": 2.3289934563131798e-05, "loss": 0.0016, "step": 297300 }, { "epoch": 71.4, "learning_rate": 2.3286900161813334e-05, "loss": 0.0015, "step": 297310 }, { "epoch": 71.4, "learning_rate": 2.3283865898174435e-05, "loss": 0.0016, "step": 297320 }, { "epoch": 71.4, "learning_rate": 2.328083177223069e-05, "loss": 0.0015, "step": 297330 }, { "epoch": 71.4, "learning_rate": 2.3277797783997783e-05, "loss": 0.0013, "step": 297340 }, { "epoch": 71.41, "learning_rate": 2.327476393349133e-05, "loss": 0.0026, "step": 297350 }, { "epoch": 71.41, "learning_rate": 2.3271730220726945e-05, "loss": 0.0016, "step": 297360 }, { "epoch": 71.41, "learning_rate": 2.3268696645720306e-05, "loss": 0.0016, "step": 297370 }, { "epoch": 71.41, "learning_rate": 2.326566320848701e-05, "loss": 0.0014, "step": 297380 }, { "epoch": 71.42, "learning_rate": 2.3262629909042728e-05, "loss": 0.0014, "step": 297390 }, { "epoch": 71.42, "learning_rate": 2.3259596747403057e-05, "loss": 0.0016, "step": 297400 }, { "epoch": 71.42, "learning_rate": 2.3256563723583664e-05, "loss": 0.0027, "step": 297410 }, { "epoch": 71.42, "learning_rate": 2.3253530837600167e-05, "loss": 0.0013, "step": 297420 }, { "epoch": 71.42, "learning_rate": 2.3250498089468175e-05, "loss": 0.0022, "step": 297430 }, { "epoch": 71.43, "learning_rate": 2.3247465479203362e-05, "loss": 0.0017, "step": 297440 }, { "epoch": 71.43, "learning_rate": 2.3244433006821313e-05, "loss": 0.0018, "step": 297450 }, { "epoch": 71.43, "learning_rate": 2.3241400672337705e-05, "loss": 0.0016, "step": 297460 }, { "epoch": 71.43, "learning_rate": 2.323836847576812e-05, "loss": 0.0016, "step": 297470 }, { "epoch": 71.44, "learning_rate": 2.3235336417128222e-05, "loss": 0.0016, "step": 297480 }, { "epoch": 71.44, "learning_rate": 2.3232304496433625e-05, "loss": 0.0018, "step": 297490 }, { "epoch": 71.44, "learning_rate": 2.3229272713699934e-05, "loss": 0.0015, "step": 297500 }, { "epoch": 71.44, "learning_rate": 2.32262410689428e-05, "loss": 0.0015, "step": 297510 }, { "epoch": 71.44, "learning_rate": 2.322320956217786e-05, "loss": 0.0016, "step": 297520 }, { "epoch": 71.45, "learning_rate": 2.3220178193420707e-05, "loss": 0.0022, "step": 297530 }, { "epoch": 71.45, "learning_rate": 2.3217146962686993e-05, "loss": 0.0014, "step": 297540 }, { "epoch": 71.45, "learning_rate": 2.321411586999231e-05, "loss": 0.0018, "step": 297550 }, { "epoch": 71.45, "learning_rate": 2.3211084915352316e-05, "loss": 0.0017, "step": 297560 }, { "epoch": 71.46, "learning_rate": 2.3208054098782595e-05, "loss": 0.0017, "step": 297570 }, { "epoch": 71.46, "learning_rate": 2.3205023420298804e-05, "loss": 0.0014, "step": 297580 }, { "epoch": 71.46, "learning_rate": 2.3201992879916535e-05, "loss": 0.0016, "step": 297590 }, { "epoch": 71.46, "learning_rate": 2.3198962477651432e-05, "loss": 0.002, "step": 297600 }, { "epoch": 71.47, "learning_rate": 2.3195932213519083e-05, "loss": 0.0016, "step": 297610 }, { "epoch": 71.47, "learning_rate": 2.319290208753514e-05, "loss": 0.0015, "step": 297620 }, { "epoch": 71.47, "learning_rate": 2.3189872099715205e-05, "loss": 0.0015, "step": 297630 }, { "epoch": 71.47, "learning_rate": 2.3186842250074875e-05, "loss": 0.0014, "step": 297640 }, { "epoch": 71.47, "learning_rate": 2.3183812538629806e-05, "loss": 0.0016, "step": 297650 }, { "epoch": 71.48, "learning_rate": 2.318078296539557e-05, "loss": 0.0015, "step": 297660 }, { "epoch": 71.48, "learning_rate": 2.3177753530387818e-05, "loss": 0.0015, "step": 297670 }, { "epoch": 71.48, "learning_rate": 2.3174724233622135e-05, "loss": 0.0015, "step": 297680 }, { "epoch": 71.48, "learning_rate": 2.3171695075114164e-05, "loss": 0.0015, "step": 297690 }, { "epoch": 71.49, "learning_rate": 2.31686660548795e-05, "loss": 0.0014, "step": 297700 }, { "epoch": 71.49, "learning_rate": 2.3165637172933735e-05, "loss": 0.0017, "step": 297710 }, { "epoch": 71.49, "learning_rate": 2.3162608429292526e-05, "loss": 0.0016, "step": 297720 }, { "epoch": 71.49, "learning_rate": 2.3159579823971432e-05, "loss": 0.0015, "step": 297730 }, { "epoch": 71.5, "learning_rate": 2.3156551356986112e-05, "loss": 0.0013, "step": 297740 }, { "epoch": 71.5, "learning_rate": 2.3153523028352125e-05, "loss": 0.0016, "step": 297750 }, { "epoch": 71.5, "learning_rate": 2.315049483808513e-05, "loss": 0.0013, "step": 297760 }, { "epoch": 71.5, "learning_rate": 2.3147466786200706e-05, "loss": 0.0015, "step": 297770 }, { "epoch": 71.5, "learning_rate": 2.3144438872714443e-05, "loss": 0.0014, "step": 297780 }, { "epoch": 71.51, "learning_rate": 2.3141411097641986e-05, "loss": 0.0014, "step": 297790 }, { "epoch": 71.51, "learning_rate": 2.3138383460998903e-05, "loss": 0.0014, "step": 297800 }, { "epoch": 71.51, "learning_rate": 2.3135355962800836e-05, "loss": 0.0012, "step": 297810 }, { "epoch": 71.51, "learning_rate": 2.3132328603063347e-05, "loss": 0.0023, "step": 297820 }, { "epoch": 71.52, "learning_rate": 2.3129301381802064e-05, "loss": 0.0014, "step": 297830 }, { "epoch": 71.52, "learning_rate": 2.3126274299032603e-05, "loss": 0.0016, "step": 297840 }, { "epoch": 71.52, "learning_rate": 2.3123247354770532e-05, "loss": 0.0015, "step": 297850 }, { "epoch": 71.52, "learning_rate": 2.3120220549031483e-05, "loss": 0.0013, "step": 297860 }, { "epoch": 71.52, "learning_rate": 2.311719388183103e-05, "loss": 0.0015, "step": 297870 }, { "epoch": 71.53, "learning_rate": 2.3114167353184797e-05, "loss": 0.0017, "step": 297880 }, { "epoch": 71.53, "learning_rate": 2.3111140963108356e-05, "loss": 0.0021, "step": 297890 }, { "epoch": 71.53, "learning_rate": 2.3108114711617334e-05, "loss": 0.002, "step": 297900 }, { "epoch": 71.53, "learning_rate": 2.3105088598727316e-05, "loss": 0.0016, "step": 297910 }, { "epoch": 71.54, "learning_rate": 2.310206262445388e-05, "loss": 0.0015, "step": 297920 }, { "epoch": 71.54, "learning_rate": 2.309903678881265e-05, "loss": 0.0018, "step": 297930 }, { "epoch": 71.54, "learning_rate": 2.30960110918192e-05, "loss": 0.0016, "step": 297940 }, { "epoch": 71.54, "learning_rate": 2.3092985533489143e-05, "loss": 0.0067, "step": 297950 }, { "epoch": 71.55, "learning_rate": 2.3089960113838048e-05, "loss": 0.0021, "step": 297960 }, { "epoch": 71.55, "learning_rate": 2.3086934832881545e-05, "loss": 0.0017, "step": 297970 }, { "epoch": 71.55, "learning_rate": 2.3083909690635204e-05, "loss": 0.0018, "step": 297980 }, { "epoch": 71.55, "learning_rate": 2.3080884687114595e-05, "loss": 0.0017, "step": 297990 }, { "epoch": 71.55, "learning_rate": 2.3077859822335353e-05, "loss": 0.0021, "step": 298000 }, { "epoch": 71.56, "learning_rate": 2.3074835096313024e-05, "loss": 0.0019, "step": 298010 }, { "epoch": 71.56, "learning_rate": 2.3071810509063246e-05, "loss": 0.0022, "step": 298020 }, { "epoch": 71.56, "learning_rate": 2.3068786060601562e-05, "loss": 0.0036, "step": 298030 }, { "epoch": 71.56, "learning_rate": 2.3065761750943594e-05, "loss": 0.002, "step": 298040 }, { "epoch": 71.57, "learning_rate": 2.3062737580104893e-05, "loss": 0.0016, "step": 298050 }, { "epoch": 71.57, "learning_rate": 2.3059713548101093e-05, "loss": 0.0017, "step": 298060 }, { "epoch": 71.57, "learning_rate": 2.3056689654947754e-05, "loss": 0.0017, "step": 298070 }, { "epoch": 71.57, "learning_rate": 2.3053665900660443e-05, "loss": 0.0017, "step": 298080 }, { "epoch": 71.58, "learning_rate": 2.305064228525478e-05, "loss": 0.0015, "step": 298090 }, { "epoch": 71.58, "learning_rate": 2.3047618808746315e-05, "loss": 0.0017, "step": 298100 }, { "epoch": 71.58, "learning_rate": 2.3044595471150665e-05, "loss": 0.0029, "step": 298110 }, { "epoch": 71.58, "learning_rate": 2.3041572272483374e-05, "loss": 0.0017, "step": 298120 }, { "epoch": 71.58, "learning_rate": 2.3038549212760067e-05, "loss": 0.0015, "step": 298130 }, { "epoch": 71.59, "learning_rate": 2.3035526291996283e-05, "loss": 0.0018, "step": 298140 }, { "epoch": 71.59, "learning_rate": 2.3032503510207624e-05, "loss": 0.0015, "step": 298150 }, { "epoch": 71.59, "learning_rate": 2.3029480867409686e-05, "loss": 0.0016, "step": 298160 }, { "epoch": 71.59, "learning_rate": 2.302645836361801e-05, "loss": 0.0018, "step": 298170 }, { "epoch": 71.6, "learning_rate": 2.3023435998848207e-05, "loss": 0.0016, "step": 298180 }, { "epoch": 71.6, "learning_rate": 2.3020413773115827e-05, "loss": 0.0023, "step": 298190 }, { "epoch": 71.6, "learning_rate": 2.301739168643648e-05, "loss": 0.0016, "step": 298200 }, { "epoch": 71.6, "learning_rate": 2.3014369738825714e-05, "loss": 0.0017, "step": 298210 }, { "epoch": 71.6, "learning_rate": 2.3011347930299098e-05, "loss": 0.0016, "step": 298220 }, { "epoch": 71.61, "learning_rate": 2.3008326260872242e-05, "loss": 0.0017, "step": 298230 }, { "epoch": 71.61, "learning_rate": 2.300530473056067e-05, "loss": 0.0017, "step": 298240 }, { "epoch": 71.61, "learning_rate": 2.3002283339380015e-05, "loss": 0.0051, "step": 298250 }, { "epoch": 71.61, "learning_rate": 2.299926208734579e-05, "loss": 0.0017, "step": 298260 }, { "epoch": 71.62, "learning_rate": 2.2996240974473616e-05, "loss": 0.0016, "step": 298270 }, { "epoch": 71.62, "learning_rate": 2.2993220000779037e-05, "loss": 0.0017, "step": 298280 }, { "epoch": 71.62, "learning_rate": 2.2990199166277615e-05, "loss": 0.0017, "step": 298290 }, { "epoch": 71.62, "learning_rate": 2.2987178470984948e-05, "loss": 0.0017, "step": 298300 }, { "epoch": 71.63, "learning_rate": 2.298415791491657e-05, "loss": 0.0015, "step": 298310 }, { "epoch": 71.63, "learning_rate": 2.2981137498088086e-05, "loss": 0.0017, "step": 298320 }, { "epoch": 71.63, "learning_rate": 2.297811722051503e-05, "loss": 0.0016, "step": 298330 }, { "epoch": 71.63, "learning_rate": 2.2975097082213e-05, "loss": 0.0016, "step": 298340 }, { "epoch": 71.63, "learning_rate": 2.297207708319754e-05, "loss": 0.0018, "step": 298350 }, { "epoch": 71.64, "learning_rate": 2.2969057223484208e-05, "loss": 0.0016, "step": 298360 }, { "epoch": 71.64, "learning_rate": 2.29660375030886e-05, "loss": 0.0018, "step": 298370 }, { "epoch": 71.64, "learning_rate": 2.2963017922026243e-05, "loss": 0.0026, "step": 298380 }, { "epoch": 71.64, "learning_rate": 2.2959998480312735e-05, "loss": 0.0016, "step": 298390 }, { "epoch": 71.65, "learning_rate": 2.29569791779636e-05, "loss": 0.0023, "step": 298400 }, { "epoch": 71.65, "learning_rate": 2.295396001499444e-05, "loss": 0.0016, "step": 298410 }, { "epoch": 71.65, "learning_rate": 2.2950940991420782e-05, "loss": 0.0025, "step": 298420 }, { "epoch": 71.65, "learning_rate": 2.2947922107258215e-05, "loss": 0.0021, "step": 298430 }, { "epoch": 71.66, "learning_rate": 2.2944903362522264e-05, "loss": 0.0054, "step": 298440 }, { "epoch": 71.66, "learning_rate": 2.2941884757228526e-05, "loss": 0.0016, "step": 298450 }, { "epoch": 71.66, "learning_rate": 2.2938866291392526e-05, "loss": 0.002, "step": 298460 }, { "epoch": 71.66, "learning_rate": 2.2935847965029828e-05, "loss": 0.0016, "step": 298470 }, { "epoch": 71.66, "learning_rate": 2.2932829778156017e-05, "loss": 0.0041, "step": 298480 }, { "epoch": 71.67, "learning_rate": 2.2929811730786632e-05, "loss": 0.0015, "step": 298490 }, { "epoch": 71.67, "learning_rate": 2.2926793822937197e-05, "loss": 0.0019, "step": 298500 }, { "epoch": 71.67, "learning_rate": 2.292377605462332e-05, "loss": 0.0017, "step": 298510 }, { "epoch": 71.67, "learning_rate": 2.2920758425860506e-05, "loss": 0.0016, "step": 298520 }, { "epoch": 71.68, "learning_rate": 2.2917740936664346e-05, "loss": 0.0018, "step": 298530 }, { "epoch": 71.68, "learning_rate": 2.291472358705036e-05, "loss": 0.0016, "step": 298540 }, { "epoch": 71.68, "learning_rate": 2.291170637703413e-05, "loss": 0.0017, "step": 298550 }, { "epoch": 71.68, "learning_rate": 2.2908689306631192e-05, "loss": 0.0017, "step": 298560 }, { "epoch": 71.68, "learning_rate": 2.290567237585708e-05, "loss": 0.0016, "step": 298570 }, { "epoch": 71.69, "learning_rate": 2.290265558472738e-05, "loss": 0.0018, "step": 298580 }, { "epoch": 71.69, "learning_rate": 2.2899638933257595e-05, "loss": 0.0015, "step": 298590 }, { "epoch": 71.69, "learning_rate": 2.2896622421463314e-05, "loss": 0.0015, "step": 298600 }, { "epoch": 71.69, "learning_rate": 2.2893606049360056e-05, "loss": 0.0015, "step": 298610 }, { "epoch": 71.7, "learning_rate": 2.2890589816963393e-05, "loss": 0.0014, "step": 298620 }, { "epoch": 71.7, "learning_rate": 2.2887573724288865e-05, "loss": 0.0015, "step": 298630 }, { "epoch": 71.7, "learning_rate": 2.2884557771351977e-05, "loss": 0.0017, "step": 298640 }, { "epoch": 71.7, "learning_rate": 2.2881541958168335e-05, "loss": 0.0015, "step": 298650 }, { "epoch": 71.71, "learning_rate": 2.2878526284753428e-05, "loss": 0.0029, "step": 298660 }, { "epoch": 71.71, "learning_rate": 2.2875510751122843e-05, "loss": 0.0073, "step": 298670 }, { "epoch": 71.71, "learning_rate": 2.2872495357292085e-05, "loss": 0.0059, "step": 298680 }, { "epoch": 71.71, "learning_rate": 2.286948010327673e-05, "loss": 0.0016, "step": 298690 }, { "epoch": 71.71, "learning_rate": 2.2866464989092302e-05, "loss": 0.0015, "step": 298700 }, { "epoch": 71.72, "learning_rate": 2.2863450014754317e-05, "loss": 0.0015, "step": 298710 }, { "epoch": 71.72, "learning_rate": 2.2860435180278343e-05, "loss": 0.0017, "step": 298720 }, { "epoch": 71.72, "learning_rate": 2.285742048567993e-05, "loss": 0.0014, "step": 298730 }, { "epoch": 71.72, "learning_rate": 2.2854405930974576e-05, "loss": 0.0017, "step": 298740 }, { "epoch": 71.73, "learning_rate": 2.2851391516177868e-05, "loss": 0.0018, "step": 298750 }, { "epoch": 71.73, "learning_rate": 2.284837724130529e-05, "loss": 0.0016, "step": 298760 }, { "epoch": 71.73, "learning_rate": 2.2845363106372426e-05, "loss": 0.0016, "step": 298770 }, { "epoch": 71.73, "learning_rate": 2.284234911139476e-05, "loss": 0.0016, "step": 298780 }, { "epoch": 71.74, "learning_rate": 2.2839335256387883e-05, "loss": 0.0017, "step": 298790 }, { "epoch": 71.74, "learning_rate": 2.2836321541367272e-05, "loss": 0.0017, "step": 298800 }, { "epoch": 71.74, "learning_rate": 2.283330796634851e-05, "loss": 0.0015, "step": 298810 }, { "epoch": 71.74, "learning_rate": 2.2830294531347086e-05, "loss": 0.0015, "step": 298820 }, { "epoch": 71.74, "learning_rate": 2.2827281236378573e-05, "loss": 0.0016, "step": 298830 }, { "epoch": 71.75, "learning_rate": 2.2824268081458454e-05, "loss": 0.0019, "step": 298840 }, { "epoch": 71.75, "learning_rate": 2.282125506660231e-05, "loss": 0.0015, "step": 298850 }, { "epoch": 71.75, "learning_rate": 2.281824219182564e-05, "loss": 0.0015, "step": 298860 }, { "epoch": 71.75, "learning_rate": 2.281522945714396e-05, "loss": 0.0016, "step": 298870 }, { "epoch": 71.76, "learning_rate": 2.2812216862572833e-05, "loss": 0.0015, "step": 298880 }, { "epoch": 71.76, "learning_rate": 2.2809204408127748e-05, "loss": 0.0021, "step": 298890 }, { "epoch": 71.76, "learning_rate": 2.2806192093824274e-05, "loss": 0.0029, "step": 298900 }, { "epoch": 71.76, "learning_rate": 2.2803179919677892e-05, "loss": 0.0016, "step": 298910 }, { "epoch": 71.76, "learning_rate": 2.2800167885704164e-05, "loss": 0.0017, "step": 298920 }, { "epoch": 71.77, "learning_rate": 2.27971559919186e-05, "loss": 0.0015, "step": 298930 }, { "epoch": 71.77, "learning_rate": 2.27941442383367e-05, "loss": 0.0018, "step": 298940 }, { "epoch": 71.77, "learning_rate": 2.279113262497403e-05, "loss": 0.0016, "step": 298950 }, { "epoch": 71.77, "learning_rate": 2.2788121151846076e-05, "loss": 0.0146, "step": 298960 }, { "epoch": 71.78, "learning_rate": 2.2785109818968385e-05, "loss": 0.0017, "step": 298970 }, { "epoch": 71.78, "learning_rate": 2.2782098626356447e-05, "loss": 0.0015, "step": 298980 }, { "epoch": 71.78, "learning_rate": 2.277908757402582e-05, "loss": 0.0013, "step": 298990 }, { "epoch": 71.78, "learning_rate": 2.2776076661992e-05, "loss": 0.0016, "step": 299000 }, { "epoch": 71.79, "learning_rate": 2.2773065890270494e-05, "loss": 0.0016, "step": 299010 }, { "epoch": 71.79, "learning_rate": 2.2770055258876854e-05, "loss": 0.0017, "step": 299020 }, { "epoch": 71.79, "learning_rate": 2.2767044767826555e-05, "loss": 0.0018, "step": 299030 }, { "epoch": 71.79, "learning_rate": 2.2764034417135138e-05, "loss": 0.0017, "step": 299040 }, { "epoch": 71.79, "learning_rate": 2.276102420681813e-05, "loss": 0.0035, "step": 299050 }, { "epoch": 71.8, "learning_rate": 2.2758014136891014e-05, "loss": 0.0013, "step": 299060 }, { "epoch": 71.8, "learning_rate": 2.275500420736934e-05, "loss": 0.0015, "step": 299070 }, { "epoch": 71.8, "learning_rate": 2.2751994418268578e-05, "loss": 0.0015, "step": 299080 }, { "epoch": 71.8, "learning_rate": 2.274898476960429e-05, "loss": 0.0015, "step": 299090 }, { "epoch": 71.81, "learning_rate": 2.2745975261391945e-05, "loss": 0.0014, "step": 299100 }, { "epoch": 71.81, "learning_rate": 2.2742965893647084e-05, "loss": 0.0017, "step": 299110 }, { "epoch": 71.81, "learning_rate": 2.2739956666385186e-05, "loss": 0.0015, "step": 299120 }, { "epoch": 71.81, "learning_rate": 2.2736947579621804e-05, "loss": 0.0014, "step": 299130 }, { "epoch": 71.82, "learning_rate": 2.2733938633372413e-05, "loss": 0.0015, "step": 299140 }, { "epoch": 71.82, "learning_rate": 2.273092982765252e-05, "loss": 0.0015, "step": 299150 }, { "epoch": 71.82, "learning_rate": 2.272792116247766e-05, "loss": 0.0017, "step": 299160 }, { "epoch": 71.82, "learning_rate": 2.27249126378633e-05, "loss": 0.0015, "step": 299170 }, { "epoch": 71.82, "learning_rate": 2.2721904253824987e-05, "loss": 0.0017, "step": 299180 }, { "epoch": 71.83, "learning_rate": 2.2718896010378193e-05, "loss": 0.0022, "step": 299190 }, { "epoch": 71.83, "learning_rate": 2.2715887907538454e-05, "loss": 0.0015, "step": 299200 }, { "epoch": 71.83, "learning_rate": 2.2712879945321258e-05, "loss": 0.0017, "step": 299210 }, { "epoch": 71.83, "learning_rate": 2.2709872123742082e-05, "loss": 0.0016, "step": 299220 }, { "epoch": 71.84, "learning_rate": 2.2706864442816478e-05, "loss": 0.0025, "step": 299230 }, { "epoch": 71.84, "learning_rate": 2.27038569025599e-05, "loss": 0.0013, "step": 299240 }, { "epoch": 71.84, "learning_rate": 2.2700849502987892e-05, "loss": 0.0017, "step": 299250 }, { "epoch": 71.84, "learning_rate": 2.2697842244115918e-05, "loss": 0.0019, "step": 299260 }, { "epoch": 71.84, "learning_rate": 2.2694835125959506e-05, "loss": 0.0025, "step": 299270 }, { "epoch": 71.85, "learning_rate": 2.269182814853415e-05, "loss": 0.0038, "step": 299280 }, { "epoch": 71.85, "learning_rate": 2.2688821311855318e-05, "loss": 0.0015, "step": 299290 }, { "epoch": 71.85, "learning_rate": 2.2685814615938545e-05, "loss": 0.0015, "step": 299300 }, { "epoch": 71.85, "learning_rate": 2.2682808060799294e-05, "loss": 0.0039, "step": 299310 }, { "epoch": 71.86, "learning_rate": 2.2679801646453098e-05, "loss": 0.0021, "step": 299320 }, { "epoch": 71.86, "learning_rate": 2.2676795372915416e-05, "loss": 0.0016, "step": 299330 }, { "epoch": 71.86, "learning_rate": 2.267378924020176e-05, "loss": 0.0015, "step": 299340 }, { "epoch": 71.86, "learning_rate": 2.2670783248327637e-05, "loss": 0.0014, "step": 299350 }, { "epoch": 71.87, "learning_rate": 2.266777739730851e-05, "loss": 0.0016, "step": 299360 }, { "epoch": 71.87, "learning_rate": 2.26647716871599e-05, "loss": 0.0014, "step": 299370 }, { "epoch": 71.87, "learning_rate": 2.266176611789727e-05, "loss": 0.0013, "step": 299380 }, { "epoch": 71.87, "learning_rate": 2.2658760689536147e-05, "loss": 0.0017, "step": 299390 }, { "epoch": 71.87, "learning_rate": 2.2655755402091976e-05, "loss": 0.0015, "step": 299400 }, { "epoch": 71.88, "learning_rate": 2.2652750255580297e-05, "loss": 0.0017, "step": 299410 }, { "epoch": 71.88, "learning_rate": 2.2649745250016564e-05, "loss": 0.0014, "step": 299420 }, { "epoch": 71.88, "learning_rate": 2.2646740385416258e-05, "loss": 0.0015, "step": 299430 }, { "epoch": 71.88, "learning_rate": 2.2643735661794896e-05, "loss": 0.0015, "step": 299440 }, { "epoch": 71.89, "learning_rate": 2.2640731079167938e-05, "loss": 0.0016, "step": 299450 }, { "epoch": 71.89, "learning_rate": 2.2637726637550894e-05, "loss": 0.0022, "step": 299460 }, { "epoch": 71.89, "learning_rate": 2.2634722336959212e-05, "loss": 0.0016, "step": 299470 }, { "epoch": 71.89, "learning_rate": 2.2631718177408423e-05, "loss": 0.0015, "step": 299480 }, { "epoch": 71.9, "learning_rate": 2.262871415891399e-05, "loss": 0.0018, "step": 299490 }, { "epoch": 71.9, "learning_rate": 2.2625710281491376e-05, "loss": 0.0016, "step": 299500 }, { "epoch": 71.9, "learning_rate": 2.2622706545156093e-05, "loss": 0.0016, "step": 299510 }, { "epoch": 71.9, "learning_rate": 2.2619702949923593e-05, "loss": 0.0019, "step": 299520 }, { "epoch": 71.9, "learning_rate": 2.261669949580939e-05, "loss": 0.0017, "step": 299530 }, { "epoch": 71.91, "learning_rate": 2.261369618282893e-05, "loss": 0.0015, "step": 299540 }, { "epoch": 71.91, "learning_rate": 2.2610693010997724e-05, "loss": 0.0039, "step": 299550 }, { "epoch": 71.91, "learning_rate": 2.2607689980331237e-05, "loss": 0.0017, "step": 299560 }, { "epoch": 71.91, "learning_rate": 2.260468709084493e-05, "loss": 0.0015, "step": 299570 }, { "epoch": 71.92, "learning_rate": 2.2601684342554307e-05, "loss": 0.002, "step": 299580 }, { "epoch": 71.92, "learning_rate": 2.259868173547482e-05, "loss": 0.0019, "step": 299590 }, { "epoch": 71.92, "learning_rate": 2.2595679269621968e-05, "loss": 0.0021, "step": 299600 }, { "epoch": 71.92, "learning_rate": 2.25926769450112e-05, "loss": 0.0041, "step": 299610 }, { "epoch": 71.92, "learning_rate": 2.258967476165802e-05, "loss": 0.0023, "step": 299620 }, { "epoch": 71.93, "learning_rate": 2.2586672719577872e-05, "loss": 0.0015, "step": 299630 }, { "epoch": 71.93, "learning_rate": 2.2583670818786255e-05, "loss": 0.0016, "step": 299640 }, { "epoch": 71.93, "learning_rate": 2.258066905929861e-05, "loss": 0.0015, "step": 299650 }, { "epoch": 71.93, "learning_rate": 2.2577667441130428e-05, "loss": 0.0016, "step": 299660 }, { "epoch": 71.94, "learning_rate": 2.257466596429719e-05, "loss": 0.0017, "step": 299670 }, { "epoch": 71.94, "learning_rate": 2.2571664628814344e-05, "loss": 0.0016, "step": 299680 }, { "epoch": 71.94, "learning_rate": 2.2568663434697378e-05, "loss": 0.0014, "step": 299690 }, { "epoch": 71.94, "learning_rate": 2.2565662381961738e-05, "loss": 0.0016, "step": 299700 }, { "epoch": 71.95, "learning_rate": 2.256266147062292e-05, "loss": 0.0015, "step": 299710 }, { "epoch": 71.95, "learning_rate": 2.255966070069637e-05, "loss": 0.0016, "step": 299720 }, { "epoch": 71.95, "learning_rate": 2.2556660072197545e-05, "loss": 0.0015, "step": 299730 }, { "epoch": 72.0, "learning_rate": 2.255365958514194e-05, "loss": 0.0014, "step": 299740 }, { "epoch": 72.0, "learning_rate": 2.255065923954498e-05, "loss": 0.0018, "step": 299750 }, { "epoch": 72.01, "learning_rate": 2.2547659035422175e-05, "loss": 0.0019, "step": 299760 }, { "epoch": 72.01, "learning_rate": 2.2544658972788947e-05, "loss": 0.0016, "step": 299770 }, { "epoch": 72.01, "learning_rate": 2.254165905166079e-05, "loss": 0.0016, "step": 299780 }, { "epoch": 72.01, "learning_rate": 2.253865927205316e-05, "loss": 0.0018, "step": 299790 }, { "epoch": 72.01, "learning_rate": 2.253565963398148e-05, "loss": 0.0015, "step": 299800 }, { "epoch": 72.02, "learning_rate": 2.253266013746127e-05, "loss": 0.0016, "step": 299810 }, { "epoch": 72.02, "learning_rate": 2.252966078250793e-05, "loss": 0.0014, "step": 299820 }, { "epoch": 72.02, "learning_rate": 2.2526661569136974e-05, "loss": 0.0015, "step": 299830 }, { "epoch": 72.02, "learning_rate": 2.2523662497363813e-05, "loss": 0.0015, "step": 299840 }, { "epoch": 72.03, "learning_rate": 2.2520663567203943e-05, "loss": 0.0014, "step": 299850 }, { "epoch": 72.03, "learning_rate": 2.2517664778672802e-05, "loss": 0.0016, "step": 299860 }, { "epoch": 72.03, "learning_rate": 2.2514666131785835e-05, "loss": 0.0015, "step": 299870 }, { "epoch": 72.03, "learning_rate": 2.2511667626558517e-05, "loss": 0.0016, "step": 299880 }, { "epoch": 72.04, "learning_rate": 2.2508669263006277e-05, "loss": 0.0016, "step": 299890 }, { "epoch": 72.04, "learning_rate": 2.250567104114461e-05, "loss": 0.0015, "step": 299900 }, { "epoch": 72.04, "learning_rate": 2.250267296098892e-05, "loss": 0.0013, "step": 299910 }, { "epoch": 72.04, "learning_rate": 2.2499675022554708e-05, "loss": 0.0016, "step": 299920 }, { "epoch": 72.04, "learning_rate": 2.2496677225857376e-05, "loss": 0.0014, "step": 299930 }, { "epoch": 72.05, "learning_rate": 2.2493679570912418e-05, "loss": 0.0018, "step": 299940 }, { "epoch": 72.05, "learning_rate": 2.2490682057735252e-05, "loss": 0.0017, "step": 299950 }, { "epoch": 72.05, "learning_rate": 2.2487684686341352e-05, "loss": 0.0017, "step": 299960 }, { "epoch": 72.05, "learning_rate": 2.2484687456746145e-05, "loss": 0.0018, "step": 299970 }, { "epoch": 72.06, "learning_rate": 2.248169036896508e-05, "loss": 0.0017, "step": 299980 }, { "epoch": 72.06, "learning_rate": 2.247869342301364e-05, "loss": 0.0017, "step": 299990 }, { "epoch": 72.06, "learning_rate": 2.2475696618907237e-05, "loss": 0.0015, "step": 300000 }, { "epoch": 72.06, "learning_rate": 2.2472699956661308e-05, "loss": 0.0016, "step": 300010 }, { "epoch": 72.06, "learning_rate": 2.2469703436291334e-05, "loss": 0.0016, "step": 300020 }, { "epoch": 72.07, "learning_rate": 2.2466707057812718e-05, "loss": 0.0015, "step": 300030 }, { "epoch": 72.07, "learning_rate": 2.2463710821240947e-05, "loss": 0.0015, "step": 300040 }, { "epoch": 72.07, "learning_rate": 2.2460714726591413e-05, "loss": 0.0016, "step": 300050 }, { "epoch": 72.07, "learning_rate": 2.245771877387961e-05, "loss": 0.0137, "step": 300060 }, { "epoch": 72.08, "learning_rate": 2.2454722963120955e-05, "loss": 0.0015, "step": 300070 }, { "epoch": 72.08, "learning_rate": 2.2451727294330872e-05, "loss": 0.0016, "step": 300080 }, { "epoch": 72.08, "learning_rate": 2.2448731767524826e-05, "loss": 0.0016, "step": 300090 }, { "epoch": 72.08, "learning_rate": 2.2445736382718237e-05, "loss": 0.0014, "step": 300100 }, { "epoch": 72.09, "learning_rate": 2.2442741139926567e-05, "loss": 0.0016, "step": 300110 }, { "epoch": 72.09, "learning_rate": 2.2439746039165222e-05, "loss": 0.0016, "step": 300120 }, { "epoch": 72.09, "learning_rate": 2.2436751080449676e-05, "loss": 0.0015, "step": 300130 }, { "epoch": 72.09, "learning_rate": 2.243375626379535e-05, "loss": 0.0016, "step": 300140 }, { "epoch": 72.09, "learning_rate": 2.243076158921765e-05, "loss": 0.0016, "step": 300150 }, { "epoch": 72.1, "learning_rate": 2.2427767056732053e-05, "loss": 0.0016, "step": 300160 }, { "epoch": 72.1, "learning_rate": 2.2424772666353954e-05, "loss": 0.0019, "step": 300170 }, { "epoch": 72.1, "learning_rate": 2.2421778418098833e-05, "loss": 0.0017, "step": 300180 }, { "epoch": 72.1, "learning_rate": 2.241878431198207e-05, "loss": 0.0015, "step": 300190 }, { "epoch": 72.11, "learning_rate": 2.241579034801915e-05, "loss": 0.0014, "step": 300200 }, { "epoch": 72.11, "learning_rate": 2.2412796526225472e-05, "loss": 0.0017, "step": 300210 }, { "epoch": 72.11, "learning_rate": 2.2409802846616457e-05, "loss": 0.0016, "step": 300220 }, { "epoch": 72.11, "learning_rate": 2.2406809309207543e-05, "loss": 0.0016, "step": 300230 }, { "epoch": 72.12, "learning_rate": 2.2403815914014187e-05, "loss": 0.0015, "step": 300240 }, { "epoch": 72.12, "learning_rate": 2.2400822661051774e-05, "loss": 0.0015, "step": 300250 }, { "epoch": 72.12, "learning_rate": 2.2397829550335768e-05, "loss": 0.0016, "step": 300260 }, { "epoch": 72.12, "learning_rate": 2.2394836581881568e-05, "loss": 0.0015, "step": 300270 }, { "epoch": 72.12, "learning_rate": 2.2391843755704624e-05, "loss": 0.0018, "step": 300280 }, { "epoch": 72.13, "learning_rate": 2.238885107182033e-05, "loss": 0.0015, "step": 300290 }, { "epoch": 72.13, "learning_rate": 2.2385858530244147e-05, "loss": 0.0013, "step": 300300 }, { "epoch": 72.13, "learning_rate": 2.2382866130991466e-05, "loss": 0.0016, "step": 300310 }, { "epoch": 72.13, "learning_rate": 2.237987387407774e-05, "loss": 0.0021, "step": 300320 }, { "epoch": 72.14, "learning_rate": 2.2376881759518354e-05, "loss": 0.0015, "step": 300330 }, { "epoch": 72.14, "learning_rate": 2.2373889787328765e-05, "loss": 0.0015, "step": 300340 }, { "epoch": 72.14, "learning_rate": 2.2370897957524385e-05, "loss": 0.0015, "step": 300350 }, { "epoch": 72.14, "learning_rate": 2.236790627012061e-05, "loss": 0.0015, "step": 300360 }, { "epoch": 72.14, "learning_rate": 2.236491472513289e-05, "loss": 0.0015, "step": 300370 }, { "epoch": 72.15, "learning_rate": 2.2361923322576618e-05, "loss": 0.0021, "step": 300380 }, { "epoch": 72.15, "learning_rate": 2.235893206246724e-05, "loss": 0.0023, "step": 300390 }, { "epoch": 72.15, "learning_rate": 2.2355940944820143e-05, "loss": 0.0014, "step": 300400 }, { "epoch": 72.15, "learning_rate": 2.2352949969650773e-05, "loss": 0.0015, "step": 300410 }, { "epoch": 72.16, "learning_rate": 2.2349959136974524e-05, "loss": 0.002, "step": 300420 }, { "epoch": 72.16, "learning_rate": 2.2346968446806804e-05, "loss": 0.0014, "step": 300430 }, { "epoch": 72.16, "learning_rate": 2.234397789916306e-05, "loss": 0.0015, "step": 300440 }, { "epoch": 72.16, "learning_rate": 2.234098749405866e-05, "loss": 0.0014, "step": 300450 }, { "epoch": 72.17, "learning_rate": 2.2337997231509067e-05, "loss": 0.0016, "step": 300460 }, { "epoch": 72.17, "learning_rate": 2.2335007111529643e-05, "loss": 0.0017, "step": 300470 }, { "epoch": 72.17, "learning_rate": 2.2332017134135845e-05, "loss": 0.0018, "step": 300480 }, { "epoch": 72.17, "learning_rate": 2.2329027299343046e-05, "loss": 0.0014, "step": 300490 }, { "epoch": 72.17, "learning_rate": 2.232603760716669e-05, "loss": 0.0017, "step": 300500 }, { "epoch": 72.18, "learning_rate": 2.2323048057622165e-05, "loss": 0.0014, "step": 300510 }, { "epoch": 72.18, "learning_rate": 2.232005865072486e-05, "loss": 0.0016, "step": 300520 }, { "epoch": 72.18, "learning_rate": 2.2317069386490226e-05, "loss": 0.0015, "step": 300530 }, { "epoch": 72.18, "learning_rate": 2.231408026493363e-05, "loss": 0.0015, "step": 300540 }, { "epoch": 72.19, "learning_rate": 2.2311091286070497e-05, "loss": 0.0014, "step": 300550 }, { "epoch": 72.19, "learning_rate": 2.2308102449916247e-05, "loss": 0.0017, "step": 300560 }, { "epoch": 72.19, "learning_rate": 2.230511375648625e-05, "loss": 0.0015, "step": 300570 }, { "epoch": 72.19, "learning_rate": 2.2302125205795948e-05, "loss": 0.0015, "step": 300580 }, { "epoch": 72.2, "learning_rate": 2.2299136797860702e-05, "loss": 0.0015, "step": 300590 }, { "epoch": 72.2, "learning_rate": 2.229614853269596e-05, "loss": 0.0015, "step": 300600 }, { "epoch": 72.2, "learning_rate": 2.2293160410317077e-05, "loss": 0.002, "step": 300610 }, { "epoch": 72.2, "learning_rate": 2.22901724307395e-05, "loss": 0.0015, "step": 300620 }, { "epoch": 72.2, "learning_rate": 2.2287184593978583e-05, "loss": 0.0014, "step": 300630 }, { "epoch": 72.21, "learning_rate": 2.228419690004977e-05, "loss": 0.0017, "step": 300640 }, { "epoch": 72.21, "learning_rate": 2.2281209348968434e-05, "loss": 0.0015, "step": 300650 }, { "epoch": 72.21, "learning_rate": 2.2278221940749967e-05, "loss": 0.0024, "step": 300660 }, { "epoch": 72.21, "learning_rate": 2.2275234675409784e-05, "loss": 0.0016, "step": 300670 }, { "epoch": 72.22, "learning_rate": 2.227224755296326e-05, "loss": 0.0016, "step": 300680 }, { "epoch": 72.22, "learning_rate": 2.2269260573425823e-05, "loss": 0.0016, "step": 300690 }, { "epoch": 72.22, "learning_rate": 2.2266273736812826e-05, "loss": 0.0016, "step": 300700 }, { "epoch": 72.22, "learning_rate": 2.226328704313971e-05, "loss": 0.0016, "step": 300710 }, { "epoch": 72.22, "learning_rate": 2.2260300492421836e-05, "loss": 0.0017, "step": 300720 }, { "epoch": 72.23, "learning_rate": 2.2257314084674597e-05, "loss": 0.0015, "step": 300730 }, { "epoch": 72.23, "learning_rate": 2.2254327819913407e-05, "loss": 0.0014, "step": 300740 }, { "epoch": 72.23, "learning_rate": 2.2251341698153622e-05, "loss": 0.0019, "step": 300750 }, { "epoch": 72.23, "learning_rate": 2.2248355719410675e-05, "loss": 0.0016, "step": 300760 }, { "epoch": 72.24, "learning_rate": 2.2245369883699917e-05, "loss": 0.0014, "step": 300770 }, { "epoch": 72.24, "learning_rate": 2.224238419103677e-05, "loss": 0.0015, "step": 300780 }, { "epoch": 72.24, "learning_rate": 2.2239398641436608e-05, "loss": 0.0015, "step": 300790 }, { "epoch": 72.24, "learning_rate": 2.2236413234914805e-05, "loss": 0.0015, "step": 300800 }, { "epoch": 72.25, "learning_rate": 2.223342797148677e-05, "loss": 0.0016, "step": 300810 }, { "epoch": 72.25, "learning_rate": 2.2230442851167865e-05, "loss": 0.0016, "step": 300820 }, { "epoch": 72.25, "learning_rate": 2.2227457873973507e-05, "loss": 0.0024, "step": 300830 }, { "epoch": 72.25, "learning_rate": 2.2224473039919047e-05, "loss": 0.0023, "step": 300840 }, { "epoch": 72.25, "learning_rate": 2.2221488349019903e-05, "loss": 0.002, "step": 300850 }, { "epoch": 72.26, "learning_rate": 2.221850380129142e-05, "loss": 0.0015, "step": 300860 }, { "epoch": 72.26, "learning_rate": 2.2215519396749002e-05, "loss": 0.0015, "step": 300870 }, { "epoch": 72.26, "learning_rate": 2.2212535135408046e-05, "loss": 0.0014, "step": 300880 }, { "epoch": 72.26, "learning_rate": 2.22095510172839e-05, "loss": 0.0017, "step": 300890 }, { "epoch": 72.27, "learning_rate": 2.2206567042391978e-05, "loss": 0.0015, "step": 300900 }, { "epoch": 72.27, "learning_rate": 2.2203583210747624e-05, "loss": 0.0018, "step": 300910 }, { "epoch": 72.27, "learning_rate": 2.220059952236625e-05, "loss": 0.0015, "step": 300920 }, { "epoch": 72.27, "learning_rate": 2.219761597726322e-05, "loss": 0.0021, "step": 300930 }, { "epoch": 72.28, "learning_rate": 2.2194632575453893e-05, "loss": 0.0017, "step": 300940 }, { "epoch": 72.28, "learning_rate": 2.2191649316953678e-05, "loss": 0.0015, "step": 300950 }, { "epoch": 72.28, "learning_rate": 2.218866620177792e-05, "loss": 0.0015, "step": 300960 }, { "epoch": 72.28, "learning_rate": 2.2185683229942022e-05, "loss": 0.0015, "step": 300970 }, { "epoch": 72.28, "learning_rate": 2.2182700401461332e-05, "loss": 0.0016, "step": 300980 }, { "epoch": 72.29, "learning_rate": 2.217971771635125e-05, "loss": 0.0015, "step": 300990 }, { "epoch": 72.29, "learning_rate": 2.2176735174627138e-05, "loss": 0.0016, "step": 301000 }, { "epoch": 72.29, "learning_rate": 2.217375277630435e-05, "loss": 0.0019, "step": 301010 }, { "epoch": 72.29, "learning_rate": 2.217077052139829e-05, "loss": 0.0015, "step": 301020 }, { "epoch": 72.3, "learning_rate": 2.216778840992429e-05, "loss": 0.0015, "step": 301030 }, { "epoch": 72.3, "learning_rate": 2.216480644189776e-05, "loss": 0.0016, "step": 301040 }, { "epoch": 72.3, "learning_rate": 2.216182461733403e-05, "loss": 0.0221, "step": 301050 }, { "epoch": 72.3, "learning_rate": 2.2158842936248515e-05, "loss": 0.0016, "step": 301060 }, { "epoch": 72.3, "learning_rate": 2.2155861398656547e-05, "loss": 0.0015, "step": 301070 }, { "epoch": 72.31, "learning_rate": 2.215288000457349e-05, "loss": 0.0014, "step": 301080 }, { "epoch": 72.31, "learning_rate": 2.2149898754014737e-05, "loss": 0.0017, "step": 301090 }, { "epoch": 72.31, "learning_rate": 2.2146917646995623e-05, "loss": 0.0021, "step": 301100 }, { "epoch": 72.31, "learning_rate": 2.2143936683531548e-05, "loss": 0.0024, "step": 301110 }, { "epoch": 72.32, "learning_rate": 2.214095586363783e-05, "loss": 0.0015, "step": 301120 }, { "epoch": 72.32, "learning_rate": 2.2137975187329883e-05, "loss": 0.0014, "step": 301130 }, { "epoch": 72.32, "learning_rate": 2.2134994654623024e-05, "loss": 0.0013, "step": 301140 }, { "epoch": 72.32, "learning_rate": 2.2132014265532658e-05, "loss": 0.0017, "step": 301150 }, { "epoch": 72.33, "learning_rate": 2.2129034020074102e-05, "loss": 0.0015, "step": 301160 }, { "epoch": 72.33, "learning_rate": 2.2126053918262736e-05, "loss": 0.0016, "step": 301170 }, { "epoch": 72.33, "learning_rate": 2.2123073960113944e-05, "loss": 0.0014, "step": 301180 }, { "epoch": 72.33, "learning_rate": 2.2120094145643038e-05, "loss": 0.0015, "step": 301190 }, { "epoch": 72.33, "learning_rate": 2.211711447486542e-05, "loss": 0.0012, "step": 301200 }, { "epoch": 72.34, "learning_rate": 2.211413494779643e-05, "loss": 0.0015, "step": 301210 }, { "epoch": 72.34, "learning_rate": 2.2111155564451395e-05, "loss": 0.0017, "step": 301220 }, { "epoch": 72.34, "learning_rate": 2.2108176324845725e-05, "loss": 0.0015, "step": 301230 }, { "epoch": 72.34, "learning_rate": 2.210519722899473e-05, "loss": 0.0015, "step": 301240 }, { "epoch": 72.35, "learning_rate": 2.2102218276913796e-05, "loss": 0.0028, "step": 301250 }, { "epoch": 72.35, "learning_rate": 2.2099239468618237e-05, "loss": 0.0015, "step": 301260 }, { "epoch": 72.35, "learning_rate": 2.209626080412346e-05, "loss": 0.0015, "step": 301270 }, { "epoch": 72.35, "learning_rate": 2.2093282283444768e-05, "loss": 0.0013, "step": 301280 }, { "epoch": 72.36, "learning_rate": 2.2090303906597543e-05, "loss": 0.0014, "step": 301290 }, { "epoch": 72.36, "learning_rate": 2.208732567359713e-05, "loss": 0.0013, "step": 301300 }, { "epoch": 72.36, "learning_rate": 2.208434758445886e-05, "loss": 0.0018, "step": 301310 }, { "epoch": 72.36, "learning_rate": 2.2081369639198106e-05, "loss": 0.0025, "step": 301320 }, { "epoch": 72.36, "learning_rate": 2.2078391837830192e-05, "loss": 0.0017, "step": 301330 }, { "epoch": 72.37, "learning_rate": 2.2075414180370503e-05, "loss": 0.0019, "step": 301340 }, { "epoch": 72.37, "learning_rate": 2.2072436666834336e-05, "loss": 0.0019, "step": 301350 }, { "epoch": 72.37, "learning_rate": 2.2069459297237082e-05, "loss": 0.002, "step": 301360 }, { "epoch": 72.37, "learning_rate": 2.2066482071594074e-05, "loss": 0.0019, "step": 301370 }, { "epoch": 72.38, "learning_rate": 2.206350498992063e-05, "loss": 0.0014, "step": 301380 }, { "epoch": 72.38, "learning_rate": 2.2060528052232137e-05, "loss": 0.0017, "step": 301390 }, { "epoch": 72.38, "learning_rate": 2.205755125854389e-05, "loss": 0.0017, "step": 301400 }, { "epoch": 72.38, "learning_rate": 2.205457460887128e-05, "loss": 0.0014, "step": 301410 }, { "epoch": 72.38, "learning_rate": 2.2051598103229608e-05, "loss": 0.0016, "step": 301420 }, { "epoch": 72.39, "learning_rate": 2.204862174163425e-05, "loss": 0.0031, "step": 301430 }, { "epoch": 72.39, "learning_rate": 2.2045645524100516e-05, "loss": 0.0014, "step": 301440 }, { "epoch": 72.39, "learning_rate": 2.204266945064377e-05, "loss": 0.0014, "step": 301450 }, { "epoch": 72.39, "learning_rate": 2.2039693521279325e-05, "loss": 0.0018, "step": 301460 }, { "epoch": 72.4, "learning_rate": 2.203671773602255e-05, "loss": 0.0017, "step": 301470 }, { "epoch": 72.4, "learning_rate": 2.2033742094888748e-05, "loss": 0.0016, "step": 301480 }, { "epoch": 72.4, "learning_rate": 2.2030766597893272e-05, "loss": 0.0015, "step": 301490 }, { "epoch": 72.4, "learning_rate": 2.2027791245051478e-05, "loss": 0.0015, "step": 301500 }, { "epoch": 72.41, "learning_rate": 2.2024816036378683e-05, "loss": 0.0016, "step": 301510 }, { "epoch": 72.41, "learning_rate": 2.20218409718902e-05, "loss": 0.0014, "step": 301520 }, { "epoch": 72.41, "learning_rate": 2.20188660516014e-05, "loss": 0.0014, "step": 301530 }, { "epoch": 72.41, "learning_rate": 2.201589127552758e-05, "loss": 0.0015, "step": 301540 }, { "epoch": 72.41, "learning_rate": 2.2012916643684112e-05, "loss": 0.002, "step": 301550 }, { "epoch": 72.42, "learning_rate": 2.2009942156086284e-05, "loss": 0.0015, "step": 301560 }, { "epoch": 72.42, "learning_rate": 2.200696781274947e-05, "loss": 0.0016, "step": 301570 }, { "epoch": 72.42, "learning_rate": 2.2003993613688973e-05, "loss": 0.0016, "step": 301580 }, { "epoch": 72.42, "learning_rate": 2.200101955892011e-05, "loss": 0.0173, "step": 301590 }, { "epoch": 72.43, "learning_rate": 2.1998045648458245e-05, "loss": 0.0017, "step": 301600 }, { "epoch": 72.43, "learning_rate": 2.199507188231867e-05, "loss": 0.0035, "step": 301610 }, { "epoch": 72.43, "learning_rate": 2.199209826051674e-05, "loss": 0.0021, "step": 301620 }, { "epoch": 72.43, "learning_rate": 2.198912478306776e-05, "loss": 0.0018, "step": 301630 }, { "epoch": 72.44, "learning_rate": 2.198615144998708e-05, "loss": 0.0017, "step": 301640 }, { "epoch": 72.44, "learning_rate": 2.198317826129001e-05, "loss": 0.0017, "step": 301650 }, { "epoch": 72.44, "learning_rate": 2.1980205216991857e-05, "loss": 0.0014, "step": 301660 }, { "epoch": 72.44, "learning_rate": 2.1977232317107978e-05, "loss": 0.0013, "step": 301670 }, { "epoch": 72.44, "learning_rate": 2.1974259561653654e-05, "loss": 0.0023, "step": 301680 }, { "epoch": 72.45, "learning_rate": 2.1971286950644253e-05, "loss": 0.0017, "step": 301690 }, { "epoch": 72.45, "learning_rate": 2.1968314484095053e-05, "loss": 0.0013, "step": 301700 }, { "epoch": 72.45, "learning_rate": 2.1965342162021417e-05, "loss": 0.0015, "step": 301710 }, { "epoch": 72.45, "learning_rate": 2.1962369984438642e-05, "loss": 0.0018, "step": 301720 }, { "epoch": 72.46, "learning_rate": 2.195939795136202e-05, "loss": 0.0016, "step": 301730 }, { "epoch": 72.46, "learning_rate": 2.1956426062806907e-05, "loss": 0.0015, "step": 301740 }, { "epoch": 72.46, "learning_rate": 2.195345431878862e-05, "loss": 0.0015, "step": 301750 }, { "epoch": 72.46, "learning_rate": 2.1950482719322446e-05, "loss": 0.0016, "step": 301760 }, { "epoch": 72.46, "learning_rate": 2.1947511264423736e-05, "loss": 0.0015, "step": 301770 }, { "epoch": 72.47, "learning_rate": 2.1944539954107774e-05, "loss": 0.0015, "step": 301780 }, { "epoch": 72.47, "learning_rate": 2.1941568788389898e-05, "loss": 0.0015, "step": 301790 }, { "epoch": 72.47, "learning_rate": 2.1938597767285397e-05, "loss": 0.0014, "step": 301800 }, { "epoch": 72.47, "learning_rate": 2.1935626890809617e-05, "loss": 0.0014, "step": 301810 }, { "epoch": 72.48, "learning_rate": 2.1932656158977832e-05, "loss": 0.002, "step": 301820 }, { "epoch": 72.48, "learning_rate": 2.1929685571805393e-05, "loss": 0.0015, "step": 301830 }, { "epoch": 72.48, "learning_rate": 2.192671512930756e-05, "loss": 0.0033, "step": 301840 }, { "epoch": 72.48, "learning_rate": 2.19237448314997e-05, "loss": 0.0018, "step": 301850 }, { "epoch": 72.49, "learning_rate": 2.1920774678397094e-05, "loss": 0.0015, "step": 301860 }, { "epoch": 72.49, "learning_rate": 2.191780467001503e-05, "loss": 0.0015, "step": 301870 }, { "epoch": 72.49, "learning_rate": 2.191483480636885e-05, "loss": 0.0016, "step": 301880 }, { "epoch": 72.49, "learning_rate": 2.191186508747383e-05, "loss": 0.0015, "step": 301890 }, { "epoch": 72.49, "learning_rate": 2.1908895513345313e-05, "loss": 0.0015, "step": 301900 }, { "epoch": 72.5, "learning_rate": 2.190592608399856e-05, "loss": 0.0015, "step": 301910 }, { "epoch": 72.5, "learning_rate": 2.190295679944892e-05, "loss": 0.0014, "step": 301920 }, { "epoch": 72.5, "learning_rate": 2.189998765971168e-05, "loss": 0.0017, "step": 301930 }, { "epoch": 72.5, "learning_rate": 2.1897018664802116e-05, "loss": 0.0017, "step": 301940 }, { "epoch": 72.51, "learning_rate": 2.189404981473557e-05, "loss": 0.0015, "step": 301950 }, { "epoch": 72.51, "learning_rate": 2.1891081109527305e-05, "loss": 0.0015, "step": 301960 }, { "epoch": 72.51, "learning_rate": 2.1888112549192667e-05, "loss": 0.0021, "step": 301970 }, { "epoch": 72.51, "learning_rate": 2.188514413374691e-05, "loss": 0.002, "step": 301980 }, { "epoch": 72.52, "learning_rate": 2.1882175863205378e-05, "loss": 0.0016, "step": 301990 }, { "epoch": 72.52, "learning_rate": 2.187920773758334e-05, "loss": 0.0017, "step": 302000 }, { "epoch": 72.52, "learning_rate": 2.1876239756896088e-05, "loss": 0.0016, "step": 302010 }, { "epoch": 72.52, "learning_rate": 2.187327192115895e-05, "loss": 0.0016, "step": 302020 }, { "epoch": 72.52, "learning_rate": 2.187030423038718e-05, "loss": 0.0015, "step": 302030 }, { "epoch": 72.53, "learning_rate": 2.186733668459612e-05, "loss": 0.0045, "step": 302040 }, { "epoch": 72.53, "learning_rate": 2.1864369283801017e-05, "loss": 0.0018, "step": 302050 }, { "epoch": 72.53, "learning_rate": 2.1861402028017196e-05, "loss": 0.0015, "step": 302060 }, { "epoch": 72.53, "learning_rate": 2.185843491725996e-05, "loss": 0.0028, "step": 302070 }, { "epoch": 72.54, "learning_rate": 2.1855467951544572e-05, "loss": 0.0017, "step": 302080 }, { "epoch": 72.54, "learning_rate": 2.185250113088635e-05, "loss": 0.0016, "step": 302090 }, { "epoch": 72.54, "learning_rate": 2.1849534455300556e-05, "loss": 0.0016, "step": 302100 }, { "epoch": 72.54, "learning_rate": 2.184656792480252e-05, "loss": 0.0017, "step": 302110 }, { "epoch": 72.54, "learning_rate": 2.1843601539407482e-05, "loss": 0.0016, "step": 302120 }, { "epoch": 72.55, "learning_rate": 2.184063529913078e-05, "loss": 0.0017, "step": 302130 }, { "epoch": 72.55, "learning_rate": 2.183766920398766e-05, "loss": 0.0026, "step": 302140 }, { "epoch": 72.55, "learning_rate": 2.1834703253993445e-05, "loss": 0.0027, "step": 302150 }, { "epoch": 72.55, "learning_rate": 2.1831737449163402e-05, "loss": 0.0014, "step": 302160 }, { "epoch": 72.56, "learning_rate": 2.1828771789512807e-05, "loss": 0.0016, "step": 302170 }, { "epoch": 72.56, "learning_rate": 2.1825806275056975e-05, "loss": 0.0016, "step": 302180 }, { "epoch": 72.56, "learning_rate": 2.1822840905811155e-05, "loss": 0.0014, "step": 302190 }, { "epoch": 72.56, "learning_rate": 2.1819875681790662e-05, "loss": 0.0014, "step": 302200 }, { "epoch": 72.57, "learning_rate": 2.1816910603010753e-05, "loss": 0.0015, "step": 302210 }, { "epoch": 72.57, "learning_rate": 2.1813945669486735e-05, "loss": 0.0015, "step": 302220 }, { "epoch": 72.57, "learning_rate": 2.1810980881233885e-05, "loss": 0.0014, "step": 302230 }, { "epoch": 72.57, "learning_rate": 2.1808016238267446e-05, "loss": 0.0016, "step": 302240 }, { "epoch": 72.57, "learning_rate": 2.1805051740602754e-05, "loss": 0.0016, "step": 302250 }, { "epoch": 72.58, "learning_rate": 2.1802087388255038e-05, "loss": 0.0015, "step": 302260 }, { "epoch": 72.58, "learning_rate": 2.1799123181239622e-05, "loss": 0.0017, "step": 302270 }, { "epoch": 72.58, "learning_rate": 2.1796159119571742e-05, "loss": 0.0045, "step": 302280 }, { "epoch": 72.58, "learning_rate": 2.1793195203266707e-05, "loss": 0.0017, "step": 302290 }, { "epoch": 72.59, "learning_rate": 2.179023143233978e-05, "loss": 0.0017, "step": 302300 }, { "epoch": 72.59, "learning_rate": 2.178726780680622e-05, "loss": 0.002, "step": 302310 }, { "epoch": 72.59, "learning_rate": 2.1784304326681338e-05, "loss": 0.0015, "step": 302320 }, { "epoch": 72.59, "learning_rate": 2.1781340991980363e-05, "loss": 0.0016, "step": 302330 }, { "epoch": 72.6, "learning_rate": 2.1778377802718618e-05, "loss": 0.0017, "step": 302340 }, { "epoch": 72.6, "learning_rate": 2.177541475891133e-05, "loss": 0.0017, "step": 302350 }, { "epoch": 72.6, "learning_rate": 2.1772451860573807e-05, "loss": 0.0018, "step": 302360 }, { "epoch": 72.6, "learning_rate": 2.176948910772128e-05, "loss": 0.0021, "step": 302370 }, { "epoch": 72.6, "learning_rate": 2.176652650036905e-05, "loss": 0.0019, "step": 302380 }, { "epoch": 72.61, "learning_rate": 2.176356403853239e-05, "loss": 0.0015, "step": 302390 }, { "epoch": 72.61, "learning_rate": 2.176060172222654e-05, "loss": 0.0015, "step": 302400 }, { "epoch": 72.61, "learning_rate": 2.1757639551466807e-05, "loss": 0.0015, "step": 302410 }, { "epoch": 72.61, "learning_rate": 2.1754677526268418e-05, "loss": 0.0015, "step": 302420 }, { "epoch": 72.62, "learning_rate": 2.175171564664667e-05, "loss": 0.0033, "step": 302430 }, { "epoch": 72.62, "learning_rate": 2.174875391261682e-05, "loss": 0.0017, "step": 302440 }, { "epoch": 72.62, "learning_rate": 2.1745792324194108e-05, "loss": 0.0015, "step": 302450 }, { "epoch": 72.62, "learning_rate": 2.1742830881393838e-05, "loss": 0.0016, "step": 302460 }, { "epoch": 72.62, "learning_rate": 2.1739869584231238e-05, "loss": 0.0016, "step": 302470 }, { "epoch": 72.63, "learning_rate": 2.1736908432721598e-05, "loss": 0.0015, "step": 302480 }, { "epoch": 72.63, "learning_rate": 2.1733947426880157e-05, "loss": 0.0015, "step": 302490 }, { "epoch": 72.63, "learning_rate": 2.17309865667222e-05, "loss": 0.0016, "step": 302500 }, { "epoch": 72.63, "learning_rate": 2.172802585226298e-05, "loss": 0.0014, "step": 302510 }, { "epoch": 72.64, "learning_rate": 2.1725065283517727e-05, "loss": 0.0014, "step": 302520 }, { "epoch": 72.64, "learning_rate": 2.1722104860501748e-05, "loss": 0.0015, "step": 302530 }, { "epoch": 72.64, "learning_rate": 2.1719144583230256e-05, "loss": 0.0017, "step": 302540 }, { "epoch": 72.64, "learning_rate": 2.171618445171854e-05, "loss": 0.0014, "step": 302550 }, { "epoch": 72.65, "learning_rate": 2.1713224465981837e-05, "loss": 0.0015, "step": 302560 }, { "epoch": 72.65, "learning_rate": 2.1710264626035427e-05, "loss": 0.0014, "step": 302570 }, { "epoch": 72.65, "learning_rate": 2.170730493189455e-05, "loss": 0.0016, "step": 302580 }, { "epoch": 72.65, "learning_rate": 2.1704345383574443e-05, "loss": 0.0018, "step": 302590 }, { "epoch": 72.65, "learning_rate": 2.1701385981090393e-05, "loss": 0.0015, "step": 302600 }, { "epoch": 72.66, "learning_rate": 2.1698426724457617e-05, "loss": 0.0015, "step": 302610 }, { "epoch": 72.66, "learning_rate": 2.1695467613691405e-05, "loss": 0.0015, "step": 302620 }, { "epoch": 72.66, "learning_rate": 2.169250864880697e-05, "loss": 0.0016, "step": 302630 }, { "epoch": 72.66, "learning_rate": 2.1689549829819605e-05, "loss": 0.0014, "step": 302640 }, { "epoch": 72.67, "learning_rate": 2.1686591156744513e-05, "loss": 0.0016, "step": 302650 }, { "epoch": 72.67, "learning_rate": 2.168363262959699e-05, "loss": 0.0014, "step": 302660 }, { "epoch": 72.67, "learning_rate": 2.1680674248392242e-05, "loss": 0.0015, "step": 302670 }, { "epoch": 72.67, "learning_rate": 2.1677716013145532e-05, "loss": 0.0015, "step": 302680 }, { "epoch": 72.68, "learning_rate": 2.167475792387213e-05, "loss": 0.0016, "step": 302690 }, { "epoch": 72.68, "learning_rate": 2.1671799980587243e-05, "loss": 0.0015, "step": 302700 }, { "epoch": 72.68, "learning_rate": 2.166884218330616e-05, "loss": 0.0016, "step": 302710 }, { "epoch": 72.68, "learning_rate": 2.1665884532044096e-05, "loss": 0.0014, "step": 302720 }, { "epoch": 72.68, "learning_rate": 2.1662927026816283e-05, "loss": 0.0015, "step": 302730 }, { "epoch": 72.69, "learning_rate": 2.1659969667637997e-05, "loss": 0.0014, "step": 302740 }, { "epoch": 72.69, "learning_rate": 2.165701245452445e-05, "loss": 0.0016, "step": 302750 }, { "epoch": 72.69, "learning_rate": 2.1654055387490912e-05, "loss": 0.0017, "step": 302760 }, { "epoch": 72.69, "learning_rate": 2.1651098466552593e-05, "loss": 0.0014, "step": 302770 }, { "epoch": 72.7, "learning_rate": 2.1648141691724766e-05, "loss": 0.0015, "step": 302780 }, { "epoch": 72.7, "learning_rate": 2.164518506302266e-05, "loss": 0.0015, "step": 302790 }, { "epoch": 72.7, "learning_rate": 2.164222858046148e-05, "loss": 0.0016, "step": 302800 }, { "epoch": 72.7, "learning_rate": 2.163927224405652e-05, "loss": 0.0014, "step": 302810 }, { "epoch": 72.7, "learning_rate": 2.163631605382296e-05, "loss": 0.0015, "step": 302820 }, { "epoch": 72.71, "learning_rate": 2.1633360009776088e-05, "loss": 0.0014, "step": 302830 }, { "epoch": 72.71, "learning_rate": 2.163040411193109e-05, "loss": 0.0015, "step": 302840 }, { "epoch": 72.71, "learning_rate": 2.1627448360303255e-05, "loss": 0.0014, "step": 302850 }, { "epoch": 72.71, "learning_rate": 2.162449275490778e-05, "loss": 0.0014, "step": 302860 }, { "epoch": 72.72, "learning_rate": 2.162153729575989e-05, "loss": 0.0014, "step": 302870 }, { "epoch": 72.72, "learning_rate": 2.161858198287485e-05, "loss": 0.0013, "step": 302880 }, { "epoch": 72.72, "learning_rate": 2.1615626816267865e-05, "loss": 0.0014, "step": 302890 }, { "epoch": 72.72, "learning_rate": 2.1612671795954192e-05, "loss": 0.0017, "step": 302900 }, { "epoch": 72.73, "learning_rate": 2.1609716921949025e-05, "loss": 0.0012, "step": 302910 }, { "epoch": 72.73, "learning_rate": 2.1606762194267637e-05, "loss": 0.0018, "step": 302920 }, { "epoch": 72.73, "learning_rate": 2.1603807612925208e-05, "loss": 0.0014, "step": 302930 }, { "epoch": 72.73, "learning_rate": 2.160085317793702e-05, "loss": 0.0016, "step": 302940 }, { "epoch": 72.73, "learning_rate": 2.1597898889318248e-05, "loss": 0.0012, "step": 302950 }, { "epoch": 72.74, "learning_rate": 2.159494474708416e-05, "loss": 0.0015, "step": 302960 }, { "epoch": 72.74, "learning_rate": 2.1591990751249945e-05, "loss": 0.0015, "step": 302970 }, { "epoch": 72.74, "learning_rate": 2.158903690183087e-05, "loss": 0.0015, "step": 302980 }, { "epoch": 72.74, "learning_rate": 2.1586083198842116e-05, "loss": 0.0018, "step": 302990 }, { "epoch": 72.75, "learning_rate": 2.1583129642298927e-05, "loss": 0.0016, "step": 303000 }, { "epoch": 72.75, "learning_rate": 2.1580176232216544e-05, "loss": 0.0019, "step": 303010 }, { "epoch": 72.75, "learning_rate": 2.1577222968610165e-05, "loss": 0.0018, "step": 303020 }, { "epoch": 72.75, "learning_rate": 2.1574269851495005e-05, "loss": 0.0014, "step": 303030 }, { "epoch": 72.76, "learning_rate": 2.157131688088631e-05, "loss": 0.0016, "step": 303040 }, { "epoch": 72.76, "learning_rate": 2.156836405679927e-05, "loss": 0.0029, "step": 303050 }, { "epoch": 72.76, "learning_rate": 2.156541137924914e-05, "loss": 0.0026, "step": 303060 }, { "epoch": 72.76, "learning_rate": 2.1562458848251093e-05, "loss": 0.0019, "step": 303070 }, { "epoch": 72.76, "learning_rate": 2.1559506463820394e-05, "loss": 0.0014, "step": 303080 }, { "epoch": 72.77, "learning_rate": 2.155655422597223e-05, "loss": 0.0068, "step": 303090 }, { "epoch": 72.77, "learning_rate": 2.1553602134721812e-05, "loss": 0.0015, "step": 303100 }, { "epoch": 72.77, "learning_rate": 2.155065019008438e-05, "loss": 0.0016, "step": 303110 }, { "epoch": 72.77, "learning_rate": 2.154769839207512e-05, "loss": 0.0017, "step": 303120 }, { "epoch": 72.78, "learning_rate": 2.1544746740709275e-05, "loss": 0.0014, "step": 303130 }, { "epoch": 72.78, "learning_rate": 2.1541795236002028e-05, "loss": 0.0016, "step": 303140 }, { "epoch": 72.78, "learning_rate": 2.1538843877968622e-05, "loss": 0.0015, "step": 303150 }, { "epoch": 72.78, "learning_rate": 2.1535892666624253e-05, "loss": 0.0015, "step": 303160 }, { "epoch": 72.78, "learning_rate": 2.1532941601984114e-05, "loss": 0.0014, "step": 303170 }, { "epoch": 72.79, "learning_rate": 2.152999068406345e-05, "loss": 0.002, "step": 303180 }, { "epoch": 72.79, "learning_rate": 2.1527039912877432e-05, "loss": 0.0015, "step": 303190 }, { "epoch": 72.79, "learning_rate": 2.152408928844131e-05, "loss": 0.0015, "step": 303200 }, { "epoch": 72.79, "learning_rate": 2.1521138810770247e-05, "loss": 0.0016, "step": 303210 }, { "epoch": 72.8, "learning_rate": 2.1518188479879497e-05, "loss": 0.0016, "step": 303220 }, { "epoch": 72.8, "learning_rate": 2.1515238295784235e-05, "loss": 0.0015, "step": 303230 }, { "epoch": 72.8, "learning_rate": 2.1512288258499657e-05, "loss": 0.0015, "step": 303240 }, { "epoch": 72.8, "learning_rate": 2.1509338368040987e-05, "loss": 0.0017, "step": 303250 }, { "epoch": 72.81, "learning_rate": 2.150638862442344e-05, "loss": 0.0023, "step": 303260 }, { "epoch": 72.81, "learning_rate": 2.1503439027662187e-05, "loss": 0.0015, "step": 303270 }, { "epoch": 72.81, "learning_rate": 2.1500489577772464e-05, "loss": 0.0015, "step": 303280 }, { "epoch": 72.81, "learning_rate": 2.149754027476944e-05, "loss": 0.0016, "step": 303290 }, { "epoch": 72.81, "learning_rate": 2.149459111866835e-05, "loss": 0.0014, "step": 303300 }, { "epoch": 72.82, "learning_rate": 2.1491642109484356e-05, "loss": 0.0014, "step": 303310 }, { "epoch": 72.82, "learning_rate": 2.1488693247232696e-05, "loss": 0.0094, "step": 303320 }, { "epoch": 72.82, "learning_rate": 2.1485744531928533e-05, "loss": 0.0015, "step": 303330 }, { "epoch": 72.82, "learning_rate": 2.1482795963587093e-05, "loss": 0.0014, "step": 303340 }, { "epoch": 72.83, "learning_rate": 2.1479847542223546e-05, "loss": 0.0016, "step": 303350 }, { "epoch": 72.83, "learning_rate": 2.1476899267853124e-05, "loss": 0.0016, "step": 303360 }, { "epoch": 72.83, "learning_rate": 2.1473951140491e-05, "loss": 0.0016, "step": 303370 }, { "epoch": 72.83, "learning_rate": 2.1471003160152348e-05, "loss": 0.0015, "step": 303380 }, { "epoch": 72.84, "learning_rate": 2.1468055326852405e-05, "loss": 0.002, "step": 303390 }, { "epoch": 72.84, "learning_rate": 2.146510764060633e-05, "loss": 0.0018, "step": 303400 }, { "epoch": 72.84, "learning_rate": 2.146216010142934e-05, "loss": 0.0013, "step": 303410 }, { "epoch": 72.84, "learning_rate": 2.14592127093366e-05, "loss": 0.0016, "step": 303420 }, { "epoch": 72.84, "learning_rate": 2.1456265464343334e-05, "loss": 0.0016, "step": 303430 }, { "epoch": 72.85, "learning_rate": 2.1453318366464714e-05, "loss": 0.0015, "step": 303440 }, { "epoch": 72.85, "learning_rate": 2.1450371415715915e-05, "loss": 0.0018, "step": 303450 }, { "epoch": 72.85, "learning_rate": 2.1447424612112154e-05, "loss": 0.0014, "step": 303460 }, { "epoch": 72.85, "learning_rate": 2.144447795566859e-05, "loss": 0.0018, "step": 303470 }, { "epoch": 72.86, "learning_rate": 2.1441531446400444e-05, "loss": 0.0016, "step": 303480 }, { "epoch": 72.86, "learning_rate": 2.1438585084322866e-05, "loss": 0.0015, "step": 303490 }, { "epoch": 72.86, "learning_rate": 2.1435638869451076e-05, "loss": 0.0019, "step": 303500 }, { "epoch": 72.86, "learning_rate": 2.1432692801800236e-05, "loss": 0.0015, "step": 303510 }, { "epoch": 72.86, "learning_rate": 2.1429746881385525e-05, "loss": 0.0014, "step": 303520 }, { "epoch": 72.87, "learning_rate": 2.1426801108222156e-05, "loss": 0.0076, "step": 303530 }, { "epoch": 72.87, "learning_rate": 2.1423855482325273e-05, "loss": 0.0016, "step": 303540 }, { "epoch": 72.87, "learning_rate": 2.1420910003710093e-05, "loss": 0.0015, "step": 303550 }, { "epoch": 72.87, "learning_rate": 2.1417964672391767e-05, "loss": 0.0017, "step": 303560 }, { "epoch": 72.88, "learning_rate": 2.1415019488385492e-05, "loss": 0.0014, "step": 303570 }, { "epoch": 72.88, "learning_rate": 2.141207445170646e-05, "loss": 0.0025, "step": 303580 }, { "epoch": 72.88, "learning_rate": 2.1409129562369816e-05, "loss": 0.0025, "step": 303590 }, { "epoch": 72.88, "learning_rate": 2.1406184820390774e-05, "loss": 0.0014, "step": 303600 }, { "epoch": 72.89, "learning_rate": 2.1403240225784484e-05, "loss": 0.0021, "step": 303610 }, { "epoch": 72.89, "learning_rate": 2.140029577856614e-05, "loss": 0.0017, "step": 303620 }, { "epoch": 72.89, "learning_rate": 2.1397351478750905e-05, "loss": 0.0015, "step": 303630 }, { "epoch": 72.89, "learning_rate": 2.139440732635397e-05, "loss": 0.0035, "step": 303640 }, { "epoch": 72.89, "learning_rate": 2.13914633213905e-05, "loss": 0.0018, "step": 303650 }, { "epoch": 72.9, "learning_rate": 2.138851946387565e-05, "loss": 0.0018, "step": 303660 }, { "epoch": 72.9, "learning_rate": 2.1385575753824628e-05, "loss": 0.0015, "step": 303670 }, { "epoch": 72.9, "learning_rate": 2.1382632191252567e-05, "loss": 0.0068, "step": 303680 }, { "epoch": 72.9, "learning_rate": 2.137968877617468e-05, "loss": 0.0015, "step": 303690 }, { "epoch": 72.91, "learning_rate": 2.13767455086061e-05, "loss": 0.0014, "step": 303700 }, { "epoch": 72.91, "learning_rate": 2.1373802388562027e-05, "loss": 0.0016, "step": 303710 }, { "epoch": 72.91, "learning_rate": 2.1370859416057597e-05, "loss": 0.0016, "step": 303720 }, { "epoch": 72.91, "learning_rate": 2.1367916591108017e-05, "loss": 0.0016, "step": 303730 }, { "epoch": 72.91, "learning_rate": 2.1364973913728436e-05, "loss": 0.0014, "step": 303740 }, { "epoch": 72.92, "learning_rate": 2.1362031383934002e-05, "loss": 0.0016, "step": 303750 }, { "epoch": 72.92, "learning_rate": 2.1359089001739907e-05, "loss": 0.0015, "step": 303760 }, { "epoch": 72.92, "learning_rate": 2.1356146767161294e-05, "loss": 0.0015, "step": 303770 }, { "epoch": 72.92, "learning_rate": 2.1353204680213357e-05, "loss": 0.0017, "step": 303780 }, { "epoch": 72.93, "learning_rate": 2.1350262740911226e-05, "loss": 0.0014, "step": 303790 }, { "epoch": 72.93, "learning_rate": 2.13473209492701e-05, "loss": 0.0014, "step": 303800 }, { "epoch": 72.93, "learning_rate": 2.134437930530512e-05, "loss": 0.0021, "step": 303810 }, { "epoch": 72.93, "learning_rate": 2.1341437809031427e-05, "loss": 0.0013, "step": 303820 }, { "epoch": 72.94, "learning_rate": 2.1338496460464225e-05, "loss": 0.0019, "step": 303830 }, { "epoch": 72.94, "learning_rate": 2.1335555259618634e-05, "loss": 0.002, "step": 303840 }, { "epoch": 72.94, "learning_rate": 2.133261420650985e-05, "loss": 0.0021, "step": 303850 }, { "epoch": 72.94, "learning_rate": 2.1329673301152992e-05, "loss": 0.0018, "step": 303860 }, { "epoch": 72.94, "learning_rate": 2.1326732543563256e-05, "loss": 0.0015, "step": 303870 }, { "epoch": 72.95, "learning_rate": 2.132379193375576e-05, "loss": 0.0013, "step": 303880 }, { "epoch": 72.95, "learning_rate": 2.132085147174568e-05, "loss": 0.0015, "step": 303890 }, { "epoch": 73.0, "learning_rate": 2.1317911157548187e-05, "loss": 0.0014, "step": 303900 }, { "epoch": 73.0, "learning_rate": 2.131497099117841e-05, "loss": 0.0016, "step": 303910 }, { "epoch": 73.0, "learning_rate": 2.1312030972651525e-05, "loss": 0.0015, "step": 303920 }, { "epoch": 73.01, "learning_rate": 2.1309091101982653e-05, "loss": 0.0015, "step": 303930 }, { "epoch": 73.01, "learning_rate": 2.1306151379186983e-05, "loss": 0.0014, "step": 303940 }, { "epoch": 73.01, "learning_rate": 2.1303211804279653e-05, "loss": 0.0016, "step": 303950 }, { "epoch": 73.01, "learning_rate": 2.1300272377275786e-05, "loss": 0.0015, "step": 303960 }, { "epoch": 73.02, "learning_rate": 2.1297333098190574e-05, "loss": 0.0015, "step": 303970 }, { "epoch": 73.02, "learning_rate": 2.1294393967039133e-05, "loss": 0.0015, "step": 303980 }, { "epoch": 73.02, "learning_rate": 2.1291454983836644e-05, "loss": 0.0016, "step": 303990 }, { "epoch": 73.02, "learning_rate": 2.1288516148598214e-05, "loss": 0.0014, "step": 304000 }, { "epoch": 73.03, "learning_rate": 2.1285577461339028e-05, "loss": 0.0015, "step": 304010 }, { "epoch": 73.03, "learning_rate": 2.128263892207422e-05, "loss": 0.0021, "step": 304020 }, { "epoch": 73.03, "learning_rate": 2.1279700530818915e-05, "loss": 0.0013, "step": 304030 }, { "epoch": 73.03, "learning_rate": 2.1276762287588288e-05, "loss": 0.0014, "step": 304040 }, { "epoch": 73.03, "learning_rate": 2.127382419239745e-05, "loss": 0.0013, "step": 304050 }, { "epoch": 73.04, "learning_rate": 2.127088624526158e-05, "loss": 0.0016, "step": 304060 }, { "epoch": 73.04, "learning_rate": 2.1267948446195786e-05, "loss": 0.0015, "step": 304070 }, { "epoch": 73.04, "learning_rate": 2.1265010795215247e-05, "loss": 0.0014, "step": 304080 }, { "epoch": 73.04, "learning_rate": 2.126207329233508e-05, "loss": 0.0015, "step": 304090 }, { "epoch": 73.05, "learning_rate": 2.1259135937570402e-05, "loss": 0.0014, "step": 304100 }, { "epoch": 73.05, "learning_rate": 2.1256198730936405e-05, "loss": 0.0019, "step": 304110 }, { "epoch": 73.05, "learning_rate": 2.1253261672448176e-05, "loss": 0.0014, "step": 304120 }, { "epoch": 73.05, "learning_rate": 2.1250324762120897e-05, "loss": 0.0014, "step": 304130 }, { "epoch": 73.06, "learning_rate": 2.124738799996967e-05, "loss": 0.0014, "step": 304140 }, { "epoch": 73.06, "learning_rate": 2.124445138600966e-05, "loss": 0.0013, "step": 304150 }, { "epoch": 73.06, "learning_rate": 2.1241514920255972e-05, "loss": 0.0014, "step": 304160 }, { "epoch": 73.06, "learning_rate": 2.123857860272377e-05, "loss": 0.0014, "step": 304170 }, { "epoch": 73.06, "learning_rate": 2.123564243342816e-05, "loss": 0.0015, "step": 304180 }, { "epoch": 73.07, "learning_rate": 2.1232706412384306e-05, "loss": 0.0017, "step": 304190 }, { "epoch": 73.07, "learning_rate": 2.122977053960731e-05, "loss": 0.0016, "step": 304200 }, { "epoch": 73.07, "learning_rate": 2.1226834815112312e-05, "loss": 0.0016, "step": 304210 }, { "epoch": 73.07, "learning_rate": 2.1223899238914465e-05, "loss": 0.0015, "step": 304220 }, { "epoch": 73.08, "learning_rate": 2.122096381102888e-05, "loss": 0.0014, "step": 304230 }, { "epoch": 73.08, "learning_rate": 2.121802853147068e-05, "loss": 0.0015, "step": 304240 }, { "epoch": 73.08, "learning_rate": 2.1215093400255015e-05, "loss": 0.0014, "step": 304250 }, { "epoch": 73.08, "learning_rate": 2.1212158417396977e-05, "loss": 0.0016, "step": 304260 }, { "epoch": 73.08, "learning_rate": 2.1209223582911736e-05, "loss": 0.0015, "step": 304270 }, { "epoch": 73.09, "learning_rate": 2.120628889681438e-05, "loss": 0.0015, "step": 304280 }, { "epoch": 73.09, "learning_rate": 2.120335435912007e-05, "loss": 0.0014, "step": 304290 }, { "epoch": 73.09, "learning_rate": 2.120041996984391e-05, "loss": 0.0028, "step": 304300 }, { "epoch": 73.09, "learning_rate": 2.119748572900101e-05, "loss": 0.0015, "step": 304310 }, { "epoch": 73.1, "learning_rate": 2.1194551636606525e-05, "loss": 0.0015, "step": 304320 }, { "epoch": 73.1, "learning_rate": 2.1191617692675547e-05, "loss": 0.0014, "step": 304330 }, { "epoch": 73.1, "learning_rate": 2.1188683897223227e-05, "loss": 0.0015, "step": 304340 }, { "epoch": 73.1, "learning_rate": 2.118575025026466e-05, "loss": 0.0023, "step": 304350 }, { "epoch": 73.11, "learning_rate": 2.118281675181499e-05, "loss": 0.0015, "step": 304360 }, { "epoch": 73.11, "learning_rate": 2.117988340188932e-05, "loss": 0.0015, "step": 304370 }, { "epoch": 73.11, "learning_rate": 2.1176950200502755e-05, "loss": 0.0014, "step": 304380 }, { "epoch": 73.11, "learning_rate": 2.117401714767045e-05, "loss": 0.0016, "step": 304390 }, { "epoch": 73.11, "learning_rate": 2.1171084243407485e-05, "loss": 0.0015, "step": 304400 }, { "epoch": 73.12, "learning_rate": 2.116815148772901e-05, "loss": 0.0018, "step": 304410 }, { "epoch": 73.12, "learning_rate": 2.11652188806501e-05, "loss": 0.0014, "step": 304420 }, { "epoch": 73.12, "learning_rate": 2.1162286422185918e-05, "loss": 0.0014, "step": 304430 }, { "epoch": 73.12, "learning_rate": 2.1159354112351548e-05, "loss": 0.002, "step": 304440 }, { "epoch": 73.13, "learning_rate": 2.1156421951162093e-05, "loss": 0.0015, "step": 304450 }, { "epoch": 73.13, "learning_rate": 2.1153489938632682e-05, "loss": 0.0015, "step": 304460 }, { "epoch": 73.13, "learning_rate": 2.1150558074778436e-05, "loss": 0.0016, "step": 304470 }, { "epoch": 73.13, "learning_rate": 2.1147626359614443e-05, "loss": 0.002, "step": 304480 }, { "epoch": 73.14, "learning_rate": 2.114469479315584e-05, "loss": 0.0015, "step": 304490 }, { "epoch": 73.14, "learning_rate": 2.1141763375417705e-05, "loss": 0.0016, "step": 304500 }, { "epoch": 73.14, "learning_rate": 2.1138832106415164e-05, "loss": 0.0015, "step": 304510 }, { "epoch": 73.14, "learning_rate": 2.113590098616334e-05, "loss": 0.0014, "step": 304520 }, { "epoch": 73.14, "learning_rate": 2.1132970014677323e-05, "loss": 0.0015, "step": 304530 }, { "epoch": 73.15, "learning_rate": 2.11300391919722e-05, "loss": 0.0014, "step": 304540 }, { "epoch": 73.15, "learning_rate": 2.1127108518063116e-05, "loss": 0.0014, "step": 304550 }, { "epoch": 73.15, "learning_rate": 2.1124177992965137e-05, "loss": 0.0014, "step": 304560 }, { "epoch": 73.15, "learning_rate": 2.112124761669341e-05, "loss": 0.0013, "step": 304570 }, { "epoch": 73.16, "learning_rate": 2.1118317389262987e-05, "loss": 0.0018, "step": 304580 }, { "epoch": 73.16, "learning_rate": 2.111538731068902e-05, "loss": 0.0016, "step": 304590 }, { "epoch": 73.16, "learning_rate": 2.1112457380986587e-05, "loss": 0.0061, "step": 304600 }, { "epoch": 73.16, "learning_rate": 2.1109527600170774e-05, "loss": 0.0014, "step": 304610 }, { "epoch": 73.16, "learning_rate": 2.1106597968256715e-05, "loss": 0.0017, "step": 304620 }, { "epoch": 73.17, "learning_rate": 2.1103668485259475e-05, "loss": 0.0014, "step": 304630 }, { "epoch": 73.17, "learning_rate": 2.1100739151194188e-05, "loss": 0.0015, "step": 304640 }, { "epoch": 73.17, "learning_rate": 2.109780996607591e-05, "loss": 0.0016, "step": 304650 }, { "epoch": 73.17, "learning_rate": 2.109488092991978e-05, "loss": 0.0016, "step": 304660 }, { "epoch": 73.18, "learning_rate": 2.1091952042740875e-05, "loss": 0.0013, "step": 304670 }, { "epoch": 73.18, "learning_rate": 2.1089023304554278e-05, "loss": 0.0013, "step": 304680 }, { "epoch": 73.18, "learning_rate": 2.108609471537511e-05, "loss": 0.0015, "step": 304690 }, { "epoch": 73.18, "learning_rate": 2.1083166275218435e-05, "loss": 0.0014, "step": 304700 }, { "epoch": 73.19, "learning_rate": 2.108023798409938e-05, "loss": 0.0014, "step": 304710 }, { "epoch": 73.19, "learning_rate": 2.1077309842033003e-05, "loss": 0.0014, "step": 304720 }, { "epoch": 73.19, "learning_rate": 2.107438184903443e-05, "loss": 0.0014, "step": 304730 }, { "epoch": 73.19, "learning_rate": 2.1071454005118736e-05, "loss": 0.0016, "step": 304740 }, { "epoch": 73.19, "learning_rate": 2.106852631030099e-05, "loss": 0.0015, "step": 304750 }, { "epoch": 73.2, "learning_rate": 2.106559876459632e-05, "loss": 0.0016, "step": 304760 }, { "epoch": 73.2, "learning_rate": 2.1062671368019778e-05, "loss": 0.0015, "step": 304770 }, { "epoch": 73.2, "learning_rate": 2.105974412058647e-05, "loss": 0.0015, "step": 304780 }, { "epoch": 73.2, "learning_rate": 2.10568170223115e-05, "loss": 0.0015, "step": 304790 }, { "epoch": 73.21, "learning_rate": 2.105389007320992e-05, "loss": 0.0014, "step": 304800 }, { "epoch": 73.21, "learning_rate": 2.105096327329685e-05, "loss": 0.0014, "step": 304810 }, { "epoch": 73.21, "learning_rate": 2.1048036622587337e-05, "loss": 0.0013, "step": 304820 }, { "epoch": 73.21, "learning_rate": 2.1045110121096506e-05, "loss": 0.0015, "step": 304830 }, { "epoch": 73.22, "learning_rate": 2.1042183768839402e-05, "loss": 0.0015, "step": 304840 }, { "epoch": 73.22, "learning_rate": 2.1039257565831137e-05, "loss": 0.0015, "step": 304850 }, { "epoch": 73.22, "learning_rate": 2.103633151208677e-05, "loss": 0.0013, "step": 304860 }, { "epoch": 73.22, "learning_rate": 2.103340560762141e-05, "loss": 0.0014, "step": 304870 }, { "epoch": 73.22, "learning_rate": 2.103047985245012e-05, "loss": 0.0014, "step": 304880 }, { "epoch": 73.23, "learning_rate": 2.1027554246587956e-05, "loss": 0.0014, "step": 304890 }, { "epoch": 73.23, "learning_rate": 2.1024628790050038e-05, "loss": 0.0015, "step": 304900 }, { "epoch": 73.23, "learning_rate": 2.1021703482851413e-05, "loss": 0.0013, "step": 304910 }, { "epoch": 73.23, "learning_rate": 2.101877832500718e-05, "loss": 0.0015, "step": 304920 }, { "epoch": 73.24, "learning_rate": 2.1015853316532395e-05, "loss": 0.0015, "step": 304930 }, { "epoch": 73.24, "learning_rate": 2.101292845744216e-05, "loss": 0.0014, "step": 304940 }, { "epoch": 73.24, "learning_rate": 2.1010003747751533e-05, "loss": 0.0014, "step": 304950 }, { "epoch": 73.24, "learning_rate": 2.100707918747557e-05, "loss": 0.0014, "step": 304960 }, { "epoch": 73.24, "learning_rate": 2.1004154776629387e-05, "loss": 0.0034, "step": 304970 }, { "epoch": 73.25, "learning_rate": 2.100123051522801e-05, "loss": 0.0014, "step": 304980 }, { "epoch": 73.25, "learning_rate": 2.099830640328655e-05, "loss": 0.009, "step": 304990 }, { "epoch": 73.25, "learning_rate": 2.0995382440820045e-05, "loss": 0.0014, "step": 305000 }, { "epoch": 73.25, "learning_rate": 2.0992458627843603e-05, "loss": 0.0015, "step": 305010 }, { "epoch": 73.26, "learning_rate": 2.0989534964372265e-05, "loss": 0.0014, "step": 305020 }, { "epoch": 73.26, "learning_rate": 2.0986611450421096e-05, "loss": 0.0014, "step": 305030 }, { "epoch": 73.26, "learning_rate": 2.0983688086005182e-05, "loss": 0.0015, "step": 305040 }, { "epoch": 73.26, "learning_rate": 2.0980764871139575e-05, "loss": 0.0011, "step": 305050 }, { "epoch": 73.27, "learning_rate": 2.097784180583936e-05, "loss": 0.0012, "step": 305060 }, { "epoch": 73.27, "learning_rate": 2.0974918890119573e-05, "loss": 0.0014, "step": 305070 }, { "epoch": 73.27, "learning_rate": 2.0971996123995297e-05, "loss": 0.0021, "step": 305080 }, { "epoch": 73.27, "learning_rate": 2.0969073507481618e-05, "loss": 0.0016, "step": 305090 }, { "epoch": 73.27, "learning_rate": 2.096615104059355e-05, "loss": 0.0014, "step": 305100 }, { "epoch": 73.28, "learning_rate": 2.0963228723346207e-05, "loss": 0.0015, "step": 305110 }, { "epoch": 73.28, "learning_rate": 2.0960306555754606e-05, "loss": 0.0016, "step": 305120 }, { "epoch": 73.28, "learning_rate": 2.0957384537833846e-05, "loss": 0.0017, "step": 305130 }, { "epoch": 73.28, "learning_rate": 2.0954462669598952e-05, "loss": 0.0014, "step": 305140 }, { "epoch": 73.29, "learning_rate": 2.095154095106502e-05, "loss": 0.0014, "step": 305150 }, { "epoch": 73.29, "learning_rate": 2.094861938224708e-05, "loss": 0.0014, "step": 305160 }, { "epoch": 73.29, "learning_rate": 2.094569796316019e-05, "loss": 0.0014, "step": 305170 }, { "epoch": 73.29, "learning_rate": 2.0942776693819432e-05, "loss": 0.0014, "step": 305180 }, { "epoch": 73.3, "learning_rate": 2.0939855574239826e-05, "loss": 0.0016, "step": 305190 }, { "epoch": 73.3, "learning_rate": 2.0936934604436466e-05, "loss": 0.0016, "step": 305200 }, { "epoch": 73.3, "learning_rate": 2.0934013784424367e-05, "loss": 0.0014, "step": 305210 }, { "epoch": 73.3, "learning_rate": 2.0931093114218626e-05, "loss": 0.0014, "step": 305220 }, { "epoch": 73.3, "learning_rate": 2.0928172593834268e-05, "loss": 0.0024, "step": 305230 }, { "epoch": 73.31, "learning_rate": 2.092525222328634e-05, "loss": 0.0014, "step": 305240 }, { "epoch": 73.31, "learning_rate": 2.0922332002589917e-05, "loss": 0.0015, "step": 305250 }, { "epoch": 73.31, "learning_rate": 2.0919411931760025e-05, "loss": 0.0014, "step": 305260 }, { "epoch": 73.31, "learning_rate": 2.0916492010811746e-05, "loss": 0.0016, "step": 305270 }, { "epoch": 73.32, "learning_rate": 2.0913572239760088e-05, "loss": 0.0014, "step": 305280 }, { "epoch": 73.32, "learning_rate": 2.091065261862014e-05, "loss": 0.0014, "step": 305290 }, { "epoch": 73.32, "learning_rate": 2.0907733147406914e-05, "loss": 0.0013, "step": 305300 }, { "epoch": 73.32, "learning_rate": 2.0904813826135495e-05, "loss": 0.0029, "step": 305310 }, { "epoch": 73.32, "learning_rate": 2.0901894654820908e-05, "loss": 0.0014, "step": 305320 }, { "epoch": 73.33, "learning_rate": 2.089897563347818e-05, "loss": 0.0015, "step": 305330 }, { "epoch": 73.33, "learning_rate": 2.0896056762122395e-05, "loss": 0.0014, "step": 305340 }, { "epoch": 73.33, "learning_rate": 2.0893138040768555e-05, "loss": 0.0014, "step": 305350 }, { "epoch": 73.33, "learning_rate": 2.089021946943175e-05, "loss": 0.0014, "step": 305360 }, { "epoch": 73.34, "learning_rate": 2.0887301048126974e-05, "loss": 0.0014, "step": 305370 }, { "epoch": 73.34, "learning_rate": 2.0884382776869305e-05, "loss": 0.0014, "step": 305380 }, { "epoch": 73.34, "learning_rate": 2.088146465567376e-05, "loss": 0.0015, "step": 305390 }, { "epoch": 73.34, "learning_rate": 2.0878546684555385e-05, "loss": 0.0014, "step": 305400 }, { "epoch": 73.35, "learning_rate": 2.0875628863529246e-05, "loss": 0.0016, "step": 305410 }, { "epoch": 73.35, "learning_rate": 2.087271119261034e-05, "loss": 0.0013, "step": 305420 }, { "epoch": 73.35, "learning_rate": 2.0869793671813735e-05, "loss": 0.0014, "step": 305430 }, { "epoch": 73.35, "learning_rate": 2.086687630115445e-05, "loss": 0.0013, "step": 305440 }, { "epoch": 73.35, "learning_rate": 2.086395908064754e-05, "loss": 0.0015, "step": 305450 }, { "epoch": 73.36, "learning_rate": 2.086104201030803e-05, "loss": 0.0013, "step": 305460 }, { "epoch": 73.36, "learning_rate": 2.085812509015093e-05, "loss": 0.0014, "step": 305470 }, { "epoch": 73.36, "learning_rate": 2.085520832019132e-05, "loss": 0.0014, "step": 305480 }, { "epoch": 73.36, "learning_rate": 2.0852291700444194e-05, "loss": 0.0015, "step": 305490 }, { "epoch": 73.37, "learning_rate": 2.0849375230924616e-05, "loss": 0.0021, "step": 305500 }, { "epoch": 73.37, "learning_rate": 2.084645891164758e-05, "loss": 0.0014, "step": 305510 }, { "epoch": 73.37, "learning_rate": 2.0843542742628164e-05, "loss": 0.0014, "step": 305520 }, { "epoch": 73.37, "learning_rate": 2.084062672388137e-05, "loss": 0.0014, "step": 305530 }, { "epoch": 73.38, "learning_rate": 2.0837710855422205e-05, "loss": 0.0014, "step": 305540 }, { "epoch": 73.38, "learning_rate": 2.0834795137265743e-05, "loss": 0.0016, "step": 305550 }, { "epoch": 73.38, "learning_rate": 2.0831879569426978e-05, "loss": 0.0014, "step": 305560 }, { "epoch": 73.38, "learning_rate": 2.082896415192096e-05, "loss": 0.002, "step": 305570 }, { "epoch": 73.38, "learning_rate": 2.0826048884762693e-05, "loss": 0.0016, "step": 305580 }, { "epoch": 73.39, "learning_rate": 2.082313376796723e-05, "loss": 0.0015, "step": 305590 }, { "epoch": 73.39, "learning_rate": 2.082021880154958e-05, "loss": 0.0016, "step": 305600 }, { "epoch": 73.39, "learning_rate": 2.0817303985524745e-05, "loss": 0.0018, "step": 305610 }, { "epoch": 73.39, "learning_rate": 2.081438931990779e-05, "loss": 0.0015, "step": 305620 }, { "epoch": 73.4, "learning_rate": 2.08114748047137e-05, "loss": 0.0014, "step": 305630 }, { "epoch": 73.4, "learning_rate": 2.0808560439957525e-05, "loss": 0.0014, "step": 305640 }, { "epoch": 73.4, "learning_rate": 2.0805646225654258e-05, "loss": 0.0012, "step": 305650 }, { "epoch": 73.4, "learning_rate": 2.0802732161818954e-05, "loss": 0.0014, "step": 305660 }, { "epoch": 73.4, "learning_rate": 2.0799818248466594e-05, "loss": 0.0015, "step": 305670 }, { "epoch": 73.41, "learning_rate": 2.0796904485612234e-05, "loss": 0.0015, "step": 305680 }, { "epoch": 73.41, "learning_rate": 2.0793990873270854e-05, "loss": 0.0014, "step": 305690 }, { "epoch": 73.41, "learning_rate": 2.0791077411457505e-05, "loss": 0.0013, "step": 305700 }, { "epoch": 73.41, "learning_rate": 2.078816410018717e-05, "loss": 0.0014, "step": 305710 }, { "epoch": 73.42, "learning_rate": 2.0785250939474883e-05, "loss": 0.0014, "step": 305720 }, { "epoch": 73.42, "learning_rate": 2.078233792933567e-05, "loss": 0.0014, "step": 305730 }, { "epoch": 73.42, "learning_rate": 2.0779425069784535e-05, "loss": 0.0015, "step": 305740 }, { "epoch": 73.42, "learning_rate": 2.077651236083647e-05, "loss": 0.0013, "step": 305750 }, { "epoch": 73.43, "learning_rate": 2.077359980250652e-05, "loss": 0.0014, "step": 305760 }, { "epoch": 73.43, "learning_rate": 2.077068739480967e-05, "loss": 0.0014, "step": 305770 }, { "epoch": 73.43, "learning_rate": 2.0767775137760954e-05, "loss": 0.0013, "step": 305780 }, { "epoch": 73.43, "learning_rate": 2.0764863031375348e-05, "loss": 0.0014, "step": 305790 }, { "epoch": 73.43, "learning_rate": 2.0761951075667908e-05, "loss": 0.0013, "step": 305800 }, { "epoch": 73.44, "learning_rate": 2.0759039270653612e-05, "loss": 0.0016, "step": 305810 }, { "epoch": 73.44, "learning_rate": 2.0756127616347454e-05, "loss": 0.0014, "step": 305820 }, { "epoch": 73.44, "learning_rate": 2.075321611276448e-05, "loss": 0.0013, "step": 305830 }, { "epoch": 73.44, "learning_rate": 2.0750304759919652e-05, "loss": 0.0015, "step": 305840 }, { "epoch": 73.45, "learning_rate": 2.0747393557828016e-05, "loss": 0.0014, "step": 305850 }, { "epoch": 73.45, "learning_rate": 2.0744482506504542e-05, "loss": 0.0015, "step": 305860 }, { "epoch": 73.45, "learning_rate": 2.0741571605964266e-05, "loss": 0.0012, "step": 305870 }, { "epoch": 73.45, "learning_rate": 2.073866085622218e-05, "loss": 0.0016, "step": 305880 }, { "epoch": 73.45, "learning_rate": 2.0735750257293256e-05, "loss": 0.0014, "step": 305890 }, { "epoch": 73.46, "learning_rate": 2.073283980919254e-05, "loss": 0.0013, "step": 305900 }, { "epoch": 73.46, "learning_rate": 2.0729929511935e-05, "loss": 0.0015, "step": 305910 }, { "epoch": 73.46, "learning_rate": 2.0727019365535654e-05, "loss": 0.0013, "step": 305920 }, { "epoch": 73.46, "learning_rate": 2.0724109370009485e-05, "loss": 0.0016, "step": 305930 }, { "epoch": 73.47, "learning_rate": 2.072119952537152e-05, "loss": 0.0015, "step": 305940 }, { "epoch": 73.47, "learning_rate": 2.0718289831636732e-05, "loss": 0.0014, "step": 305950 }, { "epoch": 73.47, "learning_rate": 2.071538028882011e-05, "loss": 0.0015, "step": 305960 }, { "epoch": 73.47, "learning_rate": 2.071247089693666e-05, "loss": 0.0013, "step": 305970 }, { "epoch": 73.48, "learning_rate": 2.0709561656001396e-05, "loss": 0.0017, "step": 305980 }, { "epoch": 73.48, "learning_rate": 2.0706652566029284e-05, "loss": 0.0014, "step": 305990 }, { "epoch": 73.48, "learning_rate": 2.0703743627035344e-05, "loss": 0.0015, "step": 306000 }, { "epoch": 73.48, "learning_rate": 2.0700834839034533e-05, "loss": 0.0012, "step": 306010 }, { "epoch": 73.48, "learning_rate": 2.069792620204189e-05, "loss": 0.0014, "step": 306020 }, { "epoch": 73.49, "learning_rate": 2.0695017716072357e-05, "loss": 0.0014, "step": 306030 }, { "epoch": 73.49, "learning_rate": 2.0692109381140963e-05, "loss": 0.0014, "step": 306040 }, { "epoch": 73.49, "learning_rate": 2.068920119726267e-05, "loss": 0.0014, "step": 306050 }, { "epoch": 73.49, "learning_rate": 2.068629316445249e-05, "loss": 0.0014, "step": 306060 }, { "epoch": 73.5, "learning_rate": 2.0683385282725386e-05, "loss": 0.0017, "step": 306070 }, { "epoch": 73.5, "learning_rate": 2.0680477552096383e-05, "loss": 0.0016, "step": 306080 }, { "epoch": 73.5, "learning_rate": 2.067756997258042e-05, "loss": 0.0016, "step": 306090 }, { "epoch": 73.5, "learning_rate": 2.0674662544192526e-05, "loss": 0.0013, "step": 306100 }, { "epoch": 73.51, "learning_rate": 2.0671755266947662e-05, "loss": 0.0015, "step": 306110 }, { "epoch": 73.51, "learning_rate": 2.0668848140860802e-05, "loss": 0.0013, "step": 306120 }, { "epoch": 73.51, "learning_rate": 2.066594116594696e-05, "loss": 0.0014, "step": 306130 }, { "epoch": 73.51, "learning_rate": 2.066303434222109e-05, "loss": 0.0014, "step": 306140 }, { "epoch": 73.51, "learning_rate": 2.0660127669698197e-05, "loss": 0.0011, "step": 306150 }, { "epoch": 73.52, "learning_rate": 2.065722114839324e-05, "loss": 0.0026, "step": 306160 }, { "epoch": 73.52, "learning_rate": 2.0654314778321226e-05, "loss": 0.0013, "step": 306170 }, { "epoch": 73.52, "learning_rate": 2.0651408559497116e-05, "loss": 0.0014, "step": 306180 }, { "epoch": 73.52, "learning_rate": 2.0648502491935878e-05, "loss": 0.0017, "step": 306190 }, { "epoch": 73.53, "learning_rate": 2.0645596575652522e-05, "loss": 0.0017, "step": 306200 }, { "epoch": 73.53, "learning_rate": 2.064269081066198e-05, "loss": 0.0015, "step": 306210 }, { "epoch": 73.53, "learning_rate": 2.0639785196979285e-05, "loss": 0.0015, "step": 306220 }, { "epoch": 73.53, "learning_rate": 2.063687973461935e-05, "loss": 0.0016, "step": 306230 }, { "epoch": 73.53, "learning_rate": 2.0633974423597214e-05, "loss": 0.0018, "step": 306240 }, { "epoch": 73.54, "learning_rate": 2.063106926392781e-05, "loss": 0.0015, "step": 306250 }, { "epoch": 73.54, "learning_rate": 2.062816425562611e-05, "loss": 0.0015, "step": 306260 }, { "epoch": 73.54, "learning_rate": 2.0625259398707107e-05, "loss": 0.0015, "step": 306270 }, { "epoch": 73.54, "learning_rate": 2.0622354693185752e-05, "loss": 0.0019, "step": 306280 }, { "epoch": 73.55, "learning_rate": 2.0619450139077024e-05, "loss": 0.0015, "step": 306290 }, { "epoch": 73.55, "learning_rate": 2.0616545736395914e-05, "loss": 0.0017, "step": 306300 }, { "epoch": 73.55, "learning_rate": 2.0613641485157352e-05, "loss": 0.0016, "step": 306310 }, { "epoch": 73.55, "learning_rate": 2.061073738537635e-05, "loss": 0.0019, "step": 306320 }, { "epoch": 73.56, "learning_rate": 2.060783343706783e-05, "loss": 0.0014, "step": 306330 }, { "epoch": 73.56, "learning_rate": 2.06049296402468e-05, "loss": 0.0014, "step": 306340 }, { "epoch": 73.56, "learning_rate": 2.06020259949282e-05, "loss": 0.0018, "step": 306350 }, { "epoch": 73.56, "learning_rate": 2.059912250112701e-05, "loss": 0.0016, "step": 306360 }, { "epoch": 73.56, "learning_rate": 2.0596219158858176e-05, "loss": 0.003, "step": 306370 }, { "epoch": 73.57, "learning_rate": 2.059331596813669e-05, "loss": 0.0016, "step": 306380 }, { "epoch": 73.57, "learning_rate": 2.0590412928977505e-05, "loss": 0.0016, "step": 306390 }, { "epoch": 73.57, "learning_rate": 2.0587510041395554e-05, "loss": 0.0015, "step": 306400 }, { "epoch": 73.57, "learning_rate": 2.058460730540584e-05, "loss": 0.0014, "step": 306410 }, { "epoch": 73.58, "learning_rate": 2.058170472102329e-05, "loss": 0.0015, "step": 306420 }, { "epoch": 73.58, "learning_rate": 2.0578802288262895e-05, "loss": 0.0015, "step": 306430 }, { "epoch": 73.58, "learning_rate": 2.057590000713958e-05, "loss": 0.0018, "step": 306440 }, { "epoch": 73.58, "learning_rate": 2.057299787766835e-05, "loss": 0.0015, "step": 306450 }, { "epoch": 73.59, "learning_rate": 2.057009589986412e-05, "loss": 0.0017, "step": 306460 }, { "epoch": 73.59, "learning_rate": 2.0567194073741857e-05, "loss": 0.0145, "step": 306470 }, { "epoch": 73.59, "learning_rate": 2.0564292399316533e-05, "loss": 0.0016, "step": 306480 }, { "epoch": 73.59, "learning_rate": 2.0561390876603076e-05, "loss": 0.0021, "step": 306490 }, { "epoch": 73.59, "learning_rate": 2.0558489505616473e-05, "loss": 0.002, "step": 306500 }, { "epoch": 73.6, "learning_rate": 2.0555588286371645e-05, "loss": 0.0017, "step": 306510 }, { "epoch": 73.6, "learning_rate": 2.0552687218883575e-05, "loss": 0.0016, "step": 306520 }, { "epoch": 73.6, "learning_rate": 2.0549786303167206e-05, "loss": 0.0015, "step": 306530 }, { "epoch": 73.6, "learning_rate": 2.0546885539237465e-05, "loss": 0.0102, "step": 306540 }, { "epoch": 73.61, "learning_rate": 2.0543984927109343e-05, "loss": 0.0016, "step": 306550 }, { "epoch": 73.61, "learning_rate": 2.0541084466797745e-05, "loss": 0.002, "step": 306560 }, { "epoch": 73.61, "learning_rate": 2.053818415831767e-05, "loss": 0.0015, "step": 306570 }, { "epoch": 73.61, "learning_rate": 2.0535284001684013e-05, "loss": 0.002, "step": 306580 }, { "epoch": 73.61, "learning_rate": 2.053238399691177e-05, "loss": 0.0019, "step": 306590 }, { "epoch": 73.62, "learning_rate": 2.052948414401585e-05, "loss": 0.0014, "step": 306600 }, { "epoch": 73.62, "learning_rate": 2.0526584443011215e-05, "loss": 0.0016, "step": 306610 }, { "epoch": 73.62, "learning_rate": 2.0523684893912827e-05, "loss": 0.0017, "step": 306620 }, { "epoch": 73.62, "learning_rate": 2.0520785496735595e-05, "loss": 0.0016, "step": 306630 }, { "epoch": 73.63, "learning_rate": 2.05178862514945e-05, "loss": 0.0015, "step": 306640 }, { "epoch": 73.63, "learning_rate": 2.0514987158204447e-05, "loss": 0.0022, "step": 306650 }, { "epoch": 73.63, "learning_rate": 2.0512088216880415e-05, "loss": 0.0015, "step": 306660 }, { "epoch": 73.63, "learning_rate": 2.0509189427537322e-05, "loss": 0.0017, "step": 306670 }, { "epoch": 73.64, "learning_rate": 2.05062907901901e-05, "loss": 0.0014, "step": 306680 }, { "epoch": 73.64, "learning_rate": 2.0503392304853726e-05, "loss": 0.0019, "step": 306690 }, { "epoch": 73.64, "learning_rate": 2.050049397154309e-05, "loss": 0.0015, "step": 306700 }, { "epoch": 73.64, "learning_rate": 2.0497595790273173e-05, "loss": 0.0015, "step": 306710 }, { "epoch": 73.64, "learning_rate": 2.0494697761058873e-05, "loss": 0.0058, "step": 306720 }, { "epoch": 73.65, "learning_rate": 2.049179988391517e-05, "loss": 0.0018, "step": 306730 }, { "epoch": 73.65, "learning_rate": 2.0488902158856972e-05, "loss": 0.0014, "step": 306740 }, { "epoch": 73.65, "learning_rate": 2.0486004585899206e-05, "loss": 0.0021, "step": 306750 }, { "epoch": 73.65, "learning_rate": 2.0483107165056838e-05, "loss": 0.0025, "step": 306760 }, { "epoch": 73.66, "learning_rate": 2.048020989634476e-05, "loss": 0.0014, "step": 306770 }, { "epoch": 73.66, "learning_rate": 2.0477312779777946e-05, "loss": 0.0017, "step": 306780 }, { "epoch": 73.66, "learning_rate": 2.047441581537129e-05, "loss": 0.0015, "step": 306790 }, { "epoch": 73.66, "learning_rate": 2.0471519003139762e-05, "loss": 0.0018, "step": 306800 }, { "epoch": 73.67, "learning_rate": 2.046862234309827e-05, "loss": 0.0019, "step": 306810 }, { "epoch": 73.67, "learning_rate": 2.046572583526173e-05, "loss": 0.0018, "step": 306820 }, { "epoch": 73.67, "learning_rate": 2.04628294796451e-05, "loss": 0.0017, "step": 306830 }, { "epoch": 73.67, "learning_rate": 2.0459933276263276e-05, "loss": 0.0015, "step": 306840 }, { "epoch": 73.67, "learning_rate": 2.0457037225131226e-05, "loss": 0.0016, "step": 306850 }, { "epoch": 73.68, "learning_rate": 2.045414132626383e-05, "loss": 0.0015, "step": 306860 }, { "epoch": 73.68, "learning_rate": 2.0451245579676055e-05, "loss": 0.0016, "step": 306870 }, { "epoch": 73.68, "learning_rate": 2.0448349985382792e-05, "loss": 0.0015, "step": 306880 }, { "epoch": 73.68, "learning_rate": 2.0445454543398995e-05, "loss": 0.0033, "step": 306890 }, { "epoch": 73.69, "learning_rate": 2.0442559253739556e-05, "loss": 0.0013, "step": 306900 }, { "epoch": 73.69, "learning_rate": 2.0439664116419415e-05, "loss": 0.0035, "step": 306910 }, { "epoch": 73.69, "learning_rate": 2.043676913145351e-05, "loss": 0.0014, "step": 306920 }, { "epoch": 73.69, "learning_rate": 2.0433874298856727e-05, "loss": 0.0015, "step": 306930 }, { "epoch": 73.69, "learning_rate": 2.0430979618644015e-05, "loss": 0.0015, "step": 306940 }, { "epoch": 73.7, "learning_rate": 2.0428085090830268e-05, "loss": 0.0015, "step": 306950 }, { "epoch": 73.7, "learning_rate": 2.0425190715430433e-05, "loss": 0.0013, "step": 306960 }, { "epoch": 73.7, "learning_rate": 2.0422296492459414e-05, "loss": 0.0014, "step": 306970 }, { "epoch": 73.7, "learning_rate": 2.041940242193211e-05, "loss": 0.002, "step": 306980 }, { "epoch": 73.71, "learning_rate": 2.041650850386347e-05, "loss": 0.0016, "step": 306990 }, { "epoch": 73.71, "learning_rate": 2.0413614738268373e-05, "loss": 0.0014, "step": 307000 }, { "epoch": 73.71, "learning_rate": 2.0410721125161768e-05, "loss": 0.0016, "step": 307010 }, { "epoch": 73.71, "learning_rate": 2.0407827664558542e-05, "loss": 0.0019, "step": 307020 }, { "epoch": 73.72, "learning_rate": 2.0404934356473638e-05, "loss": 0.0016, "step": 307030 }, { "epoch": 73.72, "learning_rate": 2.0402041200921945e-05, "loss": 0.0016, "step": 307040 }, { "epoch": 73.72, "learning_rate": 2.039914819791836e-05, "loss": 0.0016, "step": 307050 }, { "epoch": 73.72, "learning_rate": 2.039625534747783e-05, "loss": 0.0015, "step": 307060 }, { "epoch": 73.72, "learning_rate": 2.039336264961524e-05, "loss": 0.0013, "step": 307070 }, { "epoch": 73.73, "learning_rate": 2.0390470104345516e-05, "loss": 0.0013, "step": 307080 }, { "epoch": 73.73, "learning_rate": 2.0387577711683535e-05, "loss": 0.0015, "step": 307090 }, { "epoch": 73.73, "learning_rate": 2.038468547164425e-05, "loss": 0.0018, "step": 307100 }, { "epoch": 73.73, "learning_rate": 2.0381793384242544e-05, "loss": 0.0013, "step": 307110 }, { "epoch": 73.74, "learning_rate": 2.0378901449493306e-05, "loss": 0.0017, "step": 307120 }, { "epoch": 73.74, "learning_rate": 2.0376009667411466e-05, "loss": 0.0017, "step": 307130 }, { "epoch": 73.74, "learning_rate": 2.0373118038011914e-05, "loss": 0.0014, "step": 307140 }, { "epoch": 73.74, "learning_rate": 2.037022656130957e-05, "loss": 0.0017, "step": 307150 }, { "epoch": 73.75, "learning_rate": 2.0367335237319306e-05, "loss": 0.0018, "step": 307160 }, { "epoch": 73.75, "learning_rate": 2.0364444066056066e-05, "loss": 0.0015, "step": 307170 }, { "epoch": 73.75, "learning_rate": 2.036155304753471e-05, "loss": 0.0051, "step": 307180 }, { "epoch": 73.75, "learning_rate": 2.035866218177018e-05, "loss": 0.0016, "step": 307190 }, { "epoch": 73.75, "learning_rate": 2.0355771468777323e-05, "loss": 0.0017, "step": 307200 }, { "epoch": 73.76, "learning_rate": 2.03528809085711e-05, "loss": 0.0016, "step": 307210 }, { "epoch": 73.76, "learning_rate": 2.0349990501166348e-05, "loss": 0.0031, "step": 307220 }, { "epoch": 73.76, "learning_rate": 2.0347100246577993e-05, "loss": 0.0016, "step": 307230 }, { "epoch": 73.76, "learning_rate": 2.0344210144820958e-05, "loss": 0.0019, "step": 307240 }, { "epoch": 73.77, "learning_rate": 2.03413201959101e-05, "loss": 0.0017, "step": 307250 }, { "epoch": 73.77, "learning_rate": 2.033843039986032e-05, "loss": 0.0014, "step": 307260 }, { "epoch": 73.77, "learning_rate": 2.0335540756686527e-05, "loss": 0.0016, "step": 307270 }, { "epoch": 73.77, "learning_rate": 2.033265126640359e-05, "loss": 0.0051, "step": 307280 }, { "epoch": 73.77, "learning_rate": 2.0329761929026438e-05, "loss": 0.0016, "step": 307290 }, { "epoch": 73.78, "learning_rate": 2.0326872744569913e-05, "loss": 0.0022, "step": 307300 }, { "epoch": 73.78, "learning_rate": 2.032398371304896e-05, "loss": 0.0015, "step": 307310 }, { "epoch": 73.78, "learning_rate": 2.032109483447844e-05, "loss": 0.0046, "step": 307320 }, { "epoch": 73.78, "learning_rate": 2.031820610887323e-05, "loss": 0.0013, "step": 307330 }, { "epoch": 73.79, "learning_rate": 2.0315317536248246e-05, "loss": 0.0014, "step": 307340 }, { "epoch": 73.79, "learning_rate": 2.0312429116618353e-05, "loss": 0.0015, "step": 307350 }, { "epoch": 73.79, "learning_rate": 2.030954084999846e-05, "loss": 0.0015, "step": 307360 }, { "epoch": 73.79, "learning_rate": 2.030665273640343e-05, "loss": 0.0018, "step": 307370 }, { "epoch": 73.8, "learning_rate": 2.030376477584817e-05, "loss": 0.0017, "step": 307380 }, { "epoch": 73.8, "learning_rate": 2.030087696834756e-05, "loss": 0.0016, "step": 307390 }, { "epoch": 73.8, "learning_rate": 2.029798931391646e-05, "loss": 0.0015, "step": 307400 }, { "epoch": 73.8, "learning_rate": 2.029510181256979e-05, "loss": 0.0026, "step": 307410 }, { "epoch": 73.8, "learning_rate": 2.0292214464322395e-05, "loss": 0.0014, "step": 307420 }, { "epoch": 73.81, "learning_rate": 2.028932726918919e-05, "loss": 0.0013, "step": 307430 }, { "epoch": 73.81, "learning_rate": 2.0286440227185026e-05, "loss": 0.003, "step": 307440 }, { "epoch": 73.81, "learning_rate": 2.028355333832482e-05, "loss": 0.0015, "step": 307450 }, { "epoch": 73.81, "learning_rate": 2.0280666602623417e-05, "loss": 0.0014, "step": 307460 }, { "epoch": 73.82, "learning_rate": 2.0277780020095694e-05, "loss": 0.0232, "step": 307470 }, { "epoch": 73.82, "learning_rate": 2.0274893590756545e-05, "loss": 0.0018, "step": 307480 }, { "epoch": 73.82, "learning_rate": 2.0272007314620855e-05, "loss": 0.0015, "step": 307490 }, { "epoch": 73.82, "learning_rate": 2.026912119170347e-05, "loss": 0.0016, "step": 307500 }, { "epoch": 73.83, "learning_rate": 2.0266235222019307e-05, "loss": 0.0014, "step": 307510 }, { "epoch": 73.83, "learning_rate": 2.0263349405583194e-05, "loss": 0.0015, "step": 307520 }, { "epoch": 73.83, "learning_rate": 2.0260463742410045e-05, "loss": 0.0012, "step": 307530 }, { "epoch": 73.83, "learning_rate": 2.0257578232514702e-05, "loss": 0.0014, "step": 307540 }, { "epoch": 73.83, "learning_rate": 2.0254692875912057e-05, "loss": 0.0017, "step": 307550 }, { "epoch": 73.84, "learning_rate": 2.025180767261696e-05, "loss": 0.0014, "step": 307560 }, { "epoch": 73.84, "learning_rate": 2.0248922622644316e-05, "loss": 0.0014, "step": 307570 }, { "epoch": 73.84, "learning_rate": 2.0246037726008954e-05, "loss": 0.0015, "step": 307580 }, { "epoch": 73.84, "learning_rate": 2.0243152982725777e-05, "loss": 0.0017, "step": 307590 }, { "epoch": 73.85, "learning_rate": 2.024026839280964e-05, "loss": 0.0128, "step": 307600 }, { "epoch": 73.85, "learning_rate": 2.023738395627539e-05, "loss": 0.0024, "step": 307610 }, { "epoch": 73.85, "learning_rate": 2.0234499673137935e-05, "loss": 0.0016, "step": 307620 }, { "epoch": 73.85, "learning_rate": 2.0231615543412096e-05, "loss": 0.0014, "step": 307630 }, { "epoch": 73.85, "learning_rate": 2.0228731567112773e-05, "loss": 0.0015, "step": 307640 }, { "epoch": 73.86, "learning_rate": 2.0225847744254807e-05, "loss": 0.0015, "step": 307650 }, { "epoch": 73.86, "learning_rate": 2.022296407485308e-05, "loss": 0.0015, "step": 307660 }, { "epoch": 73.86, "learning_rate": 2.022008055892245e-05, "loss": 0.0015, "step": 307670 }, { "epoch": 73.86, "learning_rate": 2.0217197196477754e-05, "loss": 0.0015, "step": 307680 }, { "epoch": 73.87, "learning_rate": 2.0214313987533896e-05, "loss": 0.0015, "step": 307690 }, { "epoch": 73.87, "learning_rate": 2.0211430932105684e-05, "loss": 0.0102, "step": 307700 }, { "epoch": 73.87, "learning_rate": 2.020854803020803e-05, "loss": 0.0015, "step": 307710 }, { "epoch": 73.87, "learning_rate": 2.0205665281855752e-05, "loss": 0.0013, "step": 307720 }, { "epoch": 73.88, "learning_rate": 2.020278268706374e-05, "loss": 0.0015, "step": 307730 }, { "epoch": 73.88, "learning_rate": 2.019990024584682e-05, "loss": 0.0015, "step": 307740 }, { "epoch": 73.88, "learning_rate": 2.0197017958219875e-05, "loss": 0.0016, "step": 307750 }, { "epoch": 73.88, "learning_rate": 2.019413582419775e-05, "loss": 0.0014, "step": 307760 }, { "epoch": 73.88, "learning_rate": 2.0191253843795288e-05, "loss": 0.0014, "step": 307770 }, { "epoch": 73.89, "learning_rate": 2.0188372017027363e-05, "loss": 0.0014, "step": 307780 }, { "epoch": 73.89, "learning_rate": 2.01854903439088e-05, "loss": 0.0015, "step": 307790 }, { "epoch": 73.89, "learning_rate": 2.0182608824454475e-05, "loss": 0.0013, "step": 307800 }, { "epoch": 73.89, "learning_rate": 2.0179727458679247e-05, "loss": 0.0013, "step": 307810 }, { "epoch": 73.9, "learning_rate": 2.0176846246597937e-05, "loss": 0.0014, "step": 307820 }, { "epoch": 73.9, "learning_rate": 2.0173965188225423e-05, "loss": 0.0015, "step": 307830 }, { "epoch": 73.9, "learning_rate": 2.017108428357653e-05, "loss": 0.0014, "step": 307840 }, { "epoch": 73.9, "learning_rate": 2.0168203532666135e-05, "loss": 0.0014, "step": 307850 }, { "epoch": 73.91, "learning_rate": 2.0165322935509047e-05, "loss": 0.0013, "step": 307860 }, { "epoch": 73.91, "learning_rate": 2.0162442492120152e-05, "loss": 0.0015, "step": 307870 }, { "epoch": 73.91, "learning_rate": 2.0159562202514263e-05, "loss": 0.0014, "step": 307880 }, { "epoch": 73.91, "learning_rate": 2.0156682066706257e-05, "loss": 0.0037, "step": 307890 }, { "epoch": 73.91, "learning_rate": 2.015380208471096e-05, "loss": 0.0013, "step": 307900 }, { "epoch": 73.92, "learning_rate": 2.0150922256543204e-05, "loss": 0.0015, "step": 307910 }, { "epoch": 73.92, "learning_rate": 2.0148042582217857e-05, "loss": 0.0015, "step": 307920 }, { "epoch": 73.92, "learning_rate": 2.014516306174973e-05, "loss": 0.0015, "step": 307930 }, { "epoch": 73.92, "learning_rate": 2.01422836951537e-05, "loss": 0.0014, "step": 307940 }, { "epoch": 73.93, "learning_rate": 2.0139404482444573e-05, "loss": 0.0015, "step": 307950 }, { "epoch": 73.93, "learning_rate": 2.013652542363722e-05, "loss": 0.0012, "step": 307960 }, { "epoch": 73.93, "learning_rate": 2.013364651874647e-05, "loss": 0.0012, "step": 307970 }, { "epoch": 73.93, "learning_rate": 2.013076776778713e-05, "loss": 0.0014, "step": 307980 }, { "epoch": 73.93, "learning_rate": 2.0127889170774084e-05, "loss": 0.0014, "step": 307990 }, { "epoch": 73.94, "learning_rate": 2.012501072772213e-05, "loss": 0.0014, "step": 308000 }, { "epoch": 73.94, "learning_rate": 2.012213243864614e-05, "loss": 0.0017, "step": 308010 }, { "epoch": 73.94, "learning_rate": 2.0119254303560907e-05, "loss": 0.0014, "step": 308020 }, { "epoch": 73.94, "learning_rate": 2.0116376322481307e-05, "loss": 0.0014, "step": 308030 }, { "epoch": 73.95, "learning_rate": 2.0113498495422155e-05, "loss": 0.0015, "step": 308040 }, { "epoch": 73.95, "learning_rate": 2.0110620822398263e-05, "loss": 0.0016, "step": 308050 }, { "epoch": 73.95, "learning_rate": 2.0107743303424496e-05, "loss": 0.0016, "step": 308060 }, { "epoch": 74.0, "learning_rate": 2.0104865938515655e-05, "loss": 0.0014, "step": 308070 }, { "epoch": 74.0, "learning_rate": 2.01019887276866e-05, "loss": 0.0015, "step": 308080 }, { "epoch": 74.01, "learning_rate": 2.009911167095213e-05, "loss": 0.0015, "step": 308090 }, { "epoch": 74.01, "learning_rate": 2.0096234768327105e-05, "loss": 0.0014, "step": 308100 }, { "epoch": 74.01, "learning_rate": 2.009335801982632e-05, "loss": 0.0014, "step": 308110 }, { "epoch": 74.01, "learning_rate": 2.0090481425464614e-05, "loss": 0.0014, "step": 308120 }, { "epoch": 74.02, "learning_rate": 2.0087604985256837e-05, "loss": 0.0013, "step": 308130 }, { "epoch": 74.02, "learning_rate": 2.0084728699217774e-05, "loss": 0.0013, "step": 308140 }, { "epoch": 74.02, "learning_rate": 2.0081852567362292e-05, "loss": 0.0016, "step": 308150 }, { "epoch": 74.02, "learning_rate": 2.0078976589705174e-05, "loss": 0.0014, "step": 308160 }, { "epoch": 74.02, "learning_rate": 2.0076100766261274e-05, "loss": 0.0014, "step": 308170 }, { "epoch": 74.03, "learning_rate": 2.00732250970454e-05, "loss": 0.0014, "step": 308180 }, { "epoch": 74.03, "learning_rate": 2.007034958207236e-05, "loss": 0.0034, "step": 308190 }, { "epoch": 74.03, "learning_rate": 2.0067474221357003e-05, "loss": 0.0013, "step": 308200 }, { "epoch": 74.03, "learning_rate": 2.006459901491412e-05, "loss": 0.0015, "step": 308210 }, { "epoch": 74.04, "learning_rate": 2.006172396275856e-05, "loss": 0.0015, "step": 308220 }, { "epoch": 74.04, "learning_rate": 2.0058849064905105e-05, "loss": 0.0014, "step": 308230 }, { "epoch": 74.04, "learning_rate": 2.0055974321368615e-05, "loss": 0.0018, "step": 308240 }, { "epoch": 74.04, "learning_rate": 2.0053099732163875e-05, "loss": 0.0015, "step": 308250 }, { "epoch": 74.05, "learning_rate": 2.0050225297305703e-05, "loss": 0.0015, "step": 308260 }, { "epoch": 74.05, "learning_rate": 2.0047351016808928e-05, "loss": 0.0013, "step": 308270 }, { "epoch": 74.05, "learning_rate": 2.004447689068834e-05, "loss": 0.0015, "step": 308280 }, { "epoch": 74.05, "learning_rate": 2.004160291895879e-05, "loss": 0.0016, "step": 308290 }, { "epoch": 74.05, "learning_rate": 2.003872910163505e-05, "loss": 0.0019, "step": 308300 }, { "epoch": 74.06, "learning_rate": 2.003585543873197e-05, "loss": 0.0014, "step": 308310 }, { "epoch": 74.06, "learning_rate": 2.003298193026434e-05, "loss": 0.0014, "step": 308320 }, { "epoch": 74.06, "learning_rate": 2.0030108576246955e-05, "loss": 0.0016, "step": 308330 }, { "epoch": 74.06, "learning_rate": 2.002723537669466e-05, "loss": 0.0013, "step": 308340 }, { "epoch": 74.07, "learning_rate": 2.0024362331622222e-05, "loss": 0.0023, "step": 308350 }, { "epoch": 74.07, "learning_rate": 2.002148944104449e-05, "loss": 0.0029, "step": 308360 }, { "epoch": 74.07, "learning_rate": 2.0018616704976234e-05, "loss": 0.0013, "step": 308370 }, { "epoch": 74.07, "learning_rate": 2.0015744123432297e-05, "loss": 0.0015, "step": 308380 }, { "epoch": 74.07, "learning_rate": 2.001287169642745e-05, "loss": 0.0015, "step": 308390 }, { "epoch": 74.08, "learning_rate": 2.0009999423976528e-05, "loss": 0.0015, "step": 308400 }, { "epoch": 74.08, "learning_rate": 2.00071273060943e-05, "loss": 0.0014, "step": 308410 }, { "epoch": 74.08, "learning_rate": 2.000425534279559e-05, "loss": 0.0017, "step": 308420 }, { "epoch": 74.08, "learning_rate": 2.000138353409522e-05, "loss": 0.0013, "step": 308430 }, { "epoch": 74.09, "learning_rate": 1.999851188000795e-05, "loss": 0.0015, "step": 308440 }, { "epoch": 74.09, "learning_rate": 1.9995640380548615e-05, "loss": 0.0015, "step": 308450 }, { "epoch": 74.09, "learning_rate": 1.9992769035732e-05, "loss": 0.0013, "step": 308460 }, { "epoch": 74.09, "learning_rate": 1.998989784557289e-05, "loss": 0.0016, "step": 308470 }, { "epoch": 74.1, "learning_rate": 1.9987026810086117e-05, "loss": 0.0015, "step": 308480 }, { "epoch": 74.1, "learning_rate": 1.998415592928644e-05, "loss": 0.0014, "step": 308490 }, { "epoch": 74.1, "learning_rate": 1.9981285203188686e-05, "loss": 0.0014, "step": 308500 }, { "epoch": 74.1, "learning_rate": 1.997841463180763e-05, "loss": 0.0015, "step": 308510 }, { "epoch": 74.1, "learning_rate": 1.9975544215158087e-05, "loss": 0.0015, "step": 308520 }, { "epoch": 74.11, "learning_rate": 1.9972673953254828e-05, "loss": 0.0015, "step": 308530 }, { "epoch": 74.11, "learning_rate": 1.996980384611267e-05, "loss": 0.0014, "step": 308540 }, { "epoch": 74.11, "learning_rate": 1.9966933893746398e-05, "loss": 0.0013, "step": 308550 }, { "epoch": 74.11, "learning_rate": 1.996406409617078e-05, "loss": 0.0013, "step": 308560 }, { "epoch": 74.12, "learning_rate": 1.9961194453400645e-05, "loss": 0.0015, "step": 308570 }, { "epoch": 74.12, "learning_rate": 1.995832496545075e-05, "loss": 0.0015, "step": 308580 }, { "epoch": 74.12, "learning_rate": 1.9955455632335912e-05, "loss": 0.0015, "step": 308590 }, { "epoch": 74.12, "learning_rate": 1.9952586454070895e-05, "loss": 0.0015, "step": 308600 }, { "epoch": 74.13, "learning_rate": 1.994971743067051e-05, "loss": 0.0015, "step": 308610 }, { "epoch": 74.13, "learning_rate": 1.9946848562149538e-05, "loss": 0.0014, "step": 308620 }, { "epoch": 74.13, "learning_rate": 1.9943979848522736e-05, "loss": 0.0014, "step": 308630 }, { "epoch": 74.13, "learning_rate": 1.9941111289804938e-05, "loss": 0.0015, "step": 308640 }, { "epoch": 74.13, "learning_rate": 1.9938242886010883e-05, "loss": 0.0013, "step": 308650 }, { "epoch": 74.14, "learning_rate": 1.993537463715539e-05, "loss": 0.0013, "step": 308660 }, { "epoch": 74.14, "learning_rate": 1.993250654325321e-05, "loss": 0.0014, "step": 308670 }, { "epoch": 74.14, "learning_rate": 1.9929638604319167e-05, "loss": 0.0014, "step": 308680 }, { "epoch": 74.14, "learning_rate": 1.9926770820367996e-05, "loss": 0.0014, "step": 308690 }, { "epoch": 74.15, "learning_rate": 1.9923903191414517e-05, "loss": 0.0014, "step": 308700 }, { "epoch": 74.15, "learning_rate": 1.9921035717473475e-05, "loss": 0.0015, "step": 308710 }, { "epoch": 74.15, "learning_rate": 1.991816839855968e-05, "loss": 0.0014, "step": 308720 }, { "epoch": 74.15, "learning_rate": 1.9915301234687885e-05, "loss": 0.0013, "step": 308730 }, { "epoch": 74.15, "learning_rate": 1.991243422587287e-05, "loss": 0.0015, "step": 308740 }, { "epoch": 74.16, "learning_rate": 1.990956737212945e-05, "loss": 0.0013, "step": 308750 }, { "epoch": 74.16, "learning_rate": 1.9906700673472366e-05, "loss": 0.0014, "step": 308760 }, { "epoch": 74.16, "learning_rate": 1.9903834129916376e-05, "loss": 0.0014, "step": 308770 }, { "epoch": 74.16, "learning_rate": 1.9900967741476302e-05, "loss": 0.0013, "step": 308780 }, { "epoch": 74.17, "learning_rate": 1.989810150816687e-05, "loss": 0.0014, "step": 308790 }, { "epoch": 74.17, "learning_rate": 1.9895235430002894e-05, "loss": 0.0013, "step": 308800 }, { "epoch": 74.17, "learning_rate": 1.989236950699911e-05, "loss": 0.0013, "step": 308810 }, { "epoch": 74.17, "learning_rate": 1.9889503739170316e-05, "loss": 0.0052, "step": 308820 }, { "epoch": 74.18, "learning_rate": 1.9886638126531277e-05, "loss": 0.0018, "step": 308830 }, { "epoch": 74.18, "learning_rate": 1.988377266909674e-05, "loss": 0.0019, "step": 308840 }, { "epoch": 74.18, "learning_rate": 1.98809073668815e-05, "loss": 0.0014, "step": 308850 }, { "epoch": 74.18, "learning_rate": 1.9878042219900307e-05, "loss": 0.0018, "step": 308860 }, { "epoch": 74.18, "learning_rate": 1.987517722816795e-05, "loss": 0.0115, "step": 308870 }, { "epoch": 74.19, "learning_rate": 1.9872312391699167e-05, "loss": 0.0015, "step": 308880 }, { "epoch": 74.19, "learning_rate": 1.9869447710508748e-05, "loss": 0.0015, "step": 308890 }, { "epoch": 74.19, "learning_rate": 1.9866583184611455e-05, "loss": 0.0016, "step": 308900 }, { "epoch": 74.19, "learning_rate": 1.986371881402202e-05, "loss": 0.0018, "step": 308910 }, { "epoch": 74.2, "learning_rate": 1.9860854598755253e-05, "loss": 0.0014, "step": 308920 }, { "epoch": 74.2, "learning_rate": 1.9857990538825872e-05, "loss": 0.0015, "step": 308930 }, { "epoch": 74.2, "learning_rate": 1.9855126634248676e-05, "loss": 0.0014, "step": 308940 }, { "epoch": 74.2, "learning_rate": 1.9852262885038396e-05, "loss": 0.0015, "step": 308950 }, { "epoch": 74.21, "learning_rate": 1.9849399291209826e-05, "loss": 0.0015, "step": 308960 }, { "epoch": 74.21, "learning_rate": 1.9846535852777697e-05, "loss": 0.0021, "step": 308970 }, { "epoch": 74.21, "learning_rate": 1.984367256975676e-05, "loss": 0.0014, "step": 308980 }, { "epoch": 74.21, "learning_rate": 1.98408094421618e-05, "loss": 0.0013, "step": 308990 }, { "epoch": 74.21, "learning_rate": 1.9837946470007552e-05, "loss": 0.0013, "step": 309000 }, { "epoch": 74.22, "learning_rate": 1.9835083653308773e-05, "loss": 0.0016, "step": 309010 }, { "epoch": 74.22, "learning_rate": 1.9832220992080242e-05, "loss": 0.0015, "step": 309020 }, { "epoch": 74.22, "learning_rate": 1.982935848633668e-05, "loss": 0.0015, "step": 309030 }, { "epoch": 74.22, "learning_rate": 1.9826496136092875e-05, "loss": 0.0013, "step": 309040 }, { "epoch": 74.23, "learning_rate": 1.982363394136354e-05, "loss": 0.0013, "step": 309050 }, { "epoch": 74.23, "learning_rate": 1.982077190216347e-05, "loss": 0.0015, "step": 309060 }, { "epoch": 74.23, "learning_rate": 1.9817910018507375e-05, "loss": 0.0014, "step": 309070 }, { "epoch": 74.23, "learning_rate": 1.9815048290410044e-05, "loss": 0.0016, "step": 309080 }, { "epoch": 74.23, "learning_rate": 1.9812186717886184e-05, "loss": 0.0014, "step": 309090 }, { "epoch": 74.24, "learning_rate": 1.9809325300950588e-05, "loss": 0.0014, "step": 309100 }, { "epoch": 74.24, "learning_rate": 1.9806464039617976e-05, "loss": 0.0014, "step": 309110 }, { "epoch": 74.24, "learning_rate": 1.9803602933903088e-05, "loss": 0.0014, "step": 309120 }, { "epoch": 74.24, "learning_rate": 1.9800741983820698e-05, "loss": 0.002, "step": 309130 }, { "epoch": 74.25, "learning_rate": 1.979788118938552e-05, "loss": 0.0014, "step": 309140 }, { "epoch": 74.25, "learning_rate": 1.979502055061233e-05, "loss": 0.0013, "step": 309150 }, { "epoch": 74.25, "learning_rate": 1.979216006751584e-05, "loss": 0.0016, "step": 309160 }, { "epoch": 74.25, "learning_rate": 1.9789299740110834e-05, "loss": 0.0015, "step": 309170 }, { "epoch": 74.26, "learning_rate": 1.9786439568412018e-05, "loss": 0.0019, "step": 309180 }, { "epoch": 74.26, "learning_rate": 1.9783579552434133e-05, "loss": 0.0015, "step": 309190 }, { "epoch": 74.26, "learning_rate": 1.978071969219195e-05, "loss": 0.0016, "step": 309200 }, { "epoch": 74.26, "learning_rate": 1.9777859987700177e-05, "loss": 0.0015, "step": 309210 }, { "epoch": 74.26, "learning_rate": 1.9775000438973578e-05, "loss": 0.0014, "step": 309220 }, { "epoch": 74.27, "learning_rate": 1.977214104602686e-05, "loss": 0.0013, "step": 309230 }, { "epoch": 74.27, "learning_rate": 1.9769281808874803e-05, "loss": 0.0014, "step": 309240 }, { "epoch": 74.27, "learning_rate": 1.9766422727532114e-05, "loss": 0.0013, "step": 309250 }, { "epoch": 74.27, "learning_rate": 1.9763563802013523e-05, "loss": 0.0016, "step": 309260 }, { "epoch": 74.28, "learning_rate": 1.976070503233379e-05, "loss": 0.0013, "step": 309270 }, { "epoch": 74.28, "learning_rate": 1.9757846418507624e-05, "loss": 0.0013, "step": 309280 }, { "epoch": 74.28, "learning_rate": 1.975498796054978e-05, "loss": 0.0013, "step": 309290 }, { "epoch": 74.28, "learning_rate": 1.9752129658474973e-05, "loss": 0.0013, "step": 309300 }, { "epoch": 74.29, "learning_rate": 1.9749271512297935e-05, "loss": 0.0015, "step": 309310 }, { "epoch": 74.29, "learning_rate": 1.9746413522033426e-05, "loss": 0.0014, "step": 309320 }, { "epoch": 74.29, "learning_rate": 1.9743555687696135e-05, "loss": 0.0019, "step": 309330 }, { "epoch": 74.29, "learning_rate": 1.974069800930083e-05, "loss": 0.0016, "step": 309340 }, { "epoch": 74.29, "learning_rate": 1.9737840486862197e-05, "loss": 0.0014, "step": 309350 }, { "epoch": 74.3, "learning_rate": 1.9734983120395014e-05, "loss": 0.0014, "step": 309360 }, { "epoch": 74.3, "learning_rate": 1.9732125909913958e-05, "loss": 0.0016, "step": 309370 }, { "epoch": 74.3, "learning_rate": 1.9729268855433796e-05, "loss": 0.0014, "step": 309380 }, { "epoch": 74.3, "learning_rate": 1.9726411956969216e-05, "loss": 0.0013, "step": 309390 }, { "epoch": 74.31, "learning_rate": 1.9723555214534983e-05, "loss": 0.0014, "step": 309400 }, { "epoch": 74.31, "learning_rate": 1.97206986281458e-05, "loss": 0.0015, "step": 309410 }, { "epoch": 74.31, "learning_rate": 1.9717842197816367e-05, "loss": 0.0013, "step": 309420 }, { "epoch": 74.31, "learning_rate": 1.971498592356145e-05, "loss": 0.0013, "step": 309430 }, { "epoch": 74.31, "learning_rate": 1.9712129805395728e-05, "loss": 0.0014, "step": 309440 }, { "epoch": 74.32, "learning_rate": 1.9709273843333965e-05, "loss": 0.0039, "step": 309450 }, { "epoch": 74.32, "learning_rate": 1.9706418037390834e-05, "loss": 0.0014, "step": 309460 }, { "epoch": 74.32, "learning_rate": 1.97035623875811e-05, "loss": 0.0014, "step": 309470 }, { "epoch": 74.32, "learning_rate": 1.9700706893919456e-05, "loss": 0.0013, "step": 309480 }, { "epoch": 74.33, "learning_rate": 1.9697851556420604e-05, "loss": 0.0014, "step": 309490 }, { "epoch": 74.33, "learning_rate": 1.96949963750993e-05, "loss": 0.0015, "step": 309500 }, { "epoch": 74.33, "learning_rate": 1.9692141349970215e-05, "loss": 0.0013, "step": 309510 }, { "epoch": 74.33, "learning_rate": 1.9689286481048106e-05, "loss": 0.0014, "step": 309520 }, { "epoch": 74.34, "learning_rate": 1.9686431768347652e-05, "loss": 0.0173, "step": 309530 }, { "epoch": 74.34, "learning_rate": 1.9683577211883604e-05, "loss": 0.0015, "step": 309540 }, { "epoch": 74.34, "learning_rate": 1.9680722811670643e-05, "loss": 0.0051, "step": 309550 }, { "epoch": 74.34, "learning_rate": 1.967786856772348e-05, "loss": 0.0015, "step": 309560 }, { "epoch": 74.34, "learning_rate": 1.9675014480056847e-05, "loss": 0.0016, "step": 309570 }, { "epoch": 74.35, "learning_rate": 1.967216054868543e-05, "loss": 0.0014, "step": 309580 }, { "epoch": 74.35, "learning_rate": 1.9669306773623967e-05, "loss": 0.0015, "step": 309590 }, { "epoch": 74.35, "learning_rate": 1.9666453154887134e-05, "loss": 0.0013, "step": 309600 }, { "epoch": 74.35, "learning_rate": 1.966359969248967e-05, "loss": 0.0013, "step": 309610 }, { "epoch": 74.36, "learning_rate": 1.9660746386446248e-05, "loss": 0.0014, "step": 309620 }, { "epoch": 74.36, "learning_rate": 1.9657893236771595e-05, "loss": 0.0086, "step": 309630 }, { "epoch": 74.36, "learning_rate": 1.9655040243480437e-05, "loss": 0.0015, "step": 309640 }, { "epoch": 74.36, "learning_rate": 1.965218740658743e-05, "loss": 0.0015, "step": 309650 }, { "epoch": 74.37, "learning_rate": 1.9649334726107327e-05, "loss": 0.0015, "step": 309660 }, { "epoch": 74.37, "learning_rate": 1.9646482202054783e-05, "loss": 0.0015, "step": 309670 }, { "epoch": 74.37, "learning_rate": 1.9643629834444542e-05, "loss": 0.0015, "step": 309680 }, { "epoch": 74.37, "learning_rate": 1.964077762329129e-05, "loss": 0.0014, "step": 309690 }, { "epoch": 74.37, "learning_rate": 1.96379255686097e-05, "loss": 0.0013, "step": 309700 }, { "epoch": 74.38, "learning_rate": 1.9635073670414517e-05, "loss": 0.0016, "step": 309710 }, { "epoch": 74.38, "learning_rate": 1.96322219287204e-05, "loss": 0.0013, "step": 309720 }, { "epoch": 74.38, "learning_rate": 1.9629370343542086e-05, "loss": 0.0013, "step": 309730 }, { "epoch": 74.38, "learning_rate": 1.9626518914894227e-05, "loss": 0.0014, "step": 309740 }, { "epoch": 74.39, "learning_rate": 1.9623667642791565e-05, "loss": 0.0016, "step": 309750 }, { "epoch": 74.39, "learning_rate": 1.9620816527248774e-05, "loss": 0.0013, "step": 309760 }, { "epoch": 74.39, "learning_rate": 1.9617965568280532e-05, "loss": 0.0012, "step": 309770 }, { "epoch": 74.39, "learning_rate": 1.9615114765901566e-05, "loss": 0.0014, "step": 309780 }, { "epoch": 74.39, "learning_rate": 1.9612264120126535e-05, "loss": 0.0016, "step": 309790 }, { "epoch": 74.4, "learning_rate": 1.9609413630970165e-05, "loss": 0.0015, "step": 309800 }, { "epoch": 74.4, "learning_rate": 1.960656329844711e-05, "loss": 0.0017, "step": 309810 }, { "epoch": 74.4, "learning_rate": 1.9603713122572104e-05, "loss": 0.0013, "step": 309820 }, { "epoch": 74.4, "learning_rate": 1.960086310335981e-05, "loss": 0.0014, "step": 309830 }, { "epoch": 74.41, "learning_rate": 1.9598013240824914e-05, "loss": 0.0013, "step": 309840 }, { "epoch": 74.41, "learning_rate": 1.9595163534982124e-05, "loss": 0.0015, "step": 309850 }, { "epoch": 74.41, "learning_rate": 1.9592313985846093e-05, "loss": 0.0013, "step": 309860 }, { "epoch": 74.41, "learning_rate": 1.9589464593431555e-05, "loss": 0.0014, "step": 309870 }, { "epoch": 74.42, "learning_rate": 1.958661535775315e-05, "loss": 0.0015, "step": 309880 }, { "epoch": 74.42, "learning_rate": 1.9583766278825598e-05, "loss": 0.0015, "step": 309890 }, { "epoch": 74.42, "learning_rate": 1.958091735666356e-05, "loss": 0.0015, "step": 309900 }, { "epoch": 74.42, "learning_rate": 1.957806859128174e-05, "loss": 0.0014, "step": 309910 }, { "epoch": 74.42, "learning_rate": 1.9575219982694788e-05, "loss": 0.0013, "step": 309920 }, { "epoch": 74.43, "learning_rate": 1.9572371530917425e-05, "loss": 0.0014, "step": 309930 }, { "epoch": 74.43, "learning_rate": 1.95695232359643e-05, "loss": 0.0014, "step": 309940 }, { "epoch": 74.43, "learning_rate": 1.9566675097850105e-05, "loss": 0.0015, "step": 309950 }, { "epoch": 74.43, "learning_rate": 1.956382711658954e-05, "loss": 0.0014, "step": 309960 }, { "epoch": 74.44, "learning_rate": 1.9560979292197263e-05, "loss": 0.0012, "step": 309970 }, { "epoch": 74.44, "learning_rate": 1.9558131624687937e-05, "loss": 0.0014, "step": 309980 }, { "epoch": 74.44, "learning_rate": 1.9555284114076268e-05, "loss": 0.0014, "step": 309990 }, { "epoch": 74.44, "learning_rate": 1.9552436760376907e-05, "loss": 0.0015, "step": 310000 }, { "epoch": 74.45, "learning_rate": 1.9549589563604552e-05, "loss": 0.0014, "step": 310010 }, { "epoch": 74.45, "learning_rate": 1.954674252377386e-05, "loss": 0.0019, "step": 310020 }, { "epoch": 74.45, "learning_rate": 1.9543895640899525e-05, "loss": 0.0013, "step": 310030 }, { "epoch": 74.45, "learning_rate": 1.95410489149962e-05, "loss": 0.0014, "step": 310040 }, { "epoch": 74.45, "learning_rate": 1.953820234607855e-05, "loss": 0.0016, "step": 310050 }, { "epoch": 74.46, "learning_rate": 1.953535593416128e-05, "loss": 0.0014, "step": 310060 }, { "epoch": 74.46, "learning_rate": 1.953250967925902e-05, "loss": 0.0015, "step": 310070 }, { "epoch": 74.46, "learning_rate": 1.9529663581386477e-05, "loss": 0.0014, "step": 310080 }, { "epoch": 74.46, "learning_rate": 1.9526817640558286e-05, "loss": 0.0014, "step": 310090 }, { "epoch": 74.47, "learning_rate": 1.9523971856789146e-05, "loss": 0.0015, "step": 310100 }, { "epoch": 74.47, "learning_rate": 1.95211262300937e-05, "loss": 0.0015, "step": 310110 }, { "epoch": 74.47, "learning_rate": 1.9518280760486635e-05, "loss": 0.0015, "step": 310120 }, { "epoch": 74.47, "learning_rate": 1.9515435447982612e-05, "loss": 0.0014, "step": 310130 }, { "epoch": 74.47, "learning_rate": 1.9512590292596266e-05, "loss": 0.0014, "step": 310140 }, { "epoch": 74.48, "learning_rate": 1.9509745294342303e-05, "loss": 0.0014, "step": 310150 }, { "epoch": 74.48, "learning_rate": 1.950690045323535e-05, "loss": 0.0016, "step": 310160 }, { "epoch": 74.48, "learning_rate": 1.9504055769290104e-05, "loss": 0.0014, "step": 310170 }, { "epoch": 74.48, "learning_rate": 1.9501211242521195e-05, "loss": 0.002, "step": 310180 }, { "epoch": 74.49, "learning_rate": 1.9498366872943312e-05, "loss": 0.0015, "step": 310190 }, { "epoch": 74.49, "learning_rate": 1.9495522660571085e-05, "loss": 0.0014, "step": 310200 }, { "epoch": 74.49, "learning_rate": 1.949267860541921e-05, "loss": 0.0016, "step": 310210 }, { "epoch": 74.49, "learning_rate": 1.94898347075023e-05, "loss": 0.0013, "step": 310220 }, { "epoch": 74.5, "learning_rate": 1.9486990966835062e-05, "loss": 0.0013, "step": 310230 }, { "epoch": 74.5, "learning_rate": 1.9484147383432104e-05, "loss": 0.0019, "step": 310240 }, { "epoch": 74.5, "learning_rate": 1.948130395730811e-05, "loss": 0.0019, "step": 310250 }, { "epoch": 74.5, "learning_rate": 1.9478460688477745e-05, "loss": 0.0015, "step": 310260 }, { "epoch": 74.5, "learning_rate": 1.9475617576955652e-05, "loss": 0.0015, "step": 310270 }, { "epoch": 74.51, "learning_rate": 1.947277462275646e-05, "loss": 0.0015, "step": 310280 }, { "epoch": 74.51, "learning_rate": 1.946993182589486e-05, "loss": 0.0013, "step": 310290 }, { "epoch": 74.51, "learning_rate": 1.9467089186385472e-05, "loss": 0.0015, "step": 310300 }, { "epoch": 74.51, "learning_rate": 1.9464246704242977e-05, "loss": 0.0014, "step": 310310 }, { "epoch": 74.52, "learning_rate": 1.9461404379481996e-05, "loss": 0.0015, "step": 310320 }, { "epoch": 74.52, "learning_rate": 1.9458562212117202e-05, "loss": 0.0048, "step": 310330 }, { "epoch": 74.52, "learning_rate": 1.9455720202163243e-05, "loss": 0.0015, "step": 310340 }, { "epoch": 74.52, "learning_rate": 1.9452878349634734e-05, "loss": 0.0016, "step": 310350 }, { "epoch": 74.53, "learning_rate": 1.9450036654546367e-05, "loss": 0.0013, "step": 310360 }, { "epoch": 74.53, "learning_rate": 1.944719511691274e-05, "loss": 0.0013, "step": 310370 }, { "epoch": 74.53, "learning_rate": 1.944435373674855e-05, "loss": 0.0015, "step": 310380 }, { "epoch": 74.53, "learning_rate": 1.94415125140684e-05, "loss": 0.0033, "step": 310390 }, { "epoch": 74.53, "learning_rate": 1.9438671448886965e-05, "loss": 0.0015, "step": 310400 }, { "epoch": 74.54, "learning_rate": 1.9435830541218867e-05, "loss": 0.0016, "step": 310410 }, { "epoch": 74.54, "learning_rate": 1.943298979107875e-05, "loss": 0.0037, "step": 310420 }, { "epoch": 74.54, "learning_rate": 1.9430149198481263e-05, "loss": 0.0019, "step": 310430 }, { "epoch": 74.54, "learning_rate": 1.9427308763441032e-05, "loss": 0.0016, "step": 310440 }, { "epoch": 74.55, "learning_rate": 1.9424468485972725e-05, "loss": 0.0016, "step": 310450 }, { "epoch": 74.55, "learning_rate": 1.9421628366090937e-05, "loss": 0.0016, "step": 310460 }, { "epoch": 74.55, "learning_rate": 1.9418788403810362e-05, "loss": 0.0017, "step": 310470 }, { "epoch": 74.55, "learning_rate": 1.94159485991456e-05, "loss": 0.0016, "step": 310480 }, { "epoch": 74.55, "learning_rate": 1.9413108952111275e-05, "loss": 0.0014, "step": 310490 }, { "epoch": 74.56, "learning_rate": 1.9410269462722062e-05, "loss": 0.0021, "step": 310500 }, { "epoch": 74.56, "learning_rate": 1.940743013099256e-05, "loss": 0.0018, "step": 310510 }, { "epoch": 74.56, "learning_rate": 1.9404590956937417e-05, "loss": 0.0026, "step": 310520 }, { "epoch": 74.56, "learning_rate": 1.9401751940571287e-05, "loss": 0.0017, "step": 310530 }, { "epoch": 74.57, "learning_rate": 1.939891308190877e-05, "loss": 0.0015, "step": 310540 }, { "epoch": 74.57, "learning_rate": 1.9396074380964524e-05, "loss": 0.0016, "step": 310550 }, { "epoch": 74.57, "learning_rate": 1.9393235837753147e-05, "loss": 0.0015, "step": 310560 }, { "epoch": 74.57, "learning_rate": 1.9390397452289304e-05, "loss": 0.0018, "step": 310570 }, { "epoch": 74.58, "learning_rate": 1.93875592245876e-05, "loss": 0.0015, "step": 310580 }, { "epoch": 74.58, "learning_rate": 1.938472115466268e-05, "loss": 0.0014, "step": 310590 }, { "epoch": 74.58, "learning_rate": 1.9381883242529146e-05, "loss": 0.0015, "step": 310600 }, { "epoch": 74.58, "learning_rate": 1.9379045488201664e-05, "loss": 0.0014, "step": 310610 }, { "epoch": 74.58, "learning_rate": 1.9376207891694838e-05, "loss": 0.0015, "step": 310620 }, { "epoch": 74.59, "learning_rate": 1.937337045302327e-05, "loss": 0.0015, "step": 310630 }, { "epoch": 74.59, "learning_rate": 1.9370533172201626e-05, "loss": 0.0015, "step": 310640 }, { "epoch": 74.59, "learning_rate": 1.9367696049244493e-05, "loss": 0.0014, "step": 310650 }, { "epoch": 74.59, "learning_rate": 1.9364859084166533e-05, "loss": 0.0016, "step": 310660 }, { "epoch": 74.6, "learning_rate": 1.9362022276982324e-05, "loss": 0.0013, "step": 310670 }, { "epoch": 74.6, "learning_rate": 1.9359185627706523e-05, "loss": 0.0025, "step": 310680 }, { "epoch": 74.6, "learning_rate": 1.9356349136353735e-05, "loss": 0.0014, "step": 310690 }, { "epoch": 74.6, "learning_rate": 1.9353512802938567e-05, "loss": 0.0014, "step": 310700 }, { "epoch": 74.61, "learning_rate": 1.9350676627475667e-05, "loss": 0.0014, "step": 310710 }, { "epoch": 74.61, "learning_rate": 1.9347840609979617e-05, "loss": 0.0015, "step": 310720 }, { "epoch": 74.61, "learning_rate": 1.934500475046507e-05, "loss": 0.0015, "step": 310730 }, { "epoch": 74.61, "learning_rate": 1.9342169048946606e-05, "loss": 0.0013, "step": 310740 }, { "epoch": 74.61, "learning_rate": 1.9339333505438878e-05, "loss": 0.0015, "step": 310750 }, { "epoch": 74.62, "learning_rate": 1.9336498119956482e-05, "loss": 0.0013, "step": 310760 }, { "epoch": 74.62, "learning_rate": 1.933366289251401e-05, "loss": 0.0014, "step": 310770 }, { "epoch": 74.62, "learning_rate": 1.933082782312612e-05, "loss": 0.0016, "step": 310780 }, { "epoch": 74.62, "learning_rate": 1.9327992911807373e-05, "loss": 0.0018, "step": 310790 }, { "epoch": 74.63, "learning_rate": 1.9325158158572433e-05, "loss": 0.0013, "step": 310800 }, { "epoch": 74.63, "learning_rate": 1.9322323563435863e-05, "loss": 0.0015, "step": 310810 }, { "epoch": 74.63, "learning_rate": 1.9319489126412295e-05, "loss": 0.0014, "step": 310820 }, { "epoch": 74.63, "learning_rate": 1.931665484751635e-05, "loss": 0.0012, "step": 310830 }, { "epoch": 74.63, "learning_rate": 1.931382072676261e-05, "loss": 0.0015, "step": 310840 }, { "epoch": 74.64, "learning_rate": 1.9310986764165705e-05, "loss": 0.0016, "step": 310850 }, { "epoch": 74.64, "learning_rate": 1.9308152959740223e-05, "loss": 0.0014, "step": 310860 }, { "epoch": 74.64, "learning_rate": 1.9305319313500787e-05, "loss": 0.0015, "step": 310870 }, { "epoch": 74.64, "learning_rate": 1.930248582546198e-05, "loss": 0.0014, "step": 310880 }, { "epoch": 74.65, "learning_rate": 1.9299652495638432e-05, "loss": 0.0014, "step": 310890 }, { "epoch": 74.65, "learning_rate": 1.929681932404473e-05, "loss": 0.0015, "step": 310900 }, { "epoch": 74.65, "learning_rate": 1.929398631069546e-05, "loss": 0.002, "step": 310910 }, { "epoch": 74.65, "learning_rate": 1.9291153455605264e-05, "loss": 0.0014, "step": 310920 }, { "epoch": 74.66, "learning_rate": 1.9288320758788697e-05, "loss": 0.0016, "step": 310930 }, { "epoch": 74.66, "learning_rate": 1.9285488220260402e-05, "loss": 0.0015, "step": 310940 }, { "epoch": 74.66, "learning_rate": 1.9282655840034942e-05, "loss": 0.0017, "step": 310950 }, { "epoch": 74.66, "learning_rate": 1.927982361812694e-05, "loss": 0.0021, "step": 310960 }, { "epoch": 74.66, "learning_rate": 1.9276991554550977e-05, "loss": 0.0013, "step": 310970 }, { "epoch": 74.67, "learning_rate": 1.9274159649321665e-05, "loss": 0.0015, "step": 310980 }, { "epoch": 74.67, "learning_rate": 1.9271327902453595e-05, "loss": 0.0021, "step": 310990 }, { "epoch": 74.67, "learning_rate": 1.9268496313961343e-05, "loss": 0.0014, "step": 311000 }, { "epoch": 74.67, "learning_rate": 1.926566488385953e-05, "loss": 0.0015, "step": 311010 }, { "epoch": 74.68, "learning_rate": 1.9262833612162723e-05, "loss": 0.0016, "step": 311020 }, { "epoch": 74.68, "learning_rate": 1.9260002498885544e-05, "loss": 0.0013, "step": 311030 }, { "epoch": 74.68, "learning_rate": 1.925717154404255e-05, "loss": 0.0016, "step": 311040 }, { "epoch": 74.68, "learning_rate": 1.9254340747648375e-05, "loss": 0.0015, "step": 311050 }, { "epoch": 74.69, "learning_rate": 1.925151010971758e-05, "loss": 0.0016, "step": 311060 }, { "epoch": 74.69, "learning_rate": 1.9248679630264738e-05, "loss": 0.0017, "step": 311070 }, { "epoch": 74.69, "learning_rate": 1.924584930930448e-05, "loss": 0.0015, "step": 311080 }, { "epoch": 74.69, "learning_rate": 1.9243019146851353e-05, "loss": 0.0015, "step": 311090 }, { "epoch": 74.69, "learning_rate": 1.9240189142919983e-05, "loss": 0.0014, "step": 311100 }, { "epoch": 74.7, "learning_rate": 1.9237359297524915e-05, "loss": 0.0016, "step": 311110 }, { "epoch": 74.7, "learning_rate": 1.9234529610680773e-05, "loss": 0.0014, "step": 311120 }, { "epoch": 74.7, "learning_rate": 1.9231700082402104e-05, "loss": 0.0013, "step": 311130 }, { "epoch": 74.7, "learning_rate": 1.9228870712703513e-05, "loss": 0.0012, "step": 311140 }, { "epoch": 74.71, "learning_rate": 1.9226041501599597e-05, "loss": 0.0016, "step": 311150 }, { "epoch": 74.71, "learning_rate": 1.9223212449104894e-05, "loss": 0.0014, "step": 311160 }, { "epoch": 74.71, "learning_rate": 1.922038355523404e-05, "loss": 0.002, "step": 311170 }, { "epoch": 74.71, "learning_rate": 1.921755482000156e-05, "loss": 0.0014, "step": 311180 }, { "epoch": 74.71, "learning_rate": 1.9214726243422082e-05, "loss": 0.0017, "step": 311190 }, { "epoch": 74.72, "learning_rate": 1.9211897825510162e-05, "loss": 0.0015, "step": 311200 }, { "epoch": 74.72, "learning_rate": 1.9209069566280357e-05, "loss": 0.0013, "step": 311210 }, { "epoch": 74.72, "learning_rate": 1.9206241465747288e-05, "loss": 0.002, "step": 311220 }, { "epoch": 74.72, "learning_rate": 1.920341352392549e-05, "loss": 0.0014, "step": 311230 }, { "epoch": 74.73, "learning_rate": 1.9200585740829567e-05, "loss": 0.0042, "step": 311240 }, { "epoch": 74.73, "learning_rate": 1.9197758116474067e-05, "loss": 0.0014, "step": 311250 }, { "epoch": 74.73, "learning_rate": 1.9194930650873605e-05, "loss": 0.0038, "step": 311260 }, { "epoch": 74.73, "learning_rate": 1.9192103344042723e-05, "loss": 0.0014, "step": 311270 }, { "epoch": 74.74, "learning_rate": 1.9189276195995974e-05, "loss": 0.0016, "step": 311280 }, { "epoch": 74.74, "learning_rate": 1.9186449206747976e-05, "loss": 0.0014, "step": 311290 }, { "epoch": 74.74, "learning_rate": 1.918362237631326e-05, "loss": 0.0021, "step": 311300 }, { "epoch": 74.74, "learning_rate": 1.918079570470643e-05, "loss": 0.0021, "step": 311310 }, { "epoch": 74.74, "learning_rate": 1.9177969191942013e-05, "loss": 0.0012, "step": 311320 }, { "epoch": 74.75, "learning_rate": 1.9175142838034625e-05, "loss": 0.0014, "step": 311330 }, { "epoch": 74.75, "learning_rate": 1.9172316642998807e-05, "loss": 0.0013, "step": 311340 }, { "epoch": 74.75, "learning_rate": 1.9169490606849104e-05, "loss": 0.0014, "step": 311350 }, { "epoch": 74.75, "learning_rate": 1.9166664729600125e-05, "loss": 0.0014, "step": 311360 }, { "epoch": 74.76, "learning_rate": 1.91638390112664e-05, "loss": 0.0014, "step": 311370 }, { "epoch": 74.76, "learning_rate": 1.916101345186252e-05, "loss": 0.0013, "step": 311380 }, { "epoch": 74.76, "learning_rate": 1.9158188051403014e-05, "loss": 0.0013, "step": 311390 }, { "epoch": 74.76, "learning_rate": 1.9155362809902488e-05, "loss": 0.0017, "step": 311400 }, { "epoch": 74.77, "learning_rate": 1.9152537727375457e-05, "loss": 0.0013, "step": 311410 }, { "epoch": 74.77, "learning_rate": 1.9149712803836527e-05, "loss": 0.0014, "step": 311420 }, { "epoch": 74.77, "learning_rate": 1.9146888039300216e-05, "loss": 0.0014, "step": 311430 }, { "epoch": 74.77, "learning_rate": 1.9144063433781118e-05, "loss": 0.0014, "step": 311440 }, { "epoch": 74.77, "learning_rate": 1.914123898729376e-05, "loss": 0.0055, "step": 311450 }, { "epoch": 74.78, "learning_rate": 1.9138414699852707e-05, "loss": 0.0014, "step": 311460 }, { "epoch": 74.78, "learning_rate": 1.913559057147255e-05, "loss": 0.0014, "step": 311470 }, { "epoch": 74.78, "learning_rate": 1.9132766602167812e-05, "loss": 0.0014, "step": 311480 }, { "epoch": 74.78, "learning_rate": 1.9129942791953037e-05, "loss": 0.0016, "step": 311490 }, { "epoch": 74.79, "learning_rate": 1.912711914084281e-05, "loss": 0.0015, "step": 311500 }, { "epoch": 74.79, "learning_rate": 1.9124295648851655e-05, "loss": 0.002, "step": 311510 }, { "epoch": 74.79, "learning_rate": 1.9121472315994155e-05, "loss": 0.0014, "step": 311520 }, { "epoch": 74.79, "learning_rate": 1.9118649142284822e-05, "loss": 0.0013, "step": 311530 }, { "epoch": 74.79, "learning_rate": 1.9115826127738252e-05, "loss": 0.0166, "step": 311540 }, { "epoch": 74.8, "learning_rate": 1.9113003272368973e-05, "loss": 0.0011, "step": 311550 }, { "epoch": 74.8, "learning_rate": 1.911018057619151e-05, "loss": 0.0015, "step": 311560 }, { "epoch": 74.8, "learning_rate": 1.910735803922046e-05, "loss": 0.0015, "step": 311570 }, { "epoch": 74.8, "learning_rate": 1.9104535661470325e-05, "loss": 0.0012, "step": 311580 }, { "epoch": 74.81, "learning_rate": 1.910171344295569e-05, "loss": 0.0015, "step": 311590 }, { "epoch": 74.81, "learning_rate": 1.9098891383691058e-05, "loss": 0.0015, "step": 311600 }, { "epoch": 74.81, "learning_rate": 1.909606948369102e-05, "loss": 0.0016, "step": 311610 }, { "epoch": 74.81, "learning_rate": 1.90932477429701e-05, "loss": 0.0014, "step": 311620 }, { "epoch": 74.82, "learning_rate": 1.9090426161542817e-05, "loss": 0.0014, "step": 311630 }, { "epoch": 74.82, "learning_rate": 1.9087604739423758e-05, "loss": 0.0013, "step": 311640 }, { "epoch": 74.82, "learning_rate": 1.9084783476627422e-05, "loss": 0.0013, "step": 311650 }, { "epoch": 74.82, "learning_rate": 1.908196237316839e-05, "loss": 0.0015, "step": 311660 }, { "epoch": 74.82, "learning_rate": 1.9079141429061165e-05, "loss": 0.0015, "step": 311670 }, { "epoch": 74.83, "learning_rate": 1.907632064432032e-05, "loss": 0.0013, "step": 311680 }, { "epoch": 74.83, "learning_rate": 1.9073500018960378e-05, "loss": 0.0014, "step": 311690 }, { "epoch": 74.83, "learning_rate": 1.9070679552995857e-05, "loss": 0.0014, "step": 311700 }, { "epoch": 74.83, "learning_rate": 1.906785924644131e-05, "loss": 0.0015, "step": 311710 }, { "epoch": 74.84, "learning_rate": 1.9065039099311294e-05, "loss": 0.0014, "step": 311720 }, { "epoch": 74.84, "learning_rate": 1.906221911162031e-05, "loss": 0.0014, "step": 311730 }, { "epoch": 74.84, "learning_rate": 1.9059399283382922e-05, "loss": 0.0014, "step": 311740 }, { "epoch": 74.84, "learning_rate": 1.9056579614613634e-05, "loss": 0.0015, "step": 311750 }, { "epoch": 74.85, "learning_rate": 1.9053760105327006e-05, "loss": 0.0016, "step": 311760 }, { "epoch": 74.85, "learning_rate": 1.9050940755537543e-05, "loss": 0.0014, "step": 311770 }, { "epoch": 74.85, "learning_rate": 1.9048121565259806e-05, "loss": 0.0015, "step": 311780 }, { "epoch": 74.85, "learning_rate": 1.9045302534508297e-05, "loss": 0.0014, "step": 311790 }, { "epoch": 74.85, "learning_rate": 1.9042483663297572e-05, "loss": 0.0017, "step": 311800 }, { "epoch": 74.86, "learning_rate": 1.903966495164212e-05, "loss": 0.0013, "step": 311810 }, { "epoch": 74.86, "learning_rate": 1.9036846399556523e-05, "loss": 0.0015, "step": 311820 }, { "epoch": 74.86, "learning_rate": 1.9034028007055253e-05, "loss": 0.0015, "step": 311830 }, { "epoch": 74.86, "learning_rate": 1.903120977415288e-05, "loss": 0.0014, "step": 311840 }, { "epoch": 74.87, "learning_rate": 1.902839170086391e-05, "loss": 0.0013, "step": 311850 }, { "epoch": 74.87, "learning_rate": 1.9025573787202855e-05, "loss": 0.0015, "step": 311860 }, { "epoch": 74.87, "learning_rate": 1.902275603318427e-05, "loss": 0.0013, "step": 311870 }, { "epoch": 74.87, "learning_rate": 1.9019938438822638e-05, "loss": 0.0015, "step": 311880 }, { "epoch": 74.87, "learning_rate": 1.901712100413252e-05, "loss": 0.0015, "step": 311890 }, { "epoch": 74.88, "learning_rate": 1.90143037291284e-05, "loss": 0.0014, "step": 311900 }, { "epoch": 74.88, "learning_rate": 1.9011486613824842e-05, "loss": 0.0014, "step": 311910 }, { "epoch": 74.88, "learning_rate": 1.9008669658236332e-05, "loss": 0.0015, "step": 311920 }, { "epoch": 74.88, "learning_rate": 1.900585286237739e-05, "loss": 0.0013, "step": 311930 }, { "epoch": 74.89, "learning_rate": 1.900303622626255e-05, "loss": 0.0013, "step": 311940 }, { "epoch": 74.89, "learning_rate": 1.9000219749906305e-05, "loss": 0.0012, "step": 311950 }, { "epoch": 74.89, "learning_rate": 1.8997403433323208e-05, "loss": 0.0015, "step": 311960 }, { "epoch": 74.89, "learning_rate": 1.899458727652773e-05, "loss": 0.0015, "step": 311970 }, { "epoch": 74.9, "learning_rate": 1.8991771279534426e-05, "loss": 0.0012, "step": 311980 }, { "epoch": 74.9, "learning_rate": 1.8988955442357797e-05, "loss": 0.0015, "step": 311990 }, { "epoch": 74.9, "learning_rate": 1.898613976501233e-05, "loss": 0.0013, "step": 312000 }, { "epoch": 74.9, "learning_rate": 1.898332424751258e-05, "loss": 0.0014, "step": 312010 }, { "epoch": 74.9, "learning_rate": 1.898050888987301e-05, "loss": 0.0161, "step": 312020 }, { "epoch": 74.91, "learning_rate": 1.8977693692108162e-05, "loss": 0.0014, "step": 312030 }, { "epoch": 74.91, "learning_rate": 1.8974878654232558e-05, "loss": 0.0014, "step": 312040 }, { "epoch": 74.91, "learning_rate": 1.8972063776260668e-05, "loss": 0.0014, "step": 312050 }, { "epoch": 74.91, "learning_rate": 1.896924905820704e-05, "loss": 0.0013, "step": 312060 }, { "epoch": 74.92, "learning_rate": 1.8966434500086143e-05, "loss": 0.0025, "step": 312070 }, { "epoch": 74.92, "learning_rate": 1.896362010191252e-05, "loss": 0.0014, "step": 312080 }, { "epoch": 74.92, "learning_rate": 1.8960805863700648e-05, "loss": 0.0014, "step": 312090 }, { "epoch": 74.92, "learning_rate": 1.8957991785465052e-05, "loss": 0.0014, "step": 312100 }, { "epoch": 74.93, "learning_rate": 1.8955177867220207e-05, "loss": 0.0016, "step": 312110 }, { "epoch": 74.93, "learning_rate": 1.8952364108980658e-05, "loss": 0.0014, "step": 312120 }, { "epoch": 74.93, "learning_rate": 1.8949550510760876e-05, "loss": 0.0015, "step": 312130 }, { "epoch": 74.93, "learning_rate": 1.894673707257536e-05, "loss": 0.0013, "step": 312140 }, { "epoch": 74.93, "learning_rate": 1.8943923794438635e-05, "loss": 0.0015, "step": 312150 }, { "epoch": 74.94, "learning_rate": 1.894111067636517e-05, "loss": 0.0014, "step": 312160 }, { "epoch": 74.94, "learning_rate": 1.8938297718369496e-05, "loss": 0.0183, "step": 312170 }, { "epoch": 74.94, "learning_rate": 1.893548492046608e-05, "loss": 0.0012, "step": 312180 }, { "epoch": 74.94, "learning_rate": 1.893267228266945e-05, "loss": 0.0014, "step": 312190 }, { "epoch": 74.95, "learning_rate": 1.8929859804994086e-05, "loss": 0.0016, "step": 312200 }, { "epoch": 74.95, "learning_rate": 1.8927047487454473e-05, "loss": 0.0015, "step": 312210 }, { "epoch": 74.95, "learning_rate": 1.8924235330065128e-05, "loss": 0.0015, "step": 312220 }, { "epoch": 75.0, "learning_rate": 1.892142333284052e-05, "loss": 0.0015, "step": 312230 }, { "epoch": 75.0, "learning_rate": 1.891861149579517e-05, "loss": 0.0013, "step": 312240 }, { "epoch": 75.01, "learning_rate": 1.8915799818943542e-05, "loss": 0.0051, "step": 312250 }, { "epoch": 75.01, "learning_rate": 1.8912988302300154e-05, "loss": 0.0014, "step": 312260 }, { "epoch": 75.01, "learning_rate": 1.8910176945879488e-05, "loss": 0.0033, "step": 312270 }, { "epoch": 75.01, "learning_rate": 1.8907365749696016e-05, "loss": 0.0013, "step": 312280 }, { "epoch": 75.01, "learning_rate": 1.890455471376425e-05, "loss": 0.0014, "step": 312290 }, { "epoch": 75.02, "learning_rate": 1.8901743838098657e-05, "loss": 0.0013, "step": 312300 }, { "epoch": 75.02, "learning_rate": 1.8898933122713752e-05, "loss": 0.0014, "step": 312310 }, { "epoch": 75.02, "learning_rate": 1.8896122567623985e-05, "loss": 0.0015, "step": 312320 }, { "epoch": 75.02, "learning_rate": 1.8893312172843887e-05, "loss": 0.0015, "step": 312330 }, { "epoch": 75.03, "learning_rate": 1.8890501938387894e-05, "loss": 0.0013, "step": 312340 }, { "epoch": 75.03, "learning_rate": 1.888769186427052e-05, "loss": 0.0012, "step": 312350 }, { "epoch": 75.03, "learning_rate": 1.8884881950506256e-05, "loss": 0.0012, "step": 312360 }, { "epoch": 75.03, "learning_rate": 1.888207219710955e-05, "loss": 0.0013, "step": 312370 }, { "epoch": 75.04, "learning_rate": 1.8879262604094926e-05, "loss": 0.0019, "step": 312380 }, { "epoch": 75.04, "learning_rate": 1.8876453171476825e-05, "loss": 0.0013, "step": 312390 }, { "epoch": 75.04, "learning_rate": 1.887364389926976e-05, "loss": 0.0014, "step": 312400 }, { "epoch": 75.04, "learning_rate": 1.88708347874882e-05, "loss": 0.0014, "step": 312410 }, { "epoch": 75.04, "learning_rate": 1.8868025836146597e-05, "loss": 0.0015, "step": 312420 }, { "epoch": 75.05, "learning_rate": 1.8865217045259464e-05, "loss": 0.0014, "step": 312430 }, { "epoch": 75.05, "learning_rate": 1.8862408414841243e-05, "loss": 0.0014, "step": 312440 }, { "epoch": 75.05, "learning_rate": 1.8859599944906454e-05, "loss": 0.0013, "step": 312450 }, { "epoch": 75.05, "learning_rate": 1.8856791635469522e-05, "loss": 0.0014, "step": 312460 }, { "epoch": 75.06, "learning_rate": 1.8853983486544967e-05, "loss": 0.0015, "step": 312470 }, { "epoch": 75.06, "learning_rate": 1.8851175498147244e-05, "loss": 0.0014, "step": 312480 }, { "epoch": 75.06, "learning_rate": 1.8848367670290806e-05, "loss": 0.0013, "step": 312490 }, { "epoch": 75.06, "learning_rate": 1.8845560002990154e-05, "loss": 0.0015, "step": 312500 }, { "epoch": 75.07, "learning_rate": 1.884275249625973e-05, "loss": 0.0014, "step": 312510 }, { "epoch": 75.07, "learning_rate": 1.883994515011404e-05, "loss": 0.0016, "step": 312520 }, { "epoch": 75.07, "learning_rate": 1.8837137964567514e-05, "loss": 0.0013, "step": 312530 }, { "epoch": 75.07, "learning_rate": 1.883433093963466e-05, "loss": 0.0014, "step": 312540 }, { "epoch": 75.07, "learning_rate": 1.8831524075329903e-05, "loss": 0.0013, "step": 312550 }, { "epoch": 75.08, "learning_rate": 1.8828717371667752e-05, "loss": 0.0015, "step": 312560 }, { "epoch": 75.08, "learning_rate": 1.8825910828662652e-05, "loss": 0.0014, "step": 312570 }, { "epoch": 75.08, "learning_rate": 1.882310444632905e-05, "loss": 0.0014, "step": 312580 }, { "epoch": 75.08, "learning_rate": 1.8820298224681443e-05, "loss": 0.0014, "step": 312590 }, { "epoch": 75.09, "learning_rate": 1.8817492163734263e-05, "loss": 0.0048, "step": 312600 }, { "epoch": 75.09, "learning_rate": 1.881468626350201e-05, "loss": 0.0013, "step": 312610 }, { "epoch": 75.09, "learning_rate": 1.8811880523999105e-05, "loss": 0.0018, "step": 312620 }, { "epoch": 75.09, "learning_rate": 1.8809074945240046e-05, "loss": 0.0013, "step": 312630 }, { "epoch": 75.09, "learning_rate": 1.8806269527239258e-05, "loss": 0.0015, "step": 312640 }, { "epoch": 75.1, "learning_rate": 1.880346427001122e-05, "loss": 0.0026, "step": 312650 }, { "epoch": 75.1, "learning_rate": 1.88006591735704e-05, "loss": 0.0014, "step": 312660 }, { "epoch": 75.1, "learning_rate": 1.879785423793123e-05, "loss": 0.0014, "step": 312670 }, { "epoch": 75.1, "learning_rate": 1.8795049463108196e-05, "loss": 0.0013, "step": 312680 }, { "epoch": 75.11, "learning_rate": 1.879224484911572e-05, "loss": 0.0014, "step": 312690 }, { "epoch": 75.11, "learning_rate": 1.8789440395968295e-05, "loss": 0.0013, "step": 312700 }, { "epoch": 75.11, "learning_rate": 1.878663610368035e-05, "loss": 0.0014, "step": 312710 }, { "epoch": 75.11, "learning_rate": 1.878383197226633e-05, "loss": 0.0015, "step": 312720 }, { "epoch": 75.12, "learning_rate": 1.878102800174072e-05, "loss": 0.0015, "step": 312730 }, { "epoch": 75.12, "learning_rate": 1.8778224192117933e-05, "loss": 0.0014, "step": 312740 }, { "epoch": 75.12, "learning_rate": 1.8775420543412454e-05, "loss": 0.0014, "step": 312750 }, { "epoch": 75.12, "learning_rate": 1.87726170556387e-05, "loss": 0.0014, "step": 312760 }, { "epoch": 75.12, "learning_rate": 1.8769813728811163e-05, "loss": 0.0112, "step": 312770 }, { "epoch": 75.13, "learning_rate": 1.8767010562944266e-05, "loss": 0.0014, "step": 312780 }, { "epoch": 75.13, "learning_rate": 1.876420755805244e-05, "loss": 0.0016, "step": 312790 }, { "epoch": 75.13, "learning_rate": 1.876140471415016e-05, "loss": 0.0013, "step": 312800 }, { "epoch": 75.13, "learning_rate": 1.8758602031251856e-05, "loss": 0.0014, "step": 312810 }, { "epoch": 75.14, "learning_rate": 1.8755799509371985e-05, "loss": 0.0012, "step": 312820 }, { "epoch": 75.14, "learning_rate": 1.875299714852497e-05, "loss": 0.0014, "step": 312830 }, { "epoch": 75.14, "learning_rate": 1.8750194948725286e-05, "loss": 0.0025, "step": 312840 }, { "epoch": 75.14, "learning_rate": 1.874739290998736e-05, "loss": 0.0016, "step": 312850 }, { "epoch": 75.15, "learning_rate": 1.8744591032325615e-05, "loss": 0.0014, "step": 312860 }, { "epoch": 75.15, "learning_rate": 1.8741789315754527e-05, "loss": 0.0014, "step": 312870 }, { "epoch": 75.15, "learning_rate": 1.8738987760288495e-05, "loss": 0.0014, "step": 312880 }, { "epoch": 75.15, "learning_rate": 1.8736186365942005e-05, "loss": 0.0014, "step": 312890 }, { "epoch": 75.15, "learning_rate": 1.8733385132729455e-05, "loss": 0.0013, "step": 312900 }, { "epoch": 75.16, "learning_rate": 1.8730584060665312e-05, "loss": 0.0013, "step": 312910 }, { "epoch": 75.16, "learning_rate": 1.8727783149763984e-05, "loss": 0.0013, "step": 312920 }, { "epoch": 75.16, "learning_rate": 1.872498240003994e-05, "loss": 0.0013, "step": 312930 }, { "epoch": 75.16, "learning_rate": 1.8722181811507582e-05, "loss": 0.0016, "step": 312940 }, { "epoch": 75.17, "learning_rate": 1.871938138418138e-05, "loss": 0.0014, "step": 312950 }, { "epoch": 75.17, "learning_rate": 1.8716581118075726e-05, "loss": 0.0012, "step": 312960 }, { "epoch": 75.17, "learning_rate": 1.871378101320508e-05, "loss": 0.0013, "step": 312970 }, { "epoch": 75.17, "learning_rate": 1.8710981069583884e-05, "loss": 0.0013, "step": 312980 }, { "epoch": 75.17, "learning_rate": 1.870818128722655e-05, "loss": 0.0013, "step": 312990 }, { "epoch": 75.18, "learning_rate": 1.8705381666147493e-05, "loss": 0.002, "step": 313000 }, { "epoch": 75.18, "learning_rate": 1.870258220636118e-05, "loss": 0.0012, "step": 313010 }, { "epoch": 75.18, "learning_rate": 1.8699782907882003e-05, "loss": 0.0013, "step": 313020 }, { "epoch": 75.18, "learning_rate": 1.8696983770724424e-05, "loss": 0.0014, "step": 313030 }, { "epoch": 75.19, "learning_rate": 1.8694184794902837e-05, "loss": 0.0014, "step": 313040 }, { "epoch": 75.19, "learning_rate": 1.8691385980431696e-05, "loss": 0.0016, "step": 313050 }, { "epoch": 75.19, "learning_rate": 1.8688587327325414e-05, "loss": 0.0012, "step": 313060 }, { "epoch": 75.19, "learning_rate": 1.86857888355984e-05, "loss": 0.0013, "step": 313070 }, { "epoch": 75.2, "learning_rate": 1.8682990505265107e-05, "loss": 0.0013, "step": 313080 }, { "epoch": 75.2, "learning_rate": 1.868019233633993e-05, "loss": 0.0014, "step": 313090 }, { "epoch": 75.2, "learning_rate": 1.8677394328837318e-05, "loss": 0.0015, "step": 313100 }, { "epoch": 75.2, "learning_rate": 1.8674596482771654e-05, "loss": 0.0014, "step": 313110 }, { "epoch": 75.2, "learning_rate": 1.867179879815741e-05, "loss": 0.0016, "step": 313120 }, { "epoch": 75.21, "learning_rate": 1.866900127500897e-05, "loss": 0.0015, "step": 313130 }, { "epoch": 75.21, "learning_rate": 1.8666203913340742e-05, "loss": 0.0012, "step": 313140 }, { "epoch": 75.21, "learning_rate": 1.866340671316718e-05, "loss": 0.0015, "step": 313150 }, { "epoch": 75.21, "learning_rate": 1.8660609674502666e-05, "loss": 0.0015, "step": 313160 }, { "epoch": 75.22, "learning_rate": 1.8657812797361647e-05, "loss": 0.0022, "step": 313170 }, { "epoch": 75.22, "learning_rate": 1.8655016081758504e-05, "loss": 0.0015, "step": 313180 }, { "epoch": 75.22, "learning_rate": 1.865221952770769e-05, "loss": 0.0013, "step": 313190 }, { "epoch": 75.22, "learning_rate": 1.8649423135223593e-05, "loss": 0.0015, "step": 313200 }, { "epoch": 75.23, "learning_rate": 1.8646626904320618e-05, "loss": 0.0013, "step": 313210 }, { "epoch": 75.23, "learning_rate": 1.8643830835013192e-05, "loss": 0.0015, "step": 313220 }, { "epoch": 75.23, "learning_rate": 1.8641034927315743e-05, "loss": 0.0015, "step": 313230 }, { "epoch": 75.23, "learning_rate": 1.863823918124264e-05, "loss": 0.0013, "step": 313240 }, { "epoch": 75.23, "learning_rate": 1.8635443596808334e-05, "loss": 0.0016, "step": 313250 }, { "epoch": 75.24, "learning_rate": 1.8632648174027195e-05, "loss": 0.0014, "step": 313260 }, { "epoch": 75.24, "learning_rate": 1.8629852912913664e-05, "loss": 0.0015, "step": 313270 }, { "epoch": 75.24, "learning_rate": 1.8627057813482124e-05, "loss": 0.0015, "step": 313280 }, { "epoch": 75.24, "learning_rate": 1.8624262875747e-05, "loss": 0.0015, "step": 313290 }, { "epoch": 75.25, "learning_rate": 1.8621468099722673e-05, "loss": 0.0019, "step": 313300 }, { "epoch": 75.25, "learning_rate": 1.8618673485423582e-05, "loss": 0.0013, "step": 313310 }, { "epoch": 75.25, "learning_rate": 1.8615879032864087e-05, "loss": 0.0015, "step": 313320 }, { "epoch": 75.25, "learning_rate": 1.8613084742058635e-05, "loss": 0.0015, "step": 313330 }, { "epoch": 75.25, "learning_rate": 1.8610290613021593e-05, "loss": 0.0016, "step": 313340 }, { "epoch": 75.26, "learning_rate": 1.8607496645767385e-05, "loss": 0.0014, "step": 313350 }, { "epoch": 75.26, "learning_rate": 1.8604702840310406e-05, "loss": 0.0013, "step": 313360 }, { "epoch": 75.26, "learning_rate": 1.8601909196665028e-05, "loss": 0.0023, "step": 313370 }, { "epoch": 75.26, "learning_rate": 1.85991157148457e-05, "loss": 0.0014, "step": 313380 }, { "epoch": 75.27, "learning_rate": 1.8596322394866767e-05, "loss": 0.0019, "step": 313390 }, { "epoch": 75.27, "learning_rate": 1.859352923674267e-05, "loss": 0.0013, "step": 313400 }, { "epoch": 75.27, "learning_rate": 1.8590736240487765e-05, "loss": 0.0013, "step": 313410 }, { "epoch": 75.27, "learning_rate": 1.8587943406116492e-05, "loss": 0.0013, "step": 313420 }, { "epoch": 75.28, "learning_rate": 1.858515073364322e-05, "loss": 0.0016, "step": 313430 }, { "epoch": 75.28, "learning_rate": 1.8582358223082324e-05, "loss": 0.0018, "step": 313440 }, { "epoch": 75.28, "learning_rate": 1.8579565874448234e-05, "loss": 0.0016, "step": 313450 }, { "epoch": 75.28, "learning_rate": 1.8576773687755304e-05, "loss": 0.0016, "step": 313460 }, { "epoch": 75.28, "learning_rate": 1.857398166301797e-05, "loss": 0.0015, "step": 313470 }, { "epoch": 75.29, "learning_rate": 1.8571189800250578e-05, "loss": 0.0017, "step": 313480 }, { "epoch": 75.29, "learning_rate": 1.8568398099467548e-05, "loss": 0.0014, "step": 313490 }, { "epoch": 75.29, "learning_rate": 1.856560656068326e-05, "loss": 0.0014, "step": 313500 }, { "epoch": 75.29, "learning_rate": 1.856281518391208e-05, "loss": 0.0015, "step": 313510 }, { "epoch": 75.3, "learning_rate": 1.8560023969168432e-05, "loss": 0.002, "step": 313520 }, { "epoch": 75.3, "learning_rate": 1.8557232916466667e-05, "loss": 0.0013, "step": 313530 }, { "epoch": 75.3, "learning_rate": 1.855444202582119e-05, "loss": 0.0014, "step": 313540 }, { "epoch": 75.3, "learning_rate": 1.8551651297246392e-05, "loss": 0.0015, "step": 313550 }, { "epoch": 75.31, "learning_rate": 1.854886073075663e-05, "loss": 0.0014, "step": 313560 }, { "epoch": 75.31, "learning_rate": 1.854607032636632e-05, "loss": 0.0014, "step": 313570 }, { "epoch": 75.31, "learning_rate": 1.854328008408981e-05, "loss": 0.0014, "step": 313580 }, { "epoch": 75.31, "learning_rate": 1.8540490003941518e-05, "loss": 0.015, "step": 313590 }, { "epoch": 75.31, "learning_rate": 1.8537700085935782e-05, "loss": 0.0014, "step": 313600 }, { "epoch": 75.32, "learning_rate": 1.853491033008702e-05, "loss": 0.0014, "step": 313610 }, { "epoch": 75.32, "learning_rate": 1.853212073640958e-05, "loss": 0.0014, "step": 313620 }, { "epoch": 75.32, "learning_rate": 1.852933130491786e-05, "loss": 0.0014, "step": 313630 }, { "epoch": 75.32, "learning_rate": 1.8526542035626244e-05, "loss": 0.0014, "step": 313640 }, { "epoch": 75.33, "learning_rate": 1.8523752928549066e-05, "loss": 0.0014, "step": 313650 }, { "epoch": 75.33, "learning_rate": 1.852096398370075e-05, "loss": 0.0014, "step": 313660 }, { "epoch": 75.33, "learning_rate": 1.8518175201095627e-05, "loss": 0.0014, "step": 313670 }, { "epoch": 75.33, "learning_rate": 1.851538658074811e-05, "loss": 0.0014, "step": 313680 }, { "epoch": 75.33, "learning_rate": 1.8512598122672543e-05, "loss": 0.0013, "step": 313690 }, { "epoch": 75.34, "learning_rate": 1.8509809826883322e-05, "loss": 0.0014, "step": 313700 }, { "epoch": 75.34, "learning_rate": 1.8507021693394806e-05, "loss": 0.0013, "step": 313710 }, { "epoch": 75.34, "learning_rate": 1.8504233722221343e-05, "loss": 0.0014, "step": 313720 }, { "epoch": 75.34, "learning_rate": 1.850144591337734e-05, "loss": 0.0013, "step": 313730 }, { "epoch": 75.35, "learning_rate": 1.8498658266877132e-05, "loss": 0.0013, "step": 313740 }, { "epoch": 75.35, "learning_rate": 1.8495870782735118e-05, "loss": 0.0014, "step": 313750 }, { "epoch": 75.35, "learning_rate": 1.8493083460965638e-05, "loss": 0.0013, "step": 313760 }, { "epoch": 75.35, "learning_rate": 1.8490296301583083e-05, "loss": 0.0015, "step": 313770 }, { "epoch": 75.36, "learning_rate": 1.8487509304601803e-05, "loss": 0.0012, "step": 313780 }, { "epoch": 75.36, "learning_rate": 1.8484722470036143e-05, "loss": 0.0032, "step": 313790 }, { "epoch": 75.36, "learning_rate": 1.8481935797900505e-05, "loss": 0.0054, "step": 313800 }, { "epoch": 75.36, "learning_rate": 1.8479149288209223e-05, "loss": 0.0014, "step": 313810 }, { "epoch": 75.36, "learning_rate": 1.847636294097668e-05, "loss": 0.0014, "step": 313820 }, { "epoch": 75.37, "learning_rate": 1.8473576756217215e-05, "loss": 0.0014, "step": 313830 }, { "epoch": 75.37, "learning_rate": 1.8470790733945208e-05, "loss": 0.0014, "step": 313840 }, { "epoch": 75.37, "learning_rate": 1.8468004874174998e-05, "loss": 0.0015, "step": 313850 }, { "epoch": 75.37, "learning_rate": 1.846521917692095e-05, "loss": 0.0019, "step": 313860 }, { "epoch": 75.38, "learning_rate": 1.8462433642197448e-05, "loss": 0.0013, "step": 313870 }, { "epoch": 75.38, "learning_rate": 1.845964827001881e-05, "loss": 0.0013, "step": 313880 }, { "epoch": 75.38, "learning_rate": 1.845686306039942e-05, "loss": 0.0027, "step": 313890 }, { "epoch": 75.38, "learning_rate": 1.8454078013353603e-05, "loss": 0.0014, "step": 313900 }, { "epoch": 75.39, "learning_rate": 1.845129312889576e-05, "loss": 0.0014, "step": 313910 }, { "epoch": 75.39, "learning_rate": 1.8448508407040205e-05, "loss": 0.0017, "step": 313920 }, { "epoch": 75.39, "learning_rate": 1.844572384780129e-05, "loss": 0.0064, "step": 313930 }, { "epoch": 75.39, "learning_rate": 1.8442939451193393e-05, "loss": 0.0012, "step": 313940 }, { "epoch": 75.39, "learning_rate": 1.8440155217230832e-05, "loss": 0.0013, "step": 313950 }, { "epoch": 75.4, "learning_rate": 1.843737114592799e-05, "loss": 0.0016, "step": 313960 }, { "epoch": 75.4, "learning_rate": 1.843458723729919e-05, "loss": 0.0013, "step": 313970 }, { "epoch": 75.4, "learning_rate": 1.8431803491358802e-05, "loss": 0.0012, "step": 313980 }, { "epoch": 75.4, "learning_rate": 1.8429019908121165e-05, "loss": 0.0013, "step": 313990 }, { "epoch": 75.41, "learning_rate": 1.8426236487600606e-05, "loss": 0.0014, "step": 314000 }, { "epoch": 75.41, "learning_rate": 1.8423453229811506e-05, "loss": 0.0035, "step": 314010 }, { "epoch": 75.41, "learning_rate": 1.8420670134768176e-05, "loss": 0.0021, "step": 314020 }, { "epoch": 75.41, "learning_rate": 1.841788720248499e-05, "loss": 0.0013, "step": 314030 }, { "epoch": 75.41, "learning_rate": 1.841510443297626e-05, "loss": 0.0159, "step": 314040 }, { "epoch": 75.42, "learning_rate": 1.8412321826256368e-05, "loss": 0.0012, "step": 314050 }, { "epoch": 75.42, "learning_rate": 1.840953938233963e-05, "loss": 0.0014, "step": 314060 }, { "epoch": 75.42, "learning_rate": 1.8406757101240373e-05, "loss": 0.0014, "step": 314070 }, { "epoch": 75.42, "learning_rate": 1.840397498297297e-05, "loss": 0.0019, "step": 314080 }, { "epoch": 75.43, "learning_rate": 1.840119302755173e-05, "loss": 0.0013, "step": 314090 }, { "epoch": 75.43, "learning_rate": 1.839841123499102e-05, "loss": 0.0014, "step": 314100 }, { "epoch": 75.43, "learning_rate": 1.8395629605305146e-05, "loss": 0.0014, "step": 314110 }, { "epoch": 75.43, "learning_rate": 1.8392848138508477e-05, "loss": 0.0042, "step": 314120 }, { "epoch": 75.44, "learning_rate": 1.839006683461532e-05, "loss": 0.0017, "step": 314130 }, { "epoch": 75.44, "learning_rate": 1.838728569364004e-05, "loss": 0.0014, "step": 314140 }, { "epoch": 75.44, "learning_rate": 1.8384504715596928e-05, "loss": 0.0015, "step": 314150 }, { "epoch": 75.44, "learning_rate": 1.838172390050037e-05, "loss": 0.0014, "step": 314160 }, { "epoch": 75.44, "learning_rate": 1.8378943248364648e-05, "loss": 0.0013, "step": 314170 }, { "epoch": 75.45, "learning_rate": 1.837616275920412e-05, "loss": 0.0014, "step": 314180 }, { "epoch": 75.45, "learning_rate": 1.8373382433033126e-05, "loss": 0.0014, "step": 314190 }, { "epoch": 75.45, "learning_rate": 1.8370602269865973e-05, "loss": 0.0013, "step": 314200 }, { "epoch": 75.45, "learning_rate": 1.8367822269717012e-05, "loss": 0.0013, "step": 314210 }, { "epoch": 75.46, "learning_rate": 1.8365042432600566e-05, "loss": 0.0015, "step": 314220 }, { "epoch": 75.46, "learning_rate": 1.8362262758530928e-05, "loss": 0.0013, "step": 314230 }, { "epoch": 75.46, "learning_rate": 1.835948324752248e-05, "loss": 0.0013, "step": 314240 }, { "epoch": 75.46, "learning_rate": 1.8356703899589493e-05, "loss": 0.0016, "step": 314250 }, { "epoch": 75.47, "learning_rate": 1.8353924714746346e-05, "loss": 0.0015, "step": 314260 }, { "epoch": 75.47, "learning_rate": 1.835114569300731e-05, "loss": 0.0015, "step": 314270 }, { "epoch": 75.47, "learning_rate": 1.8348366834386755e-05, "loss": 0.0012, "step": 314280 }, { "epoch": 75.47, "learning_rate": 1.8345588138898983e-05, "loss": 0.0013, "step": 314290 }, { "epoch": 75.47, "learning_rate": 1.8342809606558292e-05, "loss": 0.0013, "step": 314300 }, { "epoch": 75.48, "learning_rate": 1.8340031237379048e-05, "loss": 0.0015, "step": 314310 }, { "epoch": 75.48, "learning_rate": 1.833725303137553e-05, "loss": 0.0014, "step": 314320 }, { "epoch": 75.48, "learning_rate": 1.8334474988562084e-05, "loss": 0.0013, "step": 314330 }, { "epoch": 75.48, "learning_rate": 1.8331697108953012e-05, "loss": 0.0014, "step": 314340 }, { "epoch": 75.49, "learning_rate": 1.832891939256265e-05, "loss": 0.0015, "step": 314350 }, { "epoch": 75.49, "learning_rate": 1.8326141839405296e-05, "loss": 0.0013, "step": 314360 }, { "epoch": 75.49, "learning_rate": 1.8323364449495262e-05, "loss": 0.0015, "step": 314370 }, { "epoch": 75.49, "learning_rate": 1.832058722284689e-05, "loss": 0.0016, "step": 314380 }, { "epoch": 75.49, "learning_rate": 1.8317810159474457e-05, "loss": 0.0013, "step": 314390 }, { "epoch": 75.5, "learning_rate": 1.831503325939231e-05, "loss": 0.0013, "step": 314400 }, { "epoch": 75.5, "learning_rate": 1.8312256522614735e-05, "loss": 0.0015, "step": 314410 }, { "epoch": 75.5, "learning_rate": 1.8309479949156068e-05, "loss": 0.0014, "step": 314420 }, { "epoch": 75.5, "learning_rate": 1.830670353903059e-05, "loss": 0.0016, "step": 314430 }, { "epoch": 75.51, "learning_rate": 1.830392729225264e-05, "loss": 0.0011, "step": 314440 }, { "epoch": 75.51, "learning_rate": 1.8301151208836505e-05, "loss": 0.0044, "step": 314450 }, { "epoch": 75.51, "learning_rate": 1.829837528879651e-05, "loss": 0.0014, "step": 314460 }, { "epoch": 75.51, "learning_rate": 1.8295599532146947e-05, "loss": 0.0015, "step": 314470 }, { "epoch": 75.52, "learning_rate": 1.8292823938902122e-05, "loss": 0.0014, "step": 314480 }, { "epoch": 75.52, "learning_rate": 1.8290048509076363e-05, "loss": 0.0014, "step": 314490 }, { "epoch": 75.52, "learning_rate": 1.828727324268396e-05, "loss": 0.0014, "step": 314500 }, { "epoch": 75.52, "learning_rate": 1.8284498139739198e-05, "loss": 0.0113, "step": 314510 }, { "epoch": 75.52, "learning_rate": 1.8281723200256418e-05, "loss": 0.0016, "step": 314520 }, { "epoch": 75.53, "learning_rate": 1.8278948424249886e-05, "loss": 0.0025, "step": 314530 }, { "epoch": 75.53, "learning_rate": 1.8276173811733932e-05, "loss": 0.0034, "step": 314540 }, { "epoch": 75.53, "learning_rate": 1.8273399362722826e-05, "loss": 0.0016, "step": 314550 }, { "epoch": 75.53, "learning_rate": 1.8270625077230908e-05, "loss": 0.0016, "step": 314560 }, { "epoch": 75.54, "learning_rate": 1.8267850955272447e-05, "loss": 0.0016, "step": 314570 }, { "epoch": 75.54, "learning_rate": 1.8265076996861736e-05, "loss": 0.0014, "step": 314580 }, { "epoch": 75.54, "learning_rate": 1.8262303202013093e-05, "loss": 0.0014, "step": 314590 }, { "epoch": 75.54, "learning_rate": 1.825952957074079e-05, "loss": 0.0014, "step": 314600 }, { "epoch": 75.55, "learning_rate": 1.8256756103059157e-05, "loss": 0.0013, "step": 314610 }, { "epoch": 75.55, "learning_rate": 1.825398279898245e-05, "loss": 0.0014, "step": 314620 }, { "epoch": 75.55, "learning_rate": 1.8251209658525e-05, "loss": 0.0014, "step": 314630 }, { "epoch": 75.55, "learning_rate": 1.8248436681701082e-05, "loss": 0.0013, "step": 314640 }, { "epoch": 75.55, "learning_rate": 1.8245663868524964e-05, "loss": 0.0025, "step": 314650 }, { "epoch": 75.56, "learning_rate": 1.8242891219010977e-05, "loss": 0.0015, "step": 314660 }, { "epoch": 75.56, "learning_rate": 1.8240118733173377e-05, "loss": 0.0014, "step": 314670 }, { "epoch": 75.56, "learning_rate": 1.8237346411026497e-05, "loss": 0.0016, "step": 314680 }, { "epoch": 75.56, "learning_rate": 1.8234574252584573e-05, "loss": 0.0014, "step": 314690 }, { "epoch": 75.57, "learning_rate": 1.8231802257861934e-05, "loss": 0.0021, "step": 314700 }, { "epoch": 75.57, "learning_rate": 1.8229030426872855e-05, "loss": 0.0014, "step": 314710 }, { "epoch": 75.57, "learning_rate": 1.8226258759631602e-05, "loss": 0.0013, "step": 314720 }, { "epoch": 75.57, "learning_rate": 1.8223487256152498e-05, "loss": 0.0014, "step": 314730 }, { "epoch": 75.57, "learning_rate": 1.822071591644979e-05, "loss": 0.0013, "step": 314740 }, { "epoch": 75.58, "learning_rate": 1.821794474053777e-05, "loss": 0.0015, "step": 314750 }, { "epoch": 75.58, "learning_rate": 1.8215173728430744e-05, "loss": 0.0014, "step": 314760 }, { "epoch": 75.58, "learning_rate": 1.821240288014297e-05, "loss": 0.0219, "step": 314770 }, { "epoch": 75.58, "learning_rate": 1.820963219568875e-05, "loss": 0.0014, "step": 314780 }, { "epoch": 75.59, "learning_rate": 1.820686167508234e-05, "loss": 0.0015, "step": 314790 }, { "epoch": 75.59, "learning_rate": 1.820409131833804e-05, "loss": 0.0015, "step": 314800 }, { "epoch": 75.59, "learning_rate": 1.8201321125470105e-05, "loss": 0.0014, "step": 314810 }, { "epoch": 75.59, "learning_rate": 1.819855109649284e-05, "loss": 0.0013, "step": 314820 }, { "epoch": 75.6, "learning_rate": 1.8195781231420495e-05, "loss": 0.0014, "step": 314830 }, { "epoch": 75.6, "learning_rate": 1.819301153026738e-05, "loss": 0.0012, "step": 314840 }, { "epoch": 75.6, "learning_rate": 1.8190241993047742e-05, "loss": 0.0016, "step": 314850 }, { "epoch": 75.6, "learning_rate": 1.8187472619775852e-05, "loss": 0.0013, "step": 314860 }, { "epoch": 75.6, "learning_rate": 1.8184703410466007e-05, "loss": 0.0013, "step": 314870 }, { "epoch": 75.61, "learning_rate": 1.8181934365132453e-05, "loss": 0.0011, "step": 314880 }, { "epoch": 75.61, "learning_rate": 1.817916548378949e-05, "loss": 0.0015, "step": 314890 }, { "epoch": 75.61, "learning_rate": 1.8176396766451352e-05, "loss": 0.0013, "step": 314900 }, { "epoch": 75.61, "learning_rate": 1.8173628213132353e-05, "loss": 0.0014, "step": 314910 }, { "epoch": 75.62, "learning_rate": 1.8170859823846742e-05, "loss": 0.0012, "step": 314920 }, { "epoch": 75.62, "learning_rate": 1.8168091598608767e-05, "loss": 0.0013, "step": 314930 }, { "epoch": 75.62, "learning_rate": 1.8165323537432732e-05, "loss": 0.0012, "step": 314940 }, { "epoch": 75.62, "learning_rate": 1.8162555640332867e-05, "loss": 0.0013, "step": 314950 }, { "epoch": 75.62, "learning_rate": 1.815978790732347e-05, "loss": 0.0014, "step": 314960 }, { "epoch": 75.63, "learning_rate": 1.8157020338418784e-05, "loss": 0.0016, "step": 314970 }, { "epoch": 75.63, "learning_rate": 1.8154252933633093e-05, "loss": 0.0014, "step": 314980 }, { "epoch": 75.63, "learning_rate": 1.8151485692980635e-05, "loss": 0.0016, "step": 314990 }, { "epoch": 75.63, "learning_rate": 1.8148718616475696e-05, "loss": 0.0013, "step": 315000 }, { "epoch": 75.64, "learning_rate": 1.8145951704132534e-05, "loss": 0.0014, "step": 315010 }, { "epoch": 75.64, "learning_rate": 1.814318495596538e-05, "loss": 0.0013, "step": 315020 }, { "epoch": 75.64, "learning_rate": 1.8140418371988545e-05, "loss": 0.0013, "step": 315030 }, { "epoch": 75.64, "learning_rate": 1.8137651952216235e-05, "loss": 0.0015, "step": 315040 }, { "epoch": 75.65, "learning_rate": 1.813488569666273e-05, "loss": 0.0013, "step": 315050 }, { "epoch": 75.65, "learning_rate": 1.8132119605342312e-05, "loss": 0.0014, "step": 315060 }, { "epoch": 75.65, "learning_rate": 1.81293536782692e-05, "loss": 0.0014, "step": 315070 }, { "epoch": 75.65, "learning_rate": 1.8126587915457676e-05, "loss": 0.0014, "step": 315080 }, { "epoch": 75.65, "learning_rate": 1.8123822316921973e-05, "loss": 0.0014, "step": 315090 }, { "epoch": 75.66, "learning_rate": 1.8121056882676373e-05, "loss": 0.0014, "step": 315100 }, { "epoch": 75.66, "learning_rate": 1.8118291612735094e-05, "loss": 0.0012, "step": 315110 }, { "epoch": 75.66, "learning_rate": 1.811552650711243e-05, "loss": 0.0012, "step": 315120 }, { "epoch": 75.66, "learning_rate": 1.8112761565822583e-05, "loss": 0.0014, "step": 315130 }, { "epoch": 75.67, "learning_rate": 1.8109996788879853e-05, "loss": 0.0014, "step": 315140 }, { "epoch": 75.67, "learning_rate": 1.8107232176298462e-05, "loss": 0.0014, "step": 315150 }, { "epoch": 75.67, "learning_rate": 1.8104467728092644e-05, "loss": 0.0013, "step": 315160 }, { "epoch": 75.67, "learning_rate": 1.8101703444276687e-05, "loss": 0.0014, "step": 315170 }, { "epoch": 75.68, "learning_rate": 1.8098939324864793e-05, "loss": 0.0014, "step": 315180 }, { "epoch": 75.68, "learning_rate": 1.809617536987126e-05, "loss": 0.0015, "step": 315190 }, { "epoch": 75.68, "learning_rate": 1.8093411579310283e-05, "loss": 0.0013, "step": 315200 }, { "epoch": 75.68, "learning_rate": 1.8090647953196145e-05, "loss": 0.0014, "step": 315210 }, { "epoch": 75.68, "learning_rate": 1.808788449154308e-05, "loss": 0.0015, "step": 315220 }, { "epoch": 75.69, "learning_rate": 1.80851211943653e-05, "loss": 0.0013, "step": 315230 }, { "epoch": 75.69, "learning_rate": 1.8082358061677097e-05, "loss": 0.0014, "step": 315240 }, { "epoch": 75.69, "learning_rate": 1.807959509349267e-05, "loss": 0.0015, "step": 315250 }, { "epoch": 75.69, "learning_rate": 1.8076832289826286e-05, "loss": 0.0014, "step": 315260 }, { "epoch": 75.7, "learning_rate": 1.8074069650692166e-05, "loss": 0.0014, "step": 315270 }, { "epoch": 75.7, "learning_rate": 1.8071307176104567e-05, "loss": 0.0015, "step": 315280 }, { "epoch": 75.7, "learning_rate": 1.8068544866077726e-05, "loss": 0.0015, "step": 315290 }, { "epoch": 75.7, "learning_rate": 1.806578272062585e-05, "loss": 0.0015, "step": 315300 }, { "epoch": 75.7, "learning_rate": 1.8063020739763215e-05, "loss": 0.0013, "step": 315310 }, { "epoch": 75.71, "learning_rate": 1.806025892350402e-05, "loss": 0.0013, "step": 315320 }, { "epoch": 75.71, "learning_rate": 1.8057497271862532e-05, "loss": 0.0013, "step": 315330 }, { "epoch": 75.71, "learning_rate": 1.805473578485296e-05, "loss": 0.0015, "step": 315340 }, { "epoch": 75.71, "learning_rate": 1.8051974462489562e-05, "loss": 0.0013, "step": 315350 }, { "epoch": 75.72, "learning_rate": 1.8049213304786533e-05, "loss": 0.0014, "step": 315360 }, { "epoch": 75.72, "learning_rate": 1.8046452311758126e-05, "loss": 0.0012, "step": 315370 }, { "epoch": 75.72, "learning_rate": 1.8043691483418596e-05, "loss": 0.0013, "step": 315380 }, { "epoch": 75.72, "learning_rate": 1.804093081978212e-05, "loss": 0.0015, "step": 315390 }, { "epoch": 75.73, "learning_rate": 1.803817032086298e-05, "loss": 0.0013, "step": 315400 }, { "epoch": 75.73, "learning_rate": 1.8035409986675356e-05, "loss": 0.0013, "step": 315410 }, { "epoch": 75.73, "learning_rate": 1.803264981723351e-05, "loss": 0.0017, "step": 315420 }, { "epoch": 75.73, "learning_rate": 1.802988981255166e-05, "loss": 0.0013, "step": 315430 }, { "epoch": 75.73, "learning_rate": 1.8027129972644e-05, "loss": 0.0015, "step": 315440 }, { "epoch": 75.74, "learning_rate": 1.8024370297524806e-05, "loss": 0.0069, "step": 315450 }, { "epoch": 75.74, "learning_rate": 1.8021610787208255e-05, "loss": 0.0015, "step": 315460 }, { "epoch": 75.74, "learning_rate": 1.80188514417086e-05, "loss": 0.0013, "step": 315470 }, { "epoch": 75.74, "learning_rate": 1.801609226104004e-05, "loss": 0.0013, "step": 315480 }, { "epoch": 75.75, "learning_rate": 1.8013333245216824e-05, "loss": 0.0015, "step": 315490 }, { "epoch": 75.75, "learning_rate": 1.8010574394253154e-05, "loss": 0.0014, "step": 315500 }, { "epoch": 75.75, "learning_rate": 1.800781570816324e-05, "loss": 0.0041, "step": 315510 }, { "epoch": 75.75, "learning_rate": 1.800505718696132e-05, "loss": 0.0015, "step": 315520 }, { "epoch": 75.76, "learning_rate": 1.8002298830661596e-05, "loss": 0.0013, "step": 315530 }, { "epoch": 75.76, "learning_rate": 1.7999540639278302e-05, "loss": 0.0015, "step": 315540 }, { "epoch": 75.76, "learning_rate": 1.7996782612825624e-05, "loss": 0.0018, "step": 315550 }, { "epoch": 75.76, "learning_rate": 1.7994024751317817e-05, "loss": 0.0013, "step": 315560 }, { "epoch": 75.76, "learning_rate": 1.7991267054769074e-05, "loss": 0.0015, "step": 315570 }, { "epoch": 75.77, "learning_rate": 1.7988509523193587e-05, "loss": 0.0014, "step": 315580 }, { "epoch": 75.77, "learning_rate": 1.7985752156605606e-05, "loss": 0.0014, "step": 315590 }, { "epoch": 75.77, "learning_rate": 1.798299495501931e-05, "loss": 0.0016, "step": 315600 }, { "epoch": 75.77, "learning_rate": 1.798023791844895e-05, "loss": 0.0013, "step": 315610 }, { "epoch": 75.78, "learning_rate": 1.7977481046908685e-05, "loss": 0.0013, "step": 315620 }, { "epoch": 75.78, "learning_rate": 1.7974724340412775e-05, "loss": 0.0015, "step": 315630 }, { "epoch": 75.78, "learning_rate": 1.797196779897538e-05, "loss": 0.0019, "step": 315640 }, { "epoch": 75.78, "learning_rate": 1.796921142261075e-05, "loss": 0.0015, "step": 315650 }, { "epoch": 75.78, "learning_rate": 1.7966455211333055e-05, "loss": 0.0013, "step": 315660 }, { "epoch": 75.79, "learning_rate": 1.796369916515654e-05, "loss": 0.0016, "step": 315670 }, { "epoch": 75.79, "learning_rate": 1.796094328409536e-05, "loss": 0.0014, "step": 315680 }, { "epoch": 75.79, "learning_rate": 1.7958187568163753e-05, "loss": 0.0015, "step": 315690 }, { "epoch": 75.79, "learning_rate": 1.7955432017375927e-05, "loss": 0.0049, "step": 315700 }, { "epoch": 75.8, "learning_rate": 1.795267663174608e-05, "loss": 0.0019, "step": 315710 }, { "epoch": 75.8, "learning_rate": 1.7949921411288384e-05, "loss": 0.0014, "step": 315720 }, { "epoch": 75.8, "learning_rate": 1.7947166356017076e-05, "loss": 0.0017, "step": 315730 }, { "epoch": 75.8, "learning_rate": 1.7944411465946326e-05, "loss": 0.0014, "step": 315740 }, { "epoch": 75.81, "learning_rate": 1.7941656741090367e-05, "loss": 0.0016, "step": 315750 }, { "epoch": 75.81, "learning_rate": 1.793890218146336e-05, "loss": 0.0013, "step": 315760 }, { "epoch": 75.81, "learning_rate": 1.7936147787079526e-05, "loss": 0.0016, "step": 315770 }, { "epoch": 75.81, "learning_rate": 1.7933393557953048e-05, "loss": 0.0064, "step": 315780 }, { "epoch": 75.81, "learning_rate": 1.793063949409814e-05, "loss": 0.0013, "step": 315790 }, { "epoch": 75.82, "learning_rate": 1.7927885595528988e-05, "loss": 0.0016, "step": 315800 }, { "epoch": 75.82, "learning_rate": 1.7925131862259757e-05, "loss": 0.003, "step": 315810 }, { "epoch": 75.82, "learning_rate": 1.7922378294304694e-05, "loss": 0.0014, "step": 315820 }, { "epoch": 75.82, "learning_rate": 1.7919624891677932e-05, "loss": 0.0014, "step": 315830 }, { "epoch": 75.83, "learning_rate": 1.7916871654393713e-05, "loss": 0.0014, "step": 315840 }, { "epoch": 75.83, "learning_rate": 1.7914118582466188e-05, "loss": 0.0017, "step": 315850 }, { "epoch": 75.83, "learning_rate": 1.7911365675909585e-05, "loss": 0.0013, "step": 315860 }, { "epoch": 75.83, "learning_rate": 1.790861293473807e-05, "loss": 0.0013, "step": 315870 }, { "epoch": 75.84, "learning_rate": 1.790586035896581e-05, "loss": 0.0012, "step": 315880 }, { "epoch": 75.84, "learning_rate": 1.7903107948607035e-05, "loss": 0.0014, "step": 315890 }, { "epoch": 75.84, "learning_rate": 1.7900355703675893e-05, "loss": 0.0013, "step": 315900 }, { "epoch": 75.84, "learning_rate": 1.7897603624186603e-05, "loss": 0.0014, "step": 315910 }, { "epoch": 75.84, "learning_rate": 1.7894851710153314e-05, "loss": 0.0013, "step": 315920 }, { "epoch": 75.85, "learning_rate": 1.789209996159025e-05, "loss": 0.0016, "step": 315930 }, { "epoch": 75.85, "learning_rate": 1.7889348378511546e-05, "loss": 0.0013, "step": 315940 }, { "epoch": 75.85, "learning_rate": 1.788659696093143e-05, "loss": 0.0013, "step": 315950 }, { "epoch": 75.85, "learning_rate": 1.7883845708864045e-05, "loss": 0.0012, "step": 315960 }, { "epoch": 75.86, "learning_rate": 1.78810946223236e-05, "loss": 0.0018, "step": 315970 }, { "epoch": 75.86, "learning_rate": 1.787834370132425e-05, "loss": 0.0014, "step": 315980 }, { "epoch": 75.86, "learning_rate": 1.7875592945880188e-05, "loss": 0.0014, "step": 315990 }, { "epoch": 75.86, "learning_rate": 1.7872842356005597e-05, "loss": 0.0015, "step": 316000 }, { "epoch": 75.86, "learning_rate": 1.787009193171465e-05, "loss": 0.0014, "step": 316010 }, { "epoch": 75.87, "learning_rate": 1.7867341673021504e-05, "loss": 0.0014, "step": 316020 }, { "epoch": 75.87, "learning_rate": 1.786459157994036e-05, "loss": 0.0096, "step": 316030 }, { "epoch": 75.87, "learning_rate": 1.786184165248536e-05, "loss": 0.0013, "step": 316040 }, { "epoch": 75.87, "learning_rate": 1.785909189067072e-05, "loss": 0.0015, "step": 316050 }, { "epoch": 75.88, "learning_rate": 1.785634229451057e-05, "loss": 0.0013, "step": 316060 }, { "epoch": 75.88, "learning_rate": 1.7853592864019115e-05, "loss": 0.0022, "step": 316070 }, { "epoch": 75.88, "learning_rate": 1.7850843599210514e-05, "loss": 0.0015, "step": 316080 }, { "epoch": 75.88, "learning_rate": 1.7848094500098918e-05, "loss": 0.0013, "step": 316090 }, { "epoch": 75.89, "learning_rate": 1.7845345566698523e-05, "loss": 0.0015, "step": 316100 }, { "epoch": 75.89, "learning_rate": 1.784259679902347e-05, "loss": 0.0015, "step": 316110 }, { "epoch": 75.89, "learning_rate": 1.783984819708796e-05, "loss": 0.0024, "step": 316120 }, { "epoch": 75.89, "learning_rate": 1.783709976090613e-05, "loss": 0.0085, "step": 316130 }, { "epoch": 75.89, "learning_rate": 1.7834351490492168e-05, "loss": 0.0013, "step": 316140 }, { "epoch": 75.9, "learning_rate": 1.7831603385860223e-05, "loss": 0.0013, "step": 316150 }, { "epoch": 75.9, "learning_rate": 1.7828855447024455e-05, "loss": 0.0014, "step": 316160 }, { "epoch": 75.9, "learning_rate": 1.782610767399905e-05, "loss": 0.0014, "step": 316170 }, { "epoch": 75.9, "learning_rate": 1.7823360066798133e-05, "loss": 0.0013, "step": 316180 }, { "epoch": 75.91, "learning_rate": 1.7820612625435907e-05, "loss": 0.0013, "step": 316190 }, { "epoch": 75.91, "learning_rate": 1.7817865349926494e-05, "loss": 0.0015, "step": 316200 }, { "epoch": 75.91, "learning_rate": 1.7815118240284095e-05, "loss": 0.0014, "step": 316210 }, { "epoch": 75.91, "learning_rate": 1.781237129652284e-05, "loss": 0.0024, "step": 316220 }, { "epoch": 75.92, "learning_rate": 1.7809624518656877e-05, "loss": 0.0014, "step": 316230 }, { "epoch": 75.92, "learning_rate": 1.7806877906700392e-05, "loss": 0.0011, "step": 316240 }, { "epoch": 75.92, "learning_rate": 1.7804131460667518e-05, "loss": 0.0013, "step": 316250 }, { "epoch": 75.92, "learning_rate": 1.780138518057241e-05, "loss": 0.0014, "step": 316260 }, { "epoch": 75.92, "learning_rate": 1.7798639066429256e-05, "loss": 0.0014, "step": 316270 }, { "epoch": 75.93, "learning_rate": 1.7795893118252167e-05, "loss": 0.0014, "step": 316280 }, { "epoch": 75.93, "learning_rate": 1.7793147336055327e-05, "loss": 0.0019, "step": 316290 }, { "epoch": 75.93, "learning_rate": 1.7790401719852862e-05, "loss": 0.0014, "step": 316300 }, { "epoch": 75.93, "learning_rate": 1.7787656269658955e-05, "loss": 0.0013, "step": 316310 }, { "epoch": 75.94, "learning_rate": 1.7784910985487713e-05, "loss": 0.0014, "step": 316320 }, { "epoch": 75.94, "learning_rate": 1.778216586735333e-05, "loss": 0.0014, "step": 316330 }, { "epoch": 75.94, "learning_rate": 1.7779420915269917e-05, "loss": 0.0013, "step": 316340 }, { "epoch": 75.94, "learning_rate": 1.7776676129251657e-05, "loss": 0.0013, "step": 316350 }, { "epoch": 75.94, "learning_rate": 1.7773931509312675e-05, "loss": 0.0012, "step": 316360 }, { "epoch": 75.95, "learning_rate": 1.7771187055467097e-05, "loss": 0.0015, "step": 316370 }, { "epoch": 75.95, "learning_rate": 1.7768442767729114e-05, "loss": 0.0014, "step": 316380 }, { "epoch": 76.0, "learning_rate": 1.776569864611283e-05, "loss": 0.0012, "step": 316390 }, { "epoch": 76.0, "learning_rate": 1.7762954690632417e-05, "loss": 0.0013, "step": 316400 }, { "epoch": 76.01, "learning_rate": 1.7760210901301993e-05, "loss": 0.0015, "step": 316410 }, { "epoch": 76.01, "learning_rate": 1.7757467278135727e-05, "loss": 0.0013, "step": 316420 }, { "epoch": 76.01, "learning_rate": 1.775472382114774e-05, "loss": 0.0014, "step": 316430 }, { "epoch": 76.01, "learning_rate": 1.7751980530352164e-05, "loss": 0.0014, "step": 316440 }, { "epoch": 76.01, "learning_rate": 1.7749237405763165e-05, "loss": 0.0014, "step": 316450 }, { "epoch": 76.02, "learning_rate": 1.7746494447394845e-05, "loss": 0.0013, "step": 316460 }, { "epoch": 76.02, "learning_rate": 1.774375165526139e-05, "loss": 0.0012, "step": 316470 }, { "epoch": 76.02, "learning_rate": 1.774100902937688e-05, "loss": 0.0016, "step": 316480 }, { "epoch": 76.02, "learning_rate": 1.7738266569755502e-05, "loss": 0.0013, "step": 316490 }, { "epoch": 76.03, "learning_rate": 1.7735524276411363e-05, "loss": 0.0013, "step": 316500 }, { "epoch": 76.03, "learning_rate": 1.773278214935859e-05, "loss": 0.0014, "step": 316510 }, { "epoch": 76.03, "learning_rate": 1.773004018861134e-05, "loss": 0.0015, "step": 316520 }, { "epoch": 76.03, "learning_rate": 1.7727298394183723e-05, "loss": 0.0013, "step": 316530 }, { "epoch": 76.03, "learning_rate": 1.772455676608989e-05, "loss": 0.0013, "step": 316540 }, { "epoch": 76.04, "learning_rate": 1.7721815304343947e-05, "loss": 0.0013, "step": 316550 }, { "epoch": 76.04, "learning_rate": 1.771907400896005e-05, "loss": 0.0013, "step": 316560 }, { "epoch": 76.04, "learning_rate": 1.7716332879952306e-05, "loss": 0.0012, "step": 316570 }, { "epoch": 76.04, "learning_rate": 1.771359191733485e-05, "loss": 0.0015, "step": 316580 }, { "epoch": 76.05, "learning_rate": 1.7710851121121825e-05, "loss": 0.0013, "step": 316590 }, { "epoch": 76.05, "learning_rate": 1.7708110491327327e-05, "loss": 0.0014, "step": 316600 }, { "epoch": 76.05, "learning_rate": 1.7705370027965517e-05, "loss": 0.0014, "step": 316610 }, { "epoch": 76.05, "learning_rate": 1.770262973105048e-05, "loss": 0.0013, "step": 316620 }, { "epoch": 76.06, "learning_rate": 1.7699889600596375e-05, "loss": 0.0012, "step": 316630 }, { "epoch": 76.06, "learning_rate": 1.7697149636617293e-05, "loss": 0.0024, "step": 316640 }, { "epoch": 76.06, "learning_rate": 1.7694409839127395e-05, "loss": 0.0014, "step": 316650 }, { "epoch": 76.06, "learning_rate": 1.769167020814077e-05, "loss": 0.0014, "step": 316660 }, { "epoch": 76.06, "learning_rate": 1.7688930743671537e-05, "loss": 0.0012, "step": 316670 }, { "epoch": 76.07, "learning_rate": 1.7686191445733842e-05, "loss": 0.0014, "step": 316680 }, { "epoch": 76.07, "learning_rate": 1.7683452314341763e-05, "loss": 0.0013, "step": 316690 }, { "epoch": 76.07, "learning_rate": 1.768071334950946e-05, "loss": 0.0013, "step": 316700 }, { "epoch": 76.07, "learning_rate": 1.7677974551251015e-05, "loss": 0.0013, "step": 316710 }, { "epoch": 76.08, "learning_rate": 1.7675235919580573e-05, "loss": 0.0014, "step": 316720 }, { "epoch": 76.08, "learning_rate": 1.7672497454512244e-05, "loss": 0.0016, "step": 316730 }, { "epoch": 76.08, "learning_rate": 1.7669759156060107e-05, "loss": 0.0012, "step": 316740 }, { "epoch": 76.08, "learning_rate": 1.766702102423832e-05, "loss": 0.0014, "step": 316750 }, { "epoch": 76.09, "learning_rate": 1.7664283059060964e-05, "loss": 0.0014, "step": 316760 }, { "epoch": 76.09, "learning_rate": 1.7661545260542178e-05, "loss": 0.0014, "step": 316770 }, { "epoch": 76.09, "learning_rate": 1.7658807628696046e-05, "loss": 0.0014, "step": 316780 }, { "epoch": 76.09, "learning_rate": 1.76560701635367e-05, "loss": 0.0015, "step": 316790 }, { "epoch": 76.09, "learning_rate": 1.7653332865078242e-05, "loss": 0.0065, "step": 316800 }, { "epoch": 76.1, "learning_rate": 1.7650595733334756e-05, "loss": 0.0015, "step": 316810 }, { "epoch": 76.1, "learning_rate": 1.764785876832039e-05, "loss": 0.0015, "step": 316820 }, { "epoch": 76.1, "learning_rate": 1.7645121970049215e-05, "loss": 0.0015, "step": 316830 }, { "epoch": 76.1, "learning_rate": 1.7642385338535367e-05, "loss": 0.0013, "step": 316840 }, { "epoch": 76.11, "learning_rate": 1.7639648873792918e-05, "loss": 0.0012, "step": 316850 }, { "epoch": 76.11, "learning_rate": 1.7636912575836006e-05, "loss": 0.0012, "step": 316860 }, { "epoch": 76.11, "learning_rate": 1.7634176444678703e-05, "loss": 0.0014, "step": 316870 }, { "epoch": 76.11, "learning_rate": 1.763144048033512e-05, "loss": 0.0014, "step": 316880 }, { "epoch": 76.11, "learning_rate": 1.7628704682819385e-05, "loss": 0.002, "step": 316890 }, { "epoch": 76.12, "learning_rate": 1.762596905214556e-05, "loss": 0.0014, "step": 316900 }, { "epoch": 76.12, "learning_rate": 1.7623233588327768e-05, "loss": 0.0012, "step": 316910 }, { "epoch": 76.12, "learning_rate": 1.7620498291380096e-05, "loss": 0.0014, "step": 316920 }, { "epoch": 76.12, "learning_rate": 1.7617763161316657e-05, "loss": 0.0014, "step": 316930 }, { "epoch": 76.13, "learning_rate": 1.761502819815154e-05, "loss": 0.0012, "step": 316940 }, { "epoch": 76.13, "learning_rate": 1.7612293401898822e-05, "loss": 0.0013, "step": 316950 }, { "epoch": 76.13, "learning_rate": 1.7609558772572632e-05, "loss": 0.0014, "step": 316960 }, { "epoch": 76.13, "learning_rate": 1.7606824310187024e-05, "loss": 0.0013, "step": 316970 }, { "epoch": 76.14, "learning_rate": 1.7604090014756136e-05, "loss": 0.0013, "step": 316980 }, { "epoch": 76.14, "learning_rate": 1.7601355886294023e-05, "loss": 0.0014, "step": 316990 }, { "epoch": 76.14, "learning_rate": 1.7598621924814806e-05, "loss": 0.0015, "step": 317000 }, { "epoch": 76.14, "learning_rate": 1.7595888130332566e-05, "loss": 0.0012, "step": 317010 }, { "epoch": 76.14, "learning_rate": 1.759315450286137e-05, "loss": 0.0013, "step": 317020 }, { "epoch": 76.15, "learning_rate": 1.7590421042415345e-05, "loss": 0.0013, "step": 317030 }, { "epoch": 76.15, "learning_rate": 1.758768774900854e-05, "loss": 0.0012, "step": 317040 }, { "epoch": 76.15, "learning_rate": 1.7584954622655088e-05, "loss": 0.0013, "step": 317050 }, { "epoch": 76.15, "learning_rate": 1.758222166336903e-05, "loss": 0.0013, "step": 317060 }, { "epoch": 76.16, "learning_rate": 1.7579488871164486e-05, "loss": 0.0013, "step": 317070 }, { "epoch": 76.16, "learning_rate": 1.757675624605553e-05, "loss": 0.0013, "step": 317080 }, { "epoch": 76.16, "learning_rate": 1.7574023788056226e-05, "loss": 0.0014, "step": 317090 }, { "epoch": 76.16, "learning_rate": 1.757129149718069e-05, "loss": 0.0027, "step": 317100 }, { "epoch": 76.16, "learning_rate": 1.7568559373442977e-05, "loss": 0.0012, "step": 317110 }, { "epoch": 76.17, "learning_rate": 1.7565827416857193e-05, "loss": 0.0013, "step": 317120 }, { "epoch": 76.17, "learning_rate": 1.7563095627437387e-05, "loss": 0.0013, "step": 317130 }, { "epoch": 76.17, "learning_rate": 1.7560364005197676e-05, "loss": 0.0019, "step": 317140 }, { "epoch": 76.17, "learning_rate": 1.7557632550152108e-05, "loss": 0.0014, "step": 317150 }, { "epoch": 76.18, "learning_rate": 1.7554901262314784e-05, "loss": 0.0012, "step": 317160 }, { "epoch": 76.18, "learning_rate": 1.7552170141699755e-05, "loss": 0.0022, "step": 317170 }, { "epoch": 76.18, "learning_rate": 1.7549439188321125e-05, "loss": 0.0013, "step": 317180 }, { "epoch": 76.18, "learning_rate": 1.7546708402192945e-05, "loss": 0.0014, "step": 317190 }, { "epoch": 76.19, "learning_rate": 1.75439777833293e-05, "loss": 0.0014, "step": 317200 }, { "epoch": 76.19, "learning_rate": 1.754124733174428e-05, "loss": 0.0013, "step": 317210 }, { "epoch": 76.19, "learning_rate": 1.7538517047451946e-05, "loss": 0.0013, "step": 317220 }, { "epoch": 76.19, "learning_rate": 1.7535786930466347e-05, "loss": 0.0013, "step": 317230 }, { "epoch": 76.19, "learning_rate": 1.7533056980801594e-05, "loss": 0.0014, "step": 317240 }, { "epoch": 76.2, "learning_rate": 1.753032719847172e-05, "loss": 0.0022, "step": 317250 }, { "epoch": 76.2, "learning_rate": 1.7527597583490822e-05, "loss": 0.0012, "step": 317260 }, { "epoch": 76.2, "learning_rate": 1.752486813587294e-05, "loss": 0.0014, "step": 317270 }, { "epoch": 76.2, "learning_rate": 1.7522138855632182e-05, "loss": 0.0016, "step": 317280 }, { "epoch": 76.21, "learning_rate": 1.751940974278259e-05, "loss": 0.0016, "step": 317290 }, { "epoch": 76.21, "learning_rate": 1.7516680797338215e-05, "loss": 0.0012, "step": 317300 }, { "epoch": 76.21, "learning_rate": 1.751395201931315e-05, "loss": 0.0015, "step": 317310 }, { "epoch": 76.21, "learning_rate": 1.751122340872144e-05, "loss": 0.0012, "step": 317320 }, { "epoch": 76.22, "learning_rate": 1.7508494965577167e-05, "loss": 0.0013, "step": 317330 }, { "epoch": 76.22, "learning_rate": 1.7505766689894364e-05, "loss": 0.0012, "step": 317340 }, { "epoch": 76.22, "learning_rate": 1.7503038581687136e-05, "loss": 0.0014, "step": 317350 }, { "epoch": 76.22, "learning_rate": 1.7500310640969496e-05, "loss": 0.0012, "step": 317360 }, { "epoch": 76.22, "learning_rate": 1.7497582867755548e-05, "loss": 0.0013, "step": 317370 }, { "epoch": 76.23, "learning_rate": 1.7494855262059323e-05, "loss": 0.0012, "step": 317380 }, { "epoch": 76.23, "learning_rate": 1.7492127823894872e-05, "loss": 0.0013, "step": 317390 }, { "epoch": 76.23, "learning_rate": 1.7489400553276282e-05, "loss": 0.0012, "step": 317400 }, { "epoch": 76.23, "learning_rate": 1.7486673450217577e-05, "loss": 0.0013, "step": 317410 }, { "epoch": 76.24, "learning_rate": 1.7483946514732845e-05, "loss": 0.0011, "step": 317420 }, { "epoch": 76.24, "learning_rate": 1.748121974683611e-05, "loss": 0.0013, "step": 317430 }, { "epoch": 76.24, "learning_rate": 1.7478493146541453e-05, "loss": 0.0014, "step": 317440 }, { "epoch": 76.24, "learning_rate": 1.74757667138629e-05, "loss": 0.0012, "step": 317450 }, { "epoch": 76.24, "learning_rate": 1.747304044881454e-05, "loss": 0.0013, "step": 317460 }, { "epoch": 76.25, "learning_rate": 1.747031435141037e-05, "loss": 0.0014, "step": 317470 }, { "epoch": 76.25, "learning_rate": 1.74675884216645e-05, "loss": 0.0014, "step": 317480 }, { "epoch": 76.25, "learning_rate": 1.746486265959093e-05, "loss": 0.0015, "step": 317490 }, { "epoch": 76.25, "learning_rate": 1.7462137065203747e-05, "loss": 0.0013, "step": 317500 }, { "epoch": 76.26, "learning_rate": 1.745941163851697e-05, "loss": 0.0014, "step": 317510 }, { "epoch": 76.26, "learning_rate": 1.745668637954467e-05, "loss": 0.0014, "step": 317520 }, { "epoch": 76.26, "learning_rate": 1.7453961288300863e-05, "loss": 0.0021, "step": 317530 }, { "epoch": 76.26, "learning_rate": 1.7451236364799626e-05, "loss": 0.0014, "step": 317540 }, { "epoch": 76.27, "learning_rate": 1.744851160905498e-05, "loss": 0.0012, "step": 317550 }, { "epoch": 76.27, "learning_rate": 1.744578702108099e-05, "loss": 0.0012, "step": 317560 }, { "epoch": 76.27, "learning_rate": 1.7443062600891663e-05, "loss": 0.0014, "step": 317570 }, { "epoch": 76.27, "learning_rate": 1.7440338348501088e-05, "loss": 0.0012, "step": 317580 }, { "epoch": 76.27, "learning_rate": 1.743761426392328e-05, "loss": 0.0012, "step": 317590 }, { "epoch": 76.28, "learning_rate": 1.743489034717226e-05, "loss": 0.0013, "step": 317600 }, { "epoch": 76.28, "learning_rate": 1.7432166598262107e-05, "loss": 0.0116, "step": 317610 }, { "epoch": 76.28, "learning_rate": 1.742944301720682e-05, "loss": 0.0013, "step": 317620 }, { "epoch": 76.28, "learning_rate": 1.7426719604020474e-05, "loss": 0.0013, "step": 317630 }, { "epoch": 76.29, "learning_rate": 1.742399635871707e-05, "loss": 0.0013, "step": 317640 }, { "epoch": 76.29, "learning_rate": 1.7421273281310685e-05, "loss": 0.0014, "step": 317650 }, { "epoch": 76.29, "learning_rate": 1.7418550371815323e-05, "loss": 0.0013, "step": 317660 }, { "epoch": 76.29, "learning_rate": 1.7415827630245006e-05, "loss": 0.0014, "step": 317670 }, { "epoch": 76.3, "learning_rate": 1.741310505661381e-05, "loss": 0.0015, "step": 317680 }, { "epoch": 76.3, "learning_rate": 1.741038265093572e-05, "loss": 0.0013, "step": 317690 }, { "epoch": 76.3, "learning_rate": 1.7407660413224806e-05, "loss": 0.0012, "step": 317700 }, { "epoch": 76.3, "learning_rate": 1.740493834349507e-05, "loss": 0.0066, "step": 317710 }, { "epoch": 76.3, "learning_rate": 1.7402216441760572e-05, "loss": 0.0013, "step": 317720 }, { "epoch": 76.31, "learning_rate": 1.739949470803532e-05, "loss": 0.0012, "step": 317730 }, { "epoch": 76.31, "learning_rate": 1.7396773142333328e-05, "loss": 0.0012, "step": 317740 }, { "epoch": 76.31, "learning_rate": 1.7394051744668656e-05, "loss": 0.0017, "step": 317750 }, { "epoch": 76.31, "learning_rate": 1.73913305150553e-05, "loss": 0.0014, "step": 317760 }, { "epoch": 76.32, "learning_rate": 1.7388609453507294e-05, "loss": 0.0014, "step": 317770 }, { "epoch": 76.32, "learning_rate": 1.738588856003869e-05, "loss": 0.0013, "step": 317780 }, { "epoch": 76.32, "learning_rate": 1.7383167834663467e-05, "loss": 0.0014, "step": 317790 }, { "epoch": 76.32, "learning_rate": 1.738044727739569e-05, "loss": 0.0013, "step": 317800 }, { "epoch": 76.32, "learning_rate": 1.7377726888249346e-05, "loss": 0.0044, "step": 317810 }, { "epoch": 76.33, "learning_rate": 1.737500666723848e-05, "loss": 0.0015, "step": 317820 }, { "epoch": 76.33, "learning_rate": 1.737228661437709e-05, "loss": 0.0015, "step": 317830 }, { "epoch": 76.33, "learning_rate": 1.7369566729679227e-05, "loss": 0.0013, "step": 317840 }, { "epoch": 76.33, "learning_rate": 1.7366847013158867e-05, "loss": 0.0013, "step": 317850 }, { "epoch": 76.34, "learning_rate": 1.736412746483007e-05, "loss": 0.0013, "step": 317860 }, { "epoch": 76.34, "learning_rate": 1.7361408084706833e-05, "loss": 0.0011, "step": 317870 }, { "epoch": 76.34, "learning_rate": 1.7358688872803153e-05, "loss": 0.0014, "step": 317880 }, { "epoch": 76.34, "learning_rate": 1.7355969829133084e-05, "loss": 0.0013, "step": 317890 }, { "epoch": 76.35, "learning_rate": 1.73532509537106e-05, "loss": 0.0012, "step": 317900 }, { "epoch": 76.35, "learning_rate": 1.735053224654975e-05, "loss": 0.0012, "step": 317910 }, { "epoch": 76.35, "learning_rate": 1.7347813707664513e-05, "loss": 0.0013, "step": 317920 }, { "epoch": 76.35, "learning_rate": 1.7345095337068935e-05, "loss": 0.0013, "step": 317930 }, { "epoch": 76.35, "learning_rate": 1.7342377134777005e-05, "loss": 0.0013, "step": 317940 }, { "epoch": 76.36, "learning_rate": 1.7339659100802725e-05, "loss": 0.0013, "step": 317950 }, { "epoch": 76.36, "learning_rate": 1.7336941235160126e-05, "loss": 0.0012, "step": 317960 }, { "epoch": 76.36, "learning_rate": 1.733422353786319e-05, "loss": 0.0013, "step": 317970 }, { "epoch": 76.36, "learning_rate": 1.7331506008925957e-05, "loss": 0.0012, "step": 317980 }, { "epoch": 76.37, "learning_rate": 1.73287886483624e-05, "loss": 0.0013, "step": 317990 }, { "epoch": 76.37, "learning_rate": 1.7326071456186555e-05, "loss": 0.0014, "step": 318000 }, { "epoch": 76.37, "learning_rate": 1.732335443241241e-05, "loss": 0.0012, "step": 318010 }, { "epoch": 76.37, "learning_rate": 1.732063757705395e-05, "loss": 0.0096, "step": 318020 }, { "epoch": 76.38, "learning_rate": 1.7317920890125217e-05, "loss": 0.0014, "step": 318030 }, { "epoch": 76.38, "learning_rate": 1.7315204371640175e-05, "loss": 0.0014, "step": 318040 }, { "epoch": 76.38, "learning_rate": 1.731248802161286e-05, "loss": 0.0013, "step": 318050 }, { "epoch": 76.38, "learning_rate": 1.7309771840057244e-05, "loss": 0.0014, "step": 318060 }, { "epoch": 76.38, "learning_rate": 1.7307055826987346e-05, "loss": 0.0057, "step": 318070 }, { "epoch": 76.39, "learning_rate": 1.730433998241714e-05, "loss": 0.0013, "step": 318080 }, { "epoch": 76.39, "learning_rate": 1.7301624306360642e-05, "loss": 0.0012, "step": 318090 }, { "epoch": 76.39, "learning_rate": 1.729890879883186e-05, "loss": 0.0013, "step": 318100 }, { "epoch": 76.39, "learning_rate": 1.7296193459844758e-05, "loss": 0.0016, "step": 318110 }, { "epoch": 76.4, "learning_rate": 1.7293478289413366e-05, "loss": 0.0014, "step": 318120 }, { "epoch": 76.4, "learning_rate": 1.7290763287551642e-05, "loss": 0.0014, "step": 318130 }, { "epoch": 76.4, "learning_rate": 1.728804845427362e-05, "loss": 0.0013, "step": 318140 }, { "epoch": 76.4, "learning_rate": 1.728533378959325e-05, "loss": 0.0013, "step": 318150 }, { "epoch": 76.4, "learning_rate": 1.7282619293524555e-05, "loss": 0.0013, "step": 318160 }, { "epoch": 76.41, "learning_rate": 1.727990496608152e-05, "loss": 0.0012, "step": 318170 }, { "epoch": 76.41, "learning_rate": 1.727719080727811e-05, "loss": 0.0015, "step": 318180 }, { "epoch": 76.41, "learning_rate": 1.727447681712835e-05, "loss": 0.0013, "step": 318190 }, { "epoch": 76.41, "learning_rate": 1.7271762995646185e-05, "loss": 0.0013, "step": 318200 }, { "epoch": 76.42, "learning_rate": 1.726904934284565e-05, "loss": 0.0013, "step": 318210 }, { "epoch": 76.42, "learning_rate": 1.7266335858740694e-05, "loss": 0.0014, "step": 318220 }, { "epoch": 76.42, "learning_rate": 1.7263622543345332e-05, "loss": 0.0013, "step": 318230 }, { "epoch": 76.42, "learning_rate": 1.726090939667353e-05, "loss": 0.0015, "step": 318240 }, { "epoch": 76.43, "learning_rate": 1.7258196418739258e-05, "loss": 0.0012, "step": 318250 }, { "epoch": 76.43, "learning_rate": 1.7255483609556538e-05, "loss": 0.0013, "step": 318260 }, { "epoch": 76.43, "learning_rate": 1.725277096913931e-05, "loss": 0.0013, "step": 318270 }, { "epoch": 76.43, "learning_rate": 1.7250058497501587e-05, "loss": 0.0012, "step": 318280 }, { "epoch": 76.43, "learning_rate": 1.7247346194657322e-05, "loss": 0.0012, "step": 318290 }, { "epoch": 76.44, "learning_rate": 1.7244634060620522e-05, "loss": 0.0014, "step": 318300 }, { "epoch": 76.44, "learning_rate": 1.7241922095405155e-05, "loss": 0.0013, "step": 318310 }, { "epoch": 76.44, "learning_rate": 1.7239210299025178e-05, "loss": 0.0012, "step": 318320 }, { "epoch": 76.44, "learning_rate": 1.7236498671494606e-05, "loss": 0.0013, "step": 318330 }, { "epoch": 76.45, "learning_rate": 1.7233787212827367e-05, "loss": 0.0017, "step": 318340 }, { "epoch": 76.45, "learning_rate": 1.7231075923037488e-05, "loss": 0.0014, "step": 318350 }, { "epoch": 76.45, "learning_rate": 1.7228364802138897e-05, "loss": 0.0014, "step": 318360 }, { "epoch": 76.45, "learning_rate": 1.7225653850145605e-05, "loss": 0.0014, "step": 318370 }, { "epoch": 76.46, "learning_rate": 1.7222943067071557e-05, "loss": 0.0012, "step": 318380 }, { "epoch": 76.46, "learning_rate": 1.7220232452930725e-05, "loss": 0.0013, "step": 318390 }, { "epoch": 76.46, "learning_rate": 1.7217522007737106e-05, "loss": 0.0014, "step": 318400 }, { "epoch": 76.46, "learning_rate": 1.7214811731504643e-05, "loss": 0.0012, "step": 318410 }, { "epoch": 76.46, "learning_rate": 1.7212101624247328e-05, "loss": 0.001, "step": 318420 }, { "epoch": 76.47, "learning_rate": 1.72093916859791e-05, "loss": 0.0012, "step": 318430 }, { "epoch": 76.47, "learning_rate": 1.720668191671395e-05, "loss": 0.0012, "step": 318440 }, { "epoch": 76.47, "learning_rate": 1.7203972316465844e-05, "loss": 0.0013, "step": 318450 }, { "epoch": 76.47, "learning_rate": 1.720126288524872e-05, "loss": 0.0012, "step": 318460 }, { "epoch": 76.48, "learning_rate": 1.7198553623076575e-05, "loss": 0.0013, "step": 318470 }, { "epoch": 76.48, "learning_rate": 1.7195844529963344e-05, "loss": 0.0013, "step": 318480 }, { "epoch": 76.48, "learning_rate": 1.7193135605923022e-05, "loss": 0.0013, "step": 318490 }, { "epoch": 76.48, "learning_rate": 1.7190426850969538e-05, "loss": 0.005, "step": 318500 }, { "epoch": 76.48, "learning_rate": 1.718771826511688e-05, "loss": 0.0027, "step": 318510 }, { "epoch": 76.49, "learning_rate": 1.7185009848379e-05, "loss": 0.0014, "step": 318520 }, { "epoch": 76.49, "learning_rate": 1.7182301600769833e-05, "loss": 0.0013, "step": 318530 }, { "epoch": 76.49, "learning_rate": 1.7179593522303383e-05, "loss": 0.0013, "step": 318540 }, { "epoch": 76.49, "learning_rate": 1.717688561299356e-05, "loss": 0.0012, "step": 318550 }, { "epoch": 76.5, "learning_rate": 1.7174177872854356e-05, "loss": 0.0013, "step": 318560 }, { "epoch": 76.5, "learning_rate": 1.7171470301899704e-05, "loss": 0.0321, "step": 318570 }, { "epoch": 76.5, "learning_rate": 1.716876290014358e-05, "loss": 0.0013, "step": 318580 }, { "epoch": 76.5, "learning_rate": 1.716605566759993e-05, "loss": 0.0014, "step": 318590 }, { "epoch": 76.51, "learning_rate": 1.7163348604282686e-05, "loss": 0.0012, "step": 318600 }, { "epoch": 76.51, "learning_rate": 1.7160641710205832e-05, "loss": 0.0013, "step": 318610 }, { "epoch": 76.51, "learning_rate": 1.7157934985383294e-05, "loss": 0.0013, "step": 318620 }, { "epoch": 76.51, "learning_rate": 1.7155228429829046e-05, "loss": 0.0013, "step": 318630 }, { "epoch": 76.51, "learning_rate": 1.7152522043557008e-05, "loss": 0.0013, "step": 318640 }, { "epoch": 76.52, "learning_rate": 1.714981582658116e-05, "loss": 0.0013, "step": 318650 }, { "epoch": 76.52, "learning_rate": 1.7147109778915427e-05, "loss": 0.0013, "step": 318660 }, { "epoch": 76.52, "learning_rate": 1.714440390057378e-05, "loss": 0.0014, "step": 318670 }, { "epoch": 76.52, "learning_rate": 1.7141698191570128e-05, "loss": 0.0014, "step": 318680 }, { "epoch": 76.53, "learning_rate": 1.7138992651918455e-05, "loss": 0.0028, "step": 318690 }, { "epoch": 76.53, "learning_rate": 1.713628728163268e-05, "loss": 0.0013, "step": 318700 }, { "epoch": 76.53, "learning_rate": 1.7133582080726745e-05, "loss": 0.0026, "step": 318710 }, { "epoch": 76.53, "learning_rate": 1.7130877049214626e-05, "loss": 0.0014, "step": 318720 }, { "epoch": 76.54, "learning_rate": 1.7128172187110235e-05, "loss": 0.0014, "step": 318730 }, { "epoch": 76.54, "learning_rate": 1.712546749442751e-05, "loss": 0.0014, "step": 318740 }, { "epoch": 76.54, "learning_rate": 1.7122762971180412e-05, "loss": 0.0015, "step": 318750 }, { "epoch": 76.54, "learning_rate": 1.7120058617382855e-05, "loss": 0.0014, "step": 318760 }, { "epoch": 76.54, "learning_rate": 1.7117354433048803e-05, "loss": 0.0014, "step": 318770 }, { "epoch": 76.55, "learning_rate": 1.7114650418192167e-05, "loss": 0.0014, "step": 318780 }, { "epoch": 76.55, "learning_rate": 1.711194657282692e-05, "loss": 0.0013, "step": 318790 }, { "epoch": 76.55, "learning_rate": 1.710924289696697e-05, "loss": 0.0013, "step": 318800 }, { "epoch": 76.55, "learning_rate": 1.710653939062624e-05, "loss": 0.0018, "step": 318810 }, { "epoch": 76.56, "learning_rate": 1.7103836053818694e-05, "loss": 0.0015, "step": 318820 }, { "epoch": 76.56, "learning_rate": 1.710113288655824e-05, "loss": 0.0013, "step": 318830 }, { "epoch": 76.56, "learning_rate": 1.7098429888858843e-05, "loss": 0.0016, "step": 318840 }, { "epoch": 76.56, "learning_rate": 1.709572706073439e-05, "loss": 0.0014, "step": 318850 }, { "epoch": 76.56, "learning_rate": 1.7093024402198853e-05, "loss": 0.0014, "step": 318860 }, { "epoch": 76.57, "learning_rate": 1.7090321913266145e-05, "loss": 0.0015, "step": 318870 }, { "epoch": 76.57, "learning_rate": 1.7087619593950173e-05, "loss": 0.0014, "step": 318880 }, { "epoch": 76.57, "learning_rate": 1.7084917444264904e-05, "loss": 0.0012, "step": 318890 }, { "epoch": 76.57, "learning_rate": 1.7082215464224228e-05, "loss": 0.0015, "step": 318900 }, { "epoch": 76.58, "learning_rate": 1.7079513653842107e-05, "loss": 0.0015, "step": 318910 }, { "epoch": 76.58, "learning_rate": 1.7076812013132428e-05, "loss": 0.0014, "step": 318920 }, { "epoch": 76.58, "learning_rate": 1.707411054210915e-05, "loss": 0.0013, "step": 318930 }, { "epoch": 76.58, "learning_rate": 1.7071409240786183e-05, "loss": 0.0013, "step": 318940 }, { "epoch": 76.59, "learning_rate": 1.7068708109177438e-05, "loss": 0.0014, "step": 318950 }, { "epoch": 76.59, "learning_rate": 1.7066007147296842e-05, "loss": 0.0012, "step": 318960 }, { "epoch": 76.59, "learning_rate": 1.7063306355158336e-05, "loss": 0.0013, "step": 318970 }, { "epoch": 76.59, "learning_rate": 1.706060573277581e-05, "loss": 0.0014, "step": 318980 }, { "epoch": 76.59, "learning_rate": 1.705790528016321e-05, "loss": 0.0031, "step": 318990 }, { "epoch": 76.6, "learning_rate": 1.7055204997334427e-05, "loss": 0.0013, "step": 319000 }, { "epoch": 76.6, "learning_rate": 1.705250488430341e-05, "loss": 0.0013, "step": 319010 }, { "epoch": 76.6, "learning_rate": 1.704980494108404e-05, "loss": 0.0014, "step": 319020 }, { "epoch": 76.6, "learning_rate": 1.704710516769027e-05, "loss": 0.0014, "step": 319030 }, { "epoch": 76.61, "learning_rate": 1.704440556413598e-05, "loss": 0.0013, "step": 319040 }, { "epoch": 76.61, "learning_rate": 1.7041706130435115e-05, "loss": 0.0014, "step": 319050 }, { "epoch": 76.61, "learning_rate": 1.7039006866601553e-05, "loss": 0.0013, "step": 319060 }, { "epoch": 76.61, "learning_rate": 1.7036307772649242e-05, "loss": 0.0013, "step": 319070 }, { "epoch": 76.62, "learning_rate": 1.7033608848592058e-05, "loss": 0.0012, "step": 319080 }, { "epoch": 76.62, "learning_rate": 1.7030910094443954e-05, "loss": 0.0012, "step": 319090 }, { "epoch": 76.62, "learning_rate": 1.7028211510218804e-05, "loss": 0.0014, "step": 319100 }, { "epoch": 76.62, "learning_rate": 1.7025513095930517e-05, "loss": 0.0012, "step": 319110 }, { "epoch": 76.62, "learning_rate": 1.7022814851593028e-05, "loss": 0.0013, "step": 319120 }, { "epoch": 76.63, "learning_rate": 1.7020116777220207e-05, "loss": 0.0013, "step": 319130 }, { "epoch": 76.63, "learning_rate": 1.7017418872826002e-05, "loss": 0.0014, "step": 319140 }, { "epoch": 76.63, "learning_rate": 1.7014721138424278e-05, "loss": 0.0015, "step": 319150 }, { "epoch": 76.63, "learning_rate": 1.701202357402897e-05, "loss": 0.0012, "step": 319160 }, { "epoch": 76.64, "learning_rate": 1.7009326179653968e-05, "loss": 0.0014, "step": 319170 }, { "epoch": 76.64, "learning_rate": 1.7006628955313157e-05, "loss": 0.0014, "step": 319180 }, { "epoch": 76.64, "learning_rate": 1.7003931901020482e-05, "loss": 0.0012, "step": 319190 }, { "epoch": 76.64, "learning_rate": 1.700123501678979e-05, "loss": 0.0015, "step": 319200 }, { "epoch": 76.64, "learning_rate": 1.699853830263503e-05, "loss": 0.0015, "step": 319210 }, { "epoch": 76.65, "learning_rate": 1.6995841758570063e-05, "loss": 0.0013, "step": 319220 }, { "epoch": 76.65, "learning_rate": 1.6993145384608823e-05, "loss": 0.0013, "step": 319230 }, { "epoch": 76.65, "learning_rate": 1.6990449180765183e-05, "loss": 0.0013, "step": 319240 }, { "epoch": 76.65, "learning_rate": 1.6987753147053033e-05, "loss": 0.0016, "step": 319250 }, { "epoch": 76.66, "learning_rate": 1.6985057283486288e-05, "loss": 0.0014, "step": 319260 }, { "epoch": 76.66, "learning_rate": 1.698236159007882e-05, "loss": 0.0015, "step": 319270 }, { "epoch": 76.66, "learning_rate": 1.6979666066844537e-05, "loss": 0.0014, "step": 319280 }, { "epoch": 76.66, "learning_rate": 1.6976970713797346e-05, "loss": 0.0012, "step": 319290 }, { "epoch": 76.67, "learning_rate": 1.697427553095111e-05, "loss": 0.0013, "step": 319300 }, { "epoch": 76.67, "learning_rate": 1.6971580518319753e-05, "loss": 0.0014, "step": 319310 }, { "epoch": 76.67, "learning_rate": 1.696888567591712e-05, "loss": 0.0015, "step": 319320 }, { "epoch": 76.67, "learning_rate": 1.6966191003757153e-05, "loss": 0.0013, "step": 319330 }, { "epoch": 76.67, "learning_rate": 1.6963496501853693e-05, "loss": 0.0014, "step": 319340 }, { "epoch": 76.68, "learning_rate": 1.6960802170220663e-05, "loss": 0.0012, "step": 319350 }, { "epoch": 76.68, "learning_rate": 1.695810800887192e-05, "loss": 0.0014, "step": 319360 }, { "epoch": 76.68, "learning_rate": 1.6955414017821382e-05, "loss": 0.0013, "step": 319370 }, { "epoch": 76.68, "learning_rate": 1.6952720197082916e-05, "loss": 0.0013, "step": 319380 }, { "epoch": 76.69, "learning_rate": 1.695002654667039e-05, "loss": 0.0014, "step": 319390 }, { "epoch": 76.69, "learning_rate": 1.694733306659772e-05, "loss": 0.0014, "step": 319400 }, { "epoch": 76.69, "learning_rate": 1.6944639756878755e-05, "loss": 0.0015, "step": 319410 }, { "epoch": 76.69, "learning_rate": 1.694194661752741e-05, "loss": 0.0014, "step": 319420 }, { "epoch": 76.7, "learning_rate": 1.693925364855753e-05, "loss": 0.0014, "step": 319430 }, { "epoch": 76.7, "learning_rate": 1.693656084998303e-05, "loss": 0.0012, "step": 319440 }, { "epoch": 76.7, "learning_rate": 1.6933868221817773e-05, "loss": 0.0015, "step": 319450 }, { "epoch": 76.7, "learning_rate": 1.6931175764075618e-05, "loss": 0.0034, "step": 319460 }, { "epoch": 76.7, "learning_rate": 1.6928483476770474e-05, "loss": 0.0014, "step": 319470 }, { "epoch": 76.71, "learning_rate": 1.6925791359916187e-05, "loss": 0.0012, "step": 319480 }, { "epoch": 76.71, "learning_rate": 1.6923099413526667e-05, "loss": 0.0016, "step": 319490 }, { "epoch": 76.71, "learning_rate": 1.6920407637615754e-05, "loss": 0.0013, "step": 319500 }, { "epoch": 76.71, "learning_rate": 1.691771603219735e-05, "loss": 0.0012, "step": 319510 }, { "epoch": 76.72, "learning_rate": 1.6915024597285312e-05, "loss": 0.0014, "step": 319520 }, { "epoch": 76.72, "learning_rate": 1.6912333332893497e-05, "loss": 0.0014, "step": 319530 }, { "epoch": 76.72, "learning_rate": 1.6909642239035818e-05, "loss": 0.0012, "step": 319540 }, { "epoch": 76.72, "learning_rate": 1.6906951315726095e-05, "loss": 0.0036, "step": 319550 }, { "epoch": 76.72, "learning_rate": 1.6904260562978237e-05, "loss": 0.0016, "step": 319560 }, { "epoch": 76.73, "learning_rate": 1.6901569980806087e-05, "loss": 0.0014, "step": 319570 }, { "epoch": 76.73, "learning_rate": 1.689887956922353e-05, "loss": 0.0015, "step": 319580 }, { "epoch": 76.73, "learning_rate": 1.6896189328244416e-05, "loss": 0.0014, "step": 319590 }, { "epoch": 76.73, "learning_rate": 1.689349925788261e-05, "loss": 0.0013, "step": 319600 }, { "epoch": 76.74, "learning_rate": 1.689080935815201e-05, "loss": 0.0014, "step": 319610 }, { "epoch": 76.74, "learning_rate": 1.6888119629066434e-05, "loss": 0.0012, "step": 319620 }, { "epoch": 76.74, "learning_rate": 1.6885430070639784e-05, "loss": 0.0017, "step": 319630 }, { "epoch": 76.74, "learning_rate": 1.688274068288589e-05, "loss": 0.0014, "step": 319640 }, { "epoch": 76.75, "learning_rate": 1.688005146581864e-05, "loss": 0.0014, "step": 319650 }, { "epoch": 76.75, "learning_rate": 1.6877362419451886e-05, "loss": 0.0018, "step": 319660 }, { "epoch": 76.75, "learning_rate": 1.6874673543799468e-05, "loss": 0.0013, "step": 319670 }, { "epoch": 76.75, "learning_rate": 1.687198483887527e-05, "loss": 0.0015, "step": 319680 }, { "epoch": 76.75, "learning_rate": 1.6869296304693127e-05, "loss": 0.0014, "step": 319690 }, { "epoch": 76.76, "learning_rate": 1.6866607941266922e-05, "loss": 0.0013, "step": 319700 }, { "epoch": 76.76, "learning_rate": 1.686391974861048e-05, "loss": 0.0014, "step": 319710 }, { "epoch": 76.76, "learning_rate": 1.6861231726737686e-05, "loss": 0.0014, "step": 319720 }, { "epoch": 76.76, "learning_rate": 1.6858543875662385e-05, "loss": 0.0018, "step": 319730 }, { "epoch": 76.77, "learning_rate": 1.685585619539841e-05, "loss": 0.0012, "step": 319740 }, { "epoch": 76.77, "learning_rate": 1.6853168685959643e-05, "loss": 0.0014, "step": 319750 }, { "epoch": 76.77, "learning_rate": 1.685048134735991e-05, "loss": 0.0014, "step": 319760 }, { "epoch": 76.77, "learning_rate": 1.6847794179613084e-05, "loss": 0.0012, "step": 319770 }, { "epoch": 76.78, "learning_rate": 1.6845107182732987e-05, "loss": 0.0015, "step": 319780 }, { "epoch": 76.78, "learning_rate": 1.6842420356733507e-05, "loss": 0.0015, "step": 319790 }, { "epoch": 76.78, "learning_rate": 1.6839733701628447e-05, "loss": 0.0014, "step": 319800 }, { "epoch": 76.78, "learning_rate": 1.6837047217431694e-05, "loss": 0.0013, "step": 319810 }, { "epoch": 76.78, "learning_rate": 1.6834360904157083e-05, "loss": 0.0013, "step": 319820 }, { "epoch": 76.79, "learning_rate": 1.6831674761818433e-05, "loss": 0.0014, "step": 319830 }, { "epoch": 76.79, "learning_rate": 1.6828988790429623e-05, "loss": 0.0013, "step": 319840 }, { "epoch": 76.79, "learning_rate": 1.6826302990004466e-05, "loss": 0.0014, "step": 319850 }, { "epoch": 76.79, "learning_rate": 1.6823617360556836e-05, "loss": 0.0013, "step": 319860 }, { "epoch": 76.8, "learning_rate": 1.682093190210055e-05, "loss": 0.0012, "step": 319870 }, { "epoch": 76.8, "learning_rate": 1.681824661464947e-05, "loss": 0.0013, "step": 319880 }, { "epoch": 76.8, "learning_rate": 1.681556149821741e-05, "loss": 0.0013, "step": 319890 }, { "epoch": 76.8, "learning_rate": 1.6812876552818236e-05, "loss": 0.0037, "step": 319900 }, { "epoch": 76.8, "learning_rate": 1.6810191778465755e-05, "loss": 0.0012, "step": 319910 }, { "epoch": 76.81, "learning_rate": 1.6807507175173827e-05, "loss": 0.0013, "step": 319920 }, { "epoch": 76.81, "learning_rate": 1.68048227429563e-05, "loss": 0.0014, "step": 319930 }, { "epoch": 76.81, "learning_rate": 1.6802138481826978e-05, "loss": 0.0013, "step": 319940 }, { "epoch": 76.81, "learning_rate": 1.679945439179973e-05, "loss": 0.0018, "step": 319950 }, { "epoch": 76.82, "learning_rate": 1.6796770472888374e-05, "loss": 0.0013, "step": 319960 }, { "epoch": 76.82, "learning_rate": 1.6794086725106716e-05, "loss": 0.0014, "step": 319970 }, { "epoch": 76.82, "learning_rate": 1.679140314846863e-05, "loss": 0.0014, "step": 319980 }, { "epoch": 76.82, "learning_rate": 1.678871974298792e-05, "loss": 0.0015, "step": 319990 }, { "epoch": 76.83, "learning_rate": 1.6786036508678437e-05, "loss": 0.0013, "step": 320000 }, { "epoch": 76.83, "learning_rate": 1.678335344555399e-05, "loss": 0.0014, "step": 320010 }, { "epoch": 76.83, "learning_rate": 1.6780670553628423e-05, "loss": 0.0013, "step": 320020 }, { "epoch": 76.83, "learning_rate": 1.6777987832915566e-05, "loss": 0.0014, "step": 320030 }, { "epoch": 76.83, "learning_rate": 1.677530528342922e-05, "loss": 0.0012, "step": 320040 }, { "epoch": 76.84, "learning_rate": 1.6772622905183243e-05, "loss": 0.0015, "step": 320050 }, { "epoch": 76.84, "learning_rate": 1.6769940698191426e-05, "loss": 0.0014, "step": 320060 }, { "epoch": 76.84, "learning_rate": 1.6767258662467632e-05, "loss": 0.0013, "step": 320070 }, { "epoch": 76.84, "learning_rate": 1.676457679802565e-05, "loss": 0.0015, "step": 320080 }, { "epoch": 76.85, "learning_rate": 1.6761895104879327e-05, "loss": 0.0014, "step": 320090 }, { "epoch": 76.85, "learning_rate": 1.6759213583042484e-05, "loss": 0.0015, "step": 320100 }, { "epoch": 76.85, "learning_rate": 1.675653223252891e-05, "loss": 0.0015, "step": 320110 }, { "epoch": 76.85, "learning_rate": 1.675385105335246e-05, "loss": 0.0012, "step": 320120 }, { "epoch": 76.86, "learning_rate": 1.6751170045526928e-05, "loss": 0.0015, "step": 320130 }, { "epoch": 76.86, "learning_rate": 1.674848920906616e-05, "loss": 0.0012, "step": 320140 }, { "epoch": 76.86, "learning_rate": 1.674580854398394e-05, "loss": 0.0014, "step": 320150 }, { "epoch": 76.86, "learning_rate": 1.674312805029411e-05, "loss": 0.0013, "step": 320160 }, { "epoch": 76.86, "learning_rate": 1.6740447728010468e-05, "loss": 0.0014, "step": 320170 }, { "epoch": 76.87, "learning_rate": 1.673776757714685e-05, "loss": 0.0013, "step": 320180 }, { "epoch": 76.87, "learning_rate": 1.6735087597717035e-05, "loss": 0.0012, "step": 320190 }, { "epoch": 76.87, "learning_rate": 1.6732407789734884e-05, "loss": 0.0014, "step": 320200 }, { "epoch": 76.87, "learning_rate": 1.672972815321416e-05, "loss": 0.0014, "step": 320210 }, { "epoch": 76.88, "learning_rate": 1.6727048688168688e-05, "loss": 0.0014, "step": 320220 }, { "epoch": 76.88, "learning_rate": 1.6724369394612312e-05, "loss": 0.002, "step": 320230 }, { "epoch": 76.88, "learning_rate": 1.6721690272558803e-05, "loss": 0.0014, "step": 320240 }, { "epoch": 76.88, "learning_rate": 1.6719011322021978e-05, "loss": 0.0014, "step": 320250 }, { "epoch": 76.88, "learning_rate": 1.671633254301565e-05, "loss": 0.0015, "step": 320260 }, { "epoch": 76.89, "learning_rate": 1.6713653935553613e-05, "loss": 0.0014, "step": 320270 }, { "epoch": 76.89, "learning_rate": 1.67109754996497e-05, "loss": 0.0043, "step": 320280 }, { "epoch": 76.89, "learning_rate": 1.6708297235317678e-05, "loss": 0.0012, "step": 320290 }, { "epoch": 76.89, "learning_rate": 1.670561914257139e-05, "loss": 0.0012, "step": 320300 }, { "epoch": 76.9, "learning_rate": 1.6702941221424612e-05, "loss": 0.0013, "step": 320310 }, { "epoch": 76.9, "learning_rate": 1.670026347189114e-05, "loss": 0.0013, "step": 320320 }, { "epoch": 76.9, "learning_rate": 1.6697585893984807e-05, "loss": 0.0016, "step": 320330 }, { "epoch": 76.9, "learning_rate": 1.6694908487719372e-05, "loss": 0.0013, "step": 320340 }, { "epoch": 76.91, "learning_rate": 1.6692231253108682e-05, "loss": 0.0013, "step": 320350 }, { "epoch": 76.91, "learning_rate": 1.668955419016649e-05, "loss": 0.0013, "step": 320360 }, { "epoch": 76.91, "learning_rate": 1.6686877298906633e-05, "loss": 0.0014, "step": 320370 }, { "epoch": 76.91, "learning_rate": 1.6684200579342884e-05, "loss": 0.0014, "step": 320380 }, { "epoch": 76.91, "learning_rate": 1.668152403148903e-05, "loss": 0.0014, "step": 320390 }, { "epoch": 76.92, "learning_rate": 1.6678847655358897e-05, "loss": 0.0015, "step": 320400 }, { "epoch": 76.92, "learning_rate": 1.667617145096625e-05, "loss": 0.0014, "step": 320410 }, { "epoch": 76.92, "learning_rate": 1.6673495418324902e-05, "loss": 0.0013, "step": 320420 }, { "epoch": 76.92, "learning_rate": 1.6670819557448624e-05, "loss": 0.0013, "step": 320430 }, { "epoch": 76.93, "learning_rate": 1.6668143868351237e-05, "loss": 0.0014, "step": 320440 }, { "epoch": 76.93, "learning_rate": 1.6665468351046514e-05, "loss": 0.0012, "step": 320450 }, { "epoch": 76.93, "learning_rate": 1.6662793005548232e-05, "loss": 0.0013, "step": 320460 }, { "epoch": 76.93, "learning_rate": 1.666011783187021e-05, "loss": 0.0013, "step": 320470 }, { "epoch": 76.94, "learning_rate": 1.66574428300262e-05, "loss": 0.0013, "step": 320480 }, { "epoch": 76.94, "learning_rate": 1.6654768000030006e-05, "loss": 0.0013, "step": 320490 }, { "epoch": 76.94, "learning_rate": 1.6652093341895437e-05, "loss": 0.0012, "step": 320500 }, { "epoch": 76.94, "learning_rate": 1.664941885563624e-05, "loss": 0.0014, "step": 320510 }, { "epoch": 76.94, "learning_rate": 1.6646744541266235e-05, "loss": 0.0013, "step": 320520 }, { "epoch": 76.95, "learning_rate": 1.664407039879917e-05, "loss": 0.0014, "step": 320530 }, { "epoch": 76.95, "learning_rate": 1.6641396428248862e-05, "loss": 0.0013, "step": 320540 }, { "epoch": 76.95, "learning_rate": 1.663872262962906e-05, "loss": 0.0014, "step": 320550 }, { "epoch": 77.0, "learning_rate": 1.6636049002953575e-05, "loss": 0.0012, "step": 320560 }, { "epoch": 77.0, "learning_rate": 1.6633375548236157e-05, "loss": 0.0014, "step": 320570 }, { "epoch": 77.01, "learning_rate": 1.6630702265490618e-05, "loss": 0.0012, "step": 320580 }, { "epoch": 77.01, "learning_rate": 1.6628029154730697e-05, "loss": 0.0013, "step": 320590 }, { "epoch": 77.01, "learning_rate": 1.662535621597021e-05, "loss": 0.0013, "step": 320600 }, { "epoch": 77.01, "learning_rate": 1.662268344922292e-05, "loss": 0.0013, "step": 320610 }, { "epoch": 77.02, "learning_rate": 1.6620010854502583e-05, "loss": 0.0013, "step": 320620 }, { "epoch": 77.02, "learning_rate": 1.6617338431823005e-05, "loss": 0.0013, "step": 320630 }, { "epoch": 77.02, "learning_rate": 1.6614666181197924e-05, "loss": 0.0016, "step": 320640 }, { "epoch": 77.02, "learning_rate": 1.661199410264115e-05, "loss": 0.0012, "step": 320650 }, { "epoch": 77.02, "learning_rate": 1.660932219616642e-05, "loss": 0.0012, "step": 320660 }, { "epoch": 77.03, "learning_rate": 1.6606650461787538e-05, "loss": 0.0014, "step": 320670 }, { "epoch": 77.03, "learning_rate": 1.6603978899518262e-05, "loss": 0.0014, "step": 320680 }, { "epoch": 77.03, "learning_rate": 1.660130750937234e-05, "loss": 0.0014, "step": 320690 }, { "epoch": 77.03, "learning_rate": 1.659863629136357e-05, "loss": 0.003, "step": 320700 }, { "epoch": 77.04, "learning_rate": 1.6595965245505702e-05, "loss": 0.0012, "step": 320710 }, { "epoch": 77.04, "learning_rate": 1.6593294371812518e-05, "loss": 0.0014, "step": 320720 }, { "epoch": 77.04, "learning_rate": 1.659062367029776e-05, "loss": 0.0013, "step": 320730 }, { "epoch": 77.04, "learning_rate": 1.658795314097522e-05, "loss": 0.0013, "step": 320740 }, { "epoch": 77.05, "learning_rate": 1.658528278385865e-05, "loss": 0.0012, "step": 320750 }, { "epoch": 77.05, "learning_rate": 1.65826125989618e-05, "loss": 0.0014, "step": 320760 }, { "epoch": 77.05, "learning_rate": 1.6579942586298454e-05, "loss": 0.0013, "step": 320770 }, { "epoch": 77.05, "learning_rate": 1.657727274588235e-05, "loss": 0.0012, "step": 320780 }, { "epoch": 77.05, "learning_rate": 1.6574603077727264e-05, "loss": 0.0022, "step": 320790 }, { "epoch": 77.06, "learning_rate": 1.6571933581846965e-05, "loss": 0.0012, "step": 320800 }, { "epoch": 77.06, "learning_rate": 1.6569264258255184e-05, "loss": 0.0013, "step": 320810 }, { "epoch": 77.06, "learning_rate": 1.656659510696571e-05, "loss": 0.0012, "step": 320820 }, { "epoch": 77.06, "learning_rate": 1.656392612799227e-05, "loss": 0.0013, "step": 320830 }, { "epoch": 77.07, "learning_rate": 1.656125732134865e-05, "loss": 0.0012, "step": 320840 }, { "epoch": 77.07, "learning_rate": 1.6558588687048578e-05, "loss": 0.0013, "step": 320850 }, { "epoch": 77.07, "learning_rate": 1.6555920225105826e-05, "loss": 0.0011, "step": 320860 }, { "epoch": 77.07, "learning_rate": 1.655325193553413e-05, "loss": 0.0019, "step": 320870 }, { "epoch": 77.08, "learning_rate": 1.655058381834727e-05, "loss": 0.0011, "step": 320880 }, { "epoch": 77.08, "learning_rate": 1.654791587355898e-05, "loss": 0.0014, "step": 320890 }, { "epoch": 77.08, "learning_rate": 1.654524810118299e-05, "loss": 0.0015, "step": 320900 }, { "epoch": 77.08, "learning_rate": 1.6542580501233097e-05, "loss": 0.0012, "step": 320910 }, { "epoch": 77.08, "learning_rate": 1.6539913073723003e-05, "loss": 0.0012, "step": 320920 }, { "epoch": 77.09, "learning_rate": 1.6537245818666493e-05, "loss": 0.0017, "step": 320930 }, { "epoch": 77.09, "learning_rate": 1.6534578736077278e-05, "loss": 0.0015, "step": 320940 }, { "epoch": 77.09, "learning_rate": 1.6531911825969142e-05, "loss": 0.0016, "step": 320950 }, { "epoch": 77.09, "learning_rate": 1.652924508835581e-05, "loss": 0.0014, "step": 320960 }, { "epoch": 77.1, "learning_rate": 1.6526578523251017e-05, "loss": 0.0013, "step": 320970 }, { "epoch": 77.1, "learning_rate": 1.6523912130668533e-05, "loss": 0.0015, "step": 320980 }, { "epoch": 77.1, "learning_rate": 1.652124591062207e-05, "loss": 0.0017, "step": 320990 }, { "epoch": 77.1, "learning_rate": 1.6518579863125398e-05, "loss": 0.0013, "step": 321000 }, { "epoch": 77.1, "learning_rate": 1.6515913988192232e-05, "loss": 0.0013, "step": 321010 }, { "epoch": 77.11, "learning_rate": 1.651324828583634e-05, "loss": 0.0013, "step": 321020 }, { "epoch": 77.11, "learning_rate": 1.6510582756071446e-05, "loss": 0.0012, "step": 321030 }, { "epoch": 77.11, "learning_rate": 1.6507917398911276e-05, "loss": 0.0014, "step": 321040 }, { "epoch": 77.11, "learning_rate": 1.6505252214369593e-05, "loss": 0.0012, "step": 321050 }, { "epoch": 77.12, "learning_rate": 1.6502587202460107e-05, "loss": 0.0012, "step": 321060 }, { "epoch": 77.12, "learning_rate": 1.649992236319658e-05, "loss": 0.0013, "step": 321070 }, { "epoch": 77.12, "learning_rate": 1.6497257696592718e-05, "loss": 0.0012, "step": 321080 }, { "epoch": 77.12, "learning_rate": 1.6494593202662282e-05, "loss": 0.0012, "step": 321090 }, { "epoch": 77.13, "learning_rate": 1.649192888141898e-05, "loss": 0.0012, "step": 321100 }, { "epoch": 77.13, "learning_rate": 1.648926473287655e-05, "loss": 0.0013, "step": 321110 }, { "epoch": 77.13, "learning_rate": 1.648660075704876e-05, "loss": 0.0012, "step": 321120 }, { "epoch": 77.13, "learning_rate": 1.648393695394928e-05, "loss": 0.0014, "step": 321130 }, { "epoch": 77.13, "learning_rate": 1.6481273323591896e-05, "loss": 0.0014, "step": 321140 }, { "epoch": 77.14, "learning_rate": 1.6478609865990286e-05, "loss": 0.0014, "step": 321150 }, { "epoch": 77.14, "learning_rate": 1.6475946581158218e-05, "loss": 0.0013, "step": 321160 }, { "epoch": 77.14, "learning_rate": 1.64732834691094e-05, "loss": 0.0015, "step": 321170 }, { "epoch": 77.14, "learning_rate": 1.647062052985755e-05, "loss": 0.0012, "step": 321180 }, { "epoch": 77.15, "learning_rate": 1.6467957763416414e-05, "loss": 0.0015, "step": 321190 }, { "epoch": 77.15, "learning_rate": 1.6465295169799687e-05, "loss": 0.0013, "step": 321200 }, { "epoch": 77.15, "learning_rate": 1.646263274902113e-05, "loss": 0.0014, "step": 321210 }, { "epoch": 77.15, "learning_rate": 1.645997050109442e-05, "loss": 0.0012, "step": 321220 }, { "epoch": 77.16, "learning_rate": 1.6457308426033325e-05, "loss": 0.0049, "step": 321230 }, { "epoch": 77.16, "learning_rate": 1.645464652385154e-05, "loss": 0.0014, "step": 321240 }, { "epoch": 77.16, "learning_rate": 1.645198479456277e-05, "loss": 0.0019, "step": 321250 }, { "epoch": 77.16, "learning_rate": 1.644932323818077e-05, "loss": 0.0012, "step": 321260 }, { "epoch": 77.16, "learning_rate": 1.644666185471922e-05, "loss": 0.0013, "step": 321270 }, { "epoch": 77.17, "learning_rate": 1.644400064419187e-05, "loss": 0.0013, "step": 321280 }, { "epoch": 77.17, "learning_rate": 1.644133960661241e-05, "loss": 0.0013, "step": 321290 }, { "epoch": 77.17, "learning_rate": 1.643867874199458e-05, "loss": 0.0015, "step": 321300 }, { "epoch": 77.17, "learning_rate": 1.6436018050352076e-05, "loss": 0.0012, "step": 321310 }, { "epoch": 77.18, "learning_rate": 1.6433357531698607e-05, "loss": 0.0013, "step": 321320 }, { "epoch": 77.18, "learning_rate": 1.6430697186047904e-05, "loss": 0.0032, "step": 321330 }, { "epoch": 77.18, "learning_rate": 1.6428037013413655e-05, "loss": 0.0014, "step": 321340 }, { "epoch": 77.18, "learning_rate": 1.6425377013809602e-05, "loss": 0.0015, "step": 321350 }, { "epoch": 77.18, "learning_rate": 1.6422717187249414e-05, "loss": 0.0014, "step": 321360 }, { "epoch": 77.19, "learning_rate": 1.6420057533746842e-05, "loss": 0.0016, "step": 321370 }, { "epoch": 77.19, "learning_rate": 1.6417398053315558e-05, "loss": 0.0014, "step": 321380 }, { "epoch": 77.19, "learning_rate": 1.64147387459693e-05, "loss": 0.0012, "step": 321390 }, { "epoch": 77.19, "learning_rate": 1.6412079611721747e-05, "loss": 0.0015, "step": 321400 }, { "epoch": 77.2, "learning_rate": 1.6409420650586627e-05, "loss": 0.0012, "step": 321410 }, { "epoch": 77.2, "learning_rate": 1.6406761862577625e-05, "loss": 0.0013, "step": 321420 }, { "epoch": 77.2, "learning_rate": 1.6404103247708445e-05, "loss": 0.0014, "step": 321430 }, { "epoch": 77.2, "learning_rate": 1.640144480599282e-05, "loss": 0.0015, "step": 321440 }, { "epoch": 77.21, "learning_rate": 1.6398786537444412e-05, "loss": 0.0013, "step": 321450 }, { "epoch": 77.21, "learning_rate": 1.639612844207695e-05, "loss": 0.0013, "step": 321460 }, { "epoch": 77.21, "learning_rate": 1.639347051990413e-05, "loss": 0.0013, "step": 321470 }, { "epoch": 77.21, "learning_rate": 1.6390812770939622e-05, "loss": 0.0013, "step": 321480 }, { "epoch": 77.21, "learning_rate": 1.6388155195197164e-05, "loss": 0.0013, "step": 321490 }, { "epoch": 77.22, "learning_rate": 1.6385497792690423e-05, "loss": 0.0014, "step": 321500 }, { "epoch": 77.22, "learning_rate": 1.6382840563433118e-05, "loss": 0.0013, "step": 321510 }, { "epoch": 77.22, "learning_rate": 1.638018350743892e-05, "loss": 0.0014, "step": 321520 }, { "epoch": 77.22, "learning_rate": 1.6377526624721552e-05, "loss": 0.0013, "step": 321530 }, { "epoch": 77.23, "learning_rate": 1.6374869915294695e-05, "loss": 0.0013, "step": 321540 }, { "epoch": 77.23, "learning_rate": 1.6372213379172023e-05, "loss": 0.0011, "step": 321550 }, { "epoch": 77.23, "learning_rate": 1.636955701636726e-05, "loss": 0.0012, "step": 321560 }, { "epoch": 77.23, "learning_rate": 1.6366900826894065e-05, "loss": 0.0013, "step": 321570 }, { "epoch": 77.24, "learning_rate": 1.636424481076616e-05, "loss": 0.0014, "step": 321580 }, { "epoch": 77.24, "learning_rate": 1.63615889679972e-05, "loss": 0.0012, "step": 321590 }, { "epoch": 77.24, "learning_rate": 1.635893329860091e-05, "loss": 0.0012, "step": 321600 }, { "epoch": 77.24, "learning_rate": 1.6356277802590956e-05, "loss": 0.0013, "step": 321610 }, { "epoch": 77.24, "learning_rate": 1.6353622479981017e-05, "loss": 0.0014, "step": 321620 }, { "epoch": 77.25, "learning_rate": 1.6350967330784807e-05, "loss": 0.0014, "step": 321630 }, { "epoch": 77.25, "learning_rate": 1.634831235501597e-05, "loss": 0.0013, "step": 321640 }, { "epoch": 77.25, "learning_rate": 1.6345657552688233e-05, "loss": 0.0022, "step": 321650 }, { "epoch": 77.25, "learning_rate": 1.634300292381524e-05, "loss": 0.0012, "step": 321660 }, { "epoch": 77.26, "learning_rate": 1.6340348468410705e-05, "loss": 0.0013, "step": 321670 }, { "epoch": 77.26, "learning_rate": 1.6337694186488277e-05, "loss": 0.0013, "step": 321680 }, { "epoch": 77.26, "learning_rate": 1.633504007806168e-05, "loss": 0.0012, "step": 321690 }, { "epoch": 77.26, "learning_rate": 1.6332386143144544e-05, "loss": 0.0012, "step": 321700 }, { "epoch": 77.26, "learning_rate": 1.6329732381750588e-05, "loss": 0.0012, "step": 321710 }, { "epoch": 77.27, "learning_rate": 1.6327078793893463e-05, "loss": 0.0013, "step": 321720 }, { "epoch": 77.27, "learning_rate": 1.6324425379586866e-05, "loss": 0.0014, "step": 321730 }, { "epoch": 77.27, "learning_rate": 1.632177213884445e-05, "loss": 0.0013, "step": 321740 }, { "epoch": 77.27, "learning_rate": 1.6319119071679912e-05, "loss": 0.0012, "step": 321750 }, { "epoch": 77.28, "learning_rate": 1.6316466178106904e-05, "loss": 0.0012, "step": 321760 }, { "epoch": 77.28, "learning_rate": 1.6313813458139127e-05, "loss": 0.0013, "step": 321770 }, { "epoch": 77.28, "learning_rate": 1.631116091179022e-05, "loss": 0.0013, "step": 321780 }, { "epoch": 77.28, "learning_rate": 1.6308508539073885e-05, "loss": 0.0011, "step": 321790 }, { "epoch": 77.29, "learning_rate": 1.6305856340003767e-05, "loss": 0.0012, "step": 321800 }, { "epoch": 77.29, "learning_rate": 1.6303204314593557e-05, "loss": 0.0012, "step": 321810 }, { "epoch": 77.29, "learning_rate": 1.6300552462856922e-05, "loss": 0.0013, "step": 321820 }, { "epoch": 77.29, "learning_rate": 1.6297900784807497e-05, "loss": 0.0012, "step": 321830 }, { "epoch": 77.29, "learning_rate": 1.6295249280458996e-05, "loss": 0.0013, "step": 321840 }, { "epoch": 77.3, "learning_rate": 1.629259794982504e-05, "loss": 0.0016, "step": 321850 }, { "epoch": 77.3, "learning_rate": 1.6289946792919337e-05, "loss": 0.0013, "step": 321860 }, { "epoch": 77.3, "learning_rate": 1.628729580975551e-05, "loss": 0.0012, "step": 321870 }, { "epoch": 77.3, "learning_rate": 1.628464500034726e-05, "loss": 0.0013, "step": 321880 }, { "epoch": 77.31, "learning_rate": 1.628199436470823e-05, "loss": 0.0013, "step": 321890 }, { "epoch": 77.31, "learning_rate": 1.627934390285207e-05, "loss": 0.0014, "step": 321900 }, { "epoch": 77.31, "learning_rate": 1.6276693614792465e-05, "loss": 0.0012, "step": 321910 }, { "epoch": 77.31, "learning_rate": 1.6274043500543053e-05, "loss": 0.0012, "step": 321920 }, { "epoch": 77.32, "learning_rate": 1.6271393560117513e-05, "loss": 0.0014, "step": 321930 }, { "epoch": 77.32, "learning_rate": 1.6268743793529477e-05, "loss": 0.0013, "step": 321940 }, { "epoch": 77.32, "learning_rate": 1.6266094200792637e-05, "loss": 0.0011, "step": 321950 }, { "epoch": 77.32, "learning_rate": 1.6263444781920628e-05, "loss": 0.0036, "step": 321960 }, { "epoch": 77.32, "learning_rate": 1.6260795536927092e-05, "loss": 0.0014, "step": 321970 }, { "epoch": 77.33, "learning_rate": 1.6258146465825714e-05, "loss": 0.003, "step": 321980 }, { "epoch": 77.33, "learning_rate": 1.6255497568630113e-05, "loss": 0.0012, "step": 321990 }, { "epoch": 77.33, "learning_rate": 1.6252848845353958e-05, "loss": 0.0014, "step": 322000 }, { "epoch": 77.33, "learning_rate": 1.625020029601092e-05, "loss": 0.0012, "step": 322010 }, { "epoch": 77.34, "learning_rate": 1.624755192061461e-05, "loss": 0.0014, "step": 322020 }, { "epoch": 77.34, "learning_rate": 1.6244903719178727e-05, "loss": 0.0013, "step": 322030 }, { "epoch": 77.34, "learning_rate": 1.624225569171687e-05, "loss": 0.0013, "step": 322040 }, { "epoch": 77.34, "learning_rate": 1.6239607838242726e-05, "loss": 0.0012, "step": 322050 }, { "epoch": 77.34, "learning_rate": 1.623696015876991e-05, "loss": 0.0012, "step": 322060 }, { "epoch": 77.35, "learning_rate": 1.6234312653312102e-05, "loss": 0.0013, "step": 322070 }, { "epoch": 77.35, "learning_rate": 1.6231665321882905e-05, "loss": 0.0014, "step": 322080 }, { "epoch": 77.35, "learning_rate": 1.6229018164496007e-05, "loss": 0.0014, "step": 322090 }, { "epoch": 77.35, "learning_rate": 1.6226371181165035e-05, "loss": 0.0012, "step": 322100 }, { "epoch": 77.36, "learning_rate": 1.622372437190361e-05, "loss": 0.0012, "step": 322110 }, { "epoch": 77.36, "learning_rate": 1.622107773672541e-05, "loss": 0.0012, "step": 322120 }, { "epoch": 77.36, "learning_rate": 1.6218431275644035e-05, "loss": 0.0012, "step": 322130 }, { "epoch": 77.36, "learning_rate": 1.621578498867317e-05, "loss": 0.0014, "step": 322140 }, { "epoch": 77.37, "learning_rate": 1.6213138875826412e-05, "loss": 0.0011, "step": 322150 }, { "epoch": 77.37, "learning_rate": 1.6210492937117437e-05, "loss": 0.0015, "step": 322160 }, { "epoch": 77.37, "learning_rate": 1.620784717255985e-05, "loss": 0.001, "step": 322170 }, { "epoch": 77.37, "learning_rate": 1.620520158216731e-05, "loss": 0.0013, "step": 322180 }, { "epoch": 77.37, "learning_rate": 1.620255616595345e-05, "loss": 0.0012, "step": 322190 }, { "epoch": 77.38, "learning_rate": 1.6199910923931878e-05, "loss": 0.0013, "step": 322200 }, { "epoch": 77.38, "learning_rate": 1.6197265856116267e-05, "loss": 0.0012, "step": 322210 }, { "epoch": 77.38, "learning_rate": 1.619462096252021e-05, "loss": 0.0014, "step": 322220 }, { "epoch": 77.38, "learning_rate": 1.619197624315738e-05, "loss": 0.0013, "step": 322230 }, { "epoch": 77.39, "learning_rate": 1.6189331698041372e-05, "loss": 0.0012, "step": 322240 }, { "epoch": 77.39, "learning_rate": 1.618668732718584e-05, "loss": 0.0012, "step": 322250 }, { "epoch": 77.39, "learning_rate": 1.618404313060441e-05, "loss": 0.0012, "step": 322260 }, { "epoch": 77.39, "learning_rate": 1.6181399108310687e-05, "loss": 0.0011, "step": 322270 }, { "epoch": 77.4, "learning_rate": 1.617875526031833e-05, "loss": 0.0012, "step": 322280 }, { "epoch": 77.4, "learning_rate": 1.6176111586640934e-05, "loss": 0.0012, "step": 322290 }, { "epoch": 77.4, "learning_rate": 1.6173468087292166e-05, "loss": 0.0011, "step": 322300 }, { "epoch": 77.4, "learning_rate": 1.6170824762285603e-05, "loss": 0.0011, "step": 322310 }, { "epoch": 77.4, "learning_rate": 1.6168181611634892e-05, "loss": 0.0013, "step": 322320 }, { "epoch": 77.41, "learning_rate": 1.616553863535367e-05, "loss": 0.0012, "step": 322330 }, { "epoch": 77.41, "learning_rate": 1.616289583345553e-05, "loss": 0.0012, "step": 322340 }, { "epoch": 77.41, "learning_rate": 1.616025320595413e-05, "loss": 0.0024, "step": 322350 }, { "epoch": 77.41, "learning_rate": 1.6157610752863046e-05, "loss": 0.0012, "step": 322360 }, { "epoch": 77.42, "learning_rate": 1.6154968474195935e-05, "loss": 0.0012, "step": 322370 }, { "epoch": 77.42, "learning_rate": 1.6152326369966386e-05, "loss": 0.0012, "step": 322380 }, { "epoch": 77.42, "learning_rate": 1.614968444018804e-05, "loss": 0.0013, "step": 322390 }, { "epoch": 77.42, "learning_rate": 1.6147042684874508e-05, "loss": 0.0011, "step": 322400 }, { "epoch": 77.42, "learning_rate": 1.6144401104039387e-05, "loss": 0.0011, "step": 322410 }, { "epoch": 77.43, "learning_rate": 1.614175969769632e-05, "loss": 0.0013, "step": 322420 }, { "epoch": 77.43, "learning_rate": 1.6139118465858887e-05, "loss": 0.0012, "step": 322430 }, { "epoch": 77.43, "learning_rate": 1.613647740854074e-05, "loss": 0.0013, "step": 322440 }, { "epoch": 77.43, "learning_rate": 1.6133836525755458e-05, "loss": 0.0012, "step": 322450 }, { "epoch": 77.44, "learning_rate": 1.6131195817516677e-05, "loss": 0.0013, "step": 322460 }, { "epoch": 77.44, "learning_rate": 1.6128555283838e-05, "loss": 0.0012, "step": 322470 }, { "epoch": 77.44, "learning_rate": 1.612591492473301e-05, "loss": 0.0012, "step": 322480 }, { "epoch": 77.44, "learning_rate": 1.6123274740215354e-05, "loss": 0.0013, "step": 322490 }, { "epoch": 77.45, "learning_rate": 1.6120634730298613e-05, "loss": 0.0012, "step": 322500 }, { "epoch": 77.45, "learning_rate": 1.611799489499642e-05, "loss": 0.0012, "step": 322510 }, { "epoch": 77.45, "learning_rate": 1.6115355234322343e-05, "loss": 0.0013, "step": 322520 }, { "epoch": 77.45, "learning_rate": 1.6112715748290024e-05, "loss": 0.0013, "step": 322530 }, { "epoch": 77.45, "learning_rate": 1.6110076436913056e-05, "loss": 0.0013, "step": 322540 }, { "epoch": 77.46, "learning_rate": 1.610743730020502e-05, "loss": 0.0011, "step": 322550 }, { "epoch": 77.46, "learning_rate": 1.610479833817955e-05, "loss": 0.0013, "step": 322560 }, { "epoch": 77.46, "learning_rate": 1.6102159550850223e-05, "loss": 0.0011, "step": 322570 }, { "epoch": 77.46, "learning_rate": 1.6099520938230656e-05, "loss": 0.0014, "step": 322580 }, { "epoch": 77.47, "learning_rate": 1.6096882500334426e-05, "loss": 0.0014, "step": 322590 }, { "epoch": 77.47, "learning_rate": 1.609424423717517e-05, "loss": 0.0012, "step": 322600 }, { "epoch": 77.47, "learning_rate": 1.6091606148766443e-05, "loss": 0.0015, "step": 322610 }, { "epoch": 77.47, "learning_rate": 1.608896823512186e-05, "loss": 0.0014, "step": 322620 }, { "epoch": 77.48, "learning_rate": 1.6086330496255036e-05, "loss": 0.0013, "step": 322630 }, { "epoch": 77.48, "learning_rate": 1.608369293217953e-05, "loss": 0.0014, "step": 322640 }, { "epoch": 77.48, "learning_rate": 1.6081055542908974e-05, "loss": 0.0013, "step": 322650 }, { "epoch": 77.48, "learning_rate": 1.6078418328456918e-05, "loss": 0.0013, "step": 322660 }, { "epoch": 77.48, "learning_rate": 1.6075781288837e-05, "loss": 0.0013, "step": 322670 }, { "epoch": 77.49, "learning_rate": 1.6073144424062787e-05, "loss": 0.0013, "step": 322680 }, { "epoch": 77.49, "learning_rate": 1.6070507734147854e-05, "loss": 0.0012, "step": 322690 }, { "epoch": 77.49, "learning_rate": 1.6067871219105824e-05, "loss": 0.0012, "step": 322700 }, { "epoch": 77.49, "learning_rate": 1.606523487895026e-05, "loss": 0.0012, "step": 322710 }, { "epoch": 77.5, "learning_rate": 1.6062598713694764e-05, "loss": 0.0012, "step": 322720 }, { "epoch": 77.5, "learning_rate": 1.605996272335291e-05, "loss": 0.0014, "step": 322730 }, { "epoch": 77.5, "learning_rate": 1.6057326907938303e-05, "loss": 0.0013, "step": 322740 }, { "epoch": 77.5, "learning_rate": 1.6054691267464523e-05, "loss": 0.0012, "step": 322750 }, { "epoch": 77.5, "learning_rate": 1.6052055801945125e-05, "loss": 0.0013, "step": 322760 }, { "epoch": 77.51, "learning_rate": 1.604942051139373e-05, "loss": 0.0014, "step": 322770 }, { "epoch": 77.51, "learning_rate": 1.60467853958239e-05, "loss": 0.0012, "step": 322780 }, { "epoch": 77.51, "learning_rate": 1.604415045524923e-05, "loss": 0.0015, "step": 322790 }, { "epoch": 77.51, "learning_rate": 1.604151568968328e-05, "loss": 0.0012, "step": 322800 }, { "epoch": 77.52, "learning_rate": 1.603888109913965e-05, "loss": 0.0013, "step": 322810 }, { "epoch": 77.52, "learning_rate": 1.6036246683631916e-05, "loss": 0.0015, "step": 322820 }, { "epoch": 77.52, "learning_rate": 1.603361244317364e-05, "loss": 0.0013, "step": 322830 }, { "epoch": 77.52, "learning_rate": 1.6030978377778415e-05, "loss": 0.0012, "step": 322840 }, { "epoch": 77.53, "learning_rate": 1.60283444874598e-05, "loss": 0.0013, "step": 322850 }, { "epoch": 77.53, "learning_rate": 1.6025710772231402e-05, "loss": 0.0014, "step": 322860 }, { "epoch": 77.53, "learning_rate": 1.6023077232106753e-05, "loss": 0.0014, "step": 322870 }, { "epoch": 77.53, "learning_rate": 1.6020443867099467e-05, "loss": 0.0014, "step": 322880 }, { "epoch": 77.53, "learning_rate": 1.6017810677223084e-05, "loss": 0.0012, "step": 322890 }, { "epoch": 77.54, "learning_rate": 1.60151776624912e-05, "loss": 0.0014, "step": 322900 }, { "epoch": 77.54, "learning_rate": 1.6012544822917357e-05, "loss": 0.0012, "step": 322910 }, { "epoch": 77.54, "learning_rate": 1.6009912158515162e-05, "loss": 0.0013, "step": 322920 }, { "epoch": 77.54, "learning_rate": 1.600727966929814e-05, "loss": 0.0013, "step": 322930 }, { "epoch": 77.55, "learning_rate": 1.6004647355279894e-05, "loss": 0.0013, "step": 322940 }, { "epoch": 77.55, "learning_rate": 1.6002015216473992e-05, "loss": 0.0013, "step": 322950 }, { "epoch": 77.55, "learning_rate": 1.5999383252893983e-05, "loss": 0.0012, "step": 322960 }, { "epoch": 77.55, "learning_rate": 1.599675146455343e-05, "loss": 0.0013, "step": 322970 }, { "epoch": 77.56, "learning_rate": 1.599411985146591e-05, "loss": 0.0013, "step": 322980 }, { "epoch": 77.56, "learning_rate": 1.5991488413644967e-05, "loss": 0.0014, "step": 322990 }, { "epoch": 77.56, "learning_rate": 1.5988857151104197e-05, "loss": 0.0012, "step": 323000 }, { "epoch": 77.56, "learning_rate": 1.5986226063857123e-05, "loss": 0.0012, "step": 323010 }, { "epoch": 77.56, "learning_rate": 1.598359515191734e-05, "loss": 0.0013, "step": 323020 }, { "epoch": 77.57, "learning_rate": 1.5980964415298377e-05, "loss": 0.0013, "step": 323030 }, { "epoch": 77.57, "learning_rate": 1.5978333854013823e-05, "loss": 0.0012, "step": 323040 }, { "epoch": 77.57, "learning_rate": 1.5975703468077225e-05, "loss": 0.0012, "step": 323050 }, { "epoch": 77.57, "learning_rate": 1.5973073257502113e-05, "loss": 0.0015, "step": 323060 }, { "epoch": 77.58, "learning_rate": 1.5970443222302082e-05, "loss": 0.0014, "step": 323070 }, { "epoch": 77.58, "learning_rate": 1.596781336249066e-05, "loss": 0.0013, "step": 323080 }, { "epoch": 77.58, "learning_rate": 1.5965183678081426e-05, "loss": 0.0014, "step": 323090 }, { "epoch": 77.58, "learning_rate": 1.5962554169087908e-05, "loss": 0.0014, "step": 323100 }, { "epoch": 77.58, "learning_rate": 1.5959924835523675e-05, "loss": 0.0015, "step": 323110 }, { "epoch": 77.59, "learning_rate": 1.5957295677402284e-05, "loss": 0.0013, "step": 323120 }, { "epoch": 77.59, "learning_rate": 1.595466669473726e-05, "loss": 0.0013, "step": 323130 }, { "epoch": 77.59, "learning_rate": 1.5952037887542183e-05, "loss": 0.0013, "step": 323140 }, { "epoch": 77.59, "learning_rate": 1.5949409255830565e-05, "loss": 0.0012, "step": 323150 }, { "epoch": 77.6, "learning_rate": 1.5946780799615995e-05, "loss": 0.0012, "step": 323160 }, { "epoch": 77.6, "learning_rate": 1.594415251891199e-05, "loss": 0.0015, "step": 323170 }, { "epoch": 77.6, "learning_rate": 1.5941524413732124e-05, "loss": 0.0014, "step": 323180 }, { "epoch": 77.6, "learning_rate": 1.5938896484089904e-05, "loss": 0.0014, "step": 323190 }, { "epoch": 77.61, "learning_rate": 1.5936268729998914e-05, "loss": 0.0014, "step": 323200 }, { "epoch": 77.61, "learning_rate": 1.5933641151472667e-05, "loss": 0.0013, "step": 323210 }, { "epoch": 77.61, "learning_rate": 1.5931013748524733e-05, "loss": 0.0015, "step": 323220 }, { "epoch": 77.61, "learning_rate": 1.592838652116862e-05, "loss": 0.0014, "step": 323230 }, { "epoch": 77.61, "learning_rate": 1.5925759469417904e-05, "loss": 0.0012, "step": 323240 }, { "epoch": 77.62, "learning_rate": 1.5923132593286096e-05, "loss": 0.0012, "step": 323250 }, { "epoch": 77.62, "learning_rate": 1.5920505892786758e-05, "loss": 0.0014, "step": 323260 }, { "epoch": 77.62, "learning_rate": 1.5917879367933407e-05, "loss": 0.0014, "step": 323270 }, { "epoch": 77.62, "learning_rate": 1.5915253018739606e-05, "loss": 0.0012, "step": 323280 }, { "epoch": 77.63, "learning_rate": 1.591262684521886e-05, "loss": 0.0013, "step": 323290 }, { "epoch": 77.63, "learning_rate": 1.5910000847384732e-05, "loss": 0.0013, "step": 323300 }, { "epoch": 77.63, "learning_rate": 1.590737502525073e-05, "loss": 0.0014, "step": 323310 }, { "epoch": 77.63, "learning_rate": 1.5904749378830418e-05, "loss": 0.0012, "step": 323320 }, { "epoch": 77.64, "learning_rate": 1.590212390813732e-05, "loss": 0.0015, "step": 323330 }, { "epoch": 77.64, "learning_rate": 1.5899498613184932e-05, "loss": 0.0013, "step": 323340 }, { "epoch": 77.64, "learning_rate": 1.5896873493986836e-05, "loss": 0.0014, "step": 323350 }, { "epoch": 77.64, "learning_rate": 1.5894248550556524e-05, "loss": 0.0014, "step": 323360 }, { "epoch": 77.64, "learning_rate": 1.5891623782907554e-05, "loss": 0.0013, "step": 323370 }, { "epoch": 77.65, "learning_rate": 1.5888999191053428e-05, "loss": 0.0013, "step": 323380 }, { "epoch": 77.65, "learning_rate": 1.5886374775007696e-05, "loss": 0.0012, "step": 323390 }, { "epoch": 77.65, "learning_rate": 1.5883750534783875e-05, "loss": 0.0013, "step": 323400 }, { "epoch": 77.65, "learning_rate": 1.5881126470395475e-05, "loss": 0.0014, "step": 323410 }, { "epoch": 77.66, "learning_rate": 1.587850258185605e-05, "loss": 0.0012, "step": 323420 }, { "epoch": 77.66, "learning_rate": 1.587587886917909e-05, "loss": 0.0011, "step": 323430 }, { "epoch": 77.66, "learning_rate": 1.587325533237815e-05, "loss": 0.0013, "step": 323440 }, { "epoch": 77.66, "learning_rate": 1.5870631971466727e-05, "loss": 0.0014, "step": 323450 }, { "epoch": 77.66, "learning_rate": 1.586800878645836e-05, "loss": 0.0014, "step": 323460 }, { "epoch": 77.67, "learning_rate": 1.586538577736657e-05, "loss": 0.0014, "step": 323470 }, { "epoch": 77.67, "learning_rate": 1.5862762944204844e-05, "loss": 0.0014, "step": 323480 }, { "epoch": 77.67, "learning_rate": 1.586014028698674e-05, "loss": 0.0016, "step": 323490 }, { "epoch": 77.67, "learning_rate": 1.5857517805725747e-05, "loss": 0.0013, "step": 323500 }, { "epoch": 77.68, "learning_rate": 1.585489550043539e-05, "loss": 0.0012, "step": 323510 }, { "epoch": 77.68, "learning_rate": 1.58522733711292e-05, "loss": 0.0016, "step": 323520 }, { "epoch": 77.68, "learning_rate": 1.5849651417820666e-05, "loss": 0.0012, "step": 323530 }, { "epoch": 77.68, "learning_rate": 1.584702964052333e-05, "loss": 0.0014, "step": 323540 }, { "epoch": 77.69, "learning_rate": 1.5844408039250676e-05, "loss": 0.0204, "step": 323550 }, { "epoch": 77.69, "learning_rate": 1.584178661401624e-05, "loss": 0.0015, "step": 323560 }, { "epoch": 77.69, "learning_rate": 1.5839165364833502e-05, "loss": 0.0013, "step": 323570 }, { "epoch": 77.69, "learning_rate": 1.5836544291716016e-05, "loss": 0.0013, "step": 323580 }, { "epoch": 77.69, "learning_rate": 1.5833923394677242e-05, "loss": 0.0013, "step": 323590 }, { "epoch": 77.7, "learning_rate": 1.583130267373073e-05, "loss": 0.0014, "step": 323600 }, { "epoch": 77.7, "learning_rate": 1.5828682128889975e-05, "loss": 0.0012, "step": 323610 }, { "epoch": 77.7, "learning_rate": 1.582606176016846e-05, "loss": 0.0013, "step": 323620 }, { "epoch": 77.7, "learning_rate": 1.5823441567579723e-05, "loss": 0.0012, "step": 323630 }, { "epoch": 77.71, "learning_rate": 1.5820821551137234e-05, "loss": 0.0012, "step": 323640 }, { "epoch": 77.71, "learning_rate": 1.5818201710854535e-05, "loss": 0.0015, "step": 323650 }, { "epoch": 77.71, "learning_rate": 1.5815582046745098e-05, "loss": 0.0014, "step": 323660 }, { "epoch": 77.71, "learning_rate": 1.5812962558822447e-05, "loss": 0.0013, "step": 323670 }, { "epoch": 77.72, "learning_rate": 1.5810343247100078e-05, "loss": 0.0057, "step": 323680 }, { "epoch": 77.72, "learning_rate": 1.5807724111591465e-05, "loss": 0.0013, "step": 323690 }, { "epoch": 77.72, "learning_rate": 1.5805105152310147e-05, "loss": 0.0013, "step": 323700 }, { "epoch": 77.72, "learning_rate": 1.580248636926959e-05, "loss": 0.0022, "step": 323710 }, { "epoch": 77.72, "learning_rate": 1.5799867762483312e-05, "loss": 0.0017, "step": 323720 }, { "epoch": 77.73, "learning_rate": 1.579724933196479e-05, "loss": 0.0013, "step": 323730 }, { "epoch": 77.73, "learning_rate": 1.5794631077727546e-05, "loss": 0.0013, "step": 323740 }, { "epoch": 77.73, "learning_rate": 1.579201299978506e-05, "loss": 0.0013, "step": 323750 }, { "epoch": 77.73, "learning_rate": 1.578939509815081e-05, "loss": 0.0012, "step": 323760 }, { "epoch": 77.74, "learning_rate": 1.578677737283832e-05, "loss": 0.0013, "step": 323770 }, { "epoch": 77.74, "learning_rate": 1.5784159823861045e-05, "loss": 0.0012, "step": 323780 }, { "epoch": 77.74, "learning_rate": 1.5781542451232513e-05, "loss": 0.0014, "step": 323790 }, { "epoch": 77.74, "learning_rate": 1.577892525496618e-05, "loss": 0.0013, "step": 323800 }, { "epoch": 77.74, "learning_rate": 1.5776308235075575e-05, "loss": 0.0012, "step": 323810 }, { "epoch": 77.75, "learning_rate": 1.5773691391574146e-05, "loss": 0.0015, "step": 323820 }, { "epoch": 77.75, "learning_rate": 1.5771074724475392e-05, "loss": 0.0013, "step": 323830 }, { "epoch": 77.75, "learning_rate": 1.5768458233792828e-05, "loss": 0.0013, "step": 323840 }, { "epoch": 77.75, "learning_rate": 1.57658419195399e-05, "loss": 0.0015, "step": 323850 }, { "epoch": 77.76, "learning_rate": 1.576322578173012e-05, "loss": 0.0014, "step": 323860 }, { "epoch": 77.76, "learning_rate": 1.5760609820376943e-05, "loss": 0.0014, "step": 323870 }, { "epoch": 77.76, "learning_rate": 1.575799403549389e-05, "loss": 0.0012, "step": 323880 }, { "epoch": 77.76, "learning_rate": 1.5755378427094403e-05, "loss": 0.0014, "step": 323890 }, { "epoch": 77.77, "learning_rate": 1.5752762995192e-05, "loss": 0.0014, "step": 323900 }, { "epoch": 77.77, "learning_rate": 1.575014773980014e-05, "loss": 0.0014, "step": 323910 }, { "epoch": 77.77, "learning_rate": 1.574753266093229e-05, "loss": 0.0016, "step": 323920 }, { "epoch": 77.77, "learning_rate": 1.574491775860196e-05, "loss": 0.0012, "step": 323930 }, { "epoch": 77.77, "learning_rate": 1.5742303032822596e-05, "loss": 0.0013, "step": 323940 }, { "epoch": 77.78, "learning_rate": 1.57396884836077e-05, "loss": 0.0013, "step": 323950 }, { "epoch": 77.78, "learning_rate": 1.5737074110970723e-05, "loss": 0.0029, "step": 323960 }, { "epoch": 77.78, "learning_rate": 1.573445991492517e-05, "loss": 0.0016, "step": 323970 }, { "epoch": 77.78, "learning_rate": 1.5731845895484493e-05, "loss": 0.0013, "step": 323980 }, { "epoch": 77.79, "learning_rate": 1.572923205266216e-05, "loss": 0.0013, "step": 323990 }, { "epoch": 77.79, "learning_rate": 1.572661838647166e-05, "loss": 0.0012, "step": 324000 }, { "epoch": 77.79, "learning_rate": 1.5724004896926435e-05, "loss": 0.0013, "step": 324010 }, { "epoch": 77.79, "learning_rate": 1.5721391584040002e-05, "loss": 0.0014, "step": 324020 }, { "epoch": 77.8, "learning_rate": 1.5718778447825783e-05, "loss": 0.0014, "step": 324030 }, { "epoch": 77.8, "learning_rate": 1.571616548829728e-05, "loss": 0.0014, "step": 324040 }, { "epoch": 77.8, "learning_rate": 1.5713552705467948e-05, "loss": 0.0014, "step": 324050 }, { "epoch": 77.8, "learning_rate": 1.571094009935124e-05, "loss": 0.0013, "step": 324060 }, { "epoch": 77.8, "learning_rate": 1.570832766996065e-05, "loss": 0.0017, "step": 324070 }, { "epoch": 77.81, "learning_rate": 1.57057154173096e-05, "loss": 0.0014, "step": 324080 }, { "epoch": 77.81, "learning_rate": 1.5703103341411602e-05, "loss": 0.0012, "step": 324090 }, { "epoch": 77.81, "learning_rate": 1.5700491442280078e-05, "loss": 0.011, "step": 324100 }, { "epoch": 77.81, "learning_rate": 1.5697879719928525e-05, "loss": 0.0021, "step": 324110 }, { "epoch": 77.82, "learning_rate": 1.5695268174370376e-05, "loss": 0.0014, "step": 324120 }, { "epoch": 77.82, "learning_rate": 1.5692656805619093e-05, "loss": 0.0013, "step": 324130 }, { "epoch": 77.82, "learning_rate": 1.5690045613688164e-05, "loss": 0.0015, "step": 324140 }, { "epoch": 77.82, "learning_rate": 1.5687434598591012e-05, "loss": 0.0014, "step": 324150 }, { "epoch": 77.82, "learning_rate": 1.5684823760341123e-05, "loss": 0.0013, "step": 324160 }, { "epoch": 77.83, "learning_rate": 1.568221309895192e-05, "loss": 0.0014, "step": 324170 }, { "epoch": 77.83, "learning_rate": 1.56796026144369e-05, "loss": 0.0013, "step": 324180 }, { "epoch": 77.83, "learning_rate": 1.567699230680949e-05, "loss": 0.0013, "step": 324190 }, { "epoch": 77.83, "learning_rate": 1.5674382176083135e-05, "loss": 0.0013, "step": 324200 }, { "epoch": 77.84, "learning_rate": 1.5671772222271313e-05, "loss": 0.0013, "step": 324210 }, { "epoch": 77.84, "learning_rate": 1.5669162445387452e-05, "loss": 0.0013, "step": 324220 }, { "epoch": 77.84, "learning_rate": 1.566655284544503e-05, "loss": 0.0015, "step": 324230 }, { "epoch": 77.84, "learning_rate": 1.5663943422457467e-05, "loss": 0.0012, "step": 324240 }, { "epoch": 77.85, "learning_rate": 1.5661334176438242e-05, "loss": 0.0016, "step": 324250 }, { "epoch": 77.85, "learning_rate": 1.5658725107400784e-05, "loss": 0.0013, "step": 324260 }, { "epoch": 77.85, "learning_rate": 1.5656116215358528e-05, "loss": 0.0013, "step": 324270 }, { "epoch": 77.85, "learning_rate": 1.565350750032496e-05, "loss": 0.002, "step": 324280 }, { "epoch": 77.85, "learning_rate": 1.5650898962313475e-05, "loss": 0.0013, "step": 324290 }, { "epoch": 77.86, "learning_rate": 1.5648290601337566e-05, "loss": 0.0014, "step": 324300 }, { "epoch": 77.86, "learning_rate": 1.564568241741064e-05, "loss": 0.0019, "step": 324310 }, { "epoch": 77.86, "learning_rate": 1.5643074410546165e-05, "loss": 0.0018, "step": 324320 }, { "epoch": 77.86, "learning_rate": 1.564046658075758e-05, "loss": 0.0014, "step": 324330 }, { "epoch": 77.87, "learning_rate": 1.563785892805829e-05, "loss": 0.005, "step": 324340 }, { "epoch": 77.87, "learning_rate": 1.5635251452461787e-05, "loss": 0.0015, "step": 324350 }, { "epoch": 77.87, "learning_rate": 1.5632644153981463e-05, "loss": 0.0016, "step": 324360 }, { "epoch": 77.87, "learning_rate": 1.56300370326308e-05, "loss": 0.0014, "step": 324370 }, { "epoch": 77.88, "learning_rate": 1.5627430088423197e-05, "loss": 0.0015, "step": 324380 }, { "epoch": 77.88, "learning_rate": 1.5624823321372116e-05, "loss": 0.0015, "step": 324390 }, { "epoch": 77.88, "learning_rate": 1.5622216731490973e-05, "loss": 0.0022, "step": 324400 }, { "epoch": 77.88, "learning_rate": 1.5619610318793226e-05, "loss": 0.0013, "step": 324410 }, { "epoch": 77.88, "learning_rate": 1.561700408329228e-05, "loss": 0.0016, "step": 324420 }, { "epoch": 77.89, "learning_rate": 1.56143980250016e-05, "loss": 0.0012, "step": 324430 }, { "epoch": 77.89, "learning_rate": 1.5611792143934577e-05, "loss": 0.0019, "step": 324440 }, { "epoch": 77.89, "learning_rate": 1.5609186440104673e-05, "loss": 0.0016, "step": 324450 }, { "epoch": 77.89, "learning_rate": 1.560658091352532e-05, "loss": 0.0014, "step": 324460 }, { "epoch": 77.9, "learning_rate": 1.5603975564209937e-05, "loss": 0.0273, "step": 324470 }, { "epoch": 77.9, "learning_rate": 1.560137039217194e-05, "loss": 0.0016, "step": 324480 }, { "epoch": 77.9, "learning_rate": 1.559876539742478e-05, "loss": 0.0012, "step": 324490 }, { "epoch": 77.9, "learning_rate": 1.5596160579981855e-05, "loss": 0.0055, "step": 324500 }, { "epoch": 77.9, "learning_rate": 1.5593555939856624e-05, "loss": 0.0013, "step": 324510 }, { "epoch": 77.91, "learning_rate": 1.559095147706247e-05, "loss": 0.0013, "step": 324520 }, { "epoch": 77.91, "learning_rate": 1.5588347191612862e-05, "loss": 0.0013, "step": 324530 }, { "epoch": 77.91, "learning_rate": 1.5585743083521202e-05, "loss": 0.0015, "step": 324540 }, { "epoch": 77.91, "learning_rate": 1.558313915280089e-05, "loss": 0.0016, "step": 324550 }, { "epoch": 77.92, "learning_rate": 1.5580535399465383e-05, "loss": 0.0015, "step": 324560 }, { "epoch": 77.92, "learning_rate": 1.5577931823528068e-05, "loss": 0.0013, "step": 324570 }, { "epoch": 77.92, "learning_rate": 1.55753284250024e-05, "loss": 0.0024, "step": 324580 }, { "epoch": 77.92, "learning_rate": 1.5572725203901755e-05, "loss": 0.0016, "step": 324590 }, { "epoch": 77.93, "learning_rate": 1.557012216023959e-05, "loss": 0.0013, "step": 324600 }, { "epoch": 77.93, "learning_rate": 1.556751929402929e-05, "loss": 0.0012, "step": 324610 }, { "epoch": 77.93, "learning_rate": 1.5564916605284297e-05, "loss": 0.0015, "step": 324620 }, { "epoch": 77.93, "learning_rate": 1.5562314094018014e-05, "loss": 0.0013, "step": 324630 }, { "epoch": 77.93, "learning_rate": 1.5559711760243833e-05, "loss": 0.0017, "step": 324640 }, { "epoch": 77.94, "learning_rate": 1.5557109603975205e-05, "loss": 0.0014, "step": 324650 }, { "epoch": 77.94, "learning_rate": 1.5554507625225502e-05, "loss": 0.0014, "step": 324660 }, { "epoch": 77.94, "learning_rate": 1.5551905824008172e-05, "loss": 0.0013, "step": 324670 }, { "epoch": 77.94, "learning_rate": 1.5549304200336595e-05, "loss": 0.0012, "step": 324680 }, { "epoch": 77.95, "learning_rate": 1.55467027542242e-05, "loss": 0.0013, "step": 324690 }, { "epoch": 77.95, "learning_rate": 1.554410148568439e-05, "loss": 0.0013, "step": 324700 }, { "epoch": 77.95, "learning_rate": 1.5541500394730557e-05, "loss": 0.0015, "step": 324710 }, { "epoch": 78.0, "learning_rate": 1.5538899481376117e-05, "loss": 0.0011, "step": 324720 }, { "epoch": 78.0, "learning_rate": 1.5536298745634498e-05, "loss": 0.0014, "step": 324730 }, { "epoch": 78.01, "learning_rate": 1.553369818751906e-05, "loss": 0.0014, "step": 324740 }, { "epoch": 78.01, "learning_rate": 1.5531097807043247e-05, "loss": 0.0015, "step": 324750 }, { "epoch": 78.01, "learning_rate": 1.5528497604220427e-05, "loss": 0.0013, "step": 324760 }, { "epoch": 78.01, "learning_rate": 1.5525897579064037e-05, "loss": 0.0013, "step": 324770 }, { "epoch": 78.02, "learning_rate": 1.5523297731587445e-05, "loss": 0.0013, "step": 324780 }, { "epoch": 78.02, "learning_rate": 1.5520698061804077e-05, "loss": 0.0013, "step": 324790 }, { "epoch": 78.02, "learning_rate": 1.55180985697273e-05, "loss": 0.0012, "step": 324800 }, { "epoch": 78.02, "learning_rate": 1.551549925537056e-05, "loss": 0.0013, "step": 324810 }, { "epoch": 78.02, "learning_rate": 1.5512900118747197e-05, "loss": 0.0014, "step": 324820 }, { "epoch": 78.03, "learning_rate": 1.5510301159870654e-05, "loss": 0.0012, "step": 324830 }, { "epoch": 78.03, "learning_rate": 1.550770237875431e-05, "loss": 0.0012, "step": 324840 }, { "epoch": 78.03, "learning_rate": 1.5505103775411538e-05, "loss": 0.0013, "step": 324850 }, { "epoch": 78.03, "learning_rate": 1.5502505349855768e-05, "loss": 0.0012, "step": 324860 }, { "epoch": 78.04, "learning_rate": 1.549990710210035e-05, "loss": 0.0014, "step": 324870 }, { "epoch": 78.04, "learning_rate": 1.5497309032158723e-05, "loss": 0.0013, "step": 324880 }, { "epoch": 78.04, "learning_rate": 1.5494711140044232e-05, "loss": 0.0013, "step": 324890 }, { "epoch": 78.04, "learning_rate": 1.549211342577031e-05, "loss": 0.0011, "step": 324900 }, { "epoch": 78.04, "learning_rate": 1.548951588935032e-05, "loss": 0.0017, "step": 324910 }, { "epoch": 78.05, "learning_rate": 1.548691853079764e-05, "loss": 0.0013, "step": 324920 }, { "epoch": 78.05, "learning_rate": 1.5484321350125684e-05, "loss": 0.0014, "step": 324930 }, { "epoch": 78.05, "learning_rate": 1.548172434734781e-05, "loss": 0.0024, "step": 324940 }, { "epoch": 78.05, "learning_rate": 1.5479127522477433e-05, "loss": 0.0013, "step": 324950 }, { "epoch": 78.06, "learning_rate": 1.5476530875527907e-05, "loss": 0.0014, "step": 324960 }, { "epoch": 78.06, "learning_rate": 1.547393440651264e-05, "loss": 0.0012, "step": 324970 }, { "epoch": 78.06, "learning_rate": 1.547133811544501e-05, "loss": 0.0013, "step": 324980 }, { "epoch": 78.06, "learning_rate": 1.546874200233837e-05, "loss": 0.0015, "step": 324990 }, { "epoch": 78.07, "learning_rate": 1.5466146067206145e-05, "loss": 0.0013, "step": 325000 }, { "epoch": 78.07, "learning_rate": 1.546355031006167e-05, "loss": 0.0012, "step": 325010 }, { "epoch": 78.07, "learning_rate": 1.5460954730918348e-05, "loss": 0.0011, "step": 325020 }, { "epoch": 78.07, "learning_rate": 1.5458359329789573e-05, "loss": 0.0013, "step": 325030 }, { "epoch": 78.07, "learning_rate": 1.545576410668868e-05, "loss": 0.0013, "step": 325040 }, { "epoch": 78.08, "learning_rate": 1.5453169061629085e-05, "loss": 0.0013, "step": 325050 }, { "epoch": 78.08, "learning_rate": 1.5450574194624136e-05, "loss": 0.0015, "step": 325060 }, { "epoch": 78.08, "learning_rate": 1.5447979505687226e-05, "loss": 0.0013, "step": 325070 }, { "epoch": 78.08, "learning_rate": 1.54453849948317e-05, "loss": 0.0013, "step": 325080 }, { "epoch": 78.09, "learning_rate": 1.544279066207097e-05, "loss": 0.0011, "step": 325090 }, { "epoch": 78.09, "learning_rate": 1.544019650741837e-05, "loss": 0.0012, "step": 325100 }, { "epoch": 78.09, "learning_rate": 1.5437602530887303e-05, "loss": 0.0012, "step": 325110 }, { "epoch": 78.09, "learning_rate": 1.543500873249112e-05, "loss": 0.0012, "step": 325120 }, { "epoch": 78.1, "learning_rate": 1.543241511224317e-05, "loss": 0.0011, "step": 325130 }, { "epoch": 78.1, "learning_rate": 1.5429821670156862e-05, "loss": 0.0013, "step": 325140 }, { "epoch": 78.1, "learning_rate": 1.5427228406245526e-05, "loss": 0.0012, "step": 325150 }, { "epoch": 78.1, "learning_rate": 1.5424635320522563e-05, "loss": 0.0033, "step": 325160 }, { "epoch": 78.1, "learning_rate": 1.54220424130013e-05, "loss": 0.0013, "step": 325170 }, { "epoch": 78.11, "learning_rate": 1.541944968369513e-05, "loss": 0.0013, "step": 325180 }, { "epoch": 78.11, "learning_rate": 1.541685713261741e-05, "loss": 0.0012, "step": 325190 }, { "epoch": 78.11, "learning_rate": 1.5414264759781483e-05, "loss": 0.0022, "step": 325200 }, { "epoch": 78.11, "learning_rate": 1.5411672565200735e-05, "loss": 0.0013, "step": 325210 }, { "epoch": 78.12, "learning_rate": 1.5409080548888503e-05, "loss": 0.0013, "step": 325220 }, { "epoch": 78.12, "learning_rate": 1.540648871085818e-05, "loss": 0.0012, "step": 325230 }, { "epoch": 78.12, "learning_rate": 1.5403897051123085e-05, "loss": 0.0013, "step": 325240 }, { "epoch": 78.12, "learning_rate": 1.5401305569696605e-05, "loss": 0.0014, "step": 325250 }, { "epoch": 78.12, "learning_rate": 1.5398714266592084e-05, "loss": 0.0012, "step": 325260 }, { "epoch": 78.13, "learning_rate": 1.5396123141822873e-05, "loss": 0.0013, "step": 325270 }, { "epoch": 78.13, "learning_rate": 1.5393532195402337e-05, "loss": 0.0012, "step": 325280 }, { "epoch": 78.13, "learning_rate": 1.5390941427343813e-05, "loss": 0.0011, "step": 325290 }, { "epoch": 78.13, "learning_rate": 1.5388350837660687e-05, "loss": 0.0014, "step": 325300 }, { "epoch": 78.14, "learning_rate": 1.538576042636627e-05, "loss": 0.0014, "step": 325310 }, { "epoch": 78.14, "learning_rate": 1.538317019347395e-05, "loss": 0.0013, "step": 325320 }, { "epoch": 78.14, "learning_rate": 1.5380580138997048e-05, "loss": 0.0013, "step": 325330 }, { "epoch": 78.14, "learning_rate": 1.5377990262948917e-05, "loss": 0.0014, "step": 325340 }, { "epoch": 78.15, "learning_rate": 1.5375400565342934e-05, "loss": 0.0013, "step": 325350 }, { "epoch": 78.15, "learning_rate": 1.537281104619241e-05, "loss": 0.0013, "step": 325360 }, { "epoch": 78.15, "learning_rate": 1.5370221705510725e-05, "loss": 0.0013, "step": 325370 }, { "epoch": 78.15, "learning_rate": 1.536763254331119e-05, "loss": 0.0012, "step": 325380 }, { "epoch": 78.15, "learning_rate": 1.5365043559607177e-05, "loss": 0.0013, "step": 325390 }, { "epoch": 78.16, "learning_rate": 1.536245475441201e-05, "loss": 0.0012, "step": 325400 }, { "epoch": 78.16, "learning_rate": 1.5359866127739052e-05, "loss": 0.0013, "step": 325410 }, { "epoch": 78.16, "learning_rate": 1.535727767960164e-05, "loss": 0.0012, "step": 325420 }, { "epoch": 78.16, "learning_rate": 1.5354689410013085e-05, "loss": 0.0014, "step": 325430 }, { "epoch": 78.17, "learning_rate": 1.535210131898677e-05, "loss": 0.0012, "step": 325440 }, { "epoch": 78.17, "learning_rate": 1.5349513406536e-05, "loss": 0.0012, "step": 325450 }, { "epoch": 78.17, "learning_rate": 1.534692567267414e-05, "loss": 0.0013, "step": 325460 }, { "epoch": 78.17, "learning_rate": 1.5344338117414496e-05, "loss": 0.0012, "step": 325470 }, { "epoch": 78.18, "learning_rate": 1.5341750740770444e-05, "loss": 0.0014, "step": 325480 }, { "epoch": 78.18, "learning_rate": 1.5339163542755303e-05, "loss": 0.0012, "step": 325490 }, { "epoch": 78.18, "learning_rate": 1.533657652338238e-05, "loss": 0.0011, "step": 325500 }, { "epoch": 78.18, "learning_rate": 1.5333989682665044e-05, "loss": 0.0011, "step": 325510 }, { "epoch": 78.18, "learning_rate": 1.5331403020616608e-05, "loss": 0.0038, "step": 325520 }, { "epoch": 78.19, "learning_rate": 1.5328816537250422e-05, "loss": 0.0012, "step": 325530 }, { "epoch": 78.19, "learning_rate": 1.5326230232579785e-05, "loss": 0.0012, "step": 325540 }, { "epoch": 78.19, "learning_rate": 1.5323644106618074e-05, "loss": 0.0013, "step": 325550 }, { "epoch": 78.19, "learning_rate": 1.5321058159378583e-05, "loss": 0.0013, "step": 325560 }, { "epoch": 78.2, "learning_rate": 1.5318472390874632e-05, "loss": 0.0013, "step": 325570 }, { "epoch": 78.2, "learning_rate": 1.5315886801119582e-05, "loss": 0.0014, "step": 325580 }, { "epoch": 78.2, "learning_rate": 1.5313301390126727e-05, "loss": 0.0014, "step": 325590 }, { "epoch": 78.2, "learning_rate": 1.531071615790942e-05, "loss": 0.0013, "step": 325600 }, { "epoch": 78.2, "learning_rate": 1.530813110448096e-05, "loss": 0.0012, "step": 325610 }, { "epoch": 78.21, "learning_rate": 1.5305546229854696e-05, "loss": 0.0013, "step": 325620 }, { "epoch": 78.21, "learning_rate": 1.5302961534043918e-05, "loss": 0.0015, "step": 325630 }, { "epoch": 78.21, "learning_rate": 1.5300377017061985e-05, "loss": 0.0013, "step": 325640 }, { "epoch": 78.21, "learning_rate": 1.529779267892218e-05, "loss": 0.0025, "step": 325650 }, { "epoch": 78.22, "learning_rate": 1.5295208519637844e-05, "loss": 0.0012, "step": 325660 }, { "epoch": 78.22, "learning_rate": 1.529262453922231e-05, "loss": 0.0012, "step": 325670 }, { "epoch": 78.22, "learning_rate": 1.529004073768886e-05, "loss": 0.0012, "step": 325680 }, { "epoch": 78.22, "learning_rate": 1.528745711505085e-05, "loss": 0.0012, "step": 325690 }, { "epoch": 78.23, "learning_rate": 1.5284873671321576e-05, "loss": 0.0013, "step": 325700 }, { "epoch": 78.23, "learning_rate": 1.5282290406514337e-05, "loss": 0.0012, "step": 325710 }, { "epoch": 78.23, "learning_rate": 1.5279707320642477e-05, "loss": 0.0011, "step": 325720 }, { "epoch": 78.23, "learning_rate": 1.527712441371928e-05, "loss": 0.0012, "step": 325730 }, { "epoch": 78.23, "learning_rate": 1.5274541685758094e-05, "loss": 0.0013, "step": 325740 }, { "epoch": 78.24, "learning_rate": 1.527195913677219e-05, "loss": 0.0013, "step": 325750 }, { "epoch": 78.24, "learning_rate": 1.5269376766774916e-05, "loss": 0.0014, "step": 325760 }, { "epoch": 78.24, "learning_rate": 1.5266794575779565e-05, "loss": 0.0013, "step": 325770 }, { "epoch": 78.24, "learning_rate": 1.526421256379943e-05, "loss": 0.0014, "step": 325780 }, { "epoch": 78.25, "learning_rate": 1.526163073084785e-05, "loss": 0.0012, "step": 325790 }, { "epoch": 78.25, "learning_rate": 1.5259049076938098e-05, "loss": 0.0013, "step": 325800 }, { "epoch": 78.25, "learning_rate": 1.5256467602083513e-05, "loss": 0.0012, "step": 325810 }, { "epoch": 78.25, "learning_rate": 1.5253886306297371e-05, "loss": 0.0012, "step": 325820 }, { "epoch": 78.26, "learning_rate": 1.5251305189593002e-05, "loss": 0.0012, "step": 325830 }, { "epoch": 78.26, "learning_rate": 1.5248724251983699e-05, "loss": 0.0012, "step": 325840 }, { "epoch": 78.26, "learning_rate": 1.5246143493482746e-05, "loss": 0.0013, "step": 325850 }, { "epoch": 78.26, "learning_rate": 1.5243562914103471e-05, "loss": 0.0012, "step": 325860 }, { "epoch": 78.26, "learning_rate": 1.5240982513859154e-05, "loss": 0.0012, "step": 325870 }, { "epoch": 78.27, "learning_rate": 1.5238402292763115e-05, "loss": 0.0015, "step": 325880 }, { "epoch": 78.27, "learning_rate": 1.5235822250828623e-05, "loss": 0.0012, "step": 325890 }, { "epoch": 78.27, "learning_rate": 1.5233242388069019e-05, "loss": 0.0014, "step": 325900 }, { "epoch": 78.27, "learning_rate": 1.523066270449755e-05, "loss": 0.0013, "step": 325910 }, { "epoch": 78.28, "learning_rate": 1.5228083200127557e-05, "loss": 0.0014, "step": 325920 }, { "epoch": 78.28, "learning_rate": 1.5225503874972297e-05, "loss": 0.0011, "step": 325930 }, { "epoch": 78.28, "learning_rate": 1.522292472904509e-05, "loss": 0.0011, "step": 325940 }, { "epoch": 78.28, "learning_rate": 1.5220345762359211e-05, "loss": 0.0013, "step": 325950 }, { "epoch": 78.28, "learning_rate": 1.521776697492796e-05, "loss": 0.0012, "step": 325960 }, { "epoch": 78.29, "learning_rate": 1.5215188366764643e-05, "loss": 0.001, "step": 325970 }, { "epoch": 78.29, "learning_rate": 1.5212609937882539e-05, "loss": 0.0013, "step": 325980 }, { "epoch": 78.29, "learning_rate": 1.5210031688294912e-05, "loss": 0.0013, "step": 325990 }, { "epoch": 78.29, "learning_rate": 1.5207453618015094e-05, "loss": 0.0012, "step": 326000 }, { "epoch": 78.3, "learning_rate": 1.5204875727056333e-05, "loss": 0.0013, "step": 326010 }, { "epoch": 78.3, "learning_rate": 1.5202298015431949e-05, "loss": 0.0012, "step": 326020 }, { "epoch": 78.3, "learning_rate": 1.5199720483155194e-05, "loss": 0.0013, "step": 326030 }, { "epoch": 78.3, "learning_rate": 1.5197143130239388e-05, "loss": 0.0013, "step": 326040 }, { "epoch": 78.31, "learning_rate": 1.5194565956697798e-05, "loss": 0.0011, "step": 326050 }, { "epoch": 78.31, "learning_rate": 1.5191988962543691e-05, "loss": 0.0012, "step": 326060 }, { "epoch": 78.31, "learning_rate": 1.5189412147790377e-05, "loss": 0.0014, "step": 326070 }, { "epoch": 78.31, "learning_rate": 1.5186835512451114e-05, "loss": 0.0013, "step": 326080 }, { "epoch": 78.31, "learning_rate": 1.5184259056539201e-05, "loss": 0.0012, "step": 326090 }, { "epoch": 78.32, "learning_rate": 1.5181682780067896e-05, "loss": 0.0011, "step": 326100 }, { "epoch": 78.32, "learning_rate": 1.5179106683050504e-05, "loss": 0.0011, "step": 326110 }, { "epoch": 78.32, "learning_rate": 1.5176530765500285e-05, "loss": 0.0012, "step": 326120 }, { "epoch": 78.32, "learning_rate": 1.5173955027430502e-05, "loss": 0.0014, "step": 326130 }, { "epoch": 78.33, "learning_rate": 1.5171379468854464e-05, "loss": 0.0013, "step": 326140 }, { "epoch": 78.33, "learning_rate": 1.516880408978541e-05, "loss": 0.0015, "step": 326150 }, { "epoch": 78.33, "learning_rate": 1.5166228890236644e-05, "loss": 0.0013, "step": 326160 }, { "epoch": 78.33, "learning_rate": 1.5163653870221411e-05, "loss": 0.0013, "step": 326170 }, { "epoch": 78.34, "learning_rate": 1.5161079029753017e-05, "loss": 0.0012, "step": 326180 }, { "epoch": 78.34, "learning_rate": 1.5158504368844695e-05, "loss": 0.0012, "step": 326190 }, { "epoch": 78.34, "learning_rate": 1.5155929887509746e-05, "loss": 0.0013, "step": 326200 }, { "epoch": 78.34, "learning_rate": 1.515335558576143e-05, "loss": 0.0011, "step": 326210 }, { "epoch": 78.34, "learning_rate": 1.515078146361299e-05, "loss": 0.0012, "step": 326220 }, { "epoch": 78.35, "learning_rate": 1.5148207521077718e-05, "loss": 0.0013, "step": 326230 }, { "epoch": 78.35, "learning_rate": 1.5145633758168888e-05, "loss": 0.0013, "step": 326240 }, { "epoch": 78.35, "learning_rate": 1.5143060174899742e-05, "loss": 0.0027, "step": 326250 }, { "epoch": 78.35, "learning_rate": 1.5140486771283563e-05, "loss": 0.0015, "step": 326260 }, { "epoch": 78.36, "learning_rate": 1.5137913547333598e-05, "loss": 0.0013, "step": 326270 }, { "epoch": 78.36, "learning_rate": 1.5135340503063133e-05, "loss": 0.0014, "step": 326280 }, { "epoch": 78.36, "learning_rate": 1.5132767638485396e-05, "loss": 0.0012, "step": 326290 }, { "epoch": 78.36, "learning_rate": 1.513019495361368e-05, "loss": 0.0013, "step": 326300 }, { "epoch": 78.36, "learning_rate": 1.512762244846122e-05, "loss": 0.0012, "step": 326310 }, { "epoch": 78.37, "learning_rate": 1.51250501230413e-05, "loss": 0.0012, "step": 326320 }, { "epoch": 78.37, "learning_rate": 1.5122477977367144e-05, "loss": 0.0013, "step": 326330 }, { "epoch": 78.37, "learning_rate": 1.5119906011452045e-05, "loss": 0.0016, "step": 326340 }, { "epoch": 78.37, "learning_rate": 1.5117334225309242e-05, "loss": 0.0013, "step": 326350 }, { "epoch": 78.38, "learning_rate": 1.5114762618951978e-05, "loss": 0.0012, "step": 326360 }, { "epoch": 78.38, "learning_rate": 1.5112191192393532e-05, "loss": 0.0013, "step": 326370 }, { "epoch": 78.38, "learning_rate": 1.510961994564713e-05, "loss": 0.0013, "step": 326380 }, { "epoch": 78.38, "learning_rate": 1.510704887872605e-05, "loss": 0.0016, "step": 326390 }, { "epoch": 78.39, "learning_rate": 1.5104477991643517e-05, "loss": 0.0011, "step": 326400 }, { "epoch": 78.39, "learning_rate": 1.510190728441282e-05, "loss": 0.0015, "step": 326410 }, { "epoch": 78.39, "learning_rate": 1.5099336757047177e-05, "loss": 0.0011, "step": 326420 }, { "epoch": 78.39, "learning_rate": 1.5096766409559827e-05, "loss": 0.0012, "step": 326430 }, { "epoch": 78.39, "learning_rate": 1.5094196241964054e-05, "loss": 0.0013, "step": 326440 }, { "epoch": 78.4, "learning_rate": 1.5091626254273068e-05, "loss": 0.0012, "step": 326450 }, { "epoch": 78.4, "learning_rate": 1.5089056446500149e-05, "loss": 0.0012, "step": 326460 }, { "epoch": 78.4, "learning_rate": 1.5086486818658508e-05, "loss": 0.0012, "step": 326470 }, { "epoch": 78.4, "learning_rate": 1.508391737076142e-05, "loss": 0.0013, "step": 326480 }, { "epoch": 78.41, "learning_rate": 1.5081348102822118e-05, "loss": 0.0012, "step": 326490 }, { "epoch": 78.41, "learning_rate": 1.5078779014853822e-05, "loss": 0.001, "step": 326500 }, { "epoch": 78.41, "learning_rate": 1.5076210106869804e-05, "loss": 0.0012, "step": 326510 }, { "epoch": 78.41, "learning_rate": 1.507364137888328e-05, "loss": 0.0012, "step": 326520 }, { "epoch": 78.41, "learning_rate": 1.5071072830907495e-05, "loss": 0.0013, "step": 326530 }, { "epoch": 78.42, "learning_rate": 1.5068504462955712e-05, "loss": 0.0013, "step": 326540 }, { "epoch": 78.42, "learning_rate": 1.5065936275041132e-05, "loss": 0.0012, "step": 326550 }, { "epoch": 78.42, "learning_rate": 1.5063368267177025e-05, "loss": 0.0012, "step": 326560 }, { "epoch": 78.42, "learning_rate": 1.5060800439376593e-05, "loss": 0.0013, "step": 326570 }, { "epoch": 78.43, "learning_rate": 1.5058232791653105e-05, "loss": 0.001, "step": 326580 }, { "epoch": 78.43, "learning_rate": 1.5055665324019764e-05, "loss": 0.0011, "step": 326590 }, { "epoch": 78.43, "learning_rate": 1.5053098036489826e-05, "loss": 0.0012, "step": 326600 }, { "epoch": 78.43, "learning_rate": 1.50505309290765e-05, "loss": 0.0013, "step": 326610 }, { "epoch": 78.44, "learning_rate": 1.5047964001793047e-05, "loss": 0.0011, "step": 326620 }, { "epoch": 78.44, "learning_rate": 1.5045397254652677e-05, "loss": 0.0011, "step": 326630 }, { "epoch": 78.44, "learning_rate": 1.5042830687668602e-05, "loss": 0.0013, "step": 326640 }, { "epoch": 78.44, "learning_rate": 1.5040264300854096e-05, "loss": 0.0012, "step": 326650 }, { "epoch": 78.44, "learning_rate": 1.5037698094222335e-05, "loss": 0.0012, "step": 326660 }, { "epoch": 78.45, "learning_rate": 1.5035132067786588e-05, "loss": 0.0012, "step": 326670 }, { "epoch": 78.45, "learning_rate": 1.5032566221560052e-05, "loss": 0.0012, "step": 326680 }, { "epoch": 78.45, "learning_rate": 1.5030000555555973e-05, "loss": 0.0014, "step": 326690 }, { "epoch": 78.45, "learning_rate": 1.5027435069787565e-05, "loss": 0.0013, "step": 326700 }, { "epoch": 78.46, "learning_rate": 1.5024869764268029e-05, "loss": 0.0013, "step": 326710 }, { "epoch": 78.46, "learning_rate": 1.5022304639010627e-05, "loss": 0.0012, "step": 326720 }, { "epoch": 78.46, "learning_rate": 1.5019739694028546e-05, "loss": 0.0014, "step": 326730 }, { "epoch": 78.46, "learning_rate": 1.5017174929335032e-05, "loss": 0.0013, "step": 326740 }, { "epoch": 78.47, "learning_rate": 1.5014610344943269e-05, "loss": 0.0013, "step": 326750 }, { "epoch": 78.47, "learning_rate": 1.501204594086652e-05, "loss": 0.0012, "step": 326760 }, { "epoch": 78.47, "learning_rate": 1.5009481717117979e-05, "loss": 0.0013, "step": 326770 }, { "epoch": 78.47, "learning_rate": 1.5006917673710841e-05, "loss": 0.0011, "step": 326780 }, { "epoch": 78.47, "learning_rate": 1.5004353810658362e-05, "loss": 0.0012, "step": 326790 }, { "epoch": 78.48, "learning_rate": 1.5001790127973719e-05, "loss": 0.0011, "step": 326800 }, { "epoch": 78.48, "learning_rate": 1.4999226625670154e-05, "loss": 0.0012, "step": 326810 }, { "epoch": 78.48, "learning_rate": 1.4996663303760855e-05, "loss": 0.0014, "step": 326820 }, { "epoch": 78.48, "learning_rate": 1.4994100162259062e-05, "loss": 0.0013, "step": 326830 }, { "epoch": 78.49, "learning_rate": 1.4991537201177952e-05, "loss": 0.0011, "step": 326840 }, { "epoch": 78.49, "learning_rate": 1.4988974420530754e-05, "loss": 0.0013, "step": 326850 }, { "epoch": 78.49, "learning_rate": 1.4986411820330692e-05, "loss": 0.0012, "step": 326860 }, { "epoch": 78.49, "learning_rate": 1.4983849400590939e-05, "loss": 0.0012, "step": 326870 }, { "epoch": 78.49, "learning_rate": 1.498128716132473e-05, "loss": 0.0012, "step": 326880 }, { "epoch": 78.5, "learning_rate": 1.4978725102545249e-05, "loss": 0.0011, "step": 326890 }, { "epoch": 78.5, "learning_rate": 1.4976163224265726e-05, "loss": 0.0012, "step": 326900 }, { "epoch": 78.5, "learning_rate": 1.4973601526499349e-05, "loss": 0.0012, "step": 326910 }, { "epoch": 78.5, "learning_rate": 1.4971040009259307e-05, "loss": 0.0013, "step": 326920 }, { "epoch": 78.51, "learning_rate": 1.4968478672558838e-05, "loss": 0.0011, "step": 326930 }, { "epoch": 78.51, "learning_rate": 1.4965917516411104e-05, "loss": 0.0013, "step": 326940 }, { "epoch": 78.51, "learning_rate": 1.4963356540829337e-05, "loss": 0.0013, "step": 326950 }, { "epoch": 78.51, "learning_rate": 1.4960795745826712e-05, "loss": 0.0012, "step": 326960 }, { "epoch": 78.52, "learning_rate": 1.4958235131416448e-05, "loss": 0.0012, "step": 326970 }, { "epoch": 78.52, "learning_rate": 1.4955674697611738e-05, "loss": 0.0012, "step": 326980 }, { "epoch": 78.52, "learning_rate": 1.4953114444425759e-05, "loss": 0.0011, "step": 326990 }, { "epoch": 78.52, "learning_rate": 1.4950554371871733e-05, "loss": 0.0012, "step": 327000 }, { "epoch": 78.52, "learning_rate": 1.4947994479962829e-05, "loss": 0.0015, "step": 327010 }, { "epoch": 78.53, "learning_rate": 1.4945434768712268e-05, "loss": 0.0012, "step": 327020 }, { "epoch": 78.53, "learning_rate": 1.4942875238133214e-05, "loss": 0.0023, "step": 327030 }, { "epoch": 78.53, "learning_rate": 1.4940315888238892e-05, "loss": 0.0018, "step": 327040 }, { "epoch": 78.53, "learning_rate": 1.4937756719042462e-05, "loss": 0.0011, "step": 327050 }, { "epoch": 78.54, "learning_rate": 1.4935197730557137e-05, "loss": 0.0014, "step": 327060 }, { "epoch": 78.54, "learning_rate": 1.49326389227961e-05, "loss": 0.0012, "step": 327070 }, { "epoch": 78.54, "learning_rate": 1.4930080295772514e-05, "loss": 0.0014, "step": 327080 }, { "epoch": 78.54, "learning_rate": 1.4927521849499604e-05, "loss": 0.0012, "step": 327090 }, { "epoch": 78.55, "learning_rate": 1.492496358399053e-05, "loss": 0.0033, "step": 327100 }, { "epoch": 78.55, "learning_rate": 1.4922405499258497e-05, "loss": 0.0012, "step": 327110 }, { "epoch": 78.55, "learning_rate": 1.4919847595316666e-05, "loss": 0.0026, "step": 327120 }, { "epoch": 78.55, "learning_rate": 1.4917289872178247e-05, "loss": 0.0014, "step": 327130 }, { "epoch": 78.55, "learning_rate": 1.4914732329856396e-05, "loss": 0.0025, "step": 327140 }, { "epoch": 78.56, "learning_rate": 1.4912174968364323e-05, "loss": 0.0012, "step": 327150 }, { "epoch": 78.56, "learning_rate": 1.490961778771518e-05, "loss": 0.0013, "step": 327160 }, { "epoch": 78.56, "learning_rate": 1.4907060787922156e-05, "loss": 0.0013, "step": 327170 }, { "epoch": 78.56, "learning_rate": 1.490450396899845e-05, "loss": 0.0013, "step": 327180 }, { "epoch": 78.57, "learning_rate": 1.4901947330957212e-05, "loss": 0.0166, "step": 327190 }, { "epoch": 78.57, "learning_rate": 1.4899390873811642e-05, "loss": 0.0014, "step": 327200 }, { "epoch": 78.57, "learning_rate": 1.489683459757491e-05, "loss": 0.0014, "step": 327210 }, { "epoch": 78.57, "learning_rate": 1.4894278502260167e-05, "loss": 0.0016, "step": 327220 }, { "epoch": 78.57, "learning_rate": 1.4891722587880619e-05, "loss": 0.0013, "step": 327230 }, { "epoch": 78.58, "learning_rate": 1.4889166854449415e-05, "loss": 0.0014, "step": 327240 }, { "epoch": 78.58, "learning_rate": 1.4886611301979752e-05, "loss": 0.0013, "step": 327250 }, { "epoch": 78.58, "learning_rate": 1.4884055930484775e-05, "loss": 0.0019, "step": 327260 }, { "epoch": 78.58, "learning_rate": 1.4881500739977678e-05, "loss": 0.0017, "step": 327270 }, { "epoch": 78.59, "learning_rate": 1.4878945730471628e-05, "loss": 0.0012, "step": 327280 }, { "epoch": 78.59, "learning_rate": 1.4876390901979759e-05, "loss": 0.0014, "step": 327290 }, { "epoch": 78.59, "learning_rate": 1.487383625451529e-05, "loss": 0.0052, "step": 327300 }, { "epoch": 78.59, "learning_rate": 1.487128178809134e-05, "loss": 0.0016, "step": 327310 }, { "epoch": 78.6, "learning_rate": 1.4868727502721114e-05, "loss": 0.0014, "step": 327320 }, { "epoch": 78.6, "learning_rate": 1.4866173398417749e-05, "loss": 0.0014, "step": 327330 }, { "epoch": 78.6, "learning_rate": 1.486361947519443e-05, "loss": 0.0012, "step": 327340 }, { "epoch": 78.6, "learning_rate": 1.4861065733064317e-05, "loss": 0.0013, "step": 327350 }, { "epoch": 78.6, "learning_rate": 1.485851217204054e-05, "loss": 0.0013, "step": 327360 }, { "epoch": 78.61, "learning_rate": 1.485595879213631e-05, "loss": 0.0013, "step": 327370 }, { "epoch": 78.61, "learning_rate": 1.485340559336474e-05, "loss": 0.0015, "step": 327380 }, { "epoch": 78.61, "learning_rate": 1.4850852575739027e-05, "loss": 0.0012, "step": 327390 }, { "epoch": 78.61, "learning_rate": 1.4848299739272303e-05, "loss": 0.0012, "step": 327400 }, { "epoch": 78.62, "learning_rate": 1.4845747083977746e-05, "loss": 0.0014, "step": 327410 }, { "epoch": 78.62, "learning_rate": 1.4843194609868493e-05, "loss": 0.0023, "step": 327420 }, { "epoch": 78.62, "learning_rate": 1.484064231695772e-05, "loss": 0.0014, "step": 327430 }, { "epoch": 78.62, "learning_rate": 1.4838090205258554e-05, "loss": 0.0012, "step": 327440 }, { "epoch": 78.63, "learning_rate": 1.4835538274784182e-05, "loss": 0.0014, "step": 327450 }, { "epoch": 78.63, "learning_rate": 1.4832986525547726e-05, "loss": 0.0014, "step": 327460 }, { "epoch": 78.63, "learning_rate": 1.4830434957562367e-05, "loss": 0.0015, "step": 327470 }, { "epoch": 78.63, "learning_rate": 1.4827883570841222e-05, "loss": 0.0012, "step": 327480 }, { "epoch": 78.63, "learning_rate": 1.4825332365397477e-05, "loss": 0.0014, "step": 327490 }, { "epoch": 78.64, "learning_rate": 1.4822781341244241e-05, "loss": 0.0013, "step": 327500 }, { "epoch": 78.64, "learning_rate": 1.4820230498394704e-05, "loss": 0.0031, "step": 327510 }, { "epoch": 78.64, "learning_rate": 1.481767983686198e-05, "loss": 0.0017, "step": 327520 }, { "epoch": 78.64, "learning_rate": 1.481512935665924e-05, "loss": 0.0012, "step": 327530 }, { "epoch": 78.65, "learning_rate": 1.4812579057799608e-05, "loss": 0.0015, "step": 327540 }, { "epoch": 78.65, "learning_rate": 1.4810028940296244e-05, "loss": 0.0015, "step": 327550 }, { "epoch": 78.65, "learning_rate": 1.4807479004162294e-05, "loss": 0.0014, "step": 327560 }, { "epoch": 78.65, "learning_rate": 1.4804929249410871e-05, "loss": 0.0012, "step": 327570 }, { "epoch": 78.65, "learning_rate": 1.480237967605515e-05, "loss": 0.0017, "step": 327580 }, { "epoch": 78.66, "learning_rate": 1.4799830284108246e-05, "loss": 0.0012, "step": 327590 }, { "epoch": 78.66, "learning_rate": 1.479728107358333e-05, "loss": 0.0014, "step": 327600 }, { "epoch": 78.66, "learning_rate": 1.4794732044493504e-05, "loss": 0.0013, "step": 327610 }, { "epoch": 78.66, "learning_rate": 1.4792183196851933e-05, "loss": 0.0036, "step": 327620 }, { "epoch": 78.67, "learning_rate": 1.4789634530671748e-05, "loss": 0.0013, "step": 327630 }, { "epoch": 78.67, "learning_rate": 1.478708604596607e-05, "loss": 0.0014, "step": 327640 }, { "epoch": 78.67, "learning_rate": 1.4784537742748055e-05, "loss": 0.0018, "step": 327650 }, { "epoch": 78.67, "learning_rate": 1.4781989621030811e-05, "loss": 0.0012, "step": 327660 }, { "epoch": 78.68, "learning_rate": 1.4779441680827505e-05, "loss": 0.0012, "step": 327670 }, { "epoch": 78.68, "learning_rate": 1.4776893922151236e-05, "loss": 0.0012, "step": 327680 }, { "epoch": 78.68, "learning_rate": 1.477434634501516e-05, "loss": 0.0013, "step": 327690 }, { "epoch": 78.68, "learning_rate": 1.4771798949432403e-05, "loss": 0.0013, "step": 327700 }, { "epoch": 78.68, "learning_rate": 1.4769251735416074e-05, "loss": 0.0013, "step": 327710 }, { "epoch": 78.69, "learning_rate": 1.4766704702979328e-05, "loss": 0.0013, "step": 327720 }, { "epoch": 78.69, "learning_rate": 1.4764157852135263e-05, "loss": 0.0014, "step": 327730 }, { "epoch": 78.69, "learning_rate": 1.4761611182897029e-05, "loss": 0.0014, "step": 327740 }, { "epoch": 78.69, "learning_rate": 1.4759064695277758e-05, "loss": 0.0014, "step": 327750 }, { "epoch": 78.7, "learning_rate": 1.4756518389290546e-05, "loss": 0.0014, "step": 327760 }, { "epoch": 78.7, "learning_rate": 1.4753972264948546e-05, "loss": 0.0012, "step": 327770 }, { "epoch": 78.7, "learning_rate": 1.4751426322264856e-05, "loss": 0.0013, "step": 327780 }, { "epoch": 78.7, "learning_rate": 1.4748880561252626e-05, "loss": 0.0011, "step": 327790 }, { "epoch": 78.71, "learning_rate": 1.4746334981924943e-05, "loss": 0.0013, "step": 327800 }, { "epoch": 78.71, "learning_rate": 1.474378958429496e-05, "loss": 0.0013, "step": 327810 }, { "epoch": 78.71, "learning_rate": 1.4741244368375761e-05, "loss": 0.0029, "step": 327820 }, { "epoch": 78.71, "learning_rate": 1.47386993341805e-05, "loss": 0.0013, "step": 327830 }, { "epoch": 78.71, "learning_rate": 1.4736154481722264e-05, "loss": 0.0012, "step": 327840 }, { "epoch": 78.72, "learning_rate": 1.4733609811014198e-05, "loss": 0.0013, "step": 327850 }, { "epoch": 78.72, "learning_rate": 1.4731065322069404e-05, "loss": 0.0012, "step": 327860 }, { "epoch": 78.72, "learning_rate": 1.4728521014900975e-05, "loss": 0.0012, "step": 327870 }, { "epoch": 78.72, "learning_rate": 1.4725976889522058e-05, "loss": 0.0013, "step": 327880 }, { "epoch": 78.73, "learning_rate": 1.4723432945945743e-05, "loss": 0.0011, "step": 327890 }, { "epoch": 78.73, "learning_rate": 1.4720889184185154e-05, "loss": 0.0012, "step": 327900 }, { "epoch": 78.73, "learning_rate": 1.4718345604253392e-05, "loss": 0.0013, "step": 327910 }, { "epoch": 78.73, "learning_rate": 1.4715802206163582e-05, "loss": 0.0013, "step": 327920 }, { "epoch": 78.73, "learning_rate": 1.4713258989928819e-05, "loss": 0.0013, "step": 327930 }, { "epoch": 78.74, "learning_rate": 1.4710715955562204e-05, "loss": 0.0012, "step": 327940 }, { "epoch": 78.74, "learning_rate": 1.4708173103076866e-05, "loss": 0.0014, "step": 327950 }, { "epoch": 78.74, "learning_rate": 1.4705630432485884e-05, "loss": 0.0013, "step": 327960 }, { "epoch": 78.74, "learning_rate": 1.4703087943802397e-05, "loss": 0.0023, "step": 327970 }, { "epoch": 78.75, "learning_rate": 1.470054563703947e-05, "loss": 0.0014, "step": 327980 }, { "epoch": 78.75, "learning_rate": 1.4698003512210246e-05, "loss": 0.0013, "step": 327990 }, { "epoch": 78.75, "learning_rate": 1.46954615693278e-05, "loss": 0.0015, "step": 328000 }, { "epoch": 78.75, "learning_rate": 1.4692919808405231e-05, "loss": 0.0015, "step": 328010 }, { "epoch": 78.76, "learning_rate": 1.469037822945566e-05, "loss": 0.0013, "step": 328020 }, { "epoch": 78.76, "learning_rate": 1.4687836832492163e-05, "loss": 0.0012, "step": 328030 }, { "epoch": 78.76, "learning_rate": 1.468529561752786e-05, "loss": 0.0012, "step": 328040 }, { "epoch": 78.76, "learning_rate": 1.4682754584575831e-05, "loss": 0.0013, "step": 328050 }, { "epoch": 78.76, "learning_rate": 1.4680213733649172e-05, "loss": 0.0013, "step": 328060 }, { "epoch": 78.77, "learning_rate": 1.4677673064761005e-05, "loss": 0.0012, "step": 328070 }, { "epoch": 78.77, "learning_rate": 1.4675132577924394e-05, "loss": 0.0012, "step": 328080 }, { "epoch": 78.77, "learning_rate": 1.4672592273152458e-05, "loss": 0.0013, "step": 328090 }, { "epoch": 78.77, "learning_rate": 1.4670052150458258e-05, "loss": 0.0012, "step": 328100 }, { "epoch": 78.78, "learning_rate": 1.4667512209854928e-05, "loss": 0.0017, "step": 328110 }, { "epoch": 78.78, "learning_rate": 1.4664972451355514e-05, "loss": 0.0025, "step": 328120 }, { "epoch": 78.78, "learning_rate": 1.4662432874973142e-05, "loss": 0.0012, "step": 328130 }, { "epoch": 78.78, "learning_rate": 1.4659893480720887e-05, "loss": 0.0012, "step": 328140 }, { "epoch": 78.79, "learning_rate": 1.4657354268611822e-05, "loss": 0.0014, "step": 328150 }, { "epoch": 78.79, "learning_rate": 1.4654815238659065e-05, "loss": 0.0012, "step": 328160 }, { "epoch": 78.79, "learning_rate": 1.4652276390875669e-05, "loss": 0.0012, "step": 328170 }, { "epoch": 78.79, "learning_rate": 1.4649737725274754e-05, "loss": 0.0013, "step": 328180 }, { "epoch": 78.79, "learning_rate": 1.4647199241869369e-05, "loss": 0.002, "step": 328190 }, { "epoch": 78.8, "learning_rate": 1.4644660940672627e-05, "loss": 0.0012, "step": 328200 }, { "epoch": 78.8, "learning_rate": 1.46421228216976e-05, "loss": 0.0011, "step": 328210 }, { "epoch": 78.8, "learning_rate": 1.4639584884957352e-05, "loss": 0.0013, "step": 328220 }, { "epoch": 78.8, "learning_rate": 1.4637047130464998e-05, "loss": 0.0016, "step": 328230 }, { "epoch": 78.81, "learning_rate": 1.4634509558233577e-05, "loss": 0.0013, "step": 328240 }, { "epoch": 78.81, "learning_rate": 1.4631972168276209e-05, "loss": 0.0011, "step": 328250 }, { "epoch": 78.81, "learning_rate": 1.4629434960605936e-05, "loss": 0.0013, "step": 328260 }, { "epoch": 78.81, "learning_rate": 1.4626897935235868e-05, "loss": 0.0013, "step": 328270 }, { "epoch": 78.81, "learning_rate": 1.4624361092179062e-05, "loss": 0.0014, "step": 328280 }, { "epoch": 78.82, "learning_rate": 1.4621824431448578e-05, "loss": 0.0013, "step": 328290 }, { "epoch": 78.82, "learning_rate": 1.4619287953057525e-05, "loss": 0.0013, "step": 328300 }, { "epoch": 78.82, "learning_rate": 1.461675165701894e-05, "loss": 0.0011, "step": 328310 }, { "epoch": 78.82, "learning_rate": 1.4614215543345927e-05, "loss": 0.0013, "step": 328320 }, { "epoch": 78.83, "learning_rate": 1.4611679612051532e-05, "loss": 0.0012, "step": 328330 }, { "epoch": 78.83, "learning_rate": 1.4609143863148845e-05, "loss": 0.0012, "step": 328340 }, { "epoch": 78.83, "learning_rate": 1.4606608296650915e-05, "loss": 0.0012, "step": 328350 }, { "epoch": 78.83, "learning_rate": 1.460407291257082e-05, "loss": 0.001, "step": 328360 }, { "epoch": 78.84, "learning_rate": 1.4601537710921648e-05, "loss": 0.0013, "step": 328370 }, { "epoch": 78.84, "learning_rate": 1.459900269171643e-05, "loss": 0.0014, "step": 328380 }, { "epoch": 78.84, "learning_rate": 1.459646785496826e-05, "loss": 0.0012, "step": 328390 }, { "epoch": 78.84, "learning_rate": 1.4593933200690179e-05, "loss": 0.0013, "step": 328400 }, { "epoch": 78.84, "learning_rate": 1.4591398728895272e-05, "loss": 0.0011, "step": 328410 }, { "epoch": 78.85, "learning_rate": 1.45888644395966e-05, "loss": 0.0013, "step": 328420 }, { "epoch": 78.85, "learning_rate": 1.4586330332807197e-05, "loss": 0.0013, "step": 328430 }, { "epoch": 78.85, "learning_rate": 1.4583796408540157e-05, "loss": 0.0013, "step": 328440 }, { "epoch": 78.85, "learning_rate": 1.4581262666808515e-05, "loss": 0.0013, "step": 328450 }, { "epoch": 78.86, "learning_rate": 1.4578729107625356e-05, "loss": 0.0013, "step": 328460 }, { "epoch": 78.86, "learning_rate": 1.4576195731003705e-05, "loss": 0.0013, "step": 328470 }, { "epoch": 78.86, "learning_rate": 1.457366253695665e-05, "loss": 0.0012, "step": 328480 }, { "epoch": 78.86, "learning_rate": 1.4571129525497241e-05, "loss": 0.0014, "step": 328490 }, { "epoch": 78.87, "learning_rate": 1.4568596696638509e-05, "loss": 0.0012, "step": 328500 }, { "epoch": 78.87, "learning_rate": 1.4566064050393542e-05, "loss": 0.024, "step": 328510 }, { "epoch": 78.87, "learning_rate": 1.4563531586775359e-05, "loss": 0.0012, "step": 328520 }, { "epoch": 78.87, "learning_rate": 1.4560999305797046e-05, "loss": 0.0012, "step": 328530 }, { "epoch": 78.87, "learning_rate": 1.4558467207471626e-05, "loss": 0.0014, "step": 328540 }, { "epoch": 78.88, "learning_rate": 1.4555935291812178e-05, "loss": 0.0012, "step": 328550 }, { "epoch": 78.88, "learning_rate": 1.4553403558831735e-05, "loss": 0.0011, "step": 328560 }, { "epoch": 78.88, "learning_rate": 1.4550872008543325e-05, "loss": 0.0014, "step": 328570 }, { "epoch": 78.88, "learning_rate": 1.454834064096004e-05, "loss": 0.0012, "step": 328580 }, { "epoch": 78.89, "learning_rate": 1.4545809456094889e-05, "loss": 0.0013, "step": 328590 }, { "epoch": 78.89, "learning_rate": 1.454327845396094e-05, "loss": 0.0013, "step": 328600 }, { "epoch": 78.89, "learning_rate": 1.4540747634571222e-05, "loss": 0.0013, "step": 328610 }, { "epoch": 78.89, "learning_rate": 1.4538216997938797e-05, "loss": 0.0011, "step": 328620 }, { "epoch": 78.89, "learning_rate": 1.4535686544076688e-05, "loss": 0.0012, "step": 328630 }, { "epoch": 78.9, "learning_rate": 1.4533156272997961e-05, "loss": 0.0079, "step": 328640 }, { "epoch": 78.9, "learning_rate": 1.4530626184715623e-05, "loss": 0.0014, "step": 328650 }, { "epoch": 78.9, "learning_rate": 1.4528096279242752e-05, "loss": 0.0014, "step": 328660 }, { "epoch": 78.9, "learning_rate": 1.4525566556592357e-05, "loss": 0.0012, "step": 328670 }, { "epoch": 78.91, "learning_rate": 1.4523037016777486e-05, "loss": 0.0012, "step": 328680 }, { "epoch": 78.91, "learning_rate": 1.4520507659811195e-05, "loss": 0.0013, "step": 328690 }, { "epoch": 78.91, "learning_rate": 1.451797848570649e-05, "loss": 0.0012, "step": 328700 }, { "epoch": 78.91, "learning_rate": 1.4515449494476436e-05, "loss": 0.0011, "step": 328710 }, { "epoch": 78.92, "learning_rate": 1.4512920686134046e-05, "loss": 0.0013, "step": 328720 }, { "epoch": 78.92, "learning_rate": 1.451039206069235e-05, "loss": 0.0012, "step": 328730 }, { "epoch": 78.92, "learning_rate": 1.4507863618164402e-05, "loss": 0.0013, "step": 328740 }, { "epoch": 78.92, "learning_rate": 1.450533535856321e-05, "loss": 0.0013, "step": 328750 }, { "epoch": 78.92, "learning_rate": 1.4502807281901832e-05, "loss": 0.0012, "step": 328760 }, { "epoch": 78.93, "learning_rate": 1.450027938819326e-05, "loss": 0.0013, "step": 328770 }, { "epoch": 78.93, "learning_rate": 1.4497751677450566e-05, "loss": 0.0012, "step": 328780 }, { "epoch": 78.93, "learning_rate": 1.4495224149686753e-05, "loss": 0.0013, "step": 328790 }, { "epoch": 78.93, "learning_rate": 1.449269680491484e-05, "loss": 0.0013, "step": 328800 }, { "epoch": 78.94, "learning_rate": 1.4490169643147877e-05, "loss": 0.0012, "step": 328810 }, { "epoch": 78.94, "learning_rate": 1.4487642664398859e-05, "loss": 0.0011, "step": 328820 }, { "epoch": 78.94, "learning_rate": 1.4485115868680848e-05, "loss": 0.0012, "step": 328830 }, { "epoch": 78.94, "learning_rate": 1.4482589256006829e-05, "loss": 0.0014, "step": 328840 }, { "epoch": 78.95, "learning_rate": 1.4480062826389856e-05, "loss": 0.0014, "step": 328850 }, { "epoch": 78.95, "learning_rate": 1.4477536579842938e-05, "loss": 0.0013, "step": 328860 }, { "epoch": 78.95, "learning_rate": 1.4475010516379078e-05, "loss": 0.0012, "step": 328870 }, { "epoch": 79.0, "learning_rate": 1.4472484636011325e-05, "loss": 0.0011, "step": 328880 }, { "epoch": 79.0, "learning_rate": 1.446995893875267e-05, "loss": 0.0013, "step": 328890 }, { "epoch": 79.01, "learning_rate": 1.4467433424616156e-05, "loss": 0.0012, "step": 328900 }, { "epoch": 79.01, "learning_rate": 1.446490809361477e-05, "loss": 0.0011, "step": 328910 }, { "epoch": 79.01, "learning_rate": 1.4462382945761566e-05, "loss": 0.0012, "step": 328920 }, { "epoch": 79.01, "learning_rate": 1.4459857981069519e-05, "loss": 0.0014, "step": 328930 }, { "epoch": 79.01, "learning_rate": 1.4457333199551675e-05, "loss": 0.0011, "step": 328940 }, { "epoch": 79.02, "learning_rate": 1.445480860122102e-05, "loss": 0.001, "step": 328950 }, { "epoch": 79.02, "learning_rate": 1.4452284186090592e-05, "loss": 0.0011, "step": 328960 }, { "epoch": 79.02, "learning_rate": 1.4449759954173375e-05, "loss": 0.0012, "step": 328970 }, { "epoch": 79.02, "learning_rate": 1.4447235905482404e-05, "loss": 0.0012, "step": 328980 }, { "epoch": 79.03, "learning_rate": 1.4444712040030667e-05, "loss": 0.0014, "step": 328990 }, { "epoch": 79.03, "learning_rate": 1.4442188357831187e-05, "loss": 0.0014, "step": 329000 }, { "epoch": 79.03, "learning_rate": 1.4439664858896962e-05, "loss": 0.0013, "step": 329010 }, { "epoch": 79.03, "learning_rate": 1.4437141543241006e-05, "loss": 0.0012, "step": 329020 }, { "epoch": 79.03, "learning_rate": 1.4434618410876311e-05, "loss": 0.0013, "step": 329030 }, { "epoch": 79.04, "learning_rate": 1.4432095461815903e-05, "loss": 0.0012, "step": 329040 }, { "epoch": 79.04, "learning_rate": 1.4429572696072757e-05, "loss": 0.0013, "step": 329050 }, { "epoch": 79.04, "learning_rate": 1.4427050113659912e-05, "loss": 0.0012, "step": 329060 }, { "epoch": 79.04, "learning_rate": 1.4424527714590341e-05, "loss": 0.0011, "step": 329070 }, { "epoch": 79.05, "learning_rate": 1.442200549887704e-05, "loss": 0.0012, "step": 329080 }, { "epoch": 79.05, "learning_rate": 1.441948346653303e-05, "loss": 0.0013, "step": 329090 }, { "epoch": 79.05, "learning_rate": 1.441696161757129e-05, "loss": 0.0012, "step": 329100 }, { "epoch": 79.05, "learning_rate": 1.4414439952004838e-05, "loss": 0.0012, "step": 329110 }, { "epoch": 79.06, "learning_rate": 1.4411918469846648e-05, "loss": 0.0012, "step": 329120 }, { "epoch": 79.06, "learning_rate": 1.440939717110974e-05, "loss": 0.0012, "step": 329130 }, { "epoch": 79.06, "learning_rate": 1.44068760558071e-05, "loss": 0.0012, "step": 329140 }, { "epoch": 79.06, "learning_rate": 1.4404355123951702e-05, "loss": 0.0011, "step": 329150 }, { "epoch": 79.06, "learning_rate": 1.4401834375556572e-05, "loss": 0.0012, "step": 329160 }, { "epoch": 79.07, "learning_rate": 1.4399313810634668e-05, "loss": 0.0011, "step": 329170 }, { "epoch": 79.07, "learning_rate": 1.4396793429199013e-05, "loss": 0.0012, "step": 329180 }, { "epoch": 79.07, "learning_rate": 1.4394273231262568e-05, "loss": 0.0012, "step": 329190 }, { "epoch": 79.07, "learning_rate": 1.4391753216838349e-05, "loss": 0.0012, "step": 329200 }, { "epoch": 79.08, "learning_rate": 1.4389233385939332e-05, "loss": 0.0012, "step": 329210 }, { "epoch": 79.08, "learning_rate": 1.4386713738578489e-05, "loss": 0.0013, "step": 329220 }, { "epoch": 79.08, "learning_rate": 1.4384194274768842e-05, "loss": 0.0012, "step": 329230 }, { "epoch": 79.08, "learning_rate": 1.438167499452333e-05, "loss": 0.0017, "step": 329240 }, { "epoch": 79.09, "learning_rate": 1.4379155897854973e-05, "loss": 0.0013, "step": 329250 }, { "epoch": 79.09, "learning_rate": 1.4376636984776753e-05, "loss": 0.0013, "step": 329260 }, { "epoch": 79.09, "learning_rate": 1.4374118255301634e-05, "loss": 0.0014, "step": 329270 }, { "epoch": 79.09, "learning_rate": 1.4371599709442618e-05, "loss": 0.0014, "step": 329280 }, { "epoch": 79.09, "learning_rate": 1.436908134721266e-05, "loss": 0.0017, "step": 329290 }, { "epoch": 79.1, "learning_rate": 1.4366563168624769e-05, "loss": 0.0012, "step": 329300 }, { "epoch": 79.1, "learning_rate": 1.4364045173691892e-05, "loss": 0.0013, "step": 329310 }, { "epoch": 79.1, "learning_rate": 1.4361527362427046e-05, "loss": 0.0011, "step": 329320 }, { "epoch": 79.1, "learning_rate": 1.4359009734843165e-05, "loss": 0.0012, "step": 329330 }, { "epoch": 79.11, "learning_rate": 1.4356492290953266e-05, "loss": 0.0011, "step": 329340 }, { "epoch": 79.11, "learning_rate": 1.43539750307703e-05, "loss": 0.0018, "step": 329350 }, { "epoch": 79.11, "learning_rate": 1.435145795430723e-05, "loss": 0.0013, "step": 329360 }, { "epoch": 79.11, "learning_rate": 1.4348941061577059e-05, "loss": 0.0012, "step": 329370 }, { "epoch": 79.11, "learning_rate": 1.434642435259273e-05, "loss": 0.0012, "step": 329380 }, { "epoch": 79.12, "learning_rate": 1.4343907827367242e-05, "loss": 0.0012, "step": 329390 }, { "epoch": 79.12, "learning_rate": 1.4341391485913535e-05, "loss": 0.0012, "step": 329400 }, { "epoch": 79.12, "learning_rate": 1.433887532824461e-05, "loss": 0.0012, "step": 329410 }, { "epoch": 79.12, "learning_rate": 1.4336359354373408e-05, "loss": 0.0013, "step": 329420 }, { "epoch": 79.13, "learning_rate": 1.4333843564312915e-05, "loss": 0.0012, "step": 329430 }, { "epoch": 79.13, "learning_rate": 1.4331327958076097e-05, "loss": 0.0012, "step": 329440 }, { "epoch": 79.13, "learning_rate": 1.4328812535675894e-05, "loss": 0.0012, "step": 329450 }, { "epoch": 79.13, "learning_rate": 1.4326297297125308e-05, "loss": 0.0011, "step": 329460 }, { "epoch": 79.14, "learning_rate": 1.4323782242437268e-05, "loss": 0.0013, "step": 329470 }, { "epoch": 79.14, "learning_rate": 1.432126737162477e-05, "loss": 0.0011, "step": 329480 }, { "epoch": 79.14, "learning_rate": 1.4318752684700738e-05, "loss": 0.0012, "step": 329490 }, { "epoch": 79.14, "learning_rate": 1.4316238181678172e-05, "loss": 0.001, "step": 329500 }, { "epoch": 79.14, "learning_rate": 1.4313723862570011e-05, "loss": 0.0018, "step": 329510 }, { "epoch": 79.15, "learning_rate": 1.4311209727389197e-05, "loss": 0.0012, "step": 329520 }, { "epoch": 79.15, "learning_rate": 1.4308695776148728e-05, "loss": 0.0012, "step": 329530 }, { "epoch": 79.15, "learning_rate": 1.430618200886152e-05, "loss": 0.0013, "step": 329540 }, { "epoch": 79.15, "learning_rate": 1.4303668425540561e-05, "loss": 0.0012, "step": 329550 }, { "epoch": 79.16, "learning_rate": 1.4301155026198781e-05, "loss": 0.0014, "step": 329560 }, { "epoch": 79.16, "learning_rate": 1.4298641810849151e-05, "loss": 0.0012, "step": 329570 }, { "epoch": 79.16, "learning_rate": 1.4296128779504631e-05, "loss": 0.0013, "step": 329580 }, { "epoch": 79.16, "learning_rate": 1.4293615932178145e-05, "loss": 0.0013, "step": 329590 }, { "epoch": 79.17, "learning_rate": 1.4291103268882677e-05, "loss": 0.0011, "step": 329600 }, { "epoch": 79.17, "learning_rate": 1.4288590789631146e-05, "loss": 0.0013, "step": 329610 }, { "epoch": 79.17, "learning_rate": 1.4286078494436533e-05, "loss": 0.0011, "step": 329620 }, { "epoch": 79.17, "learning_rate": 1.4283566383311753e-05, "loss": 0.0012, "step": 329630 }, { "epoch": 79.17, "learning_rate": 1.4281054456269788e-05, "loss": 0.0012, "step": 329640 }, { "epoch": 79.18, "learning_rate": 1.4278542713323562e-05, "loss": 0.0012, "step": 329650 }, { "epoch": 79.18, "learning_rate": 1.4276031154486014e-05, "loss": 0.0012, "step": 329660 }, { "epoch": 79.18, "learning_rate": 1.4273519779770117e-05, "loss": 0.0013, "step": 329670 }, { "epoch": 79.18, "learning_rate": 1.4271008589188777e-05, "loss": 0.0011, "step": 329680 }, { "epoch": 79.19, "learning_rate": 1.4268497582754975e-05, "loss": 0.0074, "step": 329690 }, { "epoch": 79.19, "learning_rate": 1.4265986760481625e-05, "loss": 0.0012, "step": 329700 }, { "epoch": 79.19, "learning_rate": 1.4263476122381686e-05, "loss": 0.0013, "step": 329710 }, { "epoch": 79.19, "learning_rate": 1.4260965668468096e-05, "loss": 0.0011, "step": 329720 }, { "epoch": 79.19, "learning_rate": 1.4258455398753768e-05, "loss": 0.0012, "step": 329730 }, { "epoch": 79.2, "learning_rate": 1.4255945313251673e-05, "loss": 0.0012, "step": 329740 }, { "epoch": 79.2, "learning_rate": 1.4253435411974725e-05, "loss": 0.0012, "step": 329750 }, { "epoch": 79.2, "learning_rate": 1.4250925694935879e-05, "loss": 0.0013, "step": 329760 }, { "epoch": 79.2, "learning_rate": 1.4248416162148054e-05, "loss": 0.0013, "step": 329770 }, { "epoch": 79.21, "learning_rate": 1.42459068136242e-05, "loss": 0.0012, "step": 329780 }, { "epoch": 79.21, "learning_rate": 1.4243397649377238e-05, "loss": 0.0019, "step": 329790 }, { "epoch": 79.21, "learning_rate": 1.4240888669420094e-05, "loss": 0.0012, "step": 329800 }, { "epoch": 79.21, "learning_rate": 1.4238379873765722e-05, "loss": 0.0012, "step": 329810 }, { "epoch": 79.22, "learning_rate": 1.4235871262427025e-05, "loss": 0.0017, "step": 329820 }, { "epoch": 79.22, "learning_rate": 1.4233362835416964e-05, "loss": 0.0012, "step": 329830 }, { "epoch": 79.22, "learning_rate": 1.4230854592748427e-05, "loss": 0.0013, "step": 329840 }, { "epoch": 79.22, "learning_rate": 1.4228346534434384e-05, "loss": 0.0015, "step": 329850 }, { "epoch": 79.22, "learning_rate": 1.4225838660487728e-05, "loss": 0.0012, "step": 329860 }, { "epoch": 79.23, "learning_rate": 1.4223330970921411e-05, "loss": 0.0013, "step": 329870 }, { "epoch": 79.23, "learning_rate": 1.4220823465748334e-05, "loss": 0.0012, "step": 329880 }, { "epoch": 79.23, "learning_rate": 1.421831614498143e-05, "loss": 0.0012, "step": 329890 }, { "epoch": 79.23, "learning_rate": 1.4215809008633636e-05, "loss": 0.0013, "step": 329900 }, { "epoch": 79.24, "learning_rate": 1.4213302056717848e-05, "loss": 0.0011, "step": 329910 }, { "epoch": 79.24, "learning_rate": 1.4210795289247019e-05, "loss": 0.0021, "step": 329920 }, { "epoch": 79.24, "learning_rate": 1.4208288706234047e-05, "loss": 0.0014, "step": 329930 }, { "epoch": 79.24, "learning_rate": 1.420578230769184e-05, "loss": 0.0011, "step": 329940 }, { "epoch": 79.25, "learning_rate": 1.4203276093633344e-05, "loss": 0.0012, "step": 329950 }, { "epoch": 79.25, "learning_rate": 1.420077006407145e-05, "loss": 0.0014, "step": 329960 }, { "epoch": 79.25, "learning_rate": 1.4198264219019097e-05, "loss": 0.0012, "step": 329970 }, { "epoch": 79.25, "learning_rate": 1.4195758558489175e-05, "loss": 0.0011, "step": 329980 }, { "epoch": 79.25, "learning_rate": 1.4193253082494629e-05, "loss": 0.0012, "step": 329990 }, { "epoch": 79.26, "learning_rate": 1.4190747791048359e-05, "loss": 0.0012, "step": 330000 }, { "epoch": 79.26, "learning_rate": 1.4188242684163256e-05, "loss": 0.0011, "step": 330010 }, { "epoch": 79.26, "learning_rate": 1.4185737761852263e-05, "loss": 0.0012, "step": 330020 }, { "epoch": 79.26, "learning_rate": 1.4183233024128267e-05, "loss": 0.0013, "step": 330030 }, { "epoch": 79.27, "learning_rate": 1.4180728471004201e-05, "loss": 0.0013, "step": 330040 }, { "epoch": 79.27, "learning_rate": 1.4178224102492943e-05, "loss": 0.0012, "step": 330050 }, { "epoch": 79.27, "learning_rate": 1.4175719918607434e-05, "loss": 0.0013, "step": 330060 }, { "epoch": 79.27, "learning_rate": 1.4173215919360562e-05, "loss": 0.0012, "step": 330070 }, { "epoch": 79.27, "learning_rate": 1.4170712104765215e-05, "loss": 0.0011, "step": 330080 }, { "epoch": 79.28, "learning_rate": 1.4168208474834339e-05, "loss": 0.0011, "step": 330090 }, { "epoch": 79.28, "learning_rate": 1.41657050295808e-05, "loss": 0.0012, "step": 330100 }, { "epoch": 79.28, "learning_rate": 1.4163201769017531e-05, "loss": 0.0012, "step": 330110 }, { "epoch": 79.28, "learning_rate": 1.4160698693157404e-05, "loss": 0.0012, "step": 330120 }, { "epoch": 79.29, "learning_rate": 1.4158195802013352e-05, "loss": 0.0017, "step": 330130 }, { "epoch": 79.29, "learning_rate": 1.4155693095598244e-05, "loss": 0.0012, "step": 330140 }, { "epoch": 79.29, "learning_rate": 1.4153190573925006e-05, "loss": 0.0013, "step": 330150 }, { "epoch": 79.29, "learning_rate": 1.4150688237006509e-05, "loss": 0.0013, "step": 330160 }, { "epoch": 79.3, "learning_rate": 1.4148186084855686e-05, "loss": 0.0011, "step": 330170 }, { "epoch": 79.3, "learning_rate": 1.4145684117485386e-05, "loss": 0.0012, "step": 330180 }, { "epoch": 79.3, "learning_rate": 1.4143182334908533e-05, "loss": 0.0012, "step": 330190 }, { "epoch": 79.3, "learning_rate": 1.414068073713804e-05, "loss": 0.0012, "step": 330200 }, { "epoch": 79.3, "learning_rate": 1.4138179324186774e-05, "loss": 0.0012, "step": 330210 }, { "epoch": 79.31, "learning_rate": 1.4135678096067611e-05, "loss": 0.0022, "step": 330220 }, { "epoch": 79.31, "learning_rate": 1.4133177052793484e-05, "loss": 0.0011, "step": 330230 }, { "epoch": 79.31, "learning_rate": 1.4130676194377246e-05, "loss": 0.0012, "step": 330240 }, { "epoch": 79.31, "learning_rate": 1.4128175520831816e-05, "loss": 0.0013, "step": 330250 }, { "epoch": 79.32, "learning_rate": 1.4125675032170055e-05, "loss": 0.0012, "step": 330260 }, { "epoch": 79.32, "learning_rate": 1.4123174728404881e-05, "loss": 0.0025, "step": 330270 }, { "epoch": 79.32, "learning_rate": 1.412067460954915e-05, "loss": 0.0012, "step": 330280 }, { "epoch": 79.32, "learning_rate": 1.4118174675615775e-05, "loss": 0.0012, "step": 330290 }, { "epoch": 79.33, "learning_rate": 1.4115674926617629e-05, "loss": 0.0011, "step": 330300 }, { "epoch": 79.33, "learning_rate": 1.4113175362567576e-05, "loss": 0.006, "step": 330310 }, { "epoch": 79.33, "learning_rate": 1.4110675983478532e-05, "loss": 0.002, "step": 330320 }, { "epoch": 79.33, "learning_rate": 1.4108176789363354e-05, "loss": 0.0013, "step": 330330 }, { "epoch": 79.33, "learning_rate": 1.4105677780234943e-05, "loss": 0.0013, "step": 330340 }, { "epoch": 79.34, "learning_rate": 1.4103178956106161e-05, "loss": 0.0012, "step": 330350 }, { "epoch": 79.34, "learning_rate": 1.41006803169899e-05, "loss": 0.0012, "step": 330360 }, { "epoch": 79.34, "learning_rate": 1.409818186289904e-05, "loss": 0.0013, "step": 330370 }, { "epoch": 79.34, "learning_rate": 1.4095683593846432e-05, "loss": 0.0012, "step": 330380 }, { "epoch": 79.35, "learning_rate": 1.4093185509844992e-05, "loss": 0.0013, "step": 330390 }, { "epoch": 79.35, "learning_rate": 1.409068761090755e-05, "loss": 0.0014, "step": 330400 }, { "epoch": 79.35, "learning_rate": 1.4088189897047027e-05, "loss": 0.0013, "step": 330410 }, { "epoch": 79.35, "learning_rate": 1.4085692368276254e-05, "loss": 0.0014, "step": 330420 }, { "epoch": 79.35, "learning_rate": 1.4083195024608137e-05, "loss": 0.0013, "step": 330430 }, { "epoch": 79.36, "learning_rate": 1.4080697866055536e-05, "loss": 0.0011, "step": 330440 }, { "epoch": 79.36, "learning_rate": 1.40782008926313e-05, "loss": 0.0012, "step": 330450 }, { "epoch": 79.36, "learning_rate": 1.4075704104348319e-05, "loss": 0.0012, "step": 330460 }, { "epoch": 79.36, "learning_rate": 1.4073207501219477e-05, "loss": 0.0018, "step": 330470 }, { "epoch": 79.37, "learning_rate": 1.4070711083257603e-05, "loss": 0.0015, "step": 330480 }, { "epoch": 79.37, "learning_rate": 1.4068214850475603e-05, "loss": 0.0012, "step": 330490 }, { "epoch": 79.37, "learning_rate": 1.4065718802886307e-05, "loss": 0.0013, "step": 330500 }, { "epoch": 79.37, "learning_rate": 1.4063222940502618e-05, "loss": 0.0012, "step": 330510 }, { "epoch": 79.38, "learning_rate": 1.4060727263337359e-05, "loss": 0.0012, "step": 330520 }, { "epoch": 79.38, "learning_rate": 1.4058231771403424e-05, "loss": 0.0013, "step": 330530 }, { "epoch": 79.38, "learning_rate": 1.4055736464713654e-05, "loss": 0.0011, "step": 330540 }, { "epoch": 79.38, "learning_rate": 1.4053241343280927e-05, "loss": 0.0012, "step": 330550 }, { "epoch": 79.38, "learning_rate": 1.4050746407118082e-05, "loss": 0.0013, "step": 330560 }, { "epoch": 79.39, "learning_rate": 1.404825165623801e-05, "loss": 0.0012, "step": 330570 }, { "epoch": 79.39, "learning_rate": 1.4045757090653545e-05, "loss": 0.0013, "step": 330580 }, { "epoch": 79.39, "learning_rate": 1.404326271037753e-05, "loss": 0.0012, "step": 330590 }, { "epoch": 79.39, "learning_rate": 1.4040768515422864e-05, "loss": 0.0012, "step": 330600 }, { "epoch": 79.4, "learning_rate": 1.4038274505802356e-05, "loss": 0.0011, "step": 330610 }, { "epoch": 79.4, "learning_rate": 1.4035780681528898e-05, "loss": 0.0013, "step": 330620 }, { "epoch": 79.4, "learning_rate": 1.4033287042615311e-05, "loss": 0.0012, "step": 330630 }, { "epoch": 79.4, "learning_rate": 1.4030793589074481e-05, "loss": 0.0012, "step": 330640 }, { "epoch": 79.41, "learning_rate": 1.4028300320919241e-05, "loss": 0.0012, "step": 330650 }, { "epoch": 79.41, "learning_rate": 1.4025807238162425e-05, "loss": 0.0012, "step": 330660 }, { "epoch": 79.41, "learning_rate": 1.4023314340816912e-05, "loss": 0.0012, "step": 330670 }, { "epoch": 79.41, "learning_rate": 1.4020821628895531e-05, "loss": 0.0011, "step": 330680 }, { "epoch": 79.41, "learning_rate": 1.4018329102411142e-05, "loss": 0.0012, "step": 330690 }, { "epoch": 79.42, "learning_rate": 1.4015836761376577e-05, "loss": 0.0012, "step": 330700 }, { "epoch": 79.42, "learning_rate": 1.4013344605804702e-05, "loss": 0.0012, "step": 330710 }, { "epoch": 79.42, "learning_rate": 1.401085263570835e-05, "loss": 0.0012, "step": 330720 }, { "epoch": 79.42, "learning_rate": 1.4008360851100349e-05, "loss": 0.0012, "step": 330730 }, { "epoch": 79.43, "learning_rate": 1.400586925199357e-05, "loss": 0.0011, "step": 330740 }, { "epoch": 79.43, "learning_rate": 1.4003377838400834e-05, "loss": 0.0013, "step": 330750 }, { "epoch": 79.43, "learning_rate": 1.4000886610334979e-05, "loss": 0.0014, "step": 330760 }, { "epoch": 79.43, "learning_rate": 1.3998395567808881e-05, "loss": 0.0012, "step": 330770 }, { "epoch": 79.43, "learning_rate": 1.3995904710835328e-05, "loss": 0.0012, "step": 330780 }, { "epoch": 79.44, "learning_rate": 1.3993414039427206e-05, "loss": 0.0012, "step": 330790 }, { "epoch": 79.44, "learning_rate": 1.3990923553597312e-05, "loss": 0.0013, "step": 330800 }, { "epoch": 79.44, "learning_rate": 1.3988433253358513e-05, "loss": 0.0012, "step": 330810 }, { "epoch": 79.44, "learning_rate": 1.3985943138723612e-05, "loss": 0.0013, "step": 330820 }, { "epoch": 79.45, "learning_rate": 1.3983453209705482e-05, "loss": 0.0011, "step": 330830 }, { "epoch": 79.45, "learning_rate": 1.3980963466316916e-05, "loss": 0.0013, "step": 330840 }, { "epoch": 79.45, "learning_rate": 1.3978473908570783e-05, "loss": 0.0012, "step": 330850 }, { "epoch": 79.45, "learning_rate": 1.3975984536479897e-05, "loss": 0.0013, "step": 330860 }, { "epoch": 79.46, "learning_rate": 1.397349535005707e-05, "loss": 0.0039, "step": 330870 }, { "epoch": 79.46, "learning_rate": 1.3971006349315163e-05, "loss": 0.0011, "step": 330880 }, { "epoch": 79.46, "learning_rate": 1.3968517534266978e-05, "loss": 0.0013, "step": 330890 }, { "epoch": 79.46, "learning_rate": 1.396602890492537e-05, "loss": 0.0011, "step": 330900 }, { "epoch": 79.46, "learning_rate": 1.3963540461303137e-05, "loss": 0.0012, "step": 330910 }, { "epoch": 79.47, "learning_rate": 1.3961052203413132e-05, "loss": 0.0012, "step": 330920 }, { "epoch": 79.47, "learning_rate": 1.3958564131268164e-05, "loss": 0.0013, "step": 330930 }, { "epoch": 79.47, "learning_rate": 1.395607624488104e-05, "loss": 0.0011, "step": 330940 }, { "epoch": 79.47, "learning_rate": 1.3953588544264617e-05, "loss": 0.0012, "step": 330950 }, { "epoch": 79.48, "learning_rate": 1.395110102943169e-05, "loss": 0.0013, "step": 330960 }, { "epoch": 79.48, "learning_rate": 1.3948613700395098e-05, "loss": 0.0017, "step": 330970 }, { "epoch": 79.48, "learning_rate": 1.3946126557167639e-05, "loss": 0.0011, "step": 330980 }, { "epoch": 79.48, "learning_rate": 1.394363959976216e-05, "loss": 0.0012, "step": 330990 }, { "epoch": 79.49, "learning_rate": 1.3941152828191467e-05, "loss": 0.0011, "step": 331000 }, { "epoch": 79.49, "learning_rate": 1.3938666242468356e-05, "loss": 0.0013, "step": 331010 }, { "epoch": 79.49, "learning_rate": 1.3936179842605673e-05, "loss": 0.0011, "step": 331020 }, { "epoch": 79.49, "learning_rate": 1.3933693628616213e-05, "loss": 0.0012, "step": 331030 }, { "epoch": 79.49, "learning_rate": 1.3931207600512807e-05, "loss": 0.0011, "step": 331040 }, { "epoch": 79.5, "learning_rate": 1.3928721758308243e-05, "loss": 0.0012, "step": 331050 }, { "epoch": 79.5, "learning_rate": 1.3926236102015367e-05, "loss": 0.0012, "step": 331060 }, { "epoch": 79.5, "learning_rate": 1.3923750631646953e-05, "loss": 0.0012, "step": 331070 }, { "epoch": 79.5, "learning_rate": 1.3921265347215833e-05, "loss": 0.0014, "step": 331080 }, { "epoch": 79.51, "learning_rate": 1.3918780248734825e-05, "loss": 0.0013, "step": 331090 }, { "epoch": 79.51, "learning_rate": 1.3916295336216712e-05, "loss": 0.0012, "step": 331100 }, { "epoch": 79.51, "learning_rate": 1.3913810609674332e-05, "loss": 0.0011, "step": 331110 }, { "epoch": 79.51, "learning_rate": 1.3911326069120456e-05, "loss": 0.0013, "step": 331120 }, { "epoch": 79.51, "learning_rate": 1.3908841714567921e-05, "loss": 0.0011, "step": 331130 }, { "epoch": 79.52, "learning_rate": 1.3906357546029503e-05, "loss": 0.0012, "step": 331140 }, { "epoch": 79.52, "learning_rate": 1.3903873563518033e-05, "loss": 0.0011, "step": 331150 }, { "epoch": 79.52, "learning_rate": 1.3901389767046302e-05, "loss": 0.0011, "step": 331160 }, { "epoch": 79.52, "learning_rate": 1.38989061566271e-05, "loss": 0.0017, "step": 331170 }, { "epoch": 79.53, "learning_rate": 1.3896422732273246e-05, "loss": 0.0013, "step": 331180 }, { "epoch": 79.53, "learning_rate": 1.389393949399752e-05, "loss": 0.0012, "step": 331190 }, { "epoch": 79.53, "learning_rate": 1.3891456441812745e-05, "loss": 0.0013, "step": 331200 }, { "epoch": 79.53, "learning_rate": 1.3888973575731689e-05, "loss": 0.0014, "step": 331210 }, { "epoch": 79.54, "learning_rate": 1.3886490895767179e-05, "loss": 0.0012, "step": 331220 }, { "epoch": 79.54, "learning_rate": 1.3884008401932002e-05, "loss": 0.0014, "step": 331230 }, { "epoch": 79.54, "learning_rate": 1.3881526094238928e-05, "loss": 0.0012, "step": 331240 }, { "epoch": 79.54, "learning_rate": 1.387904397270079e-05, "loss": 0.0012, "step": 331250 }, { "epoch": 79.54, "learning_rate": 1.3876562037330343e-05, "loss": 0.0014, "step": 331260 }, { "epoch": 79.55, "learning_rate": 1.3874080288140412e-05, "loss": 0.0013, "step": 331270 }, { "epoch": 79.55, "learning_rate": 1.3871598725143758e-05, "loss": 0.0013, "step": 331280 }, { "epoch": 79.55, "learning_rate": 1.38691173483532e-05, "loss": 0.0013, "step": 331290 }, { "epoch": 79.55, "learning_rate": 1.3866636157781515e-05, "loss": 0.0014, "step": 331300 }, { "epoch": 79.56, "learning_rate": 1.3864155153441477e-05, "loss": 0.0013, "step": 331310 }, { "epoch": 79.56, "learning_rate": 1.3861674335345897e-05, "loss": 0.0012, "step": 331320 }, { "epoch": 79.56, "learning_rate": 1.3859193703507534e-05, "loss": 0.0013, "step": 331330 }, { "epoch": 79.56, "learning_rate": 1.3856713257939203e-05, "loss": 0.0014, "step": 331340 }, { "epoch": 79.57, "learning_rate": 1.385423299865366e-05, "loss": 0.009, "step": 331350 }, { "epoch": 79.57, "learning_rate": 1.385175292566372e-05, "loss": 0.0012, "step": 331360 }, { "epoch": 79.57, "learning_rate": 1.384927303898213e-05, "loss": 0.0013, "step": 331370 }, { "epoch": 79.57, "learning_rate": 1.3846793338621706e-05, "loss": 0.0013, "step": 331380 }, { "epoch": 79.57, "learning_rate": 1.3844313824595195e-05, "loss": 0.0012, "step": 331390 }, { "epoch": 79.58, "learning_rate": 1.384183449691539e-05, "loss": 0.0012, "step": 331400 }, { "epoch": 79.58, "learning_rate": 1.383935535559509e-05, "loss": 0.0012, "step": 331410 }, { "epoch": 79.58, "learning_rate": 1.3836876400647042e-05, "loss": 0.0012, "step": 331420 }, { "epoch": 79.58, "learning_rate": 1.383439763208405e-05, "loss": 0.0011, "step": 331430 }, { "epoch": 79.59, "learning_rate": 1.3831919049918873e-05, "loss": 0.0011, "step": 331440 }, { "epoch": 79.59, "learning_rate": 1.3829440654164271e-05, "loss": 0.0138, "step": 331450 }, { "epoch": 79.59, "learning_rate": 1.3826962444833053e-05, "loss": 0.0012, "step": 331460 }, { "epoch": 79.59, "learning_rate": 1.382448442193795e-05, "loss": 0.0013, "step": 331470 }, { "epoch": 79.59, "learning_rate": 1.3822006585491781e-05, "loss": 0.0012, "step": 331480 }, { "epoch": 79.6, "learning_rate": 1.381952893550727e-05, "loss": 0.0013, "step": 331490 }, { "epoch": 79.6, "learning_rate": 1.3817051471997234e-05, "loss": 0.0014, "step": 331500 }, { "epoch": 79.6, "learning_rate": 1.3814574194974406e-05, "loss": 0.0012, "step": 331510 }, { "epoch": 79.6, "learning_rate": 1.3812097104451554e-05, "loss": 0.0012, "step": 331520 }, { "epoch": 79.61, "learning_rate": 1.3809620200441476e-05, "loss": 0.0012, "step": 331530 }, { "epoch": 79.61, "learning_rate": 1.3807143482956897e-05, "loss": 0.0012, "step": 331540 }, { "epoch": 79.61, "learning_rate": 1.380466695201062e-05, "loss": 0.0012, "step": 331550 }, { "epoch": 79.61, "learning_rate": 1.3802190607615379e-05, "loss": 0.0013, "step": 331560 }, { "epoch": 79.62, "learning_rate": 1.3799714449783962e-05, "loss": 0.0012, "step": 331570 }, { "epoch": 79.62, "learning_rate": 1.3797238478529124e-05, "loss": 0.0012, "step": 331580 }, { "epoch": 79.62, "learning_rate": 1.37947626938636e-05, "loss": 0.0013, "step": 331590 }, { "epoch": 79.62, "learning_rate": 1.3792287095800193e-05, "loss": 0.0012, "step": 331600 }, { "epoch": 79.62, "learning_rate": 1.3789811684351623e-05, "loss": 0.0013, "step": 331610 }, { "epoch": 79.63, "learning_rate": 1.3787336459530681e-05, "loss": 0.0013, "step": 331620 }, { "epoch": 79.63, "learning_rate": 1.3784861421350093e-05, "loss": 0.0013, "step": 331630 }, { "epoch": 79.63, "learning_rate": 1.3782386569822647e-05, "loss": 0.0012, "step": 331640 }, { "epoch": 79.63, "learning_rate": 1.3779911904961073e-05, "loss": 0.0013, "step": 331650 }, { "epoch": 79.64, "learning_rate": 1.3777437426778151e-05, "loss": 0.0012, "step": 331660 }, { "epoch": 79.64, "learning_rate": 1.3774963135286601e-05, "loss": 0.0014, "step": 331670 }, { "epoch": 79.64, "learning_rate": 1.3772489030499207e-05, "loss": 0.0014, "step": 331680 }, { "epoch": 79.64, "learning_rate": 1.3770015112428692e-05, "loss": 0.0013, "step": 331690 }, { "epoch": 79.65, "learning_rate": 1.3767541381087823e-05, "loss": 0.0011, "step": 331700 }, { "epoch": 79.65, "learning_rate": 1.3765067836489365e-05, "loss": 0.0011, "step": 331710 }, { "epoch": 79.65, "learning_rate": 1.3762594478646051e-05, "loss": 0.0013, "step": 331720 }, { "epoch": 79.65, "learning_rate": 1.3760121307570612e-05, "loss": 0.0012, "step": 331730 }, { "epoch": 79.65, "learning_rate": 1.375764832327583e-05, "loss": 0.0013, "step": 331740 }, { "epoch": 79.66, "learning_rate": 1.3755175525774411e-05, "loss": 0.0011, "step": 331750 }, { "epoch": 79.66, "learning_rate": 1.3752702915079136e-05, "loss": 0.0012, "step": 331760 }, { "epoch": 79.66, "learning_rate": 1.375023049120272e-05, "loss": 0.0013, "step": 331770 }, { "epoch": 79.66, "learning_rate": 1.3747758254157934e-05, "loss": 0.0014, "step": 331780 }, { "epoch": 79.67, "learning_rate": 1.3745286203957503e-05, "loss": 0.0011, "step": 331790 }, { "epoch": 79.67, "learning_rate": 1.3742814340614152e-05, "loss": 0.0011, "step": 331800 }, { "epoch": 79.67, "learning_rate": 1.374034266414066e-05, "loss": 0.0117, "step": 331810 }, { "epoch": 79.67, "learning_rate": 1.3737871174549726e-05, "loss": 0.0012, "step": 331820 }, { "epoch": 79.67, "learning_rate": 1.3735399871854126e-05, "loss": 0.002, "step": 331830 }, { "epoch": 79.68, "learning_rate": 1.373292875606656e-05, "loss": 0.0012, "step": 331840 }, { "epoch": 79.68, "learning_rate": 1.37304578271998e-05, "loss": 0.0015, "step": 331850 }, { "epoch": 79.68, "learning_rate": 1.3727987085266542e-05, "loss": 0.0014, "step": 331860 }, { "epoch": 79.68, "learning_rate": 1.3725516530279564e-05, "loss": 0.0012, "step": 331870 }, { "epoch": 79.69, "learning_rate": 1.3723046162251573e-05, "loss": 0.0012, "step": 331880 }, { "epoch": 79.69, "learning_rate": 1.3720575981195294e-05, "loss": 0.0013, "step": 331890 }, { "epoch": 79.69, "learning_rate": 1.3718105987123481e-05, "loss": 0.0012, "step": 331900 }, { "epoch": 79.69, "learning_rate": 1.3715636180048842e-05, "loss": 0.0012, "step": 331910 }, { "epoch": 79.7, "learning_rate": 1.3713166559984125e-05, "loss": 0.0013, "step": 331920 }, { "epoch": 79.7, "learning_rate": 1.3710697126942045e-05, "loss": 0.0038, "step": 331930 }, { "epoch": 79.7, "learning_rate": 1.3708227880935342e-05, "loss": 0.0011, "step": 331940 }, { "epoch": 79.7, "learning_rate": 1.3705758821976744e-05, "loss": 0.0012, "step": 331950 }, { "epoch": 79.7, "learning_rate": 1.3703289950078945e-05, "loss": 0.0012, "step": 331960 }, { "epoch": 79.71, "learning_rate": 1.3700821265254698e-05, "loss": 0.0012, "step": 331970 }, { "epoch": 79.71, "learning_rate": 1.3698352767516736e-05, "loss": 0.0012, "step": 331980 }, { "epoch": 79.71, "learning_rate": 1.3695884456877756e-05, "loss": 0.0011, "step": 331990 }, { "epoch": 79.71, "learning_rate": 1.3693416333350501e-05, "loss": 0.0013, "step": 332000 }, { "epoch": 79.72, "learning_rate": 1.3690948396947667e-05, "loss": 0.0015, "step": 332010 }, { "epoch": 79.72, "learning_rate": 1.3688480647682006e-05, "loss": 0.0012, "step": 332020 }, { "epoch": 79.72, "learning_rate": 1.3686013085566202e-05, "loss": 0.0013, "step": 332030 }, { "epoch": 79.72, "learning_rate": 1.3683545710613006e-05, "loss": 0.0013, "step": 332040 }, { "epoch": 79.73, "learning_rate": 1.36810785228351e-05, "loss": 0.0011, "step": 332050 }, { "epoch": 79.73, "learning_rate": 1.3678611522245238e-05, "loss": 0.0012, "step": 332060 }, { "epoch": 79.73, "learning_rate": 1.3676144708856103e-05, "loss": 0.0012, "step": 332070 }, { "epoch": 79.73, "learning_rate": 1.3673678082680435e-05, "loss": 0.0012, "step": 332080 }, { "epoch": 79.73, "learning_rate": 1.367121164373093e-05, "loss": 0.0012, "step": 332090 }, { "epoch": 79.74, "learning_rate": 1.3668745392020294e-05, "loss": 0.0013, "step": 332100 }, { "epoch": 79.74, "learning_rate": 1.366627932756126e-05, "loss": 0.0011, "step": 332110 }, { "epoch": 79.74, "learning_rate": 1.3663813450366514e-05, "loss": 0.0013, "step": 332120 }, { "epoch": 79.74, "learning_rate": 1.366134776044879e-05, "loss": 0.0012, "step": 332130 }, { "epoch": 79.75, "learning_rate": 1.3658882257820766e-05, "loss": 0.0012, "step": 332140 }, { "epoch": 79.75, "learning_rate": 1.3656416942495187e-05, "loss": 0.0014, "step": 332150 }, { "epoch": 79.75, "learning_rate": 1.3653951814484733e-05, "loss": 0.0012, "step": 332160 }, { "epoch": 79.75, "learning_rate": 1.3651486873802105e-05, "loss": 0.0012, "step": 332170 }, { "epoch": 79.75, "learning_rate": 1.3649022120460031e-05, "loss": 0.0012, "step": 332180 }, { "epoch": 79.76, "learning_rate": 1.3646557554471184e-05, "loss": 0.0013, "step": 332190 }, { "epoch": 79.76, "learning_rate": 1.36440931758483e-05, "loss": 0.0013, "step": 332200 }, { "epoch": 79.76, "learning_rate": 1.3641628984604049e-05, "loss": 0.0015, "step": 332210 }, { "epoch": 79.76, "learning_rate": 1.3639164980751157e-05, "loss": 0.0013, "step": 332220 }, { "epoch": 79.77, "learning_rate": 1.3636701164302319e-05, "loss": 0.0012, "step": 332230 }, { "epoch": 79.77, "learning_rate": 1.3634237535270206e-05, "loss": 0.0012, "step": 332240 }, { "epoch": 79.77, "learning_rate": 1.3631774093667554e-05, "loss": 0.0013, "step": 332250 }, { "epoch": 79.77, "learning_rate": 1.3629310839507032e-05, "loss": 0.0013, "step": 332260 }, { "epoch": 79.78, "learning_rate": 1.3626847772801355e-05, "loss": 0.0012, "step": 332270 }, { "epoch": 79.78, "learning_rate": 1.3624384893563197e-05, "loss": 0.0117, "step": 332280 }, { "epoch": 79.78, "learning_rate": 1.362192220180526e-05, "loss": 0.0013, "step": 332290 }, { "epoch": 79.78, "learning_rate": 1.361945969754026e-05, "loss": 0.0012, "step": 332300 }, { "epoch": 79.78, "learning_rate": 1.361699738078085e-05, "loss": 0.0013, "step": 332310 }, { "epoch": 79.79, "learning_rate": 1.3614535251539756e-05, "loss": 0.0012, "step": 332320 }, { "epoch": 79.79, "learning_rate": 1.3612073309829637e-05, "loss": 0.0011, "step": 332330 }, { "epoch": 79.79, "learning_rate": 1.360961155566321e-05, "loss": 0.0013, "step": 332340 }, { "epoch": 79.79, "learning_rate": 1.360714998905313e-05, "loss": 0.0013, "step": 332350 }, { "epoch": 79.8, "learning_rate": 1.3604688610012123e-05, "loss": 0.0012, "step": 332360 }, { "epoch": 79.8, "learning_rate": 1.360222741855286e-05, "loss": 0.0012, "step": 332370 }, { "epoch": 79.8, "learning_rate": 1.3599766414687998e-05, "loss": 0.0012, "step": 332380 }, { "epoch": 79.8, "learning_rate": 1.359730559843026e-05, "loss": 0.0011, "step": 332390 }, { "epoch": 79.81, "learning_rate": 1.3594844969792303e-05, "loss": 0.0012, "step": 332400 }, { "epoch": 79.81, "learning_rate": 1.3592384528786833e-05, "loss": 0.0013, "step": 332410 }, { "epoch": 79.81, "learning_rate": 1.3589924275426497e-05, "loss": 0.0013, "step": 332420 }, { "epoch": 79.81, "learning_rate": 1.3587464209724016e-05, "loss": 0.0011, "step": 332430 }, { "epoch": 79.81, "learning_rate": 1.3585004331692048e-05, "loss": 0.0012, "step": 332440 }, { "epoch": 79.82, "learning_rate": 1.3582544641343259e-05, "loss": 0.0013, "step": 332450 }, { "epoch": 79.82, "learning_rate": 1.3580085138690352e-05, "loss": 0.0012, "step": 332460 }, { "epoch": 79.82, "learning_rate": 1.357762582374597e-05, "loss": 0.0013, "step": 332470 }, { "epoch": 79.82, "learning_rate": 1.3575166696522835e-05, "loss": 0.0012, "step": 332480 }, { "epoch": 79.83, "learning_rate": 1.3572707757033571e-05, "loss": 0.0012, "step": 332490 }, { "epoch": 79.83, "learning_rate": 1.3570249005290896e-05, "loss": 0.0012, "step": 332500 }, { "epoch": 79.83, "learning_rate": 1.3567790441307459e-05, "loss": 0.0013, "step": 332510 }, { "epoch": 79.83, "learning_rate": 1.356533206509592e-05, "loss": 0.0011, "step": 332520 }, { "epoch": 79.83, "learning_rate": 1.3562873876668985e-05, "loss": 0.0013, "step": 332530 }, { "epoch": 79.84, "learning_rate": 1.3560415876039278e-05, "loss": 0.0011, "step": 332540 }, { "epoch": 79.84, "learning_rate": 1.3557958063219517e-05, "loss": 0.0011, "step": 332550 }, { "epoch": 79.84, "learning_rate": 1.3555500438222323e-05, "loss": 0.0013, "step": 332560 }, { "epoch": 79.84, "learning_rate": 1.35530430010604e-05, "loss": 0.0013, "step": 332570 }, { "epoch": 79.85, "learning_rate": 1.3550585751746387e-05, "loss": 0.0012, "step": 332580 }, { "epoch": 79.85, "learning_rate": 1.3548128690292954e-05, "loss": 0.0013, "step": 332590 }, { "epoch": 79.85, "learning_rate": 1.354567181671279e-05, "loss": 0.0012, "step": 332600 }, { "epoch": 79.85, "learning_rate": 1.3543215131018521e-05, "loss": 0.0013, "step": 332610 }, { "epoch": 79.86, "learning_rate": 1.3540758633222844e-05, "loss": 0.0012, "step": 332620 }, { "epoch": 79.86, "learning_rate": 1.3538302323338381e-05, "loss": 0.0011, "step": 332630 }, { "epoch": 79.86, "learning_rate": 1.3535846201377834e-05, "loss": 0.0013, "step": 332640 }, { "epoch": 79.86, "learning_rate": 1.3533390267353818e-05, "loss": 0.0036, "step": 332650 }, { "epoch": 79.86, "learning_rate": 1.3530934521279037e-05, "loss": 0.0013, "step": 332660 }, { "epoch": 79.87, "learning_rate": 1.3528478963166119e-05, "loss": 0.0012, "step": 332670 }, { "epoch": 79.87, "learning_rate": 1.3526023593027709e-05, "loss": 0.0011, "step": 332680 }, { "epoch": 79.87, "learning_rate": 1.3523568410876497e-05, "loss": 0.0012, "step": 332690 }, { "epoch": 79.87, "learning_rate": 1.3521113416725101e-05, "loss": 0.0013, "step": 332700 }, { "epoch": 79.88, "learning_rate": 1.351865861058621e-05, "loss": 0.0011, "step": 332710 }, { "epoch": 79.88, "learning_rate": 1.3516203992472437e-05, "loss": 0.0011, "step": 332720 }, { "epoch": 79.88, "learning_rate": 1.3513749562396471e-05, "loss": 0.0012, "step": 332730 }, { "epoch": 79.88, "learning_rate": 1.3511295320370948e-05, "loss": 0.0011, "step": 332740 }, { "epoch": 79.89, "learning_rate": 1.3508841266408495e-05, "loss": 0.0011, "step": 332750 }, { "epoch": 79.89, "learning_rate": 1.3506387400521792e-05, "loss": 0.0012, "step": 332760 }, { "epoch": 79.89, "learning_rate": 1.350393372272346e-05, "loss": 0.0045, "step": 332770 }, { "epoch": 79.89, "learning_rate": 1.3501480233026175e-05, "loss": 0.0012, "step": 332780 }, { "epoch": 79.89, "learning_rate": 1.3499026931442554e-05, "loss": 0.0013, "step": 332790 }, { "epoch": 79.9, "learning_rate": 1.3496573817985264e-05, "loss": 0.0012, "step": 332800 }, { "epoch": 79.9, "learning_rate": 1.3494120892666939e-05, "loss": 0.0011, "step": 332810 }, { "epoch": 79.9, "learning_rate": 1.3491668155500203e-05, "loss": 0.0013, "step": 332820 }, { "epoch": 79.9, "learning_rate": 1.3489215606497736e-05, "loss": 0.0013, "step": 332830 }, { "epoch": 79.91, "learning_rate": 1.3486763245672135e-05, "loss": 0.0012, "step": 332840 }, { "epoch": 79.91, "learning_rate": 1.3484311073036082e-05, "loss": 0.0011, "step": 332850 }, { "epoch": 79.91, "learning_rate": 1.3481859088602172e-05, "loss": 0.0014, "step": 332860 }, { "epoch": 79.91, "learning_rate": 1.3479407292383089e-05, "loss": 0.0011, "step": 332870 }, { "epoch": 79.91, "learning_rate": 1.3476955684391429e-05, "loss": 0.0012, "step": 332880 }, { "epoch": 79.92, "learning_rate": 1.3474504264639853e-05, "loss": 0.0012, "step": 332890 }, { "epoch": 79.92, "learning_rate": 1.347205303314098e-05, "loss": 0.0011, "step": 332900 }, { "epoch": 79.92, "learning_rate": 1.346960198990745e-05, "loss": 0.0011, "step": 332910 }, { "epoch": 79.92, "learning_rate": 1.3467151134951911e-05, "loss": 0.0012, "step": 332920 }, { "epoch": 79.93, "learning_rate": 1.346470046828696e-05, "loss": 0.0011, "step": 332930 }, { "epoch": 79.93, "learning_rate": 1.3462249989925268e-05, "loss": 0.0013, "step": 332940 }, { "epoch": 79.93, "learning_rate": 1.345979969987945e-05, "loss": 0.0012, "step": 332950 }, { "epoch": 79.93, "learning_rate": 1.3457349598162106e-05, "loss": 0.0013, "step": 332960 }, { "epoch": 79.94, "learning_rate": 1.3454899684785905e-05, "loss": 0.0012, "step": 332970 }, { "epoch": 79.94, "learning_rate": 1.3452449959763447e-05, "loss": 0.0012, "step": 332980 }, { "epoch": 79.94, "learning_rate": 1.3450000423107374e-05, "loss": 0.0012, "step": 332990 }, { "epoch": 79.94, "learning_rate": 1.3447551074830295e-05, "loss": 0.0011, "step": 333000 }, { "epoch": 79.94, "learning_rate": 1.3445101914944858e-05, "loss": 0.0013, "step": 333010 }, { "epoch": 79.95, "learning_rate": 1.3442652943463669e-05, "loss": 0.0013, "step": 333020 }, { "epoch": 79.95, "learning_rate": 1.3440204160399339e-05, "loss": 0.0013, "step": 333030 }, { "epoch": 79.95, "learning_rate": 1.3437755565764514e-05, "loss": 0.0012, "step": 333040 }, { "epoch": 80.0, "learning_rate": 1.3435307159571792e-05, "loss": 0.0011, "step": 333050 }, { "epoch": 80.0, "learning_rate": 1.3432858941833815e-05, "loss": 0.0013, "step": 333060 }, { "epoch": 80.01, "learning_rate": 1.3430410912563174e-05, "loss": 0.0013, "step": 333070 }, { "epoch": 80.01, "learning_rate": 1.3427963071772515e-05, "loss": 0.001, "step": 333080 }, { "epoch": 80.01, "learning_rate": 1.3425515419474444e-05, "loss": 0.0013, "step": 333090 }, { "epoch": 80.01, "learning_rate": 1.342306795568155e-05, "loss": 0.0011, "step": 333100 }, { "epoch": 80.02, "learning_rate": 1.3420620680406492e-05, "loss": 0.0013, "step": 333110 }, { "epoch": 80.02, "learning_rate": 1.3418173593661843e-05, "loss": 0.0013, "step": 333120 }, { "epoch": 80.02, "learning_rate": 1.3415726695460246e-05, "loss": 0.0013, "step": 333130 }, { "epoch": 80.02, "learning_rate": 1.3413279985814286e-05, "loss": 0.0011, "step": 333140 }, { "epoch": 80.03, "learning_rate": 1.34108334647366e-05, "loss": 0.0013, "step": 333150 }, { "epoch": 80.03, "learning_rate": 1.3408387132239774e-05, "loss": 0.0011, "step": 333160 }, { "epoch": 80.03, "learning_rate": 1.3405940988336435e-05, "loss": 0.001, "step": 333170 }, { "epoch": 80.03, "learning_rate": 1.340349503303917e-05, "loss": 0.0012, "step": 333180 }, { "epoch": 80.03, "learning_rate": 1.3401049266360617e-05, "loss": 0.0011, "step": 333190 }, { "epoch": 80.04, "learning_rate": 1.3398603688313344e-05, "loss": 0.0013, "step": 333200 }, { "epoch": 80.04, "learning_rate": 1.3396158298909983e-05, "loss": 0.0011, "step": 333210 }, { "epoch": 80.04, "learning_rate": 1.3393713098163118e-05, "loss": 0.0013, "step": 333220 }, { "epoch": 80.04, "learning_rate": 1.3391268086085379e-05, "loss": 0.0012, "step": 333230 }, { "epoch": 80.05, "learning_rate": 1.3388823262689331e-05, "loss": 0.0011, "step": 333240 }, { "epoch": 80.05, "learning_rate": 1.338637862798761e-05, "loss": 0.0014, "step": 333250 }, { "epoch": 80.05, "learning_rate": 1.3383934181992786e-05, "loss": 0.0012, "step": 333260 }, { "epoch": 80.05, "learning_rate": 1.3381489924717489e-05, "loss": 0.0011, "step": 333270 }, { "epoch": 80.05, "learning_rate": 1.3379045856174277e-05, "loss": 0.0012, "step": 333280 }, { "epoch": 80.06, "learning_rate": 1.337660197637579e-05, "loss": 0.0013, "step": 333290 }, { "epoch": 80.06, "learning_rate": 1.3374158285334598e-05, "loss": 0.0014, "step": 333300 }, { "epoch": 80.06, "learning_rate": 1.3371714783063289e-05, "loss": 0.0013, "step": 333310 }, { "epoch": 80.06, "learning_rate": 1.336927146957448e-05, "loss": 0.0012, "step": 333320 }, { "epoch": 80.07, "learning_rate": 1.3366828344880739e-05, "loss": 0.0012, "step": 333330 }, { "epoch": 80.07, "learning_rate": 1.3364385408994684e-05, "loss": 0.0012, "step": 333340 }, { "epoch": 80.07, "learning_rate": 1.3361942661928877e-05, "loss": 0.0013, "step": 333350 }, { "epoch": 80.07, "learning_rate": 1.3359500103695943e-05, "loss": 0.0012, "step": 333360 }, { "epoch": 80.08, "learning_rate": 1.3357057734308448e-05, "loss": 0.0013, "step": 333370 }, { "epoch": 80.08, "learning_rate": 1.335461555377897e-05, "loss": 0.0013, "step": 333380 }, { "epoch": 80.08, "learning_rate": 1.3352173562120129e-05, "loss": 0.0013, "step": 333390 }, { "epoch": 80.08, "learning_rate": 1.334973175934447e-05, "loss": 0.0012, "step": 333400 }, { "epoch": 80.08, "learning_rate": 1.334729014546462e-05, "loss": 0.0013, "step": 333410 }, { "epoch": 80.09, "learning_rate": 1.3344848720493124e-05, "loss": 0.0013, "step": 333420 }, { "epoch": 80.09, "learning_rate": 1.3342407484442603e-05, "loss": 0.0012, "step": 333430 }, { "epoch": 80.09, "learning_rate": 1.3339966437325602e-05, "loss": 0.0013, "step": 333440 }, { "epoch": 80.09, "learning_rate": 1.3337525579154736e-05, "loss": 0.0011, "step": 333450 }, { "epoch": 80.1, "learning_rate": 1.3335084909942569e-05, "loss": 0.0012, "step": 333460 }, { "epoch": 80.1, "learning_rate": 1.3332644429701668e-05, "loss": 0.0011, "step": 333470 }, { "epoch": 80.1, "learning_rate": 1.3330204138444624e-05, "loss": 0.0012, "step": 333480 }, { "epoch": 80.1, "learning_rate": 1.3327764036184026e-05, "loss": 0.0012, "step": 333490 }, { "epoch": 80.11, "learning_rate": 1.3325324122932426e-05, "loss": 0.0011, "step": 333500 }, { "epoch": 80.11, "learning_rate": 1.3322884398702429e-05, "loss": 0.0012, "step": 333510 }, { "epoch": 80.11, "learning_rate": 1.3320444863506577e-05, "loss": 0.0013, "step": 333520 }, { "epoch": 80.11, "learning_rate": 1.3318005517357469e-05, "loss": 0.0016, "step": 333530 }, { "epoch": 80.11, "learning_rate": 1.3315566360267656e-05, "loss": 0.0011, "step": 333540 }, { "epoch": 80.12, "learning_rate": 1.3313127392249735e-05, "loss": 0.0014, "step": 333550 }, { "epoch": 80.12, "learning_rate": 1.3310688613316247e-05, "loss": 0.0013, "step": 333560 }, { "epoch": 80.12, "learning_rate": 1.330825002347979e-05, "loss": 0.0012, "step": 333570 }, { "epoch": 80.12, "learning_rate": 1.3305811622752906e-05, "loss": 0.0014, "step": 333580 }, { "epoch": 80.13, "learning_rate": 1.330337341114819e-05, "loss": 0.001, "step": 333590 }, { "epoch": 80.13, "learning_rate": 1.3300935388678199e-05, "loss": 0.0013, "step": 333600 }, { "epoch": 80.13, "learning_rate": 1.3298497555355471e-05, "loss": 0.0013, "step": 333610 }, { "epoch": 80.13, "learning_rate": 1.329605991119261e-05, "loss": 0.0013, "step": 333620 }, { "epoch": 80.13, "learning_rate": 1.3293622456202153e-05, "loss": 0.0017, "step": 333630 }, { "epoch": 80.14, "learning_rate": 1.3291185190396682e-05, "loss": 0.0022, "step": 333640 }, { "epoch": 80.14, "learning_rate": 1.3288748113788741e-05, "loss": 0.0013, "step": 333650 }, { "epoch": 80.14, "learning_rate": 1.3286311226390907e-05, "loss": 0.0012, "step": 333660 }, { "epoch": 80.14, "learning_rate": 1.3283874528215733e-05, "loss": 0.0011, "step": 333670 }, { "epoch": 80.15, "learning_rate": 1.3281438019275766e-05, "loss": 0.0011, "step": 333680 }, { "epoch": 80.15, "learning_rate": 1.3279001699583587e-05, "loss": 0.0012, "step": 333690 }, { "epoch": 80.15, "learning_rate": 1.3276565569151722e-05, "loss": 0.0011, "step": 333700 }, { "epoch": 80.15, "learning_rate": 1.3274129627992765e-05, "loss": 0.0012, "step": 333710 }, { "epoch": 80.16, "learning_rate": 1.3271693876119235e-05, "loss": 0.0013, "step": 333720 }, { "epoch": 80.16, "learning_rate": 1.3269258313543715e-05, "loss": 0.0012, "step": 333730 }, { "epoch": 80.16, "learning_rate": 1.3266822940278745e-05, "loss": 0.0012, "step": 333740 }, { "epoch": 80.16, "learning_rate": 1.326438775633686e-05, "loss": 0.0014, "step": 333750 }, { "epoch": 80.16, "learning_rate": 1.3261952761730644e-05, "loss": 0.0012, "step": 333760 }, { "epoch": 80.17, "learning_rate": 1.3259517956472617e-05, "loss": 0.0011, "step": 333770 }, { "epoch": 80.17, "learning_rate": 1.3257083340575355e-05, "loss": 0.0013, "step": 333780 }, { "epoch": 80.17, "learning_rate": 1.3254648914051376e-05, "loss": 0.0012, "step": 333790 }, { "epoch": 80.17, "learning_rate": 1.3252214676913249e-05, "loss": 0.0012, "step": 333800 }, { "epoch": 80.18, "learning_rate": 1.3249780629173525e-05, "loss": 0.0012, "step": 333810 }, { "epoch": 80.18, "learning_rate": 1.3247346770844726e-05, "loss": 0.0013, "step": 333820 }, { "epoch": 80.18, "learning_rate": 1.324491310193942e-05, "loss": 0.0012, "step": 333830 }, { "epoch": 80.18, "learning_rate": 1.3242479622470127e-05, "loss": 0.0045, "step": 333840 }, { "epoch": 80.19, "learning_rate": 1.3240046332449418e-05, "loss": 0.0014, "step": 333850 }, { "epoch": 80.19, "learning_rate": 1.32376132318898e-05, "loss": 0.0012, "step": 333860 }, { "epoch": 80.19, "learning_rate": 1.3235180320803848e-05, "loss": 0.0012, "step": 333870 }, { "epoch": 80.19, "learning_rate": 1.3232747599204082e-05, "loss": 0.003, "step": 333880 }, { "epoch": 80.19, "learning_rate": 1.3230315067103028e-05, "loss": 0.0012, "step": 333890 }, { "epoch": 80.2, "learning_rate": 1.3227882724513252e-05, "loss": 0.001, "step": 333900 }, { "epoch": 80.2, "learning_rate": 1.3225450571447262e-05, "loss": 0.0014, "step": 333910 }, { "epoch": 80.2, "learning_rate": 1.322301860791762e-05, "loss": 0.0012, "step": 333920 }, { "epoch": 80.2, "learning_rate": 1.3220586833936832e-05, "loss": 0.0011, "step": 333930 }, { "epoch": 80.21, "learning_rate": 1.3218155249517467e-05, "loss": 0.0011, "step": 333940 }, { "epoch": 80.21, "learning_rate": 1.3215723854672035e-05, "loss": 0.0012, "step": 333950 }, { "epoch": 80.21, "learning_rate": 1.321329264941305e-05, "loss": 0.0012, "step": 333960 }, { "epoch": 80.21, "learning_rate": 1.321086163375308e-05, "loss": 0.0012, "step": 333970 }, { "epoch": 80.21, "learning_rate": 1.3208430807704626e-05, "loss": 0.0012, "step": 333980 }, { "epoch": 80.22, "learning_rate": 1.3206000171280237e-05, "loss": 0.0011, "step": 333990 }, { "epoch": 80.22, "learning_rate": 1.3203569724492415e-05, "loss": 0.001, "step": 334000 }, { "epoch": 80.22, "learning_rate": 1.3201139467353723e-05, "loss": 0.0012, "step": 334010 }, { "epoch": 80.22, "learning_rate": 1.3198709399876662e-05, "loss": 0.0011, "step": 334020 }, { "epoch": 80.23, "learning_rate": 1.3196279522073746e-05, "loss": 0.0013, "step": 334030 }, { "epoch": 80.23, "learning_rate": 1.3193849833957528e-05, "loss": 0.0012, "step": 334040 }, { "epoch": 80.23, "learning_rate": 1.31914203355405e-05, "loss": 0.0013, "step": 334050 }, { "epoch": 80.23, "learning_rate": 1.3188991026835212e-05, "loss": 0.0011, "step": 334060 }, { "epoch": 80.24, "learning_rate": 1.3186561907854162e-05, "loss": 0.0013, "step": 334070 }, { "epoch": 80.24, "learning_rate": 1.3184132978609892e-05, "loss": 0.0012, "step": 334080 }, { "epoch": 80.24, "learning_rate": 1.318170423911489e-05, "loss": 0.0013, "step": 334090 }, { "epoch": 80.24, "learning_rate": 1.3179275689381699e-05, "loss": 0.0012, "step": 334100 }, { "epoch": 80.24, "learning_rate": 1.3176847329422837e-05, "loss": 0.0011, "step": 334110 }, { "epoch": 80.25, "learning_rate": 1.31744191592508e-05, "loss": 0.0012, "step": 334120 }, { "epoch": 80.25, "learning_rate": 1.317199117887813e-05, "loss": 0.0011, "step": 334130 }, { "epoch": 80.25, "learning_rate": 1.3169563388317314e-05, "loss": 0.0012, "step": 334140 }, { "epoch": 80.25, "learning_rate": 1.3167135787580886e-05, "loss": 0.0012, "step": 334150 }, { "epoch": 80.26, "learning_rate": 1.3164708376681345e-05, "loss": 0.0012, "step": 334160 }, { "epoch": 80.26, "learning_rate": 1.3162281155631195e-05, "loss": 0.0011, "step": 334170 }, { "epoch": 80.26, "learning_rate": 1.3159854124442972e-05, "loss": 0.0012, "step": 334180 }, { "epoch": 80.26, "learning_rate": 1.3157427283129148e-05, "loss": 0.0015, "step": 334190 }, { "epoch": 80.27, "learning_rate": 1.3155000631702275e-05, "loss": 0.0012, "step": 334200 }, { "epoch": 80.27, "learning_rate": 1.3152574170174813e-05, "loss": 0.0013, "step": 334210 }, { "epoch": 80.27, "learning_rate": 1.3150147898559312e-05, "loss": 0.0011, "step": 334220 }, { "epoch": 80.27, "learning_rate": 1.3147721816868258e-05, "loss": 0.0011, "step": 334230 }, { "epoch": 80.27, "learning_rate": 1.3145295925114132e-05, "loss": 0.0013, "step": 334240 }, { "epoch": 80.28, "learning_rate": 1.3142870223309478e-05, "loss": 0.0012, "step": 334250 }, { "epoch": 80.28, "learning_rate": 1.3140444711466765e-05, "loss": 0.0012, "step": 334260 }, { "epoch": 80.28, "learning_rate": 1.3138019389598522e-05, "loss": 0.0011, "step": 334270 }, { "epoch": 80.28, "learning_rate": 1.3135594257717222e-05, "loss": 0.0012, "step": 334280 }, { "epoch": 80.29, "learning_rate": 1.3133169315835393e-05, "loss": 0.0011, "step": 334290 }, { "epoch": 80.29, "learning_rate": 1.3130744563965497e-05, "loss": 0.0013, "step": 334300 }, { "epoch": 80.29, "learning_rate": 1.312832000212007e-05, "loss": 0.0013, "step": 334310 }, { "epoch": 80.29, "learning_rate": 1.312589563031159e-05, "loss": 0.0013, "step": 334320 }, { "epoch": 80.29, "learning_rate": 1.3123471448552538e-05, "loss": 0.0011, "step": 334330 }, { "epoch": 80.3, "learning_rate": 1.3121047456855433e-05, "loss": 0.0011, "step": 334340 }, { "epoch": 80.3, "learning_rate": 1.3118623655232748e-05, "loss": 0.0012, "step": 334350 }, { "epoch": 80.3, "learning_rate": 1.3116200043696996e-05, "loss": 0.0012, "step": 334360 }, { "epoch": 80.3, "learning_rate": 1.3113776622260648e-05, "loss": 0.0013, "step": 334370 }, { "epoch": 80.31, "learning_rate": 1.3111353390936215e-05, "loss": 0.0012, "step": 334380 }, { "epoch": 80.31, "learning_rate": 1.310893034973616e-05, "loss": 0.0011, "step": 334390 }, { "epoch": 80.31, "learning_rate": 1.3106507498672999e-05, "loss": 0.0011, "step": 334400 }, { "epoch": 80.31, "learning_rate": 1.3104084837759195e-05, "loss": 0.0012, "step": 334410 }, { "epoch": 80.32, "learning_rate": 1.3101662367007244e-05, "loss": 0.0012, "step": 334420 }, { "epoch": 80.32, "learning_rate": 1.3099240086429649e-05, "loss": 0.0011, "step": 334430 }, { "epoch": 80.32, "learning_rate": 1.3096817996038863e-05, "loss": 0.0012, "step": 334440 }, { "epoch": 80.32, "learning_rate": 1.3094396095847406e-05, "loss": 0.0013, "step": 334450 }, { "epoch": 80.32, "learning_rate": 1.3091974385867734e-05, "loss": 0.0011, "step": 334460 }, { "epoch": 80.33, "learning_rate": 1.308955286611232e-05, "loss": 0.0012, "step": 334470 }, { "epoch": 80.33, "learning_rate": 1.3087131536593678e-05, "loss": 0.0012, "step": 334480 }, { "epoch": 80.33, "learning_rate": 1.308471039732425e-05, "loss": 0.0012, "step": 334490 }, { "epoch": 80.33, "learning_rate": 1.3082289448316548e-05, "loss": 0.0012, "step": 334500 }, { "epoch": 80.34, "learning_rate": 1.3079868689583025e-05, "loss": 0.0011, "step": 334510 }, { "epoch": 80.34, "learning_rate": 1.3077448121136177e-05, "loss": 0.0011, "step": 334520 }, { "epoch": 80.34, "learning_rate": 1.3075027742988472e-05, "loss": 0.0012, "step": 334530 }, { "epoch": 80.34, "learning_rate": 1.3072607555152366e-05, "loss": 0.0011, "step": 334540 }, { "epoch": 80.35, "learning_rate": 1.3070187557640368e-05, "loss": 0.001, "step": 334550 }, { "epoch": 80.35, "learning_rate": 1.3067767750464915e-05, "loss": 0.0011, "step": 334560 }, { "epoch": 80.35, "learning_rate": 1.306534813363851e-05, "loss": 0.0012, "step": 334570 }, { "epoch": 80.35, "learning_rate": 1.3062928707173594e-05, "loss": 0.0011, "step": 334580 }, { "epoch": 80.35, "learning_rate": 1.3060509471082665e-05, "loss": 0.0011, "step": 334590 }, { "epoch": 80.36, "learning_rate": 1.3058090425378183e-05, "loss": 0.0013, "step": 334600 }, { "epoch": 80.36, "learning_rate": 1.3055671570072598e-05, "loss": 0.0012, "step": 334610 }, { "epoch": 80.36, "learning_rate": 1.3053252905178404e-05, "loss": 0.0011, "step": 334620 }, { "epoch": 80.36, "learning_rate": 1.3050834430708036e-05, "loss": 0.0011, "step": 334630 }, { "epoch": 80.37, "learning_rate": 1.3048416146673991e-05, "loss": 0.0011, "step": 334640 }, { "epoch": 80.37, "learning_rate": 1.3045998053088704e-05, "loss": 0.0012, "step": 334650 }, { "epoch": 80.37, "learning_rate": 1.3043580149964668e-05, "loss": 0.0011, "step": 334660 }, { "epoch": 80.37, "learning_rate": 1.3041162437314314e-05, "loss": 0.0011, "step": 334670 }, { "epoch": 80.37, "learning_rate": 1.3038744915150136e-05, "loss": 0.0012, "step": 334680 }, { "epoch": 80.38, "learning_rate": 1.3036327583484553e-05, "loss": 0.0011, "step": 334690 }, { "epoch": 80.38, "learning_rate": 1.3033910442330066e-05, "loss": 0.0012, "step": 334700 }, { "epoch": 80.38, "learning_rate": 1.3031493491699099e-05, "loss": 0.0011, "step": 334710 }, { "epoch": 80.38, "learning_rate": 1.302907673160414e-05, "loss": 0.0011, "step": 334720 }, { "epoch": 80.39, "learning_rate": 1.3026660162057609e-05, "loss": 0.0012, "step": 334730 }, { "epoch": 80.39, "learning_rate": 1.3024243783072e-05, "loss": 0.0011, "step": 334740 }, { "epoch": 80.39, "learning_rate": 1.302182759465973e-05, "loss": 0.0012, "step": 334750 }, { "epoch": 80.39, "learning_rate": 1.3019411596833287e-05, "loss": 0.0013, "step": 334760 }, { "epoch": 80.4, "learning_rate": 1.3016995789605085e-05, "loss": 0.0011, "step": 334770 }, { "epoch": 80.4, "learning_rate": 1.3014580172987617e-05, "loss": 0.0011, "step": 334780 }, { "epoch": 80.4, "learning_rate": 1.3012164746993295e-05, "loss": 0.0013, "step": 334790 }, { "epoch": 80.4, "learning_rate": 1.30097495116346e-05, "loss": 0.0012, "step": 334800 }, { "epoch": 80.4, "learning_rate": 1.3007334466923964e-05, "loss": 0.0012, "step": 334810 }, { "epoch": 80.41, "learning_rate": 1.3004919612873816e-05, "loss": 0.0011, "step": 334820 }, { "epoch": 80.41, "learning_rate": 1.3002504949496646e-05, "loss": 0.0011, "step": 334830 }, { "epoch": 80.41, "learning_rate": 1.3000090476804855e-05, "loss": 0.0012, "step": 334840 }, { "epoch": 80.41, "learning_rate": 1.299767619481092e-05, "loss": 0.0011, "step": 334850 }, { "epoch": 80.42, "learning_rate": 1.2995262103527262e-05, "loss": 0.0013, "step": 334860 }, { "epoch": 80.42, "learning_rate": 1.2992848202966345e-05, "loss": 0.0014, "step": 334870 }, { "epoch": 80.42, "learning_rate": 1.2990434493140596e-05, "loss": 0.0016, "step": 334880 }, { "epoch": 80.42, "learning_rate": 1.2988020974062442e-05, "loss": 0.0012, "step": 334890 }, { "epoch": 80.43, "learning_rate": 1.2985607645744352e-05, "loss": 0.0012, "step": 334900 }, { "epoch": 80.43, "learning_rate": 1.2983194508198736e-05, "loss": 0.0011, "step": 334910 }, { "epoch": 80.43, "learning_rate": 1.298078156143806e-05, "loss": 0.0011, "step": 334920 }, { "epoch": 80.43, "learning_rate": 1.2978368805474728e-05, "loss": 0.0012, "step": 334930 }, { "epoch": 80.43, "learning_rate": 1.2975956240321213e-05, "loss": 0.0012, "step": 334940 }, { "epoch": 80.44, "learning_rate": 1.2973543865989924e-05, "loss": 0.0012, "step": 334950 }, { "epoch": 80.44, "learning_rate": 1.2971131682493287e-05, "loss": 0.0013, "step": 334960 }, { "epoch": 80.44, "learning_rate": 1.2968719689843761e-05, "loss": 0.0012, "step": 334970 }, { "epoch": 80.44, "learning_rate": 1.2966307888053747e-05, "loss": 0.0012, "step": 334980 }, { "epoch": 80.45, "learning_rate": 1.296389627713569e-05, "loss": 0.0012, "step": 334990 }, { "epoch": 80.45, "learning_rate": 1.296148485710204e-05, "loss": 0.0011, "step": 335000 }, { "epoch": 80.45, "learning_rate": 1.2959073627965191e-05, "loss": 0.0012, "step": 335010 }, { "epoch": 80.45, "learning_rate": 1.2956662589737601e-05, "loss": 0.0012, "step": 335020 }, { "epoch": 80.45, "learning_rate": 1.2954251742431666e-05, "loss": 0.0013, "step": 335030 }, { "epoch": 80.46, "learning_rate": 1.295184108605984e-05, "loss": 0.0012, "step": 335040 }, { "epoch": 80.46, "learning_rate": 1.2949430620634522e-05, "loss": 0.0012, "step": 335050 }, { "epoch": 80.46, "learning_rate": 1.2947020346168165e-05, "loss": 0.0011, "step": 335060 }, { "epoch": 80.46, "learning_rate": 1.2944610262673157e-05, "loss": 0.001, "step": 335070 }, { "epoch": 80.47, "learning_rate": 1.2942200370161956e-05, "loss": 0.0011, "step": 335080 }, { "epoch": 80.47, "learning_rate": 1.2939790668646945e-05, "loss": 0.0018, "step": 335090 }, { "epoch": 80.47, "learning_rate": 1.2937381158140583e-05, "loss": 0.0014, "step": 335100 }, { "epoch": 80.47, "learning_rate": 1.2934971838655263e-05, "loss": 0.0011, "step": 335110 }, { "epoch": 80.48, "learning_rate": 1.2932562710203394e-05, "loss": 0.0013, "step": 335120 }, { "epoch": 80.48, "learning_rate": 1.2930153772797421e-05, "loss": 0.0011, "step": 335130 }, { "epoch": 80.48, "learning_rate": 1.2927745026449733e-05, "loss": 0.0012, "step": 335140 }, { "epoch": 80.48, "learning_rate": 1.2925336471172771e-05, "loss": 0.0012, "step": 335150 }, { "epoch": 80.48, "learning_rate": 1.292292810697892e-05, "loss": 0.0015, "step": 335160 }, { "epoch": 80.49, "learning_rate": 1.292051993388062e-05, "loss": 0.0012, "step": 335170 }, { "epoch": 80.49, "learning_rate": 1.2918111951890272e-05, "loss": 0.0011, "step": 335180 }, { "epoch": 80.49, "learning_rate": 1.291570416102027e-05, "loss": 0.0012, "step": 335190 }, { "epoch": 80.49, "learning_rate": 1.2913296561283057e-05, "loss": 0.0012, "step": 335200 }, { "epoch": 80.5, "learning_rate": 1.2910889152691003e-05, "loss": 0.0012, "step": 335210 }, { "epoch": 80.5, "learning_rate": 1.2908481935256555e-05, "loss": 0.0012, "step": 335220 }, { "epoch": 80.5, "learning_rate": 1.2906074908992083e-05, "loss": 0.0011, "step": 335230 }, { "epoch": 80.5, "learning_rate": 1.290366807391003e-05, "loss": 0.0011, "step": 335240 }, { "epoch": 80.51, "learning_rate": 1.2901261430022776e-05, "loss": 0.0012, "step": 335250 }, { "epoch": 80.51, "learning_rate": 1.2898854977342722e-05, "loss": 0.0015, "step": 335260 }, { "epoch": 80.51, "learning_rate": 1.2896448715882293e-05, "loss": 0.0012, "step": 335270 }, { "epoch": 80.51, "learning_rate": 1.289404264565386e-05, "loss": 0.0012, "step": 335280 }, { "epoch": 80.51, "learning_rate": 1.2891636766669857e-05, "loss": 0.0012, "step": 335290 }, { "epoch": 80.52, "learning_rate": 1.2889231078942654e-05, "loss": 0.0011, "step": 335300 }, { "epoch": 80.52, "learning_rate": 1.2886825582484663e-05, "loss": 0.0011, "step": 335310 }, { "epoch": 80.52, "learning_rate": 1.2884420277308302e-05, "loss": 0.0012, "step": 335320 }, { "epoch": 80.52, "learning_rate": 1.2882015163425931e-05, "loss": 0.0011, "step": 335330 }, { "epoch": 80.53, "learning_rate": 1.2879610240849977e-05, "loss": 0.0012, "step": 335340 }, { "epoch": 80.53, "learning_rate": 1.287720550959281e-05, "loss": 0.0011, "step": 335350 }, { "epoch": 80.53, "learning_rate": 1.287480096966685e-05, "loss": 0.0011, "step": 335360 }, { "epoch": 80.53, "learning_rate": 1.2872396621084465e-05, "loss": 0.0012, "step": 335370 }, { "epoch": 80.53, "learning_rate": 1.2869992463858066e-05, "loss": 0.0011, "step": 335380 }, { "epoch": 80.54, "learning_rate": 1.2867588498000044e-05, "loss": 0.0012, "step": 335390 }, { "epoch": 80.54, "learning_rate": 1.2865184723522761e-05, "loss": 0.0012, "step": 335400 }, { "epoch": 80.54, "learning_rate": 1.286278114043864e-05, "loss": 0.0012, "step": 335410 }, { "epoch": 80.54, "learning_rate": 1.2860377748760044e-05, "loss": 0.0011, "step": 335420 }, { "epoch": 80.55, "learning_rate": 1.2857974548499385e-05, "loss": 0.0012, "step": 335430 }, { "epoch": 80.55, "learning_rate": 1.2855571539669021e-05, "loss": 0.0011, "step": 335440 }, { "epoch": 80.55, "learning_rate": 1.2853168722281367e-05, "loss": 0.0013, "step": 335450 }, { "epoch": 80.55, "learning_rate": 1.2850766096348793e-05, "loss": 0.0013, "step": 335460 }, { "epoch": 80.56, "learning_rate": 1.2848363661883667e-05, "loss": 0.0011, "step": 335470 }, { "epoch": 80.56, "learning_rate": 1.2845961418898394e-05, "loss": 0.0012, "step": 335480 }, { "epoch": 80.56, "learning_rate": 1.2843559367405338e-05, "loss": 0.0014, "step": 335490 }, { "epoch": 80.56, "learning_rate": 1.28411575074169e-05, "loss": 0.0012, "step": 335500 }, { "epoch": 80.56, "learning_rate": 1.2838755838945433e-05, "loss": 0.0012, "step": 335510 }, { "epoch": 80.57, "learning_rate": 1.2836354362003344e-05, "loss": 0.001, "step": 335520 }, { "epoch": 80.57, "learning_rate": 1.2833953076602994e-05, "loss": 0.0012, "step": 335530 }, { "epoch": 80.57, "learning_rate": 1.2831551982756745e-05, "loss": 0.0012, "step": 335540 }, { "epoch": 80.57, "learning_rate": 1.2829151080477004e-05, "loss": 0.0012, "step": 335550 }, { "epoch": 80.58, "learning_rate": 1.2826750369776113e-05, "loss": 0.001, "step": 335560 }, { "epoch": 80.58, "learning_rate": 1.2824349850666479e-05, "loss": 0.0013, "step": 335570 }, { "epoch": 80.58, "learning_rate": 1.2821949523160438e-05, "loss": 0.0012, "step": 335580 }, { "epoch": 80.58, "learning_rate": 1.2819549387270396e-05, "loss": 0.0013, "step": 335590 }, { "epoch": 80.59, "learning_rate": 1.2817149443008691e-05, "loss": 0.0012, "step": 335600 }, { "epoch": 80.59, "learning_rate": 1.281474969038773e-05, "loss": 0.0012, "step": 335610 }, { "epoch": 80.59, "learning_rate": 1.2812350129419837e-05, "loss": 0.0013, "step": 335620 }, { "epoch": 80.59, "learning_rate": 1.2809950760117407e-05, "loss": 0.0013, "step": 335630 }, { "epoch": 80.59, "learning_rate": 1.2807551582492816e-05, "loss": 0.0012, "step": 335640 }, { "epoch": 80.6, "learning_rate": 1.28051525965584e-05, "loss": 0.0013, "step": 335650 }, { "epoch": 80.6, "learning_rate": 1.280275380232655e-05, "loss": 0.0012, "step": 335660 }, { "epoch": 80.6, "learning_rate": 1.2800355199809621e-05, "loss": 0.0014, "step": 335670 }, { "epoch": 80.6, "learning_rate": 1.2797956789019955e-05, "loss": 0.0011, "step": 335680 }, { "epoch": 80.61, "learning_rate": 1.2795558569969951e-05, "loss": 0.0012, "step": 335690 }, { "epoch": 80.61, "learning_rate": 1.2793160542671928e-05, "loss": 0.0012, "step": 335700 }, { "epoch": 80.61, "learning_rate": 1.2790762707138287e-05, "loss": 0.0011, "step": 335710 }, { "epoch": 80.61, "learning_rate": 1.2788365063381346e-05, "loss": 0.0012, "step": 335720 }, { "epoch": 80.61, "learning_rate": 1.2785967611413502e-05, "loss": 0.0012, "step": 335730 }, { "epoch": 80.62, "learning_rate": 1.2783570351247088e-05, "loss": 0.0012, "step": 335740 }, { "epoch": 80.62, "learning_rate": 1.2781173282894449e-05, "loss": 0.0012, "step": 335750 }, { "epoch": 80.62, "learning_rate": 1.2778776406367971e-05, "loss": 0.0014, "step": 335760 }, { "epoch": 80.62, "learning_rate": 1.2776379721679977e-05, "loss": 0.0011, "step": 335770 }, { "epoch": 80.63, "learning_rate": 1.2773983228842846e-05, "loss": 0.0012, "step": 335780 }, { "epoch": 80.63, "learning_rate": 1.2771586927868901e-05, "loss": 0.0013, "step": 335790 }, { "epoch": 80.63, "learning_rate": 1.2769190818770521e-05, "loss": 0.0011, "step": 335800 }, { "epoch": 80.63, "learning_rate": 1.2766794901560042e-05, "loss": 0.0014, "step": 335810 }, { "epoch": 80.64, "learning_rate": 1.2764399176249802e-05, "loss": 0.0014, "step": 335820 }, { "epoch": 80.64, "learning_rate": 1.2762003642852176e-05, "loss": 0.0011, "step": 335830 }, { "epoch": 80.64, "learning_rate": 1.2759608301379477e-05, "loss": 0.0013, "step": 335840 }, { "epoch": 80.64, "learning_rate": 1.2757213151844082e-05, "loss": 0.0013, "step": 335850 }, { "epoch": 80.64, "learning_rate": 1.2754818194258312e-05, "loss": 0.0012, "step": 335860 }, { "epoch": 80.65, "learning_rate": 1.275242342863453e-05, "loss": 0.0011, "step": 335870 }, { "epoch": 80.65, "learning_rate": 1.2750028854985058e-05, "loss": 0.0013, "step": 335880 }, { "epoch": 80.65, "learning_rate": 1.2747634473322263e-05, "loss": 0.0012, "step": 335890 }, { "epoch": 80.65, "learning_rate": 1.2745240283658455e-05, "loss": 0.0011, "step": 335900 }, { "epoch": 80.66, "learning_rate": 1.2742846286006004e-05, "loss": 0.0012, "step": 335910 }, { "epoch": 80.66, "learning_rate": 1.274045248037722e-05, "loss": 0.0012, "step": 335920 }, { "epoch": 80.66, "learning_rate": 1.2738058866784452e-05, "loss": 0.0012, "step": 335930 }, { "epoch": 80.66, "learning_rate": 1.2735665445240063e-05, "loss": 0.0011, "step": 335940 }, { "epoch": 80.66, "learning_rate": 1.2733272215756348e-05, "loss": 0.0011, "step": 335950 }, { "epoch": 80.67, "learning_rate": 1.2730879178345673e-05, "loss": 0.0011, "step": 335960 }, { "epoch": 80.67, "learning_rate": 1.2728486333020356e-05, "loss": 0.0012, "step": 335970 }, { "epoch": 80.67, "learning_rate": 1.2726093679792722e-05, "loss": 0.0011, "step": 335980 }, { "epoch": 80.67, "learning_rate": 1.272370121867512e-05, "loss": 0.0012, "step": 335990 }, { "epoch": 80.68, "learning_rate": 1.2721308949679866e-05, "loss": 0.0013, "step": 336000 }, { "epoch": 80.68, "learning_rate": 1.2718916872819308e-05, "loss": 0.0012, "step": 336010 }, { "epoch": 80.68, "learning_rate": 1.2716524988105754e-05, "loss": 0.0012, "step": 336020 }, { "epoch": 80.68, "learning_rate": 1.2714133295551555e-05, "loss": 0.0012, "step": 336030 }, { "epoch": 80.69, "learning_rate": 1.2711741795169024e-05, "loss": 0.0012, "step": 336040 }, { "epoch": 80.69, "learning_rate": 1.2709350486970472e-05, "loss": 0.0013, "step": 336050 }, { "epoch": 80.69, "learning_rate": 1.2706959370968252e-05, "loss": 0.0017, "step": 336060 }, { "epoch": 80.69, "learning_rate": 1.2704568447174664e-05, "loss": 0.0014, "step": 336070 }, { "epoch": 80.69, "learning_rate": 1.2702177715602054e-05, "loss": 0.0011, "step": 336080 }, { "epoch": 80.7, "learning_rate": 1.2699787176262717e-05, "loss": 0.0016, "step": 336090 }, { "epoch": 80.7, "learning_rate": 1.2697396829169006e-05, "loss": 0.0011, "step": 336100 }, { "epoch": 80.7, "learning_rate": 1.269500667433322e-05, "loss": 0.0012, "step": 336110 }, { "epoch": 80.7, "learning_rate": 1.2692616711767674e-05, "loss": 0.0012, "step": 336120 }, { "epoch": 80.71, "learning_rate": 1.26902269414847e-05, "loss": 0.0015, "step": 336130 }, { "epoch": 80.71, "learning_rate": 1.2687837363496597e-05, "loss": 0.0012, "step": 336140 }, { "epoch": 80.71, "learning_rate": 1.2685447977815706e-05, "loss": 0.0013, "step": 336150 }, { "epoch": 80.71, "learning_rate": 1.2683058784454316e-05, "loss": 0.0012, "step": 336160 }, { "epoch": 80.72, "learning_rate": 1.2680669783424765e-05, "loss": 0.0013, "step": 336170 }, { "epoch": 80.72, "learning_rate": 1.2678280974739353e-05, "loss": 0.0012, "step": 336180 }, { "epoch": 80.72, "learning_rate": 1.2675892358410379e-05, "loss": 0.0015, "step": 336190 }, { "epoch": 80.72, "learning_rate": 1.2673503934450171e-05, "loss": 0.0012, "step": 336200 }, { "epoch": 80.72, "learning_rate": 1.2671115702871046e-05, "loss": 0.0012, "step": 336210 }, { "epoch": 80.73, "learning_rate": 1.2668727663685287e-05, "loss": 0.0012, "step": 336220 }, { "epoch": 80.73, "learning_rate": 1.2666339816905237e-05, "loss": 0.0012, "step": 336230 }, { "epoch": 80.73, "learning_rate": 1.266395216254317e-05, "loss": 0.0012, "step": 336240 }, { "epoch": 80.73, "learning_rate": 1.266156470061141e-05, "loss": 0.0012, "step": 336250 }, { "epoch": 80.74, "learning_rate": 1.2659177431122255e-05, "loss": 0.0012, "step": 336260 }, { "epoch": 80.74, "learning_rate": 1.2656790354088022e-05, "loss": 0.0013, "step": 336270 }, { "epoch": 80.74, "learning_rate": 1.2654403469520986e-05, "loss": 0.0011, "step": 336280 }, { "epoch": 80.74, "learning_rate": 1.2652016777433484e-05, "loss": 0.0012, "step": 336290 }, { "epoch": 80.74, "learning_rate": 1.2649630277837788e-05, "loss": 0.0012, "step": 336300 }, { "epoch": 80.75, "learning_rate": 1.264724397074622e-05, "loss": 0.0011, "step": 336310 }, { "epoch": 80.75, "learning_rate": 1.2644857856171066e-05, "loss": 0.0012, "step": 336320 }, { "epoch": 80.75, "learning_rate": 1.2642471934124616e-05, "loss": 0.0011, "step": 336330 }, { "epoch": 80.75, "learning_rate": 1.2640086204619195e-05, "loss": 0.0013, "step": 336340 }, { "epoch": 80.76, "learning_rate": 1.2637700667667062e-05, "loss": 0.0013, "step": 336350 }, { "epoch": 80.76, "learning_rate": 1.2635315323280555e-05, "loss": 0.0012, "step": 336360 }, { "epoch": 80.76, "learning_rate": 1.2632930171471924e-05, "loss": 0.0012, "step": 336370 }, { "epoch": 80.76, "learning_rate": 1.2630545212253497e-05, "loss": 0.0012, "step": 336380 }, { "epoch": 80.77, "learning_rate": 1.2628160445637555e-05, "loss": 0.0013, "step": 336390 }, { "epoch": 80.77, "learning_rate": 1.2625775871636375e-05, "loss": 0.0011, "step": 336400 }, { "epoch": 80.77, "learning_rate": 1.2623391490262266e-05, "loss": 0.0013, "step": 336410 }, { "epoch": 80.77, "learning_rate": 1.26210073015275e-05, "loss": 0.0011, "step": 336420 }, { "epoch": 80.77, "learning_rate": 1.2618623305444388e-05, "loss": 0.0012, "step": 336430 }, { "epoch": 80.78, "learning_rate": 1.261623950202519e-05, "loss": 0.0012, "step": 336440 }, { "epoch": 80.78, "learning_rate": 1.2613855891282218e-05, "loss": 0.0012, "step": 336450 }, { "epoch": 80.78, "learning_rate": 1.2611472473227748e-05, "loss": 0.0011, "step": 336460 }, { "epoch": 80.78, "learning_rate": 1.2609089247874045e-05, "loss": 0.0012, "step": 336470 }, { "epoch": 80.79, "learning_rate": 1.2606706215233427e-05, "loss": 0.0011, "step": 336480 }, { "epoch": 80.79, "learning_rate": 1.260432337531814e-05, "loss": 0.0012, "step": 336490 }, { "epoch": 80.79, "learning_rate": 1.2601940728140482e-05, "loss": 0.0013, "step": 336500 }, { "epoch": 80.79, "learning_rate": 1.2599558273712748e-05, "loss": 0.0012, "step": 336510 }, { "epoch": 80.8, "learning_rate": 1.259717601204719e-05, "loss": 0.0012, "step": 336520 }, { "epoch": 80.8, "learning_rate": 1.2594793943156119e-05, "loss": 0.0012, "step": 336530 }, { "epoch": 80.8, "learning_rate": 1.2592412067051773e-05, "loss": 0.0012, "step": 336540 }, { "epoch": 80.8, "learning_rate": 1.259003038374646e-05, "loss": 0.0013, "step": 336550 }, { "epoch": 80.8, "learning_rate": 1.2587648893252434e-05, "loss": 0.0011, "step": 336560 }, { "epoch": 80.81, "learning_rate": 1.258526759558199e-05, "loss": 0.0013, "step": 336570 }, { "epoch": 80.81, "learning_rate": 1.2582886490747375e-05, "loss": 0.0012, "step": 336580 }, { "epoch": 80.81, "learning_rate": 1.2580505578760892e-05, "loss": 0.0064, "step": 336590 }, { "epoch": 80.81, "learning_rate": 1.2578124859634793e-05, "loss": 0.0011, "step": 336600 }, { "epoch": 80.82, "learning_rate": 1.2575744333381339e-05, "loss": 0.0011, "step": 336610 }, { "epoch": 80.82, "learning_rate": 1.2573364000012828e-05, "loss": 0.0012, "step": 336620 }, { "epoch": 80.82, "learning_rate": 1.2570983859541497e-05, "loss": 0.0013, "step": 336630 }, { "epoch": 80.82, "learning_rate": 1.2568603911979637e-05, "loss": 0.0011, "step": 336640 }, { "epoch": 80.82, "learning_rate": 1.2566224157339496e-05, "loss": 0.0011, "step": 336650 }, { "epoch": 80.83, "learning_rate": 1.2563844595633362e-05, "loss": 0.0011, "step": 336660 }, { "epoch": 80.83, "learning_rate": 1.256146522687347e-05, "loss": 0.0013, "step": 336670 }, { "epoch": 80.83, "learning_rate": 1.2559086051072116e-05, "loss": 0.0012, "step": 336680 }, { "epoch": 80.83, "learning_rate": 1.2556707068241542e-05, "loss": 0.0012, "step": 336690 }, { "epoch": 80.84, "learning_rate": 1.2554328278394001e-05, "loss": 0.0013, "step": 336700 }, { "epoch": 80.84, "learning_rate": 1.2551949681541781e-05, "loss": 0.0014, "step": 336710 }, { "epoch": 80.84, "learning_rate": 1.2549571277697109e-05, "loss": 0.0012, "step": 336720 }, { "epoch": 80.84, "learning_rate": 1.254719306687227e-05, "loss": 0.0013, "step": 336730 }, { "epoch": 80.85, "learning_rate": 1.25448150490795e-05, "loss": 0.0011, "step": 336740 }, { "epoch": 80.85, "learning_rate": 1.2542437224331082e-05, "loss": 0.0012, "step": 336750 }, { "epoch": 80.85, "learning_rate": 1.2540059592639258e-05, "loss": 0.0011, "step": 336760 }, { "epoch": 80.85, "learning_rate": 1.2537682154016261e-05, "loss": 0.0011, "step": 336770 }, { "epoch": 80.85, "learning_rate": 1.2535304908474377e-05, "loss": 0.0011, "step": 336780 }, { "epoch": 80.86, "learning_rate": 1.2532927856025834e-05, "loss": 0.0012, "step": 336790 }, { "epoch": 80.86, "learning_rate": 1.2530550996682905e-05, "loss": 0.0012, "step": 336800 }, { "epoch": 80.86, "learning_rate": 1.2528174330457821e-05, "loss": 0.0012, "step": 336810 }, { "epoch": 80.86, "learning_rate": 1.252579785736283e-05, "loss": 0.0012, "step": 336820 }, { "epoch": 80.87, "learning_rate": 1.252342157741021e-05, "loss": 0.0011, "step": 336830 }, { "epoch": 80.87, "learning_rate": 1.2521045490612177e-05, "loss": 0.0011, "step": 336840 }, { "epoch": 80.87, "learning_rate": 1.2518669596980997e-05, "loss": 0.001, "step": 336850 }, { "epoch": 80.87, "learning_rate": 1.2516293896528897e-05, "loss": 0.001, "step": 336860 }, { "epoch": 80.88, "learning_rate": 1.2513918389268148e-05, "loss": 0.0011, "step": 336870 }, { "epoch": 80.88, "learning_rate": 1.2511543075210957e-05, "loss": 0.0011, "step": 336880 }, { "epoch": 80.88, "learning_rate": 1.2509167954369605e-05, "loss": 0.0012, "step": 336890 }, { "epoch": 80.88, "learning_rate": 1.2506793026756313e-05, "loss": 0.0012, "step": 336900 }, { "epoch": 80.88, "learning_rate": 1.2504418292383308e-05, "loss": 0.0012, "step": 336910 }, { "epoch": 80.89, "learning_rate": 1.250204375126286e-05, "loss": 0.0011, "step": 336920 }, { "epoch": 80.89, "learning_rate": 1.2499669403407176e-05, "loss": 0.0011, "step": 336930 }, { "epoch": 80.89, "learning_rate": 1.2497295248828523e-05, "loss": 0.0012, "step": 336940 }, { "epoch": 80.89, "learning_rate": 1.2494921287539114e-05, "loss": 0.0012, "step": 336950 }, { "epoch": 80.9, "learning_rate": 1.2492547519551207e-05, "loss": 0.0299, "step": 336960 }, { "epoch": 80.9, "learning_rate": 1.249017394487702e-05, "loss": 0.0012, "step": 336970 }, { "epoch": 80.9, "learning_rate": 1.248780056352878e-05, "loss": 0.0013, "step": 336980 }, { "epoch": 80.9, "learning_rate": 1.2485427375518738e-05, "loss": 0.0011, "step": 336990 }, { "epoch": 80.9, "learning_rate": 1.248305438085911e-05, "loss": 0.0011, "step": 337000 }, { "epoch": 80.91, "learning_rate": 1.2480681579562142e-05, "loss": 0.0011, "step": 337010 }, { "epoch": 80.91, "learning_rate": 1.2478308971640046e-05, "loss": 0.0065, "step": 337020 }, { "epoch": 80.91, "learning_rate": 1.2475936557105067e-05, "loss": 0.0012, "step": 337030 }, { "epoch": 80.91, "learning_rate": 1.2473564335969429e-05, "loss": 0.0062, "step": 337040 }, { "epoch": 80.92, "learning_rate": 1.2471192308245339e-05, "loss": 0.0013, "step": 337050 }, { "epoch": 80.92, "learning_rate": 1.2468820473945047e-05, "loss": 0.0019, "step": 337060 }, { "epoch": 80.92, "learning_rate": 1.2466448833080762e-05, "loss": 0.0011, "step": 337070 }, { "epoch": 80.92, "learning_rate": 1.2464077385664725e-05, "loss": 0.0013, "step": 337080 }, { "epoch": 80.93, "learning_rate": 1.2461706131709128e-05, "loss": 0.0011, "step": 337090 }, { "epoch": 80.93, "learning_rate": 1.245933507122623e-05, "loss": 0.0013, "step": 337100 }, { "epoch": 80.93, "learning_rate": 1.2456964204228217e-05, "loss": 0.0011, "step": 337110 }, { "epoch": 80.93, "learning_rate": 1.2454593530727338e-05, "loss": 0.0012, "step": 337120 }, { "epoch": 80.93, "learning_rate": 1.2452223050735783e-05, "loss": 0.0012, "step": 337130 }, { "epoch": 80.94, "learning_rate": 1.244985276426579e-05, "loss": 0.0011, "step": 337140 }, { "epoch": 80.94, "learning_rate": 1.244748267132958e-05, "loss": 0.0011, "step": 337150 }, { "epoch": 80.94, "learning_rate": 1.2445112771939343e-05, "loss": 0.0012, "step": 337160 }, { "epoch": 80.94, "learning_rate": 1.2442743066107321e-05, "loss": 0.001, "step": 337170 }, { "epoch": 80.95, "learning_rate": 1.244037355384572e-05, "loss": 0.0012, "step": 337180 }, { "epoch": 80.95, "learning_rate": 1.2438004235166734e-05, "loss": 0.001, "step": 337190 }, { "epoch": 80.95, "learning_rate": 1.24356351100826e-05, "loss": 0.0012, "step": 337200 }, { "epoch": 81.0, "learning_rate": 1.2433266178605501e-05, "loss": 0.0013, "step": 337210 }, { "epoch": 81.0, "learning_rate": 1.2430897440747673e-05, "loss": 0.0012, "step": 337220 }, { "epoch": 81.01, "learning_rate": 1.2428528896521308e-05, "loss": 0.0012, "step": 337230 }, { "epoch": 81.01, "learning_rate": 1.2426160545938625e-05, "loss": 0.0011, "step": 337240 }, { "epoch": 81.01, "learning_rate": 1.2423792389011835e-05, "loss": 0.0012, "step": 337250 }, { "epoch": 81.01, "learning_rate": 1.2421424425753108e-05, "loss": 0.0013, "step": 337260 }, { "epoch": 81.02, "learning_rate": 1.2419056656174693e-05, "loss": 0.0011, "step": 337270 }, { "epoch": 81.02, "learning_rate": 1.2416689080288763e-05, "loss": 0.001, "step": 337280 }, { "epoch": 81.02, "learning_rate": 1.241432169810754e-05, "loss": 0.0011, "step": 337290 }, { "epoch": 81.02, "learning_rate": 1.2411954509643204e-05, "loss": 0.0012, "step": 337300 }, { "epoch": 81.02, "learning_rate": 1.2409587514907983e-05, "loss": 0.0011, "step": 337310 }, { "epoch": 81.03, "learning_rate": 1.2407220713914064e-05, "loss": 0.0011, "step": 337320 }, { "epoch": 81.03, "learning_rate": 1.240485410667363e-05, "loss": 0.0011, "step": 337330 }, { "epoch": 81.03, "learning_rate": 1.2402487693198906e-05, "loss": 0.0011, "step": 337340 }, { "epoch": 81.03, "learning_rate": 1.2400121473502057e-05, "loss": 0.0011, "step": 337350 }, { "epoch": 81.04, "learning_rate": 1.2397755447595317e-05, "loss": 0.0012, "step": 337360 }, { "epoch": 81.04, "learning_rate": 1.2395389615490838e-05, "loss": 0.0013, "step": 337370 }, { "epoch": 81.04, "learning_rate": 1.2393023977200852e-05, "loss": 0.0012, "step": 337380 }, { "epoch": 81.04, "learning_rate": 1.2390658532737527e-05, "loss": 0.0011, "step": 337390 }, { "epoch": 81.05, "learning_rate": 1.2388293282113067e-05, "loss": 0.0012, "step": 337400 }, { "epoch": 81.05, "learning_rate": 1.2385928225339649e-05, "loss": 0.0013, "step": 337410 }, { "epoch": 81.05, "learning_rate": 1.2383563362429484e-05, "loss": 0.0011, "step": 337420 }, { "epoch": 81.05, "learning_rate": 1.2381198693394736e-05, "loss": 0.0011, "step": 337430 }, { "epoch": 81.05, "learning_rate": 1.2378834218247614e-05, "loss": 0.0012, "step": 337440 }, { "epoch": 81.06, "learning_rate": 1.2376469937000285e-05, "loss": 0.0011, "step": 337450 }, { "epoch": 81.06, "learning_rate": 1.237410584966494e-05, "loss": 0.0011, "step": 337460 }, { "epoch": 81.06, "learning_rate": 1.2371741956253784e-05, "loss": 0.0012, "step": 337470 }, { "epoch": 81.06, "learning_rate": 1.2369378256778985e-05, "loss": 0.0012, "step": 337480 }, { "epoch": 81.07, "learning_rate": 1.2367014751252715e-05, "loss": 0.0011, "step": 337490 }, { "epoch": 81.07, "learning_rate": 1.2364651439687174e-05, "loss": 0.0011, "step": 337500 }, { "epoch": 81.07, "learning_rate": 1.2362288322094518e-05, "loss": 0.0011, "step": 337510 }, { "epoch": 81.07, "learning_rate": 1.235992539848696e-05, "loss": 0.0012, "step": 337520 }, { "epoch": 81.07, "learning_rate": 1.235756266887665e-05, "loss": 0.001, "step": 337530 }, { "epoch": 81.08, "learning_rate": 1.235520013327579e-05, "loss": 0.001, "step": 337540 }, { "epoch": 81.08, "learning_rate": 1.2352837791696542e-05, "loss": 0.0011, "step": 337550 }, { "epoch": 81.08, "learning_rate": 1.2350475644151067e-05, "loss": 0.0013, "step": 337560 }, { "epoch": 81.08, "learning_rate": 1.234811369065157e-05, "loss": 0.0011, "step": 337570 }, { "epoch": 81.09, "learning_rate": 1.2345751931210193e-05, "loss": 0.0012, "step": 337580 }, { "epoch": 81.09, "learning_rate": 1.2343390365839141e-05, "loss": 0.0011, "step": 337590 }, { "epoch": 81.09, "learning_rate": 1.2341028994550558e-05, "loss": 0.001, "step": 337600 }, { "epoch": 81.09, "learning_rate": 1.2338667817356642e-05, "loss": 0.0011, "step": 337610 }, { "epoch": 81.1, "learning_rate": 1.2336306834269545e-05, "loss": 0.0017, "step": 337620 }, { "epoch": 81.1, "learning_rate": 1.233394604530142e-05, "loss": 0.0011, "step": 337630 }, { "epoch": 81.1, "learning_rate": 1.2331585450464472e-05, "loss": 0.0011, "step": 337640 }, { "epoch": 81.1, "learning_rate": 1.2329225049770826e-05, "loss": 0.0011, "step": 337650 }, { "epoch": 81.1, "learning_rate": 1.2326864843232689e-05, "loss": 0.0011, "step": 337660 }, { "epoch": 81.11, "learning_rate": 1.2324504830862188e-05, "loss": 0.0011, "step": 337670 }, { "epoch": 81.11, "learning_rate": 1.2322145012671521e-05, "loss": 0.0012, "step": 337680 }, { "epoch": 81.11, "learning_rate": 1.2319785388672834e-05, "loss": 0.001, "step": 337690 }, { "epoch": 81.11, "learning_rate": 1.2317425958878271e-05, "loss": 0.0013, "step": 337700 }, { "epoch": 81.12, "learning_rate": 1.2315066723300011e-05, "loss": 0.0011, "step": 337710 }, { "epoch": 81.12, "learning_rate": 1.2312707681950225e-05, "loss": 0.0012, "step": 337720 }, { "epoch": 81.12, "learning_rate": 1.2310348834841046e-05, "loss": 0.0012, "step": 337730 }, { "epoch": 81.12, "learning_rate": 1.2307990181984658e-05, "loss": 0.0012, "step": 337740 }, { "epoch": 81.12, "learning_rate": 1.2305631723393185e-05, "loss": 0.0011, "step": 337750 }, { "epoch": 81.13, "learning_rate": 1.2303273459078824e-05, "loss": 0.001, "step": 337760 }, { "epoch": 81.13, "learning_rate": 1.2300915389053685e-05, "loss": 0.0011, "step": 337770 }, { "epoch": 81.13, "learning_rate": 1.229855751332996e-05, "loss": 0.0013, "step": 337780 }, { "epoch": 81.13, "learning_rate": 1.2296199831919769e-05, "loss": 0.0011, "step": 337790 }, { "epoch": 81.14, "learning_rate": 1.22938423448353e-05, "loss": 0.0012, "step": 337800 }, { "epoch": 81.14, "learning_rate": 1.2291485052088664e-05, "loss": 0.0011, "step": 337810 }, { "epoch": 81.14, "learning_rate": 1.2289127953692042e-05, "loss": 0.0011, "step": 337820 }, { "epoch": 81.14, "learning_rate": 1.2286771049657569e-05, "loss": 0.0011, "step": 337830 }, { "epoch": 81.15, "learning_rate": 1.228441433999738e-05, "loss": 0.0013, "step": 337840 }, { "epoch": 81.15, "learning_rate": 1.2282057824723652e-05, "loss": 0.0011, "step": 337850 }, { "epoch": 81.15, "learning_rate": 1.2279701503848495e-05, "loss": 0.0013, "step": 337860 }, { "epoch": 81.15, "learning_rate": 1.2277345377384091e-05, "loss": 0.0011, "step": 337870 }, { "epoch": 81.15, "learning_rate": 1.2274989445342544e-05, "loss": 0.0011, "step": 337880 }, { "epoch": 81.16, "learning_rate": 1.2272633707736036e-05, "loss": 0.0012, "step": 337890 }, { "epoch": 81.16, "learning_rate": 1.2270278164576687e-05, "loss": 0.0012, "step": 337900 }, { "epoch": 81.16, "learning_rate": 1.2267922815876626e-05, "loss": 0.0011, "step": 337910 }, { "epoch": 81.16, "learning_rate": 1.226556766164802e-05, "loss": 0.0012, "step": 337920 }, { "epoch": 81.17, "learning_rate": 1.2263212701902982e-05, "loss": 0.001, "step": 337930 }, { "epoch": 81.17, "learning_rate": 1.2260857936653669e-05, "loss": 0.0012, "step": 337940 }, { "epoch": 81.17, "learning_rate": 1.22585033659122e-05, "loss": 0.0012, "step": 337950 }, { "epoch": 81.17, "learning_rate": 1.2256148989690735e-05, "loss": 0.0012, "step": 337960 }, { "epoch": 81.18, "learning_rate": 1.2253794808001396e-05, "loss": 0.0011, "step": 337970 }, { "epoch": 81.18, "learning_rate": 1.225144082085629e-05, "loss": 0.0012, "step": 337980 }, { "epoch": 81.18, "learning_rate": 1.2249087028267597e-05, "loss": 0.0012, "step": 337990 }, { "epoch": 81.18, "learning_rate": 1.2246733430247409e-05, "loss": 0.0011, "step": 338000 }, { "epoch": 81.18, "learning_rate": 1.2244380026807884e-05, "loss": 0.0012, "step": 338010 }, { "epoch": 81.19, "learning_rate": 1.2242026817961128e-05, "loss": 0.0012, "step": 338020 }, { "epoch": 81.19, "learning_rate": 1.223967380371928e-05, "loss": 0.0011, "step": 338030 }, { "epoch": 81.19, "learning_rate": 1.2237320984094481e-05, "loss": 0.0011, "step": 338040 }, { "epoch": 81.19, "learning_rate": 1.2234968359098837e-05, "loss": 0.0013, "step": 338050 }, { "epoch": 81.2, "learning_rate": 1.223261592874449e-05, "loss": 0.0012, "step": 338060 }, { "epoch": 81.2, "learning_rate": 1.2230263693043548e-05, "loss": 0.0014, "step": 338070 }, { "epoch": 81.2, "learning_rate": 1.222791165200815e-05, "loss": 0.0013, "step": 338080 }, { "epoch": 81.2, "learning_rate": 1.22255598056504e-05, "loss": 0.0011, "step": 338090 }, { "epoch": 81.2, "learning_rate": 1.2223208153982447e-05, "loss": 0.0014, "step": 338100 }, { "epoch": 81.21, "learning_rate": 1.2220856697016392e-05, "loss": 0.0012, "step": 338110 }, { "epoch": 81.21, "learning_rate": 1.2218505434764343e-05, "loss": 0.0013, "step": 338120 }, { "epoch": 81.21, "learning_rate": 1.2216154367238452e-05, "loss": 0.0011, "step": 338130 }, { "epoch": 81.21, "learning_rate": 1.2213803494450799e-05, "loss": 0.0011, "step": 338140 }, { "epoch": 81.22, "learning_rate": 1.2211452816413531e-05, "loss": 0.0011, "step": 338150 }, { "epoch": 81.22, "learning_rate": 1.220910233313874e-05, "loss": 0.0011, "step": 338160 }, { "epoch": 81.22, "learning_rate": 1.2206752044638564e-05, "loss": 0.0012, "step": 338170 }, { "epoch": 81.22, "learning_rate": 1.2204401950925103e-05, "loss": 0.001, "step": 338180 }, { "epoch": 81.23, "learning_rate": 1.220205205201046e-05, "loss": 0.0013, "step": 338190 }, { "epoch": 81.23, "learning_rate": 1.2199702347906767e-05, "loss": 0.0011, "step": 338200 }, { "epoch": 81.23, "learning_rate": 1.2197352838626108e-05, "loss": 0.001, "step": 338210 }, { "epoch": 81.23, "learning_rate": 1.2195003524180626e-05, "loss": 0.0011, "step": 338220 }, { "epoch": 81.23, "learning_rate": 1.2192654404582399e-05, "loss": 0.0011, "step": 338230 }, { "epoch": 81.24, "learning_rate": 1.2190305479843561e-05, "loss": 0.0012, "step": 338240 }, { "epoch": 81.24, "learning_rate": 1.2187956749976204e-05, "loss": 0.0013, "step": 338250 }, { "epoch": 81.24, "learning_rate": 1.2185608214992416e-05, "loss": 0.0012, "step": 338260 }, { "epoch": 81.24, "learning_rate": 1.218325987490434e-05, "loss": 0.0011, "step": 338270 }, { "epoch": 81.25, "learning_rate": 1.2180911729724043e-05, "loss": 0.0012, "step": 338280 }, { "epoch": 81.25, "learning_rate": 1.2178563779463653e-05, "loss": 0.0011, "step": 338290 }, { "epoch": 81.25, "learning_rate": 1.2176216024135251e-05, "loss": 0.0012, "step": 338300 }, { "epoch": 81.25, "learning_rate": 1.217386846375096e-05, "loss": 0.0011, "step": 338310 }, { "epoch": 81.26, "learning_rate": 1.2171521098322852e-05, "loss": 0.0011, "step": 338320 }, { "epoch": 81.26, "learning_rate": 1.2169173927863043e-05, "loss": 0.0011, "step": 338330 }, { "epoch": 81.26, "learning_rate": 1.2166826952383642e-05, "loss": 0.0011, "step": 338340 }, { "epoch": 81.26, "learning_rate": 1.2164480171896714e-05, "loss": 0.0012, "step": 338350 }, { "epoch": 81.26, "learning_rate": 1.2162133586414388e-05, "loss": 0.0011, "step": 338360 }, { "epoch": 81.27, "learning_rate": 1.215978719594873e-05, "loss": 0.0011, "step": 338370 }, { "epoch": 81.27, "learning_rate": 1.2157441000511854e-05, "loss": 0.0012, "step": 338380 }, { "epoch": 81.27, "learning_rate": 1.2155095000115835e-05, "loss": 0.0012, "step": 338390 }, { "epoch": 81.27, "learning_rate": 1.2152749194772784e-05, "loss": 0.0011, "step": 338400 }, { "epoch": 81.28, "learning_rate": 1.215040358449478e-05, "loss": 0.0011, "step": 338410 }, { "epoch": 81.28, "learning_rate": 1.2148058169293897e-05, "loss": 0.0011, "step": 338420 }, { "epoch": 81.28, "learning_rate": 1.2145712949182253e-05, "loss": 0.0012, "step": 338430 }, { "epoch": 81.28, "learning_rate": 1.2143367924171905e-05, "loss": 0.0011, "step": 338440 }, { "epoch": 81.28, "learning_rate": 1.2141023094274973e-05, "loss": 0.0011, "step": 338450 }, { "epoch": 81.29, "learning_rate": 1.2138678459503505e-05, "loss": 0.0012, "step": 338460 }, { "epoch": 81.29, "learning_rate": 1.2136334019869627e-05, "loss": 0.0012, "step": 338470 }, { "epoch": 81.29, "learning_rate": 1.2133989775385396e-05, "loss": 0.001, "step": 338480 }, { "epoch": 81.29, "learning_rate": 1.2131645726062879e-05, "loss": 0.0012, "step": 338490 }, { "epoch": 81.3, "learning_rate": 1.21293018719142e-05, "loss": 0.0012, "step": 338500 }, { "epoch": 81.3, "learning_rate": 1.2126958212951396e-05, "loss": 0.0011, "step": 338510 }, { "epoch": 81.3, "learning_rate": 1.212461474918658e-05, "loss": 0.0011, "step": 338520 }, { "epoch": 81.3, "learning_rate": 1.2122271480631803e-05, "loss": 0.0011, "step": 338530 }, { "epoch": 81.31, "learning_rate": 1.211992840729917e-05, "loss": 0.0012, "step": 338540 }, { "epoch": 81.31, "learning_rate": 1.2117585529200742e-05, "loss": 0.001, "step": 338550 }, { "epoch": 81.31, "learning_rate": 1.2115242846348579e-05, "loss": 0.0011, "step": 338560 }, { "epoch": 81.31, "learning_rate": 1.2112900358754786e-05, "loss": 0.001, "step": 338570 }, { "epoch": 81.31, "learning_rate": 1.211055806643141e-05, "loss": 0.0012, "step": 338580 }, { "epoch": 81.32, "learning_rate": 1.2108215969390546e-05, "loss": 0.0011, "step": 338590 }, { "epoch": 81.32, "learning_rate": 1.210587406764424e-05, "loss": 0.001, "step": 338600 }, { "epoch": 81.32, "learning_rate": 1.210353236120459e-05, "loss": 0.0034, "step": 338610 }, { "epoch": 81.32, "learning_rate": 1.2101190850083638e-05, "loss": 0.0013, "step": 338620 }, { "epoch": 81.33, "learning_rate": 1.2098849534293478e-05, "loss": 0.0027, "step": 338630 }, { "epoch": 81.33, "learning_rate": 1.2096508413846153e-05, "loss": 0.0012, "step": 338640 }, { "epoch": 81.33, "learning_rate": 1.2094167488753733e-05, "loss": 0.0029, "step": 338650 }, { "epoch": 81.33, "learning_rate": 1.2091826759028312e-05, "loss": 0.0013, "step": 338660 }, { "epoch": 81.34, "learning_rate": 1.2089486224681917e-05, "loss": 0.0012, "step": 338670 }, { "epoch": 81.34, "learning_rate": 1.2087145885726637e-05, "loss": 0.0012, "step": 338680 }, { "epoch": 81.34, "learning_rate": 1.2084805742174526e-05, "loss": 0.001, "step": 338690 }, { "epoch": 81.34, "learning_rate": 1.2082465794037634e-05, "loss": 0.0014, "step": 338700 }, { "epoch": 81.34, "learning_rate": 1.2080126041328038e-05, "loss": 0.0012, "step": 338710 }, { "epoch": 81.35, "learning_rate": 1.2077786484057779e-05, "loss": 0.001, "step": 338720 }, { "epoch": 81.35, "learning_rate": 1.2075447122238936e-05, "loss": 0.0011, "step": 338730 }, { "epoch": 81.35, "learning_rate": 1.2073107955883544e-05, "loss": 0.0013, "step": 338740 }, { "epoch": 81.35, "learning_rate": 1.2070768985003688e-05, "loss": 0.0012, "step": 338750 }, { "epoch": 81.36, "learning_rate": 1.2068430209611403e-05, "loss": 0.0012, "step": 338760 }, { "epoch": 81.36, "learning_rate": 1.2066091629718728e-05, "loss": 0.0012, "step": 338770 }, { "epoch": 81.36, "learning_rate": 1.206375324533775e-05, "loss": 0.0011, "step": 338780 }, { "epoch": 81.36, "learning_rate": 1.2061415056480491e-05, "loss": 0.0012, "step": 338790 }, { "epoch": 81.36, "learning_rate": 1.2059077063159035e-05, "loss": 0.0012, "step": 338800 }, { "epoch": 81.37, "learning_rate": 1.2056739265385391e-05, "loss": 0.0011, "step": 338810 }, { "epoch": 81.37, "learning_rate": 1.205440166317165e-05, "loss": 0.0012, "step": 338820 }, { "epoch": 81.37, "learning_rate": 1.2052064256529838e-05, "loss": 0.0013, "step": 338830 }, { "epoch": 81.37, "learning_rate": 1.2049727045471986e-05, "loss": 0.0011, "step": 338840 }, { "epoch": 81.38, "learning_rate": 1.2047390030010174e-05, "loss": 0.0012, "step": 338850 }, { "epoch": 81.38, "learning_rate": 1.204505321015642e-05, "loss": 0.0011, "step": 338860 }, { "epoch": 81.38, "learning_rate": 1.2042716585922793e-05, "loss": 0.0012, "step": 338870 }, { "epoch": 81.38, "learning_rate": 1.2040380157321307e-05, "loss": 0.0011, "step": 338880 }, { "epoch": 81.39, "learning_rate": 1.2038043924364035e-05, "loss": 0.0011, "step": 338890 }, { "epoch": 81.39, "learning_rate": 1.203570788706298e-05, "loss": 0.0012, "step": 338900 }, { "epoch": 81.39, "learning_rate": 1.2033372045430225e-05, "loss": 0.0011, "step": 338910 }, { "epoch": 81.39, "learning_rate": 1.2031036399477774e-05, "loss": 0.0011, "step": 338920 }, { "epoch": 81.39, "learning_rate": 1.2028700949217691e-05, "loss": 0.0011, "step": 338930 }, { "epoch": 81.4, "learning_rate": 1.2026365694661984e-05, "loss": 0.0012, "step": 338940 }, { "epoch": 81.4, "learning_rate": 1.2024030635822725e-05, "loss": 0.0012, "step": 338950 }, { "epoch": 81.4, "learning_rate": 1.202169577271191e-05, "loss": 0.0011, "step": 338960 }, { "epoch": 81.4, "learning_rate": 1.2019361105341609e-05, "loss": 0.0012, "step": 338970 }, { "epoch": 81.41, "learning_rate": 1.2017026633723827e-05, "loss": 0.0011, "step": 338980 }, { "epoch": 81.41, "learning_rate": 1.2014692357870616e-05, "loss": 0.0011, "step": 338990 }, { "epoch": 81.41, "learning_rate": 1.201235827779399e-05, "loss": 0.0011, "step": 339000 }, { "epoch": 81.41, "learning_rate": 1.2010024393505997e-05, "loss": 0.0011, "step": 339010 }, { "epoch": 81.42, "learning_rate": 1.2007690705018642e-05, "loss": 0.0011, "step": 339020 }, { "epoch": 81.42, "learning_rate": 1.2005357212343981e-05, "loss": 0.0012, "step": 339030 }, { "epoch": 81.42, "learning_rate": 1.2003023915494027e-05, "loss": 0.0012, "step": 339040 }, { "epoch": 81.42, "learning_rate": 1.2000690814480791e-05, "loss": 0.0012, "step": 339050 }, { "epoch": 81.42, "learning_rate": 1.1998357909316326e-05, "loss": 0.0012, "step": 339060 }, { "epoch": 81.43, "learning_rate": 1.1996025200012628e-05, "loss": 0.0011, "step": 339070 }, { "epoch": 81.43, "learning_rate": 1.1993692686581747e-05, "loss": 0.001, "step": 339080 }, { "epoch": 81.43, "learning_rate": 1.1991360369035681e-05, "loss": 0.0011, "step": 339090 }, { "epoch": 81.43, "learning_rate": 1.1989028247386475e-05, "loss": 0.0012, "step": 339100 }, { "epoch": 81.44, "learning_rate": 1.1986696321646119e-05, "loss": 0.0011, "step": 339110 }, { "epoch": 81.44, "learning_rate": 1.1984364591826658e-05, "loss": 0.0011, "step": 339120 }, { "epoch": 81.44, "learning_rate": 1.1982033057940106e-05, "loss": 0.0011, "step": 339130 }, { "epoch": 81.44, "learning_rate": 1.1979701719998453e-05, "loss": 0.0012, "step": 339140 }, { "epoch": 81.44, "learning_rate": 1.1977370578013758e-05, "loss": 0.0011, "step": 339150 }, { "epoch": 81.45, "learning_rate": 1.1975039631997992e-05, "loss": 0.0013, "step": 339160 }, { "epoch": 81.45, "learning_rate": 1.1972708881963207e-05, "loss": 0.0013, "step": 339170 }, { "epoch": 81.45, "learning_rate": 1.1970378327921383e-05, "loss": 0.0011, "step": 339180 }, { "epoch": 81.45, "learning_rate": 1.1968047969884561e-05, "loss": 0.0011, "step": 339190 }, { "epoch": 81.46, "learning_rate": 1.196571780786474e-05, "loss": 0.0034, "step": 339200 }, { "epoch": 81.46, "learning_rate": 1.1963387841873908e-05, "loss": 0.0012, "step": 339210 }, { "epoch": 81.46, "learning_rate": 1.1961058071924097e-05, "loss": 0.0012, "step": 339220 }, { "epoch": 81.46, "learning_rate": 1.1958728498027322e-05, "loss": 0.0013, "step": 339230 }, { "epoch": 81.47, "learning_rate": 1.1956399120195566e-05, "loss": 0.0012, "step": 339240 }, { "epoch": 81.47, "learning_rate": 1.195406993844086e-05, "loss": 0.0012, "step": 339250 }, { "epoch": 81.47, "learning_rate": 1.195174095277518e-05, "loss": 0.0015, "step": 339260 }, { "epoch": 81.47, "learning_rate": 1.1949412163210566e-05, "loss": 0.0011, "step": 339270 }, { "epoch": 81.47, "learning_rate": 1.1947083569758982e-05, "loss": 0.0012, "step": 339280 }, { "epoch": 81.48, "learning_rate": 1.1944755172432459e-05, "loss": 0.0013, "step": 339290 }, { "epoch": 81.48, "learning_rate": 1.1942426971242976e-05, "loss": 0.0012, "step": 339300 }, { "epoch": 81.48, "learning_rate": 1.194009896620255e-05, "loss": 0.0012, "step": 339310 }, { "epoch": 81.48, "learning_rate": 1.1937771157323163e-05, "loss": 0.0012, "step": 339320 }, { "epoch": 81.49, "learning_rate": 1.1935443544616837e-05, "loss": 0.0012, "step": 339330 }, { "epoch": 81.49, "learning_rate": 1.193311612809555e-05, "loss": 0.001, "step": 339340 }, { "epoch": 81.49, "learning_rate": 1.193078890777129e-05, "loss": 0.0012, "step": 339350 }, { "epoch": 81.49, "learning_rate": 1.1928461883656073e-05, "loss": 0.0009, "step": 339360 }, { "epoch": 81.5, "learning_rate": 1.1926135055761866e-05, "loss": 0.0012, "step": 339370 }, { "epoch": 81.5, "learning_rate": 1.1923808424100697e-05, "loss": 0.0013, "step": 339380 }, { "epoch": 81.5, "learning_rate": 1.1921481988684519e-05, "loss": 0.0011, "step": 339390 }, { "epoch": 81.5, "learning_rate": 1.1919155749525357e-05, "loss": 0.0012, "step": 339400 }, { "epoch": 81.5, "learning_rate": 1.191682970663518e-05, "loss": 0.0013, "step": 339410 }, { "epoch": 81.51, "learning_rate": 1.1914503860025971e-05, "loss": 0.001, "step": 339420 }, { "epoch": 81.51, "learning_rate": 1.1912178209709746e-05, "loss": 0.001, "step": 339430 }, { "epoch": 81.51, "learning_rate": 1.1909852755698453e-05, "loss": 0.0011, "step": 339440 }, { "epoch": 81.51, "learning_rate": 1.1907527498004112e-05, "loss": 0.0012, "step": 339450 }, { "epoch": 81.52, "learning_rate": 1.1905202436638679e-05, "loss": 0.0012, "step": 339460 }, { "epoch": 81.52, "learning_rate": 1.1902877571614163e-05, "loss": 0.0024, "step": 339470 }, { "epoch": 81.52, "learning_rate": 1.190055290294254e-05, "loss": 0.0012, "step": 339480 }, { "epoch": 81.52, "learning_rate": 1.1898228430635766e-05, "loss": 0.0012, "step": 339490 }, { "epoch": 81.52, "learning_rate": 1.1895904154705862e-05, "loss": 0.0011, "step": 339500 }, { "epoch": 81.53, "learning_rate": 1.1893580075164768e-05, "loss": 0.0011, "step": 339510 }, { "epoch": 81.53, "learning_rate": 1.189125619202449e-05, "loss": 0.0012, "step": 339520 }, { "epoch": 81.53, "learning_rate": 1.188893250529699e-05, "loss": 0.0011, "step": 339530 }, { "epoch": 81.53, "learning_rate": 1.1886609014994249e-05, "loss": 0.0011, "step": 339540 }, { "epoch": 81.54, "learning_rate": 1.1884285721128252e-05, "loss": 0.0012, "step": 339550 }, { "epoch": 81.54, "learning_rate": 1.1881962623710957e-05, "loss": 0.0012, "step": 339560 }, { "epoch": 81.54, "learning_rate": 1.187963972275436e-05, "loss": 0.0013, "step": 339570 }, { "epoch": 81.54, "learning_rate": 1.1877317018270401e-05, "loss": 0.0012, "step": 339580 }, { "epoch": 81.55, "learning_rate": 1.1874994510271081e-05, "loss": 0.0012, "step": 339590 }, { "epoch": 81.55, "learning_rate": 1.1872672198768347e-05, "loss": 0.0011, "step": 339600 }, { "epoch": 81.55, "learning_rate": 1.1870350083774195e-05, "loss": 0.0012, "step": 339610 }, { "epoch": 81.55, "learning_rate": 1.1868028165300576e-05, "loss": 0.0012, "step": 339620 }, { "epoch": 81.55, "learning_rate": 1.1865706443359442e-05, "loss": 0.0012, "step": 339630 }, { "epoch": 81.56, "learning_rate": 1.1863384917962794e-05, "loss": 0.0011, "step": 339640 }, { "epoch": 81.56, "learning_rate": 1.1861063589122561e-05, "loss": 0.0012, "step": 339650 }, { "epoch": 81.56, "learning_rate": 1.185874245685074e-05, "loss": 0.0011, "step": 339660 }, { "epoch": 81.56, "learning_rate": 1.1856421521159267e-05, "loss": 0.0011, "step": 339670 }, { "epoch": 81.57, "learning_rate": 1.1854100782060129e-05, "loss": 0.0023, "step": 339680 }, { "epoch": 81.57, "learning_rate": 1.1851780239565274e-05, "loss": 0.0011, "step": 339690 }, { "epoch": 81.57, "learning_rate": 1.1849459893686648e-05, "loss": 0.0012, "step": 339700 }, { "epoch": 81.57, "learning_rate": 1.1847139744436241e-05, "loss": 0.0012, "step": 339710 }, { "epoch": 81.58, "learning_rate": 1.1844819791825978e-05, "loss": 0.0036, "step": 339720 }, { "epoch": 81.58, "learning_rate": 1.1842500035867848e-05, "loss": 0.0011, "step": 339730 }, { "epoch": 81.58, "learning_rate": 1.1840180476573781e-05, "loss": 0.0011, "step": 339740 }, { "epoch": 81.58, "learning_rate": 1.1837861113955751e-05, "loss": 0.0013, "step": 339750 }, { "epoch": 81.58, "learning_rate": 1.1835541948025708e-05, "loss": 0.001, "step": 339760 }, { "epoch": 81.59, "learning_rate": 1.1833222978795582e-05, "loss": 0.0013, "step": 339770 }, { "epoch": 81.59, "learning_rate": 1.1830904206277366e-05, "loss": 0.0012, "step": 339780 }, { "epoch": 81.59, "learning_rate": 1.1828585630482968e-05, "loss": 0.001, "step": 339790 }, { "epoch": 81.59, "learning_rate": 1.1826267251424372e-05, "loss": 0.0012, "step": 339800 }, { "epoch": 81.6, "learning_rate": 1.1823949069113505e-05, "loss": 0.0012, "step": 339810 }, { "epoch": 81.6, "learning_rate": 1.1821631083562335e-05, "loss": 0.0012, "step": 339820 }, { "epoch": 81.6, "learning_rate": 1.181931329478278e-05, "loss": 0.0011, "step": 339830 }, { "epoch": 81.6, "learning_rate": 1.181699570278681e-05, "loss": 0.0013, "step": 339840 }, { "epoch": 81.6, "learning_rate": 1.1814678307586375e-05, "loss": 0.0013, "step": 339850 }, { "epoch": 81.61, "learning_rate": 1.1812361109193388e-05, "loss": 0.0034, "step": 339860 }, { "epoch": 81.61, "learning_rate": 1.1810044107619833e-05, "loss": 0.0012, "step": 339870 }, { "epoch": 81.61, "learning_rate": 1.1807727302877609e-05, "loss": 0.0012, "step": 339880 }, { "epoch": 81.61, "learning_rate": 1.1805410694978696e-05, "loss": 0.0012, "step": 339890 }, { "epoch": 81.62, "learning_rate": 1.1803094283935001e-05, "loss": 0.0018, "step": 339900 }, { "epoch": 81.62, "learning_rate": 1.180077806975849e-05, "loss": 0.0012, "step": 339910 }, { "epoch": 81.62, "learning_rate": 1.179846205246109e-05, "loss": 0.0012, "step": 339920 }, { "epoch": 81.62, "learning_rate": 1.1796146232054723e-05, "loss": 0.0012, "step": 339930 }, { "epoch": 81.63, "learning_rate": 1.1793830608551349e-05, "loss": 0.0013, "step": 339940 }, { "epoch": 81.63, "learning_rate": 1.1791515181962875e-05, "loss": 0.0015, "step": 339950 }, { "epoch": 81.63, "learning_rate": 1.1789199952301266e-05, "loss": 0.0011, "step": 339960 }, { "epoch": 81.63, "learning_rate": 1.1786884919578428e-05, "loss": 0.0011, "step": 339970 }, { "epoch": 81.63, "learning_rate": 1.1784570083806318e-05, "loss": 0.0011, "step": 339980 }, { "epoch": 81.64, "learning_rate": 1.1782255444996854e-05, "loss": 0.0012, "step": 339990 }, { "epoch": 81.64, "learning_rate": 1.1779941003161955e-05, "loss": 0.0011, "step": 340000 }, { "epoch": 81.64, "learning_rate": 1.1777626758313564e-05, "loss": 0.0011, "step": 340010 }, { "epoch": 81.64, "learning_rate": 1.17753127104636e-05, "loss": 0.0012, "step": 340020 }, { "epoch": 81.65, "learning_rate": 1.1772998859624e-05, "loss": 0.0011, "step": 340030 }, { "epoch": 81.65, "learning_rate": 1.177068520580667e-05, "loss": 0.0012, "step": 340040 }, { "epoch": 81.65, "learning_rate": 1.1768371749023566e-05, "loss": 0.0012, "step": 340050 }, { "epoch": 81.65, "learning_rate": 1.176605848928659e-05, "loss": 0.0011, "step": 340060 }, { "epoch": 81.66, "learning_rate": 1.1763745426607658e-05, "loss": 0.0011, "step": 340070 }, { "epoch": 81.66, "learning_rate": 1.1761432560998715e-05, "loss": 0.0012, "step": 340080 }, { "epoch": 81.66, "learning_rate": 1.1759119892471655e-05, "loss": 0.0036, "step": 340090 }, { "epoch": 81.66, "learning_rate": 1.1756807421038418e-05, "loss": 0.0012, "step": 340100 }, { "epoch": 81.66, "learning_rate": 1.175449514671091e-05, "loss": 0.0012, "step": 340110 }, { "epoch": 81.67, "learning_rate": 1.175218306950106e-05, "loss": 0.0011, "step": 340120 }, { "epoch": 81.67, "learning_rate": 1.174987118942077e-05, "loss": 0.0012, "step": 340130 }, { "epoch": 81.67, "learning_rate": 1.1747559506481976e-05, "loss": 0.0012, "step": 340140 }, { "epoch": 81.67, "learning_rate": 1.1745248020696564e-05, "loss": 0.0013, "step": 340150 }, { "epoch": 81.68, "learning_rate": 1.1742936732076466e-05, "loss": 0.0013, "step": 340160 }, { "epoch": 81.68, "learning_rate": 1.17406256406336e-05, "loss": 0.0012, "step": 340170 }, { "epoch": 81.68, "learning_rate": 1.1738314746379864e-05, "loss": 0.0012, "step": 340180 }, { "epoch": 81.68, "learning_rate": 1.1736004049327182e-05, "loss": 0.0013, "step": 340190 }, { "epoch": 81.68, "learning_rate": 1.1733693549487457e-05, "loss": 0.0014, "step": 340200 }, { "epoch": 81.69, "learning_rate": 1.173138324687258e-05, "loss": 0.0012, "step": 340210 }, { "epoch": 81.69, "learning_rate": 1.172907314149449e-05, "loss": 0.0011, "step": 340220 }, { "epoch": 81.69, "learning_rate": 1.1726763233365063e-05, "loss": 0.0011, "step": 340230 }, { "epoch": 81.69, "learning_rate": 1.1724453522496232e-05, "loss": 0.0012, "step": 340240 }, { "epoch": 81.7, "learning_rate": 1.1722144008899871e-05, "loss": 0.0013, "step": 340250 }, { "epoch": 81.7, "learning_rate": 1.1719834692587911e-05, "loss": 0.0013, "step": 340260 }, { "epoch": 81.7, "learning_rate": 1.1717525573572247e-05, "loss": 0.0012, "step": 340270 }, { "epoch": 81.7, "learning_rate": 1.1715216651864763e-05, "loss": 0.0013, "step": 340280 }, { "epoch": 81.71, "learning_rate": 1.1712907927477384e-05, "loss": 0.0012, "step": 340290 }, { "epoch": 81.71, "learning_rate": 1.1710599400421985e-05, "loss": 0.001, "step": 340300 }, { "epoch": 81.71, "learning_rate": 1.1708291070710491e-05, "loss": 0.0012, "step": 340310 }, { "epoch": 81.71, "learning_rate": 1.170598293835477e-05, "loss": 0.0012, "step": 340320 }, { "epoch": 81.71, "learning_rate": 1.1703675003366749e-05, "loss": 0.0016, "step": 340330 }, { "epoch": 81.72, "learning_rate": 1.1701367265758306e-05, "loss": 0.0012, "step": 340340 }, { "epoch": 81.72, "learning_rate": 1.1699059725541323e-05, "loss": 0.0012, "step": 340350 }, { "epoch": 81.72, "learning_rate": 1.1696752382727722e-05, "loss": 0.0018, "step": 340360 }, { "epoch": 81.72, "learning_rate": 1.169444523732936e-05, "loss": 0.0011, "step": 340370 }, { "epoch": 81.73, "learning_rate": 1.1692138289358163e-05, "loss": 0.0012, "step": 340380 }, { "epoch": 81.73, "learning_rate": 1.168983153882599e-05, "loss": 0.0012, "step": 340390 }, { "epoch": 81.73, "learning_rate": 1.1687524985744764e-05, "loss": 0.0011, "step": 340400 }, { "epoch": 81.73, "learning_rate": 1.1685218630126355e-05, "loss": 0.001, "step": 340410 }, { "epoch": 81.74, "learning_rate": 1.1682912471982632e-05, "loss": 0.0012, "step": 340420 }, { "epoch": 81.74, "learning_rate": 1.1680606511325499e-05, "loss": 0.0012, "step": 340430 }, { "epoch": 81.74, "learning_rate": 1.1678300748166853e-05, "loss": 0.0011, "step": 340440 }, { "epoch": 81.74, "learning_rate": 1.1675995182518557e-05, "loss": 0.001, "step": 340450 }, { "epoch": 81.74, "learning_rate": 1.1673689814392509e-05, "loss": 0.0011, "step": 340460 }, { "epoch": 81.75, "learning_rate": 1.1671384643800576e-05, "loss": 0.0011, "step": 340470 }, { "epoch": 81.75, "learning_rate": 1.1669079670754656e-05, "loss": 0.0013, "step": 340480 }, { "epoch": 81.75, "learning_rate": 1.1666774895266609e-05, "loss": 0.0012, "step": 340490 }, { "epoch": 81.75, "learning_rate": 1.1664470317348337e-05, "loss": 0.0011, "step": 340500 }, { "epoch": 81.76, "learning_rate": 1.1662165937011693e-05, "loss": 0.0012, "step": 340510 }, { "epoch": 81.76, "learning_rate": 1.1659861754268575e-05, "loss": 0.0012, "step": 340520 }, { "epoch": 81.76, "learning_rate": 1.1657557769130845e-05, "loss": 0.0036, "step": 340530 }, { "epoch": 81.76, "learning_rate": 1.1655253981610392e-05, "loss": 0.0012, "step": 340540 }, { "epoch": 81.76, "learning_rate": 1.165295039171908e-05, "loss": 0.0013, "step": 340550 }, { "epoch": 81.77, "learning_rate": 1.1650646999468766e-05, "loss": 0.0012, "step": 340560 }, { "epoch": 81.77, "learning_rate": 1.1648343804871353e-05, "loss": 0.0014, "step": 340570 }, { "epoch": 81.77, "learning_rate": 1.1646040807938685e-05, "loss": 0.0011, "step": 340580 }, { "epoch": 81.77, "learning_rate": 1.164373800868266e-05, "loss": 0.0011, "step": 340590 }, { "epoch": 81.78, "learning_rate": 1.164143540711511e-05, "loss": 0.0012, "step": 340600 }, { "epoch": 81.78, "learning_rate": 1.1639133003247938e-05, "loss": 0.001, "step": 340610 }, { "epoch": 81.78, "learning_rate": 1.1636830797092997e-05, "loss": 0.0012, "step": 340620 }, { "epoch": 81.78, "learning_rate": 1.1634528788662135e-05, "loss": 0.0013, "step": 340630 }, { "epoch": 81.79, "learning_rate": 1.1632226977967247e-05, "loss": 0.0013, "step": 340640 }, { "epoch": 81.79, "learning_rate": 1.1629925365020167e-05, "loss": 0.0011, "step": 340650 }, { "epoch": 81.79, "learning_rate": 1.1627623949832789e-05, "loss": 0.0011, "step": 340660 }, { "epoch": 81.79, "learning_rate": 1.1625322732416944e-05, "loss": 0.0011, "step": 340670 }, { "epoch": 81.79, "learning_rate": 1.1623021712784515e-05, "loss": 0.0013, "step": 340680 }, { "epoch": 81.8, "learning_rate": 1.1620720890947345e-05, "loss": 0.0013, "step": 340690 }, { "epoch": 81.8, "learning_rate": 1.1618420266917312e-05, "loss": 0.0011, "step": 340700 }, { "epoch": 81.8, "learning_rate": 1.1616119840706262e-05, "loss": 0.0135, "step": 340710 }, { "epoch": 81.8, "learning_rate": 1.1613819612326032e-05, "loss": 0.0011, "step": 340720 }, { "epoch": 81.81, "learning_rate": 1.1611519581788504e-05, "loss": 0.0013, "step": 340730 }, { "epoch": 81.81, "learning_rate": 1.1609219749105538e-05, "loss": 0.0011, "step": 340740 }, { "epoch": 81.81, "learning_rate": 1.1606920114288955e-05, "loss": 0.0011, "step": 340750 }, { "epoch": 81.81, "learning_rate": 1.1604620677350647e-05, "loss": 0.0012, "step": 340760 }, { "epoch": 81.82, "learning_rate": 1.1602321438302426e-05, "loss": 0.0011, "step": 340770 }, { "epoch": 81.82, "learning_rate": 1.1600022397156179e-05, "loss": 0.0012, "step": 340780 }, { "epoch": 81.82, "learning_rate": 1.1597723553923723e-05, "loss": 0.001, "step": 340790 }, { "epoch": 81.82, "learning_rate": 1.1595424908616931e-05, "loss": 0.0012, "step": 340800 }, { "epoch": 81.82, "learning_rate": 1.1593126461247633e-05, "loss": 0.0012, "step": 340810 }, { "epoch": 81.83, "learning_rate": 1.1590828211827693e-05, "loss": 0.0011, "step": 340820 }, { "epoch": 81.83, "learning_rate": 1.1588530160368927e-05, "loss": 0.0012, "step": 340830 }, { "epoch": 81.83, "learning_rate": 1.1586232306883215e-05, "loss": 0.0012, "step": 340840 }, { "epoch": 81.83, "learning_rate": 1.1583934651382383e-05, "loss": 0.0009, "step": 340850 }, { "epoch": 81.84, "learning_rate": 1.1581637193878258e-05, "loss": 0.0011, "step": 340860 }, { "epoch": 81.84, "learning_rate": 1.157933993438271e-05, "loss": 0.0025, "step": 340870 }, { "epoch": 81.84, "learning_rate": 1.1577042872907557e-05, "loss": 0.0011, "step": 340880 }, { "epoch": 81.84, "learning_rate": 1.1574746009464655e-05, "loss": 0.0108, "step": 340890 }, { "epoch": 81.84, "learning_rate": 1.1572449344065817e-05, "loss": 0.0011, "step": 340900 }, { "epoch": 81.85, "learning_rate": 1.1570152876722912e-05, "loss": 0.0012, "step": 340910 }, { "epoch": 81.85, "learning_rate": 1.1567856607447763e-05, "loss": 0.0013, "step": 340920 }, { "epoch": 81.85, "learning_rate": 1.1565560536252185e-05, "loss": 0.0011, "step": 340930 }, { "epoch": 81.85, "learning_rate": 1.1563264663148044e-05, "loss": 0.0011, "step": 340940 }, { "epoch": 81.86, "learning_rate": 1.1560968988147148e-05, "loss": 0.001, "step": 340950 }, { "epoch": 81.86, "learning_rate": 1.1558673511261348e-05, "loss": 0.0012, "step": 340960 }, { "epoch": 81.86, "learning_rate": 1.1556378232502451e-05, "loss": 0.0011, "step": 340970 }, { "epoch": 81.86, "learning_rate": 1.1554083151882322e-05, "loss": 0.0012, "step": 340980 }, { "epoch": 81.87, "learning_rate": 1.1551788269412767e-05, "loss": 0.0014, "step": 340990 }, { "epoch": 81.87, "learning_rate": 1.1549493585105602e-05, "loss": 0.0011, "step": 341000 }, { "epoch": 81.87, "learning_rate": 1.1547199098972684e-05, "loss": 0.0013, "step": 341010 }, { "epoch": 81.87, "learning_rate": 1.1544904811025808e-05, "loss": 0.0012, "step": 341020 }, { "epoch": 81.87, "learning_rate": 1.1542610721276826e-05, "loss": 0.0012, "step": 341030 }, { "epoch": 81.88, "learning_rate": 1.1540316829737541e-05, "loss": 0.0011, "step": 341040 }, { "epoch": 81.88, "learning_rate": 1.1538023136419779e-05, "loss": 0.0095, "step": 341050 }, { "epoch": 81.88, "learning_rate": 1.1535729641335385e-05, "loss": 0.0013, "step": 341060 }, { "epoch": 81.88, "learning_rate": 1.1533436344496145e-05, "loss": 0.0011, "step": 341070 }, { "epoch": 81.89, "learning_rate": 1.1531143245913912e-05, "loss": 0.0012, "step": 341080 }, { "epoch": 81.89, "learning_rate": 1.1528850345600473e-05, "loss": 0.0012, "step": 341090 }, { "epoch": 81.89, "learning_rate": 1.1526557643567676e-05, "loss": 0.0012, "step": 341100 }, { "epoch": 81.89, "learning_rate": 1.1524265139827306e-05, "loss": 0.0012, "step": 341110 }, { "epoch": 81.9, "learning_rate": 1.1521972834391215e-05, "loss": 0.0011, "step": 341120 }, { "epoch": 81.9, "learning_rate": 1.1519680727271192e-05, "loss": 0.0011, "step": 341130 }, { "epoch": 81.9, "learning_rate": 1.1517388818479041e-05, "loss": 0.001, "step": 341140 }, { "epoch": 81.9, "learning_rate": 1.1515097108026607e-05, "loss": 0.0012, "step": 341150 }, { "epoch": 81.9, "learning_rate": 1.1512805595925669e-05, "loss": 0.0012, "step": 341160 }, { "epoch": 81.91, "learning_rate": 1.1510514282188067e-05, "loss": 0.0011, "step": 341170 }, { "epoch": 81.91, "learning_rate": 1.1508223166825582e-05, "loss": 0.0011, "step": 341180 }, { "epoch": 81.91, "learning_rate": 1.1505932249850054e-05, "loss": 0.0011, "step": 341190 }, { "epoch": 81.91, "learning_rate": 1.1503641531273267e-05, "loss": 0.0013, "step": 341200 }, { "epoch": 81.92, "learning_rate": 1.1501351011107025e-05, "loss": 0.0011, "step": 341210 }, { "epoch": 81.92, "learning_rate": 1.149906068936315e-05, "loss": 0.0011, "step": 341220 }, { "epoch": 81.92, "learning_rate": 1.1496770566053427e-05, "loss": 0.001, "step": 341230 }, { "epoch": 81.92, "learning_rate": 1.1494480641189687e-05, "loss": 0.0011, "step": 341240 }, { "epoch": 81.92, "learning_rate": 1.1492190914783702e-05, "loss": 0.0011, "step": 341250 }, { "epoch": 81.93, "learning_rate": 1.1489901386847297e-05, "loss": 0.0011, "step": 341260 }, { "epoch": 81.93, "learning_rate": 1.148761205739226e-05, "loss": 0.0013, "step": 341270 }, { "epoch": 81.93, "learning_rate": 1.148532292643038e-05, "loss": 0.0012, "step": 341280 }, { "epoch": 81.93, "learning_rate": 1.1483033993973486e-05, "loss": 0.0011, "step": 341290 }, { "epoch": 81.94, "learning_rate": 1.1480745260033338e-05, "loss": 0.0012, "step": 341300 }, { "epoch": 81.94, "learning_rate": 1.1478456724621767e-05, "loss": 0.0012, "step": 341310 }, { "epoch": 81.94, "learning_rate": 1.1476168387750536e-05, "loss": 0.0011, "step": 341320 }, { "epoch": 81.94, "learning_rate": 1.1473880249431473e-05, "loss": 0.0012, "step": 341330 }, { "epoch": 81.95, "learning_rate": 1.1471592309676338e-05, "loss": 0.0012, "step": 341340 }, { "epoch": 81.95, "learning_rate": 1.1469304568496952e-05, "loss": 0.002, "step": 341350 }, { "epoch": 81.95, "learning_rate": 1.1467017025905075e-05, "loss": 0.0013, "step": 341360 }, { "epoch": 82.0, "learning_rate": 1.1464729681912517e-05, "loss": 0.0012, "step": 341370 }, { "epoch": 82.0, "learning_rate": 1.1462442536531076e-05, "loss": 0.0011, "step": 341380 }, { "epoch": 82.01, "learning_rate": 1.146015558977252e-05, "loss": 0.0013, "step": 341390 }, { "epoch": 82.01, "learning_rate": 1.1457868841648655e-05, "loss": 0.001, "step": 341400 }, { "epoch": 82.01, "learning_rate": 1.1455582292171257e-05, "loss": 0.0011, "step": 341410 }, { "epoch": 82.01, "learning_rate": 1.1453295941352094e-05, "loss": 0.001, "step": 341420 }, { "epoch": 82.01, "learning_rate": 1.1451009789202983e-05, "loss": 0.0011, "step": 341430 }, { "epoch": 82.02, "learning_rate": 1.144872383573567e-05, "loss": 0.0011, "step": 341440 }, { "epoch": 82.02, "learning_rate": 1.1446438080961974e-05, "loss": 0.0011, "step": 341450 }, { "epoch": 82.02, "learning_rate": 1.1444152524893647e-05, "loss": 0.001, "step": 341460 }, { "epoch": 82.02, "learning_rate": 1.1441867167542491e-05, "loss": 0.0012, "step": 341470 }, { "epoch": 82.03, "learning_rate": 1.1439582008920257e-05, "loss": 0.0011, "step": 341480 }, { "epoch": 82.03, "learning_rate": 1.1437297049038759e-05, "loss": 0.0012, "step": 341490 }, { "epoch": 82.03, "learning_rate": 1.1435012287909752e-05, "loss": 0.0013, "step": 341500 }, { "epoch": 82.03, "learning_rate": 1.1432727725545e-05, "loss": 0.0013, "step": 341510 }, { "epoch": 82.04, "learning_rate": 1.1430443361956312e-05, "loss": 0.001, "step": 341520 }, { "epoch": 82.04, "learning_rate": 1.1428159197155419e-05, "loss": 0.0016, "step": 341530 }, { "epoch": 82.04, "learning_rate": 1.1425875231154131e-05, "loss": 0.0011, "step": 341540 }, { "epoch": 82.04, "learning_rate": 1.1423591463964195e-05, "loss": 0.0012, "step": 341550 }, { "epoch": 82.04, "learning_rate": 1.14213078955974e-05, "loss": 0.0011, "step": 341560 }, { "epoch": 82.05, "learning_rate": 1.1419024526065508e-05, "loss": 0.0009, "step": 341570 }, { "epoch": 82.05, "learning_rate": 1.1416741355380273e-05, "loss": 0.0012, "step": 341580 }, { "epoch": 82.05, "learning_rate": 1.1414458383553489e-05, "loss": 0.0012, "step": 341590 }, { "epoch": 82.05, "learning_rate": 1.1412175610596897e-05, "loss": 0.0011, "step": 341600 }, { "epoch": 82.06, "learning_rate": 1.1409893036522285e-05, "loss": 0.001, "step": 341610 }, { "epoch": 82.06, "learning_rate": 1.1407610661341395e-05, "loss": 0.0011, "step": 341620 }, { "epoch": 82.06, "learning_rate": 1.1405328485066018e-05, "loss": 0.001, "step": 341630 }, { "epoch": 82.06, "learning_rate": 1.1403046507707883e-05, "loss": 0.0011, "step": 341640 }, { "epoch": 82.06, "learning_rate": 1.1400764729278785e-05, "loss": 0.0011, "step": 341650 }, { "epoch": 82.07, "learning_rate": 1.1398483149790456e-05, "loss": 0.001, "step": 341660 }, { "epoch": 82.07, "learning_rate": 1.139620176925466e-05, "loss": 0.0011, "step": 341670 }, { "epoch": 82.07, "learning_rate": 1.1393920587683188e-05, "loss": 0.0011, "step": 341680 }, { "epoch": 82.07, "learning_rate": 1.139163960508775e-05, "loss": 0.0013, "step": 341690 }, { "epoch": 82.08, "learning_rate": 1.138935882148014e-05, "loss": 0.001, "step": 341700 }, { "epoch": 82.08, "learning_rate": 1.1387078236872096e-05, "loss": 0.0012, "step": 341710 }, { "epoch": 82.08, "learning_rate": 1.1384797851275364e-05, "loss": 0.001, "step": 341720 }, { "epoch": 82.08, "learning_rate": 1.1382517664701714e-05, "loss": 0.0013, "step": 341730 }, { "epoch": 82.09, "learning_rate": 1.1380237677162881e-05, "loss": 0.0011, "step": 341740 }, { "epoch": 82.09, "learning_rate": 1.1377957888670643e-05, "loss": 0.0011, "step": 341750 }, { "epoch": 82.09, "learning_rate": 1.1375678299236715e-05, "loss": 0.0011, "step": 341760 }, { "epoch": 82.09, "learning_rate": 1.1373398908872873e-05, "loss": 0.0011, "step": 341770 }, { "epoch": 82.09, "learning_rate": 1.1371119717590862e-05, "loss": 0.001, "step": 341780 }, { "epoch": 82.1, "learning_rate": 1.1368840725402407e-05, "loss": 0.0013, "step": 341790 }, { "epoch": 82.1, "learning_rate": 1.1366561932319286e-05, "loss": 0.0011, "step": 341800 }, { "epoch": 82.1, "learning_rate": 1.1364283338353215e-05, "loss": 0.0012, "step": 341810 }, { "epoch": 82.1, "learning_rate": 1.1362004943515958e-05, "loss": 0.0072, "step": 341820 }, { "epoch": 82.11, "learning_rate": 1.1359726747819243e-05, "loss": 0.0012, "step": 341830 }, { "epoch": 82.11, "learning_rate": 1.135744875127483e-05, "loss": 0.0012, "step": 341840 }, { "epoch": 82.11, "learning_rate": 1.135517095389445e-05, "loss": 0.0012, "step": 341850 }, { "epoch": 82.11, "learning_rate": 1.1352893355689826e-05, "loss": 0.001, "step": 341860 }, { "epoch": 82.12, "learning_rate": 1.1350615956672728e-05, "loss": 0.0011, "step": 341870 }, { "epoch": 82.12, "learning_rate": 1.1348338756854865e-05, "loss": 0.0011, "step": 341880 }, { "epoch": 82.12, "learning_rate": 1.1346061756248005e-05, "loss": 0.0011, "step": 341890 }, { "epoch": 82.12, "learning_rate": 1.1343784954863846e-05, "loss": 0.0011, "step": 341900 }, { "epoch": 82.12, "learning_rate": 1.1341508352714158e-05, "loss": 0.0011, "step": 341910 }, { "epoch": 82.13, "learning_rate": 1.1339231949810657e-05, "loss": 0.001, "step": 341920 }, { "epoch": 82.13, "learning_rate": 1.1336955746165067e-05, "loss": 0.0012, "step": 341930 }, { "epoch": 82.13, "learning_rate": 1.1334679741789133e-05, "loss": 0.0011, "step": 341940 }, { "epoch": 82.13, "learning_rate": 1.1332403936694592e-05, "loss": 0.0011, "step": 341950 }, { "epoch": 82.14, "learning_rate": 1.1330128330893153e-05, "loss": 0.0011, "step": 341960 }, { "epoch": 82.14, "learning_rate": 1.1327852924396565e-05, "loss": 0.0011, "step": 341970 }, { "epoch": 82.14, "learning_rate": 1.1325577717216535e-05, "loss": 0.0011, "step": 341980 }, { "epoch": 82.14, "learning_rate": 1.1323302709364819e-05, "loss": 0.0012, "step": 341990 }, { "epoch": 82.14, "learning_rate": 1.1321027900853103e-05, "loss": 0.001, "step": 342000 }, { "epoch": 82.15, "learning_rate": 1.1318753291693152e-05, "loss": 0.0011, "step": 342010 }, { "epoch": 82.15, "learning_rate": 1.1316478881896653e-05, "loss": 0.0012, "step": 342020 }, { "epoch": 82.15, "learning_rate": 1.1314204671475359e-05, "loss": 0.0011, "step": 342030 }, { "epoch": 82.15, "learning_rate": 1.1311930660440967e-05, "loss": 0.0011, "step": 342040 }, { "epoch": 82.16, "learning_rate": 1.1309656848805217e-05, "loss": 0.001, "step": 342050 }, { "epoch": 82.16, "learning_rate": 1.1307383236579822e-05, "loss": 0.0009, "step": 342060 }, { "epoch": 82.16, "learning_rate": 1.1305109823776483e-05, "loss": 0.0011, "step": 342070 }, { "epoch": 82.16, "learning_rate": 1.1302836610406941e-05, "loss": 0.0011, "step": 342080 }, { "epoch": 82.17, "learning_rate": 1.1300563596482894e-05, "loss": 0.0011, "step": 342090 }, { "epoch": 82.17, "learning_rate": 1.129829078201608e-05, "loss": 0.001, "step": 342100 }, { "epoch": 82.17, "learning_rate": 1.129601816701818e-05, "loss": 0.001, "step": 342110 }, { "epoch": 82.17, "learning_rate": 1.1293745751500944e-05, "loss": 0.0011, "step": 342120 }, { "epoch": 82.17, "learning_rate": 1.1291473535476065e-05, "loss": 0.0012, "step": 342130 }, { "epoch": 82.18, "learning_rate": 1.128920151895524e-05, "loss": 0.0013, "step": 342140 }, { "epoch": 82.18, "learning_rate": 1.1286929701950211e-05, "loss": 0.0012, "step": 342150 }, { "epoch": 82.18, "learning_rate": 1.1284658084472655e-05, "loss": 0.001, "step": 342160 }, { "epoch": 82.18, "learning_rate": 1.1282386666534306e-05, "loss": 0.0013, "step": 342170 }, { "epoch": 82.19, "learning_rate": 1.1280115448146843e-05, "loss": 0.0011, "step": 342180 }, { "epoch": 82.19, "learning_rate": 1.127784442932201e-05, "loss": 0.0012, "step": 342190 }, { "epoch": 82.19, "learning_rate": 1.1275573610071488e-05, "loss": 0.0011, "step": 342200 }, { "epoch": 82.19, "learning_rate": 1.127330299040697e-05, "loss": 0.0013, "step": 342210 }, { "epoch": 82.2, "learning_rate": 1.1271032570340184e-05, "loss": 0.0011, "step": 342220 }, { "epoch": 82.2, "learning_rate": 1.1268762349882806e-05, "loss": 0.001, "step": 342230 }, { "epoch": 82.2, "learning_rate": 1.1266492329046551e-05, "loss": 0.001, "step": 342240 }, { "epoch": 82.2, "learning_rate": 1.126422250784313e-05, "loss": 0.0014, "step": 342250 }, { "epoch": 82.2, "learning_rate": 1.1261952886284215e-05, "loss": 0.0015, "step": 342260 }, { "epoch": 82.21, "learning_rate": 1.1259683464381538e-05, "loss": 0.0012, "step": 342270 }, { "epoch": 82.21, "learning_rate": 1.1257414242146763e-05, "loss": 0.0011, "step": 342280 }, { "epoch": 82.21, "learning_rate": 1.1255145219591606e-05, "loss": 0.0011, "step": 342290 }, { "epoch": 82.21, "learning_rate": 1.1252876396727747e-05, "loss": 0.0011, "step": 342300 }, { "epoch": 82.22, "learning_rate": 1.1250607773566901e-05, "loss": 0.0012, "step": 342310 }, { "epoch": 82.22, "learning_rate": 1.1248339350120729e-05, "loss": 0.001, "step": 342320 }, { "epoch": 82.22, "learning_rate": 1.1246071126400953e-05, "loss": 0.0011, "step": 342330 }, { "epoch": 82.22, "learning_rate": 1.1243803102419237e-05, "loss": 0.0011, "step": 342340 }, { "epoch": 82.22, "learning_rate": 1.1241535278187299e-05, "loss": 0.001, "step": 342350 }, { "epoch": 82.23, "learning_rate": 1.1239267653716812e-05, "loss": 0.001, "step": 342360 }, { "epoch": 82.23, "learning_rate": 1.1237000229019451e-05, "loss": 0.0012, "step": 342370 }, { "epoch": 82.23, "learning_rate": 1.1234733004106929e-05, "loss": 0.0011, "step": 342380 }, { "epoch": 82.23, "learning_rate": 1.1232465978990898e-05, "loss": 0.0011, "step": 342390 }, { "epoch": 82.24, "learning_rate": 1.123019915368308e-05, "loss": 0.0012, "step": 342400 }, { "epoch": 82.24, "learning_rate": 1.1227932528195123e-05, "loss": 0.001, "step": 342410 }, { "epoch": 82.24, "learning_rate": 1.1225666102538746e-05, "loss": 0.0011, "step": 342420 }, { "epoch": 82.24, "learning_rate": 1.1223399876725605e-05, "loss": 0.0011, "step": 342430 }, { "epoch": 82.25, "learning_rate": 1.1221133850767368e-05, "loss": 0.0011, "step": 342440 }, { "epoch": 82.25, "learning_rate": 1.121886802467575e-05, "loss": 0.0011, "step": 342450 }, { "epoch": 82.25, "learning_rate": 1.1216602398462395e-05, "loss": 0.0011, "step": 342460 }, { "epoch": 82.25, "learning_rate": 1.1214336972139011e-05, "loss": 0.001, "step": 342470 }, { "epoch": 82.25, "learning_rate": 1.121207174571724e-05, "loss": 0.0011, "step": 342480 }, { "epoch": 82.26, "learning_rate": 1.1209806719208793e-05, "loss": 0.0011, "step": 342490 }, { "epoch": 82.26, "learning_rate": 1.1207541892625329e-05, "loss": 0.001, "step": 342500 }, { "epoch": 82.26, "learning_rate": 1.1205277265978498e-05, "loss": 0.0011, "step": 342510 }, { "epoch": 82.26, "learning_rate": 1.1203012839280008e-05, "loss": 0.001, "step": 342520 }, { "epoch": 82.27, "learning_rate": 1.12007486125415e-05, "loss": 0.0011, "step": 342530 }, { "epoch": 82.27, "learning_rate": 1.1198484585774677e-05, "loss": 0.0011, "step": 342540 }, { "epoch": 82.27, "learning_rate": 1.1196220758991171e-05, "loss": 0.0011, "step": 342550 }, { "epoch": 82.27, "learning_rate": 1.1193957132202665e-05, "loss": 0.0011, "step": 342560 }, { "epoch": 82.28, "learning_rate": 1.1191693705420847e-05, "loss": 0.001, "step": 342570 }, { "epoch": 82.28, "learning_rate": 1.1189430478657348e-05, "loss": 0.001, "step": 342580 }, { "epoch": 82.28, "learning_rate": 1.1187167451923863e-05, "loss": 0.0012, "step": 342590 }, { "epoch": 82.28, "learning_rate": 1.1184904625232028e-05, "loss": 0.001, "step": 342600 }, { "epoch": 82.28, "learning_rate": 1.1182641998593529e-05, "loss": 0.001, "step": 342610 }, { "epoch": 82.29, "learning_rate": 1.1180379572020011e-05, "loss": 0.0011, "step": 342620 }, { "epoch": 82.29, "learning_rate": 1.1178117345523147e-05, "loss": 0.001, "step": 342630 }, { "epoch": 82.29, "learning_rate": 1.1175855319114597e-05, "loss": 0.0031, "step": 342640 }, { "epoch": 82.29, "learning_rate": 1.1173593492805995e-05, "loss": 0.0012, "step": 342650 }, { "epoch": 82.3, "learning_rate": 1.1171331866609036e-05, "loss": 0.001, "step": 342660 }, { "epoch": 82.3, "learning_rate": 1.116907044053534e-05, "loss": 0.0011, "step": 342670 }, { "epoch": 82.3, "learning_rate": 1.1166809214596591e-05, "loss": 0.0011, "step": 342680 }, { "epoch": 82.3, "learning_rate": 1.1164548188804419e-05, "loss": 0.001, "step": 342690 }, { "epoch": 82.3, "learning_rate": 1.116228736317051e-05, "loss": 0.0011, "step": 342700 }, { "epoch": 82.31, "learning_rate": 1.1160026737706492e-05, "loss": 0.0012, "step": 342710 }, { "epoch": 82.31, "learning_rate": 1.1157766312424007e-05, "loss": 0.0073, "step": 342720 }, { "epoch": 82.31, "learning_rate": 1.1155506087334733e-05, "loss": 0.0012, "step": 342730 }, { "epoch": 82.31, "learning_rate": 1.115324606245029e-05, "loss": 0.0011, "step": 342740 }, { "epoch": 82.32, "learning_rate": 1.1150986237782357e-05, "loss": 0.001, "step": 342750 }, { "epoch": 82.32, "learning_rate": 1.1148726613342547e-05, "loss": 0.001, "step": 342760 }, { "epoch": 82.32, "learning_rate": 1.1146467189142546e-05, "loss": 0.0012, "step": 342770 }, { "epoch": 82.32, "learning_rate": 1.1144207965193976e-05, "loss": 0.0013, "step": 342780 }, { "epoch": 82.33, "learning_rate": 1.1141948941508468e-05, "loss": 0.0011, "step": 342790 }, { "epoch": 82.33, "learning_rate": 1.113969011809769e-05, "loss": 0.0011, "step": 342800 }, { "epoch": 82.33, "learning_rate": 1.1137431494973267e-05, "loss": 0.0011, "step": 342810 }, { "epoch": 82.33, "learning_rate": 1.1135173072146859e-05, "loss": 0.0011, "step": 342820 }, { "epoch": 82.33, "learning_rate": 1.1132914849630077e-05, "loss": 0.0011, "step": 342830 }, { "epoch": 82.34, "learning_rate": 1.1130656827434593e-05, "loss": 0.0011, "step": 342840 }, { "epoch": 82.34, "learning_rate": 1.1128399005572015e-05, "loss": 0.001, "step": 342850 }, { "epoch": 82.34, "learning_rate": 1.1126141384054007e-05, "loss": 0.001, "step": 342860 }, { "epoch": 82.34, "learning_rate": 1.1123883962892173e-05, "loss": 0.001, "step": 342870 }, { "epoch": 82.35, "learning_rate": 1.1121626742098174e-05, "loss": 0.001, "step": 342880 }, { "epoch": 82.35, "learning_rate": 1.1119369721683642e-05, "loss": 0.0012, "step": 342890 }, { "epoch": 82.35, "learning_rate": 1.1117112901660193e-05, "loss": 0.0011, "step": 342900 }, { "epoch": 82.35, "learning_rate": 1.1114856282039482e-05, "loss": 0.0011, "step": 342910 }, { "epoch": 82.36, "learning_rate": 1.1112599862833129e-05, "loss": 0.0013, "step": 342920 }, { "epoch": 82.36, "learning_rate": 1.1110343644052745e-05, "loss": 0.0011, "step": 342930 }, { "epoch": 82.36, "learning_rate": 1.110808762570999e-05, "loss": 0.0012, "step": 342940 }, { "epoch": 82.36, "learning_rate": 1.1105831807816463e-05, "loss": 0.0011, "step": 342950 }, { "epoch": 82.36, "learning_rate": 1.1103576190383819e-05, "loss": 0.001, "step": 342960 }, { "epoch": 82.37, "learning_rate": 1.1101320773423651e-05, "loss": 0.001, "step": 342970 }, { "epoch": 82.37, "learning_rate": 1.1099065556947618e-05, "loss": 0.001, "step": 342980 }, { "epoch": 82.37, "learning_rate": 1.1096810540967323e-05, "loss": 0.001, "step": 342990 }, { "epoch": 82.37, "learning_rate": 1.1094555725494382e-05, "loss": 0.0012, "step": 343000 }, { "epoch": 82.38, "learning_rate": 1.1092301110540437e-05, "loss": 0.0011, "step": 343010 }, { "epoch": 82.38, "learning_rate": 1.1090046696117085e-05, "loss": 0.0012, "step": 343020 }, { "epoch": 82.38, "learning_rate": 1.108779248223597e-05, "loss": 0.001, "step": 343030 }, { "epoch": 82.38, "learning_rate": 1.1085538468908684e-05, "loss": 0.0011, "step": 343040 }, { "epoch": 82.38, "learning_rate": 1.1083284656146875e-05, "loss": 0.0011, "step": 343050 }, { "epoch": 82.39, "learning_rate": 1.1081031043962137e-05, "loss": 0.001, "step": 343060 }, { "epoch": 82.39, "learning_rate": 1.1078777632366077e-05, "loss": 0.0011, "step": 343070 }, { "epoch": 82.39, "learning_rate": 1.1076524421370338e-05, "loss": 0.0011, "step": 343080 }, { "epoch": 82.39, "learning_rate": 1.1074271410986509e-05, "loss": 0.0011, "step": 343090 }, { "epoch": 82.4, "learning_rate": 1.1072018601226215e-05, "loss": 0.0011, "step": 343100 }, { "epoch": 82.4, "learning_rate": 1.1069765992101056e-05, "loss": 0.001, "step": 343110 }, { "epoch": 82.4, "learning_rate": 1.1067513583622657e-05, "loss": 0.001, "step": 343120 }, { "epoch": 82.4, "learning_rate": 1.106526137580261e-05, "loss": 0.0012, "step": 343130 }, { "epoch": 82.41, "learning_rate": 1.1063009368652539e-05, "loss": 0.0011, "step": 343140 }, { "epoch": 82.41, "learning_rate": 1.1060757562184032e-05, "loss": 0.0011, "step": 343150 }, { "epoch": 82.41, "learning_rate": 1.105850595640872e-05, "loss": 0.0011, "step": 343160 }, { "epoch": 82.41, "learning_rate": 1.1056254551338179e-05, "loss": 0.0012, "step": 343170 }, { "epoch": 82.41, "learning_rate": 1.1054003346984043e-05, "loss": 0.001, "step": 343180 }, { "epoch": 82.42, "learning_rate": 1.1051752343357885e-05, "loss": 0.0011, "step": 343190 }, { "epoch": 82.42, "learning_rate": 1.1049501540471325e-05, "loss": 0.0014, "step": 343200 }, { "epoch": 82.42, "learning_rate": 1.1047250938335969e-05, "loss": 0.0011, "step": 343210 }, { "epoch": 82.42, "learning_rate": 1.1045000536963406e-05, "loss": 0.001, "step": 343220 }, { "epoch": 82.43, "learning_rate": 1.104275033636522e-05, "loss": 0.0012, "step": 343230 }, { "epoch": 82.43, "learning_rate": 1.1040500336553045e-05, "loss": 0.0011, "step": 343240 }, { "epoch": 82.43, "learning_rate": 1.1038250537538442e-05, "loss": 0.0017, "step": 343250 }, { "epoch": 82.43, "learning_rate": 1.103600093933303e-05, "loss": 0.0012, "step": 343260 }, { "epoch": 82.44, "learning_rate": 1.1033751541948383e-05, "loss": 0.0011, "step": 343270 }, { "epoch": 82.44, "learning_rate": 1.1031502345396122e-05, "loss": 0.0012, "step": 343280 }, { "epoch": 82.44, "learning_rate": 1.1029253349687824e-05, "loss": 0.0012, "step": 343290 }, { "epoch": 82.44, "learning_rate": 1.1027004554835068e-05, "loss": 0.001, "step": 343300 }, { "epoch": 82.44, "learning_rate": 1.1024755960849464e-05, "loss": 0.0012, "step": 343310 }, { "epoch": 82.45, "learning_rate": 1.1022507567742585e-05, "loss": 0.0012, "step": 343320 }, { "epoch": 82.45, "learning_rate": 1.1020259375526038e-05, "loss": 0.0011, "step": 343330 }, { "epoch": 82.45, "learning_rate": 1.101801138421139e-05, "loss": 0.0011, "step": 343340 }, { "epoch": 82.45, "learning_rate": 1.1015763593810246e-05, "loss": 0.003, "step": 343350 }, { "epoch": 82.46, "learning_rate": 1.1013516004334184e-05, "loss": 0.0011, "step": 343360 }, { "epoch": 82.46, "learning_rate": 1.1011268615794779e-05, "loss": 0.001, "step": 343370 }, { "epoch": 82.46, "learning_rate": 1.1009021428203625e-05, "loss": 0.0011, "step": 343380 }, { "epoch": 82.46, "learning_rate": 1.1006774441572292e-05, "loss": 0.0011, "step": 343390 }, { "epoch": 82.46, "learning_rate": 1.1004527655912384e-05, "loss": 0.0011, "step": 343400 }, { "epoch": 82.47, "learning_rate": 1.1002281071235453e-05, "loss": 0.001, "step": 343410 }, { "epoch": 82.47, "learning_rate": 1.10000346875531e-05, "loss": 0.001, "step": 343420 }, { "epoch": 82.47, "learning_rate": 1.0997788504876899e-05, "loss": 0.0012, "step": 343430 }, { "epoch": 82.47, "learning_rate": 1.0995542523218411e-05, "loss": 0.0012, "step": 343440 }, { "epoch": 82.48, "learning_rate": 1.0993296742589215e-05, "loss": 0.0011, "step": 343450 }, { "epoch": 82.48, "learning_rate": 1.0991051163000914e-05, "loss": 0.001, "step": 343460 }, { "epoch": 82.48, "learning_rate": 1.0988805784465045e-05, "loss": 0.0012, "step": 343470 }, { "epoch": 82.48, "learning_rate": 1.0986560606993207e-05, "loss": 0.001, "step": 343480 }, { "epoch": 82.49, "learning_rate": 1.0984315630596953e-05, "loss": 0.0011, "step": 343490 }, { "epoch": 82.49, "learning_rate": 1.0982070855287874e-05, "loss": 0.0012, "step": 343500 }, { "epoch": 82.49, "learning_rate": 1.0979826281077515e-05, "loss": 0.0021, "step": 343510 }, { "epoch": 82.49, "learning_rate": 1.0977581907977474e-05, "loss": 0.001, "step": 343520 }, { "epoch": 82.49, "learning_rate": 1.0975337735999285e-05, "loss": 0.0011, "step": 343530 }, { "epoch": 82.5, "learning_rate": 1.0973093765154546e-05, "loss": 0.0011, "step": 343540 }, { "epoch": 82.5, "learning_rate": 1.0970849995454796e-05, "loss": 0.0011, "step": 343550 }, { "epoch": 82.5, "learning_rate": 1.096860642691162e-05, "loss": 0.0076, "step": 343560 }, { "epoch": 82.5, "learning_rate": 1.0966363059536578e-05, "loss": 0.0012, "step": 343570 }, { "epoch": 82.51, "learning_rate": 1.0964119893341207e-05, "loss": 0.0011, "step": 343580 }, { "epoch": 82.51, "learning_rate": 1.096187692833711e-05, "loss": 0.001, "step": 343590 }, { "epoch": 82.51, "learning_rate": 1.0959634164535808e-05, "loss": 0.0011, "step": 343600 }, { "epoch": 82.51, "learning_rate": 1.095739160194889e-05, "loss": 0.0011, "step": 343610 }, { "epoch": 82.52, "learning_rate": 1.0955149240587891e-05, "loss": 0.0011, "step": 343620 }, { "epoch": 82.52, "learning_rate": 1.0952907080464392e-05, "loss": 0.0011, "step": 343630 }, { "epoch": 82.52, "learning_rate": 1.0950665121589937e-05, "loss": 0.0011, "step": 343640 }, { "epoch": 82.52, "learning_rate": 1.0948423363976063e-05, "loss": 0.0013, "step": 343650 }, { "epoch": 82.52, "learning_rate": 1.094618180763436e-05, "loss": 0.0011, "step": 343660 }, { "epoch": 82.53, "learning_rate": 1.0943940452576346e-05, "loss": 0.0012, "step": 343670 }, { "epoch": 82.53, "learning_rate": 1.0941699298813606e-05, "loss": 0.0013, "step": 343680 }, { "epoch": 82.53, "learning_rate": 1.0939458346357657e-05, "loss": 0.0011, "step": 343690 }, { "epoch": 82.53, "learning_rate": 1.0937217595220083e-05, "loss": 0.0011, "step": 343700 }, { "epoch": 82.54, "learning_rate": 1.0934977045412414e-05, "loss": 0.0012, "step": 343710 }, { "epoch": 82.54, "learning_rate": 1.0932736696946183e-05, "loss": 0.0012, "step": 343720 }, { "epoch": 82.54, "learning_rate": 1.0930496549832975e-05, "loss": 0.0011, "step": 343730 }, { "epoch": 82.54, "learning_rate": 1.0928256604084292e-05, "loss": 0.0012, "step": 343740 }, { "epoch": 82.54, "learning_rate": 1.0926016859711725e-05, "loss": 0.0012, "step": 343750 }, { "epoch": 82.55, "learning_rate": 1.0923777316726768e-05, "loss": 0.0013, "step": 343760 }, { "epoch": 82.55, "learning_rate": 1.0921537975141e-05, "loss": 0.0012, "step": 343770 }, { "epoch": 82.55, "learning_rate": 1.0919298834965957e-05, "loss": 0.0013, "step": 343780 }, { "epoch": 82.55, "learning_rate": 1.0917059896213166e-05, "loss": 0.0012, "step": 343790 }, { "epoch": 82.56, "learning_rate": 1.0914821158894189e-05, "loss": 0.0013, "step": 343800 }, { "epoch": 82.56, "learning_rate": 1.0912582623020534e-05, "loss": 0.0011, "step": 343810 }, { "epoch": 82.56, "learning_rate": 1.091034428860377e-05, "loss": 0.0011, "step": 343820 }, { "epoch": 82.56, "learning_rate": 1.0908106155655407e-05, "loss": 0.0011, "step": 343830 }, { "epoch": 82.57, "learning_rate": 1.0905868224187e-05, "loss": 0.0012, "step": 343840 }, { "epoch": 82.57, "learning_rate": 1.0903630494210076e-05, "loss": 0.0011, "step": 343850 }, { "epoch": 82.57, "learning_rate": 1.0901392965736156e-05, "loss": 0.0011, "step": 343860 }, { "epoch": 82.57, "learning_rate": 1.0899155638776798e-05, "loss": 0.0012, "step": 343870 }, { "epoch": 82.57, "learning_rate": 1.0896918513343501e-05, "loss": 0.0026, "step": 343880 }, { "epoch": 82.58, "learning_rate": 1.089468158944783e-05, "loss": 0.0011, "step": 343890 }, { "epoch": 82.58, "learning_rate": 1.0892444867101287e-05, "loss": 0.0012, "step": 343900 }, { "epoch": 82.58, "learning_rate": 1.0890208346315417e-05, "loss": 0.0011, "step": 343910 }, { "epoch": 82.58, "learning_rate": 1.0887972027101729e-05, "loss": 0.0011, "step": 343920 }, { "epoch": 82.59, "learning_rate": 1.0885735909471773e-05, "loss": 0.001, "step": 343930 }, { "epoch": 82.59, "learning_rate": 1.0883499993437057e-05, "loss": 0.0011, "step": 343940 }, { "epoch": 82.59, "learning_rate": 1.08812642790091e-05, "loss": 0.0011, "step": 343950 }, { "epoch": 82.59, "learning_rate": 1.087902876619945e-05, "loss": 0.0012, "step": 343960 }, { "epoch": 82.6, "learning_rate": 1.0876793455019596e-05, "loss": 0.0012, "step": 343970 }, { "epoch": 82.6, "learning_rate": 1.087455834548109e-05, "loss": 0.0012, "step": 343980 }, { "epoch": 82.6, "learning_rate": 1.0872323437595422e-05, "loss": 0.0012, "step": 343990 }, { "epoch": 82.6, "learning_rate": 1.0870088731374139e-05, "loss": 0.0013, "step": 344000 }, { "epoch": 82.6, "learning_rate": 1.086785422682875e-05, "loss": 0.0011, "step": 344010 }, { "epoch": 82.61, "learning_rate": 1.0865619923970749e-05, "loss": 0.0012, "step": 344020 }, { "epoch": 82.61, "learning_rate": 1.0863385822811688e-05, "loss": 0.0011, "step": 344030 }, { "epoch": 82.61, "learning_rate": 1.086115192336305e-05, "loss": 0.0012, "step": 344040 }, { "epoch": 82.61, "learning_rate": 1.0858918225636371e-05, "loss": 0.0012, "step": 344050 }, { "epoch": 82.62, "learning_rate": 1.0856684729643146e-05, "loss": 0.0011, "step": 344060 }, { "epoch": 82.62, "learning_rate": 1.0854451435394891e-05, "loss": 0.0011, "step": 344070 }, { "epoch": 82.62, "learning_rate": 1.0852218342903137e-05, "loss": 0.0012, "step": 344080 }, { "epoch": 82.62, "learning_rate": 1.0849985452179362e-05, "loss": 0.0011, "step": 344090 }, { "epoch": 82.62, "learning_rate": 1.0847752763235102e-05, "loss": 0.0013, "step": 344100 }, { "epoch": 82.63, "learning_rate": 1.0845520276081839e-05, "loss": 0.0012, "step": 344110 }, { "epoch": 82.63, "learning_rate": 1.0843287990731105e-05, "loss": 0.001, "step": 344120 }, { "epoch": 82.63, "learning_rate": 1.0841055907194381e-05, "loss": 0.0012, "step": 344130 }, { "epoch": 82.63, "learning_rate": 1.083882402548319e-05, "loss": 0.001, "step": 344140 }, { "epoch": 82.64, "learning_rate": 1.0836592345609031e-05, "loss": 0.0011, "step": 344150 }, { "epoch": 82.64, "learning_rate": 1.0834360867583388e-05, "loss": 0.0012, "step": 344160 }, { "epoch": 82.64, "learning_rate": 1.0832129591417794e-05, "loss": 0.0013, "step": 344170 }, { "epoch": 82.64, "learning_rate": 1.0829898517123715e-05, "loss": 0.0011, "step": 344180 }, { "epoch": 82.65, "learning_rate": 1.082766764471268e-05, "loss": 0.0011, "step": 344190 }, { "epoch": 82.65, "learning_rate": 1.0825436974196157e-05, "loss": 0.0011, "step": 344200 }, { "epoch": 82.65, "learning_rate": 1.0823206505585675e-05, "loss": 0.001, "step": 344210 }, { "epoch": 82.65, "learning_rate": 1.0820976238892717e-05, "loss": 0.0011, "step": 344220 }, { "epoch": 82.65, "learning_rate": 1.0818746174128757e-05, "loss": 0.0012, "step": 344230 }, { "epoch": 82.66, "learning_rate": 1.0816516311305324e-05, "loss": 0.0012, "step": 344240 }, { "epoch": 82.66, "learning_rate": 1.0814286650433875e-05, "loss": 0.0012, "step": 344250 }, { "epoch": 82.66, "learning_rate": 1.0812057191525937e-05, "loss": 0.0011, "step": 344260 }, { "epoch": 82.66, "learning_rate": 1.080982793459297e-05, "loss": 0.0011, "step": 344270 }, { "epoch": 82.67, "learning_rate": 1.0807598879646491e-05, "loss": 0.0011, "step": 344280 }, { "epoch": 82.67, "learning_rate": 1.0805370026697975e-05, "loss": 0.0012, "step": 344290 }, { "epoch": 82.67, "learning_rate": 1.0803141375758896e-05, "loss": 0.0012, "step": 344300 }, { "epoch": 82.67, "learning_rate": 1.0800912926840767e-05, "loss": 0.0011, "step": 344310 }, { "epoch": 82.68, "learning_rate": 1.0798684679955046e-05, "loss": 0.0012, "step": 344320 }, { "epoch": 82.68, "learning_rate": 1.079645663511325e-05, "loss": 0.0012, "step": 344330 }, { "epoch": 82.68, "learning_rate": 1.0794228792326827e-05, "loss": 0.0011, "step": 344340 }, { "epoch": 82.68, "learning_rate": 1.079200115160729e-05, "loss": 0.0012, "step": 344350 }, { "epoch": 82.68, "learning_rate": 1.0789773712966094e-05, "loss": 0.0012, "step": 344360 }, { "epoch": 82.69, "learning_rate": 1.0787546476414746e-05, "loss": 0.0011, "step": 344370 }, { "epoch": 82.69, "learning_rate": 1.0785319441964692e-05, "loss": 0.0011, "step": 344380 }, { "epoch": 82.69, "learning_rate": 1.0783092609627437e-05, "loss": 0.0011, "step": 344390 }, { "epoch": 82.69, "learning_rate": 1.0780865979414462e-05, "loss": 0.0012, "step": 344400 }, { "epoch": 82.7, "learning_rate": 1.0778639551337217e-05, "loss": 0.0011, "step": 344410 }, { "epoch": 82.7, "learning_rate": 1.0776413325407203e-05, "loss": 0.0012, "step": 344420 }, { "epoch": 82.7, "learning_rate": 1.0774187301635885e-05, "loss": 0.0015, "step": 344430 }, { "epoch": 82.7, "learning_rate": 1.077196148003472e-05, "loss": 0.0012, "step": 344440 }, { "epoch": 82.7, "learning_rate": 1.076973586061521e-05, "loss": 0.0012, "step": 344450 }, { "epoch": 82.71, "learning_rate": 1.076751044338879e-05, "loss": 0.001, "step": 344460 }, { "epoch": 82.71, "learning_rate": 1.0765285228366966e-05, "loss": 0.0011, "step": 344470 }, { "epoch": 82.71, "learning_rate": 1.0763060215561177e-05, "loss": 0.0012, "step": 344480 }, { "epoch": 82.71, "learning_rate": 1.0760835404982916e-05, "loss": 0.0011, "step": 344490 }, { "epoch": 82.72, "learning_rate": 1.0758610796643636e-05, "loss": 0.0011, "step": 344500 }, { "epoch": 82.72, "learning_rate": 1.075638639055479e-05, "loss": 0.001, "step": 344510 }, { "epoch": 82.72, "learning_rate": 1.0754162186727873e-05, "loss": 0.0012, "step": 344520 }, { "epoch": 82.72, "learning_rate": 1.0751938185174315e-05, "loss": 0.0011, "step": 344530 }, { "epoch": 82.73, "learning_rate": 1.0749714385905613e-05, "loss": 0.0011, "step": 344540 }, { "epoch": 82.73, "learning_rate": 1.0747490788933195e-05, "loss": 0.0011, "step": 344550 }, { "epoch": 82.73, "learning_rate": 1.0745267394268555e-05, "loss": 0.0012, "step": 344560 }, { "epoch": 82.73, "learning_rate": 1.074304420192313e-05, "loss": 0.0011, "step": 344570 }, { "epoch": 82.73, "learning_rate": 1.0740821211908375e-05, "loss": 0.0011, "step": 344580 }, { "epoch": 82.74, "learning_rate": 1.0738598424235762e-05, "loss": 0.0011, "step": 344590 }, { "epoch": 82.74, "learning_rate": 1.0736375838916734e-05, "loss": 0.0013, "step": 344600 }, { "epoch": 82.74, "learning_rate": 1.0734153455962765e-05, "loss": 0.0013, "step": 344610 }, { "epoch": 82.74, "learning_rate": 1.0731931275385281e-05, "loss": 0.0011, "step": 344620 }, { "epoch": 82.75, "learning_rate": 1.0729709297195766e-05, "loss": 0.0011, "step": 344630 }, { "epoch": 82.75, "learning_rate": 1.0727487521405648e-05, "loss": 0.001, "step": 344640 }, { "epoch": 82.75, "learning_rate": 1.0725265948026398e-05, "loss": 0.0011, "step": 344650 }, { "epoch": 82.75, "learning_rate": 1.0723044577069441e-05, "loss": 0.0012, "step": 344660 }, { "epoch": 82.76, "learning_rate": 1.0720823408546254e-05, "loss": 0.0012, "step": 344670 }, { "epoch": 82.76, "learning_rate": 1.0718602442468261e-05, "loss": 0.0011, "step": 344680 }, { "epoch": 82.76, "learning_rate": 1.0716381678846932e-05, "loss": 0.0012, "step": 344690 }, { "epoch": 82.76, "learning_rate": 1.0714161117693683e-05, "loss": 0.0012, "step": 344700 }, { "epoch": 82.76, "learning_rate": 1.0711940759019979e-05, "loss": 0.0011, "step": 344710 }, { "epoch": 82.77, "learning_rate": 1.0709720602837275e-05, "loss": 0.0011, "step": 344720 }, { "epoch": 82.77, "learning_rate": 1.0707500649156998e-05, "loss": 0.0012, "step": 344730 }, { "epoch": 82.77, "learning_rate": 1.0705280897990577e-05, "loss": 0.0011, "step": 344740 }, { "epoch": 82.77, "learning_rate": 1.070306134934948e-05, "loss": 0.0012, "step": 344750 }, { "epoch": 82.78, "learning_rate": 1.0700842003245121e-05, "loss": 0.0012, "step": 344760 }, { "epoch": 82.78, "learning_rate": 1.0698622859688968e-05, "loss": 0.0012, "step": 344770 }, { "epoch": 82.78, "learning_rate": 1.0696403918692422e-05, "loss": 0.0011, "step": 344780 }, { "epoch": 82.78, "learning_rate": 1.0694185180266952e-05, "loss": 0.0012, "step": 344790 }, { "epoch": 82.78, "learning_rate": 1.0691966644423985e-05, "loss": 0.0012, "step": 344800 }, { "epoch": 82.79, "learning_rate": 1.068974831117493e-05, "loss": 0.0011, "step": 344810 }, { "epoch": 82.79, "learning_rate": 1.0687530180531264e-05, "loss": 0.0011, "step": 344820 }, { "epoch": 82.79, "learning_rate": 1.0685312252504376e-05, "loss": 0.0012, "step": 344830 }, { "epoch": 82.79, "learning_rate": 1.068309452710573e-05, "loss": 0.0035, "step": 344840 }, { "epoch": 82.8, "learning_rate": 1.0680877004346734e-05, "loss": 0.0011, "step": 344850 }, { "epoch": 82.8, "learning_rate": 1.0678659684238833e-05, "loss": 0.001, "step": 344860 }, { "epoch": 82.8, "learning_rate": 1.0676442566793453e-05, "loss": 0.0012, "step": 344870 }, { "epoch": 82.8, "learning_rate": 1.0674225652022007e-05, "loss": 0.0012, "step": 344880 }, { "epoch": 82.81, "learning_rate": 1.067200893993594e-05, "loss": 0.0012, "step": 344890 }, { "epoch": 82.81, "learning_rate": 1.0669792430546654e-05, "loss": 0.0012, "step": 344900 }, { "epoch": 82.81, "learning_rate": 1.0667576123865602e-05, "loss": 0.0031, "step": 344910 }, { "epoch": 82.81, "learning_rate": 1.066536001990418e-05, "loss": 0.0011, "step": 344920 }, { "epoch": 82.81, "learning_rate": 1.0663144118673829e-05, "loss": 0.0011, "step": 344930 }, { "epoch": 82.82, "learning_rate": 1.0660928420185967e-05, "loss": 0.0012, "step": 344940 }, { "epoch": 82.82, "learning_rate": 1.0658712924451992e-05, "loss": 0.0011, "step": 344950 }, { "epoch": 82.82, "learning_rate": 1.0656497631483342e-05, "loss": 0.0011, "step": 344960 }, { "epoch": 82.82, "learning_rate": 1.0654282541291444e-05, "loss": 0.001, "step": 344970 }, { "epoch": 82.83, "learning_rate": 1.0652067653887687e-05, "loss": 0.001, "step": 344980 }, { "epoch": 82.83, "learning_rate": 1.064985296928352e-05, "loss": 0.0011, "step": 344990 }, { "epoch": 82.83, "learning_rate": 1.0647638487490324e-05, "loss": 0.0012, "step": 345000 }, { "epoch": 82.83, "learning_rate": 1.0645424208519539e-05, "loss": 0.0012, "step": 345010 }, { "epoch": 82.84, "learning_rate": 1.0643210132382558e-05, "loss": 0.0011, "step": 345020 }, { "epoch": 82.84, "learning_rate": 1.0640996259090813e-05, "loss": 0.0011, "step": 345030 }, { "epoch": 82.84, "learning_rate": 1.0638782588655689e-05, "loss": 0.0011, "step": 345040 }, { "epoch": 82.84, "learning_rate": 1.063656912108862e-05, "loss": 0.0013, "step": 345050 }, { "epoch": 82.84, "learning_rate": 1.063435585640099e-05, "loss": 0.001, "step": 345060 }, { "epoch": 82.85, "learning_rate": 1.0632142794604233e-05, "loss": 0.0011, "step": 345070 }, { "epoch": 82.85, "learning_rate": 1.0629929935709742e-05, "loss": 0.0011, "step": 345080 }, { "epoch": 82.85, "learning_rate": 1.0627717279728905e-05, "loss": 0.0011, "step": 345090 }, { "epoch": 82.85, "learning_rate": 1.0625504826673161e-05, "loss": 0.0011, "step": 345100 }, { "epoch": 82.86, "learning_rate": 1.0623292576553879e-05, "loss": 0.0012, "step": 345110 }, { "epoch": 82.86, "learning_rate": 1.0621080529382483e-05, "loss": 0.001, "step": 345120 }, { "epoch": 82.86, "learning_rate": 1.0618868685170359e-05, "loss": 0.0011, "step": 345130 }, { "epoch": 82.86, "learning_rate": 1.061665704392893e-05, "loss": 0.0012, "step": 345140 }, { "epoch": 82.86, "learning_rate": 1.0614445605669577e-05, "loss": 0.0011, "step": 345150 }, { "epoch": 82.87, "learning_rate": 1.061223437040369e-05, "loss": 0.0011, "step": 345160 }, { "epoch": 82.87, "learning_rate": 1.0610023338142688e-05, "loss": 0.0013, "step": 345170 }, { "epoch": 82.87, "learning_rate": 1.060781250889794e-05, "loss": 0.0012, "step": 345180 }, { "epoch": 82.87, "learning_rate": 1.0605601882680871e-05, "loss": 0.0012, "step": 345190 }, { "epoch": 82.88, "learning_rate": 1.0603391459502842e-05, "loss": 0.0012, "step": 345200 }, { "epoch": 82.88, "learning_rate": 1.060118123937528e-05, "loss": 0.0011, "step": 345210 }, { "epoch": 82.88, "learning_rate": 1.0598971222309555e-05, "loss": 0.0012, "step": 345220 }, { "epoch": 82.88, "learning_rate": 1.0596761408317057e-05, "loss": 0.0011, "step": 345230 }, { "epoch": 82.89, "learning_rate": 1.0594551797409186e-05, "loss": 0.001, "step": 345240 }, { "epoch": 82.89, "learning_rate": 1.0592342389597315e-05, "loss": 0.001, "step": 345250 }, { "epoch": 82.89, "learning_rate": 1.0590133184892853e-05, "loss": 0.0011, "step": 345260 }, { "epoch": 82.89, "learning_rate": 1.0587924183307157e-05, "loss": 0.0011, "step": 345270 }, { "epoch": 82.89, "learning_rate": 1.058571538485163e-05, "loss": 0.0012, "step": 345280 }, { "epoch": 82.9, "learning_rate": 1.0583506789537673e-05, "loss": 0.0012, "step": 345290 }, { "epoch": 82.9, "learning_rate": 1.0581298397376638e-05, "loss": 0.0012, "step": 345300 }, { "epoch": 82.9, "learning_rate": 1.0579090208379927e-05, "loss": 0.0012, "step": 345310 }, { "epoch": 82.9, "learning_rate": 1.057688222255891e-05, "loss": 0.0011, "step": 345320 }, { "epoch": 82.91, "learning_rate": 1.057467443992498e-05, "loss": 0.0009, "step": 345330 }, { "epoch": 82.91, "learning_rate": 1.0572466860489493e-05, "loss": 0.001, "step": 345340 }, { "epoch": 82.91, "learning_rate": 1.0570259484263856e-05, "loss": 0.0011, "step": 345350 }, { "epoch": 82.91, "learning_rate": 1.0568052311259436e-05, "loss": 0.001, "step": 345360 }, { "epoch": 82.91, "learning_rate": 1.0565845341487585e-05, "loss": 0.0106, "step": 345370 }, { "epoch": 82.92, "learning_rate": 1.056363857495971e-05, "loss": 0.0012, "step": 345380 }, { "epoch": 82.92, "learning_rate": 1.0561432011687162e-05, "loss": 0.0012, "step": 345390 }, { "epoch": 82.92, "learning_rate": 1.0559225651681331e-05, "loss": 0.0012, "step": 345400 }, { "epoch": 82.92, "learning_rate": 1.0557019494953573e-05, "loss": 0.0012, "step": 345410 }, { "epoch": 82.93, "learning_rate": 1.0554813541515273e-05, "loss": 0.0012, "step": 345420 }, { "epoch": 82.93, "learning_rate": 1.0552607791377799e-05, "loss": 0.0009, "step": 345430 }, { "epoch": 82.93, "learning_rate": 1.0550402244552503e-05, "loss": 0.0012, "step": 345440 }, { "epoch": 82.93, "learning_rate": 1.0548196901050772e-05, "loss": 0.0013, "step": 345450 }, { "epoch": 82.94, "learning_rate": 1.054599176088395e-05, "loss": 0.0011, "step": 345460 }, { "epoch": 82.94, "learning_rate": 1.0543786824063434e-05, "loss": 0.0013, "step": 345470 }, { "epoch": 82.94, "learning_rate": 1.0541582090600555e-05, "loss": 0.0012, "step": 345480 }, { "epoch": 82.94, "learning_rate": 1.0539377560506702e-05, "loss": 0.0011, "step": 345490 }, { "epoch": 82.94, "learning_rate": 1.0537173233793219e-05, "loss": 0.0036, "step": 345500 }, { "epoch": 82.95, "learning_rate": 1.0534969110471487e-05, "loss": 0.0013, "step": 345510 }, { "epoch": 82.95, "learning_rate": 1.0532765190552851e-05, "loss": 0.0011, "step": 345520 }, { "epoch": 83.0, "learning_rate": 1.053056147404866e-05, "loss": 0.0011, "step": 345530 }, { "epoch": 83.0, "learning_rate": 1.0528357960970303e-05, "loss": 0.0012, "step": 345540 }, { "epoch": 83.0, "learning_rate": 1.05261546513291e-05, "loss": 0.0011, "step": 345550 }, { "epoch": 83.01, "learning_rate": 1.0523951545136446e-05, "loss": 0.0011, "step": 345560 }, { "epoch": 83.01, "learning_rate": 1.0521748642403656e-05, "loss": 0.0012, "step": 345570 }, { "epoch": 83.01, "learning_rate": 1.0519545943142118e-05, "loss": 0.0012, "step": 345580 }, { "epoch": 83.01, "learning_rate": 1.051734344736316e-05, "loss": 0.0011, "step": 345590 }, { "epoch": 83.02, "learning_rate": 1.051514115507814e-05, "loss": 0.0011, "step": 345600 }, { "epoch": 83.02, "learning_rate": 1.0512939066298426e-05, "loss": 0.0011, "step": 345610 }, { "epoch": 83.02, "learning_rate": 1.0510737181035346e-05, "loss": 0.0011, "step": 345620 }, { "epoch": 83.02, "learning_rate": 1.0508535499300264e-05, "loss": 0.0011, "step": 345630 }, { "epoch": 83.03, "learning_rate": 1.0506334021104513e-05, "loss": 0.0011, "step": 345640 }, { "epoch": 83.03, "learning_rate": 1.0504132746459456e-05, "loss": 0.0014, "step": 345650 }, { "epoch": 83.03, "learning_rate": 1.050193167537643e-05, "loss": 0.0011, "step": 345660 }, { "epoch": 83.03, "learning_rate": 1.0499730807866765e-05, "loss": 0.0011, "step": 345670 }, { "epoch": 83.03, "learning_rate": 1.0497530143941826e-05, "loss": 0.0011, "step": 345680 }, { "epoch": 83.04, "learning_rate": 1.0495329683612936e-05, "loss": 0.0011, "step": 345690 }, { "epoch": 83.04, "learning_rate": 1.0493129426891463e-05, "loss": 0.0012, "step": 345700 }, { "epoch": 83.04, "learning_rate": 1.0490929373788717e-05, "loss": 0.001, "step": 345710 }, { "epoch": 83.04, "learning_rate": 1.0488729524316065e-05, "loss": 0.0011, "step": 345720 }, { "epoch": 83.05, "learning_rate": 1.048652987848483e-05, "loss": 0.001, "step": 345730 }, { "epoch": 83.05, "learning_rate": 1.0484330436306338e-05, "loss": 0.0012, "step": 345740 }, { "epoch": 83.05, "learning_rate": 1.048213119779195e-05, "loss": 0.001, "step": 345750 }, { "epoch": 83.05, "learning_rate": 1.0479932162952976e-05, "loss": 0.0011, "step": 345760 }, { "epoch": 83.06, "learning_rate": 1.0477733331800776e-05, "loss": 0.0011, "step": 345770 }, { "epoch": 83.06, "learning_rate": 1.047553470434665e-05, "loss": 0.001, "step": 345780 }, { "epoch": 83.06, "learning_rate": 1.047333628060197e-05, "loss": 0.0011, "step": 345790 }, { "epoch": 83.06, "learning_rate": 1.0471138060578039e-05, "loss": 0.0011, "step": 345800 }, { "epoch": 83.06, "learning_rate": 1.046894004428618e-05, "loss": 0.0012, "step": 345810 }, { "epoch": 83.07, "learning_rate": 1.0466742231737753e-05, "loss": 0.0013, "step": 345820 }, { "epoch": 83.07, "learning_rate": 1.0464544622944045e-05, "loss": 0.001, "step": 345830 }, { "epoch": 83.07, "learning_rate": 1.0462347217916424e-05, "loss": 0.0011, "step": 345840 }, { "epoch": 83.07, "learning_rate": 1.0460150016666181e-05, "loss": 0.0012, "step": 345850 }, { "epoch": 83.08, "learning_rate": 1.045795301920467e-05, "loss": 0.0012, "step": 345860 }, { "epoch": 83.08, "learning_rate": 1.0455756225543183e-05, "loss": 0.001, "step": 345870 }, { "epoch": 83.08, "learning_rate": 1.0453559635693077e-05, "loss": 0.0011, "step": 345880 }, { "epoch": 83.08, "learning_rate": 1.0451363249665636e-05, "loss": 0.001, "step": 345890 }, { "epoch": 83.08, "learning_rate": 1.0449167067472205e-05, "loss": 0.0011, "step": 345900 }, { "epoch": 83.09, "learning_rate": 1.0446971089124108e-05, "loss": 0.001, "step": 345910 }, { "epoch": 83.09, "learning_rate": 1.0444775314632638e-05, "loss": 0.0012, "step": 345920 }, { "epoch": 83.09, "learning_rate": 1.0442579744009146e-05, "loss": 0.0009, "step": 345930 }, { "epoch": 83.09, "learning_rate": 1.0440384377264923e-05, "loss": 0.0011, "step": 345940 }, { "epoch": 83.1, "learning_rate": 1.0438189214411275e-05, "loss": 0.001, "step": 345950 }, { "epoch": 83.1, "learning_rate": 1.0435994255459546e-05, "loss": 0.0011, "step": 345960 }, { "epoch": 83.1, "learning_rate": 1.0433799500421021e-05, "loss": 0.001, "step": 345970 }, { "epoch": 83.1, "learning_rate": 1.0431604949307039e-05, "loss": 0.0011, "step": 345980 }, { "epoch": 83.11, "learning_rate": 1.0429410602128881e-05, "loss": 0.0095, "step": 345990 }, { "epoch": 83.11, "learning_rate": 1.0427216458897881e-05, "loss": 0.0013, "step": 346000 }, { "epoch": 83.11, "learning_rate": 1.0425022519625344e-05, "loss": 0.0012, "step": 346010 }, { "epoch": 83.11, "learning_rate": 1.0422828784322552e-05, "loss": 0.001, "step": 346020 }, { "epoch": 83.11, "learning_rate": 1.042063525300085e-05, "loss": 0.0011, "step": 346030 }, { "epoch": 83.12, "learning_rate": 1.0418441925671512e-05, "loss": 0.0011, "step": 346040 }, { "epoch": 83.12, "learning_rate": 1.0416248802345867e-05, "loss": 0.001, "step": 346050 }, { "epoch": 83.12, "learning_rate": 1.041405588303519e-05, "loss": 0.0013, "step": 346060 }, { "epoch": 83.12, "learning_rate": 1.0411863167750818e-05, "loss": 0.0011, "step": 346070 }, { "epoch": 83.13, "learning_rate": 1.0409670656504029e-05, "loss": 0.0011, "step": 346080 }, { "epoch": 83.13, "learning_rate": 1.0407478349306121e-05, "loss": 0.0012, "step": 346090 }, { "epoch": 83.13, "learning_rate": 1.040528624616841e-05, "loss": 0.0011, "step": 346100 }, { "epoch": 83.13, "learning_rate": 1.0403094347102171e-05, "loss": 0.001, "step": 346110 }, { "epoch": 83.14, "learning_rate": 1.0400902652118727e-05, "loss": 0.0011, "step": 346120 }, { "epoch": 83.14, "learning_rate": 1.0398711161229351e-05, "loss": 0.001, "step": 346130 }, { "epoch": 83.14, "learning_rate": 1.0396519874445366e-05, "loss": 0.0012, "step": 346140 }, { "epoch": 83.14, "learning_rate": 1.039432879177804e-05, "loss": 0.0011, "step": 346150 }, { "epoch": 83.14, "learning_rate": 1.0392137913238665e-05, "loss": 0.0011, "step": 346160 }, { "epoch": 83.15, "learning_rate": 1.0389947238838543e-05, "loss": 0.0011, "step": 346170 }, { "epoch": 83.15, "learning_rate": 1.0387756768588979e-05, "loss": 0.001, "step": 346180 }, { "epoch": 83.15, "learning_rate": 1.0385566502501232e-05, "loss": 0.0011, "step": 346190 }, { "epoch": 83.15, "learning_rate": 1.0383376440586617e-05, "loss": 0.001, "step": 346200 }, { "epoch": 83.16, "learning_rate": 1.03811865828564e-05, "loss": 0.001, "step": 346210 }, { "epoch": 83.16, "learning_rate": 1.0378996929321894e-05, "loss": 0.001, "step": 346220 }, { "epoch": 83.16, "learning_rate": 1.0376807479994355e-05, "loss": 0.0011, "step": 346230 }, { "epoch": 83.16, "learning_rate": 1.0374618234885092e-05, "loss": 0.0012, "step": 346240 }, { "epoch": 83.16, "learning_rate": 1.0372429194005368e-05, "loss": 0.0011, "step": 346250 }, { "epoch": 83.17, "learning_rate": 1.0370240357366489e-05, "loss": 0.001, "step": 346260 }, { "epoch": 83.17, "learning_rate": 1.0368051724979705e-05, "loss": 0.001, "step": 346270 }, { "epoch": 83.17, "learning_rate": 1.0365863296856333e-05, "loss": 0.0011, "step": 346280 }, { "epoch": 83.17, "learning_rate": 1.0363675073007623e-05, "loss": 0.0012, "step": 346290 }, { "epoch": 83.18, "learning_rate": 1.0361487053444857e-05, "loss": 0.0011, "step": 346300 }, { "epoch": 83.18, "learning_rate": 1.0359299238179332e-05, "loss": 0.0011, "step": 346310 }, { "epoch": 83.18, "learning_rate": 1.0357111627222293e-05, "loss": 0.0011, "step": 346320 }, { "epoch": 83.18, "learning_rate": 1.0354924220585049e-05, "loss": 0.001, "step": 346330 }, { "epoch": 83.19, "learning_rate": 1.035273701827884e-05, "loss": 0.0011, "step": 346340 }, { "epoch": 83.19, "learning_rate": 1.035055002031497e-05, "loss": 0.0011, "step": 346350 }, { "epoch": 83.19, "learning_rate": 1.0348363226704683e-05, "loss": 0.0011, "step": 346360 }, { "epoch": 83.19, "learning_rate": 1.0346176637459282e-05, "loss": 0.0011, "step": 346370 }, { "epoch": 83.19, "learning_rate": 1.0343990252590013e-05, "loss": 0.001, "step": 346380 }, { "epoch": 83.2, "learning_rate": 1.0341804072108136e-05, "loss": 0.001, "step": 346390 }, { "epoch": 83.2, "learning_rate": 1.0339618096024945e-05, "loss": 0.0011, "step": 346400 }, { "epoch": 83.2, "learning_rate": 1.0337432324351682e-05, "loss": 0.0011, "step": 346410 }, { "epoch": 83.2, "learning_rate": 1.0335246757099637e-05, "loss": 0.0009, "step": 346420 }, { "epoch": 83.21, "learning_rate": 1.0333061394280052e-05, "loss": 0.001, "step": 346430 }, { "epoch": 83.21, "learning_rate": 1.0330876235904213e-05, "loss": 0.0011, "step": 346440 }, { "epoch": 83.21, "learning_rate": 1.0328691281983365e-05, "loss": 0.0011, "step": 346450 }, { "epoch": 83.21, "learning_rate": 1.0326506532528762e-05, "loss": 0.001, "step": 346460 }, { "epoch": 83.22, "learning_rate": 1.0324321987551677e-05, "loss": 0.0009, "step": 346470 }, { "epoch": 83.22, "learning_rate": 1.0322137647063385e-05, "loss": 0.001, "step": 346480 }, { "epoch": 83.22, "learning_rate": 1.0319953511075109e-05, "loss": 0.001, "step": 346490 }, { "epoch": 83.22, "learning_rate": 1.0317769579598135e-05, "loss": 0.0011, "step": 346500 }, { "epoch": 83.22, "learning_rate": 1.03155858526437e-05, "loss": 0.0011, "step": 346510 }, { "epoch": 83.23, "learning_rate": 1.0313402330223081e-05, "loss": 0.0011, "step": 346520 }, { "epoch": 83.23, "learning_rate": 1.03112190123475e-05, "loss": 0.011, "step": 346530 }, { "epoch": 83.23, "learning_rate": 1.0309035899028246e-05, "loss": 0.001, "step": 346540 }, { "epoch": 83.23, "learning_rate": 1.0306852990276539e-05, "loss": 0.0012, "step": 346550 }, { "epoch": 83.24, "learning_rate": 1.0304670286103651e-05, "loss": 0.0011, "step": 346560 }, { "epoch": 83.24, "learning_rate": 1.030248778652082e-05, "loss": 0.0011, "step": 346570 }, { "epoch": 83.24, "learning_rate": 1.0300305491539308e-05, "loss": 0.001, "step": 346580 }, { "epoch": 83.24, "learning_rate": 1.029812340117035e-05, "loss": 0.0011, "step": 346590 }, { "epoch": 83.24, "learning_rate": 1.0295941515425184e-05, "loss": 0.0011, "step": 346600 }, { "epoch": 83.25, "learning_rate": 1.0293759834315087e-05, "loss": 0.0011, "step": 346610 }, { "epoch": 83.25, "learning_rate": 1.0291578357851262e-05, "loss": 0.001, "step": 346620 }, { "epoch": 83.25, "learning_rate": 1.0289397086044988e-05, "loss": 0.001, "step": 346630 }, { "epoch": 83.25, "learning_rate": 1.0287216018907486e-05, "loss": 0.0011, "step": 346640 }, { "epoch": 83.26, "learning_rate": 1.0285035156450012e-05, "loss": 0.0011, "step": 346650 }, { "epoch": 83.26, "learning_rate": 1.0282854498683802e-05, "loss": 0.001, "step": 346660 }, { "epoch": 83.26, "learning_rate": 1.0280674045620082e-05, "loss": 0.0011, "step": 346670 }, { "epoch": 83.26, "learning_rate": 1.0278493797270106e-05, "loss": 0.001, "step": 346680 }, { "epoch": 83.27, "learning_rate": 1.0276313753645096e-05, "loss": 0.0011, "step": 346690 }, { "epoch": 83.27, "learning_rate": 1.0274133914756307e-05, "loss": 0.0012, "step": 346700 }, { "epoch": 83.27, "learning_rate": 1.0271954280614955e-05, "loss": 0.0011, "step": 346710 }, { "epoch": 83.27, "learning_rate": 1.0269774851232294e-05, "loss": 0.001, "step": 346720 }, { "epoch": 83.27, "learning_rate": 1.026759562661954e-05, "loss": 0.0011, "step": 346730 }, { "epoch": 83.28, "learning_rate": 1.0265416606787926e-05, "loss": 0.001, "step": 346740 }, { "epoch": 83.28, "learning_rate": 1.0263237791748697e-05, "loss": 0.001, "step": 346750 }, { "epoch": 83.28, "learning_rate": 1.026105918151306e-05, "loss": 0.0011, "step": 346760 }, { "epoch": 83.28, "learning_rate": 1.0258880776092267e-05, "loss": 0.0012, "step": 346770 }, { "epoch": 83.29, "learning_rate": 1.0256702575497524e-05, "loss": 0.0012, "step": 346780 }, { "epoch": 83.29, "learning_rate": 1.0254524579740066e-05, "loss": 0.0012, "step": 346790 }, { "epoch": 83.29, "learning_rate": 1.0252346788831136e-05, "loss": 0.0011, "step": 346800 }, { "epoch": 83.29, "learning_rate": 1.0250169202781923e-05, "loss": 0.0012, "step": 346810 }, { "epoch": 83.3, "learning_rate": 1.0247991821603691e-05, "loss": 0.0011, "step": 346820 }, { "epoch": 83.3, "learning_rate": 1.0245814645307627e-05, "loss": 0.0011, "step": 346830 }, { "epoch": 83.3, "learning_rate": 1.0243637673904977e-05, "loss": 0.001, "step": 346840 }, { "epoch": 83.3, "learning_rate": 1.024146090740694e-05, "loss": 0.0011, "step": 346850 }, { "epoch": 83.3, "learning_rate": 1.0239284345824757e-05, "loss": 0.001, "step": 346860 }, { "epoch": 83.31, "learning_rate": 1.0237107989169636e-05, "loss": 0.0011, "step": 346870 }, { "epoch": 83.31, "learning_rate": 1.0234931837452782e-05, "loss": 0.001, "step": 346880 }, { "epoch": 83.31, "learning_rate": 1.023275589068543e-05, "loss": 0.0012, "step": 346890 }, { "epoch": 83.31, "learning_rate": 1.0230580148878777e-05, "loss": 0.0011, "step": 346900 }, { "epoch": 83.32, "learning_rate": 1.0228404612044057e-05, "loss": 0.0011, "step": 346910 }, { "epoch": 83.32, "learning_rate": 1.0226229280192463e-05, "loss": 0.0011, "step": 346920 }, { "epoch": 83.32, "learning_rate": 1.0224054153335222e-05, "loss": 0.001, "step": 346930 }, { "epoch": 83.32, "learning_rate": 1.0221879231483544e-05, "loss": 0.0011, "step": 346940 }, { "epoch": 83.32, "learning_rate": 1.021970451464862e-05, "loss": 0.0011, "step": 346950 }, { "epoch": 83.33, "learning_rate": 1.0217530002841679e-05, "loss": 0.0011, "step": 346960 }, { "epoch": 83.33, "learning_rate": 1.0215355696073914e-05, "loss": 0.0011, "step": 346970 }, { "epoch": 83.33, "learning_rate": 1.0213181594356546e-05, "loss": 0.0011, "step": 346980 }, { "epoch": 83.33, "learning_rate": 1.0211007697700764e-05, "loss": 0.001, "step": 346990 }, { "epoch": 83.34, "learning_rate": 1.0208834006117796e-05, "loss": 0.001, "step": 347000 }, { "epoch": 83.34, "learning_rate": 1.0206660519618827e-05, "loss": 0.001, "step": 347010 }, { "epoch": 83.34, "learning_rate": 1.020448723821505e-05, "loss": 0.0011, "step": 347020 }, { "epoch": 83.34, "learning_rate": 1.0202314161917687e-05, "loss": 0.001, "step": 347030 }, { "epoch": 83.35, "learning_rate": 1.020014129073792e-05, "loss": 0.001, "step": 347040 }, { "epoch": 83.35, "learning_rate": 1.0197968624686972e-05, "loss": 0.0011, "step": 347050 }, { "epoch": 83.35, "learning_rate": 1.0195796163776011e-05, "loss": 0.001, "step": 347060 }, { "epoch": 83.35, "learning_rate": 1.0193623908016265e-05, "loss": 0.001, "step": 347070 }, { "epoch": 83.35, "learning_rate": 1.01914518574189e-05, "loss": 0.0011, "step": 347080 }, { "epoch": 83.36, "learning_rate": 1.0189280011995133e-05, "loss": 0.0011, "step": 347090 }, { "epoch": 83.36, "learning_rate": 1.0187108371756143e-05, "loss": 0.0012, "step": 347100 }, { "epoch": 83.36, "learning_rate": 1.0184936936713124e-05, "loss": 0.0011, "step": 347110 }, { "epoch": 83.36, "learning_rate": 1.018276570687729e-05, "loss": 0.001, "step": 347120 }, { "epoch": 83.37, "learning_rate": 1.0180594682259798e-05, "loss": 0.001, "step": 347130 }, { "epoch": 83.37, "learning_rate": 1.0178423862871872e-05, "loss": 0.0012, "step": 347140 }, { "epoch": 83.37, "learning_rate": 1.0176253248724665e-05, "loss": 0.0011, "step": 347150 }, { "epoch": 83.37, "learning_rate": 1.0174082839829397e-05, "loss": 0.0011, "step": 347160 }, { "epoch": 83.38, "learning_rate": 1.0171912636197234e-05, "loss": 0.0011, "step": 347170 }, { "epoch": 83.38, "learning_rate": 1.0169742637839359e-05, "loss": 0.0012, "step": 347180 }, { "epoch": 83.38, "learning_rate": 1.0167572844766976e-05, "loss": 0.001, "step": 347190 }, { "epoch": 83.38, "learning_rate": 1.016540325699124e-05, "loss": 0.001, "step": 347200 }, { "epoch": 83.38, "learning_rate": 1.0163233874523359e-05, "loss": 0.0011, "step": 347210 }, { "epoch": 83.39, "learning_rate": 1.0161064697374495e-05, "loss": 0.0011, "step": 347220 }, { "epoch": 83.39, "learning_rate": 1.0158895725555851e-05, "loss": 0.001, "step": 347230 }, { "epoch": 83.39, "learning_rate": 1.0156726959078589e-05, "loss": 0.001, "step": 347240 }, { "epoch": 83.39, "learning_rate": 1.0154558397953873e-05, "loss": 0.001, "step": 347250 }, { "epoch": 83.4, "learning_rate": 1.0152390042192916e-05, "loss": 0.0011, "step": 347260 }, { "epoch": 83.4, "learning_rate": 1.0150221891806855e-05, "loss": 0.0011, "step": 347270 }, { "epoch": 83.4, "learning_rate": 1.0148053946806896e-05, "loss": 0.0011, "step": 347280 }, { "epoch": 83.4, "learning_rate": 1.0145886207204192e-05, "loss": 0.0012, "step": 347290 }, { "epoch": 83.4, "learning_rate": 1.0143718673009933e-05, "loss": 0.0011, "step": 347300 }, { "epoch": 83.41, "learning_rate": 1.0141551344235283e-05, "loss": 0.001, "step": 347310 }, { "epoch": 83.41, "learning_rate": 1.0139384220891396e-05, "loss": 0.0011, "step": 347320 }, { "epoch": 83.41, "learning_rate": 1.013721730298947e-05, "loss": 0.0011, "step": 347330 }, { "epoch": 83.41, "learning_rate": 1.0135050590540646e-05, "loss": 0.0011, "step": 347340 }, { "epoch": 83.42, "learning_rate": 1.0132884083556121e-05, "loss": 0.0011, "step": 347350 }, { "epoch": 83.42, "learning_rate": 1.0130717782047027e-05, "loss": 0.0011, "step": 347360 }, { "epoch": 83.42, "learning_rate": 1.0128551686024562e-05, "loss": 0.0011, "step": 347370 }, { "epoch": 83.42, "learning_rate": 1.012638579549986e-05, "loss": 0.001, "step": 347380 }, { "epoch": 83.43, "learning_rate": 1.0124220110484111e-05, "loss": 0.001, "step": 347390 }, { "epoch": 83.43, "learning_rate": 1.0122054630988453e-05, "loss": 0.001, "step": 347400 }, { "epoch": 83.43, "learning_rate": 1.011988935702406e-05, "loss": 0.0011, "step": 347410 }, { "epoch": 83.43, "learning_rate": 1.0117724288602105e-05, "loss": 0.0011, "step": 347420 }, { "epoch": 83.43, "learning_rate": 1.0115559425733718e-05, "loss": 0.001, "step": 347430 }, { "epoch": 83.44, "learning_rate": 1.011339476843008e-05, "loss": 0.0012, "step": 347440 }, { "epoch": 83.44, "learning_rate": 1.0111230316702342e-05, "loss": 0.001, "step": 347450 }, { "epoch": 83.44, "learning_rate": 1.0109066070561646e-05, "loss": 0.001, "step": 347460 }, { "epoch": 83.44, "learning_rate": 1.0106902030019166e-05, "loss": 0.0011, "step": 347470 }, { "epoch": 83.45, "learning_rate": 1.0104738195086034e-05, "loss": 0.0011, "step": 347480 }, { "epoch": 83.45, "learning_rate": 1.0102574565773432e-05, "loss": 0.0011, "step": 347490 }, { "epoch": 83.45, "learning_rate": 1.0100411142092475e-05, "loss": 0.0011, "step": 347500 }, { "epoch": 83.45, "learning_rate": 1.0098247924054349e-05, "loss": 0.001, "step": 347510 }, { "epoch": 83.45, "learning_rate": 1.009608491167019e-05, "loss": 0.001, "step": 347520 }, { "epoch": 83.46, "learning_rate": 1.0093922104951126e-05, "loss": 0.0011, "step": 347530 }, { "epoch": 83.46, "learning_rate": 1.0091759503908332e-05, "loss": 0.0057, "step": 347540 }, { "epoch": 83.46, "learning_rate": 1.0089597108552928e-05, "loss": 0.001, "step": 347550 }, { "epoch": 83.46, "learning_rate": 1.0087434918896094e-05, "loss": 0.0011, "step": 347560 }, { "epoch": 83.47, "learning_rate": 1.0085272934948936e-05, "loss": 0.0012, "step": 347570 }, { "epoch": 83.47, "learning_rate": 1.0083111156722635e-05, "loss": 0.0011, "step": 347580 }, { "epoch": 83.47, "learning_rate": 1.0080949584228305e-05, "loss": 0.0012, "step": 347590 }, { "epoch": 83.47, "learning_rate": 1.0078788217477086e-05, "loss": 0.0012, "step": 347600 }, { "epoch": 83.48, "learning_rate": 1.0076627056480137e-05, "loss": 0.0011, "step": 347610 }, { "epoch": 83.48, "learning_rate": 1.0074466101248576e-05, "loss": 0.0012, "step": 347620 }, { "epoch": 83.48, "learning_rate": 1.007230535179356e-05, "loss": 0.0011, "step": 347630 }, { "epoch": 83.48, "learning_rate": 1.0070144808126202e-05, "loss": 0.0011, "step": 347640 }, { "epoch": 83.48, "learning_rate": 1.0067984470257668e-05, "loss": 0.0011, "step": 347650 }, { "epoch": 83.49, "learning_rate": 1.0065824338199075e-05, "loss": 0.001, "step": 347660 }, { "epoch": 83.49, "learning_rate": 1.0063664411961543e-05, "loss": 0.0012, "step": 347670 }, { "epoch": 83.49, "learning_rate": 1.0061504691556217e-05, "loss": 0.001, "step": 347680 }, { "epoch": 83.49, "learning_rate": 1.0059345176994245e-05, "loss": 0.0011, "step": 347690 }, { "epoch": 83.5, "learning_rate": 1.0057185868286728e-05, "loss": 0.0009, "step": 347700 }, { "epoch": 83.5, "learning_rate": 1.0055026765444825e-05, "loss": 0.0012, "step": 347710 }, { "epoch": 83.5, "learning_rate": 1.0052867868479631e-05, "loss": 0.0012, "step": 347720 }, { "epoch": 83.5, "learning_rate": 1.00507091774023e-05, "loss": 0.0011, "step": 347730 }, { "epoch": 83.51, "learning_rate": 1.004855069222394e-05, "loss": 0.0012, "step": 347740 }, { "epoch": 83.51, "learning_rate": 1.0046392412955696e-05, "loss": 0.0011, "step": 347750 }, { "epoch": 83.51, "learning_rate": 1.0044234339608666e-05, "loss": 0.0012, "step": 347760 }, { "epoch": 83.51, "learning_rate": 1.0042076472194001e-05, "loss": 0.0012, "step": 347770 }, { "epoch": 83.51, "learning_rate": 1.0039918810722792e-05, "loss": 0.0012, "step": 347780 }, { "epoch": 83.52, "learning_rate": 1.0037761355206188e-05, "loss": 0.0011, "step": 347790 }, { "epoch": 83.52, "learning_rate": 1.00356041056553e-05, "loss": 0.001, "step": 347800 }, { "epoch": 83.52, "learning_rate": 1.0033447062081225e-05, "loss": 0.0012, "step": 347810 }, { "epoch": 83.52, "learning_rate": 1.0031290224495116e-05, "loss": 0.0011, "step": 347820 }, { "epoch": 83.53, "learning_rate": 1.0029133592908052e-05, "loss": 0.0012, "step": 347830 }, { "epoch": 83.53, "learning_rate": 1.0026977167331187e-05, "loss": 0.0012, "step": 347840 }, { "epoch": 83.53, "learning_rate": 1.0024820947775598e-05, "loss": 0.0011, "step": 347850 }, { "epoch": 83.53, "learning_rate": 1.002266493425243e-05, "loss": 0.001, "step": 347860 }, { "epoch": 83.53, "learning_rate": 1.0020509126772782e-05, "loss": 0.0012, "step": 347870 }, { "epoch": 83.54, "learning_rate": 1.001835352534775e-05, "loss": 0.0011, "step": 347880 }, { "epoch": 83.54, "learning_rate": 1.0016198129988475e-05, "loss": 0.0011, "step": 347890 }, { "epoch": 83.54, "learning_rate": 1.001404294070603e-05, "loss": 0.001, "step": 347900 }, { "epoch": 83.54, "learning_rate": 1.0011887957511562e-05, "loss": 0.0011, "step": 347910 }, { "epoch": 83.55, "learning_rate": 1.0009733180416136e-05, "loss": 0.0011, "step": 347920 }, { "epoch": 83.55, "learning_rate": 1.00075786094309e-05, "loss": 0.0013, "step": 347930 }, { "epoch": 83.55, "learning_rate": 1.000542424456692e-05, "loss": 0.0011, "step": 347940 }, { "epoch": 83.55, "learning_rate": 1.0003270085835336e-05, "loss": 0.0011, "step": 347950 }, { "epoch": 83.56, "learning_rate": 1.000111613324723e-05, "loss": 0.0011, "step": 347960 }, { "epoch": 83.56, "learning_rate": 9.998962386813687e-06, "loss": 0.001, "step": 347970 }, { "epoch": 83.56, "learning_rate": 9.996808846545847e-06, "loss": 0.0012, "step": 347980 }, { "epoch": 83.56, "learning_rate": 9.99465551245477e-06, "loss": 0.0011, "step": 347990 }, { "epoch": 83.56, "learning_rate": 9.992502384551577e-06, "loss": 0.001, "step": 348000 }, { "epoch": 83.57, "learning_rate": 9.990349462847377e-06, "loss": 0.0008, "step": 348010 }, { "epoch": 83.57, "learning_rate": 9.988196747353229e-06, "loss": 0.0011, "step": 348020 }, { "epoch": 83.57, "learning_rate": 9.986044238080266e-06, "loss": 0.0011, "step": 348030 }, { "epoch": 83.57, "learning_rate": 9.983891935039552e-06, "loss": 0.0012, "step": 348040 }, { "epoch": 83.58, "learning_rate": 9.98173983824221e-06, "loss": 0.0011, "step": 348050 }, { "epoch": 83.58, "learning_rate": 9.979587947699297e-06, "loss": 0.0011, "step": 348060 }, { "epoch": 83.58, "learning_rate": 9.977436263421941e-06, "loss": 0.0011, "step": 348070 }, { "epoch": 83.58, "learning_rate": 9.975284785421196e-06, "loss": 0.0011, "step": 348080 }, { "epoch": 83.59, "learning_rate": 9.973133513708182e-06, "loss": 0.0011, "step": 348090 }, { "epoch": 83.59, "learning_rate": 9.970982448293975e-06, "loss": 0.001, "step": 348100 }, { "epoch": 83.59, "learning_rate": 9.968831589189642e-06, "loss": 0.0011, "step": 348110 }, { "epoch": 83.59, "learning_rate": 9.966680936406298e-06, "loss": 0.0011, "step": 348120 }, { "epoch": 83.59, "learning_rate": 9.964530489955003e-06, "loss": 0.0011, "step": 348130 }, { "epoch": 83.6, "learning_rate": 9.96238024984687e-06, "loss": 0.0011, "step": 348140 }, { "epoch": 83.6, "learning_rate": 9.960230216092947e-06, "loss": 0.001, "step": 348150 }, { "epoch": 83.6, "learning_rate": 9.958080388704343e-06, "loss": 0.0019, "step": 348160 }, { "epoch": 83.6, "learning_rate": 9.955930767692135e-06, "loss": 0.0009, "step": 348170 }, { "epoch": 83.61, "learning_rate": 9.953781353067375e-06, "loss": 0.0017, "step": 348180 }, { "epoch": 83.61, "learning_rate": 9.951632144841173e-06, "loss": 0.0011, "step": 348190 }, { "epoch": 83.61, "learning_rate": 9.949483143024585e-06, "loss": 0.0011, "step": 348200 }, { "epoch": 83.61, "learning_rate": 9.947334347628707e-06, "loss": 0.0011, "step": 348210 }, { "epoch": 83.61, "learning_rate": 9.945185758664588e-06, "loss": 0.0013, "step": 348220 }, { "epoch": 83.62, "learning_rate": 9.943037376143333e-06, "loss": 0.001, "step": 348230 }, { "epoch": 83.62, "learning_rate": 9.940889200075992e-06, "loss": 0.0012, "step": 348240 }, { "epoch": 83.62, "learning_rate": 9.938741230473635e-06, "loss": 0.0012, "step": 348250 }, { "epoch": 83.62, "learning_rate": 9.936593467347349e-06, "loss": 0.001, "step": 348260 }, { "epoch": 83.63, "learning_rate": 9.93444591070819e-06, "loss": 0.001, "step": 348270 }, { "epoch": 83.63, "learning_rate": 9.932298560567237e-06, "loss": 0.0013, "step": 348280 }, { "epoch": 83.63, "learning_rate": 9.93015141693554e-06, "loss": 0.0012, "step": 348290 }, { "epoch": 83.63, "learning_rate": 9.928004479824183e-06, "loss": 0.0012, "step": 348300 }, { "epoch": 83.64, "learning_rate": 9.925857749244234e-06, "loss": 0.0012, "step": 348310 }, { "epoch": 83.64, "learning_rate": 9.92371122520674e-06, "loss": 0.0011, "step": 348320 }, { "epoch": 83.64, "learning_rate": 9.92156490772278e-06, "loss": 0.0011, "step": 348330 }, { "epoch": 83.64, "learning_rate": 9.919418796803403e-06, "loss": 0.0012, "step": 348340 }, { "epoch": 83.64, "learning_rate": 9.917272892459684e-06, "loss": 0.0011, "step": 348350 }, { "epoch": 83.65, "learning_rate": 9.915127194702668e-06, "loss": 0.0011, "step": 348360 }, { "epoch": 83.65, "learning_rate": 9.912981703543434e-06, "loss": 0.001, "step": 348370 }, { "epoch": 83.65, "learning_rate": 9.910836418993025e-06, "loss": 0.0012, "step": 348380 }, { "epoch": 83.65, "learning_rate": 9.908691341062488e-06, "loss": 0.0011, "step": 348390 }, { "epoch": 83.66, "learning_rate": 9.9065464697629e-06, "loss": 0.0011, "step": 348400 }, { "epoch": 83.66, "learning_rate": 9.904401805105295e-06, "loss": 0.0011, "step": 348410 }, { "epoch": 83.66, "learning_rate": 9.902257347100757e-06, "loss": 0.001, "step": 348420 }, { "epoch": 83.66, "learning_rate": 9.9001130957603e-06, "loss": 0.0011, "step": 348430 }, { "epoch": 83.67, "learning_rate": 9.897969051095012e-06, "loss": 0.0012, "step": 348440 }, { "epoch": 83.67, "learning_rate": 9.895825213115928e-06, "loss": 0.0012, "step": 348450 }, { "epoch": 83.67, "learning_rate": 9.89368158183408e-06, "loss": 0.001, "step": 348460 }, { "epoch": 83.67, "learning_rate": 9.89153815726055e-06, "loss": 0.0011, "step": 348470 }, { "epoch": 83.67, "learning_rate": 9.88939493940635e-06, "loss": 0.0012, "step": 348480 }, { "epoch": 83.68, "learning_rate": 9.887251928282559e-06, "loss": 0.001, "step": 348490 }, { "epoch": 83.68, "learning_rate": 9.885109123900187e-06, "loss": 0.0012, "step": 348500 }, { "epoch": 83.68, "learning_rate": 9.88296652627032e-06, "loss": 0.0011, "step": 348510 }, { "epoch": 83.68, "learning_rate": 9.880824135403976e-06, "loss": 0.0011, "step": 348520 }, { "epoch": 83.69, "learning_rate": 9.878681951312185e-06, "loss": 0.0012, "step": 348530 }, { "epoch": 83.69, "learning_rate": 9.876539974006016e-06, "loss": 0.0011, "step": 348540 }, { "epoch": 83.69, "learning_rate": 9.874398203496487e-06, "loss": 0.0011, "step": 348550 }, { "epoch": 83.69, "learning_rate": 9.872256639794653e-06, "loss": 0.0011, "step": 348560 }, { "epoch": 83.69, "learning_rate": 9.87011528291153e-06, "loss": 0.0011, "step": 348570 }, { "epoch": 83.7, "learning_rate": 9.867974132858182e-06, "loss": 0.0013, "step": 348580 }, { "epoch": 83.7, "learning_rate": 9.865833189645623e-06, "loss": 0.0011, "step": 348590 }, { "epoch": 83.7, "learning_rate": 9.863692453284901e-06, "loss": 0.0009, "step": 348600 }, { "epoch": 83.7, "learning_rate": 9.861551923787038e-06, "loss": 0.0009, "step": 348610 }, { "epoch": 83.71, "learning_rate": 9.859411601163065e-06, "loss": 0.0011, "step": 348620 }, { "epoch": 83.71, "learning_rate": 9.857271485424035e-06, "loss": 0.0012, "step": 348630 }, { "epoch": 83.71, "learning_rate": 9.855131576580951e-06, "loss": 0.0012, "step": 348640 }, { "epoch": 83.71, "learning_rate": 9.852991874644869e-06, "loss": 0.0011, "step": 348650 }, { "epoch": 83.72, "learning_rate": 9.850852379626802e-06, "loss": 0.0011, "step": 348660 }, { "epoch": 83.72, "learning_rate": 9.848713091537765e-06, "loss": 0.0011, "step": 348670 }, { "epoch": 83.72, "learning_rate": 9.846574010388804e-06, "loss": 0.0011, "step": 348680 }, { "epoch": 83.72, "learning_rate": 9.844435136190927e-06, "loss": 0.009, "step": 348690 }, { "epoch": 83.72, "learning_rate": 9.842296468955181e-06, "loss": 0.001, "step": 348700 }, { "epoch": 83.73, "learning_rate": 9.840158008692563e-06, "loss": 0.0011, "step": 348710 }, { "epoch": 83.73, "learning_rate": 9.838019755414113e-06, "loss": 0.0011, "step": 348720 }, { "epoch": 83.73, "learning_rate": 9.835881709130835e-06, "loss": 0.0012, "step": 348730 }, { "epoch": 83.73, "learning_rate": 9.833743869853773e-06, "loss": 0.0011, "step": 348740 }, { "epoch": 83.74, "learning_rate": 9.831606237593932e-06, "loss": 0.0011, "step": 348750 }, { "epoch": 83.74, "learning_rate": 9.829468812362314e-06, "loss": 0.0011, "step": 348760 }, { "epoch": 83.74, "learning_rate": 9.827331594169958e-06, "loss": 0.0011, "step": 348770 }, { "epoch": 83.74, "learning_rate": 9.825194583027864e-06, "loss": 0.0012, "step": 348780 }, { "epoch": 83.75, "learning_rate": 9.823057778947065e-06, "loss": 0.001, "step": 348790 }, { "epoch": 83.75, "learning_rate": 9.820921181938547e-06, "loss": 0.0011, "step": 348800 }, { "epoch": 83.75, "learning_rate": 9.818784792013347e-06, "loss": 0.0011, "step": 348810 }, { "epoch": 83.75, "learning_rate": 9.816648609182472e-06, "loss": 0.0012, "step": 348820 }, { "epoch": 83.75, "learning_rate": 9.814512633456907e-06, "loss": 0.0012, "step": 348830 }, { "epoch": 83.76, "learning_rate": 9.8123768648477e-06, "loss": 0.0011, "step": 348840 }, { "epoch": 83.76, "learning_rate": 9.81024130336582e-06, "loss": 0.001, "step": 348850 }, { "epoch": 83.76, "learning_rate": 9.808105949022306e-06, "loss": 0.0011, "step": 348860 }, { "epoch": 83.76, "learning_rate": 9.80597080182814e-06, "loss": 0.0011, "step": 348870 }, { "epoch": 83.77, "learning_rate": 9.803835861794348e-06, "loss": 0.0011, "step": 348880 }, { "epoch": 83.77, "learning_rate": 9.801701128931907e-06, "loss": 0.0012, "step": 348890 }, { "epoch": 83.77, "learning_rate": 9.799566603251848e-06, "loss": 0.001, "step": 348900 }, { "epoch": 83.77, "learning_rate": 9.797432284765146e-06, "loss": 0.0012, "step": 348910 }, { "epoch": 83.77, "learning_rate": 9.795298173482831e-06, "loss": 0.001, "step": 348920 }, { "epoch": 83.78, "learning_rate": 9.793164269415867e-06, "loss": 0.0011, "step": 348930 }, { "epoch": 83.78, "learning_rate": 9.791030572575272e-06, "loss": 0.001, "step": 348940 }, { "epoch": 83.78, "learning_rate": 9.788897082972053e-06, "loss": 0.0011, "step": 348950 }, { "epoch": 83.78, "learning_rate": 9.7867638006172e-06, "loss": 0.001, "step": 348960 }, { "epoch": 83.79, "learning_rate": 9.784630725521687e-06, "loss": 0.0009, "step": 348970 }, { "epoch": 83.79, "learning_rate": 9.782497857696531e-06, "loss": 0.0011, "step": 348980 }, { "epoch": 83.79, "learning_rate": 9.780365197152714e-06, "loss": 0.0012, "step": 348990 }, { "epoch": 83.79, "learning_rate": 9.778232743901233e-06, "loss": 0.0013, "step": 349000 }, { "epoch": 83.8, "learning_rate": 9.776100497953073e-06, "loss": 0.0011, "step": 349010 }, { "epoch": 83.8, "learning_rate": 9.773968459319232e-06, "loss": 0.001, "step": 349020 }, { "epoch": 83.8, "learning_rate": 9.7718366280107e-06, "loss": 0.001, "step": 349030 }, { "epoch": 83.8, "learning_rate": 9.769705004038442e-06, "loss": 0.0012, "step": 349040 }, { "epoch": 83.8, "learning_rate": 9.767573587413475e-06, "loss": 0.0011, "step": 349050 }, { "epoch": 83.81, "learning_rate": 9.765442378146761e-06, "loss": 0.0012, "step": 349060 }, { "epoch": 83.81, "learning_rate": 9.763311376249301e-06, "loss": 0.0011, "step": 349070 }, { "epoch": 83.81, "learning_rate": 9.76118058173206e-06, "loss": 0.001, "step": 349080 }, { "epoch": 83.81, "learning_rate": 9.75904999460604e-06, "loss": 0.0011, "step": 349090 }, { "epoch": 83.82, "learning_rate": 9.756919614882214e-06, "loss": 0.0011, "step": 349100 }, { "epoch": 83.82, "learning_rate": 9.754789442571549e-06, "loss": 0.0013, "step": 349110 }, { "epoch": 83.82, "learning_rate": 9.75265947768505e-06, "loss": 0.0013, "step": 349120 }, { "epoch": 83.82, "learning_rate": 9.75052972023367e-06, "loss": 0.0011, "step": 349130 }, { "epoch": 83.83, "learning_rate": 9.748400170228401e-06, "loss": 0.001, "step": 349140 }, { "epoch": 83.83, "learning_rate": 9.746270827680204e-06, "loss": 0.001, "step": 349150 }, { "epoch": 83.83, "learning_rate": 9.744141692600078e-06, "loss": 0.0011, "step": 349160 }, { "epoch": 83.83, "learning_rate": 9.742012764998987e-06, "loss": 0.001, "step": 349170 }, { "epoch": 83.83, "learning_rate": 9.739884044887875e-06, "loss": 0.0011, "step": 349180 }, { "epoch": 83.84, "learning_rate": 9.737755532277747e-06, "loss": 0.0011, "step": 349190 }, { "epoch": 83.84, "learning_rate": 9.735627227179572e-06, "loss": 0.0011, "step": 349200 }, { "epoch": 83.84, "learning_rate": 9.733499129604296e-06, "loss": 0.0013, "step": 349210 }, { "epoch": 83.84, "learning_rate": 9.73137123956292e-06, "loss": 0.0012, "step": 349220 }, { "epoch": 83.85, "learning_rate": 9.729243557066375e-06, "loss": 0.0011, "step": 349230 }, { "epoch": 83.85, "learning_rate": 9.727116082125664e-06, "loss": 0.001, "step": 349240 }, { "epoch": 83.85, "learning_rate": 9.724988814751718e-06, "loss": 0.0011, "step": 349250 }, { "epoch": 83.85, "learning_rate": 9.722861754955526e-06, "loss": 0.001, "step": 349260 }, { "epoch": 83.85, "learning_rate": 9.72073490274803e-06, "loss": 0.0011, "step": 349270 }, { "epoch": 83.86, "learning_rate": 9.718608258140217e-06, "loss": 0.001, "step": 349280 }, { "epoch": 83.86, "learning_rate": 9.71648182114302e-06, "loss": 0.0012, "step": 349290 }, { "epoch": 83.86, "learning_rate": 9.714355591767427e-06, "loss": 0.0012, "step": 349300 }, { "epoch": 83.86, "learning_rate": 9.712229570024384e-06, "loss": 0.0012, "step": 349310 }, { "epoch": 83.87, "learning_rate": 9.710103755924827e-06, "loss": 0.0011, "step": 349320 }, { "epoch": 83.87, "learning_rate": 9.707978149479752e-06, "loss": 0.0011, "step": 349330 }, { "epoch": 83.87, "learning_rate": 9.705852750700073e-06, "loss": 0.0011, "step": 349340 }, { "epoch": 83.87, "learning_rate": 9.703727559596788e-06, "loss": 0.001, "step": 349350 }, { "epoch": 83.88, "learning_rate": 9.701602576180807e-06, "loss": 0.0012, "step": 349360 }, { "epoch": 83.88, "learning_rate": 9.69947780046312e-06, "loss": 0.0011, "step": 349370 }, { "epoch": 83.88, "learning_rate": 9.69735323245466e-06, "loss": 0.0011, "step": 349380 }, { "epoch": 83.88, "learning_rate": 9.695228872166368e-06, "loss": 0.0011, "step": 349390 }, { "epoch": 83.88, "learning_rate": 9.693104719609213e-06, "loss": 0.0012, "step": 349400 }, { "epoch": 83.89, "learning_rate": 9.690980774794123e-06, "loss": 0.001, "step": 349410 }, { "epoch": 83.89, "learning_rate": 9.688857037732069e-06, "loss": 0.0011, "step": 349420 }, { "epoch": 83.89, "learning_rate": 9.686733508433965e-06, "loss": 0.0012, "step": 349430 }, { "epoch": 83.89, "learning_rate": 9.684610186910792e-06, "loss": 0.0011, "step": 349440 }, { "epoch": 83.9, "learning_rate": 9.682487073173469e-06, "loss": 0.0012, "step": 349450 }, { "epoch": 83.9, "learning_rate": 9.680364167232936e-06, "loss": 0.001, "step": 349460 }, { "epoch": 83.9, "learning_rate": 9.678241469100152e-06, "loss": 0.0012, "step": 349470 }, { "epoch": 83.9, "learning_rate": 9.676118978786042e-06, "loss": 0.0012, "step": 349480 }, { "epoch": 83.91, "learning_rate": 9.673996696301562e-06, "loss": 0.0011, "step": 349490 }, { "epoch": 83.91, "learning_rate": 9.671874621657623e-06, "loss": 0.0012, "step": 349500 }, { "epoch": 83.91, "learning_rate": 9.669752754865185e-06, "loss": 0.0011, "step": 349510 }, { "epoch": 83.91, "learning_rate": 9.667631095935187e-06, "loss": 0.0011, "step": 349520 }, { "epoch": 83.91, "learning_rate": 9.665509644878545e-06, "loss": 0.0012, "step": 349530 }, { "epoch": 83.92, "learning_rate": 9.663388401706219e-06, "loss": 0.0011, "step": 349540 }, { "epoch": 83.92, "learning_rate": 9.661267366429106e-06, "loss": 0.001, "step": 349550 }, { "epoch": 83.92, "learning_rate": 9.659146539058178e-06, "loss": 0.0012, "step": 349560 }, { "epoch": 83.92, "learning_rate": 9.657025919604329e-06, "loss": 0.0012, "step": 349570 }, { "epoch": 83.93, "learning_rate": 9.65490550807852e-06, "loss": 0.0011, "step": 349580 }, { "epoch": 83.93, "learning_rate": 9.652785304491652e-06, "loss": 0.0011, "step": 349590 }, { "epoch": 83.93, "learning_rate": 9.650665308854679e-06, "loss": 0.0011, "step": 349600 }, { "epoch": 83.93, "learning_rate": 9.648545521178514e-06, "loss": 0.0011, "step": 349610 }, { "epoch": 83.93, "learning_rate": 9.64642594147407e-06, "loss": 0.0012, "step": 349620 }, { "epoch": 83.94, "learning_rate": 9.644306569752299e-06, "loss": 0.0011, "step": 349630 }, { "epoch": 83.94, "learning_rate": 9.642187406024095e-06, "loss": 0.001, "step": 349640 }, { "epoch": 83.94, "learning_rate": 9.640068450300404e-06, "loss": 0.0011, "step": 349650 }, { "epoch": 83.94, "learning_rate": 9.63794970259213e-06, "loss": 0.0011, "step": 349660 }, { "epoch": 83.95, "learning_rate": 9.635831162910208e-06, "loss": 0.0011, "step": 349670 }, { "epoch": 83.95, "learning_rate": 9.633712831265551e-06, "loss": 0.0011, "step": 349680 }, { "epoch": 83.95, "learning_rate": 9.631594707669068e-06, "loss": 0.0012, "step": 349690 }, { "epoch": 84.0, "learning_rate": 9.629476792131691e-06, "loss": 0.001, "step": 349700 }, { "epoch": 84.0, "learning_rate": 9.627359084664318e-06, "loss": 0.0011, "step": 349710 }, { "epoch": 84.01, "learning_rate": 9.625241585277884e-06, "loss": 0.0012, "step": 349720 }, { "epoch": 84.01, "learning_rate": 9.623124293983283e-06, "loss": 0.001, "step": 349730 }, { "epoch": 84.01, "learning_rate": 9.621007210791444e-06, "loss": 0.0011, "step": 349740 }, { "epoch": 84.01, "learning_rate": 9.618890335713277e-06, "loss": 0.001, "step": 349750 }, { "epoch": 84.02, "learning_rate": 9.616773668759671e-06, "loss": 0.001, "step": 349760 }, { "epoch": 84.02, "learning_rate": 9.614657209941563e-06, "loss": 0.0012, "step": 349770 }, { "epoch": 84.02, "learning_rate": 9.612540959269838e-06, "loss": 0.0011, "step": 349780 }, { "epoch": 84.02, "learning_rate": 9.610424916755429e-06, "loss": 0.001, "step": 349790 }, { "epoch": 84.02, "learning_rate": 9.608309082409211e-06, "loss": 0.0011, "step": 349800 }, { "epoch": 84.03, "learning_rate": 9.606193456242107e-06, "loss": 0.001, "step": 349810 }, { "epoch": 84.03, "learning_rate": 9.604078038265035e-06, "loss": 0.0011, "step": 349820 }, { "epoch": 84.03, "learning_rate": 9.601962828488863e-06, "loss": 0.0011, "step": 349830 }, { "epoch": 84.03, "learning_rate": 9.59984782692453e-06, "loss": 0.001, "step": 349840 }, { "epoch": 84.04, "learning_rate": 9.597733033582906e-06, "loss": 0.0012, "step": 349850 }, { "epoch": 84.04, "learning_rate": 9.595618448474919e-06, "loss": 0.0011, "step": 349860 }, { "epoch": 84.04, "learning_rate": 9.593504071611436e-06, "loss": 0.001, "step": 349870 }, { "epoch": 84.04, "learning_rate": 9.591389903003384e-06, "loss": 0.0012, "step": 349880 }, { "epoch": 84.05, "learning_rate": 9.589275942661647e-06, "loss": 0.001, "step": 349890 }, { "epoch": 84.05, "learning_rate": 9.587162190597104e-06, "loss": 0.001, "step": 349900 }, { "epoch": 84.05, "learning_rate": 9.585048646820683e-06, "loss": 0.0011, "step": 349910 }, { "epoch": 84.05, "learning_rate": 9.582935311343245e-06, "loss": 0.0011, "step": 349920 }, { "epoch": 84.05, "learning_rate": 9.580822184175703e-06, "loss": 0.001, "step": 349930 }, { "epoch": 84.06, "learning_rate": 9.578709265328934e-06, "loss": 0.001, "step": 349940 }, { "epoch": 84.06, "learning_rate": 9.57659655481385e-06, "loss": 0.001, "step": 349950 }, { "epoch": 84.06, "learning_rate": 9.57448405264132e-06, "loss": 0.001, "step": 349960 }, { "epoch": 84.06, "learning_rate": 9.572371758822224e-06, "loss": 0.0012, "step": 349970 }, { "epoch": 84.07, "learning_rate": 9.570259673367476e-06, "loss": 0.001, "step": 349980 }, { "epoch": 84.07, "learning_rate": 9.568147796287941e-06, "loss": 0.0011, "step": 349990 }, { "epoch": 84.07, "learning_rate": 9.566036127594514e-06, "loss": 0.001, "step": 350000 }, { "epoch": 84.07, "learning_rate": 9.563924667298069e-06, "loss": 0.0011, "step": 350010 }, { "epoch": 84.07, "learning_rate": 9.561813415409504e-06, "loss": 0.001, "step": 350020 }, { "epoch": 84.08, "learning_rate": 9.559702371939689e-06, "loss": 0.001, "step": 350030 }, { "epoch": 84.08, "learning_rate": 9.557591536899496e-06, "loss": 0.001, "step": 350040 }, { "epoch": 84.08, "learning_rate": 9.555480910299824e-06, "loss": 0.0012, "step": 350050 }, { "epoch": 84.08, "learning_rate": 9.553370492151532e-06, "loss": 0.001, "step": 350060 }, { "epoch": 84.09, "learning_rate": 9.551260282465518e-06, "loss": 0.0011, "step": 350070 }, { "epoch": 84.09, "learning_rate": 9.549150281252633e-06, "loss": 0.0013, "step": 350080 }, { "epoch": 84.09, "learning_rate": 9.547040488523779e-06, "loss": 0.001, "step": 350090 }, { "epoch": 84.09, "learning_rate": 9.5449309042898e-06, "loss": 0.001, "step": 350100 }, { "epoch": 84.1, "learning_rate": 9.542821528561607e-06, "loss": 0.001, "step": 350110 }, { "epoch": 84.1, "learning_rate": 9.54071236135003e-06, "loss": 0.001, "step": 350120 }, { "epoch": 84.1, "learning_rate": 9.538603402665963e-06, "loss": 0.0011, "step": 350130 }, { "epoch": 84.1, "learning_rate": 9.536494652520284e-06, "loss": 0.0009, "step": 350140 }, { "epoch": 84.1, "learning_rate": 9.534386110923838e-06, "loss": 0.001, "step": 350150 }, { "epoch": 84.11, "learning_rate": 9.53227777788751e-06, "loss": 0.0011, "step": 350160 }, { "epoch": 84.11, "learning_rate": 9.530169653422172e-06, "loss": 0.001, "step": 350170 }, { "epoch": 84.11, "learning_rate": 9.528061737538658e-06, "loss": 0.0009, "step": 350180 }, { "epoch": 84.11, "learning_rate": 9.525954030247864e-06, "loss": 0.0011, "step": 350190 }, { "epoch": 84.12, "learning_rate": 9.523846531560631e-06, "loss": 0.0012, "step": 350200 }, { "epoch": 84.12, "learning_rate": 9.521739241487842e-06, "loss": 0.0011, "step": 350210 }, { "epoch": 84.12, "learning_rate": 9.519632160040337e-06, "loss": 0.0011, "step": 350220 }, { "epoch": 84.12, "learning_rate": 9.517525287229001e-06, "loss": 0.0011, "step": 350230 }, { "epoch": 84.13, "learning_rate": 9.515418623064676e-06, "loss": 0.0012, "step": 350240 }, { "epoch": 84.13, "learning_rate": 9.513312167558208e-06, "loss": 0.001, "step": 350250 }, { "epoch": 84.13, "learning_rate": 9.511205920720479e-06, "loss": 0.0011, "step": 350260 }, { "epoch": 84.13, "learning_rate": 9.509099882562323e-06, "loss": 0.0011, "step": 350270 }, { "epoch": 84.13, "learning_rate": 9.506994053094615e-06, "loss": 0.0011, "step": 350280 }, { "epoch": 84.14, "learning_rate": 9.504888432328191e-06, "loss": 0.0011, "step": 350290 }, { "epoch": 84.14, "learning_rate": 9.502783020273915e-06, "loss": 0.001, "step": 350300 }, { "epoch": 84.14, "learning_rate": 9.500677816942638e-06, "loss": 0.001, "step": 350310 }, { "epoch": 84.14, "learning_rate": 9.498572822345197e-06, "loss": 0.0011, "step": 350320 }, { "epoch": 84.15, "learning_rate": 9.496468036492457e-06, "loss": 0.001, "step": 350330 }, { "epoch": 84.15, "learning_rate": 9.49436345939525e-06, "loss": 0.001, "step": 350340 }, { "epoch": 84.15, "learning_rate": 9.492259091064443e-06, "loss": 0.001, "step": 350350 }, { "epoch": 84.15, "learning_rate": 9.490154931510859e-06, "loss": 0.001, "step": 350360 }, { "epoch": 84.15, "learning_rate": 9.488050980745366e-06, "loss": 0.0011, "step": 350370 }, { "epoch": 84.16, "learning_rate": 9.485947238778786e-06, "loss": 0.0011, "step": 350380 }, { "epoch": 84.16, "learning_rate": 9.483843705621986e-06, "loss": 0.0011, "step": 350390 }, { "epoch": 84.16, "learning_rate": 9.481740381285781e-06, "loss": 0.0012, "step": 350400 }, { "epoch": 84.16, "learning_rate": 9.479637265781039e-06, "loss": 0.0009, "step": 350410 }, { "epoch": 84.17, "learning_rate": 9.477534359118573e-06, "loss": 0.0012, "step": 350420 }, { "epoch": 84.17, "learning_rate": 9.475431661309243e-06, "loss": 0.001, "step": 350430 }, { "epoch": 84.17, "learning_rate": 9.473329172363865e-06, "loss": 0.0011, "step": 350440 }, { "epoch": 84.17, "learning_rate": 9.471226892293288e-06, "loss": 0.0009, "step": 350450 }, { "epoch": 84.18, "learning_rate": 9.46912482110836e-06, "loss": 0.0011, "step": 350460 }, { "epoch": 84.18, "learning_rate": 9.467022958819898e-06, "loss": 0.0012, "step": 350470 }, { "epoch": 84.18, "learning_rate": 9.46492130543873e-06, "loss": 0.0011, "step": 350480 }, { "epoch": 84.18, "learning_rate": 9.462819860975708e-06, "loss": 0.0011, "step": 350490 }, { "epoch": 84.18, "learning_rate": 9.460718625441639e-06, "loss": 0.0012, "step": 350500 }, { "epoch": 84.19, "learning_rate": 9.458617598847375e-06, "loss": 0.0011, "step": 350510 }, { "epoch": 84.19, "learning_rate": 9.456516781203722e-06, "loss": 0.001, "step": 350520 }, { "epoch": 84.19, "learning_rate": 9.454416172521535e-06, "loss": 0.0011, "step": 350530 }, { "epoch": 84.19, "learning_rate": 9.452315772811626e-06, "loss": 0.0011, "step": 350540 }, { "epoch": 84.2, "learning_rate": 9.45021558208481e-06, "loss": 0.0011, "step": 350550 }, { "epoch": 84.2, "learning_rate": 9.448115600351931e-06, "loss": 0.0012, "step": 350560 }, { "epoch": 84.2, "learning_rate": 9.446015827623789e-06, "loss": 0.001, "step": 350570 }, { "epoch": 84.2, "learning_rate": 9.44391626391124e-06, "loss": 0.001, "step": 350580 }, { "epoch": 84.21, "learning_rate": 9.441816909225064e-06, "loss": 0.0012, "step": 350590 }, { "epoch": 84.21, "learning_rate": 9.439717763576123e-06, "loss": 0.001, "step": 350600 }, { "epoch": 84.21, "learning_rate": 9.437618826975214e-06, "loss": 0.0011, "step": 350610 }, { "epoch": 84.21, "learning_rate": 9.435520099433143e-06, "loss": 0.001, "step": 350620 }, { "epoch": 84.21, "learning_rate": 9.43342158096075e-06, "loss": 0.0012, "step": 350630 }, { "epoch": 84.22, "learning_rate": 9.431323271568831e-06, "loss": 0.001, "step": 350640 }, { "epoch": 84.22, "learning_rate": 9.429225171268225e-06, "loss": 0.001, "step": 350650 }, { "epoch": 84.22, "learning_rate": 9.427127280069715e-06, "loss": 0.0011, "step": 350660 }, { "epoch": 84.22, "learning_rate": 9.425029597984147e-06, "loss": 0.0012, "step": 350670 }, { "epoch": 84.23, "learning_rate": 9.422932125022315e-06, "loss": 0.0011, "step": 350680 }, { "epoch": 84.23, "learning_rate": 9.420834861195016e-06, "loss": 0.001, "step": 350690 }, { "epoch": 84.23, "learning_rate": 9.418737806513073e-06, "loss": 0.001, "step": 350700 }, { "epoch": 84.23, "learning_rate": 9.41664096098731e-06, "loss": 0.0011, "step": 350710 }, { "epoch": 84.23, "learning_rate": 9.414544324628504e-06, "loss": 0.0012, "step": 350720 }, { "epoch": 84.24, "learning_rate": 9.412447897447484e-06, "loss": 0.0011, "step": 350730 }, { "epoch": 84.24, "learning_rate": 9.410351679455042e-06, "loss": 0.0011, "step": 350740 }, { "epoch": 84.24, "learning_rate": 9.408255670661997e-06, "loss": 0.0011, "step": 350750 }, { "epoch": 84.24, "learning_rate": 9.40615987107913e-06, "loss": 0.001, "step": 350760 }, { "epoch": 84.25, "learning_rate": 9.404064280717261e-06, "loss": 0.0009, "step": 350770 }, { "epoch": 84.25, "learning_rate": 9.401968899587178e-06, "loss": 0.001, "step": 350780 }, { "epoch": 84.25, "learning_rate": 9.399873727699692e-06, "loss": 0.0011, "step": 350790 }, { "epoch": 84.25, "learning_rate": 9.39777876506559e-06, "loss": 0.0011, "step": 350800 }, { "epoch": 84.26, "learning_rate": 9.395684011695689e-06, "loss": 0.0011, "step": 350810 }, { "epoch": 84.26, "learning_rate": 9.393589467600767e-06, "loss": 0.0011, "step": 350820 }, { "epoch": 84.26, "learning_rate": 9.391495132791616e-06, "loss": 0.001, "step": 350830 }, { "epoch": 84.26, "learning_rate": 9.389401007279047e-06, "loss": 0.0009, "step": 350840 }, { "epoch": 84.26, "learning_rate": 9.387307091073833e-06, "loss": 0.001, "step": 350850 }, { "epoch": 84.27, "learning_rate": 9.385213384186793e-06, "loss": 0.001, "step": 350860 }, { "epoch": 84.27, "learning_rate": 9.383119886628689e-06, "loss": 0.0011, "step": 350870 }, { "epoch": 84.27, "learning_rate": 9.381026598410336e-06, "loss": 0.0009, "step": 350880 }, { "epoch": 84.27, "learning_rate": 9.378933519542515e-06, "loss": 0.0011, "step": 350890 }, { "epoch": 84.28, "learning_rate": 9.376840650035995e-06, "loss": 0.0011, "step": 350900 }, { "epoch": 84.28, "learning_rate": 9.374747989901588e-06, "loss": 0.0011, "step": 350910 }, { "epoch": 84.28, "learning_rate": 9.37265553915006e-06, "loss": 0.001, "step": 350920 }, { "epoch": 84.28, "learning_rate": 9.370563297792217e-06, "loss": 0.0011, "step": 350930 }, { "epoch": 84.29, "learning_rate": 9.368471265838818e-06, "loss": 0.0011, "step": 350940 }, { "epoch": 84.29, "learning_rate": 9.366379443300671e-06, "loss": 0.0011, "step": 350950 }, { "epoch": 84.29, "learning_rate": 9.364287830188539e-06, "loss": 0.0011, "step": 350960 }, { "epoch": 84.29, "learning_rate": 9.362196426513197e-06, "loss": 0.0011, "step": 350970 }, { "epoch": 84.29, "learning_rate": 9.360105232285449e-06, "loss": 0.0011, "step": 350980 }, { "epoch": 84.3, "learning_rate": 9.358014247516045e-06, "loss": 0.0012, "step": 350990 }, { "epoch": 84.3, "learning_rate": 9.355923472215789e-06, "loss": 0.001, "step": 351000 }, { "epoch": 84.3, "learning_rate": 9.353832906395433e-06, "loss": 0.001, "step": 351010 }, { "epoch": 84.3, "learning_rate": 9.351742550065756e-06, "loss": 0.001, "step": 351020 }, { "epoch": 84.31, "learning_rate": 9.349652403237553e-06, "loss": 0.0052, "step": 351030 }, { "epoch": 84.31, "learning_rate": 9.347562465921567e-06, "loss": 0.001, "step": 351040 }, { "epoch": 84.31, "learning_rate": 9.345472738128597e-06, "loss": 0.001, "step": 351050 }, { "epoch": 84.31, "learning_rate": 9.34338321986939e-06, "loss": 0.001, "step": 351060 }, { "epoch": 84.31, "learning_rate": 9.341293911154736e-06, "loss": 0.001, "step": 351070 }, { "epoch": 84.32, "learning_rate": 9.339204811995383e-06, "loss": 0.001, "step": 351080 }, { "epoch": 84.32, "learning_rate": 9.337115922402117e-06, "loss": 0.0011, "step": 351090 }, { "epoch": 84.32, "learning_rate": 9.335027242385701e-06, "loss": 0.0012, "step": 351100 }, { "epoch": 84.32, "learning_rate": 9.332938771956879e-06, "loss": 0.0011, "step": 351110 }, { "epoch": 84.33, "learning_rate": 9.330850511126444e-06, "loss": 0.0011, "step": 351120 }, { "epoch": 84.33, "learning_rate": 9.328762459905127e-06, "loss": 0.0011, "step": 351130 }, { "epoch": 84.33, "learning_rate": 9.326674618303727e-06, "loss": 0.001, "step": 351140 }, { "epoch": 84.33, "learning_rate": 9.324586986332973e-06, "loss": 0.001, "step": 351150 }, { "epoch": 84.34, "learning_rate": 9.322499564003645e-06, "loss": 0.001, "step": 351160 }, { "epoch": 84.34, "learning_rate": 9.320412351326486e-06, "loss": 0.0012, "step": 351170 }, { "epoch": 84.34, "learning_rate": 9.318325348312274e-06, "loss": 0.0011, "step": 351180 }, { "epoch": 84.34, "learning_rate": 9.316238554971757e-06, "loss": 0.001, "step": 351190 }, { "epoch": 84.34, "learning_rate": 9.314151971315666e-06, "loss": 0.0011, "step": 351200 }, { "epoch": 84.35, "learning_rate": 9.312065597354796e-06, "loss": 0.001, "step": 351210 }, { "epoch": 84.35, "learning_rate": 9.309979433099864e-06, "loss": 0.0066, "step": 351220 }, { "epoch": 84.35, "learning_rate": 9.307893478561647e-06, "loss": 0.001, "step": 351230 }, { "epoch": 84.35, "learning_rate": 9.305807733750882e-06, "loss": 0.0009, "step": 351240 }, { "epoch": 84.36, "learning_rate": 9.303722198678333e-06, "loss": 0.0011, "step": 351250 }, { "epoch": 84.36, "learning_rate": 9.301636873354741e-06, "loss": 0.001, "step": 351260 }, { "epoch": 84.36, "learning_rate": 9.299551757790836e-06, "loss": 0.001, "step": 351270 }, { "epoch": 84.36, "learning_rate": 9.2974668519974e-06, "loss": 0.0035, "step": 351280 }, { "epoch": 84.37, "learning_rate": 9.295382155985144e-06, "loss": 0.0011, "step": 351290 }, { "epoch": 84.37, "learning_rate": 9.293297669764838e-06, "loss": 0.0011, "step": 351300 }, { "epoch": 84.37, "learning_rate": 9.291213393347209e-06, "loss": 0.001, "step": 351310 }, { "epoch": 84.37, "learning_rate": 9.289129326743019e-06, "loss": 0.0011, "step": 351320 }, { "epoch": 84.37, "learning_rate": 9.287045469962979e-06, "loss": 0.001, "step": 351330 }, { "epoch": 84.38, "learning_rate": 9.284961823017852e-06, "loss": 0.001, "step": 351340 }, { "epoch": 84.38, "learning_rate": 9.28287838591838e-06, "loss": 0.001, "step": 351350 }, { "epoch": 84.38, "learning_rate": 9.280795158675287e-06, "loss": 0.0011, "step": 351360 }, { "epoch": 84.38, "learning_rate": 9.278712141299323e-06, "loss": 0.001, "step": 351370 }, { "epoch": 84.39, "learning_rate": 9.276629333801207e-06, "loss": 0.001, "step": 351380 }, { "epoch": 84.39, "learning_rate": 9.274546736191696e-06, "loss": 0.001, "step": 351390 }, { "epoch": 84.39, "learning_rate": 9.272464348481512e-06, "loss": 0.0011, "step": 351400 }, { "epoch": 84.39, "learning_rate": 9.270382170681375e-06, "loss": 0.001, "step": 351410 }, { "epoch": 84.39, "learning_rate": 9.268300202802038e-06, "loss": 0.0011, "step": 351420 }, { "epoch": 84.4, "learning_rate": 9.266218444854213e-06, "loss": 0.0011, "step": 351430 }, { "epoch": 84.4, "learning_rate": 9.264136896848652e-06, "loss": 0.0011, "step": 351440 }, { "epoch": 84.4, "learning_rate": 9.262055558796057e-06, "loss": 0.0011, "step": 351450 }, { "epoch": 84.4, "learning_rate": 9.25997443070718e-06, "loss": 0.0011, "step": 351460 }, { "epoch": 84.41, "learning_rate": 9.257893512592736e-06, "loss": 0.0011, "step": 351470 }, { "epoch": 84.41, "learning_rate": 9.255812804463431e-06, "loss": 0.0011, "step": 351480 }, { "epoch": 84.41, "learning_rate": 9.253732306330026e-06, "loss": 0.0011, "step": 351490 }, { "epoch": 84.41, "learning_rate": 9.251652018203211e-06, "loss": 0.0011, "step": 351500 }, { "epoch": 84.42, "learning_rate": 9.249571940093738e-06, "loss": 0.0011, "step": 351510 }, { "epoch": 84.42, "learning_rate": 9.247492072012292e-06, "loss": 0.0009, "step": 351520 }, { "epoch": 84.42, "learning_rate": 9.245412413969634e-06, "loss": 0.0011, "step": 351530 }, { "epoch": 84.42, "learning_rate": 9.243332965976454e-06, "loss": 0.0011, "step": 351540 }, { "epoch": 84.42, "learning_rate": 9.241253728043464e-06, "loss": 0.0011, "step": 351550 }, { "epoch": 84.43, "learning_rate": 9.239174700181407e-06, "loss": 0.0009, "step": 351560 }, { "epoch": 84.43, "learning_rate": 9.237095882400975e-06, "loss": 0.001, "step": 351570 }, { "epoch": 84.43, "learning_rate": 9.235017274712904e-06, "loss": 0.001, "step": 351580 }, { "epoch": 84.43, "learning_rate": 9.232938877127879e-06, "loss": 0.001, "step": 351590 }, { "epoch": 84.44, "learning_rate": 9.23086068965664e-06, "loss": 0.001, "step": 351600 }, { "epoch": 84.44, "learning_rate": 9.228782712309875e-06, "loss": 0.0011, "step": 351610 }, { "epoch": 84.44, "learning_rate": 9.226704945098319e-06, "loss": 0.0011, "step": 351620 }, { "epoch": 84.44, "learning_rate": 9.224627388032648e-06, "loss": 0.0012, "step": 351630 }, { "epoch": 84.45, "learning_rate": 9.222550041123596e-06, "loss": 0.001, "step": 351640 }, { "epoch": 84.45, "learning_rate": 9.220472904381866e-06, "loss": 0.001, "step": 351650 }, { "epoch": 84.45, "learning_rate": 9.21839597781815e-06, "loss": 0.0009, "step": 351660 }, { "epoch": 84.45, "learning_rate": 9.216319261443179e-06, "loss": 0.0011, "step": 351670 }, { "epoch": 84.45, "learning_rate": 9.214242755267638e-06, "loss": 0.0011, "step": 351680 }, { "epoch": 84.46, "learning_rate": 9.212166459302213e-06, "loss": 0.0011, "step": 351690 }, { "epoch": 84.46, "learning_rate": 9.21009037355764e-06, "loss": 0.0012, "step": 351700 }, { "epoch": 84.46, "learning_rate": 9.208014498044593e-06, "loss": 0.001, "step": 351710 }, { "epoch": 84.46, "learning_rate": 9.205938832773786e-06, "loss": 0.001, "step": 351720 }, { "epoch": 84.47, "learning_rate": 9.2038633777559e-06, "loss": 0.001, "step": 351730 }, { "epoch": 84.47, "learning_rate": 9.20178813300166e-06, "loss": 0.001, "step": 351740 }, { "epoch": 84.47, "learning_rate": 9.19971309852174e-06, "loss": 0.001, "step": 351750 }, { "epoch": 84.47, "learning_rate": 9.197638274326831e-06, "loss": 0.0011, "step": 351760 }, { "epoch": 84.47, "learning_rate": 9.195563660427641e-06, "loss": 0.001, "step": 351770 }, { "epoch": 84.48, "learning_rate": 9.193489256834853e-06, "loss": 0.0011, "step": 351780 }, { "epoch": 84.48, "learning_rate": 9.191415063559173e-06, "loss": 0.001, "step": 351790 }, { "epoch": 84.48, "learning_rate": 9.189341080611264e-06, "loss": 0.0009, "step": 351800 }, { "epoch": 84.48, "learning_rate": 9.187267308001851e-06, "loss": 0.0016, "step": 351810 }, { "epoch": 84.49, "learning_rate": 9.185193745741599e-06, "loss": 0.0011, "step": 351820 }, { "epoch": 84.49, "learning_rate": 9.183120393841188e-06, "loss": 0.001, "step": 351830 }, { "epoch": 84.49, "learning_rate": 9.181047252311326e-06, "loss": 0.0011, "step": 351840 }, { "epoch": 84.49, "learning_rate": 9.178974321162681e-06, "loss": 0.0012, "step": 351850 }, { "epoch": 84.5, "learning_rate": 9.176901600405952e-06, "loss": 0.001, "step": 351860 }, { "epoch": 84.5, "learning_rate": 9.174829090051801e-06, "loss": 0.001, "step": 351870 }, { "epoch": 84.5, "learning_rate": 9.172756790110931e-06, "loss": 0.0064, "step": 351880 }, { "epoch": 84.5, "learning_rate": 9.170684700594023e-06, "loss": 0.0011, "step": 351890 }, { "epoch": 84.5, "learning_rate": 9.16861282151173e-06, "loss": 0.0011, "step": 351900 }, { "epoch": 84.51, "learning_rate": 9.166541152874747e-06, "loss": 0.001, "step": 351910 }, { "epoch": 84.51, "learning_rate": 9.164469694693762e-06, "loss": 0.0009, "step": 351920 }, { "epoch": 84.51, "learning_rate": 9.16239844697943e-06, "loss": 0.001, "step": 351930 }, { "epoch": 84.51, "learning_rate": 9.160327409742452e-06, "loss": 0.001, "step": 351940 }, { "epoch": 84.52, "learning_rate": 9.15825658299348e-06, "loss": 0.001, "step": 351950 }, { "epoch": 84.52, "learning_rate": 9.156185966743192e-06, "loss": 0.0011, "step": 351960 }, { "epoch": 84.52, "learning_rate": 9.15411556100227e-06, "loss": 0.0011, "step": 351970 }, { "epoch": 84.52, "learning_rate": 9.152045365781381e-06, "loss": 0.0012, "step": 351980 }, { "epoch": 84.53, "learning_rate": 9.14997538109118e-06, "loss": 0.0011, "step": 351990 }, { "epoch": 84.53, "learning_rate": 9.147905606942364e-06, "loss": 0.0011, "step": 352000 }, { "epoch": 84.53, "learning_rate": 9.145836043345568e-06, "loss": 0.0011, "step": 352010 }, { "epoch": 84.53, "learning_rate": 9.143766690311483e-06, "loss": 0.0009, "step": 352020 }, { "epoch": 84.53, "learning_rate": 9.141697547850759e-06, "loss": 0.0011, "step": 352030 }, { "epoch": 84.54, "learning_rate": 9.139628615974077e-06, "loss": 0.0012, "step": 352040 }, { "epoch": 84.54, "learning_rate": 9.137559894692094e-06, "loss": 0.0011, "step": 352050 }, { "epoch": 84.54, "learning_rate": 9.135491384015449e-06, "loss": 0.0011, "step": 352060 }, { "epoch": 84.54, "learning_rate": 9.133423083954845e-06, "loss": 0.0011, "step": 352070 }, { "epoch": 84.55, "learning_rate": 9.131354994520902e-06, "loss": 0.0011, "step": 352080 }, { "epoch": 84.55, "learning_rate": 9.129287115724311e-06, "loss": 0.0013, "step": 352090 }, { "epoch": 84.55, "learning_rate": 9.127219447575702e-06, "loss": 0.0011, "step": 352100 }, { "epoch": 84.55, "learning_rate": 9.125151990085756e-06, "loss": 0.0009, "step": 352110 }, { "epoch": 84.55, "learning_rate": 9.12308474326512e-06, "loss": 0.0011, "step": 352120 }, { "epoch": 84.56, "learning_rate": 9.121017707124435e-06, "loss": 0.001, "step": 352130 }, { "epoch": 84.56, "learning_rate": 9.118950881674383e-06, "loss": 0.0011, "step": 352140 }, { "epoch": 84.56, "learning_rate": 9.116884266925584e-06, "loss": 0.0011, "step": 352150 }, { "epoch": 84.56, "learning_rate": 9.114817862888714e-06, "loss": 0.001, "step": 352160 }, { "epoch": 84.57, "learning_rate": 9.11275166957441e-06, "loss": 0.0012, "step": 352170 }, { "epoch": 84.57, "learning_rate": 9.11068568699333e-06, "loss": 0.0011, "step": 352180 }, { "epoch": 84.57, "learning_rate": 9.108619915156124e-06, "loss": 0.0011, "step": 352190 }, { "epoch": 84.57, "learning_rate": 9.106554354073415e-06, "loss": 0.0012, "step": 352200 }, { "epoch": 84.58, "learning_rate": 9.104489003755873e-06, "loss": 0.0011, "step": 352210 }, { "epoch": 84.58, "learning_rate": 9.102423864214144e-06, "loss": 0.0012, "step": 352220 }, { "epoch": 84.58, "learning_rate": 9.100358935458852e-06, "loss": 0.001, "step": 352230 }, { "epoch": 84.58, "learning_rate": 9.098294217500664e-06, "loss": 0.0011, "step": 352240 }, { "epoch": 84.58, "learning_rate": 9.096229710350202e-06, "loss": 0.001, "step": 352250 }, { "epoch": 84.59, "learning_rate": 9.094165414018118e-06, "loss": 0.0011, "step": 352260 }, { "epoch": 84.59, "learning_rate": 9.09210132851504e-06, "loss": 0.001, "step": 352270 }, { "epoch": 84.59, "learning_rate": 9.09003745385163e-06, "loss": 0.0011, "step": 352280 }, { "epoch": 84.59, "learning_rate": 9.08797379003849e-06, "loss": 0.0012, "step": 352290 }, { "epoch": 84.6, "learning_rate": 9.08591033708629e-06, "loss": 0.0011, "step": 352300 }, { "epoch": 84.6, "learning_rate": 9.083847095005637e-06, "loss": 0.0012, "step": 352310 }, { "epoch": 84.6, "learning_rate": 9.081784063807191e-06, "loss": 0.0012, "step": 352320 }, { "epoch": 84.6, "learning_rate": 9.079721243501577e-06, "loss": 0.001, "step": 352330 }, { "epoch": 84.61, "learning_rate": 9.077658634099401e-06, "loss": 0.0011, "step": 352340 }, { "epoch": 84.61, "learning_rate": 9.075596235611334e-06, "loss": 0.001, "step": 352350 }, { "epoch": 84.61, "learning_rate": 9.073534048047966e-06, "loss": 0.0011, "step": 352360 }, { "epoch": 84.61, "learning_rate": 9.071472071419963e-06, "loss": 0.001, "step": 352370 }, { "epoch": 84.61, "learning_rate": 9.069410305737919e-06, "loss": 0.0011, "step": 352380 }, { "epoch": 84.62, "learning_rate": 9.067348751012494e-06, "loss": 0.001, "step": 352390 }, { "epoch": 84.62, "learning_rate": 9.065287407254292e-06, "loss": 0.0011, "step": 352400 }, { "epoch": 84.62, "learning_rate": 9.06322627447393e-06, "loss": 0.0012, "step": 352410 }, { "epoch": 84.62, "learning_rate": 9.061165352682056e-06, "loss": 0.0011, "step": 352420 }, { "epoch": 84.63, "learning_rate": 9.05910464188926e-06, "loss": 0.0011, "step": 352430 }, { "epoch": 84.63, "learning_rate": 9.057044142106198e-06, "loss": 0.0011, "step": 352440 }, { "epoch": 84.63, "learning_rate": 9.054983853343462e-06, "loss": 0.0011, "step": 352450 }, { "epoch": 84.63, "learning_rate": 9.052923775611689e-06, "loss": 0.001, "step": 352460 }, { "epoch": 84.63, "learning_rate": 9.050863908921491e-06, "loss": 0.0011, "step": 352470 }, { "epoch": 84.64, "learning_rate": 9.048804253283471e-06, "loss": 0.001, "step": 352480 }, { "epoch": 84.64, "learning_rate": 9.046744808708269e-06, "loss": 0.0011, "step": 352490 }, { "epoch": 84.64, "learning_rate": 9.044685575206473e-06, "loss": 0.0011, "step": 352500 }, { "epoch": 84.64, "learning_rate": 9.042626552788724e-06, "loss": 0.0011, "step": 352510 }, { "epoch": 84.65, "learning_rate": 9.040567741465606e-06, "loss": 0.0011, "step": 352520 }, { "epoch": 84.65, "learning_rate": 9.038509141247741e-06, "loss": 0.0013, "step": 352530 }, { "epoch": 84.65, "learning_rate": 9.036450752145759e-06, "loss": 0.001, "step": 352540 }, { "epoch": 84.65, "learning_rate": 9.034392574170236e-06, "loss": 0.0011, "step": 352550 }, { "epoch": 84.66, "learning_rate": 9.032334607331816e-06, "loss": 0.0011, "step": 352560 }, { "epoch": 84.66, "learning_rate": 9.030276851641067e-06, "loss": 0.0011, "step": 352570 }, { "epoch": 84.66, "learning_rate": 9.028219307108627e-06, "loss": 0.0011, "step": 352580 }, { "epoch": 84.66, "learning_rate": 9.026161973745078e-06, "loss": 0.0011, "step": 352590 }, { "epoch": 84.66, "learning_rate": 9.024104851561045e-06, "loss": 0.0012, "step": 352600 }, { "epoch": 84.67, "learning_rate": 9.022047940567114e-06, "loss": 0.0011, "step": 352610 }, { "epoch": 84.67, "learning_rate": 9.019991240773878e-06, "loss": 0.001, "step": 352620 }, { "epoch": 84.67, "learning_rate": 9.017934752191964e-06, "loss": 0.0012, "step": 352630 }, { "epoch": 84.67, "learning_rate": 9.015878474831946e-06, "loss": 0.0012, "step": 352640 }, { "epoch": 84.68, "learning_rate": 9.013822408704443e-06, "loss": 0.001, "step": 352650 }, { "epoch": 84.68, "learning_rate": 9.011766553820029e-06, "loss": 0.0011, "step": 352660 }, { "epoch": 84.68, "learning_rate": 9.009710910189328e-06, "loss": 0.0011, "step": 352670 }, { "epoch": 84.68, "learning_rate": 9.007655477822919e-06, "loss": 0.0011, "step": 352680 }, { "epoch": 84.69, "learning_rate": 9.005600256731377e-06, "loss": 0.0012, "step": 352690 }, { "epoch": 84.69, "learning_rate": 9.003545246925338e-06, "loss": 0.0011, "step": 352700 }, { "epoch": 84.69, "learning_rate": 9.00149044841535e-06, "loss": 0.0011, "step": 352710 }, { "epoch": 84.69, "learning_rate": 8.999435861212036e-06, "loss": 0.0011, "step": 352720 }, { "epoch": 84.69, "learning_rate": 8.997381485325961e-06, "loss": 0.0012, "step": 352730 }, { "epoch": 84.7, "learning_rate": 8.995327320767732e-06, "loss": 0.0012, "step": 352740 }, { "epoch": 84.7, "learning_rate": 8.993273367547921e-06, "loss": 0.0011, "step": 352750 }, { "epoch": 84.7, "learning_rate": 8.99121962567714e-06, "loss": 0.001, "step": 352760 }, { "epoch": 84.7, "learning_rate": 8.989166095165946e-06, "loss": 0.001, "step": 352770 }, { "epoch": 84.71, "learning_rate": 8.987112776024925e-06, "loss": 0.001, "step": 352780 }, { "epoch": 84.71, "learning_rate": 8.985059668264678e-06, "loss": 0.0012, "step": 352790 }, { "epoch": 84.71, "learning_rate": 8.983006771895763e-06, "loss": 0.0013, "step": 352800 }, { "epoch": 84.71, "learning_rate": 8.98095408692879e-06, "loss": 0.001, "step": 352810 }, { "epoch": 84.71, "learning_rate": 8.978901613374307e-06, "loss": 0.0011, "step": 352820 }, { "epoch": 84.72, "learning_rate": 8.976849351242928e-06, "loss": 0.001, "step": 352830 }, { "epoch": 84.72, "learning_rate": 8.97479730054519e-06, "loss": 0.0011, "step": 352840 }, { "epoch": 84.72, "learning_rate": 8.972745461291688e-06, "loss": 0.0011, "step": 352850 }, { "epoch": 84.72, "learning_rate": 8.970693833493015e-06, "loss": 0.0011, "step": 352860 }, { "epoch": 84.73, "learning_rate": 8.968642417159717e-06, "loss": 0.0011, "step": 352870 }, { "epoch": 84.73, "learning_rate": 8.966591212302388e-06, "loss": 0.0056, "step": 352880 }, { "epoch": 84.73, "learning_rate": 8.964540218931582e-06, "loss": 0.0011, "step": 352890 }, { "epoch": 84.73, "learning_rate": 8.962489437057892e-06, "loss": 0.0012, "step": 352900 }, { "epoch": 84.74, "learning_rate": 8.960438866691873e-06, "loss": 0.0011, "step": 352910 }, { "epoch": 84.74, "learning_rate": 8.958388507844085e-06, "loss": 0.0011, "step": 352920 }, { "epoch": 84.74, "learning_rate": 8.956338360525113e-06, "loss": 0.001, "step": 352930 }, { "epoch": 84.74, "learning_rate": 8.954288424745505e-06, "loss": 0.0011, "step": 352940 }, { "epoch": 84.74, "learning_rate": 8.952238700515852e-06, "loss": 0.0011, "step": 352950 }, { "epoch": 84.75, "learning_rate": 8.950189187846691e-06, "loss": 0.001, "step": 352960 }, { "epoch": 84.75, "learning_rate": 8.948139886748608e-06, "loss": 0.001, "step": 352970 }, { "epoch": 84.75, "learning_rate": 8.94609079723216e-06, "loss": 0.001, "step": 352980 }, { "epoch": 84.75, "learning_rate": 8.944041919307888e-06, "loss": 0.0011, "step": 352990 }, { "epoch": 84.76, "learning_rate": 8.94199325298638e-06, "loss": 0.0012, "step": 353000 }, { "epoch": 84.76, "learning_rate": 8.939944798278165e-06, "loss": 0.001, "step": 353010 }, { "epoch": 84.76, "learning_rate": 8.937896555193836e-06, "loss": 0.001, "step": 353020 }, { "epoch": 84.76, "learning_rate": 8.935848523743917e-06, "loss": 0.001, "step": 353030 }, { "epoch": 84.77, "learning_rate": 8.933800703938993e-06, "loss": 0.001, "step": 353040 }, { "epoch": 84.77, "learning_rate": 8.931753095789597e-06, "loss": 0.001, "step": 353050 }, { "epoch": 84.77, "learning_rate": 8.929705699306285e-06, "loss": 0.0011, "step": 353060 }, { "epoch": 84.77, "learning_rate": 8.927658514499621e-06, "loss": 0.001, "step": 353070 }, { "epoch": 84.77, "learning_rate": 8.925611541380136e-06, "loss": 0.0011, "step": 353080 }, { "epoch": 84.78, "learning_rate": 8.923564779958404e-06, "loss": 0.0011, "step": 353090 }, { "epoch": 84.78, "learning_rate": 8.921518230244946e-06, "loss": 0.0012, "step": 353100 }, { "epoch": 84.78, "learning_rate": 8.919471892250347e-06, "loss": 0.001, "step": 353110 }, { "epoch": 84.78, "learning_rate": 8.917425765985115e-06, "loss": 0.001, "step": 353120 }, { "epoch": 84.79, "learning_rate": 8.915379851459831e-06, "loss": 0.0024, "step": 353130 }, { "epoch": 84.79, "learning_rate": 8.91333414868501e-06, "loss": 0.001, "step": 353140 }, { "epoch": 84.79, "learning_rate": 8.911288657671218e-06, "loss": 0.001, "step": 353150 }, { "epoch": 84.79, "learning_rate": 8.909243378428971e-06, "loss": 0.0014, "step": 353160 }, { "epoch": 84.79, "learning_rate": 8.907198310968834e-06, "loss": 0.0011, "step": 353170 }, { "epoch": 84.8, "learning_rate": 8.905153455301352e-06, "loss": 0.0011, "step": 353180 }, { "epoch": 84.8, "learning_rate": 8.90310881143705e-06, "loss": 0.001, "step": 353190 }, { "epoch": 84.8, "learning_rate": 8.901064379386459e-06, "loss": 0.001, "step": 353200 }, { "epoch": 84.8, "learning_rate": 8.899020159160137e-06, "loss": 0.001, "step": 353210 }, { "epoch": 84.81, "learning_rate": 8.8969761507686e-06, "loss": 0.001, "step": 353220 }, { "epoch": 84.81, "learning_rate": 8.894932354222397e-06, "loss": 0.0011, "step": 353230 }, { "epoch": 84.81, "learning_rate": 8.892888769532048e-06, "loss": 0.001, "step": 353240 }, { "epoch": 84.81, "learning_rate": 8.890845396708102e-06, "loss": 0.001, "step": 353250 }, { "epoch": 84.82, "learning_rate": 8.888802235761085e-06, "loss": 0.0125, "step": 353260 }, { "epoch": 84.82, "learning_rate": 8.886759286701512e-06, "loss": 0.0011, "step": 353270 }, { "epoch": 84.82, "learning_rate": 8.88471654953994e-06, "loss": 0.0011, "step": 353280 }, { "epoch": 84.82, "learning_rate": 8.882674024286868e-06, "loss": 0.0011, "step": 353290 }, { "epoch": 84.82, "learning_rate": 8.880631710952853e-06, "loss": 0.0011, "step": 353300 }, { "epoch": 84.83, "learning_rate": 8.878589609548394e-06, "loss": 0.0011, "step": 353310 }, { "epoch": 84.83, "learning_rate": 8.87654772008404e-06, "loss": 0.0011, "step": 353320 }, { "epoch": 84.83, "learning_rate": 8.874506042570296e-06, "loss": 0.001, "step": 353330 }, { "epoch": 84.83, "learning_rate": 8.872464577017687e-06, "loss": 0.0011, "step": 353340 }, { "epoch": 84.84, "learning_rate": 8.87042332343675e-06, "loss": 0.001, "step": 353350 }, { "epoch": 84.84, "learning_rate": 8.868382281837977e-06, "loss": 0.0011, "step": 353360 }, { "epoch": 84.84, "learning_rate": 8.866341452231925e-06, "loss": 0.001, "step": 353370 }, { "epoch": 84.84, "learning_rate": 8.864300834629074e-06, "loss": 0.001, "step": 353380 }, { "epoch": 84.85, "learning_rate": 8.862260429039976e-06, "loss": 0.0013, "step": 353390 }, { "epoch": 84.85, "learning_rate": 8.860220235475136e-06, "loss": 0.001, "step": 353400 }, { "epoch": 84.85, "learning_rate": 8.858180253945048e-06, "loss": 0.001, "step": 353410 }, { "epoch": 84.85, "learning_rate": 8.856140484460241e-06, "loss": 0.0011, "step": 353420 }, { "epoch": 84.85, "learning_rate": 8.854100927031245e-06, "loss": 0.001, "step": 353430 }, { "epoch": 84.86, "learning_rate": 8.852061581668548e-06, "loss": 0.0034, "step": 353440 }, { "epoch": 84.86, "learning_rate": 8.850022448382673e-06, "loss": 0.0009, "step": 353450 }, { "epoch": 84.86, "learning_rate": 8.847983527184122e-06, "loss": 0.001, "step": 353460 }, { "epoch": 84.86, "learning_rate": 8.845944818083418e-06, "loss": 0.0011, "step": 353470 }, { "epoch": 84.87, "learning_rate": 8.843906321091044e-06, "loss": 0.0012, "step": 353480 }, { "epoch": 84.87, "learning_rate": 8.841868036217531e-06, "loss": 0.0011, "step": 353490 }, { "epoch": 84.87, "learning_rate": 8.839829963473368e-06, "loss": 0.0011, "step": 353500 }, { "epoch": 84.87, "learning_rate": 8.837792102869075e-06, "loss": 0.001, "step": 353510 }, { "epoch": 84.87, "learning_rate": 8.83575445441513e-06, "loss": 0.001, "step": 353520 }, { "epoch": 84.88, "learning_rate": 8.833717018122068e-06, "loss": 0.0011, "step": 353530 }, { "epoch": 84.88, "learning_rate": 8.831679794000358e-06, "loss": 0.001, "step": 353540 }, { "epoch": 84.88, "learning_rate": 8.829642782060527e-06, "loss": 0.001, "step": 353550 }, { "epoch": 84.88, "learning_rate": 8.827605982313059e-06, "loss": 0.0011, "step": 353560 }, { "epoch": 84.89, "learning_rate": 8.825569394768446e-06, "loss": 0.0009, "step": 353570 }, { "epoch": 84.89, "learning_rate": 8.823533019437202e-06, "loss": 0.001, "step": 353580 }, { "epoch": 84.89, "learning_rate": 8.821496856329802e-06, "loss": 0.0012, "step": 353590 }, { "epoch": 84.89, "learning_rate": 8.819460905456762e-06, "loss": 0.0011, "step": 353600 }, { "epoch": 84.9, "learning_rate": 8.817425166828553e-06, "loss": 0.001, "step": 353610 }, { "epoch": 84.9, "learning_rate": 8.815389640455696e-06, "loss": 0.0012, "step": 353620 }, { "epoch": 84.9, "learning_rate": 8.81335432634866e-06, "loss": 0.001, "step": 353630 }, { "epoch": 84.9, "learning_rate": 8.811319224517928e-06, "loss": 0.001, "step": 353640 }, { "epoch": 84.9, "learning_rate": 8.80928433497401e-06, "loss": 0.001, "step": 353650 }, { "epoch": 84.91, "learning_rate": 8.807249657727379e-06, "loss": 0.001, "step": 353660 }, { "epoch": 84.91, "learning_rate": 8.805215192788535e-06, "loss": 0.001, "step": 353670 }, { "epoch": 84.91, "learning_rate": 8.80318094016795e-06, "loss": 0.001, "step": 353680 }, { "epoch": 84.91, "learning_rate": 8.801146899876123e-06, "loss": 0.001, "step": 353690 }, { "epoch": 84.92, "learning_rate": 8.799113071923527e-06, "loss": 0.0011, "step": 353700 }, { "epoch": 84.92, "learning_rate": 8.79707945632064e-06, "loss": 0.001, "step": 353710 }, { "epoch": 84.92, "learning_rate": 8.79504605307796e-06, "loss": 0.001, "step": 353720 }, { "epoch": 84.92, "learning_rate": 8.79301286220594e-06, "loss": 0.0012, "step": 353730 }, { "epoch": 84.93, "learning_rate": 8.790979883715078e-06, "loss": 0.001, "step": 353740 }, { "epoch": 84.93, "learning_rate": 8.78894711761587e-06, "loss": 0.0011, "step": 353750 }, { "epoch": 84.93, "learning_rate": 8.786914563918753e-06, "loss": 0.0035, "step": 353760 }, { "epoch": 84.93, "learning_rate": 8.784882222634238e-06, "loss": 0.001, "step": 353770 }, { "epoch": 84.93, "learning_rate": 8.782850093772771e-06, "loss": 0.0011, "step": 353780 }, { "epoch": 84.94, "learning_rate": 8.780818177344852e-06, "loss": 0.001, "step": 353790 }, { "epoch": 84.94, "learning_rate": 8.778786473360928e-06, "loss": 0.001, "step": 353800 }, { "epoch": 84.94, "learning_rate": 8.776754981831498e-06, "loss": 0.001, "step": 353810 }, { "epoch": 84.94, "learning_rate": 8.774723702767001e-06, "loss": 0.0011, "step": 353820 }, { "epoch": 84.95, "learning_rate": 8.772692636177937e-06, "loss": 0.0011, "step": 353830 }, { "epoch": 84.95, "learning_rate": 8.770661782074757e-06, "loss": 0.0013, "step": 353840 }, { "epoch": 84.95, "learning_rate": 8.76863114046792e-06, "loss": 0.001, "step": 353850 }, { "epoch": 85.0, "learning_rate": 8.766600711367917e-06, "loss": 0.001, "step": 353860 }, { "epoch": 85.0, "learning_rate": 8.764570494785184e-06, "loss": 0.0009, "step": 353870 }, { "epoch": 85.01, "learning_rate": 8.762540490730214e-06, "loss": 0.0011, "step": 353880 }, { "epoch": 85.01, "learning_rate": 8.760510699213442e-06, "loss": 0.001, "step": 353890 }, { "epoch": 85.01, "learning_rate": 8.758481120245353e-06, "loss": 0.001, "step": 353900 }, { "epoch": 85.01, "learning_rate": 8.756451753836398e-06, "loss": 0.0011, "step": 353910 }, { "epoch": 85.01, "learning_rate": 8.754422599997025e-06, "loss": 0.001, "step": 353920 }, { "epoch": 85.02, "learning_rate": 8.752393658737711e-06, "loss": 0.0012, "step": 353930 }, { "epoch": 85.02, "learning_rate": 8.7503649300689e-06, "loss": 0.001, "step": 353940 }, { "epoch": 85.02, "learning_rate": 8.748336414001057e-06, "loss": 0.0012, "step": 353950 }, { "epoch": 85.02, "learning_rate": 8.746308110544627e-06, "loss": 0.001, "step": 353960 }, { "epoch": 85.03, "learning_rate": 8.744280019710078e-06, "loss": 0.001, "step": 353970 }, { "epoch": 85.03, "learning_rate": 8.742252141507856e-06, "loss": 0.0012, "step": 353980 }, { "epoch": 85.03, "learning_rate": 8.7402244759484e-06, "loss": 0.0009, "step": 353990 }, { "epoch": 85.03, "learning_rate": 8.738197023042183e-06, "loss": 0.0011, "step": 354000 }, { "epoch": 85.04, "learning_rate": 8.73616978279963e-06, "loss": 0.001, "step": 354010 }, { "epoch": 85.04, "learning_rate": 8.734142755231216e-06, "loss": 0.001, "step": 354020 }, { "epoch": 85.04, "learning_rate": 8.732115940347364e-06, "loss": 0.0009, "step": 354030 }, { "epoch": 85.04, "learning_rate": 8.730089338158532e-06, "loss": 0.001, "step": 354040 }, { "epoch": 85.04, "learning_rate": 8.728062948675176e-06, "loss": 0.001, "step": 354050 }, { "epoch": 85.05, "learning_rate": 8.726036771907714e-06, "loss": 0.0011, "step": 354060 }, { "epoch": 85.05, "learning_rate": 8.724010807866617e-06, "loss": 0.001, "step": 354070 }, { "epoch": 85.05, "learning_rate": 8.721985056562298e-06, "loss": 0.0012, "step": 354080 }, { "epoch": 85.05, "learning_rate": 8.719959518005232e-06, "loss": 0.001, "step": 354090 }, { "epoch": 85.06, "learning_rate": 8.717934192205823e-06, "loss": 0.001, "step": 354100 }, { "epoch": 85.06, "learning_rate": 8.715909079174538e-06, "loss": 0.0011, "step": 354110 }, { "epoch": 85.06, "learning_rate": 8.713884178921804e-06, "loss": 0.001, "step": 354120 }, { "epoch": 85.06, "learning_rate": 8.711859491458047e-06, "loss": 0.0011, "step": 354130 }, { "epoch": 85.07, "learning_rate": 8.70983501679372e-06, "loss": 0.0011, "step": 354140 }, { "epoch": 85.07, "learning_rate": 8.707810754939238e-06, "loss": 0.001, "step": 354150 }, { "epoch": 85.07, "learning_rate": 8.705786705905056e-06, "loss": 0.0011, "step": 354160 }, { "epoch": 85.07, "learning_rate": 8.703762869701582e-06, "loss": 0.0011, "step": 354170 }, { "epoch": 85.07, "learning_rate": 8.701739246339268e-06, "loss": 0.001, "step": 354180 }, { "epoch": 85.08, "learning_rate": 8.699715835828543e-06, "loss": 0.0012, "step": 354190 }, { "epoch": 85.08, "learning_rate": 8.697692638179811e-06, "loss": 0.0011, "step": 354200 }, { "epoch": 85.08, "learning_rate": 8.695669653403527e-06, "loss": 0.0011, "step": 354210 }, { "epoch": 85.08, "learning_rate": 8.693646881510099e-06, "loss": 0.0011, "step": 354220 }, { "epoch": 85.09, "learning_rate": 8.691624322509967e-06, "loss": 0.0012, "step": 354230 }, { "epoch": 85.09, "learning_rate": 8.689601976413542e-06, "loss": 0.001, "step": 354240 }, { "epoch": 85.09, "learning_rate": 8.687579843231264e-06, "loss": 0.0011, "step": 354250 }, { "epoch": 85.09, "learning_rate": 8.685557922973541e-06, "loss": 0.0011, "step": 354260 }, { "epoch": 85.09, "learning_rate": 8.68353621565079e-06, "loss": 0.001, "step": 354270 }, { "epoch": 85.1, "learning_rate": 8.681514721273449e-06, "loss": 0.001, "step": 354280 }, { "epoch": 85.1, "learning_rate": 8.679493439851915e-06, "loss": 0.001, "step": 354290 }, { "epoch": 85.1, "learning_rate": 8.677472371396628e-06, "loss": 0.0011, "step": 354300 }, { "epoch": 85.1, "learning_rate": 8.675451515917981e-06, "loss": 0.0011, "step": 354310 }, { "epoch": 85.11, "learning_rate": 8.673430873426419e-06, "loss": 0.001, "step": 354320 }, { "epoch": 85.11, "learning_rate": 8.671410443932326e-06, "loss": 0.0011, "step": 354330 }, { "epoch": 85.11, "learning_rate": 8.669390227446139e-06, "loss": 0.0011, "step": 354340 }, { "epoch": 85.11, "learning_rate": 8.66737022397825e-06, "loss": 0.0011, "step": 354350 }, { "epoch": 85.12, "learning_rate": 8.665350433539077e-06, "loss": 0.0011, "step": 354360 }, { "epoch": 85.12, "learning_rate": 8.663330856139045e-06, "loss": 0.001, "step": 354370 }, { "epoch": 85.12, "learning_rate": 8.661311491788543e-06, "loss": 0.001, "step": 354380 }, { "epoch": 85.12, "learning_rate": 8.659292340497999e-06, "loss": 0.001, "step": 354390 }, { "epoch": 85.12, "learning_rate": 8.657273402277799e-06, "loss": 0.0011, "step": 354400 }, { "epoch": 85.13, "learning_rate": 8.655254677138364e-06, "loss": 0.001, "step": 354410 }, { "epoch": 85.13, "learning_rate": 8.653236165090095e-06, "loss": 0.0009, "step": 354420 }, { "epoch": 85.13, "learning_rate": 8.65121786614338e-06, "loss": 0.0011, "step": 354430 }, { "epoch": 85.13, "learning_rate": 8.649199780308642e-06, "loss": 0.0011, "step": 354440 }, { "epoch": 85.14, "learning_rate": 8.647181907596264e-06, "loss": 0.001, "step": 354450 }, { "epoch": 85.14, "learning_rate": 8.645164248016668e-06, "loss": 0.001, "step": 354460 }, { "epoch": 85.14, "learning_rate": 8.643146801580232e-06, "loss": 0.0011, "step": 354470 }, { "epoch": 85.14, "learning_rate": 8.641129568297374e-06, "loss": 0.0009, "step": 354480 }, { "epoch": 85.15, "learning_rate": 8.63911254817848e-06, "loss": 0.001, "step": 354490 }, { "epoch": 85.15, "learning_rate": 8.63709574123393e-06, "loss": 0.0009, "step": 354500 }, { "epoch": 85.15, "learning_rate": 8.63507914747415e-06, "loss": 0.0011, "step": 354510 }, { "epoch": 85.15, "learning_rate": 8.633062766909505e-06, "loss": 0.001, "step": 354520 }, { "epoch": 85.15, "learning_rate": 8.631046599550413e-06, "loss": 0.0011, "step": 354530 }, { "epoch": 85.16, "learning_rate": 8.629030645407237e-06, "loss": 0.001, "step": 354540 }, { "epoch": 85.16, "learning_rate": 8.6270149044904e-06, "loss": 0.001, "step": 354550 }, { "epoch": 85.16, "learning_rate": 8.624999376810267e-06, "loss": 0.001, "step": 354560 }, { "epoch": 85.16, "learning_rate": 8.622984062377226e-06, "loss": 0.001, "step": 354570 }, { "epoch": 85.17, "learning_rate": 8.620968961201686e-06, "loss": 0.0011, "step": 354580 }, { "epoch": 85.17, "learning_rate": 8.618954073294e-06, "loss": 0.0011, "step": 354590 }, { "epoch": 85.17, "learning_rate": 8.616939398664587e-06, "loss": 0.0012, "step": 354600 }, { "epoch": 85.17, "learning_rate": 8.614924937323798e-06, "loss": 0.0011, "step": 354610 }, { "epoch": 85.17, "learning_rate": 8.612910689282044e-06, "loss": 0.0011, "step": 354620 }, { "epoch": 85.18, "learning_rate": 8.610896654549689e-06, "loss": 0.0011, "step": 354630 }, { "epoch": 85.18, "learning_rate": 8.608882833137122e-06, "loss": 0.0011, "step": 354640 }, { "epoch": 85.18, "learning_rate": 8.606869225054715e-06, "loss": 0.0015, "step": 354650 }, { "epoch": 85.18, "learning_rate": 8.604855830312852e-06, "loss": 0.0011, "step": 354660 }, { "epoch": 85.19, "learning_rate": 8.602842648921905e-06, "loss": 0.001, "step": 354670 }, { "epoch": 85.19, "learning_rate": 8.600829680892248e-06, "loss": 0.0011, "step": 354680 }, { "epoch": 85.19, "learning_rate": 8.598816926234277e-06, "loss": 0.001, "step": 354690 }, { "epoch": 85.19, "learning_rate": 8.596804384958346e-06, "loss": 0.001, "step": 354700 }, { "epoch": 85.2, "learning_rate": 8.594792057074819e-06, "loss": 0.0011, "step": 354710 }, { "epoch": 85.2, "learning_rate": 8.592779942594097e-06, "loss": 0.0011, "step": 354720 }, { "epoch": 85.2, "learning_rate": 8.590768041526515e-06, "loss": 0.0009, "step": 354730 }, { "epoch": 85.2, "learning_rate": 8.588756353882477e-06, "loss": 0.001, "step": 354740 }, { "epoch": 85.2, "learning_rate": 8.58674487967232e-06, "loss": 0.001, "step": 354750 }, { "epoch": 85.21, "learning_rate": 8.584733618906437e-06, "loss": 0.001, "step": 354760 }, { "epoch": 85.21, "learning_rate": 8.582722571595187e-06, "loss": 0.0011, "step": 354770 }, { "epoch": 85.21, "learning_rate": 8.58071173774892e-06, "loss": 0.0011, "step": 354780 }, { "epoch": 85.21, "learning_rate": 8.578701117378018e-06, "loss": 0.0012, "step": 354790 }, { "epoch": 85.22, "learning_rate": 8.57669071049283e-06, "loss": 0.0009, "step": 354800 }, { "epoch": 85.22, "learning_rate": 8.574680517103734e-06, "loss": 0.0009, "step": 354810 }, { "epoch": 85.22, "learning_rate": 8.572670537221067e-06, "loss": 0.0012, "step": 354820 }, { "epoch": 85.22, "learning_rate": 8.570660770855215e-06, "loss": 0.001, "step": 354830 }, { "epoch": 85.23, "learning_rate": 8.568651218016522e-06, "loss": 0.0009, "step": 354840 }, { "epoch": 85.23, "learning_rate": 8.566641878715336e-06, "loss": 0.001, "step": 354850 }, { "epoch": 85.23, "learning_rate": 8.564632752962043e-06, "loss": 0.001, "step": 354860 }, { "epoch": 85.23, "learning_rate": 8.56262384076696e-06, "loss": 0.0011, "step": 354870 }, { "epoch": 85.23, "learning_rate": 8.560615142140472e-06, "loss": 0.0011, "step": 354880 }, { "epoch": 85.24, "learning_rate": 8.55860665709291e-06, "loss": 0.001, "step": 354890 }, { "epoch": 85.24, "learning_rate": 8.556598385634646e-06, "loss": 0.0011, "step": 354900 }, { "epoch": 85.24, "learning_rate": 8.554590327776025e-06, "loss": 0.0011, "step": 354910 }, { "epoch": 85.24, "learning_rate": 8.552582483527371e-06, "loss": 0.0011, "step": 354920 }, { "epoch": 85.25, "learning_rate": 8.550574852899063e-06, "loss": 0.001, "step": 354930 }, { "epoch": 85.25, "learning_rate": 8.548567435901445e-06, "loss": 0.001, "step": 354940 }, { "epoch": 85.25, "learning_rate": 8.546560232544848e-06, "loss": 0.001, "step": 354950 }, { "epoch": 85.25, "learning_rate": 8.544553242839637e-06, "loss": 0.001, "step": 354960 }, { "epoch": 85.25, "learning_rate": 8.542546466796131e-06, "loss": 0.001, "step": 354970 }, { "epoch": 85.26, "learning_rate": 8.540539904424699e-06, "loss": 0.0011, "step": 354980 }, { "epoch": 85.26, "learning_rate": 8.538533555735662e-06, "loss": 0.0011, "step": 354990 }, { "epoch": 85.26, "learning_rate": 8.536527420739377e-06, "loss": 0.0012, "step": 355000 }, { "epoch": 85.26, "learning_rate": 8.534521499446169e-06, "loss": 0.0009, "step": 355010 }, { "epoch": 85.27, "learning_rate": 8.53251579186639e-06, "loss": 0.001, "step": 355020 }, { "epoch": 85.27, "learning_rate": 8.530510298010368e-06, "loss": 0.001, "step": 355030 }, { "epoch": 85.27, "learning_rate": 8.52850501788845e-06, "loss": 0.0011, "step": 355040 }, { "epoch": 85.27, "learning_rate": 8.526499951510964e-06, "loss": 0.0009, "step": 355050 }, { "epoch": 85.28, "learning_rate": 8.52449509888823e-06, "loss": 0.0009, "step": 355060 }, { "epoch": 85.28, "learning_rate": 8.522490460030608e-06, "loss": 0.001, "step": 355070 }, { "epoch": 85.28, "learning_rate": 8.520486034948406e-06, "loss": 0.0011, "step": 355080 }, { "epoch": 85.28, "learning_rate": 8.518481823651974e-06, "loss": 0.0011, "step": 355090 }, { "epoch": 85.28, "learning_rate": 8.516477826151626e-06, "loss": 0.0011, "step": 355100 }, { "epoch": 85.29, "learning_rate": 8.51447404245771e-06, "loss": 0.001, "step": 355110 }, { "epoch": 85.29, "learning_rate": 8.512470472580542e-06, "loss": 0.001, "step": 355120 }, { "epoch": 85.29, "learning_rate": 8.51046711653043e-06, "loss": 0.0011, "step": 355130 }, { "epoch": 85.29, "learning_rate": 8.508463974317737e-06, "loss": 0.0009, "step": 355140 }, { "epoch": 85.3, "learning_rate": 8.506461045952751e-06, "loss": 0.0011, "step": 355150 }, { "epoch": 85.3, "learning_rate": 8.504458331445825e-06, "loss": 0.0011, "step": 355160 }, { "epoch": 85.3, "learning_rate": 8.502455830807254e-06, "loss": 0.001, "step": 355170 }, { "epoch": 85.3, "learning_rate": 8.500453544047382e-06, "loss": 0.001, "step": 355180 }, { "epoch": 85.31, "learning_rate": 8.498451471176511e-06, "loss": 0.0011, "step": 355190 }, { "epoch": 85.31, "learning_rate": 8.496449612204982e-06, "loss": 0.001, "step": 355200 }, { "epoch": 85.31, "learning_rate": 8.494447967143098e-06, "loss": 0.001, "step": 355210 }, { "epoch": 85.31, "learning_rate": 8.49244653600116e-06, "loss": 0.0011, "step": 355220 }, { "epoch": 85.31, "learning_rate": 8.490445318789514e-06, "loss": 0.001, "step": 355230 }, { "epoch": 85.32, "learning_rate": 8.488444315518452e-06, "loss": 0.001, "step": 355240 }, { "epoch": 85.32, "learning_rate": 8.486443526198285e-06, "loss": 0.001, "step": 355250 }, { "epoch": 85.32, "learning_rate": 8.484442950839355e-06, "loss": 0.0011, "step": 355260 }, { "epoch": 85.32, "learning_rate": 8.48244258945194e-06, "loss": 0.0009, "step": 355270 }, { "epoch": 85.33, "learning_rate": 8.48044244204637e-06, "loss": 0.001, "step": 355280 }, { "epoch": 85.33, "learning_rate": 8.478442508632939e-06, "loss": 0.001, "step": 355290 }, { "epoch": 85.33, "learning_rate": 8.476442789221978e-06, "loss": 0.0009, "step": 355300 }, { "epoch": 85.33, "learning_rate": 8.474443283823758e-06, "loss": 0.0009, "step": 355310 }, { "epoch": 85.33, "learning_rate": 8.472443992448619e-06, "loss": 0.0011, "step": 355320 }, { "epoch": 85.34, "learning_rate": 8.470444915106845e-06, "loss": 0.001, "step": 355330 }, { "epoch": 85.34, "learning_rate": 8.468446051808747e-06, "loss": 0.0014, "step": 355340 }, { "epoch": 85.34, "learning_rate": 8.466447402564637e-06, "loss": 0.0011, "step": 355350 }, { "epoch": 85.34, "learning_rate": 8.46444896738478e-06, "loss": 0.0011, "step": 355360 }, { "epoch": 85.35, "learning_rate": 8.46245074627952e-06, "loss": 0.0011, "step": 355370 }, { "epoch": 85.35, "learning_rate": 8.460452739259123e-06, "loss": 0.0012, "step": 355380 }, { "epoch": 85.35, "learning_rate": 8.45845494633391e-06, "loss": 0.001, "step": 355390 }, { "epoch": 85.35, "learning_rate": 8.456457367514154e-06, "loss": 0.001, "step": 355400 }, { "epoch": 85.36, "learning_rate": 8.454460002810183e-06, "loss": 0.0011, "step": 355410 }, { "epoch": 85.36, "learning_rate": 8.452462852232263e-06, "loss": 0.0009, "step": 355420 }, { "epoch": 85.36, "learning_rate": 8.45046591579069e-06, "loss": 0.0011, "step": 355430 }, { "epoch": 85.36, "learning_rate": 8.448469193495774e-06, "loss": 0.001, "step": 355440 }, { "epoch": 85.36, "learning_rate": 8.446472685357786e-06, "loss": 0.0009, "step": 355450 }, { "epoch": 85.37, "learning_rate": 8.444476391387035e-06, "loss": 0.001, "step": 355460 }, { "epoch": 85.37, "learning_rate": 8.442480311593787e-06, "loss": 0.001, "step": 355470 }, { "epoch": 85.37, "learning_rate": 8.440484445988355e-06, "loss": 0.0009, "step": 355480 }, { "epoch": 85.37, "learning_rate": 8.438488794581012e-06, "loss": 0.001, "step": 355490 }, { "epoch": 85.38, "learning_rate": 8.436493357382036e-06, "loss": 0.001, "step": 355500 }, { "epoch": 85.38, "learning_rate": 8.43449813440173e-06, "loss": 0.0012, "step": 355510 }, { "epoch": 85.38, "learning_rate": 8.432503125650359e-06, "loss": 0.0056, "step": 355520 }, { "epoch": 85.38, "learning_rate": 8.430508331138225e-06, "loss": 0.0009, "step": 355530 }, { "epoch": 85.39, "learning_rate": 8.428513750875588e-06, "loss": 0.0011, "step": 355540 }, { "epoch": 85.39, "learning_rate": 8.426519384872733e-06, "loss": 0.001, "step": 355550 }, { "epoch": 85.39, "learning_rate": 8.424525233139963e-06, "loss": 0.0011, "step": 355560 }, { "epoch": 85.39, "learning_rate": 8.422531295687524e-06, "loss": 0.0011, "step": 355570 }, { "epoch": 85.39, "learning_rate": 8.420537572525717e-06, "loss": 0.0012, "step": 355580 }, { "epoch": 85.4, "learning_rate": 8.418544063664797e-06, "loss": 0.001, "step": 355590 }, { "epoch": 85.4, "learning_rate": 8.416550769115056e-06, "loss": 0.001, "step": 355600 }, { "epoch": 85.4, "learning_rate": 8.414557688886754e-06, "loss": 0.001, "step": 355610 }, { "epoch": 85.4, "learning_rate": 8.412564822990176e-06, "loss": 0.001, "step": 355620 }, { "epoch": 85.41, "learning_rate": 8.410572171435588e-06, "loss": 0.001, "step": 355630 }, { "epoch": 85.41, "learning_rate": 8.408579734233246e-06, "loss": 0.0011, "step": 355640 }, { "epoch": 85.41, "learning_rate": 8.40658751139345e-06, "loss": 0.001, "step": 355650 }, { "epoch": 85.41, "learning_rate": 8.404595502926426e-06, "loss": 0.001, "step": 355660 }, { "epoch": 85.41, "learning_rate": 8.402603708842488e-06, "loss": 0.001, "step": 355670 }, { "epoch": 85.42, "learning_rate": 8.400612129151859e-06, "loss": 0.0009, "step": 355680 }, { "epoch": 85.42, "learning_rate": 8.39862076386484e-06, "loss": 0.001, "step": 355690 }, { "epoch": 85.42, "learning_rate": 8.396629612991669e-06, "loss": 0.001, "step": 355700 }, { "epoch": 85.42, "learning_rate": 8.39463867654261e-06, "loss": 0.0009, "step": 355710 }, { "epoch": 85.43, "learning_rate": 8.392647954527944e-06, "loss": 0.001, "step": 355720 }, { "epoch": 85.43, "learning_rate": 8.390657446957905e-06, "loss": 0.001, "step": 355730 }, { "epoch": 85.43, "learning_rate": 8.388667153842777e-06, "loss": 0.001, "step": 355740 }, { "epoch": 85.43, "learning_rate": 8.386677075192794e-06, "loss": 0.001, "step": 355750 }, { "epoch": 85.44, "learning_rate": 8.384687211018244e-06, "loss": 0.001, "step": 355760 }, { "epoch": 85.44, "learning_rate": 8.382697561329356e-06, "loss": 0.001, "step": 355770 }, { "epoch": 85.44, "learning_rate": 8.380708126136383e-06, "loss": 0.001, "step": 355780 }, { "epoch": 85.44, "learning_rate": 8.3787189054496e-06, "loss": 0.001, "step": 355790 }, { "epoch": 85.44, "learning_rate": 8.376729899279234e-06, "loss": 0.0009, "step": 355800 }, { "epoch": 85.45, "learning_rate": 8.374741107635565e-06, "loss": 0.001, "step": 355810 }, { "epoch": 85.45, "learning_rate": 8.372752530528816e-06, "loss": 0.0011, "step": 355820 }, { "epoch": 85.45, "learning_rate": 8.370764167969259e-06, "loss": 0.0009, "step": 355830 }, { "epoch": 85.45, "learning_rate": 8.368776019967117e-06, "loss": 0.001, "step": 355840 }, { "epoch": 85.46, "learning_rate": 8.366788086532667e-06, "loss": 0.0014, "step": 355850 }, { "epoch": 85.46, "learning_rate": 8.364800367676128e-06, "loss": 0.0011, "step": 355860 }, { "epoch": 85.46, "learning_rate": 8.362812863407754e-06, "loss": 0.001, "step": 355870 }, { "epoch": 85.46, "learning_rate": 8.360825573737802e-06, "loss": 0.0011, "step": 355880 }, { "epoch": 85.47, "learning_rate": 8.358838498676491e-06, "loss": 0.0009, "step": 355890 }, { "epoch": 85.47, "learning_rate": 8.356851638234087e-06, "loss": 0.001, "step": 355900 }, { "epoch": 85.47, "learning_rate": 8.354864992420818e-06, "loss": 0.001, "step": 355910 }, { "epoch": 85.47, "learning_rate": 8.352878561246913e-06, "loss": 0.001, "step": 355920 }, { "epoch": 85.47, "learning_rate": 8.350892344722628e-06, "loss": 0.0011, "step": 355930 }, { "epoch": 85.48, "learning_rate": 8.348906342858182e-06, "loss": 0.001, "step": 355940 }, { "epoch": 85.48, "learning_rate": 8.346920555663835e-06, "loss": 0.001, "step": 355950 }, { "epoch": 85.48, "learning_rate": 8.344934983149793e-06, "loss": 0.001, "step": 355960 }, { "epoch": 85.48, "learning_rate": 8.342949625326314e-06, "loss": 0.001, "step": 355970 }, { "epoch": 85.49, "learning_rate": 8.340964482203612e-06, "loss": 0.0011, "step": 355980 }, { "epoch": 85.49, "learning_rate": 8.338979553791937e-06, "loss": 0.0011, "step": 355990 }, { "epoch": 85.49, "learning_rate": 8.336994840101514e-06, "loss": 0.0011, "step": 356000 }, { "epoch": 85.49, "learning_rate": 8.335010341142551e-06, "loss": 0.0012, "step": 356010 }, { "epoch": 85.49, "learning_rate": 8.333026056925307e-06, "loss": 0.001, "step": 356020 }, { "epoch": 85.5, "learning_rate": 8.331041987459986e-06, "loss": 0.001, "step": 356030 }, { "epoch": 85.5, "learning_rate": 8.329058132756834e-06, "loss": 0.001, "step": 356040 }, { "epoch": 85.5, "learning_rate": 8.327074492826048e-06, "loss": 0.001, "step": 356050 }, { "epoch": 85.5, "learning_rate": 8.325091067677881e-06, "loss": 0.001, "step": 356060 }, { "epoch": 85.51, "learning_rate": 8.323107857322548e-06, "loss": 0.0011, "step": 356070 }, { "epoch": 85.51, "learning_rate": 8.321124861770251e-06, "loss": 0.001, "step": 356080 }, { "epoch": 85.51, "learning_rate": 8.319142081031234e-06, "loss": 0.001, "step": 356090 }, { "epoch": 85.51, "learning_rate": 8.317159515115703e-06, "loss": 0.0011, "step": 356100 }, { "epoch": 85.52, "learning_rate": 8.315177164033883e-06, "loss": 0.0012, "step": 356110 }, { "epoch": 85.52, "learning_rate": 8.313195027795977e-06, "loss": 0.001, "step": 356120 }, { "epoch": 85.52, "learning_rate": 8.31121310641223e-06, "loss": 0.0011, "step": 356130 }, { "epoch": 85.52, "learning_rate": 8.309231399892824e-06, "loss": 0.001, "step": 356140 }, { "epoch": 85.52, "learning_rate": 8.307249908248005e-06, "loss": 0.0011, "step": 356150 }, { "epoch": 85.53, "learning_rate": 8.30526863148795e-06, "loss": 0.001, "step": 356160 }, { "epoch": 85.53, "learning_rate": 8.303287569622903e-06, "loss": 0.0011, "step": 356170 }, { "epoch": 85.53, "learning_rate": 8.30130672266305e-06, "loss": 0.0012, "step": 356180 }, { "epoch": 85.53, "learning_rate": 8.299326090618608e-06, "loss": 0.001, "step": 356190 }, { "epoch": 85.54, "learning_rate": 8.2973456734998e-06, "loss": 0.0011, "step": 356200 }, { "epoch": 85.54, "learning_rate": 8.295365471316824e-06, "loss": 0.0009, "step": 356210 }, { "epoch": 85.54, "learning_rate": 8.293385484079868e-06, "loss": 0.001, "step": 356220 }, { "epoch": 85.54, "learning_rate": 8.29140571179916e-06, "loss": 0.0009, "step": 356230 }, { "epoch": 85.55, "learning_rate": 8.289426154484891e-06, "loss": 0.0011, "step": 356240 }, { "epoch": 85.55, "learning_rate": 8.287446812147276e-06, "loss": 0.001, "step": 356250 }, { "epoch": 85.55, "learning_rate": 8.285467684796499e-06, "loss": 0.0012, "step": 356260 }, { "epoch": 85.55, "learning_rate": 8.283488772442782e-06, "loss": 0.0009, "step": 356270 }, { "epoch": 85.55, "learning_rate": 8.28151007509631e-06, "loss": 0.0011, "step": 356280 }, { "epoch": 85.56, "learning_rate": 8.279531592767276e-06, "loss": 0.0009, "step": 356290 }, { "epoch": 85.56, "learning_rate": 8.277553325465898e-06, "loss": 0.0011, "step": 356300 }, { "epoch": 85.56, "learning_rate": 8.275575273202341e-06, "loss": 0.001, "step": 356310 }, { "epoch": 85.56, "learning_rate": 8.27359743598683e-06, "loss": 0.0011, "step": 356320 }, { "epoch": 85.57, "learning_rate": 8.27161981382954e-06, "loss": 0.001, "step": 356330 }, { "epoch": 85.57, "learning_rate": 8.269642406740679e-06, "loss": 0.0011, "step": 356340 }, { "epoch": 85.57, "learning_rate": 8.26766521473043e-06, "loss": 0.0014, "step": 356350 }, { "epoch": 85.57, "learning_rate": 8.265688237808972e-06, "loss": 0.0012, "step": 356360 }, { "epoch": 85.57, "learning_rate": 8.26371147598652e-06, "loss": 0.0009, "step": 356370 }, { "epoch": 85.58, "learning_rate": 8.26173492927323e-06, "loss": 0.001, "step": 356380 }, { "epoch": 85.58, "learning_rate": 8.259758597679323e-06, "loss": 0.001, "step": 356390 }, { "epoch": 85.58, "learning_rate": 8.257782481214953e-06, "loss": 0.001, "step": 356400 }, { "epoch": 85.58, "learning_rate": 8.255806579890341e-06, "loss": 0.0011, "step": 356410 }, { "epoch": 85.59, "learning_rate": 8.253830893715641e-06, "loss": 0.0009, "step": 356420 }, { "epoch": 85.59, "learning_rate": 8.251855422701043e-06, "loss": 0.001, "step": 356430 }, { "epoch": 85.59, "learning_rate": 8.249880166856728e-06, "loss": 0.001, "step": 356440 }, { "epoch": 85.59, "learning_rate": 8.24790512619289e-06, "loss": 0.001, "step": 356450 }, { "epoch": 85.6, "learning_rate": 8.245930300719684e-06, "loss": 0.0011, "step": 356460 }, { "epoch": 85.6, "learning_rate": 8.243955690447314e-06, "loss": 0.0011, "step": 356470 }, { "epoch": 85.6, "learning_rate": 8.241981295385937e-06, "loss": 0.0013, "step": 356480 }, { "epoch": 85.6, "learning_rate": 8.24000711554575e-06, "loss": 0.001, "step": 356490 }, { "epoch": 85.6, "learning_rate": 8.238033150936902e-06, "loss": 0.001, "step": 356500 }, { "epoch": 85.61, "learning_rate": 8.236059401569591e-06, "loss": 0.0011, "step": 356510 }, { "epoch": 85.61, "learning_rate": 8.234085867453967e-06, "loss": 0.0011, "step": 356520 }, { "epoch": 85.61, "learning_rate": 8.23211254860023e-06, "loss": 0.001, "step": 356530 }, { "epoch": 85.61, "learning_rate": 8.230139445018514e-06, "loss": 0.001, "step": 356540 }, { "epoch": 85.62, "learning_rate": 8.228166556719024e-06, "loss": 0.001, "step": 356550 }, { "epoch": 85.62, "learning_rate": 8.226193883711919e-06, "loss": 0.0011, "step": 356560 }, { "epoch": 85.62, "learning_rate": 8.224221426007339e-06, "loss": 0.001, "step": 356570 }, { "epoch": 85.62, "learning_rate": 8.222249183615487e-06, "loss": 0.0011, "step": 356580 }, { "epoch": 85.62, "learning_rate": 8.220277156546502e-06, "loss": 0.001, "step": 356590 }, { "epoch": 85.63, "learning_rate": 8.218305344810568e-06, "loss": 0.0012, "step": 356600 }, { "epoch": 85.63, "learning_rate": 8.21633374841782e-06, "loss": 0.0011, "step": 356610 }, { "epoch": 85.63, "learning_rate": 8.214362367378454e-06, "loss": 0.0011, "step": 356620 }, { "epoch": 85.63, "learning_rate": 8.212391201702612e-06, "loss": 0.0011, "step": 356630 }, { "epoch": 85.64, "learning_rate": 8.210420251400448e-06, "loss": 0.0009, "step": 356640 }, { "epoch": 85.64, "learning_rate": 8.208449516482136e-06, "loss": 0.0011, "step": 356650 }, { "epoch": 85.64, "learning_rate": 8.206478996957811e-06, "loss": 0.001, "step": 356660 }, { "epoch": 85.64, "learning_rate": 8.20450869283766e-06, "loss": 0.001, "step": 356670 }, { "epoch": 85.65, "learning_rate": 8.202538604131798e-06, "loss": 0.0011, "step": 356680 }, { "epoch": 85.65, "learning_rate": 8.200568730850422e-06, "loss": 0.001, "step": 356690 }, { "epoch": 85.65, "learning_rate": 8.198599073003666e-06, "loss": 0.0011, "step": 356700 }, { "epoch": 85.65, "learning_rate": 8.19662963060166e-06, "loss": 0.001, "step": 356710 }, { "epoch": 85.65, "learning_rate": 8.194660403654591e-06, "loss": 0.001, "step": 356720 }, { "epoch": 85.66, "learning_rate": 8.192691392172581e-06, "loss": 0.001, "step": 356730 }, { "epoch": 85.66, "learning_rate": 8.190722596165794e-06, "loss": 0.001, "step": 356740 }, { "epoch": 85.66, "learning_rate": 8.188754015644368e-06, "loss": 0.0011, "step": 356750 }, { "epoch": 85.66, "learning_rate": 8.18678565061845e-06, "loss": 0.001, "step": 356760 }, { "epoch": 85.67, "learning_rate": 8.184817501098201e-06, "loss": 0.001, "step": 356770 }, { "epoch": 85.67, "learning_rate": 8.182849567093742e-06, "loss": 0.0011, "step": 356780 }, { "epoch": 85.67, "learning_rate": 8.180881848615235e-06, "loss": 0.001, "step": 356790 }, { "epoch": 85.67, "learning_rate": 8.1789143456728e-06, "loss": 0.0011, "step": 356800 }, { "epoch": 85.68, "learning_rate": 8.176947058276602e-06, "loss": 0.0011, "step": 356810 }, { "epoch": 85.68, "learning_rate": 8.174979986436759e-06, "loss": 0.0011, "step": 356820 }, { "epoch": 85.68, "learning_rate": 8.173013130163426e-06, "loss": 0.0011, "step": 356830 }, { "epoch": 85.68, "learning_rate": 8.171046489466728e-06, "loss": 0.001, "step": 356840 }, { "epoch": 85.68, "learning_rate": 8.169080064356816e-06, "loss": 0.001, "step": 356850 }, { "epoch": 85.69, "learning_rate": 8.167113854843811e-06, "loss": 0.0011, "step": 356860 }, { "epoch": 85.69, "learning_rate": 8.165147860937838e-06, "loss": 0.0009, "step": 356870 }, { "epoch": 85.69, "learning_rate": 8.163182082649063e-06, "loss": 0.0011, "step": 356880 }, { "epoch": 85.69, "learning_rate": 8.16121651998758e-06, "loss": 0.0011, "step": 356890 }, { "epoch": 85.7, "learning_rate": 8.159251172963544e-06, "loss": 0.001, "step": 356900 }, { "epoch": 85.7, "learning_rate": 8.15728604158707e-06, "loss": 0.0011, "step": 356910 }, { "epoch": 85.7, "learning_rate": 8.155321125868309e-06, "loss": 0.001, "step": 356920 }, { "epoch": 85.7, "learning_rate": 8.153356425817371e-06, "loss": 0.001, "step": 356930 }, { "epoch": 85.7, "learning_rate": 8.15139194144437e-06, "loss": 0.0013, "step": 356940 }, { "epoch": 85.71, "learning_rate": 8.149427672759451e-06, "loss": 0.001, "step": 356950 }, { "epoch": 85.71, "learning_rate": 8.147463619772727e-06, "loss": 0.0011, "step": 356960 }, { "epoch": 85.71, "learning_rate": 8.145499782494337e-06, "loss": 0.0011, "step": 356970 }, { "epoch": 85.71, "learning_rate": 8.143536160934379e-06, "loss": 0.001, "step": 356980 }, { "epoch": 85.72, "learning_rate": 8.141572755102995e-06, "loss": 0.001, "step": 356990 }, { "epoch": 85.72, "learning_rate": 8.139609565010297e-06, "loss": 0.0011, "step": 357000 }, { "epoch": 85.72, "learning_rate": 8.137646590666387e-06, "loss": 0.0044, "step": 357010 }, { "epoch": 85.72, "learning_rate": 8.135683832081409e-06, "loss": 0.001, "step": 357020 }, { "epoch": 85.73, "learning_rate": 8.133721289265455e-06, "loss": 0.001, "step": 357030 }, { "epoch": 85.73, "learning_rate": 8.131758962228663e-06, "loss": 0.001, "step": 357040 }, { "epoch": 85.73, "learning_rate": 8.129796850981126e-06, "loss": 0.001, "step": 357050 }, { "epoch": 85.73, "learning_rate": 8.127834955532975e-06, "loss": 0.0012, "step": 357060 }, { "epoch": 85.73, "learning_rate": 8.125873275894302e-06, "loss": 0.0011, "step": 357070 }, { "epoch": 85.74, "learning_rate": 8.123911812075224e-06, "loss": 0.0012, "step": 357080 }, { "epoch": 85.74, "learning_rate": 8.121950564085873e-06, "loss": 0.001, "step": 357090 }, { "epoch": 85.74, "learning_rate": 8.119989531936323e-06, "loss": 0.0011, "step": 357100 }, { "epoch": 85.74, "learning_rate": 8.118028715636711e-06, "loss": 0.001, "step": 357110 }, { "epoch": 85.75, "learning_rate": 8.116068115197117e-06, "loss": 0.0011, "step": 357120 }, { "epoch": 85.75, "learning_rate": 8.114107730627667e-06, "loss": 0.001, "step": 357130 }, { "epoch": 85.75, "learning_rate": 8.11214756193846e-06, "loss": 0.001, "step": 357140 }, { "epoch": 85.75, "learning_rate": 8.11018760913958e-06, "loss": 0.0011, "step": 357150 }, { "epoch": 85.76, "learning_rate": 8.108227872241153e-06, "loss": 0.0011, "step": 357160 }, { "epoch": 85.76, "learning_rate": 8.106268351253265e-06, "loss": 0.0016, "step": 357170 }, { "epoch": 85.76, "learning_rate": 8.104309046186026e-06, "loss": 0.001, "step": 357180 }, { "epoch": 85.76, "learning_rate": 8.102349957049516e-06, "loss": 0.0009, "step": 357190 }, { "epoch": 85.76, "learning_rate": 8.10039108385386e-06, "loss": 0.0011, "step": 357200 }, { "epoch": 85.77, "learning_rate": 8.098432426609138e-06, "loss": 0.0012, "step": 357210 }, { "epoch": 85.77, "learning_rate": 8.096473985325432e-06, "loss": 0.001, "step": 357220 }, { "epoch": 85.77, "learning_rate": 8.094515760012861e-06, "loss": 0.001, "step": 357230 }, { "epoch": 85.77, "learning_rate": 8.092557750681496e-06, "loss": 0.0011, "step": 357240 }, { "epoch": 85.78, "learning_rate": 8.090599957341449e-06, "loss": 0.001, "step": 357250 }, { "epoch": 85.78, "learning_rate": 8.088642380002786e-06, "loss": 0.0064, "step": 357260 }, { "epoch": 85.78, "learning_rate": 8.086685018675627e-06, "loss": 0.001, "step": 357270 }, { "epoch": 85.78, "learning_rate": 8.084727873370045e-06, "loss": 0.001, "step": 357280 }, { "epoch": 85.78, "learning_rate": 8.082770944096107e-06, "loss": 0.0011, "step": 357290 }, { "epoch": 85.79, "learning_rate": 8.080814230863936e-06, "loss": 0.0011, "step": 357300 }, { "epoch": 85.79, "learning_rate": 8.078857733683587e-06, "loss": 0.0009, "step": 357310 }, { "epoch": 85.79, "learning_rate": 8.07690145256516e-06, "loss": 0.001, "step": 357320 }, { "epoch": 85.79, "learning_rate": 8.074945387518728e-06, "loss": 0.0012, "step": 357330 }, { "epoch": 85.8, "learning_rate": 8.072989538554387e-06, "loss": 0.0009, "step": 357340 }, { "epoch": 85.8, "learning_rate": 8.071033905682201e-06, "loss": 0.0009, "step": 357350 }, { "epoch": 85.8, "learning_rate": 8.06907848891227e-06, "loss": 0.0011, "step": 357360 }, { "epoch": 85.8, "learning_rate": 8.067123288254642e-06, "loss": 0.0011, "step": 357370 }, { "epoch": 85.81, "learning_rate": 8.065168303719406e-06, "loss": 0.0011, "step": 357380 }, { "epoch": 85.81, "learning_rate": 8.06321353531666e-06, "loss": 0.0011, "step": 357390 }, { "epoch": 85.81, "learning_rate": 8.061258983056452e-06, "loss": 0.001, "step": 357400 }, { "epoch": 85.81, "learning_rate": 8.059304646948878e-06, "loss": 0.001, "step": 357410 }, { "epoch": 85.81, "learning_rate": 8.057350527003998e-06, "loss": 0.0012, "step": 357420 }, { "epoch": 85.82, "learning_rate": 8.05539662323187e-06, "loss": 0.0011, "step": 357430 }, { "epoch": 85.82, "learning_rate": 8.053442935642592e-06, "loss": 0.0011, "step": 357440 }, { "epoch": 85.82, "learning_rate": 8.051489464246204e-06, "loss": 0.0011, "step": 357450 }, { "epoch": 85.82, "learning_rate": 8.049536209052805e-06, "loss": 0.001, "step": 357460 }, { "epoch": 85.83, "learning_rate": 8.047583170072436e-06, "loss": 0.0009, "step": 357470 }, { "epoch": 85.83, "learning_rate": 8.045630347315186e-06, "loss": 0.001, "step": 357480 }, { "epoch": 85.83, "learning_rate": 8.043677740791105e-06, "loss": 0.001, "step": 357490 }, { "epoch": 85.83, "learning_rate": 8.041725350510255e-06, "loss": 0.0011, "step": 357500 }, { "epoch": 85.84, "learning_rate": 8.039773176482706e-06, "loss": 0.001, "step": 357510 }, { "epoch": 85.84, "learning_rate": 8.03782121871851e-06, "loss": 0.001, "step": 357520 }, { "epoch": 85.84, "learning_rate": 8.035869477227741e-06, "loss": 0.001, "step": 357530 }, { "epoch": 85.84, "learning_rate": 8.033917952020448e-06, "loss": 0.0011, "step": 357540 }, { "epoch": 85.84, "learning_rate": 8.031966643106698e-06, "loss": 0.0011, "step": 357550 }, { "epoch": 85.85, "learning_rate": 8.030015550496545e-06, "loss": 0.001, "step": 357560 }, { "epoch": 85.85, "learning_rate": 8.028064674200032e-06, "loss": 0.0011, "step": 357570 }, { "epoch": 85.85, "learning_rate": 8.026114014227232e-06, "loss": 0.001, "step": 357580 }, { "epoch": 85.85, "learning_rate": 8.024163570588184e-06, "loss": 0.001, "step": 357590 }, { "epoch": 85.86, "learning_rate": 8.022213343292956e-06, "loss": 0.0009, "step": 357600 }, { "epoch": 85.86, "learning_rate": 8.02026333235158e-06, "loss": 0.0012, "step": 357610 }, { "epoch": 85.86, "learning_rate": 8.01831353777413e-06, "loss": 0.001, "step": 357620 }, { "epoch": 85.86, "learning_rate": 8.016363959570633e-06, "loss": 0.001, "step": 357630 }, { "epoch": 85.86, "learning_rate": 8.014414597751158e-06, "loss": 0.001, "step": 357640 }, { "epoch": 85.87, "learning_rate": 8.012465452325729e-06, "loss": 0.0011, "step": 357650 }, { "epoch": 85.87, "learning_rate": 8.010516523304418e-06, "loss": 0.0011, "step": 357660 }, { "epoch": 85.87, "learning_rate": 8.008567810697243e-06, "loss": 0.001, "step": 357670 }, { "epoch": 85.87, "learning_rate": 8.00661931451427e-06, "loss": 0.0011, "step": 357680 }, { "epoch": 85.88, "learning_rate": 8.00467103476552e-06, "loss": 0.001, "step": 357690 }, { "epoch": 85.88, "learning_rate": 8.002722971461046e-06, "loss": 0.0011, "step": 357700 }, { "epoch": 85.88, "learning_rate": 8.000775124610904e-06, "loss": 0.001, "step": 357710 }, { "epoch": 85.88, "learning_rate": 7.99882749422512e-06, "loss": 0.0011, "step": 357720 }, { "epoch": 85.89, "learning_rate": 7.996880080313712e-06, "loss": 0.001, "step": 357730 }, { "epoch": 85.89, "learning_rate": 7.994932882886752e-06, "loss": 0.001, "step": 357740 }, { "epoch": 85.89, "learning_rate": 7.992985901954242e-06, "loss": 0.001, "step": 357750 }, { "epoch": 85.89, "learning_rate": 7.991039137526252e-06, "loss": 0.001, "step": 357760 }, { "epoch": 85.89, "learning_rate": 7.98909258961278e-06, "loss": 0.001, "step": 357770 }, { "epoch": 85.9, "learning_rate": 7.987146258223894e-06, "loss": 0.001, "step": 357780 }, { "epoch": 85.9, "learning_rate": 7.985200143369604e-06, "loss": 0.0011, "step": 357790 }, { "epoch": 85.9, "learning_rate": 7.98325424505993e-06, "loss": 0.0011, "step": 357800 }, { "epoch": 85.9, "learning_rate": 7.98130856330493e-06, "loss": 0.001, "step": 357810 }, { "epoch": 85.91, "learning_rate": 7.9793630981146e-06, "loss": 0.0009, "step": 357820 }, { "epoch": 85.91, "learning_rate": 7.977417849498996e-06, "loss": 0.0009, "step": 357830 }, { "epoch": 85.91, "learning_rate": 7.975472817468126e-06, "loss": 0.0013, "step": 357840 }, { "epoch": 85.91, "learning_rate": 7.973528002032028e-06, "loss": 0.0009, "step": 357850 }, { "epoch": 85.92, "learning_rate": 7.971583403200722e-06, "loss": 0.0011, "step": 357860 }, { "epoch": 85.92, "learning_rate": 7.96963902098421e-06, "loss": 0.001, "step": 357870 }, { "epoch": 85.92, "learning_rate": 7.967694855392543e-06, "loss": 0.001, "step": 357880 }, { "epoch": 85.92, "learning_rate": 7.965750906435714e-06, "loss": 0.0012, "step": 357890 }, { "epoch": 85.92, "learning_rate": 7.963807174123773e-06, "loss": 0.0009, "step": 357900 }, { "epoch": 85.93, "learning_rate": 7.961863658466706e-06, "loss": 0.001, "step": 357910 }, { "epoch": 85.93, "learning_rate": 7.959920359474555e-06, "loss": 0.0011, "step": 357920 }, { "epoch": 85.93, "learning_rate": 7.95797727715733e-06, "loss": 0.0045, "step": 357930 }, { "epoch": 85.93, "learning_rate": 7.956034411525026e-06, "loss": 0.0009, "step": 357940 }, { "epoch": 85.94, "learning_rate": 7.954091762587678e-06, "loss": 0.0011, "step": 357950 }, { "epoch": 85.94, "learning_rate": 7.952149330355296e-06, "loss": 0.0012, "step": 357960 }, { "epoch": 85.94, "learning_rate": 7.950207114837882e-06, "loss": 0.0011, "step": 357970 }, { "epoch": 85.94, "learning_rate": 7.948265116045461e-06, "loss": 0.001, "step": 357980 }, { "epoch": 85.94, "learning_rate": 7.946323333988025e-06, "loss": 0.001, "step": 357990 }, { "epoch": 85.95, "learning_rate": 7.944381768675602e-06, "loss": 0.001, "step": 358000 }, { "epoch": 85.95, "learning_rate": 7.942440420118169e-06, "loss": 0.0009, "step": 358010 }, { "epoch": 86.0, "learning_rate": 7.940499288325765e-06, "loss": 0.001, "step": 358020 }, { "epoch": 86.0, "learning_rate": 7.93855837330837e-06, "loss": 0.001, "step": 358030 }, { "epoch": 86.01, "learning_rate": 7.936617675076002e-06, "loss": 0.0051, "step": 358040 }, { "epoch": 86.01, "learning_rate": 7.934677193638651e-06, "loss": 0.001, "step": 358050 }, { "epoch": 86.01, "learning_rate": 7.93273692900634e-06, "loss": 0.001, "step": 358060 }, { "epoch": 86.01, "learning_rate": 7.93079688118905e-06, "loss": 0.001, "step": 358070 }, { "epoch": 86.01, "learning_rate": 7.928857050196775e-06, "loss": 0.0011, "step": 358080 }, { "epoch": 86.02, "learning_rate": 7.926917436039532e-06, "loss": 0.0011, "step": 358090 }, { "epoch": 86.02, "learning_rate": 7.9249780387273e-06, "loss": 0.0011, "step": 358100 }, { "epoch": 86.02, "learning_rate": 7.923038858270087e-06, "loss": 0.0009, "step": 358110 }, { "epoch": 86.02, "learning_rate": 7.92109989467788e-06, "loss": 0.001, "step": 358120 }, { "epoch": 86.03, "learning_rate": 7.91916114796068e-06, "loss": 0.0011, "step": 358130 }, { "epoch": 86.03, "learning_rate": 7.917222618128483e-06, "loss": 0.001, "step": 358140 }, { "epoch": 86.03, "learning_rate": 7.915284305191256e-06, "loss": 0.001, "step": 358150 }, { "epoch": 86.03, "learning_rate": 7.913346209159016e-06, "loss": 0.0012, "step": 358160 }, { "epoch": 86.03, "learning_rate": 7.911408330041736e-06, "loss": 0.0009, "step": 358170 }, { "epoch": 86.04, "learning_rate": 7.909470667849416e-06, "loss": 0.0009, "step": 358180 }, { "epoch": 86.04, "learning_rate": 7.907533222592022e-06, "loss": 0.0009, "step": 358190 }, { "epoch": 86.04, "learning_rate": 7.905595994279568e-06, "loss": 0.0011, "step": 358200 }, { "epoch": 86.04, "learning_rate": 7.90365898292203e-06, "loss": 0.001, "step": 358210 }, { "epoch": 86.05, "learning_rate": 7.901722188529364e-06, "loss": 0.0011, "step": 358220 }, { "epoch": 86.05, "learning_rate": 7.899785611111594e-06, "loss": 0.001, "step": 358230 }, { "epoch": 86.05, "learning_rate": 7.897849250678662e-06, "loss": 0.001, "step": 358240 }, { "epoch": 86.05, "learning_rate": 7.895913107240582e-06, "loss": 0.001, "step": 358250 }, { "epoch": 86.06, "learning_rate": 7.893977180807305e-06, "loss": 0.0009, "step": 358260 }, { "epoch": 86.06, "learning_rate": 7.892041471388823e-06, "loss": 0.001, "step": 358270 }, { "epoch": 86.06, "learning_rate": 7.890105978995122e-06, "loss": 0.0009, "step": 358280 }, { "epoch": 86.06, "learning_rate": 7.888170703636156e-06, "loss": 0.0012, "step": 358290 }, { "epoch": 86.06, "learning_rate": 7.88623564532192e-06, "loss": 0.0011, "step": 358300 }, { "epoch": 86.07, "learning_rate": 7.884300804062366e-06, "loss": 0.0009, "step": 358310 }, { "epoch": 86.07, "learning_rate": 7.88236617986749e-06, "loss": 0.0011, "step": 358320 }, { "epoch": 86.07, "learning_rate": 7.880431772747243e-06, "loss": 0.001, "step": 358330 }, { "epoch": 86.07, "learning_rate": 7.878497582711608e-06, "loss": 0.001, "step": 358340 }, { "epoch": 86.08, "learning_rate": 7.876563609770554e-06, "loss": 0.001, "step": 358350 }, { "epoch": 86.08, "learning_rate": 7.87462985393403e-06, "loss": 0.0011, "step": 358360 }, { "epoch": 86.08, "learning_rate": 7.872696315212025e-06, "loss": 0.001, "step": 358370 }, { "epoch": 86.08, "learning_rate": 7.870762993614483e-06, "loss": 0.001, "step": 358380 }, { "epoch": 86.09, "learning_rate": 7.868829889151397e-06, "loss": 0.0009, "step": 358390 }, { "epoch": 86.09, "learning_rate": 7.866897001832696e-06, "loss": 0.001, "step": 358400 }, { "epoch": 86.09, "learning_rate": 7.864964331668378e-06, "loss": 0.0009, "step": 358410 }, { "epoch": 86.09, "learning_rate": 7.86303187866837e-06, "loss": 0.0027, "step": 358420 }, { "epoch": 86.09, "learning_rate": 7.861099642842662e-06, "loss": 0.0011, "step": 358430 }, { "epoch": 86.1, "learning_rate": 7.859167624201197e-06, "loss": 0.001, "step": 358440 }, { "epoch": 86.1, "learning_rate": 7.857235822753928e-06, "loss": 0.001, "step": 358450 }, { "epoch": 86.1, "learning_rate": 7.855304238510824e-06, "loss": 0.001, "step": 358460 }, { "epoch": 86.1, "learning_rate": 7.853372871481823e-06, "loss": 0.0011, "step": 358470 }, { "epoch": 86.11, "learning_rate": 7.851441721676905e-06, "loss": 0.001, "step": 358480 }, { "epoch": 86.11, "learning_rate": 7.849510789105991e-06, "loss": 0.0011, "step": 358490 }, { "epoch": 86.11, "learning_rate": 7.847580073779071e-06, "loss": 0.001, "step": 358500 }, { "epoch": 86.11, "learning_rate": 7.845649575706065e-06, "loss": 0.001, "step": 358510 }, { "epoch": 86.11, "learning_rate": 7.843719294896929e-06, "loss": 0.001, "step": 358520 }, { "epoch": 86.12, "learning_rate": 7.841789231361628e-06, "loss": 0.0011, "step": 358530 }, { "epoch": 86.12, "learning_rate": 7.839859385110083e-06, "loss": 0.0009, "step": 358540 }, { "epoch": 86.12, "learning_rate": 7.837929756152268e-06, "loss": 0.001, "step": 358550 }, { "epoch": 86.12, "learning_rate": 7.836000344498107e-06, "loss": 0.0009, "step": 358560 }, { "epoch": 86.13, "learning_rate": 7.834071150157563e-06, "loss": 0.001, "step": 358570 }, { "epoch": 86.13, "learning_rate": 7.832142173140555e-06, "loss": 0.0011, "step": 358580 }, { "epoch": 86.13, "learning_rate": 7.830213413457038e-06, "loss": 0.0011, "step": 358590 }, { "epoch": 86.13, "learning_rate": 7.828284871116964e-06, "loss": 0.0009, "step": 358600 }, { "epoch": 86.14, "learning_rate": 7.826356546130254e-06, "loss": 0.001, "step": 358610 }, { "epoch": 86.14, "learning_rate": 7.824428438506864e-06, "loss": 0.001, "step": 358620 }, { "epoch": 86.14, "learning_rate": 7.822500548256712e-06, "loss": 0.001, "step": 358630 }, { "epoch": 86.14, "learning_rate": 7.820572875389758e-06, "loss": 0.001, "step": 358640 }, { "epoch": 86.14, "learning_rate": 7.818645419915926e-06, "loss": 0.001, "step": 358650 }, { "epoch": 86.15, "learning_rate": 7.816718181845128e-06, "loss": 0.001, "step": 358660 }, { "epoch": 86.15, "learning_rate": 7.814791161187335e-06, "loss": 0.001, "step": 358670 }, { "epoch": 86.15, "learning_rate": 7.812864357952448e-06, "loss": 0.0011, "step": 358680 }, { "epoch": 86.15, "learning_rate": 7.810937772150423e-06, "loss": 0.001, "step": 358690 }, { "epoch": 86.16, "learning_rate": 7.809011403791166e-06, "loss": 0.0009, "step": 358700 }, { "epoch": 86.16, "learning_rate": 7.807085252884626e-06, "loss": 0.0011, "step": 358710 }, { "epoch": 86.16, "learning_rate": 7.805159319440725e-06, "loss": 0.0027, "step": 358720 }, { "epoch": 86.16, "learning_rate": 7.803233603469372e-06, "loss": 0.0011, "step": 358730 }, { "epoch": 86.16, "learning_rate": 7.801308104980521e-06, "loss": 0.0009, "step": 358740 }, { "epoch": 86.17, "learning_rate": 7.799382823984064e-06, "loss": 0.001, "step": 358750 }, { "epoch": 86.17, "learning_rate": 7.797457760489951e-06, "loss": 0.0011, "step": 358760 }, { "epoch": 86.17, "learning_rate": 7.795532914508086e-06, "loss": 0.001, "step": 358770 }, { "epoch": 86.17, "learning_rate": 7.79360828604841e-06, "loss": 0.001, "step": 358780 }, { "epoch": 86.18, "learning_rate": 7.791683875120826e-06, "loss": 0.001, "step": 358790 }, { "epoch": 86.18, "learning_rate": 7.789759681735242e-06, "loss": 0.001, "step": 358800 }, { "epoch": 86.18, "learning_rate": 7.787835705901608e-06, "loss": 0.001, "step": 358810 }, { "epoch": 86.18, "learning_rate": 7.785911947629803e-06, "loss": 0.001, "step": 358820 }, { "epoch": 86.19, "learning_rate": 7.783988406929777e-06, "loss": 0.001, "step": 358830 }, { "epoch": 86.19, "learning_rate": 7.782065083811414e-06, "loss": 0.0009, "step": 358840 }, { "epoch": 86.19, "learning_rate": 7.780141978284655e-06, "loss": 0.001, "step": 358850 }, { "epoch": 86.19, "learning_rate": 7.778219090359384e-06, "loss": 0.0009, "step": 358860 }, { "epoch": 86.19, "learning_rate": 7.776296420045537e-06, "loss": 0.001, "step": 358870 }, { "epoch": 86.2, "learning_rate": 7.774373967352994e-06, "loss": 0.0009, "step": 358880 }, { "epoch": 86.2, "learning_rate": 7.772451732291697e-06, "loss": 0.0009, "step": 358890 }, { "epoch": 86.2, "learning_rate": 7.770529714871527e-06, "loss": 0.0011, "step": 358900 }, { "epoch": 86.2, "learning_rate": 7.768607915102393e-06, "loss": 0.0011, "step": 358910 }, { "epoch": 86.21, "learning_rate": 7.766686332994227e-06, "loss": 0.001, "step": 358920 }, { "epoch": 86.21, "learning_rate": 7.764764968556909e-06, "loss": 0.0011, "step": 358930 }, { "epoch": 86.21, "learning_rate": 7.762843821800331e-06, "loss": 0.001, "step": 358940 }, { "epoch": 86.21, "learning_rate": 7.760922892734424e-06, "loss": 0.001, "step": 358950 }, { "epoch": 86.22, "learning_rate": 7.759002181369063e-06, "loss": 0.001, "step": 358960 }, { "epoch": 86.22, "learning_rate": 7.757081687714168e-06, "loss": 0.0009, "step": 358970 }, { "epoch": 86.22, "learning_rate": 7.75516141177961e-06, "loss": 0.001, "step": 358980 }, { "epoch": 86.22, "learning_rate": 7.753241353575324e-06, "loss": 0.001, "step": 358990 }, { "epoch": 86.22, "learning_rate": 7.751321513111176e-06, "loss": 0.001, "step": 359000 }, { "epoch": 86.23, "learning_rate": 7.749401890397068e-06, "loss": 0.0009, "step": 359010 }, { "epoch": 86.23, "learning_rate": 7.747482485442902e-06, "loss": 0.0011, "step": 359020 }, { "epoch": 86.23, "learning_rate": 7.74556329825855e-06, "loss": 0.001, "step": 359030 }, { "epoch": 86.23, "learning_rate": 7.743644328853933e-06, "loss": 0.001, "step": 359040 }, { "epoch": 86.24, "learning_rate": 7.741725577238917e-06, "loss": 0.001, "step": 359050 }, { "epoch": 86.24, "learning_rate": 7.739807043423407e-06, "loss": 0.0009, "step": 359060 }, { "epoch": 86.24, "learning_rate": 7.737888727417292e-06, "loss": 0.001, "step": 359070 }, { "epoch": 86.24, "learning_rate": 7.735970629230432e-06, "loss": 0.0009, "step": 359080 }, { "epoch": 86.24, "learning_rate": 7.73405274887275e-06, "loss": 0.001, "step": 359090 }, { "epoch": 86.25, "learning_rate": 7.732135086354098e-06, "loss": 0.001, "step": 359100 }, { "epoch": 86.25, "learning_rate": 7.730217641684389e-06, "loss": 0.0011, "step": 359110 }, { "epoch": 86.25, "learning_rate": 7.72830041487348e-06, "loss": 0.0009, "step": 359120 }, { "epoch": 86.25, "learning_rate": 7.726383405931276e-06, "loss": 0.0009, "step": 359130 }, { "epoch": 86.26, "learning_rate": 7.724466614867643e-06, "loss": 0.0011, "step": 359140 }, { "epoch": 86.26, "learning_rate": 7.722550041692455e-06, "loss": 0.001, "step": 359150 }, { "epoch": 86.26, "learning_rate": 7.720633686415596e-06, "loss": 0.001, "step": 359160 }, { "epoch": 86.26, "learning_rate": 7.718717549046956e-06, "loss": 0.001, "step": 359170 }, { "epoch": 86.27, "learning_rate": 7.716801629596383e-06, "loss": 0.0009, "step": 359180 }, { "epoch": 86.27, "learning_rate": 7.714885928073784e-06, "loss": 0.0011, "step": 359190 }, { "epoch": 86.27, "learning_rate": 7.712970444489004e-06, "loss": 0.001, "step": 359200 }, { "epoch": 86.27, "learning_rate": 7.711055178851928e-06, "loss": 0.0011, "step": 359210 }, { "epoch": 86.27, "learning_rate": 7.709140131172437e-06, "loss": 0.001, "step": 359220 }, { "epoch": 86.28, "learning_rate": 7.707225301460391e-06, "loss": 0.0009, "step": 359230 }, { "epoch": 86.28, "learning_rate": 7.705310689725647e-06, "loss": 0.0009, "step": 359240 }, { "epoch": 86.28, "learning_rate": 7.7033962959781e-06, "loss": 0.001, "step": 359250 }, { "epoch": 86.28, "learning_rate": 7.701482120227587e-06, "loss": 0.0011, "step": 359260 }, { "epoch": 86.29, "learning_rate": 7.699568162484005e-06, "loss": 0.001, "step": 359270 }, { "epoch": 86.29, "learning_rate": 7.697654422757188e-06, "loss": 0.001, "step": 359280 }, { "epoch": 86.29, "learning_rate": 7.695740901057025e-06, "loss": 0.0011, "step": 359290 }, { "epoch": 86.29, "learning_rate": 7.693827597393372e-06, "loss": 0.001, "step": 359300 }, { "epoch": 86.3, "learning_rate": 7.691914511776067e-06, "loss": 0.0011, "step": 359310 }, { "epoch": 86.3, "learning_rate": 7.690001644215e-06, "loss": 0.001, "step": 359320 }, { "epoch": 86.3, "learning_rate": 7.68808899472001e-06, "loss": 0.001, "step": 359330 }, { "epoch": 86.3, "learning_rate": 7.686176563300973e-06, "loss": 0.001, "step": 359340 }, { "epoch": 86.3, "learning_rate": 7.684264349967724e-06, "loss": 0.0009, "step": 359350 }, { "epoch": 86.31, "learning_rate": 7.682352354730144e-06, "loss": 0.001, "step": 359360 }, { "epoch": 86.31, "learning_rate": 7.68044057759807e-06, "loss": 0.001, "step": 359370 }, { "epoch": 86.31, "learning_rate": 7.678529018581349e-06, "loss": 0.0011, "step": 359380 }, { "epoch": 86.31, "learning_rate": 7.676617677689857e-06, "loss": 0.001, "step": 359390 }, { "epoch": 86.32, "learning_rate": 7.674706554933414e-06, "loss": 0.0011, "step": 359400 }, { "epoch": 86.32, "learning_rate": 7.672795650321907e-06, "loss": 0.001, "step": 359410 }, { "epoch": 86.32, "learning_rate": 7.670884963865143e-06, "loss": 0.0009, "step": 359420 }, { "epoch": 86.32, "learning_rate": 7.668974495573012e-06, "loss": 0.0011, "step": 359430 }, { "epoch": 86.32, "learning_rate": 7.667064245455335e-06, "loss": 0.0009, "step": 359440 }, { "epoch": 86.33, "learning_rate": 7.665154213521958e-06, "loss": 0.001, "step": 359450 }, { "epoch": 86.33, "learning_rate": 7.663244399782738e-06, "loss": 0.0011, "step": 359460 }, { "epoch": 86.33, "learning_rate": 7.661334804247494e-06, "loss": 0.001, "step": 359470 }, { "epoch": 86.33, "learning_rate": 7.659425426926086e-06, "loss": 0.001, "step": 359480 }, { "epoch": 86.34, "learning_rate": 7.657516267828368e-06, "loss": 0.001, "step": 359490 }, { "epoch": 86.34, "learning_rate": 7.655607326964154e-06, "loss": 0.001, "step": 359500 }, { "epoch": 86.34, "learning_rate": 7.653698604343307e-06, "loss": 0.001, "step": 359510 }, { "epoch": 86.34, "learning_rate": 7.651790099975637e-06, "loss": 0.0011, "step": 359520 }, { "epoch": 86.35, "learning_rate": 7.649881813871002e-06, "loss": 0.0011, "step": 359530 }, { "epoch": 86.35, "learning_rate": 7.647973746039222e-06, "loss": 0.0011, "step": 359540 }, { "epoch": 86.35, "learning_rate": 7.646065896490156e-06, "loss": 0.001, "step": 359550 }, { "epoch": 86.35, "learning_rate": 7.644158265233603e-06, "loss": 0.001, "step": 359560 }, { "epoch": 86.35, "learning_rate": 7.642250852279425e-06, "loss": 0.001, "step": 359570 }, { "epoch": 86.36, "learning_rate": 7.640343657637439e-06, "loss": 0.0011, "step": 359580 }, { "epoch": 86.36, "learning_rate": 7.638436681317468e-06, "loss": 0.001, "step": 359590 }, { "epoch": 86.36, "learning_rate": 7.636529923329355e-06, "loss": 0.001, "step": 359600 }, { "epoch": 86.36, "learning_rate": 7.634623383682916e-06, "loss": 0.004, "step": 359610 }, { "epoch": 86.37, "learning_rate": 7.63271706238799e-06, "loss": 0.001, "step": 359620 }, { "epoch": 86.37, "learning_rate": 7.630810959454383e-06, "loss": 0.0009, "step": 359630 }, { "epoch": 86.37, "learning_rate": 7.6289050748919396e-06, "loss": 0.001, "step": 359640 }, { "epoch": 86.37, "learning_rate": 7.626999408710472e-06, "loss": 0.0011, "step": 359650 }, { "epoch": 86.38, "learning_rate": 7.625093960919799e-06, "loss": 0.001, "step": 359660 }, { "epoch": 86.38, "learning_rate": 7.623188731529751e-06, "loss": 0.0009, "step": 359670 }, { "epoch": 86.38, "learning_rate": 7.621283720550137e-06, "loss": 0.0009, "step": 359680 }, { "epoch": 86.38, "learning_rate": 7.6193789279907894e-06, "loss": 0.0011, "step": 359690 }, { "epoch": 86.38, "learning_rate": 7.617474353861504e-06, "loss": 0.001, "step": 359700 }, { "epoch": 86.39, "learning_rate": 7.615569998172123e-06, "loss": 0.0009, "step": 359710 }, { "epoch": 86.39, "learning_rate": 7.613665860932451e-06, "loss": 0.0011, "step": 359720 }, { "epoch": 86.39, "learning_rate": 7.611761942152285e-06, "loss": 0.001, "step": 359730 }, { "epoch": 86.39, "learning_rate": 7.6098582418414665e-06, "loss": 0.001, "step": 359740 }, { "epoch": 86.4, "learning_rate": 7.607954760009778e-06, "loss": 0.0009, "step": 359750 }, { "epoch": 86.4, "learning_rate": 7.606051496667061e-06, "loss": 0.001, "step": 359760 }, { "epoch": 86.4, "learning_rate": 7.60414845182309e-06, "loss": 0.001, "step": 359770 }, { "epoch": 86.4, "learning_rate": 7.6022456254876975e-06, "loss": 0.0009, "step": 359780 }, { "epoch": 86.4, "learning_rate": 7.600343017670697e-06, "loss": 0.0011, "step": 359790 }, { "epoch": 86.41, "learning_rate": 7.59844062838187e-06, "loss": 0.001, "step": 359800 }, { "epoch": 86.41, "learning_rate": 7.596538457631047e-06, "loss": 0.001, "step": 359810 }, { "epoch": 86.41, "learning_rate": 7.59463650542801e-06, "loss": 0.0011, "step": 359820 }, { "epoch": 86.41, "learning_rate": 7.592734771782578e-06, "loss": 0.001, "step": 359830 }, { "epoch": 86.42, "learning_rate": 7.590833256704533e-06, "loss": 0.001, "step": 359840 }, { "epoch": 86.42, "learning_rate": 7.588931960203705e-06, "loss": 0.001, "step": 359850 }, { "epoch": 86.42, "learning_rate": 7.5870308822898695e-06, "loss": 0.001, "step": 359860 }, { "epoch": 86.42, "learning_rate": 7.585130022972825e-06, "loss": 0.0009, "step": 359870 }, { "epoch": 86.43, "learning_rate": 7.583229382262386e-06, "loss": 0.0012, "step": 359880 }, { "epoch": 86.43, "learning_rate": 7.581328960168327e-06, "loss": 0.001, "step": 359890 }, { "epoch": 86.43, "learning_rate": 7.579428756700463e-06, "loss": 0.001, "step": 359900 }, { "epoch": 86.43, "learning_rate": 7.577528771868564e-06, "loss": 0.001, "step": 359910 }, { "epoch": 86.43, "learning_rate": 7.575629005682449e-06, "loss": 0.001, "step": 359920 }, { "epoch": 86.44, "learning_rate": 7.573729458151896e-06, "loss": 0.0011, "step": 359930 }, { "epoch": 86.44, "learning_rate": 7.571830129286689e-06, "loss": 0.001, "step": 359940 }, { "epoch": 86.44, "learning_rate": 7.569931019096632e-06, "loss": 0.0011, "step": 359950 }, { "epoch": 86.44, "learning_rate": 7.56803212759149e-06, "loss": 0.001, "step": 359960 }, { "epoch": 86.45, "learning_rate": 7.566133454781083e-06, "loss": 0.0009, "step": 359970 }, { "epoch": 86.45, "learning_rate": 7.564235000675163e-06, "loss": 0.001, "step": 359980 }, { "epoch": 86.45, "learning_rate": 7.562336765283545e-06, "loss": 0.001, "step": 359990 }, { "epoch": 86.45, "learning_rate": 7.5604387486159836e-06, "loss": 0.001, "step": 360000 }, { "epoch": 86.46, "learning_rate": 7.558540950682291e-06, "loss": 0.0009, "step": 360010 }, { "epoch": 86.46, "learning_rate": 7.556643371492233e-06, "loss": 0.001, "step": 360020 }, { "epoch": 86.46, "learning_rate": 7.554746011055575e-06, "loss": 0.0011, "step": 360030 }, { "epoch": 86.46, "learning_rate": 7.552848869382123e-06, "loss": 0.001, "step": 360040 }, { "epoch": 86.46, "learning_rate": 7.550951946481632e-06, "loss": 0.0009, "step": 360050 }, { "epoch": 86.47, "learning_rate": 7.5490552423639e-06, "loss": 0.001, "step": 360060 }, { "epoch": 86.47, "learning_rate": 7.547158757038686e-06, "loss": 0.001, "step": 360070 }, { "epoch": 86.47, "learning_rate": 7.545262490515775e-06, "loss": 0.001, "step": 360080 }, { "epoch": 86.47, "learning_rate": 7.5433664428049275e-06, "loss": 0.001, "step": 360090 }, { "epoch": 86.48, "learning_rate": 7.541470613915924e-06, "loss": 0.001, "step": 360100 }, { "epoch": 86.48, "learning_rate": 7.539575003858546e-06, "loss": 0.001, "step": 360110 }, { "epoch": 86.48, "learning_rate": 7.537679612642546e-06, "loss": 0.0009, "step": 360120 }, { "epoch": 86.48, "learning_rate": 7.53578444027771e-06, "loss": 0.001, "step": 360130 }, { "epoch": 86.48, "learning_rate": 7.533889486773782e-06, "loss": 0.0009, "step": 360140 }, { "epoch": 86.49, "learning_rate": 7.531994752140553e-06, "loss": 0.0011, "step": 360150 }, { "epoch": 86.49, "learning_rate": 7.530100236387782e-06, "loss": 0.001, "step": 360160 }, { "epoch": 86.49, "learning_rate": 7.528205939525218e-06, "loss": 0.001, "step": 360170 }, { "epoch": 86.49, "learning_rate": 7.526311861562646e-06, "loss": 0.0009, "step": 360180 }, { "epoch": 86.5, "learning_rate": 7.524418002509803e-06, "loss": 0.001, "step": 360190 }, { "epoch": 86.5, "learning_rate": 7.522524362376482e-06, "loss": 0.0011, "step": 360200 }, { "epoch": 86.5, "learning_rate": 7.5206309411724076e-06, "loss": 0.0009, "step": 360210 }, { "epoch": 86.5, "learning_rate": 7.518737738907372e-06, "loss": 0.001, "step": 360220 }, { "epoch": 86.51, "learning_rate": 7.5168447555911185e-06, "loss": 0.0011, "step": 360230 }, { "epoch": 86.51, "learning_rate": 7.514951991233387e-06, "loss": 0.0009, "step": 360240 }, { "epoch": 86.51, "learning_rate": 7.513059445843962e-06, "loss": 0.0011, "step": 360250 }, { "epoch": 86.51, "learning_rate": 7.511167119432571e-06, "loss": 0.0011, "step": 360260 }, { "epoch": 86.51, "learning_rate": 7.509275012008987e-06, "loss": 0.001, "step": 360270 }, { "epoch": 86.52, "learning_rate": 7.50738312358295e-06, "loss": 0.0009, "step": 360280 }, { "epoch": 86.52, "learning_rate": 7.505491454164226e-06, "loss": 0.001, "step": 360290 }, { "epoch": 86.52, "learning_rate": 7.503600003762551e-06, "loss": 0.0009, "step": 360300 }, { "epoch": 86.52, "learning_rate": 7.501708772387666e-06, "loss": 0.001, "step": 360310 }, { "epoch": 86.53, "learning_rate": 7.499817760049344e-06, "loss": 0.0093, "step": 360320 }, { "epoch": 86.53, "learning_rate": 7.497926966757307e-06, "loss": 0.0009, "step": 360330 }, { "epoch": 86.53, "learning_rate": 7.496036392521316e-06, "loss": 0.001, "step": 360340 }, { "epoch": 86.53, "learning_rate": 7.494146037351096e-06, "loss": 0.0011, "step": 360350 }, { "epoch": 86.54, "learning_rate": 7.4922559012564175e-06, "loss": 0.001, "step": 360360 }, { "epoch": 86.54, "learning_rate": 7.4903659842469946e-06, "loss": 0.0011, "step": 360370 }, { "epoch": 86.54, "learning_rate": 7.488476286332596e-06, "loss": 0.001, "step": 360380 }, { "epoch": 86.54, "learning_rate": 7.486586807522927e-06, "loss": 0.001, "step": 360390 }, { "epoch": 86.54, "learning_rate": 7.484697547827762e-06, "loss": 0.001, "step": 360400 }, { "epoch": 86.55, "learning_rate": 7.482808507256811e-06, "loss": 0.001, "step": 360410 }, { "epoch": 86.55, "learning_rate": 7.480919685819815e-06, "loss": 0.0009, "step": 360420 }, { "epoch": 86.55, "learning_rate": 7.479031083526528e-06, "loss": 0.001, "step": 360430 }, { "epoch": 86.55, "learning_rate": 7.477142700386674e-06, "loss": 0.002, "step": 360440 }, { "epoch": 86.56, "learning_rate": 7.4752545364099644e-06, "loss": 0.0011, "step": 360450 }, { "epoch": 86.56, "learning_rate": 7.473366591606162e-06, "loss": 0.0009, "step": 360460 }, { "epoch": 86.56, "learning_rate": 7.471478865984977e-06, "loss": 0.0011, "step": 360470 }, { "epoch": 86.56, "learning_rate": 7.469591359556149e-06, "loss": 0.001, "step": 360480 }, { "epoch": 86.56, "learning_rate": 7.467704072329396e-06, "loss": 0.001, "step": 360490 }, { "epoch": 86.57, "learning_rate": 7.465817004314463e-06, "loss": 0.001, "step": 360500 }, { "epoch": 86.57, "learning_rate": 7.463930155521065e-06, "loss": 0.001, "step": 360510 }, { "epoch": 86.57, "learning_rate": 7.462043525958912e-06, "loss": 0.0011, "step": 360520 }, { "epoch": 86.57, "learning_rate": 7.460157115637756e-06, "loss": 0.0011, "step": 360530 }, { "epoch": 86.58, "learning_rate": 7.4582709245672955e-06, "loss": 0.0011, "step": 360540 }, { "epoch": 86.58, "learning_rate": 7.456384952757273e-06, "loss": 0.001, "step": 360550 }, { "epoch": 86.58, "learning_rate": 7.454499200217385e-06, "loss": 0.0011, "step": 360560 }, { "epoch": 86.58, "learning_rate": 7.452613666957376e-06, "loss": 0.0011, "step": 360570 }, { "epoch": 86.59, "learning_rate": 7.450728352986952e-06, "loss": 0.0011, "step": 360580 }, { "epoch": 86.59, "learning_rate": 7.4488432583158185e-06, "loss": 0.001, "step": 360590 }, { "epoch": 86.59, "learning_rate": 7.446958382953712e-06, "loss": 0.001, "step": 360600 }, { "epoch": 86.59, "learning_rate": 7.445073726910329e-06, "loss": 0.0011, "step": 360610 }, { "epoch": 86.59, "learning_rate": 7.443189290195401e-06, "loss": 0.0009, "step": 360620 }, { "epoch": 86.6, "learning_rate": 7.441305072818622e-06, "loss": 0.0012, "step": 360630 }, { "epoch": 86.6, "learning_rate": 7.4394210747897205e-06, "loss": 0.001, "step": 360640 }, { "epoch": 86.6, "learning_rate": 7.437537296118402e-06, "loss": 0.0013, "step": 360650 }, { "epoch": 86.6, "learning_rate": 7.4356537368143575e-06, "loss": 0.001, "step": 360660 }, { "epoch": 86.61, "learning_rate": 7.433770396887313e-06, "loss": 0.001, "step": 360670 }, { "epoch": 86.61, "learning_rate": 7.431887276346977e-06, "loss": 0.001, "step": 360680 }, { "epoch": 86.61, "learning_rate": 7.430004375203043e-06, "loss": 0.0011, "step": 360690 }, { "epoch": 86.61, "learning_rate": 7.4281216934652344e-06, "loss": 0.0013, "step": 360700 }, { "epoch": 86.62, "learning_rate": 7.426239231143228e-06, "loss": 0.001, "step": 360710 }, { "epoch": 86.62, "learning_rate": 7.424356988246756e-06, "loss": 0.0011, "step": 360720 }, { "epoch": 86.62, "learning_rate": 7.422474964785492e-06, "loss": 0.0011, "step": 360730 }, { "epoch": 86.62, "learning_rate": 7.420593160769157e-06, "loss": 0.0011, "step": 360740 }, { "epoch": 86.62, "learning_rate": 7.418711576207427e-06, "loss": 0.001, "step": 360750 }, { "epoch": 86.63, "learning_rate": 7.4168302111100265e-06, "loss": 0.001, "step": 360760 }, { "epoch": 86.63, "learning_rate": 7.414949065486632e-06, "loss": 0.0009, "step": 360770 }, { "epoch": 86.63, "learning_rate": 7.4130681393469514e-06, "loss": 0.001, "step": 360780 }, { "epoch": 86.63, "learning_rate": 7.411187432700667e-06, "loss": 0.0009, "step": 360790 }, { "epoch": 86.64, "learning_rate": 7.409306945557487e-06, "loss": 0.001, "step": 360800 }, { "epoch": 86.64, "learning_rate": 7.4074266779270984e-06, "loss": 0.001, "step": 360810 }, { "epoch": 86.64, "learning_rate": 7.405546629819171e-06, "loss": 0.0012, "step": 360820 }, { "epoch": 86.64, "learning_rate": 7.403666801243431e-06, "loss": 0.001, "step": 360830 }, { "epoch": 86.64, "learning_rate": 7.401787192209531e-06, "loss": 0.0011, "step": 360840 }, { "epoch": 86.65, "learning_rate": 7.399907802727191e-06, "loss": 0.0011, "step": 360850 }, { "epoch": 86.65, "learning_rate": 7.39802863280607e-06, "loss": 0.001, "step": 360860 }, { "epoch": 86.65, "learning_rate": 7.396149682455877e-06, "loss": 0.0009, "step": 360870 }, { "epoch": 86.65, "learning_rate": 7.394270951686283e-06, "loss": 0.001, "step": 360880 }, { "epoch": 86.66, "learning_rate": 7.392392440506962e-06, "loss": 0.001, "step": 360890 }, { "epoch": 86.66, "learning_rate": 7.390514148927619e-06, "loss": 0.0012, "step": 360900 }, { "epoch": 86.66, "learning_rate": 7.388636076957911e-06, "loss": 0.0011, "step": 360910 }, { "epoch": 86.66, "learning_rate": 7.386758224607543e-06, "loss": 0.0009, "step": 360920 }, { "epoch": 86.67, "learning_rate": 7.384880591886162e-06, "loss": 0.0011, "step": 360930 }, { "epoch": 86.67, "learning_rate": 7.383003178803477e-06, "loss": 0.001, "step": 360940 }, { "epoch": 86.67, "learning_rate": 7.381125985369147e-06, "loss": 0.0009, "step": 360950 }, { "epoch": 86.67, "learning_rate": 7.379249011592842e-06, "loss": 0.001, "step": 360960 }, { "epoch": 86.67, "learning_rate": 7.377372257484255e-06, "loss": 0.0024, "step": 360970 }, { "epoch": 86.68, "learning_rate": 7.375495723053033e-06, "loss": 0.001, "step": 360980 }, { "epoch": 86.68, "learning_rate": 7.373619408308868e-06, "loss": 0.0011, "step": 360990 }, { "epoch": 86.68, "learning_rate": 7.371743313261431e-06, "loss": 0.0011, "step": 361000 }, { "epoch": 86.68, "learning_rate": 7.369867437920375e-06, "loss": 0.001, "step": 361010 }, { "epoch": 86.69, "learning_rate": 7.367991782295391e-06, "loss": 0.0011, "step": 361020 }, { "epoch": 86.69, "learning_rate": 7.366116346396124e-06, "loss": 0.0012, "step": 361030 }, { "epoch": 86.69, "learning_rate": 7.364241130232258e-06, "loss": 0.0011, "step": 361040 }, { "epoch": 86.69, "learning_rate": 7.362366133813442e-06, "loss": 0.001, "step": 361050 }, { "epoch": 86.7, "learning_rate": 7.360491357149351e-06, "loss": 0.001, "step": 361060 }, { "epoch": 86.7, "learning_rate": 7.35861680024964e-06, "loss": 0.001, "step": 361070 }, { "epoch": 86.7, "learning_rate": 7.356742463123983e-06, "loss": 0.001, "step": 361080 }, { "epoch": 86.7, "learning_rate": 7.3548683457820345e-06, "loss": 0.001, "step": 361090 }, { "epoch": 86.7, "learning_rate": 7.3529944482334354e-06, "loss": 0.0011, "step": 361100 }, { "epoch": 86.71, "learning_rate": 7.351120770487874e-06, "loss": 0.0009, "step": 361110 }, { "epoch": 86.71, "learning_rate": 7.34924731255498e-06, "loss": 0.0011, "step": 361120 }, { "epoch": 86.71, "learning_rate": 7.3473740744444356e-06, "loss": 0.0009, "step": 361130 }, { "epoch": 86.71, "learning_rate": 7.345501056165866e-06, "loss": 0.0009, "step": 361140 }, { "epoch": 86.72, "learning_rate": 7.343628257728952e-06, "loss": 0.001, "step": 361150 }, { "epoch": 86.72, "learning_rate": 7.341755679143336e-06, "loss": 0.001, "step": 361160 }, { "epoch": 86.72, "learning_rate": 7.3398833204186616e-06, "loss": 0.001, "step": 361170 }, { "epoch": 86.72, "learning_rate": 7.338011181564591e-06, "loss": 0.0009, "step": 361180 }, { "epoch": 86.72, "learning_rate": 7.336139262590752e-06, "loss": 0.001, "step": 361190 }, { "epoch": 86.73, "learning_rate": 7.334267563506825e-06, "loss": 0.001, "step": 361200 }, { "epoch": 86.73, "learning_rate": 7.332396084322429e-06, "loss": 0.0011, "step": 361210 }, { "epoch": 86.73, "learning_rate": 7.330524825047231e-06, "loss": 0.001, "step": 361220 }, { "epoch": 86.73, "learning_rate": 7.328653785690864e-06, "loss": 0.001, "step": 361230 }, { "epoch": 86.74, "learning_rate": 7.326782966262957e-06, "loss": 0.001, "step": 361240 }, { "epoch": 86.74, "learning_rate": 7.3249123667731845e-06, "loss": 0.001, "step": 361250 }, { "epoch": 86.74, "learning_rate": 7.323041987231155e-06, "loss": 0.0012, "step": 361260 }, { "epoch": 86.74, "learning_rate": 7.321171827646539e-06, "loss": 0.0011, "step": 361270 }, { "epoch": 86.75, "learning_rate": 7.319301888028945e-06, "loss": 0.001, "step": 361280 }, { "epoch": 86.75, "learning_rate": 7.317432168388039e-06, "loss": 0.0011, "step": 361290 }, { "epoch": 86.75, "learning_rate": 7.3155626687334335e-06, "loss": 0.001, "step": 361300 }, { "epoch": 86.75, "learning_rate": 7.313693389074771e-06, "loss": 0.0011, "step": 361310 }, { "epoch": 86.75, "learning_rate": 7.311824329421707e-06, "loss": 0.001, "step": 361320 }, { "epoch": 86.76, "learning_rate": 7.309955489783843e-06, "loss": 0.001, "step": 361330 }, { "epoch": 86.76, "learning_rate": 7.3080868701708325e-06, "loss": 0.001, "step": 361340 }, { "epoch": 86.76, "learning_rate": 7.306218470592291e-06, "loss": 0.001, "step": 361350 }, { "epoch": 86.76, "learning_rate": 7.304350291057871e-06, "loss": 0.0011, "step": 361360 }, { "epoch": 86.77, "learning_rate": 7.302482331577182e-06, "loss": 0.001, "step": 361370 }, { "epoch": 86.77, "learning_rate": 7.300614592159849e-06, "loss": 0.001, "step": 361380 }, { "epoch": 86.77, "learning_rate": 7.298747072815515e-06, "loss": 0.0009, "step": 361390 }, { "epoch": 86.77, "learning_rate": 7.296879773553783e-06, "loss": 0.0012, "step": 361400 }, { "epoch": 86.78, "learning_rate": 7.2950126943843015e-06, "loss": 0.0011, "step": 361410 }, { "epoch": 86.78, "learning_rate": 7.293145835316667e-06, "loss": 0.0012, "step": 361420 }, { "epoch": 86.78, "learning_rate": 7.291279196360529e-06, "loss": 0.0009, "step": 361430 }, { "epoch": 86.78, "learning_rate": 7.289412777525495e-06, "loss": 0.001, "step": 361440 }, { "epoch": 86.78, "learning_rate": 7.287546578821175e-06, "loss": 0.001, "step": 361450 }, { "epoch": 86.79, "learning_rate": 7.285680600257211e-06, "loss": 0.0011, "step": 361460 }, { "epoch": 86.79, "learning_rate": 7.2838148418431895e-06, "loss": 0.001, "step": 361470 }, { "epoch": 86.79, "learning_rate": 7.2819493035887585e-06, "loss": 0.001, "step": 361480 }, { "epoch": 86.79, "learning_rate": 7.280083985503505e-06, "loss": 0.0009, "step": 361490 }, { "epoch": 86.8, "learning_rate": 7.2782188875970655e-06, "loss": 0.001, "step": 361500 }, { "epoch": 86.8, "learning_rate": 7.276354009879044e-06, "loss": 0.0009, "step": 361510 }, { "epoch": 86.8, "learning_rate": 7.274489352359038e-06, "loss": 0.001, "step": 361520 }, { "epoch": 86.8, "learning_rate": 7.272624915046683e-06, "loss": 0.0011, "step": 361530 }, { "epoch": 86.8, "learning_rate": 7.270760697951568e-06, "loss": 0.0012, "step": 361540 }, { "epoch": 86.81, "learning_rate": 7.268896701083322e-06, "loss": 0.001, "step": 361550 }, { "epoch": 86.81, "learning_rate": 7.267032924451522e-06, "loss": 0.001, "step": 361560 }, { "epoch": 86.81, "learning_rate": 7.265169368065805e-06, "loss": 0.0009, "step": 361570 }, { "epoch": 86.81, "learning_rate": 7.263306031935751e-06, "loss": 0.0009, "step": 361580 }, { "epoch": 86.82, "learning_rate": 7.261442916070993e-06, "loss": 0.0009, "step": 361590 }, { "epoch": 86.82, "learning_rate": 7.259580020481093e-06, "loss": 0.0011, "step": 361600 }, { "epoch": 86.82, "learning_rate": 7.257717345175685e-06, "loss": 0.001, "step": 361610 }, { "epoch": 86.82, "learning_rate": 7.255854890164365e-06, "loss": 0.001, "step": 361620 }, { "epoch": 86.83, "learning_rate": 7.253992655456715e-06, "loss": 0.001, "step": 361630 }, { "epoch": 86.83, "learning_rate": 7.252130641062354e-06, "loss": 0.0011, "step": 361640 }, { "epoch": 86.83, "learning_rate": 7.25026884699086e-06, "loss": 0.001, "step": 361650 }, { "epoch": 86.83, "learning_rate": 7.24840727325185e-06, "loss": 0.001, "step": 361660 }, { "epoch": 86.83, "learning_rate": 7.246545919854902e-06, "loss": 0.001, "step": 361670 }, { "epoch": 86.84, "learning_rate": 7.244684786809608e-06, "loss": 0.001, "step": 361680 }, { "epoch": 86.84, "learning_rate": 7.242823874125576e-06, "loss": 0.001, "step": 361690 }, { "epoch": 86.84, "learning_rate": 7.2409631818123715e-06, "loss": 0.001, "step": 361700 }, { "epoch": 86.84, "learning_rate": 7.2391027098796135e-06, "loss": 0.001, "step": 361710 }, { "epoch": 86.85, "learning_rate": 7.237242458336868e-06, "loss": 0.0009, "step": 361720 }, { "epoch": 86.85, "learning_rate": 7.235382427193743e-06, "loss": 0.0011, "step": 361730 }, { "epoch": 86.85, "learning_rate": 7.2335226164598145e-06, "loss": 0.0011, "step": 361740 }, { "epoch": 86.85, "learning_rate": 7.231663026144658e-06, "loss": 0.001, "step": 361750 }, { "epoch": 86.86, "learning_rate": 7.229803656257878e-06, "loss": 0.0011, "step": 361760 }, { "epoch": 86.86, "learning_rate": 7.227944506809037e-06, "loss": 0.001, "step": 361770 }, { "epoch": 86.86, "learning_rate": 7.226085577807734e-06, "loss": 0.001, "step": 361780 }, { "epoch": 86.86, "learning_rate": 7.224226869263539e-06, "loss": 0.0011, "step": 361790 }, { "epoch": 86.86, "learning_rate": 7.22236838118604e-06, "loss": 0.0011, "step": 361800 }, { "epoch": 86.87, "learning_rate": 7.220510113584816e-06, "loss": 0.001, "step": 361810 }, { "epoch": 86.87, "learning_rate": 7.218652066469434e-06, "loss": 0.001, "step": 361820 }, { "epoch": 86.87, "learning_rate": 7.2167942398494835e-06, "loss": 0.001, "step": 361830 }, { "epoch": 86.87, "learning_rate": 7.21493663373452e-06, "loss": 0.0011, "step": 361840 }, { "epoch": 86.88, "learning_rate": 7.213079248134142e-06, "loss": 0.003, "step": 361850 }, { "epoch": 86.88, "learning_rate": 7.2112220830579e-06, "loss": 0.001, "step": 361860 }, { "epoch": 86.88, "learning_rate": 7.2093651385153945e-06, "loss": 0.001, "step": 361870 }, { "epoch": 86.88, "learning_rate": 7.207508414516162e-06, "loss": 0.0009, "step": 361880 }, { "epoch": 86.88, "learning_rate": 7.2056519110698e-06, "loss": 0.001, "step": 361890 }, { "epoch": 86.89, "learning_rate": 7.203795628185855e-06, "loss": 0.0008, "step": 361900 }, { "epoch": 86.89, "learning_rate": 7.201939565873917e-06, "loss": 0.001, "step": 361910 }, { "epoch": 86.89, "learning_rate": 7.20008372414353e-06, "loss": 0.0011, "step": 361920 }, { "epoch": 86.89, "learning_rate": 7.198228103004267e-06, "loss": 0.001, "step": 361930 }, { "epoch": 86.9, "learning_rate": 7.196372702465709e-06, "loss": 0.001, "step": 361940 }, { "epoch": 86.9, "learning_rate": 7.194517522537398e-06, "loss": 0.001, "step": 361950 }, { "epoch": 86.9, "learning_rate": 7.192662563228897e-06, "loss": 0.0011, "step": 361960 }, { "epoch": 86.9, "learning_rate": 7.190807824549778e-06, "loss": 0.001, "step": 361970 }, { "epoch": 86.91, "learning_rate": 7.1889533065095826e-06, "loss": 0.0011, "step": 361980 }, { "epoch": 86.91, "learning_rate": 7.187099009117893e-06, "loss": 0.001, "step": 361990 }, { "epoch": 86.91, "learning_rate": 7.185244932384239e-06, "loss": 0.001, "step": 362000 }, { "epoch": 86.91, "learning_rate": 7.183391076318202e-06, "loss": 0.001, "step": 362010 }, { "epoch": 86.91, "learning_rate": 7.181537440929326e-06, "loss": 0.001, "step": 362020 }, { "epoch": 86.92, "learning_rate": 7.179684026227152e-06, "loss": 0.0011, "step": 362030 }, { "epoch": 86.92, "learning_rate": 7.177830832221255e-06, "loss": 0.0009, "step": 362040 }, { "epoch": 86.92, "learning_rate": 7.175977858921168e-06, "loss": 0.0011, "step": 362050 }, { "epoch": 86.92, "learning_rate": 7.174125106336455e-06, "loss": 0.001, "step": 362060 }, { "epoch": 86.93, "learning_rate": 7.1722725744766514e-06, "loss": 0.001, "step": 362070 }, { "epoch": 86.93, "learning_rate": 7.170420263351324e-06, "loss": 0.001, "step": 362080 }, { "epoch": 86.93, "learning_rate": 7.168568172970008e-06, "loss": 0.001, "step": 362090 }, { "epoch": 86.93, "learning_rate": 7.166716303342241e-06, "loss": 0.0011, "step": 362100 }, { "epoch": 86.94, "learning_rate": 7.164864654477582e-06, "loss": 0.0011, "step": 362110 }, { "epoch": 86.94, "learning_rate": 7.163013226385562e-06, "loss": 0.0011, "step": 362120 }, { "epoch": 86.94, "learning_rate": 7.16116201907574e-06, "loss": 0.001, "step": 362130 }, { "epoch": 86.94, "learning_rate": 7.159311032557636e-06, "loss": 0.001, "step": 362140 }, { "epoch": 86.94, "learning_rate": 7.157460266840815e-06, "loss": 0.001, "step": 362150 }, { "epoch": 86.95, "learning_rate": 7.155609721934797e-06, "loss": 0.001, "step": 362160 }, { "epoch": 86.95, "learning_rate": 7.153759397849113e-06, "loss": 0.0011, "step": 362170 }, { "epoch": 86.95, "learning_rate": 7.151909294593318e-06, "loss": 0.0012, "step": 362180 }, { "epoch": 87.0, "learning_rate": 7.150059412176946e-06, "loss": 0.001, "step": 362190 }, { "epoch": 87.0, "learning_rate": 7.1482097506095135e-06, "loss": 0.001, "step": 362200 }, { "epoch": 87.01, "learning_rate": 7.14636030990058e-06, "loss": 0.001, "step": 362210 }, { "epoch": 87.01, "learning_rate": 7.1445110900596525e-06, "loss": 0.0008, "step": 362220 }, { "epoch": 87.01, "learning_rate": 7.142662091096286e-06, "loss": 0.001, "step": 362230 }, { "epoch": 87.01, "learning_rate": 7.140813313019984e-06, "loss": 0.001, "step": 362240 }, { "epoch": 87.02, "learning_rate": 7.1389647558403e-06, "loss": 0.001, "step": 362250 }, { "epoch": 87.02, "learning_rate": 7.137116419566736e-06, "loss": 0.0011, "step": 362260 }, { "epoch": 87.02, "learning_rate": 7.135268304208847e-06, "loss": 0.0009, "step": 362270 }, { "epoch": 87.02, "learning_rate": 7.133420409776131e-06, "loss": 0.001, "step": 362280 }, { "epoch": 87.02, "learning_rate": 7.131572736278136e-06, "loss": 0.0009, "step": 362290 }, { "epoch": 87.03, "learning_rate": 7.129725283724376e-06, "loss": 0.001, "step": 362300 }, { "epoch": 87.03, "learning_rate": 7.127878052124354e-06, "loss": 0.0009, "step": 362310 }, { "epoch": 87.03, "learning_rate": 7.1260310414876185e-06, "loss": 0.001, "step": 362320 }, { "epoch": 87.03, "learning_rate": 7.124184251823668e-06, "loss": 0.0011, "step": 362330 }, { "epoch": 87.04, "learning_rate": 7.122337683142044e-06, "loss": 0.001, "step": 362340 }, { "epoch": 87.04, "learning_rate": 7.120491335452234e-06, "loss": 0.001, "step": 362350 }, { "epoch": 87.04, "learning_rate": 7.118645208763785e-06, "loss": 0.001, "step": 362360 }, { "epoch": 87.04, "learning_rate": 7.1167993030861965e-06, "loss": 0.001, "step": 362370 }, { "epoch": 87.05, "learning_rate": 7.114953618428971e-06, "loss": 0.0011, "step": 362380 }, { "epoch": 87.05, "learning_rate": 7.113108154801645e-06, "loss": 0.001, "step": 362390 }, { "epoch": 87.05, "learning_rate": 7.1112629122137066e-06, "loss": 0.001, "step": 362400 }, { "epoch": 87.05, "learning_rate": 7.109417890674686e-06, "loss": 0.0009, "step": 362410 }, { "epoch": 87.05, "learning_rate": 7.1075730901940755e-06, "loss": 0.001, "step": 362420 }, { "epoch": 87.06, "learning_rate": 7.1057285107814005e-06, "loss": 0.001, "step": 362430 }, { "epoch": 87.06, "learning_rate": 7.10388415244615e-06, "loss": 0.0011, "step": 362440 }, { "epoch": 87.06, "learning_rate": 7.1020400151978524e-06, "loss": 0.001, "step": 362450 }, { "epoch": 87.06, "learning_rate": 7.100196099045997e-06, "loss": 0.0009, "step": 362460 }, { "epoch": 87.07, "learning_rate": 7.098352404000081e-06, "loss": 0.001, "step": 362470 }, { "epoch": 87.07, "learning_rate": 7.096508930069623e-06, "loss": 0.001, "step": 362480 }, { "epoch": 87.07, "learning_rate": 7.0946656772641065e-06, "loss": 0.001, "step": 362490 }, { "epoch": 87.07, "learning_rate": 7.092822645593039e-06, "loss": 0.001, "step": 362500 }, { "epoch": 87.08, "learning_rate": 7.090979835065937e-06, "loss": 0.001, "step": 362510 }, { "epoch": 87.08, "learning_rate": 7.089137245692273e-06, "loss": 0.001, "step": 362520 }, { "epoch": 87.08, "learning_rate": 7.087294877481565e-06, "loss": 0.001, "step": 362530 }, { "epoch": 87.08, "learning_rate": 7.0854527304432875e-06, "loss": 0.0011, "step": 362540 }, { "epoch": 87.08, "learning_rate": 7.083610804586954e-06, "loss": 0.001, "step": 362550 }, { "epoch": 87.09, "learning_rate": 7.081769099922036e-06, "loss": 0.0009, "step": 362560 }, { "epoch": 87.09, "learning_rate": 7.079927616458054e-06, "loss": 0.001, "step": 362570 }, { "epoch": 87.09, "learning_rate": 7.0780863542044715e-06, "loss": 0.0011, "step": 362580 }, { "epoch": 87.09, "learning_rate": 7.076245313170799e-06, "loss": 0.0009, "step": 362590 }, { "epoch": 87.1, "learning_rate": 7.074404493366521e-06, "loss": 0.001, "step": 362600 }, { "epoch": 87.1, "learning_rate": 7.07256389480111e-06, "loss": 0.001, "step": 362610 }, { "epoch": 87.1, "learning_rate": 7.070723517484074e-06, "loss": 0.001, "step": 362620 }, { "epoch": 87.1, "learning_rate": 7.068883361424872e-06, "loss": 0.001, "step": 362630 }, { "epoch": 87.1, "learning_rate": 7.067043426633019e-06, "loss": 0.0011, "step": 362640 }, { "epoch": 87.11, "learning_rate": 7.065203713117974e-06, "loss": 0.001, "step": 362650 }, { "epoch": 87.11, "learning_rate": 7.063364220889235e-06, "loss": 0.001, "step": 362660 }, { "epoch": 87.11, "learning_rate": 7.061524949956277e-06, "loss": 0.001, "step": 362670 }, { "epoch": 87.11, "learning_rate": 7.059685900328572e-06, "loss": 0.0009, "step": 362680 }, { "epoch": 87.12, "learning_rate": 7.057847072015611e-06, "loss": 0.001, "step": 362690 }, { "epoch": 87.12, "learning_rate": 7.056008465026853e-06, "loss": 0.001, "step": 362700 }, { "epoch": 87.12, "learning_rate": 7.054170079371802e-06, "loss": 0.0009, "step": 362710 }, { "epoch": 87.12, "learning_rate": 7.052331915059901e-06, "loss": 0.001, "step": 362720 }, { "epoch": 87.13, "learning_rate": 7.050493972100658e-06, "loss": 0.0009, "step": 362730 }, { "epoch": 87.13, "learning_rate": 7.0486562505035216e-06, "loss": 0.001, "step": 362740 }, { "epoch": 87.13, "learning_rate": 7.046818750277961e-06, "loss": 0.001, "step": 362750 }, { "epoch": 87.13, "learning_rate": 7.0449814714334646e-06, "loss": 0.001, "step": 362760 }, { "epoch": 87.13, "learning_rate": 7.043144413979486e-06, "loss": 0.0009, "step": 362770 }, { "epoch": 87.14, "learning_rate": 7.04130757792551e-06, "loss": 0.001, "step": 362780 }, { "epoch": 87.14, "learning_rate": 7.039470963280981e-06, "loss": 0.0009, "step": 362790 }, { "epoch": 87.14, "learning_rate": 7.03763457005539e-06, "loss": 0.001, "step": 362800 }, { "epoch": 87.14, "learning_rate": 7.035798398258181e-06, "loss": 0.001, "step": 362810 }, { "epoch": 87.15, "learning_rate": 7.033962447898823e-06, "loss": 0.001, "step": 362820 }, { "epoch": 87.15, "learning_rate": 7.032126718986792e-06, "loss": 0.001, "step": 362830 }, { "epoch": 87.15, "learning_rate": 7.030291211531526e-06, "loss": 0.0011, "step": 362840 }, { "epoch": 87.15, "learning_rate": 7.028455925542515e-06, "loss": 0.0009, "step": 362850 }, { "epoch": 87.16, "learning_rate": 7.026620861029187e-06, "loss": 0.0009, "step": 362860 }, { "epoch": 87.16, "learning_rate": 7.024786018001028e-06, "loss": 0.0011, "step": 362870 }, { "epoch": 87.16, "learning_rate": 7.022951396467481e-06, "loss": 0.0011, "step": 362880 }, { "epoch": 87.16, "learning_rate": 7.021116996437988e-06, "loss": 0.0011, "step": 362890 }, { "epoch": 87.16, "learning_rate": 7.01928281792203e-06, "loss": 0.0011, "step": 362900 }, { "epoch": 87.17, "learning_rate": 7.017448860929032e-06, "loss": 0.001, "step": 362910 }, { "epoch": 87.17, "learning_rate": 7.015615125468478e-06, "loss": 0.0011, "step": 362920 }, { "epoch": 87.17, "learning_rate": 7.013781611549791e-06, "loss": 0.0009, "step": 362930 }, { "epoch": 87.17, "learning_rate": 7.0119483191824435e-06, "loss": 0.001, "step": 362940 }, { "epoch": 87.18, "learning_rate": 7.010115248375876e-06, "loss": 0.001, "step": 362950 }, { "epoch": 87.18, "learning_rate": 7.008282399139515e-06, "loss": 0.0011, "step": 362960 }, { "epoch": 87.18, "learning_rate": 7.006449771482842e-06, "loss": 0.001, "step": 362970 }, { "epoch": 87.18, "learning_rate": 7.004617365415278e-06, "loss": 0.0009, "step": 362980 }, { "epoch": 87.18, "learning_rate": 7.002785180946287e-06, "loss": 0.001, "step": 362990 }, { "epoch": 87.19, "learning_rate": 7.0009532180852826e-06, "loss": 0.001, "step": 363000 }, { "epoch": 87.19, "learning_rate": 6.9991214768417415e-06, "loss": 0.0009, "step": 363010 }, { "epoch": 87.19, "learning_rate": 6.9972899572250835e-06, "loss": 0.0009, "step": 363020 }, { "epoch": 87.19, "learning_rate": 6.995458659244747e-06, "loss": 0.0009, "step": 363030 }, { "epoch": 87.2, "learning_rate": 6.993627582910184e-06, "loss": 0.0011, "step": 363040 }, { "epoch": 87.2, "learning_rate": 6.991796728230815e-06, "loss": 0.001, "step": 363050 }, { "epoch": 87.2, "learning_rate": 6.989966095216094e-06, "loss": 0.0011, "step": 363060 }, { "epoch": 87.2, "learning_rate": 6.988135683875436e-06, "loss": 0.0009, "step": 363070 }, { "epoch": 87.21, "learning_rate": 6.986305494218298e-06, "loss": 0.0011, "step": 363080 }, { "epoch": 87.21, "learning_rate": 6.984475526254086e-06, "loss": 0.0011, "step": 363090 }, { "epoch": 87.21, "learning_rate": 6.982645779992264e-06, "loss": 0.001, "step": 363100 }, { "epoch": 87.21, "learning_rate": 6.9808162554422295e-06, "loss": 0.001, "step": 363110 }, { "epoch": 87.21, "learning_rate": 6.978986952613431e-06, "loss": 0.001, "step": 363120 }, { "epoch": 87.22, "learning_rate": 6.977157871515305e-06, "loss": 0.0009, "step": 363130 }, { "epoch": 87.22, "learning_rate": 6.97532901215725e-06, "loss": 0.001, "step": 363140 }, { "epoch": 87.22, "learning_rate": 6.973500374548725e-06, "loss": 0.001, "step": 363150 }, { "epoch": 87.22, "learning_rate": 6.971671958699138e-06, "loss": 0.001, "step": 363160 }, { "epoch": 87.23, "learning_rate": 6.9698437646179e-06, "loss": 0.001, "step": 363170 }, { "epoch": 87.23, "learning_rate": 6.968015792314464e-06, "loss": 0.001, "step": 363180 }, { "epoch": 87.23, "learning_rate": 6.966188041798216e-06, "loss": 0.0011, "step": 363190 }, { "epoch": 87.23, "learning_rate": 6.9643605130786106e-06, "loss": 0.0009, "step": 363200 }, { "epoch": 87.24, "learning_rate": 6.9625332061650395e-06, "loss": 0.001, "step": 363210 }, { "epoch": 87.24, "learning_rate": 6.96070612106694e-06, "loss": 0.001, "step": 363220 }, { "epoch": 87.24, "learning_rate": 6.95887925779371e-06, "loss": 0.001, "step": 363230 }, { "epoch": 87.24, "learning_rate": 6.957052616354792e-06, "loss": 0.0009, "step": 363240 }, { "epoch": 87.24, "learning_rate": 6.955226196759579e-06, "loss": 0.0008, "step": 363250 }, { "epoch": 87.25, "learning_rate": 6.953399999017479e-06, "loss": 0.001, "step": 363260 }, { "epoch": 87.25, "learning_rate": 6.95157402313793e-06, "loss": 0.001, "step": 363270 }, { "epoch": 87.25, "learning_rate": 6.949748269130313e-06, "loss": 0.001, "step": 363280 }, { "epoch": 87.25, "learning_rate": 6.94792273700407e-06, "loss": 0.001, "step": 363290 }, { "epoch": 87.26, "learning_rate": 6.9460974267685774e-06, "loss": 0.0009, "step": 363300 }, { "epoch": 87.26, "learning_rate": 6.944272338433272e-06, "loss": 0.0011, "step": 363310 }, { "epoch": 87.26, "learning_rate": 6.942447472007546e-06, "loss": 0.0012, "step": 363320 }, { "epoch": 87.26, "learning_rate": 6.940622827500792e-06, "loss": 0.001, "step": 363330 }, { "epoch": 87.26, "learning_rate": 6.938798404922442e-06, "loss": 0.001, "step": 363340 }, { "epoch": 87.27, "learning_rate": 6.936974204281876e-06, "loss": 0.001, "step": 363350 }, { "epoch": 87.27, "learning_rate": 6.93515022558851e-06, "loss": 0.0009, "step": 363360 }, { "epoch": 87.27, "learning_rate": 6.9333264688517366e-06, "loss": 0.001, "step": 363370 }, { "epoch": 87.27, "learning_rate": 6.931502934080963e-06, "loss": 0.001, "step": 363380 }, { "epoch": 87.28, "learning_rate": 6.929679621285573e-06, "loss": 0.0009, "step": 363390 }, { "epoch": 87.28, "learning_rate": 6.9278565304749854e-06, "loss": 0.0011, "step": 363400 }, { "epoch": 87.28, "learning_rate": 6.926033661658576e-06, "loss": 0.0009, "step": 363410 }, { "epoch": 87.28, "learning_rate": 6.924211014845761e-06, "loss": 0.001, "step": 363420 }, { "epoch": 87.29, "learning_rate": 6.922388590045909e-06, "loss": 0.0009, "step": 363430 }, { "epoch": 87.29, "learning_rate": 6.920566387268429e-06, "loss": 0.001, "step": 363440 }, { "epoch": 87.29, "learning_rate": 6.91874440652272e-06, "loss": 0.001, "step": 363450 }, { "epoch": 87.29, "learning_rate": 6.916922647818158e-06, "loss": 0.001, "step": 363460 }, { "epoch": 87.29, "learning_rate": 6.915101111164129e-06, "loss": 0.0011, "step": 363470 }, { "epoch": 87.3, "learning_rate": 6.913279796570043e-06, "loss": 0.001, "step": 363480 }, { "epoch": 87.3, "learning_rate": 6.9114587040452594e-06, "loss": 0.001, "step": 363490 }, { "epoch": 87.3, "learning_rate": 6.909637833599192e-06, "loss": 0.001, "step": 363500 }, { "epoch": 87.3, "learning_rate": 6.9078171852411945e-06, "loss": 0.0011, "step": 363510 }, { "epoch": 87.31, "learning_rate": 6.905996758980682e-06, "loss": 0.0009, "step": 363520 }, { "epoch": 87.31, "learning_rate": 6.904176554827019e-06, "loss": 0.0011, "step": 363530 }, { "epoch": 87.31, "learning_rate": 6.902356572789581e-06, "loss": 0.0009, "step": 363540 }, { "epoch": 87.31, "learning_rate": 6.900536812877772e-06, "loss": 0.0011, "step": 363550 }, { "epoch": 87.32, "learning_rate": 6.898717275100941e-06, "loss": 0.0011, "step": 363560 }, { "epoch": 87.32, "learning_rate": 6.8968979594684955e-06, "loss": 0.001, "step": 363570 }, { "epoch": 87.32, "learning_rate": 6.895078865989784e-06, "loss": 0.0009, "step": 363580 }, { "epoch": 87.32, "learning_rate": 6.893259994674211e-06, "loss": 0.0009, "step": 363590 }, { "epoch": 87.32, "learning_rate": 6.8914413455311356e-06, "loss": 0.0009, "step": 363600 }, { "epoch": 87.33, "learning_rate": 6.8896229185699214e-06, "loss": 0.001, "step": 363610 }, { "epoch": 87.33, "learning_rate": 6.887804713799962e-06, "loss": 0.001, "step": 363620 }, { "epoch": 87.33, "learning_rate": 6.885986731230604e-06, "loss": 0.001, "step": 363630 }, { "epoch": 87.33, "learning_rate": 6.884168970871241e-06, "loss": 0.001, "step": 363640 }, { "epoch": 87.34, "learning_rate": 6.882351432731221e-06, "loss": 0.001, "step": 363650 }, { "epoch": 87.34, "learning_rate": 6.8805341168199365e-06, "loss": 0.001, "step": 363660 }, { "epoch": 87.34, "learning_rate": 6.878717023146736e-06, "loss": 0.001, "step": 363670 }, { "epoch": 87.34, "learning_rate": 6.876900151720977e-06, "loss": 0.0009, "step": 363680 }, { "epoch": 87.34, "learning_rate": 6.875083502552049e-06, "loss": 0.0011, "step": 363690 }, { "epoch": 87.35, "learning_rate": 6.873267075649292e-06, "loss": 0.0009, "step": 363700 }, { "epoch": 87.35, "learning_rate": 6.871450871022072e-06, "loss": 0.001, "step": 363710 }, { "epoch": 87.35, "learning_rate": 6.869634888679771e-06, "loss": 0.001, "step": 363720 }, { "epoch": 87.35, "learning_rate": 6.867819128631714e-06, "loss": 0.0009, "step": 363730 }, { "epoch": 87.36, "learning_rate": 6.866003590887293e-06, "loss": 0.001, "step": 363740 }, { "epoch": 87.36, "learning_rate": 6.86418827545584e-06, "loss": 0.0009, "step": 363750 }, { "epoch": 87.36, "learning_rate": 6.862373182346732e-06, "loss": 0.0009, "step": 363760 }, { "epoch": 87.36, "learning_rate": 6.8605583115692986e-06, "loss": 0.0011, "step": 363770 }, { "epoch": 87.37, "learning_rate": 6.858743663132921e-06, "loss": 0.001, "step": 363780 }, { "epoch": 87.37, "learning_rate": 6.856929237046933e-06, "loss": 0.001, "step": 363790 }, { "epoch": 87.37, "learning_rate": 6.855115033320697e-06, "loss": 0.001, "step": 363800 }, { "epoch": 87.37, "learning_rate": 6.8533010519635624e-06, "loss": 0.001, "step": 363810 }, { "epoch": 87.37, "learning_rate": 6.851487292984865e-06, "loss": 0.0011, "step": 363820 }, { "epoch": 87.38, "learning_rate": 6.84967375639397e-06, "loss": 0.001, "step": 363830 }, { "epoch": 87.38, "learning_rate": 6.847860442200204e-06, "loss": 0.0009, "step": 363840 }, { "epoch": 87.38, "learning_rate": 6.846047350412943e-06, "loss": 0.0011, "step": 363850 }, { "epoch": 87.38, "learning_rate": 6.8442344810415e-06, "loss": 0.001, "step": 363860 }, { "epoch": 87.39, "learning_rate": 6.842421834095247e-06, "loss": 0.0011, "step": 363870 }, { "epoch": 87.39, "learning_rate": 6.840609409583509e-06, "loss": 0.001, "step": 363880 }, { "epoch": 87.39, "learning_rate": 6.838797207515624e-06, "loss": 0.001, "step": 363890 }, { "epoch": 87.39, "learning_rate": 6.836985227900944e-06, "loss": 0.0009, "step": 363900 }, { "epoch": 87.4, "learning_rate": 6.835173470748796e-06, "loss": 0.0009, "step": 363910 }, { "epoch": 87.4, "learning_rate": 6.833361936068538e-06, "loss": 0.0009, "step": 363920 }, { "epoch": 87.4, "learning_rate": 6.831550623869482e-06, "loss": 0.001, "step": 363930 }, { "epoch": 87.4, "learning_rate": 6.829739534160984e-06, "loss": 0.001, "step": 363940 }, { "epoch": 87.4, "learning_rate": 6.827928666952366e-06, "loss": 0.0009, "step": 363950 }, { "epoch": 87.41, "learning_rate": 6.826118022252959e-06, "loss": 0.0009, "step": 363960 }, { "epoch": 87.41, "learning_rate": 6.824307600072105e-06, "loss": 0.0009, "step": 363970 }, { "epoch": 87.41, "learning_rate": 6.822497400419126e-06, "loss": 0.001, "step": 363980 }, { "epoch": 87.41, "learning_rate": 6.820687423303363e-06, "loss": 0.001, "step": 363990 }, { "epoch": 87.42, "learning_rate": 6.81887766873413e-06, "loss": 0.0009, "step": 364000 }, { "epoch": 87.42, "learning_rate": 6.8170681367207615e-06, "loss": 0.001, "step": 364010 }, { "epoch": 87.42, "learning_rate": 6.815258827272597e-06, "loss": 0.001, "step": 364020 }, { "epoch": 87.42, "learning_rate": 6.813449740398936e-06, "loss": 0.0011, "step": 364030 }, { "epoch": 87.42, "learning_rate": 6.811640876109126e-06, "loss": 0.001, "step": 364040 }, { "epoch": 87.43, "learning_rate": 6.809832234412472e-06, "loss": 0.001, "step": 364050 }, { "epoch": 87.43, "learning_rate": 6.808023815318315e-06, "loss": 0.001, "step": 364060 }, { "epoch": 87.43, "learning_rate": 6.806215618835954e-06, "loss": 0.0008, "step": 364070 }, { "epoch": 87.43, "learning_rate": 6.8044076449747255e-06, "loss": 0.001, "step": 364080 }, { "epoch": 87.44, "learning_rate": 6.802599893743933e-06, "loss": 0.001, "step": 364090 }, { "epoch": 87.44, "learning_rate": 6.800792365152908e-06, "loss": 0.0009, "step": 364100 }, { "epoch": 87.44, "learning_rate": 6.798985059210966e-06, "loss": 0.0009, "step": 364110 }, { "epoch": 87.44, "learning_rate": 6.797177975927405e-06, "loss": 0.0011, "step": 364120 }, { "epoch": 87.45, "learning_rate": 6.7953711153115604e-06, "loss": 0.001, "step": 364130 }, { "epoch": 87.45, "learning_rate": 6.793564477372721e-06, "loss": 0.0009, "step": 364140 }, { "epoch": 87.45, "learning_rate": 6.791758062120224e-06, "loss": 0.0009, "step": 364150 }, { "epoch": 87.45, "learning_rate": 6.789951869563355e-06, "loss": 0.0011, "step": 364160 }, { "epoch": 87.45, "learning_rate": 6.788145899711446e-06, "loss": 0.001, "step": 364170 }, { "epoch": 87.46, "learning_rate": 6.786340152573795e-06, "loss": 0.0011, "step": 364180 }, { "epoch": 87.46, "learning_rate": 6.7845346281597e-06, "loss": 0.0009, "step": 364190 }, { "epoch": 87.46, "learning_rate": 6.782729326478482e-06, "loss": 0.0009, "step": 364200 }, { "epoch": 87.46, "learning_rate": 6.780924247539427e-06, "loss": 0.0009, "step": 364210 }, { "epoch": 87.47, "learning_rate": 6.779119391351862e-06, "loss": 0.001, "step": 364220 }, { "epoch": 87.47, "learning_rate": 6.777314757925063e-06, "loss": 0.0011, "step": 364230 }, { "epoch": 87.47, "learning_rate": 6.7755103472683605e-06, "loss": 0.0009, "step": 364240 }, { "epoch": 87.47, "learning_rate": 6.773706159391035e-06, "loss": 0.001, "step": 364250 }, { "epoch": 87.48, "learning_rate": 6.771902194302382e-06, "loss": 0.001, "step": 364260 }, { "epoch": 87.48, "learning_rate": 6.770098452011719e-06, "loss": 0.001, "step": 364270 }, { "epoch": 87.48, "learning_rate": 6.768294932528313e-06, "loss": 0.001, "step": 364280 }, { "epoch": 87.48, "learning_rate": 6.766491635861494e-06, "loss": 0.001, "step": 364290 }, { "epoch": 87.48, "learning_rate": 6.7646885620205215e-06, "loss": 0.0009, "step": 364300 }, { "epoch": 87.49, "learning_rate": 6.762885711014716e-06, "loss": 0.001, "step": 364310 }, { "epoch": 87.49, "learning_rate": 6.761083082853353e-06, "loss": 0.001, "step": 364320 }, { "epoch": 87.49, "learning_rate": 6.759280677545726e-06, "loss": 0.0009, "step": 364330 }, { "epoch": 87.49, "learning_rate": 6.757478495101138e-06, "loss": 0.0009, "step": 364340 }, { "epoch": 87.5, "learning_rate": 6.75567653552886e-06, "loss": 0.0009, "step": 364350 }, { "epoch": 87.5, "learning_rate": 6.753874798838194e-06, "loss": 0.0011, "step": 364360 }, { "epoch": 87.5, "learning_rate": 6.752073285038413e-06, "loss": 0.001, "step": 364370 }, { "epoch": 87.5, "learning_rate": 6.750271994138813e-06, "loss": 0.0009, "step": 364380 }, { "epoch": 87.5, "learning_rate": 6.748470926148676e-06, "loss": 0.001, "step": 364390 }, { "epoch": 87.51, "learning_rate": 6.746670081077267e-06, "loss": 0.001, "step": 364400 }, { "epoch": 87.51, "learning_rate": 6.744869458933895e-06, "loss": 0.0009, "step": 364410 }, { "epoch": 87.51, "learning_rate": 6.743069059727819e-06, "loss": 0.0009, "step": 364420 }, { "epoch": 87.51, "learning_rate": 6.741268883468332e-06, "loss": 0.0022, "step": 364430 }, { "epoch": 87.52, "learning_rate": 6.7394689301647e-06, "loss": 0.0011, "step": 364440 }, { "epoch": 87.52, "learning_rate": 6.7376691998262184e-06, "loss": 0.001, "step": 364450 }, { "epoch": 87.52, "learning_rate": 6.735869692462149e-06, "loss": 0.001, "step": 364460 }, { "epoch": 87.52, "learning_rate": 6.7340704080817555e-06, "loss": 0.001, "step": 364470 }, { "epoch": 87.53, "learning_rate": 6.732271346694341e-06, "loss": 0.0012, "step": 364480 }, { "epoch": 87.53, "learning_rate": 6.730472508309149e-06, "loss": 0.001, "step": 364490 }, { "epoch": 87.53, "learning_rate": 6.728673892935472e-06, "loss": 0.001, "step": 364500 }, { "epoch": 87.53, "learning_rate": 6.726875500582563e-06, "loss": 0.001, "step": 364510 }, { "epoch": 87.53, "learning_rate": 6.725077331259711e-06, "loss": 0.0011, "step": 364520 }, { "epoch": 87.54, "learning_rate": 6.723279384976167e-06, "loss": 0.001, "step": 364530 }, { "epoch": 87.54, "learning_rate": 6.721481661741197e-06, "loss": 0.001, "step": 364540 }, { "epoch": 87.54, "learning_rate": 6.719684161564082e-06, "loss": 0.001, "step": 364550 }, { "epoch": 87.54, "learning_rate": 6.717886884454066e-06, "loss": 0.0011, "step": 364560 }, { "epoch": 87.55, "learning_rate": 6.7160898304204355e-06, "loss": 0.001, "step": 364570 }, { "epoch": 87.55, "learning_rate": 6.7142929994724216e-06, "loss": 0.0009, "step": 364580 }, { "epoch": 87.55, "learning_rate": 6.7124963916193215e-06, "loss": 0.001, "step": 364590 }, { "epoch": 87.55, "learning_rate": 6.710700006870363e-06, "loss": 0.001, "step": 364600 }, { "epoch": 87.56, "learning_rate": 6.708903845234832e-06, "loss": 0.0009, "step": 364610 }, { "epoch": 87.56, "learning_rate": 6.70710790672196e-06, "loss": 0.001, "step": 364620 }, { "epoch": 87.56, "learning_rate": 6.705312191341023e-06, "loss": 0.0012, "step": 364630 }, { "epoch": 87.56, "learning_rate": 6.7035166991012645e-06, "loss": 0.001, "step": 364640 }, { "epoch": 87.56, "learning_rate": 6.701721430011937e-06, "loss": 0.0012, "step": 364650 }, { "epoch": 87.57, "learning_rate": 6.699926384082311e-06, "loss": 0.001, "step": 364660 }, { "epoch": 87.57, "learning_rate": 6.69813156132163e-06, "loss": 0.0012, "step": 364670 }, { "epoch": 87.57, "learning_rate": 6.696336961739125e-06, "loss": 0.001, "step": 364680 }, { "epoch": 87.57, "learning_rate": 6.6945425853440765e-06, "loss": 0.001, "step": 364690 }, { "epoch": 87.58, "learning_rate": 6.6927484321457064e-06, "loss": 0.001, "step": 364700 }, { "epoch": 87.58, "learning_rate": 6.6909545021532845e-06, "loss": 0.0011, "step": 364710 }, { "epoch": 87.58, "learning_rate": 6.689160795376031e-06, "loss": 0.001, "step": 364720 }, { "epoch": 87.58, "learning_rate": 6.687367311823217e-06, "loss": 0.0011, "step": 364730 }, { "epoch": 87.58, "learning_rate": 6.6855740515040735e-06, "loss": 0.001, "step": 364740 }, { "epoch": 87.59, "learning_rate": 6.6837810144278315e-06, "loss": 0.0009, "step": 364750 }, { "epoch": 87.59, "learning_rate": 6.681988200603756e-06, "loss": 0.0009, "step": 364760 }, { "epoch": 87.59, "learning_rate": 6.6801956100410675e-06, "loss": 0.0011, "step": 364770 }, { "epoch": 87.59, "learning_rate": 6.67840324274902e-06, "loss": 0.0009, "step": 364780 }, { "epoch": 87.6, "learning_rate": 6.676611098736835e-06, "loss": 0.001, "step": 364790 }, { "epoch": 87.6, "learning_rate": 6.674819178013769e-06, "loss": 0.001, "step": 364800 }, { "epoch": 87.6, "learning_rate": 6.6730274805890335e-06, "loss": 0.001, "step": 364810 }, { "epoch": 87.6, "learning_rate": 6.671236006471892e-06, "loss": 0.001, "step": 364820 }, { "epoch": 87.61, "learning_rate": 6.6694447556715615e-06, "loss": 0.0009, "step": 364830 }, { "epoch": 87.61, "learning_rate": 6.667653728197259e-06, "loss": 0.001, "step": 364840 }, { "epoch": 87.61, "learning_rate": 6.665862924058247e-06, "loss": 0.001, "step": 364850 }, { "epoch": 87.61, "learning_rate": 6.6640723432637275e-06, "loss": 0.0009, "step": 364860 }, { "epoch": 87.61, "learning_rate": 6.662281985822954e-06, "loss": 0.001, "step": 364870 }, { "epoch": 87.62, "learning_rate": 6.660491851745132e-06, "loss": 0.001, "step": 364880 }, { "epoch": 87.62, "learning_rate": 6.658701941039503e-06, "loss": 0.001, "step": 364890 }, { "epoch": 87.62, "learning_rate": 6.65691225371528e-06, "loss": 0.0009, "step": 364900 }, { "epoch": 87.62, "learning_rate": 6.655122789781703e-06, "loss": 0.0011, "step": 364910 }, { "epoch": 87.63, "learning_rate": 6.653333549247976e-06, "loss": 0.001, "step": 364920 }, { "epoch": 87.63, "learning_rate": 6.651544532123338e-06, "loss": 0.0011, "step": 364930 }, { "epoch": 87.63, "learning_rate": 6.6497557384169905e-06, "loss": 0.0048, "step": 364940 }, { "epoch": 87.63, "learning_rate": 6.647967168138164e-06, "loss": 0.001, "step": 364950 }, { "epoch": 87.64, "learning_rate": 6.64617882129609e-06, "loss": 0.0012, "step": 364960 }, { "epoch": 87.64, "learning_rate": 6.644390697899977e-06, "loss": 0.001, "step": 364970 }, { "epoch": 87.64, "learning_rate": 6.642602797959019e-06, "loss": 0.001, "step": 364980 }, { "epoch": 87.64, "learning_rate": 6.640815121482463e-06, "loss": 0.0011, "step": 364990 }, { "epoch": 87.64, "learning_rate": 6.639027668479497e-06, "loss": 0.0011, "step": 365000 }, { "epoch": 87.65, "learning_rate": 6.637240438959352e-06, "loss": 0.001, "step": 365010 }, { "epoch": 87.65, "learning_rate": 6.635453432931227e-06, "loss": 0.0012, "step": 365020 }, { "epoch": 87.65, "learning_rate": 6.633666650404347e-06, "loss": 0.001, "step": 365030 }, { "epoch": 87.65, "learning_rate": 6.63188009138791e-06, "loss": 0.001, "step": 365040 }, { "epoch": 87.66, "learning_rate": 6.630093755891115e-06, "loss": 0.001, "step": 365050 }, { "epoch": 87.66, "learning_rate": 6.6283076439231876e-06, "loss": 0.0011, "step": 365060 }, { "epoch": 87.66, "learning_rate": 6.626521755493315e-06, "loss": 0.001, "step": 365070 }, { "epoch": 87.66, "learning_rate": 6.624736090610728e-06, "loss": 0.001, "step": 365080 }, { "epoch": 87.66, "learning_rate": 6.622950649284598e-06, "loss": 0.001, "step": 365090 }, { "epoch": 87.67, "learning_rate": 6.6211654315241566e-06, "loss": 0.001, "step": 365100 }, { "epoch": 87.67, "learning_rate": 6.61938043733859e-06, "loss": 0.001, "step": 365110 }, { "epoch": 87.67, "learning_rate": 6.6175956667370865e-06, "loss": 0.001, "step": 365120 }, { "epoch": 87.67, "learning_rate": 6.615811119728871e-06, "loss": 0.0009, "step": 365130 }, { "epoch": 87.68, "learning_rate": 6.614026796323114e-06, "loss": 0.001, "step": 365140 }, { "epoch": 87.68, "learning_rate": 6.612242696529036e-06, "loss": 0.0011, "step": 365150 }, { "epoch": 87.68, "learning_rate": 6.610458820355814e-06, "loss": 0.001, "step": 365160 }, { "epoch": 87.68, "learning_rate": 6.608675167812661e-06, "loss": 0.0011, "step": 365170 }, { "epoch": 87.69, "learning_rate": 6.60689173890876e-06, "loss": 0.001, "step": 365180 }, { "epoch": 87.69, "learning_rate": 6.605108533653287e-06, "loss": 0.001, "step": 365190 }, { "epoch": 87.69, "learning_rate": 6.6033255520554615e-06, "loss": 0.0009, "step": 365200 }, { "epoch": 87.69, "learning_rate": 6.601542794124444e-06, "loss": 0.001, "step": 365210 }, { "epoch": 87.69, "learning_rate": 6.599760259869442e-06, "loss": 0.0011, "step": 365220 }, { "epoch": 87.7, "learning_rate": 6.597977949299644e-06, "loss": 0.0011, "step": 365230 }, { "epoch": 87.7, "learning_rate": 6.5961958624242255e-06, "loss": 0.0011, "step": 365240 }, { "epoch": 87.7, "learning_rate": 6.594413999252386e-06, "loss": 0.001, "step": 365250 }, { "epoch": 87.7, "learning_rate": 6.592632359793288e-06, "loss": 0.0008, "step": 365260 }, { "epoch": 87.71, "learning_rate": 6.590850944056132e-06, "loss": 0.0009, "step": 365270 }, { "epoch": 87.71, "learning_rate": 6.5890697520500864e-06, "loss": 0.001, "step": 365280 }, { "epoch": 87.71, "learning_rate": 6.587288783784351e-06, "loss": 0.0011, "step": 365290 }, { "epoch": 87.71, "learning_rate": 6.585508039268079e-06, "loss": 0.0011, "step": 365300 }, { "epoch": 87.72, "learning_rate": 6.583727518510469e-06, "loss": 0.0011, "step": 365310 }, { "epoch": 87.72, "learning_rate": 6.581947221520695e-06, "loss": 0.001, "step": 365320 }, { "epoch": 87.72, "learning_rate": 6.580167148307914e-06, "loss": 0.0009, "step": 365330 }, { "epoch": 87.72, "learning_rate": 6.5783872988813275e-06, "loss": 0.0009, "step": 365340 }, { "epoch": 87.72, "learning_rate": 6.576607673250085e-06, "loss": 0.0009, "step": 365350 }, { "epoch": 87.73, "learning_rate": 6.5748282714233774e-06, "loss": 0.0009, "step": 365360 }, { "epoch": 87.73, "learning_rate": 6.573049093410361e-06, "loss": 0.001, "step": 365370 }, { "epoch": 87.73, "learning_rate": 6.57127013922022e-06, "loss": 0.0009, "step": 365380 }, { "epoch": 87.73, "learning_rate": 6.569491408862122e-06, "loss": 0.0009, "step": 365390 }, { "epoch": 87.74, "learning_rate": 6.567712902345208e-06, "loss": 0.001, "step": 365400 }, { "epoch": 87.74, "learning_rate": 6.565934619678682e-06, "loss": 0.0008, "step": 365410 }, { "epoch": 87.74, "learning_rate": 6.564156560871681e-06, "loss": 0.001, "step": 365420 }, { "epoch": 87.74, "learning_rate": 6.562378725933388e-06, "loss": 0.0011, "step": 365430 }, { "epoch": 87.74, "learning_rate": 6.5606011148729495e-06, "loss": 0.0009, "step": 365440 }, { "epoch": 87.75, "learning_rate": 6.5588237276995476e-06, "loss": 0.001, "step": 365450 }, { "epoch": 87.75, "learning_rate": 6.5570465644223315e-06, "loss": 0.001, "step": 365460 }, { "epoch": 87.75, "learning_rate": 6.5552696250504476e-06, "loss": 0.001, "step": 365470 }, { "epoch": 87.75, "learning_rate": 6.5534929095930785e-06, "loss": 0.0008, "step": 365480 }, { "epoch": 87.76, "learning_rate": 6.551716418059356e-06, "loss": 0.001, "step": 365490 }, { "epoch": 87.76, "learning_rate": 6.549940150458467e-06, "loss": 0.001, "step": 365500 }, { "epoch": 87.76, "learning_rate": 6.548164106799537e-06, "loss": 0.0009, "step": 365510 }, { "epoch": 87.76, "learning_rate": 6.546388287091731e-06, "loss": 0.001, "step": 365520 }, { "epoch": 87.77, "learning_rate": 6.54461269134421e-06, "loss": 0.0011, "step": 365530 }, { "epoch": 87.77, "learning_rate": 6.542837319566114e-06, "loss": 0.0009, "step": 365540 }, { "epoch": 87.77, "learning_rate": 6.541062171766605e-06, "loss": 0.001, "step": 365550 }, { "epoch": 87.77, "learning_rate": 6.539287247954817e-06, "loss": 0.001, "step": 365560 }, { "epoch": 87.77, "learning_rate": 6.537512548139918e-06, "loss": 0.0009, "step": 365570 }, { "epoch": 87.78, "learning_rate": 6.535738072331027e-06, "loss": 0.0009, "step": 365580 }, { "epoch": 87.78, "learning_rate": 6.53396382053732e-06, "loss": 0.0057, "step": 365590 }, { "epoch": 87.78, "learning_rate": 6.532189792767924e-06, "loss": 0.0008, "step": 365600 }, { "epoch": 87.78, "learning_rate": 6.5304159890319734e-06, "loss": 0.001, "step": 365610 }, { "epoch": 87.79, "learning_rate": 6.528642409338637e-06, "loss": 0.001, "step": 365620 }, { "epoch": 87.79, "learning_rate": 6.526869053697026e-06, "loss": 0.001, "step": 365630 }, { "epoch": 87.79, "learning_rate": 6.5250959221163085e-06, "loss": 0.001, "step": 365640 }, { "epoch": 87.79, "learning_rate": 6.523323014605598e-06, "loss": 0.001, "step": 365650 }, { "epoch": 87.8, "learning_rate": 6.521550331174053e-06, "loss": 0.001, "step": 365660 }, { "epoch": 87.8, "learning_rate": 6.519777871830796e-06, "loss": 0.001, "step": 365670 }, { "epoch": 87.8, "learning_rate": 6.518005636584973e-06, "loss": 0.0009, "step": 365680 }, { "epoch": 87.8, "learning_rate": 6.516233625445717e-06, "loss": 0.0011, "step": 365690 }, { "epoch": 87.8, "learning_rate": 6.5144618384221425e-06, "loss": 0.001, "step": 365700 }, { "epoch": 87.81, "learning_rate": 6.512690275523404e-06, "loss": 0.0011, "step": 365710 }, { "epoch": 87.81, "learning_rate": 6.5109189367586144e-06, "loss": 0.001, "step": 365720 }, { "epoch": 87.81, "learning_rate": 6.509147822136924e-06, "loss": 0.001, "step": 365730 }, { "epoch": 87.81, "learning_rate": 6.507376931667436e-06, "loss": 0.0009, "step": 365740 }, { "epoch": 87.82, "learning_rate": 6.505606265359304e-06, "loss": 0.0009, "step": 365750 }, { "epoch": 87.82, "learning_rate": 6.5038358232216435e-06, "loss": 0.001, "step": 365760 }, { "epoch": 87.82, "learning_rate": 6.502065605263563e-06, "loss": 0.001, "step": 365770 }, { "epoch": 87.82, "learning_rate": 6.500295611494211e-06, "loss": 0.001, "step": 365780 }, { "epoch": 87.82, "learning_rate": 6.498525841922687e-06, "loss": 0.0009, "step": 365790 }, { "epoch": 87.83, "learning_rate": 6.496756296558137e-06, "loss": 0.001, "step": 365800 }, { "epoch": 87.83, "learning_rate": 6.494986975409656e-06, "loss": 0.0009, "step": 365810 }, { "epoch": 87.83, "learning_rate": 6.493217878486385e-06, "loss": 0.001, "step": 365820 }, { "epoch": 87.83, "learning_rate": 6.491449005797423e-06, "loss": 0.0009, "step": 365830 }, { "epoch": 87.84, "learning_rate": 6.489680357351901e-06, "loss": 0.0009, "step": 365840 }, { "epoch": 87.84, "learning_rate": 6.487911933158936e-06, "loss": 0.001, "step": 365850 }, { "epoch": 87.84, "learning_rate": 6.486143733227629e-06, "loss": 0.001, "step": 365860 }, { "epoch": 87.84, "learning_rate": 6.4843757575671124e-06, "loss": 0.001, "step": 365870 }, { "epoch": 87.85, "learning_rate": 6.482608006186469e-06, "loss": 0.001, "step": 365880 }, { "epoch": 87.85, "learning_rate": 6.480840479094846e-06, "loss": 0.0011, "step": 365890 }, { "epoch": 87.85, "learning_rate": 6.479073176301332e-06, "loss": 0.001, "step": 365900 }, { "epoch": 87.85, "learning_rate": 6.477306097815028e-06, "loss": 0.0009, "step": 365910 }, { "epoch": 87.85, "learning_rate": 6.475539243645062e-06, "loss": 0.001, "step": 365920 }, { "epoch": 87.86, "learning_rate": 6.473772613800522e-06, "loss": 0.001, "step": 365930 }, { "epoch": 87.86, "learning_rate": 6.472006208290532e-06, "loss": 0.0009, "step": 365940 }, { "epoch": 87.86, "learning_rate": 6.470240027124175e-06, "loss": 0.001, "step": 365950 }, { "epoch": 87.86, "learning_rate": 6.468474070310576e-06, "loss": 0.0009, "step": 365960 }, { "epoch": 87.87, "learning_rate": 6.466708337858823e-06, "loss": 0.001, "step": 365970 }, { "epoch": 87.87, "learning_rate": 6.464942829778009e-06, "loss": 0.001, "step": 365980 }, { "epoch": 87.87, "learning_rate": 6.4631775460772594e-06, "loss": 0.0011, "step": 365990 }, { "epoch": 87.87, "learning_rate": 6.461412486765639e-06, "loss": 0.0009, "step": 366000 }, { "epoch": 87.88, "learning_rate": 6.4596476518522745e-06, "loss": 0.0009, "step": 366010 }, { "epoch": 87.88, "learning_rate": 6.457883041346241e-06, "loss": 0.001, "step": 366020 }, { "epoch": 87.88, "learning_rate": 6.456118655256655e-06, "loss": 0.001, "step": 366030 }, { "epoch": 87.88, "learning_rate": 6.454354493592596e-06, "loss": 0.0009, "step": 366040 }, { "epoch": 87.88, "learning_rate": 6.4525905563631475e-06, "loss": 0.0011, "step": 366050 }, { "epoch": 87.89, "learning_rate": 6.4508268435774175e-06, "loss": 0.001, "step": 366060 }, { "epoch": 87.89, "learning_rate": 6.449063355244483e-06, "loss": 0.0012, "step": 366070 }, { "epoch": 87.89, "learning_rate": 6.447300091373448e-06, "loss": 0.0009, "step": 366080 }, { "epoch": 87.89, "learning_rate": 6.4455370519733884e-06, "loss": 0.001, "step": 366090 }, { "epoch": 87.9, "learning_rate": 6.443774237053402e-06, "loss": 0.001, "step": 366100 }, { "epoch": 87.9, "learning_rate": 6.4420116466225536e-06, "loss": 0.001, "step": 366110 }, { "epoch": 87.9, "learning_rate": 6.440249280689953e-06, "loss": 0.0009, "step": 366120 }, { "epoch": 87.9, "learning_rate": 6.438487139264665e-06, "loss": 0.0026, "step": 366130 }, { "epoch": 87.9, "learning_rate": 6.436725222355783e-06, "loss": 0.001, "step": 366140 }, { "epoch": 87.91, "learning_rate": 6.434963529972376e-06, "loss": 0.001, "step": 366150 }, { "epoch": 87.91, "learning_rate": 6.4332020621235336e-06, "loss": 0.0009, "step": 366160 }, { "epoch": 87.91, "learning_rate": 6.431440818818341e-06, "loss": 0.001, "step": 366170 }, { "epoch": 87.91, "learning_rate": 6.429679800065863e-06, "loss": 0.001, "step": 366180 }, { "epoch": 87.92, "learning_rate": 6.4279190058751715e-06, "loss": 0.0009, "step": 366190 }, { "epoch": 87.92, "learning_rate": 6.426158436255358e-06, "loss": 0.001, "step": 366200 }, { "epoch": 87.92, "learning_rate": 6.424398091215483e-06, "loss": 0.001, "step": 366210 }, { "epoch": 87.92, "learning_rate": 6.422637970764628e-06, "loss": 0.001, "step": 366220 }, { "epoch": 87.93, "learning_rate": 6.420878074911857e-06, "loss": 0.0009, "step": 366230 }, { "epoch": 87.93, "learning_rate": 6.4191184036662524e-06, "loss": 0.001, "step": 366240 }, { "epoch": 87.93, "learning_rate": 6.417358957036879e-06, "loss": 0.001, "step": 366250 }, { "epoch": 87.93, "learning_rate": 6.415599735032785e-06, "loss": 0.0009, "step": 366260 }, { "epoch": 87.93, "learning_rate": 6.413840737663069e-06, "loss": 0.001, "step": 366270 }, { "epoch": 87.94, "learning_rate": 6.412081964936773e-06, "loss": 0.001, "step": 366280 }, { "epoch": 87.94, "learning_rate": 6.410323416862979e-06, "loss": 0.0009, "step": 366290 }, { "epoch": 87.94, "learning_rate": 6.40856509345073e-06, "loss": 0.001, "step": 366300 }, { "epoch": 87.94, "learning_rate": 6.406806994709114e-06, "loss": 0.001, "step": 366310 }, { "epoch": 87.95, "learning_rate": 6.405049120647177e-06, "loss": 0.0011, "step": 366320 }, { "epoch": 87.95, "learning_rate": 6.403291471273976e-06, "loss": 0.001, "step": 366330 }, { "epoch": 87.95, "learning_rate": 6.401534046598578e-06, "loss": 0.0009, "step": 366340 }, { "epoch": 88.0, "learning_rate": 6.399776846630034e-06, "loss": 0.0009, "step": 366350 }, { "epoch": 88.0, "learning_rate": 6.398019871377414e-06, "loss": 0.0008, "step": 366360 }, { "epoch": 88.01, "learning_rate": 6.3962631208497495e-06, "loss": 0.001, "step": 366370 }, { "epoch": 88.01, "learning_rate": 6.394506595056121e-06, "loss": 0.001, "step": 366380 }, { "epoch": 88.01, "learning_rate": 6.392750294005573e-06, "loss": 0.0009, "step": 366390 }, { "epoch": 88.01, "learning_rate": 6.390994217707141e-06, "loss": 0.0008, "step": 366400 }, { "epoch": 88.02, "learning_rate": 6.389238366169892e-06, "loss": 0.001, "step": 366410 }, { "epoch": 88.02, "learning_rate": 6.387482739402883e-06, "loss": 0.001, "step": 366420 }, { "epoch": 88.02, "learning_rate": 6.385727337415143e-06, "loss": 0.001, "step": 366430 }, { "epoch": 88.02, "learning_rate": 6.383972160215734e-06, "loss": 0.0009, "step": 366440 }, { "epoch": 88.02, "learning_rate": 6.38221720781369e-06, "loss": 0.0009, "step": 366450 }, { "epoch": 88.03, "learning_rate": 6.380462480218075e-06, "loss": 0.001, "step": 366460 }, { "epoch": 88.03, "learning_rate": 6.3787079774379085e-06, "loss": 0.0009, "step": 366470 }, { "epoch": 88.03, "learning_rate": 6.376953699482257e-06, "loss": 0.001, "step": 366480 }, { "epoch": 88.03, "learning_rate": 6.375199646360142e-06, "loss": 0.001, "step": 366490 }, { "epoch": 88.04, "learning_rate": 6.37344581808062e-06, "loss": 0.0009, "step": 366500 }, { "epoch": 88.04, "learning_rate": 6.371692214652714e-06, "loss": 0.0009, "step": 366510 }, { "epoch": 88.04, "learning_rate": 6.369938836085481e-06, "loss": 0.001, "step": 366520 }, { "epoch": 88.04, "learning_rate": 6.368185682387939e-06, "loss": 0.0009, "step": 366530 }, { "epoch": 88.04, "learning_rate": 6.36643275356914e-06, "loss": 0.0009, "step": 366540 }, { "epoch": 88.05, "learning_rate": 6.364680049638117e-06, "loss": 0.0009, "step": 366550 }, { "epoch": 88.05, "learning_rate": 6.362927570603882e-06, "loss": 0.001, "step": 366560 }, { "epoch": 88.05, "learning_rate": 6.361175316475493e-06, "loss": 0.0009, "step": 366570 }, { "epoch": 88.05, "learning_rate": 6.359423287261968e-06, "loss": 0.001, "step": 366580 }, { "epoch": 88.06, "learning_rate": 6.357671482972344e-06, "loss": 0.0009, "step": 366590 }, { "epoch": 88.06, "learning_rate": 6.3559199036156366e-06, "loss": 0.001, "step": 366600 }, { "epoch": 88.06, "learning_rate": 6.354168549200895e-06, "loss": 0.0009, "step": 366610 }, { "epoch": 88.06, "learning_rate": 6.352417419737128e-06, "loss": 0.001, "step": 366620 }, { "epoch": 88.07, "learning_rate": 6.350666515233361e-06, "loss": 0.001, "step": 366630 }, { "epoch": 88.07, "learning_rate": 6.348915835698632e-06, "loss": 0.001, "step": 366640 }, { "epoch": 88.07, "learning_rate": 6.3471653811419505e-06, "loss": 0.0009, "step": 366650 }, { "epoch": 88.07, "learning_rate": 6.3454151515723485e-06, "loss": 0.0009, "step": 366660 }, { "epoch": 88.07, "learning_rate": 6.343665146998834e-06, "loss": 0.001, "step": 366670 }, { "epoch": 88.08, "learning_rate": 6.34191536743044e-06, "loss": 0.001, "step": 366680 }, { "epoch": 88.08, "learning_rate": 6.340165812876186e-06, "loss": 0.0011, "step": 366690 }, { "epoch": 88.08, "learning_rate": 6.338416483345067e-06, "loss": 0.001, "step": 366700 }, { "epoch": 88.08, "learning_rate": 6.336667378846123e-06, "loss": 0.0009, "step": 366710 }, { "epoch": 88.09, "learning_rate": 6.334918499388354e-06, "loss": 0.001, "step": 366720 }, { "epoch": 88.09, "learning_rate": 6.3331698449807795e-06, "loss": 0.0009, "step": 366730 }, { "epoch": 88.09, "learning_rate": 6.331421415632421e-06, "loss": 0.0009, "step": 366740 }, { "epoch": 88.09, "learning_rate": 6.329673211352277e-06, "loss": 0.0009, "step": 366750 }, { "epoch": 88.1, "learning_rate": 6.3279252321493675e-06, "loss": 0.0009, "step": 366760 }, { "epoch": 88.1, "learning_rate": 6.326177478032686e-06, "loss": 0.0011, "step": 366770 }, { "epoch": 88.1, "learning_rate": 6.324429949011262e-06, "loss": 0.001, "step": 366780 }, { "epoch": 88.1, "learning_rate": 6.32268264509408e-06, "loss": 0.001, "step": 366790 }, { "epoch": 88.1, "learning_rate": 6.32093556629017e-06, "loss": 0.001, "step": 366800 }, { "epoch": 88.11, "learning_rate": 6.3191887126085094e-06, "loss": 0.0011, "step": 366810 }, { "epoch": 88.11, "learning_rate": 6.317442084058128e-06, "loss": 0.001, "step": 366820 }, { "epoch": 88.11, "learning_rate": 6.315695680648015e-06, "loss": 0.001, "step": 366830 }, { "epoch": 88.11, "learning_rate": 6.313949502387162e-06, "loss": 0.0011, "step": 366840 }, { "epoch": 88.12, "learning_rate": 6.312203549284584e-06, "loss": 0.001, "step": 366850 }, { "epoch": 88.12, "learning_rate": 6.310457821349269e-06, "loss": 0.001, "step": 366860 }, { "epoch": 88.12, "learning_rate": 6.308712318590226e-06, "loss": 0.001, "step": 366870 }, { "epoch": 88.12, "learning_rate": 6.306967041016437e-06, "loss": 0.0009, "step": 366880 }, { "epoch": 88.12, "learning_rate": 6.305221988636917e-06, "loss": 0.0011, "step": 366890 }, { "epoch": 88.13, "learning_rate": 6.3034771614606465e-06, "loss": 0.001, "step": 366900 }, { "epoch": 88.13, "learning_rate": 6.301732559496609e-06, "loss": 0.001, "step": 366910 }, { "epoch": 88.13, "learning_rate": 6.299988182753819e-06, "loss": 0.001, "step": 366920 }, { "epoch": 88.13, "learning_rate": 6.29824403124124e-06, "loss": 0.0009, "step": 366930 }, { "epoch": 88.14, "learning_rate": 6.2965001049678894e-06, "loss": 0.0011, "step": 366940 }, { "epoch": 88.14, "learning_rate": 6.2947564039427364e-06, "loss": 0.001, "step": 366950 }, { "epoch": 88.14, "learning_rate": 6.293012928174779e-06, "loss": 0.0009, "step": 366960 }, { "epoch": 88.14, "learning_rate": 6.291269677673001e-06, "loss": 0.0011, "step": 366970 }, { "epoch": 88.15, "learning_rate": 6.2895266524463756e-06, "loss": 0.001, "step": 366980 }, { "epoch": 88.15, "learning_rate": 6.287783852503904e-06, "loss": 0.0009, "step": 366990 }, { "epoch": 88.15, "learning_rate": 6.286041277854549e-06, "loss": 0.001, "step": 367000 }, { "epoch": 88.15, "learning_rate": 6.284298928507315e-06, "loss": 0.0017, "step": 367010 }, { "epoch": 88.15, "learning_rate": 6.282556804471157e-06, "loss": 0.0009, "step": 367020 }, { "epoch": 88.16, "learning_rate": 6.280814905755078e-06, "loss": 0.001, "step": 367030 }, { "epoch": 88.16, "learning_rate": 6.2790732323680325e-06, "loss": 0.0009, "step": 367040 }, { "epoch": 88.16, "learning_rate": 6.277331784319007e-06, "loss": 0.001, "step": 367050 }, { "epoch": 88.16, "learning_rate": 6.275590561616995e-06, "loss": 0.001, "step": 367060 }, { "epoch": 88.17, "learning_rate": 6.273849564270939e-06, "loss": 0.0009, "step": 367070 }, { "epoch": 88.17, "learning_rate": 6.272108792289844e-06, "loss": 0.001, "step": 367080 }, { "epoch": 88.17, "learning_rate": 6.270368245682651e-06, "loss": 0.001, "step": 367090 }, { "epoch": 88.17, "learning_rate": 6.268627924458359e-06, "loss": 0.001, "step": 367100 }, { "epoch": 88.18, "learning_rate": 6.266887828625922e-06, "loss": 0.001, "step": 367110 }, { "epoch": 88.18, "learning_rate": 6.265147958194301e-06, "loss": 0.0009, "step": 367120 }, { "epoch": 88.18, "learning_rate": 6.263408313172486e-06, "loss": 0.001, "step": 367130 }, { "epoch": 88.18, "learning_rate": 6.2616688935694165e-06, "loss": 0.0009, "step": 367140 }, { "epoch": 88.18, "learning_rate": 6.259929699394079e-06, "loss": 0.0009, "step": 367150 }, { "epoch": 88.19, "learning_rate": 6.258190730655422e-06, "loss": 0.0011, "step": 367160 }, { "epoch": 88.19, "learning_rate": 6.256451987362427e-06, "loss": 0.0009, "step": 367170 }, { "epoch": 88.19, "learning_rate": 6.254713469524042e-06, "loss": 0.0011, "step": 367180 }, { "epoch": 88.19, "learning_rate": 6.252975177149223e-06, "loss": 0.0009, "step": 367190 }, { "epoch": 88.2, "learning_rate": 6.251237110246944e-06, "loss": 0.0009, "step": 367200 }, { "epoch": 88.2, "learning_rate": 6.249499268826142e-06, "loss": 0.001, "step": 367210 }, { "epoch": 88.2, "learning_rate": 6.247761652895801e-06, "loss": 0.0009, "step": 367220 }, { "epoch": 88.2, "learning_rate": 6.246024262464845e-06, "loss": 0.0015, "step": 367230 }, { "epoch": 88.2, "learning_rate": 6.244287097542262e-06, "loss": 0.0009, "step": 367240 }, { "epoch": 88.21, "learning_rate": 6.242550158136978e-06, "loss": 0.001, "step": 367250 }, { "epoch": 88.21, "learning_rate": 6.240813444257964e-06, "loss": 0.0009, "step": 367260 }, { "epoch": 88.21, "learning_rate": 6.239076955914163e-06, "loss": 0.001, "step": 367270 }, { "epoch": 88.21, "learning_rate": 6.2373406931145185e-06, "loss": 0.001, "step": 367280 }, { "epoch": 88.22, "learning_rate": 6.235604655867993e-06, "loss": 0.0009, "step": 367290 }, { "epoch": 88.22, "learning_rate": 6.233868844183521e-06, "loss": 0.001, "step": 367300 }, { "epoch": 88.22, "learning_rate": 6.232133258070061e-06, "loss": 0.001, "step": 367310 }, { "epoch": 88.22, "learning_rate": 6.230397897536544e-06, "loss": 0.0009, "step": 367320 }, { "epoch": 88.23, "learning_rate": 6.22866276259193e-06, "loss": 0.0009, "step": 367330 }, { "epoch": 88.23, "learning_rate": 6.2269278532451455e-06, "loss": 0.0009, "step": 367340 }, { "epoch": 88.23, "learning_rate": 6.225193169505139e-06, "loss": 0.001, "step": 367350 }, { "epoch": 88.23, "learning_rate": 6.223458711380864e-06, "loss": 0.0009, "step": 367360 }, { "epoch": 88.23, "learning_rate": 6.2217244788812354e-06, "loss": 0.0011, "step": 367370 }, { "epoch": 88.24, "learning_rate": 6.219990472015219e-06, "loss": 0.001, "step": 367380 }, { "epoch": 88.24, "learning_rate": 6.21825669079173e-06, "loss": 0.0009, "step": 367390 }, { "epoch": 88.24, "learning_rate": 6.216523135219715e-06, "loss": 0.0011, "step": 367400 }, { "epoch": 88.24, "learning_rate": 6.214789805308114e-06, "loss": 0.001, "step": 367410 }, { "epoch": 88.25, "learning_rate": 6.213056701065833e-06, "loss": 0.0011, "step": 367420 }, { "epoch": 88.25, "learning_rate": 6.211323822501841e-06, "loss": 0.0008, "step": 367430 }, { "epoch": 88.25, "learning_rate": 6.2095911696250394e-06, "loss": 0.001, "step": 367440 }, { "epoch": 88.25, "learning_rate": 6.207858742444383e-06, "loss": 0.001, "step": 367450 }, { "epoch": 88.26, "learning_rate": 6.206126540968776e-06, "loss": 0.0009, "step": 367460 }, { "epoch": 88.26, "learning_rate": 6.204394565207172e-06, "loss": 0.0009, "step": 367470 }, { "epoch": 88.26, "learning_rate": 6.202662815168481e-06, "loss": 0.001, "step": 367480 }, { "epoch": 88.26, "learning_rate": 6.200931290861622e-06, "loss": 0.001, "step": 367490 }, { "epoch": 88.26, "learning_rate": 6.19919999229554e-06, "loss": 0.0009, "step": 367500 }, { "epoch": 88.27, "learning_rate": 6.197468919479138e-06, "loss": 0.0009, "step": 367510 }, { "epoch": 88.27, "learning_rate": 6.195738072421359e-06, "loss": 0.0009, "step": 367520 }, { "epoch": 88.27, "learning_rate": 6.194007451131096e-06, "loss": 0.001, "step": 367530 }, { "epoch": 88.27, "learning_rate": 6.192277055617302e-06, "loss": 0.0011, "step": 367540 }, { "epoch": 88.28, "learning_rate": 6.190546885888876e-06, "loss": 0.0009, "step": 367550 }, { "epoch": 88.28, "learning_rate": 6.1888169419547225e-06, "loss": 0.0009, "step": 367560 }, { "epoch": 88.28, "learning_rate": 6.18708722382379e-06, "loss": 0.0011, "step": 367570 }, { "epoch": 88.28, "learning_rate": 6.185357731504965e-06, "loss": 0.0009, "step": 367580 }, { "epoch": 88.28, "learning_rate": 6.183628465007179e-06, "loss": 0.0009, "step": 367590 }, { "epoch": 88.29, "learning_rate": 6.181899424339327e-06, "loss": 0.001, "step": 367600 }, { "epoch": 88.29, "learning_rate": 6.180170609510344e-06, "loss": 0.0009, "step": 367610 }, { "epoch": 88.29, "learning_rate": 6.178442020529118e-06, "loss": 0.001, "step": 367620 }, { "epoch": 88.29, "learning_rate": 6.1767136574045814e-06, "loss": 0.001, "step": 367630 }, { "epoch": 88.3, "learning_rate": 6.174985520145615e-06, "loss": 0.0009, "step": 367640 }, { "epoch": 88.3, "learning_rate": 6.173257608761152e-06, "loss": 0.0011, "step": 367650 }, { "epoch": 88.3, "learning_rate": 6.171529923260072e-06, "loss": 0.001, "step": 367660 }, { "epoch": 88.3, "learning_rate": 6.169802463651297e-06, "loss": 0.001, "step": 367670 }, { "epoch": 88.31, "learning_rate": 6.168075229943732e-06, "loss": 0.0009, "step": 367680 }, { "epoch": 88.31, "learning_rate": 6.166348222146279e-06, "loss": 0.0009, "step": 367690 }, { "epoch": 88.31, "learning_rate": 6.16462144026782e-06, "loss": 0.001, "step": 367700 }, { "epoch": 88.31, "learning_rate": 6.162894884317278e-06, "loss": 0.001, "step": 367710 }, { "epoch": 88.31, "learning_rate": 6.161168554303537e-06, "loss": 0.0012, "step": 367720 }, { "epoch": 88.32, "learning_rate": 6.159442450235503e-06, "loss": 0.001, "step": 367730 }, { "epoch": 88.32, "learning_rate": 6.157716572122063e-06, "loss": 0.001, "step": 367740 }, { "epoch": 88.32, "learning_rate": 6.155990919972127e-06, "loss": 0.0009, "step": 367750 }, { "epoch": 88.32, "learning_rate": 6.154265493794581e-06, "loss": 0.0011, "step": 367760 }, { "epoch": 88.33, "learning_rate": 6.152540293598308e-06, "loss": 0.0009, "step": 367770 }, { "epoch": 88.33, "learning_rate": 6.150815319392217e-06, "loss": 0.0009, "step": 367780 }, { "epoch": 88.33, "learning_rate": 6.149090571185184e-06, "loss": 0.001, "step": 367790 }, { "epoch": 88.33, "learning_rate": 6.1473660489861084e-06, "loss": 0.0009, "step": 367800 }, { "epoch": 88.34, "learning_rate": 6.1456417528038715e-06, "loss": 0.0011, "step": 367810 }, { "epoch": 88.34, "learning_rate": 6.143917682647371e-06, "loss": 0.001, "step": 367820 }, { "epoch": 88.34, "learning_rate": 6.142193838525484e-06, "loss": 0.0009, "step": 367830 }, { "epoch": 88.34, "learning_rate": 6.140470220447087e-06, "loss": 0.0009, "step": 367840 }, { "epoch": 88.34, "learning_rate": 6.138746828421082e-06, "loss": 0.0009, "step": 367850 }, { "epoch": 88.35, "learning_rate": 6.137023662456337e-06, "loss": 0.0008, "step": 367860 }, { "epoch": 88.35, "learning_rate": 6.135300722561743e-06, "loss": 0.0008, "step": 367870 }, { "epoch": 88.35, "learning_rate": 6.133578008746166e-06, "loss": 0.001, "step": 367880 }, { "epoch": 88.35, "learning_rate": 6.131855521018509e-06, "loss": 0.0008, "step": 367890 }, { "epoch": 88.36, "learning_rate": 6.130133259387632e-06, "loss": 0.0009, "step": 367900 }, { "epoch": 88.36, "learning_rate": 6.128411223862407e-06, "loss": 0.001, "step": 367910 }, { "epoch": 88.36, "learning_rate": 6.126689414451719e-06, "loss": 0.0055, "step": 367920 }, { "epoch": 88.36, "learning_rate": 6.124967831164447e-06, "loss": 0.001, "step": 367930 }, { "epoch": 88.36, "learning_rate": 6.123246474009448e-06, "loss": 0.001, "step": 367940 }, { "epoch": 88.37, "learning_rate": 6.121525342995616e-06, "loss": 0.001, "step": 367950 }, { "epoch": 88.37, "learning_rate": 6.119804438131793e-06, "loss": 0.0009, "step": 367960 }, { "epoch": 88.37, "learning_rate": 6.118083759426879e-06, "loss": 0.001, "step": 367970 }, { "epoch": 88.37, "learning_rate": 6.116363306889717e-06, "loss": 0.001, "step": 367980 }, { "epoch": 88.38, "learning_rate": 6.114643080529198e-06, "loss": 0.0009, "step": 367990 }, { "epoch": 88.38, "learning_rate": 6.112923080354166e-06, "loss": 0.001, "step": 368000 }, { "epoch": 88.38, "learning_rate": 6.111203306373503e-06, "loss": 0.001, "step": 368010 }, { "epoch": 88.38, "learning_rate": 6.1094837585960514e-06, "loss": 0.0011, "step": 368020 }, { "epoch": 88.39, "learning_rate": 6.1077644370307e-06, "loss": 0.0009, "step": 368030 }, { "epoch": 88.39, "learning_rate": 6.1060453416862895e-06, "loss": 0.001, "step": 368040 }, { "epoch": 88.39, "learning_rate": 6.104326472571698e-06, "loss": 0.001, "step": 368050 }, { "epoch": 88.39, "learning_rate": 6.1026078296957725e-06, "loss": 0.001, "step": 368060 }, { "epoch": 88.39, "learning_rate": 6.100889413067368e-06, "loss": 0.0009, "step": 368070 }, { "epoch": 88.4, "learning_rate": 6.099171222695349e-06, "loss": 0.001, "step": 368080 }, { "epoch": 88.4, "learning_rate": 6.097453258588564e-06, "loss": 0.0011, "step": 368090 }, { "epoch": 88.4, "learning_rate": 6.0957355207558795e-06, "loss": 0.0009, "step": 368100 }, { "epoch": 88.4, "learning_rate": 6.094018009206131e-06, "loss": 0.001, "step": 368110 }, { "epoch": 88.41, "learning_rate": 6.092300723948191e-06, "loss": 0.001, "step": 368120 }, { "epoch": 88.41, "learning_rate": 6.090583664990901e-06, "loss": 0.001, "step": 368130 }, { "epoch": 88.41, "learning_rate": 6.0888668323430985e-06, "loss": 0.001, "step": 368140 }, { "epoch": 88.41, "learning_rate": 6.087150226013655e-06, "loss": 0.0009, "step": 368150 }, { "epoch": 88.41, "learning_rate": 6.0854338460113955e-06, "loss": 0.001, "step": 368160 }, { "epoch": 88.42, "learning_rate": 6.083717692345192e-06, "loss": 0.0009, "step": 368170 }, { "epoch": 88.42, "learning_rate": 6.082001765023859e-06, "loss": 0.0009, "step": 368180 }, { "epoch": 88.42, "learning_rate": 6.080286064056268e-06, "loss": 0.0009, "step": 368190 }, { "epoch": 88.42, "learning_rate": 6.078570589451244e-06, "loss": 0.001, "step": 368200 }, { "epoch": 88.43, "learning_rate": 6.07685534121763e-06, "loss": 0.0009, "step": 368210 }, { "epoch": 88.43, "learning_rate": 6.075140319364281e-06, "loss": 0.0011, "step": 368220 }, { "epoch": 88.43, "learning_rate": 6.073425523900011e-06, "loss": 0.0009, "step": 368230 }, { "epoch": 88.43, "learning_rate": 6.071710954833676e-06, "loss": 0.001, "step": 368240 }, { "epoch": 88.44, "learning_rate": 6.069996612174122e-06, "loss": 0.0009, "step": 368250 }, { "epoch": 88.44, "learning_rate": 6.068282495930161e-06, "loss": 0.0009, "step": 368260 }, { "epoch": 88.44, "learning_rate": 6.066568606110651e-06, "loss": 0.0009, "step": 368270 }, { "epoch": 88.44, "learning_rate": 6.064854942724402e-06, "loss": 0.001, "step": 368280 }, { "epoch": 88.44, "learning_rate": 6.063141505780268e-06, "loss": 0.001, "step": 368290 }, { "epoch": 88.45, "learning_rate": 6.0614282952870586e-06, "loss": 0.0009, "step": 368300 }, { "epoch": 88.45, "learning_rate": 6.059715311253628e-06, "loss": 0.0009, "step": 368310 }, { "epoch": 88.45, "learning_rate": 6.05800255368878e-06, "loss": 0.001, "step": 368320 }, { "epoch": 88.45, "learning_rate": 6.056290022601363e-06, "loss": 0.001, "step": 368330 }, { "epoch": 88.46, "learning_rate": 6.0545777180001985e-06, "loss": 0.001, "step": 368340 }, { "epoch": 88.46, "learning_rate": 6.0528656398940895e-06, "loss": 0.0009, "step": 368350 }, { "epoch": 88.46, "learning_rate": 6.051153788291897e-06, "loss": 0.001, "step": 368360 }, { "epoch": 88.46, "learning_rate": 6.049442163202413e-06, "loss": 0.001, "step": 368370 }, { "epoch": 88.47, "learning_rate": 6.047730764634479e-06, "loss": 0.0009, "step": 368380 }, { "epoch": 88.47, "learning_rate": 6.046019592596902e-06, "loss": 0.0009, "step": 368390 }, { "epoch": 88.47, "learning_rate": 6.044308647098512e-06, "loss": 0.001, "step": 368400 }, { "epoch": 88.47, "learning_rate": 6.0425979281481245e-06, "loss": 0.0009, "step": 368410 }, { "epoch": 88.47, "learning_rate": 6.04088743575455e-06, "loss": 0.0009, "step": 368420 }, { "epoch": 88.48, "learning_rate": 6.039177169926613e-06, "loss": 0.0011, "step": 368430 }, { "epoch": 88.48, "learning_rate": 6.037467130673119e-06, "loss": 0.001, "step": 368440 }, { "epoch": 88.48, "learning_rate": 6.035757318002894e-06, "loss": 0.001, "step": 368450 }, { "epoch": 88.48, "learning_rate": 6.03404773192473e-06, "loss": 0.001, "step": 368460 }, { "epoch": 88.49, "learning_rate": 6.032338372447466e-06, "loss": 0.0009, "step": 368470 }, { "epoch": 88.49, "learning_rate": 6.030629239579899e-06, "loss": 0.001, "step": 368480 }, { "epoch": 88.49, "learning_rate": 6.028920333330823e-06, "loss": 0.0009, "step": 368490 }, { "epoch": 88.49, "learning_rate": 6.027211653709069e-06, "loss": 0.0009, "step": 368500 }, { "epoch": 88.49, "learning_rate": 6.025503200723426e-06, "loss": 0.0008, "step": 368510 }, { "epoch": 88.5, "learning_rate": 6.023794974382713e-06, "loss": 0.001, "step": 368520 }, { "epoch": 88.5, "learning_rate": 6.022086974695723e-06, "loss": 0.0009, "step": 368530 }, { "epoch": 88.5, "learning_rate": 6.020379201671272e-06, "loss": 0.001, "step": 368540 }, { "epoch": 88.5, "learning_rate": 6.018671655318148e-06, "loss": 0.0009, "step": 368550 }, { "epoch": 88.51, "learning_rate": 6.016964335645153e-06, "loss": 0.0009, "step": 368560 }, { "epoch": 88.51, "learning_rate": 6.0152572426611045e-06, "loss": 0.001, "step": 368570 }, { "epoch": 88.51, "learning_rate": 6.013550376374771e-06, "loss": 0.0009, "step": 368580 }, { "epoch": 88.51, "learning_rate": 6.011843736794986e-06, "loss": 0.001, "step": 368590 }, { "epoch": 88.52, "learning_rate": 6.010137323930509e-06, "loss": 0.0011, "step": 368600 }, { "epoch": 88.52, "learning_rate": 6.008431137790166e-06, "loss": 0.0009, "step": 368610 }, { "epoch": 88.52, "learning_rate": 6.006725178382739e-06, "loss": 0.0009, "step": 368620 }, { "epoch": 88.52, "learning_rate": 6.005019445717003e-06, "loss": 0.001, "step": 368630 }, { "epoch": 88.52, "learning_rate": 6.003313939801775e-06, "loss": 0.0008, "step": 368640 }, { "epoch": 88.53, "learning_rate": 6.0016086606458244e-06, "loss": 0.0009, "step": 368650 }, { "epoch": 88.53, "learning_rate": 5.999903608257962e-06, "loss": 0.0009, "step": 368660 }, { "epoch": 88.53, "learning_rate": 5.9981987826469575e-06, "loss": 0.001, "step": 368670 }, { "epoch": 88.53, "learning_rate": 5.996494183821611e-06, "loss": 0.0009, "step": 368680 }, { "epoch": 88.54, "learning_rate": 5.994789811790702e-06, "loss": 0.001, "step": 368690 }, { "epoch": 88.54, "learning_rate": 5.993085666563003e-06, "loss": 0.0011, "step": 368700 }, { "epoch": 88.54, "learning_rate": 5.991381748147318e-06, "loss": 0.0012, "step": 368710 }, { "epoch": 88.54, "learning_rate": 5.989678056552412e-06, "loss": 0.001, "step": 368720 }, { "epoch": 88.55, "learning_rate": 5.9879745917870765e-06, "loss": 0.0011, "step": 368730 }, { "epoch": 88.55, "learning_rate": 5.986271353860084e-06, "loss": 0.0009, "step": 368740 }, { "epoch": 88.55, "learning_rate": 5.984568342780228e-06, "loss": 0.001, "step": 368750 }, { "epoch": 88.55, "learning_rate": 5.982865558556272e-06, "loss": 0.001, "step": 368760 }, { "epoch": 88.55, "learning_rate": 5.981163001196982e-06, "loss": 0.001, "step": 368770 }, { "epoch": 88.56, "learning_rate": 5.979460670711162e-06, "loss": 0.001, "step": 368780 }, { "epoch": 88.56, "learning_rate": 5.977758567107555e-06, "loss": 0.001, "step": 368790 }, { "epoch": 88.56, "learning_rate": 5.97605669039496e-06, "loss": 0.001, "step": 368800 }, { "epoch": 88.56, "learning_rate": 5.9743550405821245e-06, "loss": 0.0009, "step": 368810 }, { "epoch": 88.57, "learning_rate": 5.9726536176778426e-06, "loss": 0.0011, "step": 368820 }, { "epoch": 88.57, "learning_rate": 5.970952421690862e-06, "loss": 0.0009, "step": 368830 }, { "epoch": 88.57, "learning_rate": 5.969251452629976e-06, "loss": 0.0009, "step": 368840 }, { "epoch": 88.57, "learning_rate": 5.967550710503916e-06, "loss": 0.001, "step": 368850 }, { "epoch": 88.57, "learning_rate": 5.965850195321488e-06, "loss": 0.001, "step": 368860 }, { "epoch": 88.58, "learning_rate": 5.964149907091421e-06, "loss": 0.0011, "step": 368870 }, { "epoch": 88.58, "learning_rate": 5.962449845822493e-06, "loss": 0.0009, "step": 368880 }, { "epoch": 88.58, "learning_rate": 5.960750011523475e-06, "loss": 0.0034, "step": 368890 }, { "epoch": 88.58, "learning_rate": 5.9590504042031095e-06, "loss": 0.001, "step": 368900 }, { "epoch": 88.59, "learning_rate": 5.957351023870184e-06, "loss": 0.0009, "step": 368910 }, { "epoch": 88.59, "learning_rate": 5.95565187053343e-06, "loss": 0.001, "step": 368920 }, { "epoch": 88.59, "learning_rate": 5.953952944201607e-06, "loss": 0.0009, "step": 368930 }, { "epoch": 88.59, "learning_rate": 5.952254244883493e-06, "loss": 0.0009, "step": 368940 }, { "epoch": 88.6, "learning_rate": 5.950555772587818e-06, "loss": 0.0009, "step": 368950 }, { "epoch": 88.6, "learning_rate": 5.948857527323354e-06, "loss": 0.0009, "step": 368960 }, { "epoch": 88.6, "learning_rate": 5.947159509098838e-06, "loss": 0.0036, "step": 368970 }, { "epoch": 88.6, "learning_rate": 5.94546171792304e-06, "loss": 0.001, "step": 368980 }, { "epoch": 88.6, "learning_rate": 5.943764153804699e-06, "loss": 0.001, "step": 368990 }, { "epoch": 88.61, "learning_rate": 5.942066816752556e-06, "loss": 0.0009, "step": 369000 }, { "epoch": 88.61, "learning_rate": 5.940369706775378e-06, "loss": 0.0011, "step": 369010 }, { "epoch": 88.61, "learning_rate": 5.938672823881897e-06, "loss": 0.001, "step": 369020 }, { "epoch": 88.61, "learning_rate": 5.936976168080871e-06, "loss": 0.001, "step": 369030 }, { "epoch": 88.62, "learning_rate": 5.935279739381028e-06, "loss": 0.001, "step": 369040 }, { "epoch": 88.62, "learning_rate": 5.933583537791132e-06, "loss": 0.001, "step": 369050 }, { "epoch": 88.62, "learning_rate": 5.931887563319916e-06, "loss": 0.001, "step": 369060 }, { "epoch": 88.62, "learning_rate": 5.930191815976111e-06, "loss": 0.001, "step": 369070 }, { "epoch": 88.63, "learning_rate": 5.9284962957684705e-06, "loss": 0.001, "step": 369080 }, { "epoch": 88.63, "learning_rate": 5.926801002705723e-06, "loss": 0.001, "step": 369090 }, { "epoch": 88.63, "learning_rate": 5.925105936796621e-06, "loss": 0.001, "step": 369100 }, { "epoch": 88.63, "learning_rate": 5.92341109804988e-06, "loss": 0.0009, "step": 369110 }, { "epoch": 88.63, "learning_rate": 5.92171648647426e-06, "loss": 0.001, "step": 369120 }, { "epoch": 88.64, "learning_rate": 5.920022102078465e-06, "loss": 0.001, "step": 369130 }, { "epoch": 88.64, "learning_rate": 5.91832794487126e-06, "loss": 0.001, "step": 369140 }, { "epoch": 88.64, "learning_rate": 5.91663401486135e-06, "loss": 0.0009, "step": 369150 }, { "epoch": 88.64, "learning_rate": 5.914940312057488e-06, "loss": 0.001, "step": 369160 }, { "epoch": 88.65, "learning_rate": 5.9132468364683834e-06, "loss": 0.001, "step": 369170 }, { "epoch": 88.65, "learning_rate": 5.91155358810277e-06, "loss": 0.0011, "step": 369180 }, { "epoch": 88.65, "learning_rate": 5.909860566969389e-06, "loss": 0.001, "step": 369190 }, { "epoch": 88.65, "learning_rate": 5.90816777307695e-06, "loss": 0.0009, "step": 369200 }, { "epoch": 88.65, "learning_rate": 5.906475206434181e-06, "loss": 0.0009, "step": 369210 }, { "epoch": 88.66, "learning_rate": 5.904782867049813e-06, "loss": 0.0009, "step": 369220 }, { "epoch": 88.66, "learning_rate": 5.903090754932556e-06, "loss": 0.001, "step": 369230 }, { "epoch": 88.66, "learning_rate": 5.901398870091146e-06, "loss": 0.0009, "step": 369240 }, { "epoch": 88.66, "learning_rate": 5.899707212534284e-06, "loss": 0.0009, "step": 369250 }, { "epoch": 88.67, "learning_rate": 5.898015782270705e-06, "loss": 0.0009, "step": 369260 }, { "epoch": 88.67, "learning_rate": 5.8963245793091316e-06, "loss": 0.001, "step": 369270 }, { "epoch": 88.67, "learning_rate": 5.894633603658251e-06, "loss": 0.0009, "step": 369280 }, { "epoch": 88.67, "learning_rate": 5.892942855326811e-06, "loss": 0.001, "step": 369290 }, { "epoch": 88.68, "learning_rate": 5.891252334323505e-06, "loss": 0.001, "step": 369300 }, { "epoch": 88.68, "learning_rate": 5.889562040657059e-06, "loss": 0.003, "step": 369310 }, { "epoch": 88.68, "learning_rate": 5.887871974336168e-06, "loss": 0.001, "step": 369320 }, { "epoch": 88.68, "learning_rate": 5.886182135369567e-06, "loss": 0.0009, "step": 369330 }, { "epoch": 88.68, "learning_rate": 5.88449252376595e-06, "loss": 0.001, "step": 369340 }, { "epoch": 88.69, "learning_rate": 5.882803139534021e-06, "loss": 0.0009, "step": 369350 }, { "epoch": 88.69, "learning_rate": 5.8811139826825015e-06, "loss": 0.001, "step": 369360 }, { "epoch": 88.69, "learning_rate": 5.879425053220078e-06, "loss": 0.0009, "step": 369370 }, { "epoch": 88.69, "learning_rate": 5.877736351155477e-06, "loss": 0.001, "step": 369380 }, { "epoch": 88.7, "learning_rate": 5.876047876497382e-06, "loss": 0.0011, "step": 369390 }, { "epoch": 88.7, "learning_rate": 5.874359629254511e-06, "loss": 0.0009, "step": 369400 }, { "epoch": 88.7, "learning_rate": 5.872671609435565e-06, "loss": 0.001, "step": 369410 }, { "epoch": 88.7, "learning_rate": 5.870983817049225e-06, "loss": 0.0012, "step": 369420 }, { "epoch": 88.71, "learning_rate": 5.8692962521042175e-06, "loss": 0.0011, "step": 369430 }, { "epoch": 88.71, "learning_rate": 5.867608914609213e-06, "loss": 0.0009, "step": 369440 }, { "epoch": 88.71, "learning_rate": 5.865921804572921e-06, "loss": 0.0011, "step": 369450 }, { "epoch": 88.71, "learning_rate": 5.864234922004047e-06, "loss": 0.0009, "step": 369460 }, { "epoch": 88.71, "learning_rate": 5.862548266911267e-06, "loss": 0.0009, "step": 369470 }, { "epoch": 88.72, "learning_rate": 5.860861839303289e-06, "loss": 0.0009, "step": 369480 }, { "epoch": 88.72, "learning_rate": 5.859175639188785e-06, "loss": 0.0009, "step": 369490 }, { "epoch": 88.72, "learning_rate": 5.857489666576477e-06, "loss": 0.0011, "step": 369500 }, { "epoch": 88.72, "learning_rate": 5.855803921475023e-06, "loss": 0.0009, "step": 369510 }, { "epoch": 88.73, "learning_rate": 5.854118403893133e-06, "loss": 0.0011, "step": 369520 }, { "epoch": 88.73, "learning_rate": 5.8524331138394785e-06, "loss": 0.001, "step": 369530 }, { "epoch": 88.73, "learning_rate": 5.850748051322757e-06, "loss": 0.001, "step": 369540 }, { "epoch": 88.73, "learning_rate": 5.849063216351658e-06, "loss": 0.001, "step": 369550 }, { "epoch": 88.73, "learning_rate": 5.847378608934839e-06, "loss": 0.001, "step": 369560 }, { "epoch": 88.74, "learning_rate": 5.845694229081011e-06, "loss": 0.001, "step": 369570 }, { "epoch": 88.74, "learning_rate": 5.844010076798833e-06, "loss": 0.0011, "step": 369580 }, { "epoch": 88.74, "learning_rate": 5.842326152097011e-06, "loss": 0.0009, "step": 369590 }, { "epoch": 88.74, "learning_rate": 5.840642454984197e-06, "loss": 0.001, "step": 369600 }, { "epoch": 88.75, "learning_rate": 5.8389589854690895e-06, "loss": 0.001, "step": 369610 }, { "epoch": 88.75, "learning_rate": 5.837275743560355e-06, "loss": 0.0009, "step": 369620 }, { "epoch": 88.75, "learning_rate": 5.8355927292666645e-06, "loss": 0.0011, "step": 369630 }, { "epoch": 88.75, "learning_rate": 5.833909942596705e-06, "loss": 0.001, "step": 369640 }, { "epoch": 88.76, "learning_rate": 5.8322273835591355e-06, "loss": 0.0009, "step": 369650 }, { "epoch": 88.76, "learning_rate": 5.830545052162645e-06, "loss": 0.001, "step": 369660 }, { "epoch": 88.76, "learning_rate": 5.8288629484158805e-06, "loss": 0.001, "step": 369670 }, { "epoch": 88.76, "learning_rate": 5.827181072327542e-06, "loss": 0.0008, "step": 369680 }, { "epoch": 88.76, "learning_rate": 5.8254994239062665e-06, "loss": 0.001, "step": 369690 }, { "epoch": 88.77, "learning_rate": 5.823818003160747e-06, "loss": 0.001, "step": 369700 }, { "epoch": 88.77, "learning_rate": 5.822136810099643e-06, "loss": 0.001, "step": 369710 }, { "epoch": 88.77, "learning_rate": 5.820455844731598e-06, "loss": 0.0011, "step": 369720 }, { "epoch": 88.77, "learning_rate": 5.818775107065305e-06, "loss": 0.001, "step": 369730 }, { "epoch": 88.78, "learning_rate": 5.817094597109407e-06, "loss": 0.0009, "step": 369740 }, { "epoch": 88.78, "learning_rate": 5.815414314872575e-06, "loss": 0.0009, "step": 369750 }, { "epoch": 88.78, "learning_rate": 5.813734260363474e-06, "loss": 0.001, "step": 369760 }, { "epoch": 88.78, "learning_rate": 5.812054433590741e-06, "loss": 0.0009, "step": 369770 }, { "epoch": 88.79, "learning_rate": 5.810374834563065e-06, "loss": 0.001, "step": 369780 }, { "epoch": 88.79, "learning_rate": 5.808695463289076e-06, "loss": 0.001, "step": 369790 }, { "epoch": 88.79, "learning_rate": 5.8070163197774476e-06, "loss": 0.001, "step": 369800 }, { "epoch": 88.79, "learning_rate": 5.80533740403682e-06, "loss": 0.001, "step": 369810 }, { "epoch": 88.79, "learning_rate": 5.80365871607586e-06, "loss": 0.0011, "step": 369820 }, { "epoch": 88.8, "learning_rate": 5.8019802559032e-06, "loss": 0.0009, "step": 369830 }, { "epoch": 88.8, "learning_rate": 5.800302023527521e-06, "loss": 0.0011, "step": 369840 }, { "epoch": 88.8, "learning_rate": 5.798624018957449e-06, "loss": 0.001, "step": 369850 }, { "epoch": 88.8, "learning_rate": 5.796946242201629e-06, "loss": 0.0009, "step": 369860 }, { "epoch": 88.81, "learning_rate": 5.795268693268724e-06, "loss": 0.001, "step": 369870 }, { "epoch": 88.81, "learning_rate": 5.793591372167367e-06, "loss": 0.001, "step": 369880 }, { "epoch": 88.81, "learning_rate": 5.791914278906224e-06, "loss": 0.0009, "step": 369890 }, { "epoch": 88.81, "learning_rate": 5.790237413493909e-06, "loss": 0.0011, "step": 369900 }, { "epoch": 88.81, "learning_rate": 5.788560775939089e-06, "loss": 0.0011, "step": 369910 }, { "epoch": 88.82, "learning_rate": 5.786884366250401e-06, "loss": 0.0009, "step": 369920 }, { "epoch": 88.82, "learning_rate": 5.7852081844364695e-06, "loss": 0.001, "step": 369930 }, { "epoch": 88.82, "learning_rate": 5.7835322305059506e-06, "loss": 0.0011, "step": 369940 }, { "epoch": 88.82, "learning_rate": 5.78185650446747e-06, "loss": 0.0009, "step": 369950 }, { "epoch": 88.83, "learning_rate": 5.780181006329677e-06, "loss": 0.0009, "step": 369960 }, { "epoch": 88.83, "learning_rate": 5.778505736101197e-06, "loss": 0.0009, "step": 369970 }, { "epoch": 88.83, "learning_rate": 5.7768306937906745e-06, "loss": 0.0009, "step": 369980 }, { "epoch": 88.83, "learning_rate": 5.775155879406735e-06, "loss": 0.001, "step": 369990 }, { "epoch": 88.84, "learning_rate": 5.7734812929579995e-06, "loss": 0.001, "step": 370000 }, { "epoch": 88.84, "learning_rate": 5.771806934453128e-06, "loss": 0.001, "step": 370010 }, { "epoch": 88.84, "learning_rate": 5.7701328039007184e-06, "loss": 0.0009, "step": 370020 }, { "epoch": 88.84, "learning_rate": 5.768458901309426e-06, "loss": 0.0009, "step": 370030 }, { "epoch": 88.84, "learning_rate": 5.766785226687854e-06, "loss": 0.001, "step": 370040 }, { "epoch": 88.85, "learning_rate": 5.765111780044652e-06, "loss": 0.0009, "step": 370050 }, { "epoch": 88.85, "learning_rate": 5.763438561388423e-06, "loss": 0.0011, "step": 370060 }, { "epoch": 88.85, "learning_rate": 5.761765570727801e-06, "loss": 0.0009, "step": 370070 }, { "epoch": 88.85, "learning_rate": 5.760092808071421e-06, "loss": 0.0009, "step": 370080 }, { "epoch": 88.86, "learning_rate": 5.758420273427884e-06, "loss": 0.001, "step": 370090 }, { "epoch": 88.86, "learning_rate": 5.756747966805826e-06, "loss": 0.0009, "step": 370100 }, { "epoch": 88.86, "learning_rate": 5.755075888213845e-06, "loss": 0.0009, "step": 370110 }, { "epoch": 88.86, "learning_rate": 5.7534040376605866e-06, "loss": 0.001, "step": 370120 }, { "epoch": 88.87, "learning_rate": 5.75173241515466e-06, "loss": 0.0013, "step": 370130 }, { "epoch": 88.87, "learning_rate": 5.750061020704656e-06, "loss": 0.0009, "step": 370140 }, { "epoch": 88.87, "learning_rate": 5.748389854319219e-06, "loss": 0.001, "step": 370150 }, { "epoch": 88.87, "learning_rate": 5.746718916006938e-06, "loss": 0.0009, "step": 370160 }, { "epoch": 88.87, "learning_rate": 5.745048205776454e-06, "loss": 0.001, "step": 370170 }, { "epoch": 88.88, "learning_rate": 5.743377723636345e-06, "loss": 0.0009, "step": 370180 }, { "epoch": 88.88, "learning_rate": 5.7417074695952536e-06, "loss": 0.001, "step": 370190 }, { "epoch": 88.88, "learning_rate": 5.740037443661766e-06, "loss": 0.001, "step": 370200 }, { "epoch": 88.88, "learning_rate": 5.738367645844489e-06, "loss": 0.001, "step": 370210 }, { "epoch": 88.89, "learning_rate": 5.736698076152047e-06, "loss": 0.0009, "step": 370220 }, { "epoch": 88.89, "learning_rate": 5.7350287345930175e-06, "loss": 0.0011, "step": 370230 }, { "epoch": 88.89, "learning_rate": 5.733359621176032e-06, "loss": 0.0009, "step": 370240 }, { "epoch": 88.89, "learning_rate": 5.731690735909672e-06, "loss": 0.001, "step": 370250 }, { "epoch": 88.89, "learning_rate": 5.73002207880256e-06, "loss": 0.0009, "step": 370260 }, { "epoch": 88.9, "learning_rate": 5.728353649863277e-06, "loss": 0.0009, "step": 370270 }, { "epoch": 88.9, "learning_rate": 5.726685449100427e-06, "loss": 0.001, "step": 370280 }, { "epoch": 88.9, "learning_rate": 5.725017476522615e-06, "loss": 0.0009, "step": 370290 }, { "epoch": 88.9, "learning_rate": 5.7233497321384275e-06, "loss": 0.001, "step": 370300 }, { "epoch": 88.91, "learning_rate": 5.721682215956476e-06, "loss": 0.0009, "step": 370310 }, { "epoch": 88.91, "learning_rate": 5.720014927985329e-06, "loss": 0.001, "step": 370320 }, { "epoch": 88.91, "learning_rate": 5.718347868233609e-06, "loss": 0.001, "step": 370330 }, { "epoch": 88.91, "learning_rate": 5.7166810367098814e-06, "loss": 0.001, "step": 370340 }, { "epoch": 88.92, "learning_rate": 5.7150144334227665e-06, "loss": 0.001, "step": 370350 }, { "epoch": 88.92, "learning_rate": 5.713348058380819e-06, "loss": 0.001, "step": 370360 }, { "epoch": 88.92, "learning_rate": 5.711681911592659e-06, "loss": 0.0009, "step": 370370 }, { "epoch": 88.92, "learning_rate": 5.710015993066853e-06, "loss": 0.0009, "step": 370380 }, { "epoch": 88.92, "learning_rate": 5.7083503028119935e-06, "loss": 0.001, "step": 370390 }, { "epoch": 88.93, "learning_rate": 5.706684840836674e-06, "loss": 0.001, "step": 370400 }, { "epoch": 88.93, "learning_rate": 5.705019607149475e-06, "loss": 0.001, "step": 370410 }, { "epoch": 88.93, "learning_rate": 5.703354601758965e-06, "loss": 0.0009, "step": 370420 }, { "epoch": 88.93, "learning_rate": 5.701689824673745e-06, "loss": 0.0009, "step": 370430 }, { "epoch": 88.94, "learning_rate": 5.700025275902371e-06, "loss": 0.0009, "step": 370440 }, { "epoch": 88.94, "learning_rate": 5.698360955453453e-06, "loss": 0.0009, "step": 370450 }, { "epoch": 88.94, "learning_rate": 5.696696863335538e-06, "loss": 0.001, "step": 370460 }, { "epoch": 88.94, "learning_rate": 5.695032999557231e-06, "loss": 0.0009, "step": 370470 }, { "epoch": 88.95, "learning_rate": 5.693369364127088e-06, "loss": 0.001, "step": 370480 }, { "epoch": 88.95, "learning_rate": 5.691705957053695e-06, "loss": 0.0009, "step": 370490 }, { "epoch": 88.95, "learning_rate": 5.690042778345617e-06, "loss": 0.0009, "step": 370500 }, { "epoch": 89.0, "learning_rate": 5.688379828011425e-06, "loss": 0.001, "step": 370510 }, { "epoch": 89.0, "learning_rate": 5.686717106059702e-06, "loss": 0.0009, "step": 370520 }, { "epoch": 89.01, "learning_rate": 5.6850546124989965e-06, "loss": 0.0009, "step": 370530 }, { "epoch": 89.01, "learning_rate": 5.683392347337902e-06, "loss": 0.001, "step": 370540 }, { "epoch": 89.01, "learning_rate": 5.681730310584965e-06, "loss": 0.0009, "step": 370550 }, { "epoch": 89.01, "learning_rate": 5.68006850224877e-06, "loss": 0.0009, "step": 370560 }, { "epoch": 89.01, "learning_rate": 5.67840692233787e-06, "loss": 0.0009, "step": 370570 }, { "epoch": 89.02, "learning_rate": 5.676745570860819e-06, "loss": 0.0011, "step": 370580 }, { "epoch": 89.02, "learning_rate": 5.675084447826206e-06, "loss": 0.0009, "step": 370590 }, { "epoch": 89.02, "learning_rate": 5.673423553242568e-06, "loss": 0.0009, "step": 370600 }, { "epoch": 89.02, "learning_rate": 5.6717628871184866e-06, "loss": 0.0009, "step": 370610 }, { "epoch": 89.03, "learning_rate": 5.6701024494624995e-06, "loss": 0.0009, "step": 370620 }, { "epoch": 89.03, "learning_rate": 5.668442240283184e-06, "loss": 0.001, "step": 370630 }, { "epoch": 89.03, "learning_rate": 5.6667822595890765e-06, "loss": 0.001, "step": 370640 }, { "epoch": 89.03, "learning_rate": 5.665122507388759e-06, "loss": 0.001, "step": 370650 }, { "epoch": 89.03, "learning_rate": 5.663462983690754e-06, "loss": 0.001, "step": 370660 }, { "epoch": 89.04, "learning_rate": 5.661803688503647e-06, "loss": 0.001, "step": 370670 }, { "epoch": 89.04, "learning_rate": 5.660144621835961e-06, "loss": 0.0009, "step": 370680 }, { "epoch": 89.04, "learning_rate": 5.65848578369626e-06, "loss": 0.0009, "step": 370690 }, { "epoch": 89.04, "learning_rate": 5.6568271740931045e-06, "loss": 0.0011, "step": 370700 }, { "epoch": 89.05, "learning_rate": 5.655168793035032e-06, "loss": 0.001, "step": 370710 }, { "epoch": 89.05, "learning_rate": 5.6535106405305795e-06, "loss": 0.001, "step": 370720 }, { "epoch": 89.05, "learning_rate": 5.651852716588319e-06, "loss": 0.001, "step": 370730 }, { "epoch": 89.05, "learning_rate": 5.650195021216764e-06, "loss": 0.0011, "step": 370740 }, { "epoch": 89.06, "learning_rate": 5.648537554424488e-06, "loss": 0.0009, "step": 370750 }, { "epoch": 89.06, "learning_rate": 5.646880316220004e-06, "loss": 0.001, "step": 370760 }, { "epoch": 89.06, "learning_rate": 5.645223306611885e-06, "loss": 0.0009, "step": 370770 }, { "epoch": 89.06, "learning_rate": 5.643566525608657e-06, "loss": 0.0009, "step": 370780 }, { "epoch": 89.06, "learning_rate": 5.641909973218845e-06, "loss": 0.001, "step": 370790 }, { "epoch": 89.07, "learning_rate": 5.640253649451016e-06, "loss": 0.0009, "step": 370800 }, { "epoch": 89.07, "learning_rate": 5.638597554313674e-06, "loss": 0.001, "step": 370810 }, { "epoch": 89.07, "learning_rate": 5.636941687815384e-06, "loss": 0.0009, "step": 370820 }, { "epoch": 89.07, "learning_rate": 5.635286049964655e-06, "loss": 0.0009, "step": 370830 }, { "epoch": 89.08, "learning_rate": 5.6336306407700435e-06, "loss": 0.0009, "step": 370840 }, { "epoch": 89.08, "learning_rate": 5.6319754602400686e-06, "loss": 0.0009, "step": 370850 }, { "epoch": 89.08, "learning_rate": 5.630320508383257e-06, "loss": 0.0009, "step": 370860 }, { "epoch": 89.08, "learning_rate": 5.628665785208154e-06, "loss": 0.0009, "step": 370870 }, { "epoch": 89.09, "learning_rate": 5.627011290723267e-06, "loss": 0.0011, "step": 370880 }, { "epoch": 89.09, "learning_rate": 5.625357024937145e-06, "loss": 0.0009, "step": 370890 }, { "epoch": 89.09, "learning_rate": 5.6237029878582925e-06, "loss": 0.001, "step": 370900 }, { "epoch": 89.09, "learning_rate": 5.622049179495254e-06, "loss": 0.0009, "step": 370910 }, { "epoch": 89.09, "learning_rate": 5.620395599856548e-06, "loss": 0.001, "step": 370920 }, { "epoch": 89.1, "learning_rate": 5.618742248950681e-06, "loss": 0.0009, "step": 370930 }, { "epoch": 89.1, "learning_rate": 5.617089126786201e-06, "loss": 0.001, "step": 370940 }, { "epoch": 89.1, "learning_rate": 5.615436233371607e-06, "loss": 0.001, "step": 370950 }, { "epoch": 89.1, "learning_rate": 5.613783568715419e-06, "loss": 0.001, "step": 370960 }, { "epoch": 89.11, "learning_rate": 5.612131132826176e-06, "loss": 0.001, "step": 370970 }, { "epoch": 89.11, "learning_rate": 5.61047892571237e-06, "loss": 0.0009, "step": 370980 }, { "epoch": 89.11, "learning_rate": 5.608826947382534e-06, "loss": 0.001, "step": 370990 }, { "epoch": 89.11, "learning_rate": 5.607175197845166e-06, "loss": 0.001, "step": 371000 }, { "epoch": 89.11, "learning_rate": 5.605523677108798e-06, "loss": 0.0009, "step": 371010 }, { "epoch": 89.12, "learning_rate": 5.603872385181924e-06, "loss": 0.001, "step": 371020 }, { "epoch": 89.12, "learning_rate": 5.6022213220730705e-06, "loss": 0.0009, "step": 371030 }, { "epoch": 89.12, "learning_rate": 5.600570487790735e-06, "loss": 0.0009, "step": 371040 }, { "epoch": 89.12, "learning_rate": 5.598919882343434e-06, "loss": 0.001, "step": 371050 }, { "epoch": 89.13, "learning_rate": 5.597269505739672e-06, "loss": 0.001, "step": 371060 }, { "epoch": 89.13, "learning_rate": 5.595619357987947e-06, "loss": 0.001, "step": 371070 }, { "epoch": 89.13, "learning_rate": 5.59396943909678e-06, "loss": 0.001, "step": 371080 }, { "epoch": 89.13, "learning_rate": 5.5923197490746534e-06, "loss": 0.0009, "step": 371090 }, { "epoch": 89.14, "learning_rate": 5.590670287930095e-06, "loss": 0.0009, "step": 371100 }, { "epoch": 89.14, "learning_rate": 5.5890210556715786e-06, "loss": 0.0009, "step": 371110 }, { "epoch": 89.14, "learning_rate": 5.587372052307632e-06, "loss": 0.0011, "step": 371120 }, { "epoch": 89.14, "learning_rate": 5.585723277846738e-06, "loss": 0.0011, "step": 371130 }, { "epoch": 89.14, "learning_rate": 5.584074732297395e-06, "loss": 0.0009, "step": 371140 }, { "epoch": 89.15, "learning_rate": 5.582426415668107e-06, "loss": 0.001, "step": 371150 }, { "epoch": 89.15, "learning_rate": 5.580778327967351e-06, "loss": 0.0011, "step": 371160 }, { "epoch": 89.15, "learning_rate": 5.579130469203653e-06, "loss": 0.0009, "step": 371170 }, { "epoch": 89.15, "learning_rate": 5.5774828393854725e-06, "loss": 0.0011, "step": 371180 }, { "epoch": 89.16, "learning_rate": 5.575835438521326e-06, "loss": 0.001, "step": 371190 }, { "epoch": 89.16, "learning_rate": 5.574188266619696e-06, "loss": 0.0011, "step": 371200 }, { "epoch": 89.16, "learning_rate": 5.572541323689062e-06, "loss": 0.001, "step": 371210 }, { "epoch": 89.16, "learning_rate": 5.5708946097379314e-06, "loss": 0.001, "step": 371220 }, { "epoch": 89.17, "learning_rate": 5.569248124774773e-06, "loss": 0.001, "step": 371230 }, { "epoch": 89.17, "learning_rate": 5.567601868808087e-06, "loss": 0.0009, "step": 371240 }, { "epoch": 89.17, "learning_rate": 5.565955841846343e-06, "loss": 0.0009, "step": 371250 }, { "epoch": 89.17, "learning_rate": 5.564310043898047e-06, "loss": 0.0009, "step": 371260 }, { "epoch": 89.17, "learning_rate": 5.5626644749716575e-06, "loss": 0.0009, "step": 371270 }, { "epoch": 89.18, "learning_rate": 5.561019135075668e-06, "loss": 0.0009, "step": 371280 }, { "epoch": 89.18, "learning_rate": 5.559374024218567e-06, "loss": 0.0009, "step": 371290 }, { "epoch": 89.18, "learning_rate": 5.557729142408807e-06, "loss": 0.001, "step": 371300 }, { "epoch": 89.18, "learning_rate": 5.5560844896549005e-06, "loss": 0.0009, "step": 371310 }, { "epoch": 89.19, "learning_rate": 5.554440065965294e-06, "loss": 0.0009, "step": 371320 }, { "epoch": 89.19, "learning_rate": 5.552795871348482e-06, "loss": 0.0009, "step": 371330 }, { "epoch": 89.19, "learning_rate": 5.551151905812924e-06, "loss": 0.001, "step": 371340 }, { "epoch": 89.19, "learning_rate": 5.549508169367113e-06, "loss": 0.001, "step": 371350 }, { "epoch": 89.19, "learning_rate": 5.547864662019503e-06, "loss": 0.0009, "step": 371360 }, { "epoch": 89.2, "learning_rate": 5.546221383778566e-06, "loss": 0.0009, "step": 371370 }, { "epoch": 89.2, "learning_rate": 5.5445783346527835e-06, "loss": 0.0009, "step": 371380 }, { "epoch": 89.2, "learning_rate": 5.542935514650605e-06, "loss": 0.001, "step": 371390 }, { "epoch": 89.2, "learning_rate": 5.541292923780517e-06, "loss": 0.001, "step": 371400 }, { "epoch": 89.21, "learning_rate": 5.539650562050969e-06, "loss": 0.001, "step": 371410 }, { "epoch": 89.21, "learning_rate": 5.538008429470442e-06, "loss": 0.0011, "step": 371420 }, { "epoch": 89.21, "learning_rate": 5.536366526047393e-06, "loss": 0.0009, "step": 371430 }, { "epoch": 89.21, "learning_rate": 5.534724851790274e-06, "loss": 0.0009, "step": 371440 }, { "epoch": 89.22, "learning_rate": 5.533083406707562e-06, "loss": 0.001, "step": 371450 }, { "epoch": 89.22, "learning_rate": 5.531442190807701e-06, "loss": 0.0008, "step": 371460 }, { "epoch": 89.22, "learning_rate": 5.529801204099166e-06, "loss": 0.0009, "step": 371470 }, { "epoch": 89.22, "learning_rate": 5.528160446590397e-06, "loss": 0.001, "step": 371480 }, { "epoch": 89.22, "learning_rate": 5.526519918289874e-06, "loss": 0.0009, "step": 371490 }, { "epoch": 89.23, "learning_rate": 5.524879619206042e-06, "loss": 0.0009, "step": 371500 }, { "epoch": 89.23, "learning_rate": 5.523239549347336e-06, "loss": 0.001, "step": 371510 }, { "epoch": 89.23, "learning_rate": 5.521599708722236e-06, "loss": 0.0009, "step": 371520 }, { "epoch": 89.23, "learning_rate": 5.5199600973391775e-06, "loss": 0.0009, "step": 371530 }, { "epoch": 89.24, "learning_rate": 5.518320715206621e-06, "loss": 0.0009, "step": 371540 }, { "epoch": 89.24, "learning_rate": 5.516681562333004e-06, "loss": 0.0009, "step": 371550 }, { "epoch": 89.24, "learning_rate": 5.515042638726792e-06, "loss": 0.0009, "step": 371560 }, { "epoch": 89.24, "learning_rate": 5.513403944396412e-06, "loss": 0.0009, "step": 371570 }, { "epoch": 89.25, "learning_rate": 5.511765479350317e-06, "loss": 0.0009, "step": 371580 }, { "epoch": 89.25, "learning_rate": 5.510127243596968e-06, "loss": 0.001, "step": 371590 }, { "epoch": 89.25, "learning_rate": 5.508489237144787e-06, "loss": 0.001, "step": 371600 }, { "epoch": 89.25, "learning_rate": 5.506851460002232e-06, "loss": 0.0011, "step": 371610 }, { "epoch": 89.25, "learning_rate": 5.505213912177726e-06, "loss": 0.001, "step": 371620 }, { "epoch": 89.26, "learning_rate": 5.503576593679726e-06, "loss": 0.0009, "step": 371630 }, { "epoch": 89.26, "learning_rate": 5.501939504516673e-06, "loss": 0.001, "step": 371640 }, { "epoch": 89.26, "learning_rate": 5.500302644696981e-06, "loss": 0.001, "step": 371650 }, { "epoch": 89.26, "learning_rate": 5.498666014229109e-06, "loss": 0.0009, "step": 371660 }, { "epoch": 89.27, "learning_rate": 5.497029613121474e-06, "loss": 0.001, "step": 371670 }, { "epoch": 89.27, "learning_rate": 5.495393441382535e-06, "loss": 0.001, "step": 371680 }, { "epoch": 89.27, "learning_rate": 5.493757499020696e-06, "loss": 0.0009, "step": 371690 }, { "epoch": 89.27, "learning_rate": 5.492121786044413e-06, "loss": 0.0009, "step": 371700 }, { "epoch": 89.27, "learning_rate": 5.490486302462111e-06, "loss": 0.001, "step": 371710 }, { "epoch": 89.28, "learning_rate": 5.488851048282201e-06, "loss": 0.0009, "step": 371720 }, { "epoch": 89.28, "learning_rate": 5.487216023513137e-06, "loss": 0.0009, "step": 371730 }, { "epoch": 89.28, "learning_rate": 5.485581228163317e-06, "loss": 0.001, "step": 371740 }, { "epoch": 89.28, "learning_rate": 5.483946662241201e-06, "loss": 0.0009, "step": 371750 }, { "epoch": 89.29, "learning_rate": 5.482312325755185e-06, "loss": 0.001, "step": 371760 }, { "epoch": 89.29, "learning_rate": 5.4806782187137086e-06, "loss": 0.001, "step": 371770 }, { "epoch": 89.29, "learning_rate": 5.479044341125194e-06, "loss": 0.001, "step": 371780 }, { "epoch": 89.29, "learning_rate": 5.477410692998042e-06, "loss": 0.0011, "step": 371790 }, { "epoch": 89.3, "learning_rate": 5.475777274340704e-06, "loss": 0.001, "step": 371800 }, { "epoch": 89.3, "learning_rate": 5.474144085161564e-06, "loss": 0.001, "step": 371810 }, { "epoch": 89.3, "learning_rate": 5.472511125469077e-06, "loss": 0.0009, "step": 371820 }, { "epoch": 89.3, "learning_rate": 5.470878395271622e-06, "loss": 0.001, "step": 371830 }, { "epoch": 89.3, "learning_rate": 5.469245894577646e-06, "loss": 0.001, "step": 371840 }, { "epoch": 89.31, "learning_rate": 5.467613623395535e-06, "loss": 0.001, "step": 371850 }, { "epoch": 89.31, "learning_rate": 5.465981581733731e-06, "loss": 0.0009, "step": 371860 }, { "epoch": 89.31, "learning_rate": 5.464349769600618e-06, "loss": 0.001, "step": 371870 }, { "epoch": 89.31, "learning_rate": 5.4627181870046284e-06, "loss": 0.001, "step": 371880 }, { "epoch": 89.32, "learning_rate": 5.461086833954149e-06, "loss": 0.001, "step": 371890 }, { "epoch": 89.32, "learning_rate": 5.459455710457601e-06, "loss": 0.0009, "step": 371900 }, { "epoch": 89.32, "learning_rate": 5.457824816523404e-06, "loss": 0.0009, "step": 371910 }, { "epoch": 89.32, "learning_rate": 5.456194152159949e-06, "loss": 0.001, "step": 371920 }, { "epoch": 89.33, "learning_rate": 5.454563717375633e-06, "loss": 0.001, "step": 371930 }, { "epoch": 89.33, "learning_rate": 5.452933512178876e-06, "loss": 0.0009, "step": 371940 }, { "epoch": 89.33, "learning_rate": 5.451303536578062e-06, "loss": 0.001, "step": 371950 }, { "epoch": 89.33, "learning_rate": 5.449673790581611e-06, "loss": 0.001, "step": 371960 }, { "epoch": 89.33, "learning_rate": 5.4480442741979055e-06, "loss": 0.001, "step": 371970 }, { "epoch": 89.34, "learning_rate": 5.446414987435361e-06, "loss": 0.001, "step": 371980 }, { "epoch": 89.34, "learning_rate": 5.444785930302365e-06, "loss": 0.001, "step": 371990 }, { "epoch": 89.34, "learning_rate": 5.443157102807306e-06, "loss": 0.0009, "step": 372000 }, { "epoch": 89.34, "learning_rate": 5.441528504958599e-06, "loss": 0.0009, "step": 372010 }, { "epoch": 89.35, "learning_rate": 5.439900136764614e-06, "loss": 0.001, "step": 372020 }, { "epoch": 89.35, "learning_rate": 5.438271998233768e-06, "loss": 0.0009, "step": 372030 }, { "epoch": 89.35, "learning_rate": 5.436644089374432e-06, "loss": 0.0009, "step": 372040 }, { "epoch": 89.35, "learning_rate": 5.4350164101950095e-06, "loss": 0.0009, "step": 372050 }, { "epoch": 89.35, "learning_rate": 5.433388960703878e-06, "loss": 0.001, "step": 372060 }, { "epoch": 89.36, "learning_rate": 5.4317617409094414e-06, "loss": 0.0008, "step": 372070 }, { "epoch": 89.36, "learning_rate": 5.430134750820082e-06, "loss": 0.001, "step": 372080 }, { "epoch": 89.36, "learning_rate": 5.428507990444165e-06, "loss": 0.001, "step": 372090 }, { "epoch": 89.36, "learning_rate": 5.426881459790107e-06, "loss": 0.001, "step": 372100 }, { "epoch": 89.37, "learning_rate": 5.425255158866254e-06, "loss": 0.0009, "step": 372110 }, { "epoch": 89.37, "learning_rate": 5.423629087681026e-06, "loss": 0.001, "step": 372120 }, { "epoch": 89.37, "learning_rate": 5.422003246242779e-06, "loss": 0.0009, "step": 372130 }, { "epoch": 89.37, "learning_rate": 5.420377634559903e-06, "loss": 0.0009, "step": 372140 }, { "epoch": 89.38, "learning_rate": 5.418752252640768e-06, "loss": 0.001, "step": 372150 }, { "epoch": 89.38, "learning_rate": 5.417127100493763e-06, "loss": 0.0011, "step": 372160 }, { "epoch": 89.38, "learning_rate": 5.415502178127252e-06, "loss": 0.0009, "step": 372170 }, { "epoch": 89.38, "learning_rate": 5.413877485549623e-06, "loss": 0.0009, "step": 372180 }, { "epoch": 89.38, "learning_rate": 5.412253022769231e-06, "loss": 0.0009, "step": 372190 }, { "epoch": 89.39, "learning_rate": 5.41062878979447e-06, "loss": 0.0008, "step": 372200 }, { "epoch": 89.39, "learning_rate": 5.409004786633692e-06, "loss": 0.001, "step": 372210 }, { "epoch": 89.39, "learning_rate": 5.407381013295282e-06, "loss": 0.001, "step": 372220 }, { "epoch": 89.39, "learning_rate": 5.405757469787598e-06, "loss": 0.001, "step": 372230 }, { "epoch": 89.4, "learning_rate": 5.404134156119023e-06, "loss": 0.0009, "step": 372240 }, { "epoch": 89.4, "learning_rate": 5.4025110722979e-06, "loss": 0.0009, "step": 372250 }, { "epoch": 89.4, "learning_rate": 5.400888218332617e-06, "loss": 0.0009, "step": 372260 }, { "epoch": 89.4, "learning_rate": 5.3992655942315225e-06, "loss": 0.0009, "step": 372270 }, { "epoch": 89.41, "learning_rate": 5.397643200002994e-06, "loss": 0.0009, "step": 372280 }, { "epoch": 89.41, "learning_rate": 5.396021035655386e-06, "loss": 0.001, "step": 372290 }, { "epoch": 89.41, "learning_rate": 5.394399101197051e-06, "loss": 0.001, "step": 372300 }, { "epoch": 89.41, "learning_rate": 5.3927773966363615e-06, "loss": 0.001, "step": 372310 }, { "epoch": 89.41, "learning_rate": 5.391155921981661e-06, "loss": 0.001, "step": 372320 }, { "epoch": 89.42, "learning_rate": 5.389534677241326e-06, "loss": 0.0009, "step": 372330 }, { "epoch": 89.42, "learning_rate": 5.387913662423694e-06, "loss": 0.0008, "step": 372340 }, { "epoch": 89.42, "learning_rate": 5.386292877537136e-06, "loss": 0.001, "step": 372350 }, { "epoch": 89.42, "learning_rate": 5.384672322590001e-06, "loss": 0.001, "step": 372360 }, { "epoch": 89.43, "learning_rate": 5.383051997590621e-06, "loss": 0.0009, "step": 372370 }, { "epoch": 89.43, "learning_rate": 5.3814319025473795e-06, "loss": 0.001, "step": 372380 }, { "epoch": 89.43, "learning_rate": 5.3798120374686016e-06, "loss": 0.0011, "step": 372390 }, { "epoch": 89.43, "learning_rate": 5.378192402362653e-06, "loss": 0.0009, "step": 372400 }, { "epoch": 89.43, "learning_rate": 5.376572997237861e-06, "loss": 0.001, "step": 372410 }, { "epoch": 89.44, "learning_rate": 5.374953822102597e-06, "loss": 0.0009, "step": 372420 }, { "epoch": 89.44, "learning_rate": 5.373334876965197e-06, "loss": 0.0009, "step": 372430 }, { "epoch": 89.44, "learning_rate": 5.37171616183399e-06, "loss": 0.001, "step": 372440 }, { "epoch": 89.44, "learning_rate": 5.37009767671734e-06, "loss": 0.001, "step": 372450 }, { "epoch": 89.45, "learning_rate": 5.368479421623568e-06, "loss": 0.0009, "step": 372460 }, { "epoch": 89.45, "learning_rate": 5.366861396561029e-06, "loss": 0.001, "step": 372470 }, { "epoch": 89.45, "learning_rate": 5.365243601538067e-06, "loss": 0.0008, "step": 372480 }, { "epoch": 89.45, "learning_rate": 5.363626036563007e-06, "loss": 0.001, "step": 372490 }, { "epoch": 89.46, "learning_rate": 5.3620087016442e-06, "loss": 0.001, "step": 372500 }, { "epoch": 89.46, "learning_rate": 5.36039159678996e-06, "loss": 0.0009, "step": 372510 }, { "epoch": 89.46, "learning_rate": 5.358774722008647e-06, "loss": 0.001, "step": 372520 }, { "epoch": 89.46, "learning_rate": 5.357158077308572e-06, "loss": 0.0008, "step": 372530 }, { "epoch": 89.46, "learning_rate": 5.3555416626980885e-06, "loss": 0.001, "step": 372540 }, { "epoch": 89.47, "learning_rate": 5.353925478185506e-06, "loss": 0.0009, "step": 372550 }, { "epoch": 89.47, "learning_rate": 5.35230952377917e-06, "loss": 0.001, "step": 372560 }, { "epoch": 89.47, "learning_rate": 5.350693799487411e-06, "loss": 0.0008, "step": 372570 }, { "epoch": 89.47, "learning_rate": 5.349078305318533e-06, "loss": 0.0011, "step": 372580 }, { "epoch": 89.48, "learning_rate": 5.347463041280898e-06, "loss": 0.0009, "step": 372590 }, { "epoch": 89.48, "learning_rate": 5.345848007382792e-06, "loss": 0.001, "step": 372600 }, { "epoch": 89.48, "learning_rate": 5.344233203632576e-06, "loss": 0.0009, "step": 372610 }, { "epoch": 89.48, "learning_rate": 5.342618630038537e-06, "loss": 0.0009, "step": 372620 }, { "epoch": 89.49, "learning_rate": 5.34100428660903e-06, "loss": 0.001, "step": 372630 }, { "epoch": 89.49, "learning_rate": 5.33939017335236e-06, "loss": 0.001, "step": 372640 }, { "epoch": 89.49, "learning_rate": 5.337776290276836e-06, "loss": 0.001, "step": 372650 }, { "epoch": 89.49, "learning_rate": 5.336162637390801e-06, "loss": 0.0011, "step": 372660 }, { "epoch": 89.49, "learning_rate": 5.334549214702539e-06, "loss": 0.0009, "step": 372670 }, { "epoch": 89.5, "learning_rate": 5.332936022220397e-06, "loss": 0.0009, "step": 372680 }, { "epoch": 89.5, "learning_rate": 5.33132305995267e-06, "loss": 0.001, "step": 372690 }, { "epoch": 89.5, "learning_rate": 5.329710327907683e-06, "loss": 0.001, "step": 372700 }, { "epoch": 89.5, "learning_rate": 5.328097826093742e-06, "loss": 0.001, "step": 372710 }, { "epoch": 89.51, "learning_rate": 5.32648555451915e-06, "loss": 0.001, "step": 372720 }, { "epoch": 89.51, "learning_rate": 5.324873513192235e-06, "loss": 0.0009, "step": 372730 }, { "epoch": 89.51, "learning_rate": 5.323261702121285e-06, "loss": 0.0008, "step": 372740 }, { "epoch": 89.51, "learning_rate": 5.321650121314625e-06, "loss": 0.001, "step": 372750 }, { "epoch": 89.51, "learning_rate": 5.320038770780544e-06, "loss": 0.001, "step": 372760 }, { "epoch": 89.52, "learning_rate": 5.3184276505273685e-06, "loss": 0.0009, "step": 372770 }, { "epoch": 89.52, "learning_rate": 5.316816760563381e-06, "loss": 0.001, "step": 372780 }, { "epoch": 89.52, "learning_rate": 5.315206100896897e-06, "loss": 0.001, "step": 372790 }, { "epoch": 89.52, "learning_rate": 5.3135956715362205e-06, "loss": 0.001, "step": 372800 }, { "epoch": 89.53, "learning_rate": 5.311985472489633e-06, "loss": 0.0009, "step": 372810 }, { "epoch": 89.53, "learning_rate": 5.3103755037654575e-06, "loss": 0.001, "step": 372820 }, { "epoch": 89.53, "learning_rate": 5.30876576537197e-06, "loss": 0.001, "step": 372830 }, { "epoch": 89.53, "learning_rate": 5.3071562573174915e-06, "loss": 0.001, "step": 372840 }, { "epoch": 89.54, "learning_rate": 5.305546979610288e-06, "loss": 0.001, "step": 372850 }, { "epoch": 89.54, "learning_rate": 5.303937932258679e-06, "loss": 0.001, "step": 372860 }, { "epoch": 89.54, "learning_rate": 5.302329115270949e-06, "loss": 0.0009, "step": 372870 }, { "epoch": 89.54, "learning_rate": 5.300720528655379e-06, "loss": 0.0009, "step": 372880 }, { "epoch": 89.54, "learning_rate": 5.299112172420279e-06, "loss": 0.0011, "step": 372890 }, { "epoch": 89.55, "learning_rate": 5.29750404657392e-06, "loss": 0.001, "step": 372900 }, { "epoch": 89.55, "learning_rate": 5.2958961511246075e-06, "loss": 0.0009, "step": 372910 }, { "epoch": 89.55, "learning_rate": 5.2942884860806064e-06, "loss": 0.0009, "step": 372920 }, { "epoch": 89.55, "learning_rate": 5.292681051450227e-06, "loss": 0.0009, "step": 372930 }, { "epoch": 89.56, "learning_rate": 5.2910738472417455e-06, "loss": 0.0009, "step": 372940 }, { "epoch": 89.56, "learning_rate": 5.289466873463433e-06, "loss": 0.001, "step": 372950 }, { "epoch": 89.56, "learning_rate": 5.2878601301235955e-06, "loss": 0.001, "step": 372960 }, { "epoch": 89.56, "learning_rate": 5.286253617230486e-06, "loss": 0.001, "step": 372970 }, { "epoch": 89.57, "learning_rate": 5.284647334792409e-06, "loss": 0.001, "step": 372980 }, { "epoch": 89.57, "learning_rate": 5.2830412828176245e-06, "loss": 0.001, "step": 372990 }, { "epoch": 89.57, "learning_rate": 5.281435461314427e-06, "loss": 0.0009, "step": 373000 }, { "epoch": 89.57, "learning_rate": 5.279829870291086e-06, "loss": 0.001, "step": 373010 }, { "epoch": 89.57, "learning_rate": 5.278224509755869e-06, "loss": 0.0009, "step": 373020 }, { "epoch": 89.58, "learning_rate": 5.276619379717063e-06, "loss": 0.001, "step": 373030 }, { "epoch": 89.58, "learning_rate": 5.275014480182927e-06, "loss": 0.001, "step": 373040 }, { "epoch": 89.58, "learning_rate": 5.2734098111617506e-06, "loss": 0.001, "step": 373050 }, { "epoch": 89.58, "learning_rate": 5.271805372661781e-06, "loss": 0.001, "step": 373060 }, { "epoch": 89.59, "learning_rate": 5.270201164691307e-06, "loss": 0.001, "step": 373070 }, { "epoch": 89.59, "learning_rate": 5.268597187258589e-06, "loss": 0.001, "step": 373080 }, { "epoch": 89.59, "learning_rate": 5.266993440371887e-06, "loss": 0.0009, "step": 373090 }, { "epoch": 89.59, "learning_rate": 5.265389924039494e-06, "loss": 0.0009, "step": 373100 }, { "epoch": 89.59, "learning_rate": 5.2637866382696355e-06, "loss": 0.001, "step": 373110 }, { "epoch": 89.6, "learning_rate": 5.262183583070607e-06, "loss": 0.0009, "step": 373120 }, { "epoch": 89.6, "learning_rate": 5.26058075845065e-06, "loss": 0.0009, "step": 373130 }, { "epoch": 89.6, "learning_rate": 5.258978164418044e-06, "loss": 0.0009, "step": 373140 }, { "epoch": 89.6, "learning_rate": 5.2573758009810405e-06, "loss": 0.0009, "step": 373150 }, { "epoch": 89.61, "learning_rate": 5.255773668147884e-06, "loss": 0.0011, "step": 373160 }, { "epoch": 89.61, "learning_rate": 5.254171765926852e-06, "loss": 0.0009, "step": 373170 }, { "epoch": 89.61, "learning_rate": 5.252570094326187e-06, "loss": 0.001, "step": 373180 }, { "epoch": 89.61, "learning_rate": 5.2509686533541545e-06, "loss": 0.0009, "step": 373190 }, { "epoch": 89.62, "learning_rate": 5.249367443018999e-06, "loss": 0.001, "step": 373200 }, { "epoch": 89.62, "learning_rate": 5.247766463328985e-06, "loss": 0.001, "step": 373210 }, { "epoch": 89.62, "learning_rate": 5.246165714292356e-06, "loss": 0.001, "step": 373220 }, { "epoch": 89.62, "learning_rate": 5.244565195917356e-06, "loss": 0.001, "step": 373230 }, { "epoch": 89.62, "learning_rate": 5.242964908212244e-06, "loss": 0.0009, "step": 373240 }, { "epoch": 89.63, "learning_rate": 5.241364851185266e-06, "loss": 0.0009, "step": 373250 }, { "epoch": 89.63, "learning_rate": 5.239765024844668e-06, "loss": 0.001, "step": 373260 }, { "epoch": 89.63, "learning_rate": 5.2381654291986885e-06, "loss": 0.0011, "step": 373270 }, { "epoch": 89.63, "learning_rate": 5.236566064255588e-06, "loss": 0.0009, "step": 373280 }, { "epoch": 89.64, "learning_rate": 5.234966930023605e-06, "loss": 0.001, "step": 373290 }, { "epoch": 89.64, "learning_rate": 5.2333680265109595e-06, "loss": 0.0009, "step": 373300 }, { "epoch": 89.64, "learning_rate": 5.231769353725924e-06, "loss": 0.001, "step": 373310 }, { "epoch": 89.64, "learning_rate": 5.230170911676713e-06, "loss": 0.001, "step": 373320 }, { "epoch": 89.65, "learning_rate": 5.228572700371581e-06, "loss": 0.0009, "step": 373330 }, { "epoch": 89.65, "learning_rate": 5.226974719818756e-06, "loss": 0.0009, "step": 373340 }, { "epoch": 89.65, "learning_rate": 5.225376970026485e-06, "loss": 0.0009, "step": 373350 }, { "epoch": 89.65, "learning_rate": 5.223779451002986e-06, "loss": 0.0009, "step": 373360 }, { "epoch": 89.65, "learning_rate": 5.222182162756506e-06, "loss": 0.001, "step": 373370 }, { "epoch": 89.66, "learning_rate": 5.220585105295272e-06, "loss": 0.001, "step": 373380 }, { "epoch": 89.66, "learning_rate": 5.218988278627524e-06, "loss": 0.0009, "step": 373390 }, { "epoch": 89.66, "learning_rate": 5.2173916827614686e-06, "loss": 0.0011, "step": 373400 }, { "epoch": 89.66, "learning_rate": 5.215795317705357e-06, "loss": 0.0008, "step": 373410 }, { "epoch": 89.67, "learning_rate": 5.214199183467422e-06, "loss": 0.001, "step": 373420 }, { "epoch": 89.67, "learning_rate": 5.212603280055872e-06, "loss": 0.001, "step": 373430 }, { "epoch": 89.67, "learning_rate": 5.211007607478935e-06, "loss": 0.0009, "step": 373440 }, { "epoch": 89.67, "learning_rate": 5.209412165744848e-06, "loss": 0.0009, "step": 373450 }, { "epoch": 89.67, "learning_rate": 5.207816954861816e-06, "loss": 0.0009, "step": 373460 }, { "epoch": 89.68, "learning_rate": 5.206221974838077e-06, "loss": 0.0009, "step": 373470 }, { "epoch": 89.68, "learning_rate": 5.204627225681835e-06, "loss": 0.0009, "step": 373480 }, { "epoch": 89.68, "learning_rate": 5.203032707401329e-06, "loss": 0.001, "step": 373490 }, { "epoch": 89.68, "learning_rate": 5.201438420004767e-06, "loss": 0.0008, "step": 373500 }, { "epoch": 89.69, "learning_rate": 5.199844363500356e-06, "loss": 0.001, "step": 373510 }, { "epoch": 89.69, "learning_rate": 5.198250537896332e-06, "loss": 0.001, "step": 373520 }, { "epoch": 89.69, "learning_rate": 5.196656943200889e-06, "loss": 0.001, "step": 373530 }, { "epoch": 89.69, "learning_rate": 5.19506357942226e-06, "loss": 0.0009, "step": 373540 }, { "epoch": 89.7, "learning_rate": 5.193470446568638e-06, "loss": 0.001, "step": 373550 }, { "epoch": 89.7, "learning_rate": 5.191877544648255e-06, "loss": 0.001, "step": 373560 }, { "epoch": 89.7, "learning_rate": 5.19028487366931e-06, "loss": 0.0009, "step": 373570 }, { "epoch": 89.7, "learning_rate": 5.188692433640002e-06, "loss": 0.0009, "step": 373580 }, { "epoch": 89.7, "learning_rate": 5.187100224568553e-06, "loss": 0.0009, "step": 373590 }, { "epoch": 89.71, "learning_rate": 5.185508246463161e-06, "loss": 0.0009, "step": 373600 }, { "epoch": 89.71, "learning_rate": 5.183916499332036e-06, "loss": 0.001, "step": 373610 }, { "epoch": 89.71, "learning_rate": 5.182324983183378e-06, "loss": 0.0009, "step": 373620 }, { "epoch": 89.71, "learning_rate": 5.180733698025398e-06, "loss": 0.0009, "step": 373630 }, { "epoch": 89.72, "learning_rate": 5.179142643866286e-06, "loss": 0.001, "step": 373640 }, { "epoch": 89.72, "learning_rate": 5.177551820714244e-06, "loss": 0.001, "step": 373650 }, { "epoch": 89.72, "learning_rate": 5.175961228577475e-06, "loss": 0.0009, "step": 373660 }, { "epoch": 89.72, "learning_rate": 5.1743708674641845e-06, "loss": 0.0009, "step": 373670 }, { "epoch": 89.73, "learning_rate": 5.172780737382549e-06, "loss": 0.0009, "step": 373680 }, { "epoch": 89.73, "learning_rate": 5.171190838340789e-06, "loss": 0.001, "step": 373690 }, { "epoch": 89.73, "learning_rate": 5.169601170347077e-06, "loss": 0.0009, "step": 373700 }, { "epoch": 89.73, "learning_rate": 5.168011733409622e-06, "loss": 0.0009, "step": 373710 }, { "epoch": 89.73, "learning_rate": 5.166422527536602e-06, "loss": 0.001, "step": 373720 }, { "epoch": 89.74, "learning_rate": 5.164833552736226e-06, "loss": 0.001, "step": 373730 }, { "epoch": 89.74, "learning_rate": 5.16324480901666e-06, "loss": 0.001, "step": 373740 }, { "epoch": 89.74, "learning_rate": 5.161656296386114e-06, "loss": 0.0009, "step": 373750 }, { "epoch": 89.74, "learning_rate": 5.160068014852759e-06, "loss": 0.001, "step": 373760 }, { "epoch": 89.75, "learning_rate": 5.158479964424795e-06, "loss": 0.001, "step": 373770 }, { "epoch": 89.75, "learning_rate": 5.1568921451103924e-06, "loss": 0.0009, "step": 373780 }, { "epoch": 89.75, "learning_rate": 5.155304556917756e-06, "loss": 0.0009, "step": 373790 }, { "epoch": 89.75, "learning_rate": 5.1537171998550515e-06, "loss": 0.0009, "step": 373800 }, { "epoch": 89.75, "learning_rate": 5.15213007393045e-06, "loss": 0.001, "step": 373810 }, { "epoch": 89.76, "learning_rate": 5.150543179152162e-06, "loss": 0.0008, "step": 373820 }, { "epoch": 89.76, "learning_rate": 5.148956515528336e-06, "loss": 0.001, "step": 373830 }, { "epoch": 89.76, "learning_rate": 5.1473700830671715e-06, "loss": 0.001, "step": 373840 }, { "epoch": 89.76, "learning_rate": 5.145783881776828e-06, "loss": 0.0009, "step": 373850 }, { "epoch": 89.77, "learning_rate": 5.144197911665499e-06, "loss": 0.0009, "step": 373860 }, { "epoch": 89.77, "learning_rate": 5.1426121727413455e-06, "loss": 0.001, "step": 373870 }, { "epoch": 89.77, "learning_rate": 5.141026665012539e-06, "loss": 0.0009, "step": 373880 }, { "epoch": 89.77, "learning_rate": 5.139441388487265e-06, "loss": 0.0009, "step": 373890 }, { "epoch": 89.78, "learning_rate": 5.137856343173675e-06, "loss": 0.001, "step": 373900 }, { "epoch": 89.78, "learning_rate": 5.1362715290799555e-06, "loss": 0.001, "step": 373910 }, { "epoch": 89.78, "learning_rate": 5.134686946214257e-06, "loss": 0.0029, "step": 373920 }, { "epoch": 89.78, "learning_rate": 5.133102594584771e-06, "loss": 0.0009, "step": 373930 }, { "epoch": 89.78, "learning_rate": 5.131518474199648e-06, "loss": 0.0011, "step": 373940 }, { "epoch": 89.79, "learning_rate": 5.129934585067042e-06, "loss": 0.001, "step": 373950 }, { "epoch": 89.79, "learning_rate": 5.1283509271951414e-06, "loss": 0.0008, "step": 373960 }, { "epoch": 89.79, "learning_rate": 5.126767500592084e-06, "loss": 0.001, "step": 373970 }, { "epoch": 89.79, "learning_rate": 5.12518430526604e-06, "loss": 0.0009, "step": 373980 }, { "epoch": 89.8, "learning_rate": 5.123601341225187e-06, "loss": 0.001, "step": 373990 }, { "epoch": 89.8, "learning_rate": 5.122018608477652e-06, "loss": 0.001, "step": 374000 }, { "epoch": 89.8, "learning_rate": 5.120436107031618e-06, "loss": 0.0008, "step": 374010 }, { "epoch": 89.8, "learning_rate": 5.118853836895227e-06, "loss": 0.001, "step": 374020 }, { "epoch": 89.81, "learning_rate": 5.117271798076639e-06, "loss": 0.001, "step": 374030 }, { "epoch": 89.81, "learning_rate": 5.115689990584005e-06, "loss": 0.0011, "step": 374040 }, { "epoch": 89.81, "learning_rate": 5.114108414425489e-06, "loss": 0.0009, "step": 374050 }, { "epoch": 89.81, "learning_rate": 5.112527069609225e-06, "loss": 0.0009, "step": 374060 }, { "epoch": 89.81, "learning_rate": 5.110945956143376e-06, "loss": 0.001, "step": 374070 }, { "epoch": 89.82, "learning_rate": 5.109365074036088e-06, "loss": 0.0009, "step": 374080 }, { "epoch": 89.82, "learning_rate": 5.107784423295503e-06, "loss": 0.0008, "step": 374090 }, { "epoch": 89.82, "learning_rate": 5.106204003929777e-06, "loss": 0.001, "step": 374100 }, { "epoch": 89.82, "learning_rate": 5.104623815947046e-06, "loss": 0.0009, "step": 374110 }, { "epoch": 89.83, "learning_rate": 5.103043859355461e-06, "loss": 0.0025, "step": 374120 }, { "epoch": 89.83, "learning_rate": 5.101464134163159e-06, "loss": 0.001, "step": 374130 }, { "epoch": 89.83, "learning_rate": 5.099884640378294e-06, "loss": 0.0008, "step": 374140 }, { "epoch": 89.83, "learning_rate": 5.0983053780090054e-06, "loss": 0.001, "step": 374150 }, { "epoch": 89.83, "learning_rate": 5.096726347063408e-06, "loss": 0.0009, "step": 374160 }, { "epoch": 89.84, "learning_rate": 5.095147547549672e-06, "loss": 0.001, "step": 374170 }, { "epoch": 89.84, "learning_rate": 5.09356897947591e-06, "loss": 0.0011, "step": 374180 }, { "epoch": 89.84, "learning_rate": 5.091990642850281e-06, "loss": 0.0009, "step": 374190 }, { "epoch": 89.84, "learning_rate": 5.090412537680894e-06, "loss": 0.0009, "step": 374200 }, { "epoch": 89.85, "learning_rate": 5.088834663975905e-06, "loss": 0.0008, "step": 374210 }, { "epoch": 89.85, "learning_rate": 5.087257021743441e-06, "loss": 0.0011, "step": 374220 }, { "epoch": 89.85, "learning_rate": 5.085679610991617e-06, "loss": 0.001, "step": 374230 }, { "epoch": 89.85, "learning_rate": 5.084102431728588e-06, "loss": 0.001, "step": 374240 }, { "epoch": 89.86, "learning_rate": 5.0825254839624635e-06, "loss": 0.0011, "step": 374250 }, { "epoch": 89.86, "learning_rate": 5.0809487677013826e-06, "loss": 0.0009, "step": 374260 }, { "epoch": 89.86, "learning_rate": 5.079372282953459e-06, "loss": 0.0008, "step": 374270 }, { "epoch": 89.86, "learning_rate": 5.077796029726839e-06, "loss": 0.001, "step": 374280 }, { "epoch": 89.86, "learning_rate": 5.076220008029619e-06, "loss": 0.0009, "step": 374290 }, { "epoch": 89.87, "learning_rate": 5.0746442178699395e-06, "loss": 0.001, "step": 374300 }, { "epoch": 89.87, "learning_rate": 5.073068659255931e-06, "loss": 0.0009, "step": 374310 }, { "epoch": 89.87, "learning_rate": 5.071493332195687e-06, "loss": 0.0009, "step": 374320 }, { "epoch": 89.87, "learning_rate": 5.069918236697357e-06, "loss": 0.0008, "step": 374330 }, { "epoch": 89.88, "learning_rate": 5.06834337276903e-06, "loss": 0.001, "step": 374340 }, { "epoch": 89.88, "learning_rate": 5.066768740418848e-06, "loss": 0.001, "step": 374350 }, { "epoch": 89.88, "learning_rate": 5.065194339654916e-06, "loss": 0.0009, "step": 374360 }, { "epoch": 89.88, "learning_rate": 5.063620170485339e-06, "loss": 0.0009, "step": 374370 }, { "epoch": 89.89, "learning_rate": 5.06204623291825e-06, "loss": 0.0009, "step": 374380 }, { "epoch": 89.89, "learning_rate": 5.0604725269617345e-06, "loss": 0.001, "step": 374390 }, { "epoch": 89.89, "learning_rate": 5.058899052623933e-06, "loss": 0.0009, "step": 374400 }, { "epoch": 89.89, "learning_rate": 5.057325809912933e-06, "loss": 0.001, "step": 374410 }, { "epoch": 89.89, "learning_rate": 5.05575279883686e-06, "loss": 0.0009, "step": 374420 }, { "epoch": 89.9, "learning_rate": 5.054180019403815e-06, "loss": 0.0009, "step": 374430 }, { "epoch": 89.9, "learning_rate": 5.052607471621889e-06, "loss": 0.0011, "step": 374440 }, { "epoch": 89.9, "learning_rate": 5.051035155499212e-06, "loss": 0.0009, "step": 374450 }, { "epoch": 89.9, "learning_rate": 5.049463071043864e-06, "loss": 0.0011, "step": 374460 }, { "epoch": 89.91, "learning_rate": 5.047891218263967e-06, "loss": 0.0009, "step": 374470 }, { "epoch": 89.91, "learning_rate": 5.046319597167609e-06, "loss": 0.001, "step": 374480 }, { "epoch": 89.91, "learning_rate": 5.044748207762901e-06, "loss": 0.001, "step": 374490 }, { "epoch": 89.91, "learning_rate": 5.043177050057929e-06, "loss": 0.0009, "step": 374500 }, { "epoch": 89.91, "learning_rate": 5.041606124060805e-06, "loss": 0.0009, "step": 374510 }, { "epoch": 89.92, "learning_rate": 5.0400354297796215e-06, "loss": 0.0009, "step": 374520 }, { "epoch": 89.92, "learning_rate": 5.038464967222461e-06, "loss": 0.001, "step": 374530 }, { "epoch": 89.92, "learning_rate": 5.036894736397441e-06, "loss": 0.001, "step": 374540 }, { "epoch": 89.92, "learning_rate": 5.03532473731263e-06, "loss": 0.0036, "step": 374550 }, { "epoch": 89.93, "learning_rate": 5.03375496997614e-06, "loss": 0.001, "step": 374560 }, { "epoch": 89.93, "learning_rate": 5.0321854343960414e-06, "loss": 0.001, "step": 374570 }, { "epoch": 89.93, "learning_rate": 5.030616130580446e-06, "loss": 0.001, "step": 374580 }, { "epoch": 89.93, "learning_rate": 5.029047058537423e-06, "loss": 0.001, "step": 374590 }, { "epoch": 89.94, "learning_rate": 5.027478218275072e-06, "loss": 0.001, "step": 374600 }, { "epoch": 89.94, "learning_rate": 5.025909609801471e-06, "loss": 0.0009, "step": 374610 }, { "epoch": 89.94, "learning_rate": 5.024341233124702e-06, "loss": 0.0009, "step": 374620 }, { "epoch": 89.94, "learning_rate": 5.022773088252869e-06, "loss": 0.0025, "step": 374630 }, { "epoch": 89.94, "learning_rate": 5.0212051751940274e-06, "loss": 0.0011, "step": 374640 }, { "epoch": 89.95, "learning_rate": 5.019637493956275e-06, "loss": 0.001, "step": 374650 }, { "epoch": 89.95, "learning_rate": 5.018070044547696e-06, "loss": 0.001, "step": 374660 }, { "epoch": 89.95, "learning_rate": 5.016502826976344e-06, "loss": 0.0009, "step": 374670 }, { "epoch": 90.0, "learning_rate": 5.014935841250324e-06, "loss": 0.0009, "step": 374680 }, { "epoch": 90.0, "learning_rate": 5.01336908737769e-06, "loss": 0.0009, "step": 374690 }, { "epoch": 90.01, "learning_rate": 5.0118025653665416e-06, "loss": 0.001, "step": 374700 }, { "epoch": 90.01, "learning_rate": 5.010236275224922e-06, "loss": 0.0009, "step": 374710 }, { "epoch": 90.01, "learning_rate": 5.008670216960936e-06, "loss": 0.001, "step": 374720 }, { "epoch": 90.01, "learning_rate": 5.00710439058264e-06, "loss": 0.0009, "step": 374730 }, { "epoch": 90.02, "learning_rate": 5.005538796098092e-06, "loss": 0.001, "step": 374740 }, { "epoch": 90.02, "learning_rate": 5.003973433515385e-06, "loss": 0.001, "step": 374750 }, { "epoch": 90.02, "learning_rate": 5.002408302842565e-06, "loss": 0.0009, "step": 374760 }, { "epoch": 90.02, "learning_rate": 5.000843404087713e-06, "loss": 0.0009, "step": 374770 }, { "epoch": 90.03, "learning_rate": 4.999278737258889e-06, "loss": 0.0009, "step": 374780 }, { "epoch": 90.03, "learning_rate": 4.997714302364159e-06, "loss": 0.0009, "step": 374790 }, { "epoch": 90.03, "learning_rate": 4.996150099411595e-06, "loss": 0.001, "step": 374800 }, { "epoch": 90.03, "learning_rate": 4.994586128409235e-06, "loss": 0.0009, "step": 374810 }, { "epoch": 90.03, "learning_rate": 4.993022389365165e-06, "loss": 0.0009, "step": 374820 }, { "epoch": 90.04, "learning_rate": 4.9914588822874196e-06, "loss": 0.001, "step": 374830 }, { "epoch": 90.04, "learning_rate": 4.989895607184087e-06, "loss": 0.001, "step": 374840 }, { "epoch": 90.04, "learning_rate": 4.988332564063197e-06, "loss": 0.001, "step": 374850 }, { "epoch": 90.04, "learning_rate": 4.9867697529328296e-06, "loss": 0.0009, "step": 374860 }, { "epoch": 90.05, "learning_rate": 4.98520717380101e-06, "loss": 0.0009, "step": 374870 }, { "epoch": 90.05, "learning_rate": 4.983644826675826e-06, "loss": 0.0009, "step": 374880 }, { "epoch": 90.05, "learning_rate": 4.9820827115653e-06, "loss": 0.001, "step": 374890 }, { "epoch": 90.05, "learning_rate": 4.980520828477509e-06, "loss": 0.0008, "step": 374900 }, { "epoch": 90.05, "learning_rate": 4.978959177420473e-06, "loss": 0.0009, "step": 374910 }, { "epoch": 90.06, "learning_rate": 4.977397758402263e-06, "loss": 0.0009, "step": 374920 }, { "epoch": 90.06, "learning_rate": 4.975836571430931e-06, "loss": 0.0008, "step": 374930 }, { "epoch": 90.06, "learning_rate": 4.974275616514512e-06, "loss": 0.0009, "step": 374940 }, { "epoch": 90.06, "learning_rate": 4.972714893661046e-06, "loss": 0.001, "step": 374950 }, { "epoch": 90.07, "learning_rate": 4.971154402878592e-06, "loss": 0.001, "step": 374960 }, { "epoch": 90.07, "learning_rate": 4.969594144175171e-06, "loss": 0.0009, "step": 374970 }, { "epoch": 90.07, "learning_rate": 4.968034117558851e-06, "loss": 0.0009, "step": 374980 }, { "epoch": 90.07, "learning_rate": 4.9664743230376505e-06, "loss": 0.0009, "step": 374990 }, { "epoch": 90.08, "learning_rate": 4.9649147606196265e-06, "loss": 0.0009, "step": 375000 }, { "epoch": 90.08, "learning_rate": 4.96335543031281e-06, "loss": 0.0009, "step": 375010 }, { "epoch": 90.08, "learning_rate": 4.961796332125224e-06, "loss": 0.001, "step": 375020 }, { "epoch": 90.08, "learning_rate": 4.9602374660649265e-06, "loss": 0.0009, "step": 375030 }, { "epoch": 90.08, "learning_rate": 4.958678832139935e-06, "loss": 0.001, "step": 375040 }, { "epoch": 90.09, "learning_rate": 4.957120430358298e-06, "loss": 0.001, "step": 375050 }, { "epoch": 90.09, "learning_rate": 4.955562260728025e-06, "loss": 0.0009, "step": 375060 }, { "epoch": 90.09, "learning_rate": 4.954004323257172e-06, "loss": 0.001, "step": 375070 }, { "epoch": 90.09, "learning_rate": 4.95244661795376e-06, "loss": 0.0009, "step": 375080 }, { "epoch": 90.1, "learning_rate": 4.9508891448258045e-06, "loss": 0.001, "step": 375090 }, { "epoch": 90.1, "learning_rate": 4.949331903881349e-06, "loss": 0.0009, "step": 375100 }, { "epoch": 90.1, "learning_rate": 4.947774895128404e-06, "loss": 0.0009, "step": 375110 }, { "epoch": 90.1, "learning_rate": 4.9462181185750185e-06, "loss": 0.0009, "step": 375120 }, { "epoch": 90.11, "learning_rate": 4.944661574229187e-06, "loss": 0.0009, "step": 375130 }, { "epoch": 90.11, "learning_rate": 4.943105262098957e-06, "loss": 0.001, "step": 375140 }, { "epoch": 90.11, "learning_rate": 4.94154918219234e-06, "loss": 0.0009, "step": 375150 }, { "epoch": 90.11, "learning_rate": 4.939993334517346e-06, "loss": 0.001, "step": 375160 }, { "epoch": 90.11, "learning_rate": 4.9384377190820116e-06, "loss": 0.0013, "step": 375170 }, { "epoch": 90.12, "learning_rate": 4.936882335894338e-06, "loss": 0.0009, "step": 375180 }, { "epoch": 90.12, "learning_rate": 4.935327184962346e-06, "loss": 0.0008, "step": 375190 }, { "epoch": 90.12, "learning_rate": 4.933772266294068e-06, "loss": 0.0009, "step": 375200 }, { "epoch": 90.12, "learning_rate": 4.932217579897491e-06, "loss": 0.0009, "step": 375210 }, { "epoch": 90.13, "learning_rate": 4.930663125780654e-06, "loss": 0.001, "step": 375220 }, { "epoch": 90.13, "learning_rate": 4.9291089039515455e-06, "loss": 0.0009, "step": 375230 }, { "epoch": 90.13, "learning_rate": 4.927554914418192e-06, "loss": 0.0009, "step": 375240 }, { "epoch": 90.13, "learning_rate": 4.9260011571885925e-06, "loss": 0.0009, "step": 375250 }, { "epoch": 90.13, "learning_rate": 4.9244476322707674e-06, "loss": 0.001, "step": 375260 }, { "epoch": 90.14, "learning_rate": 4.922894339672707e-06, "loss": 0.0009, "step": 375270 }, { "epoch": 90.14, "learning_rate": 4.921341279402436e-06, "loss": 0.0009, "step": 375280 }, { "epoch": 90.14, "learning_rate": 4.919788451467938e-06, "loss": 0.0009, "step": 375290 }, { "epoch": 90.14, "learning_rate": 4.91823585587724e-06, "loss": 0.0008, "step": 375300 }, { "epoch": 90.15, "learning_rate": 4.91668349263833e-06, "loss": 0.001, "step": 375310 }, { "epoch": 90.15, "learning_rate": 4.915131361759201e-06, "loss": 0.0009, "step": 375320 }, { "epoch": 90.15, "learning_rate": 4.913579463247869e-06, "loss": 0.001, "step": 375330 }, { "epoch": 90.15, "learning_rate": 4.912027797112312e-06, "loss": 0.0009, "step": 375340 }, { "epoch": 90.16, "learning_rate": 4.910476363360555e-06, "loss": 0.0009, "step": 375350 }, { "epoch": 90.16, "learning_rate": 4.908925162000572e-06, "loss": 0.001, "step": 375360 }, { "epoch": 90.16, "learning_rate": 4.90737419304037e-06, "loss": 0.001, "step": 375370 }, { "epoch": 90.16, "learning_rate": 4.905823456487946e-06, "loss": 0.0009, "step": 375380 }, { "epoch": 90.16, "learning_rate": 4.904272952351269e-06, "loss": 0.0009, "step": 375390 }, { "epoch": 90.17, "learning_rate": 4.902722680638355e-06, "loss": 0.0009, "step": 375400 }, { "epoch": 90.17, "learning_rate": 4.901172641357183e-06, "loss": 0.0009, "step": 375410 }, { "epoch": 90.17, "learning_rate": 4.899622834515749e-06, "loss": 0.0009, "step": 375420 }, { "epoch": 90.17, "learning_rate": 4.898073260122022e-06, "loss": 0.001, "step": 375430 }, { "epoch": 90.18, "learning_rate": 4.896523918184015e-06, "loss": 0.0008, "step": 375440 }, { "epoch": 90.18, "learning_rate": 4.894974808709707e-06, "loss": 0.0009, "step": 375450 }, { "epoch": 90.18, "learning_rate": 4.893425931707057e-06, "loss": 0.001, "step": 375460 }, { "epoch": 90.18, "learning_rate": 4.891877287184082e-06, "loss": 0.0009, "step": 375470 }, { "epoch": 90.19, "learning_rate": 4.890328875148737e-06, "loss": 0.0009, "step": 375480 }, { "epoch": 90.19, "learning_rate": 4.888780695609013e-06, "loss": 0.0009, "step": 375490 }, { "epoch": 90.19, "learning_rate": 4.887232748572901e-06, "loss": 0.0009, "step": 375500 }, { "epoch": 90.19, "learning_rate": 4.88568503404836e-06, "loss": 0.0009, "step": 375510 }, { "epoch": 90.19, "learning_rate": 4.884137552043389e-06, "loss": 0.0009, "step": 375520 }, { "epoch": 90.2, "learning_rate": 4.882590302565932e-06, "loss": 0.001, "step": 375530 }, { "epoch": 90.2, "learning_rate": 4.881043285623999e-06, "loss": 0.0009, "step": 375540 }, { "epoch": 90.2, "learning_rate": 4.879496501225528e-06, "loss": 0.001, "step": 375550 }, { "epoch": 90.2, "learning_rate": 4.877949949378524e-06, "loss": 0.0009, "step": 375560 }, { "epoch": 90.21, "learning_rate": 4.876403630090937e-06, "loss": 0.001, "step": 375570 }, { "epoch": 90.21, "learning_rate": 4.8748575433707475e-06, "loss": 0.001, "step": 375580 }, { "epoch": 90.21, "learning_rate": 4.873311689225918e-06, "loss": 0.001, "step": 375590 }, { "epoch": 90.21, "learning_rate": 4.871766067664413e-06, "loss": 0.001, "step": 375600 }, { "epoch": 90.21, "learning_rate": 4.870220678694204e-06, "loss": 0.001, "step": 375610 }, { "epoch": 90.22, "learning_rate": 4.868675522323252e-06, "loss": 0.0009, "step": 375620 }, { "epoch": 90.22, "learning_rate": 4.867130598559533e-06, "loss": 0.001, "step": 375630 }, { "epoch": 90.22, "learning_rate": 4.865585907410991e-06, "loss": 0.0009, "step": 375640 }, { "epoch": 90.22, "learning_rate": 4.864041448885603e-06, "loss": 0.0008, "step": 375650 }, { "epoch": 90.23, "learning_rate": 4.862497222991325e-06, "loss": 0.0009, "step": 375660 }, { "epoch": 90.23, "learning_rate": 4.860953229736104e-06, "loss": 0.0009, "step": 375670 }, { "epoch": 90.23, "learning_rate": 4.859409469127912e-06, "loss": 0.0009, "step": 375680 }, { "epoch": 90.23, "learning_rate": 4.857865941174699e-06, "loss": 0.001, "step": 375690 }, { "epoch": 90.24, "learning_rate": 4.8563226458844255e-06, "loss": 0.0026, "step": 375700 }, { "epoch": 90.24, "learning_rate": 4.85477958326504e-06, "loss": 0.001, "step": 375710 }, { "epoch": 90.24, "learning_rate": 4.853236753324503e-06, "loss": 0.0009, "step": 375720 }, { "epoch": 90.24, "learning_rate": 4.851694156070758e-06, "loss": 0.0009, "step": 375730 }, { "epoch": 90.24, "learning_rate": 4.8501517915117535e-06, "loss": 0.001, "step": 375740 }, { "epoch": 90.25, "learning_rate": 4.848609659655451e-06, "loss": 0.0009, "step": 375750 }, { "epoch": 90.25, "learning_rate": 4.847067760509788e-06, "loss": 0.0009, "step": 375760 }, { "epoch": 90.25, "learning_rate": 4.84552609408272e-06, "loss": 0.001, "step": 375770 }, { "epoch": 90.25, "learning_rate": 4.843984660382178e-06, "loss": 0.0009, "step": 375780 }, { "epoch": 90.26, "learning_rate": 4.842443459416124e-06, "loss": 0.0009, "step": 375790 }, { "epoch": 90.26, "learning_rate": 4.8409024911924894e-06, "loss": 0.0009, "step": 375800 }, { "epoch": 90.26, "learning_rate": 4.839361755719218e-06, "loss": 0.001, "step": 375810 }, { "epoch": 90.26, "learning_rate": 4.837821253004265e-06, "loss": 0.001, "step": 375820 }, { "epoch": 90.27, "learning_rate": 4.836280983055547e-06, "loss": 0.0008, "step": 375830 }, { "epoch": 90.27, "learning_rate": 4.834740945881028e-06, "loss": 0.0009, "step": 375840 }, { "epoch": 90.27, "learning_rate": 4.833201141488619e-06, "loss": 0.0009, "step": 375850 }, { "epoch": 90.27, "learning_rate": 4.831661569886276e-06, "loss": 0.001, "step": 375860 }, { "epoch": 90.27, "learning_rate": 4.83012223108193e-06, "loss": 0.0008, "step": 375870 }, { "epoch": 90.28, "learning_rate": 4.8285831250835025e-06, "loss": 0.001, "step": 375880 }, { "epoch": 90.28, "learning_rate": 4.827044251898944e-06, "loss": 0.001, "step": 375890 }, { "epoch": 90.28, "learning_rate": 4.825505611536163e-06, "loss": 0.0009, "step": 375900 }, { "epoch": 90.28, "learning_rate": 4.823967204003116e-06, "loss": 0.0009, "step": 375910 }, { "epoch": 90.29, "learning_rate": 4.822429029307713e-06, "loss": 0.0009, "step": 375920 }, { "epoch": 90.29, "learning_rate": 4.820891087457896e-06, "loss": 0.001, "step": 375930 }, { "epoch": 90.29, "learning_rate": 4.819353378461583e-06, "loss": 0.0008, "step": 375940 }, { "epoch": 90.29, "learning_rate": 4.817815902326695e-06, "loss": 0.0009, "step": 375950 }, { "epoch": 90.29, "learning_rate": 4.816278659061168e-06, "loss": 0.001, "step": 375960 }, { "epoch": 90.3, "learning_rate": 4.81474164867291e-06, "loss": 0.001, "step": 375970 }, { "epoch": 90.3, "learning_rate": 4.8132048711698575e-06, "loss": 0.0009, "step": 375980 }, { "epoch": 90.3, "learning_rate": 4.811668326559921e-06, "loss": 0.0009, "step": 375990 }, { "epoch": 90.3, "learning_rate": 4.810132014851027e-06, "loss": 0.0011, "step": 376000 }, { "epoch": 90.31, "learning_rate": 4.808595936051091e-06, "loss": 0.001, "step": 376010 }, { "epoch": 90.31, "learning_rate": 4.807060090168025e-06, "loss": 0.0009, "step": 376020 }, { "epoch": 90.31, "learning_rate": 4.805524477209756e-06, "loss": 0.0009, "step": 376030 }, { "epoch": 90.31, "learning_rate": 4.80398909718418e-06, "loss": 0.0009, "step": 376040 }, { "epoch": 90.32, "learning_rate": 4.8024539500992335e-06, "loss": 0.0009, "step": 376050 }, { "epoch": 90.32, "learning_rate": 4.8009190359628086e-06, "loss": 0.002, "step": 376060 }, { "epoch": 90.32, "learning_rate": 4.799384354782832e-06, "loss": 0.0009, "step": 376070 }, { "epoch": 90.32, "learning_rate": 4.797849906567197e-06, "loss": 0.001, "step": 376080 }, { "epoch": 90.32, "learning_rate": 4.796315691323833e-06, "loss": 0.001, "step": 376090 }, { "epoch": 90.33, "learning_rate": 4.794781709060625e-06, "loss": 0.0009, "step": 376100 }, { "epoch": 90.33, "learning_rate": 4.793247959785496e-06, "loss": 0.0009, "step": 376110 }, { "epoch": 90.33, "learning_rate": 4.7917144435063396e-06, "loss": 0.0009, "step": 376120 }, { "epoch": 90.33, "learning_rate": 4.790181160231061e-06, "loss": 0.001, "step": 376130 }, { "epoch": 90.34, "learning_rate": 4.78864810996758e-06, "loss": 0.0009, "step": 376140 }, { "epoch": 90.34, "learning_rate": 4.787115292723776e-06, "loss": 0.0009, "step": 376150 }, { "epoch": 90.34, "learning_rate": 4.785582708507563e-06, "loss": 0.0008, "step": 376160 }, { "epoch": 90.34, "learning_rate": 4.784050357326836e-06, "loss": 0.0009, "step": 376170 }, { "epoch": 90.35, "learning_rate": 4.782518239189487e-06, "loss": 0.0008, "step": 376180 }, { "epoch": 90.35, "learning_rate": 4.780986354103423e-06, "loss": 0.0011, "step": 376190 }, { "epoch": 90.35, "learning_rate": 4.779454702076519e-06, "loss": 0.0009, "step": 376200 }, { "epoch": 90.35, "learning_rate": 4.777923283116698e-06, "loss": 0.0009, "step": 376210 }, { "epoch": 90.35, "learning_rate": 4.77639209723183e-06, "loss": 0.0009, "step": 376220 }, { "epoch": 90.36, "learning_rate": 4.77486114442982e-06, "loss": 0.0009, "step": 376230 }, { "epoch": 90.36, "learning_rate": 4.773330424718558e-06, "loss": 0.0009, "step": 376240 }, { "epoch": 90.36, "learning_rate": 4.771799938105914e-06, "loss": 0.0009, "step": 376250 }, { "epoch": 90.36, "learning_rate": 4.770269684599804e-06, "loss": 0.0009, "step": 376260 }, { "epoch": 90.37, "learning_rate": 4.768739664208094e-06, "loss": 0.001, "step": 376270 }, { "epoch": 90.37, "learning_rate": 4.767209876938688e-06, "loss": 0.0009, "step": 376280 }, { "epoch": 90.37, "learning_rate": 4.765680322799449e-06, "loss": 0.001, "step": 376290 }, { "epoch": 90.37, "learning_rate": 4.764151001798284e-06, "loss": 0.0009, "step": 376300 }, { "epoch": 90.37, "learning_rate": 4.762621913943055e-06, "loss": 0.0014, "step": 376310 }, { "epoch": 90.38, "learning_rate": 4.76109305924165e-06, "loss": 0.0009, "step": 376320 }, { "epoch": 90.38, "learning_rate": 4.759564437701952e-06, "loss": 0.0009, "step": 376330 }, { "epoch": 90.38, "learning_rate": 4.758036049331832e-06, "loss": 0.001, "step": 376340 }, { "epoch": 90.38, "learning_rate": 4.756507894139184e-06, "loss": 0.0009, "step": 376350 }, { "epoch": 90.39, "learning_rate": 4.754979972131857e-06, "loss": 0.0009, "step": 376360 }, { "epoch": 90.39, "learning_rate": 4.753452283317755e-06, "loss": 0.001, "step": 376370 }, { "epoch": 90.39, "learning_rate": 4.7519248277047294e-06, "loss": 0.001, "step": 376380 }, { "epoch": 90.39, "learning_rate": 4.750397605300666e-06, "loss": 0.001, "step": 376390 }, { "epoch": 90.4, "learning_rate": 4.748870616113427e-06, "loss": 0.0009, "step": 376400 }, { "epoch": 90.4, "learning_rate": 4.7473438601508935e-06, "loss": 0.0009, "step": 376410 }, { "epoch": 90.4, "learning_rate": 4.745817337420921e-06, "loss": 0.0008, "step": 376420 }, { "epoch": 90.4, "learning_rate": 4.744291047931393e-06, "loss": 0.0009, "step": 376430 }, { "epoch": 90.4, "learning_rate": 4.742764991690158e-06, "loss": 0.0009, "step": 376440 }, { "epoch": 90.41, "learning_rate": 4.7412391687050976e-06, "loss": 0.0008, "step": 376450 }, { "epoch": 90.41, "learning_rate": 4.739713578984062e-06, "loss": 0.0009, "step": 376460 }, { "epoch": 90.41, "learning_rate": 4.738188222534928e-06, "loss": 0.001, "step": 376470 }, { "epoch": 90.41, "learning_rate": 4.7366630993655404e-06, "loss": 0.001, "step": 376480 }, { "epoch": 90.42, "learning_rate": 4.73513820948378e-06, "loss": 0.0009, "step": 376490 }, { "epoch": 90.42, "learning_rate": 4.733613552897486e-06, "loss": 0.0009, "step": 376500 }, { "epoch": 90.42, "learning_rate": 4.732089129614542e-06, "loss": 0.0011, "step": 376510 }, { "epoch": 90.42, "learning_rate": 4.730564939642779e-06, "loss": 0.0009, "step": 376520 }, { "epoch": 90.43, "learning_rate": 4.729040982990058e-06, "loss": 0.0024, "step": 376530 }, { "epoch": 90.43, "learning_rate": 4.727517259664249e-06, "loss": 0.0009, "step": 376540 }, { "epoch": 90.43, "learning_rate": 4.725993769673182e-06, "loss": 0.0009, "step": 376550 }, { "epoch": 90.43, "learning_rate": 4.724470513024731e-06, "loss": 0.0009, "step": 376560 }, { "epoch": 90.43, "learning_rate": 4.722947489726731e-06, "loss": 0.001, "step": 376570 }, { "epoch": 90.44, "learning_rate": 4.721424699787047e-06, "loss": 0.0009, "step": 376580 }, { "epoch": 90.44, "learning_rate": 4.719902143213517e-06, "loss": 0.0009, "step": 376590 }, { "epoch": 90.44, "learning_rate": 4.718379820013979e-06, "loss": 0.001, "step": 376600 }, { "epoch": 90.44, "learning_rate": 4.716857730196306e-06, "loss": 0.0008, "step": 376610 }, { "epoch": 90.45, "learning_rate": 4.715335873768312e-06, "loss": 0.001, "step": 376620 }, { "epoch": 90.45, "learning_rate": 4.713814250737863e-06, "loss": 0.001, "step": 376630 }, { "epoch": 90.45, "learning_rate": 4.712292861112788e-06, "loss": 0.0009, "step": 376640 }, { "epoch": 90.45, "learning_rate": 4.71077170490094e-06, "loss": 0.001, "step": 376650 }, { "epoch": 90.45, "learning_rate": 4.709250782110159e-06, "loss": 0.001, "step": 376660 }, { "epoch": 90.46, "learning_rate": 4.707730092748264e-06, "loss": 0.0009, "step": 376670 }, { "epoch": 90.46, "learning_rate": 4.706209636823117e-06, "loss": 0.001, "step": 376680 }, { "epoch": 90.46, "learning_rate": 4.704689414342533e-06, "loss": 0.0008, "step": 376690 }, { "epoch": 90.46, "learning_rate": 4.703169425314363e-06, "loss": 0.0009, "step": 376700 }, { "epoch": 90.47, "learning_rate": 4.701649669746444e-06, "loss": 0.0009, "step": 376710 }, { "epoch": 90.47, "learning_rate": 4.700130147646586e-06, "loss": 0.0008, "step": 376720 }, { "epoch": 90.47, "learning_rate": 4.69861085902265e-06, "loss": 0.0009, "step": 376730 }, { "epoch": 90.47, "learning_rate": 4.697091803882448e-06, "loss": 0.0009, "step": 376740 }, { "epoch": 90.48, "learning_rate": 4.695572982233815e-06, "loss": 0.001, "step": 376750 }, { "epoch": 90.48, "learning_rate": 4.694054394084574e-06, "loss": 0.0009, "step": 376760 }, { "epoch": 90.48, "learning_rate": 4.692536039442563e-06, "loss": 0.0009, "step": 376770 }, { "epoch": 90.48, "learning_rate": 4.691017918315588e-06, "loss": 0.0008, "step": 376780 }, { "epoch": 90.48, "learning_rate": 4.689500030711497e-06, "loss": 0.001, "step": 376790 }, { "epoch": 90.49, "learning_rate": 4.687982376638101e-06, "loss": 0.0008, "step": 376800 }, { "epoch": 90.49, "learning_rate": 4.6864649561032096e-06, "loss": 0.001, "step": 376810 }, { "epoch": 90.49, "learning_rate": 4.684947769114673e-06, "loss": 0.0009, "step": 376820 }, { "epoch": 90.49, "learning_rate": 4.683430815680279e-06, "loss": 0.001, "step": 376830 }, { "epoch": 90.5, "learning_rate": 4.681914095807876e-06, "loss": 0.0008, "step": 376840 }, { "epoch": 90.5, "learning_rate": 4.6803976095052545e-06, "loss": 0.0009, "step": 376850 }, { "epoch": 90.5, "learning_rate": 4.678881356780251e-06, "loss": 0.0009, "step": 376860 }, { "epoch": 90.5, "learning_rate": 4.67736533764066e-06, "loss": 0.001, "step": 376870 }, { "epoch": 90.51, "learning_rate": 4.675849552094319e-06, "loss": 0.001, "step": 376880 }, { "epoch": 90.51, "learning_rate": 4.674334000149033e-06, "loss": 0.0009, "step": 376890 }, { "epoch": 90.51, "learning_rate": 4.672818681812591e-06, "loss": 0.001, "step": 376900 }, { "epoch": 90.51, "learning_rate": 4.6713035970928355e-06, "loss": 0.0009, "step": 376910 }, { "epoch": 90.51, "learning_rate": 4.66978874599755e-06, "loss": 0.0008, "step": 376920 }, { "epoch": 90.52, "learning_rate": 4.668274128534561e-06, "loss": 0.001, "step": 376930 }, { "epoch": 90.52, "learning_rate": 4.666759744711652e-06, "loss": 0.0009, "step": 376940 }, { "epoch": 90.52, "learning_rate": 4.66524559453666e-06, "loss": 0.0009, "step": 376950 }, { "epoch": 90.52, "learning_rate": 4.663731678017363e-06, "loss": 0.001, "step": 376960 }, { "epoch": 90.53, "learning_rate": 4.662217995161567e-06, "loss": 0.0009, "step": 376970 }, { "epoch": 90.53, "learning_rate": 4.660704545977091e-06, "loss": 0.001, "step": 376980 }, { "epoch": 90.53, "learning_rate": 4.6591913304717075e-06, "loss": 0.001, "step": 376990 }, { "epoch": 90.53, "learning_rate": 4.657678348653244e-06, "loss": 0.001, "step": 377000 }, { "epoch": 90.53, "learning_rate": 4.656165600529472e-06, "loss": 0.001, "step": 377010 }, { "epoch": 90.54, "learning_rate": 4.654653086108202e-06, "loss": 0.001, "step": 377020 }, { "epoch": 90.54, "learning_rate": 4.653140805397243e-06, "loss": 0.0009, "step": 377030 }, { "epoch": 90.54, "learning_rate": 4.651628758404364e-06, "loss": 0.001, "step": 377040 }, { "epoch": 90.54, "learning_rate": 4.650116945137378e-06, "loss": 0.0009, "step": 377050 }, { "epoch": 90.55, "learning_rate": 4.648605365604059e-06, "loss": 0.0009, "step": 377060 }, { "epoch": 90.55, "learning_rate": 4.647094019812215e-06, "loss": 0.0011, "step": 377070 }, { "epoch": 90.55, "learning_rate": 4.645582907769619e-06, "loss": 0.001, "step": 377080 }, { "epoch": 90.55, "learning_rate": 4.644072029484075e-06, "loss": 0.0009, "step": 377090 }, { "epoch": 90.56, "learning_rate": 4.642561384963368e-06, "loss": 0.0009, "step": 377100 }, { "epoch": 90.56, "learning_rate": 4.641050974215266e-06, "loss": 0.001, "step": 377110 }, { "epoch": 90.56, "learning_rate": 4.639540797247577e-06, "loss": 0.001, "step": 377120 }, { "epoch": 90.56, "learning_rate": 4.638030854068065e-06, "loss": 0.0009, "step": 377130 }, { "epoch": 90.56, "learning_rate": 4.6365211446845306e-06, "loss": 0.0009, "step": 377140 }, { "epoch": 90.57, "learning_rate": 4.635011669104733e-06, "loss": 0.001, "step": 377150 }, { "epoch": 90.57, "learning_rate": 4.633502427336478e-06, "loss": 0.001, "step": 377160 }, { "epoch": 90.57, "learning_rate": 4.631993419387526e-06, "loss": 0.0009, "step": 377170 }, { "epoch": 90.57, "learning_rate": 4.630484645265653e-06, "loss": 0.0009, "step": 377180 }, { "epoch": 90.58, "learning_rate": 4.62897610497865e-06, "loss": 0.001, "step": 377190 }, { "epoch": 90.58, "learning_rate": 4.627467798534274e-06, "loss": 0.0009, "step": 377200 }, { "epoch": 90.58, "learning_rate": 4.625959725940316e-06, "loss": 0.0011, "step": 377210 }, { "epoch": 90.58, "learning_rate": 4.624451887204534e-06, "loss": 0.0009, "step": 377220 }, { "epoch": 90.59, "learning_rate": 4.622944282334712e-06, "loss": 0.001, "step": 377230 }, { "epoch": 90.59, "learning_rate": 4.621436911338623e-06, "loss": 0.001, "step": 377240 }, { "epoch": 90.59, "learning_rate": 4.619929774224007e-06, "loss": 0.0008, "step": 377250 }, { "epoch": 90.59, "learning_rate": 4.618422870998668e-06, "loss": 0.0016, "step": 377260 }, { "epoch": 90.59, "learning_rate": 4.616916201670346e-06, "loss": 0.0009, "step": 377270 }, { "epoch": 90.6, "learning_rate": 4.615409766246831e-06, "loss": 0.0008, "step": 377280 }, { "epoch": 90.6, "learning_rate": 4.6139035647358605e-06, "loss": 0.001, "step": 377290 }, { "epoch": 90.6, "learning_rate": 4.6123975971452185e-06, "loss": 0.001, "step": 377300 }, { "epoch": 90.6, "learning_rate": 4.610891863482647e-06, "loss": 0.0009, "step": 377310 }, { "epoch": 90.61, "learning_rate": 4.6093863637559244e-06, "loss": 0.001, "step": 377320 }, { "epoch": 90.61, "learning_rate": 4.6078810979728105e-06, "loss": 0.0009, "step": 377330 }, { "epoch": 90.61, "learning_rate": 4.6063760661410435e-06, "loss": 0.001, "step": 377340 }, { "epoch": 90.61, "learning_rate": 4.604871268268407e-06, "loss": 0.001, "step": 377350 }, { "epoch": 90.61, "learning_rate": 4.603366704362639e-06, "loss": 0.0017, "step": 377360 }, { "epoch": 90.62, "learning_rate": 4.601862374431498e-06, "loss": 0.0009, "step": 377370 }, { "epoch": 90.62, "learning_rate": 4.600358278482747e-06, "loss": 0.001, "step": 377380 }, { "epoch": 90.62, "learning_rate": 4.598854416524112e-06, "loss": 0.0017, "step": 377390 }, { "epoch": 90.62, "learning_rate": 4.597350788563376e-06, "loss": 0.0009, "step": 377400 }, { "epoch": 90.63, "learning_rate": 4.59584739460826e-06, "loss": 0.0009, "step": 377410 }, { "epoch": 90.63, "learning_rate": 4.5943442346665365e-06, "loss": 0.0009, "step": 377420 }, { "epoch": 90.63, "learning_rate": 4.592841308745932e-06, "loss": 0.001, "step": 377430 }, { "epoch": 90.63, "learning_rate": 4.591338616854213e-06, "loss": 0.0009, "step": 377440 }, { "epoch": 90.64, "learning_rate": 4.589836158999117e-06, "loss": 0.0009, "step": 377450 }, { "epoch": 90.64, "learning_rate": 4.588333935188371e-06, "loss": 0.001, "step": 377460 }, { "epoch": 90.64, "learning_rate": 4.586831945429748e-06, "loss": 0.001, "step": 377470 }, { "epoch": 90.64, "learning_rate": 4.585330189730957e-06, "loss": 0.001, "step": 377480 }, { "epoch": 90.64, "learning_rate": 4.5838286680997655e-06, "loss": 0.0008, "step": 377490 }, { "epoch": 90.65, "learning_rate": 4.582327380543888e-06, "loss": 0.0009, "step": 377500 }, { "epoch": 90.65, "learning_rate": 4.580826327071086e-06, "loss": 0.0011, "step": 377510 }, { "epoch": 90.65, "learning_rate": 4.5793255076890865e-06, "loss": 0.001, "step": 377520 }, { "epoch": 90.65, "learning_rate": 4.577824922405616e-06, "loss": 0.0009, "step": 377530 }, { "epoch": 90.66, "learning_rate": 4.5763245712284185e-06, "loss": 0.0011, "step": 377540 }, { "epoch": 90.66, "learning_rate": 4.574824454165222e-06, "loss": 0.0009, "step": 377550 }, { "epoch": 90.66, "learning_rate": 4.5733245712237634e-06, "loss": 0.001, "step": 377560 }, { "epoch": 90.66, "learning_rate": 4.57182492241176e-06, "loss": 0.0009, "step": 377570 }, { "epoch": 90.66, "learning_rate": 4.570325507736961e-06, "loss": 0.001, "step": 377580 }, { "epoch": 90.67, "learning_rate": 4.568826327207076e-06, "loss": 0.0009, "step": 377590 }, { "epoch": 90.67, "learning_rate": 4.56732738082985e-06, "loss": 0.001, "step": 377600 }, { "epoch": 90.67, "learning_rate": 4.565828668612987e-06, "loss": 0.0008, "step": 377610 }, { "epoch": 90.67, "learning_rate": 4.564330190564237e-06, "loss": 0.001, "step": 377620 }, { "epoch": 90.68, "learning_rate": 4.562831946691293e-06, "loss": 0.0009, "step": 377630 }, { "epoch": 90.68, "learning_rate": 4.5613339370018995e-06, "loss": 0.001, "step": 377640 }, { "epoch": 90.68, "learning_rate": 4.559836161503772e-06, "loss": 0.0009, "step": 377650 }, { "epoch": 90.68, "learning_rate": 4.558338620204633e-06, "loss": 0.0009, "step": 377660 }, { "epoch": 90.69, "learning_rate": 4.5568413131121865e-06, "loss": 0.0009, "step": 377670 }, { "epoch": 90.69, "learning_rate": 4.555344240234171e-06, "loss": 0.001, "step": 377680 }, { "epoch": 90.69, "learning_rate": 4.553847401578282e-06, "loss": 0.001, "step": 377690 }, { "epoch": 90.69, "learning_rate": 4.552350797152249e-06, "loss": 0.001, "step": 377700 }, { "epoch": 90.69, "learning_rate": 4.550854426963774e-06, "loss": 0.0009, "step": 377710 }, { "epoch": 90.7, "learning_rate": 4.549358291020583e-06, "loss": 0.0008, "step": 377720 }, { "epoch": 90.7, "learning_rate": 4.547862389330371e-06, "loss": 0.001, "step": 377730 }, { "epoch": 90.7, "learning_rate": 4.546366721900863e-06, "loss": 0.0009, "step": 377740 }, { "epoch": 90.7, "learning_rate": 4.544871288739766e-06, "loss": 0.0009, "step": 377750 }, { "epoch": 90.71, "learning_rate": 4.543376089854768e-06, "loss": 0.0009, "step": 377760 }, { "epoch": 90.71, "learning_rate": 4.5418811252536e-06, "loss": 0.0009, "step": 377770 }, { "epoch": 90.71, "learning_rate": 4.5403863949439515e-06, "loss": 0.0011, "step": 377780 }, { "epoch": 90.71, "learning_rate": 4.5388918989335336e-06, "loss": 0.0009, "step": 377790 }, { "epoch": 90.72, "learning_rate": 4.5373976372300454e-06, "loss": 0.0009, "step": 377800 }, { "epoch": 90.72, "learning_rate": 4.535903609841191e-06, "loss": 0.001, "step": 377810 }, { "epoch": 90.72, "learning_rate": 4.534409816774676e-06, "loss": 0.001, "step": 377820 }, { "epoch": 90.72, "learning_rate": 4.532916258038178e-06, "loss": 0.0009, "step": 377830 }, { "epoch": 90.72, "learning_rate": 4.531422933639423e-06, "loss": 0.0009, "step": 377840 }, { "epoch": 90.73, "learning_rate": 4.529929843586084e-06, "loss": 0.001, "step": 377850 }, { "epoch": 90.73, "learning_rate": 4.5284369878858755e-06, "loss": 0.0009, "step": 377860 }, { "epoch": 90.73, "learning_rate": 4.526944366546476e-06, "loss": 0.0009, "step": 377870 }, { "epoch": 90.73, "learning_rate": 4.52545197957559e-06, "loss": 0.0009, "step": 377880 }, { "epoch": 90.74, "learning_rate": 4.5239598269809005e-06, "loss": 0.001, "step": 377890 }, { "epoch": 90.74, "learning_rate": 4.522467908770106e-06, "loss": 0.0009, "step": 377900 }, { "epoch": 90.74, "learning_rate": 4.520976224950885e-06, "loss": 0.001, "step": 377910 }, { "epoch": 90.74, "learning_rate": 4.5194847755309415e-06, "loss": 0.0009, "step": 377920 }, { "epoch": 90.74, "learning_rate": 4.517993560517947e-06, "loss": 0.0009, "step": 377930 }, { "epoch": 90.75, "learning_rate": 4.516502579919602e-06, "loss": 0.0009, "step": 377940 }, { "epoch": 90.75, "learning_rate": 4.515011833743571e-06, "loss": 0.0009, "step": 377950 }, { "epoch": 90.75, "learning_rate": 4.513521321997561e-06, "loss": 0.0009, "step": 377960 }, { "epoch": 90.75, "learning_rate": 4.5120310446892355e-06, "loss": 0.0009, "step": 377970 }, { "epoch": 90.76, "learning_rate": 4.510541001826285e-06, "loss": 0.001, "step": 377980 }, { "epoch": 90.76, "learning_rate": 4.50905119341638e-06, "loss": 0.0009, "step": 377990 }, { "epoch": 90.76, "learning_rate": 4.507561619467215e-06, "loss": 0.001, "step": 378000 }, { "epoch": 90.76, "learning_rate": 4.506072279986451e-06, "loss": 0.0012, "step": 378010 }, { "epoch": 90.77, "learning_rate": 4.50458317498178e-06, "loss": 0.001, "step": 378020 }, { "epoch": 90.77, "learning_rate": 4.5030943044608645e-06, "loss": 0.0009, "step": 378030 }, { "epoch": 90.77, "learning_rate": 4.5016056684313744e-06, "loss": 0.001, "step": 378040 }, { "epoch": 90.77, "learning_rate": 4.500117266900994e-06, "loss": 0.0008, "step": 378050 }, { "epoch": 90.77, "learning_rate": 4.498629099877383e-06, "loss": 0.0011, "step": 378060 }, { "epoch": 90.78, "learning_rate": 4.497141167368229e-06, "loss": 0.0009, "step": 378070 }, { "epoch": 90.78, "learning_rate": 4.495653469381178e-06, "loss": 0.0009, "step": 378080 }, { "epoch": 90.78, "learning_rate": 4.494166005923917e-06, "loss": 0.001, "step": 378090 }, { "epoch": 90.78, "learning_rate": 4.492678777004105e-06, "loss": 0.001, "step": 378100 }, { "epoch": 90.79, "learning_rate": 4.4911917826294e-06, "loss": 0.0008, "step": 378110 }, { "epoch": 90.79, "learning_rate": 4.4897050228074835e-06, "loss": 0.001, "step": 378120 }, { "epoch": 90.79, "learning_rate": 4.4882184975459984e-06, "loss": 0.001, "step": 378130 }, { "epoch": 90.79, "learning_rate": 4.486732206852623e-06, "loss": 0.0009, "step": 378140 }, { "epoch": 90.8, "learning_rate": 4.485246150735001e-06, "loss": 0.0008, "step": 378150 }, { "epoch": 90.8, "learning_rate": 4.483760329200809e-06, "loss": 0.0009, "step": 378160 }, { "epoch": 90.8, "learning_rate": 4.4822747422577025e-06, "loss": 0.0009, "step": 378170 }, { "epoch": 90.8, "learning_rate": 4.480789389913315e-06, "loss": 0.0009, "step": 378180 }, { "epoch": 90.8, "learning_rate": 4.479304272175333e-06, "loss": 0.0009, "step": 378190 }, { "epoch": 90.81, "learning_rate": 4.477819389051391e-06, "loss": 0.0009, "step": 378200 }, { "epoch": 90.81, "learning_rate": 4.4763347405491425e-06, "loss": 0.0009, "step": 378210 }, { "epoch": 90.81, "learning_rate": 4.474850326676256e-06, "loss": 0.0009, "step": 378220 }, { "epoch": 90.81, "learning_rate": 4.473366147440367e-06, "loss": 0.0009, "step": 378230 }, { "epoch": 90.82, "learning_rate": 4.471882202849131e-06, "loss": 0.0009, "step": 378240 }, { "epoch": 90.82, "learning_rate": 4.470398492910188e-06, "loss": 0.0009, "step": 378250 }, { "epoch": 90.82, "learning_rate": 4.468915017631203e-06, "loss": 0.001, "step": 378260 }, { "epoch": 90.82, "learning_rate": 4.467431777019804e-06, "loss": 0.0009, "step": 378270 }, { "epoch": 90.82, "learning_rate": 4.465948771083644e-06, "loss": 0.001, "step": 378280 }, { "epoch": 90.83, "learning_rate": 4.4644659998303635e-06, "loss": 0.001, "step": 378290 }, { "epoch": 90.83, "learning_rate": 4.462983463267612e-06, "loss": 0.0009, "step": 378300 }, { "epoch": 90.83, "learning_rate": 4.46150116140302e-06, "loss": 0.001, "step": 378310 }, { "epoch": 90.83, "learning_rate": 4.460019094244228e-06, "loss": 0.0009, "step": 378320 }, { "epoch": 90.84, "learning_rate": 4.458537261798884e-06, "loss": 0.0009, "step": 378330 }, { "epoch": 90.84, "learning_rate": 4.457055664074611e-06, "loss": 0.001, "step": 378340 }, { "epoch": 90.84, "learning_rate": 4.455574301079063e-06, "loss": 0.0009, "step": 378350 }, { "epoch": 90.84, "learning_rate": 4.454093172819856e-06, "loss": 0.0011, "step": 378360 }, { "epoch": 90.85, "learning_rate": 4.452612279304646e-06, "loss": 0.001, "step": 378370 }, { "epoch": 90.85, "learning_rate": 4.4511316205410495e-06, "loss": 0.001, "step": 378380 }, { "epoch": 90.85, "learning_rate": 4.449651196536697e-06, "loss": 0.0009, "step": 378390 }, { "epoch": 90.85, "learning_rate": 4.448171007299229e-06, "loss": 0.0009, "step": 378400 }, { "epoch": 90.85, "learning_rate": 4.446691052836261e-06, "loss": 0.0009, "step": 378410 }, { "epoch": 90.86, "learning_rate": 4.44521133315543e-06, "loss": 0.001, "step": 378420 }, { "epoch": 90.86, "learning_rate": 4.44373184826436e-06, "loss": 0.001, "step": 378430 }, { "epoch": 90.86, "learning_rate": 4.442252598170682e-06, "loss": 0.0009, "step": 378440 }, { "epoch": 90.86, "learning_rate": 4.440773582882013e-06, "loss": 0.0008, "step": 378450 }, { "epoch": 90.87, "learning_rate": 4.439294802405974e-06, "loss": 0.0008, "step": 378460 }, { "epoch": 90.87, "learning_rate": 4.437816256750193e-06, "loss": 0.001, "step": 378470 }, { "epoch": 90.87, "learning_rate": 4.436337945922287e-06, "loss": 0.0009, "step": 378480 }, { "epoch": 90.87, "learning_rate": 4.43485986992988e-06, "loss": 0.001, "step": 378490 }, { "epoch": 90.88, "learning_rate": 4.433382028780575e-06, "loss": 0.001, "step": 378500 }, { "epoch": 90.88, "learning_rate": 4.431904422482014e-06, "loss": 0.001, "step": 378510 }, { "epoch": 90.88, "learning_rate": 4.430427051041786e-06, "loss": 0.001, "step": 378520 }, { "epoch": 90.88, "learning_rate": 4.428949914467517e-06, "loss": 0.0009, "step": 378530 }, { "epoch": 90.88, "learning_rate": 4.427473012766836e-06, "loss": 0.001, "step": 378540 }, { "epoch": 90.89, "learning_rate": 4.425996345947325e-06, "loss": 0.001, "step": 378550 }, { "epoch": 90.89, "learning_rate": 4.424519914016623e-06, "loss": 0.001, "step": 378560 }, { "epoch": 90.89, "learning_rate": 4.423043716982311e-06, "loss": 0.0009, "step": 378570 }, { "epoch": 90.89, "learning_rate": 4.4215677548520295e-06, "loss": 0.001, "step": 378580 }, { "epoch": 90.9, "learning_rate": 4.420092027633355e-06, "loss": 0.0009, "step": 378590 }, { "epoch": 90.9, "learning_rate": 4.418616535333919e-06, "loss": 0.0008, "step": 378600 }, { "epoch": 90.9, "learning_rate": 4.417141277961312e-06, "loss": 0.0009, "step": 378610 }, { "epoch": 90.9, "learning_rate": 4.415666255523132e-06, "loss": 0.001, "step": 378620 }, { "epoch": 90.9, "learning_rate": 4.414191468026996e-06, "loss": 0.001, "step": 378630 }, { "epoch": 90.91, "learning_rate": 4.412716915480492e-06, "loss": 0.0009, "step": 378640 }, { "epoch": 90.91, "learning_rate": 4.411242597891235e-06, "loss": 0.0009, "step": 378650 }, { "epoch": 90.91, "learning_rate": 4.409768515266804e-06, "loss": 0.0009, "step": 378660 }, { "epoch": 90.91, "learning_rate": 4.4082946676148155e-06, "loss": 0.0012, "step": 378670 }, { "epoch": 90.92, "learning_rate": 4.406821054942861e-06, "loss": 0.0009, "step": 378680 }, { "epoch": 90.92, "learning_rate": 4.40534767725852e-06, "loss": 0.001, "step": 378690 }, { "epoch": 90.92, "learning_rate": 4.403874534569407e-06, "loss": 0.0011, "step": 378700 }, { "epoch": 90.92, "learning_rate": 4.4024016268830955e-06, "loss": 0.001, "step": 378710 }, { "epoch": 90.93, "learning_rate": 4.400928954207201e-06, "loss": 0.001, "step": 378720 }, { "epoch": 90.93, "learning_rate": 4.399456516549288e-06, "loss": 0.0009, "step": 378730 }, { "epoch": 90.93, "learning_rate": 4.397984313916964e-06, "loss": 0.0009, "step": 378740 }, { "epoch": 90.93, "learning_rate": 4.396512346317816e-06, "loss": 0.0009, "step": 378750 }, { "epoch": 90.93, "learning_rate": 4.39504061375941e-06, "loss": 0.001, "step": 378760 }, { "epoch": 90.94, "learning_rate": 4.393569116249357e-06, "loss": 0.0009, "step": 378770 }, { "epoch": 90.94, "learning_rate": 4.392097853795219e-06, "loss": 0.0008, "step": 378780 }, { "epoch": 90.94, "learning_rate": 4.3906268264046036e-06, "loss": 0.0009, "step": 378790 }, { "epoch": 90.94, "learning_rate": 4.389156034085062e-06, "loss": 0.001, "step": 378800 }, { "epoch": 90.95, "learning_rate": 4.387685476844205e-06, "loss": 0.001, "step": 378810 }, { "epoch": 90.95, "learning_rate": 4.386215154689593e-06, "loss": 0.0009, "step": 378820 }, { "epoch": 90.95, "learning_rate": 4.384745067628804e-06, "loss": 0.001, "step": 378830 }, { "epoch": 91.0, "learning_rate": 4.38327521566943e-06, "loss": 0.0009, "step": 378840 }, { "epoch": 91.0, "learning_rate": 4.381805598819033e-06, "loss": 0.0009, "step": 378850 }, { "epoch": 91.01, "learning_rate": 4.380336217085196e-06, "loss": 0.0009, "step": 378860 }, { "epoch": 91.01, "learning_rate": 4.3788670704754784e-06, "loss": 0.001, "step": 378870 }, { "epoch": 91.01, "learning_rate": 4.37739815899747e-06, "loss": 0.001, "step": 378880 }, { "epoch": 91.01, "learning_rate": 4.375929482658731e-06, "loss": 0.0009, "step": 378890 }, { "epoch": 91.02, "learning_rate": 4.374461041466826e-06, "loss": 0.0009, "step": 378900 }, { "epoch": 91.02, "learning_rate": 4.3729928354293405e-06, "loss": 0.001, "step": 378910 }, { "epoch": 91.02, "learning_rate": 4.371524864553822e-06, "loss": 0.0009, "step": 378920 }, { "epoch": 91.02, "learning_rate": 4.370057128847854e-06, "loss": 0.0009, "step": 378930 }, { "epoch": 91.02, "learning_rate": 4.368589628318981e-06, "loss": 0.0009, "step": 378940 }, { "epoch": 91.03, "learning_rate": 4.367122362974791e-06, "loss": 0.0009, "step": 378950 }, { "epoch": 91.03, "learning_rate": 4.365655332822838e-06, "loss": 0.001, "step": 378960 }, { "epoch": 91.03, "learning_rate": 4.364188537870662e-06, "loss": 0.001, "step": 378970 }, { "epoch": 91.03, "learning_rate": 4.36272197812585e-06, "loss": 0.0009, "step": 378980 }, { "epoch": 91.04, "learning_rate": 4.361255653595947e-06, "loss": 0.0009, "step": 378990 }, { "epoch": 91.04, "learning_rate": 4.359789564288519e-06, "loss": 0.0009, "step": 379000 }, { "epoch": 91.04, "learning_rate": 4.358323710211104e-06, "loss": 0.0009, "step": 379010 }, { "epoch": 91.04, "learning_rate": 4.356858091371285e-06, "loss": 0.0009, "step": 379020 }, { "epoch": 91.05, "learning_rate": 4.355392707776601e-06, "loss": 0.0008, "step": 379030 }, { "epoch": 91.05, "learning_rate": 4.353927559434589e-06, "loss": 0.0009, "step": 379040 }, { "epoch": 91.05, "learning_rate": 4.352462646352834e-06, "loss": 0.0011, "step": 379050 }, { "epoch": 91.05, "learning_rate": 4.35099796853885e-06, "loss": 0.001, "step": 379060 }, { "epoch": 91.05, "learning_rate": 4.349533526000221e-06, "loss": 0.0009, "step": 379070 }, { "epoch": 91.06, "learning_rate": 4.348069318744463e-06, "loss": 0.001, "step": 379080 }, { "epoch": 91.06, "learning_rate": 4.346605346779148e-06, "loss": 0.001, "step": 379090 }, { "epoch": 91.06, "learning_rate": 4.3451416101118025e-06, "loss": 0.0009, "step": 379100 }, { "epoch": 91.06, "learning_rate": 4.343678108749988e-06, "loss": 0.0009, "step": 379110 }, { "epoch": 91.07, "learning_rate": 4.3422148427012314e-06, "loss": 0.0008, "step": 379120 }, { "epoch": 91.07, "learning_rate": 4.340751811973087e-06, "loss": 0.0009, "step": 379130 }, { "epoch": 91.07, "learning_rate": 4.339289016573078e-06, "loss": 0.0009, "step": 379140 }, { "epoch": 91.07, "learning_rate": 4.337826456508759e-06, "loss": 0.0009, "step": 379150 }, { "epoch": 91.07, "learning_rate": 4.336364131787674e-06, "loss": 0.001, "step": 379160 }, { "epoch": 91.08, "learning_rate": 4.3349020424173494e-06, "loss": 0.0009, "step": 379170 }, { "epoch": 91.08, "learning_rate": 4.333440188405307e-06, "loss": 0.0008, "step": 379180 }, { "epoch": 91.08, "learning_rate": 4.33197856975911e-06, "loss": 0.0009, "step": 379190 }, { "epoch": 91.08, "learning_rate": 4.330517186486266e-06, "loss": 0.0008, "step": 379200 }, { "epoch": 91.09, "learning_rate": 4.3290560385943314e-06, "loss": 0.0009, "step": 379210 }, { "epoch": 91.09, "learning_rate": 4.327595126090811e-06, "loss": 0.0008, "step": 379220 }, { "epoch": 91.09, "learning_rate": 4.326134448983255e-06, "loss": 0.0009, "step": 379230 }, { "epoch": 91.09, "learning_rate": 4.3246740072791835e-06, "loss": 0.0011, "step": 379240 }, { "epoch": 91.1, "learning_rate": 4.3232138009861205e-06, "loss": 0.0009, "step": 379250 }, { "epoch": 91.1, "learning_rate": 4.321753830111597e-06, "loss": 0.001, "step": 379260 }, { "epoch": 91.1, "learning_rate": 4.32029409466313e-06, "loss": 0.0009, "step": 379270 }, { "epoch": 91.1, "learning_rate": 4.318834594648258e-06, "loss": 0.001, "step": 379280 }, { "epoch": 91.1, "learning_rate": 4.317375330074486e-06, "loss": 0.0009, "step": 379290 }, { "epoch": 91.11, "learning_rate": 4.315916300949352e-06, "loss": 0.0009, "step": 379300 }, { "epoch": 91.11, "learning_rate": 4.314457507280362e-06, "loss": 0.0009, "step": 379310 }, { "epoch": 91.11, "learning_rate": 4.312998949075042e-06, "loss": 0.0009, "step": 379320 }, { "epoch": 91.11, "learning_rate": 4.3115406263409154e-06, "loss": 0.0009, "step": 379330 }, { "epoch": 91.12, "learning_rate": 4.310082539085475e-06, "loss": 0.0009, "step": 379340 }, { "epoch": 91.12, "learning_rate": 4.308624687316259e-06, "loss": 0.0009, "step": 379350 }, { "epoch": 91.12, "learning_rate": 4.307167071040768e-06, "loss": 0.0009, "step": 379360 }, { "epoch": 91.12, "learning_rate": 4.305709690266529e-06, "loss": 0.0008, "step": 379370 }, { "epoch": 91.12, "learning_rate": 4.3042525450010365e-06, "loss": 0.0008, "step": 379380 }, { "epoch": 91.13, "learning_rate": 4.30279563525181e-06, "loss": 0.001, "step": 379390 }, { "epoch": 91.13, "learning_rate": 4.301338961026363e-06, "loss": 0.0007, "step": 379400 }, { "epoch": 91.13, "learning_rate": 4.299882522332188e-06, "loss": 0.001, "step": 379410 }, { "epoch": 91.13, "learning_rate": 4.298426319176802e-06, "loss": 0.0009, "step": 379420 }, { "epoch": 91.14, "learning_rate": 4.296970351567714e-06, "loss": 0.001, "step": 379430 }, { "epoch": 91.14, "learning_rate": 4.295514619512414e-06, "loss": 0.0009, "step": 379440 }, { "epoch": 91.14, "learning_rate": 4.294059123018423e-06, "loss": 0.0009, "step": 379450 }, { "epoch": 91.14, "learning_rate": 4.292603862093225e-06, "loss": 0.0009, "step": 379460 }, { "epoch": 91.15, "learning_rate": 4.291148836744335e-06, "loss": 0.0009, "step": 379470 }, { "epoch": 91.15, "learning_rate": 4.2896940469792425e-06, "loss": 0.0009, "step": 379480 }, { "epoch": 91.15, "learning_rate": 4.288239492805457e-06, "loss": 0.001, "step": 379490 }, { "epoch": 91.15, "learning_rate": 4.286785174230451e-06, "loss": 0.0009, "step": 379500 }, { "epoch": 91.15, "learning_rate": 4.2853310912617515e-06, "loss": 0.0009, "step": 379510 }, { "epoch": 91.16, "learning_rate": 4.283877243906831e-06, "loss": 0.001, "step": 379520 }, { "epoch": 91.16, "learning_rate": 4.282423632173194e-06, "loss": 0.0008, "step": 379530 }, { "epoch": 91.16, "learning_rate": 4.280970256068328e-06, "loss": 0.001, "step": 379540 }, { "epoch": 91.16, "learning_rate": 4.279517115599719e-06, "loss": 0.0009, "step": 379550 }, { "epoch": 91.17, "learning_rate": 4.2780642107748625e-06, "loss": 0.0009, "step": 379560 }, { "epoch": 91.17, "learning_rate": 4.2766115416012385e-06, "loss": 0.001, "step": 379570 }, { "epoch": 91.17, "learning_rate": 4.275159108086352e-06, "loss": 0.0009, "step": 379580 }, { "epoch": 91.17, "learning_rate": 4.273706910237668e-06, "loss": 0.0009, "step": 379590 }, { "epoch": 91.18, "learning_rate": 4.2722549480626925e-06, "loss": 0.0009, "step": 379600 }, { "epoch": 91.18, "learning_rate": 4.270803221568892e-06, "loss": 0.001, "step": 379610 }, { "epoch": 91.18, "learning_rate": 4.269351730763749e-06, "loss": 0.0008, "step": 379620 }, { "epoch": 91.18, "learning_rate": 4.267900475654757e-06, "loss": 0.0008, "step": 379630 }, { "epoch": 91.18, "learning_rate": 4.266449456249378e-06, "loss": 0.0009, "step": 379640 }, { "epoch": 91.19, "learning_rate": 4.264998672555109e-06, "loss": 0.001, "step": 379650 }, { "epoch": 91.19, "learning_rate": 4.263548124579414e-06, "loss": 0.0009, "step": 379660 }, { "epoch": 91.19, "learning_rate": 4.262097812329779e-06, "loss": 0.0009, "step": 379670 }, { "epoch": 91.19, "learning_rate": 4.260647735813678e-06, "loss": 0.0008, "step": 379680 }, { "epoch": 91.2, "learning_rate": 4.259197895038569e-06, "loss": 0.0009, "step": 379690 }, { "epoch": 91.2, "learning_rate": 4.257748290011948e-06, "loss": 0.001, "step": 379700 }, { "epoch": 91.2, "learning_rate": 4.256298920741264e-06, "loss": 0.0009, "step": 379710 }, { "epoch": 91.2, "learning_rate": 4.254849787234e-06, "loss": 0.001, "step": 379720 }, { "epoch": 91.2, "learning_rate": 4.2534008894976276e-06, "loss": 0.0009, "step": 379730 }, { "epoch": 91.21, "learning_rate": 4.251952227539602e-06, "loss": 0.0009, "step": 379740 }, { "epoch": 91.21, "learning_rate": 4.2505038013674055e-06, "loss": 0.0009, "step": 379750 }, { "epoch": 91.21, "learning_rate": 4.249055610988489e-06, "loss": 0.0009, "step": 379760 }, { "epoch": 91.21, "learning_rate": 4.2476076564103295e-06, "loss": 0.001, "step": 379770 }, { "epoch": 91.22, "learning_rate": 4.24615993764037e-06, "loss": 0.001, "step": 379780 }, { "epoch": 91.22, "learning_rate": 4.244712454686095e-06, "loss": 0.0008, "step": 379790 }, { "epoch": 91.22, "learning_rate": 4.243265207554947e-06, "loss": 0.0009, "step": 379800 }, { "epoch": 91.22, "learning_rate": 4.241818196254405e-06, "loss": 0.0009, "step": 379810 }, { "epoch": 91.23, "learning_rate": 4.240371420791911e-06, "loss": 0.0009, "step": 379820 }, { "epoch": 91.23, "learning_rate": 4.238924881174916e-06, "loss": 0.001, "step": 379830 }, { "epoch": 91.23, "learning_rate": 4.237478577410892e-06, "loss": 0.0009, "step": 379840 }, { "epoch": 91.23, "learning_rate": 4.236032509507282e-06, "loss": 0.001, "step": 379850 }, { "epoch": 91.23, "learning_rate": 4.234586677471547e-06, "loss": 0.0009, "step": 379860 }, { "epoch": 91.24, "learning_rate": 4.233141081311132e-06, "loss": 0.0009, "step": 379870 }, { "epoch": 91.24, "learning_rate": 4.2316957210334905e-06, "loss": 0.0009, "step": 379880 }, { "epoch": 91.24, "learning_rate": 4.230250596646079e-06, "loss": 0.0009, "step": 379890 }, { "epoch": 91.24, "learning_rate": 4.228805708156325e-06, "loss": 0.001, "step": 379900 }, { "epoch": 91.25, "learning_rate": 4.227361055571699e-06, "loss": 0.001, "step": 379910 }, { "epoch": 91.25, "learning_rate": 4.2259166388996295e-06, "loss": 0.0008, "step": 379920 }, { "epoch": 91.25, "learning_rate": 4.224472458147577e-06, "loss": 0.0009, "step": 379930 }, { "epoch": 91.25, "learning_rate": 4.223028513322968e-06, "loss": 0.0008, "step": 379940 }, { "epoch": 91.26, "learning_rate": 4.22158480443326e-06, "loss": 0.0009, "step": 379950 }, { "epoch": 91.26, "learning_rate": 4.220141331485888e-06, "loss": 0.0009, "step": 379960 }, { "epoch": 91.26, "learning_rate": 4.218698094488277e-06, "loss": 0.001, "step": 379970 }, { "epoch": 91.26, "learning_rate": 4.2172550934478914e-06, "loss": 0.0009, "step": 379980 }, { "epoch": 91.26, "learning_rate": 4.215812328372148e-06, "loss": 0.0009, "step": 379990 }, { "epoch": 91.27, "learning_rate": 4.214369799268497e-06, "loss": 0.0009, "step": 380000 }, { "epoch": 91.27, "learning_rate": 4.212927506144359e-06, "loss": 0.001, "step": 380010 }, { "epoch": 91.27, "learning_rate": 4.211485449007186e-06, "loss": 0.001, "step": 380020 }, { "epoch": 91.27, "learning_rate": 4.210043627864385e-06, "loss": 0.0009, "step": 380030 }, { "epoch": 91.28, "learning_rate": 4.208602042723409e-06, "loss": 0.0009, "step": 380040 }, { "epoch": 91.28, "learning_rate": 4.207160693591683e-06, "loss": 0.001, "step": 380050 }, { "epoch": 91.28, "learning_rate": 4.20571958047663e-06, "loss": 0.0009, "step": 380060 }, { "epoch": 91.28, "learning_rate": 4.204278703385684e-06, "loss": 0.0009, "step": 380070 }, { "epoch": 91.28, "learning_rate": 4.202838062326264e-06, "loss": 0.0009, "step": 380080 }, { "epoch": 91.29, "learning_rate": 4.2013976573058056e-06, "loss": 0.0009, "step": 380090 }, { "epoch": 91.29, "learning_rate": 4.199957488331724e-06, "loss": 0.001, "step": 380100 }, { "epoch": 91.29, "learning_rate": 4.198517555411446e-06, "loss": 0.001, "step": 380110 }, { "epoch": 91.29, "learning_rate": 4.197077858552395e-06, "loss": 0.001, "step": 380120 }, { "epoch": 91.3, "learning_rate": 4.195638397761981e-06, "loss": 0.0009, "step": 380130 }, { "epoch": 91.3, "learning_rate": 4.19419917304763e-06, "loss": 0.001, "step": 380140 }, { "epoch": 91.3, "learning_rate": 4.192760184416761e-06, "loss": 0.0009, "step": 380150 }, { "epoch": 91.3, "learning_rate": 4.191321431876788e-06, "loss": 0.001, "step": 380160 }, { "epoch": 91.31, "learning_rate": 4.189882915435123e-06, "loss": 0.001, "step": 380170 }, { "epoch": 91.31, "learning_rate": 4.1884446350991924e-06, "loss": 0.001, "step": 380180 }, { "epoch": 91.31, "learning_rate": 4.187006590876402e-06, "loss": 0.0009, "step": 380190 }, { "epoch": 91.31, "learning_rate": 4.1855687827741575e-06, "loss": 0.0009, "step": 380200 }, { "epoch": 91.31, "learning_rate": 4.18413121079988e-06, "loss": 0.0009, "step": 380210 }, { "epoch": 91.32, "learning_rate": 4.182693874960963e-06, "loss": 0.0009, "step": 380220 }, { "epoch": 91.32, "learning_rate": 4.1812567752648305e-06, "loss": 0.0008, "step": 380230 }, { "epoch": 91.32, "learning_rate": 4.1798199117188795e-06, "loss": 0.0009, "step": 380240 }, { "epoch": 91.32, "learning_rate": 4.178383284330528e-06, "loss": 0.0009, "step": 380250 }, { "epoch": 91.33, "learning_rate": 4.1769468931071695e-06, "loss": 0.001, "step": 380260 }, { "epoch": 91.33, "learning_rate": 4.175510738056204e-06, "loss": 0.001, "step": 380270 }, { "epoch": 91.33, "learning_rate": 4.174074819185048e-06, "loss": 0.0009, "step": 380280 }, { "epoch": 91.33, "learning_rate": 4.172639136501083e-06, "loss": 0.0008, "step": 380290 }, { "epoch": 91.34, "learning_rate": 4.171203690011727e-06, "loss": 0.0009, "step": 380300 }, { "epoch": 91.34, "learning_rate": 4.169768479724367e-06, "loss": 0.0009, "step": 380310 }, { "epoch": 91.34, "learning_rate": 4.168333505646404e-06, "loss": 0.0008, "step": 380320 }, { "epoch": 91.34, "learning_rate": 4.166898767785232e-06, "loss": 0.0009, "step": 380330 }, { "epoch": 91.34, "learning_rate": 4.16546426614825e-06, "loss": 0.0009, "step": 380340 }, { "epoch": 91.35, "learning_rate": 4.164030000742841e-06, "loss": 0.0008, "step": 380350 }, { "epoch": 91.35, "learning_rate": 4.162595971576405e-06, "loss": 0.0009, "step": 380360 }, { "epoch": 91.35, "learning_rate": 4.161162178656341e-06, "loss": 0.001, "step": 380370 }, { "epoch": 91.35, "learning_rate": 4.159728621990022e-06, "loss": 0.0009, "step": 380380 }, { "epoch": 91.36, "learning_rate": 4.158295301584853e-06, "loss": 0.0008, "step": 380390 }, { "epoch": 91.36, "learning_rate": 4.1568622174482155e-06, "loss": 0.001, "step": 380400 }, { "epoch": 91.36, "learning_rate": 4.155429369587483e-06, "loss": 0.0009, "step": 380410 }, { "epoch": 91.36, "learning_rate": 4.153996758010059e-06, "loss": 0.0009, "step": 380420 }, { "epoch": 91.36, "learning_rate": 4.1525643827233115e-06, "loss": 0.0009, "step": 380430 }, { "epoch": 91.37, "learning_rate": 4.151132243734634e-06, "loss": 0.0009, "step": 380440 }, { "epoch": 91.37, "learning_rate": 4.149700341051399e-06, "loss": 0.0009, "step": 380450 }, { "epoch": 91.37, "learning_rate": 4.148268674681005e-06, "loss": 0.0009, "step": 380460 }, { "epoch": 91.37, "learning_rate": 4.146837244630813e-06, "loss": 0.001, "step": 380470 }, { "epoch": 91.38, "learning_rate": 4.145406050908196e-06, "loss": 0.001, "step": 380480 }, { "epoch": 91.38, "learning_rate": 4.1439750935205464e-06, "loss": 0.001, "step": 380490 }, { "epoch": 91.38, "learning_rate": 4.142544372475226e-06, "loss": 0.0009, "step": 380500 }, { "epoch": 91.38, "learning_rate": 4.141113887779624e-06, "loss": 0.0008, "step": 380510 }, { "epoch": 91.39, "learning_rate": 4.1396836394411e-06, "loss": 0.0009, "step": 380520 }, { "epoch": 91.39, "learning_rate": 4.138253627467031e-06, "loss": 0.0008, "step": 380530 }, { "epoch": 91.39, "learning_rate": 4.13682385186479e-06, "loss": 0.0009, "step": 380540 }, { "epoch": 91.39, "learning_rate": 4.1353943126417324e-06, "loss": 0.0009, "step": 380550 }, { "epoch": 91.39, "learning_rate": 4.1339650098052464e-06, "loss": 0.0009, "step": 380560 }, { "epoch": 91.4, "learning_rate": 4.132535943362681e-06, "loss": 0.001, "step": 380570 }, { "epoch": 91.4, "learning_rate": 4.131107113321414e-06, "loss": 0.0009, "step": 380580 }, { "epoch": 91.4, "learning_rate": 4.1296785196887955e-06, "loss": 0.0009, "step": 380590 }, { "epoch": 91.4, "learning_rate": 4.128250162472208e-06, "loss": 0.0008, "step": 380600 }, { "epoch": 91.41, "learning_rate": 4.126822041678991e-06, "loss": 0.0009, "step": 380610 }, { "epoch": 91.41, "learning_rate": 4.125394157316525e-06, "loss": 0.0009, "step": 380620 }, { "epoch": 91.41, "learning_rate": 4.123966509392158e-06, "loss": 0.0008, "step": 380630 }, { "epoch": 91.41, "learning_rate": 4.122539097913253e-06, "loss": 0.0009, "step": 380640 }, { "epoch": 91.42, "learning_rate": 4.121111922887161e-06, "loss": 0.0009, "step": 380650 }, { "epoch": 91.42, "learning_rate": 4.119684984321243e-06, "loss": 0.0009, "step": 380660 }, { "epoch": 91.42, "learning_rate": 4.118258282222854e-06, "loss": 0.0009, "step": 380670 }, { "epoch": 91.42, "learning_rate": 4.116831816599348e-06, "loss": 0.0009, "step": 380680 }, { "epoch": 91.42, "learning_rate": 4.115405587458071e-06, "loss": 0.001, "step": 380690 }, { "epoch": 91.43, "learning_rate": 4.113979594806377e-06, "loss": 0.0009, "step": 380700 }, { "epoch": 91.43, "learning_rate": 4.112553838651617e-06, "loss": 0.0009, "step": 380710 }, { "epoch": 91.43, "learning_rate": 4.1111283190011395e-06, "loss": 0.0009, "step": 380720 }, { "epoch": 91.43, "learning_rate": 4.109703035862284e-06, "loss": 0.0009, "step": 380730 }, { "epoch": 91.44, "learning_rate": 4.10827798924241e-06, "loss": 0.001, "step": 380740 }, { "epoch": 91.44, "learning_rate": 4.106853179148856e-06, "loss": 0.001, "step": 380750 }, { "epoch": 91.44, "learning_rate": 4.105428605588956e-06, "loss": 0.001, "step": 380760 }, { "epoch": 91.44, "learning_rate": 4.1040042685700665e-06, "loss": 0.0008, "step": 380770 }, { "epoch": 91.44, "learning_rate": 4.102580168099518e-06, "loss": 0.0009, "step": 380780 }, { "epoch": 91.45, "learning_rate": 4.101156304184661e-06, "loss": 0.0008, "step": 380790 }, { "epoch": 91.45, "learning_rate": 4.099732676832818e-06, "loss": 0.0009, "step": 380800 }, { "epoch": 91.45, "learning_rate": 4.098309286051349e-06, "loss": 0.001, "step": 380810 }, { "epoch": 91.45, "learning_rate": 4.096886131847577e-06, "loss": 0.001, "step": 380820 }, { "epoch": 91.46, "learning_rate": 4.095463214228828e-06, "loss": 0.0008, "step": 380830 }, { "epoch": 91.46, "learning_rate": 4.094040533202453e-06, "loss": 0.0008, "step": 380840 }, { "epoch": 91.46, "learning_rate": 4.092618088775768e-06, "loss": 0.0009, "step": 380850 }, { "epoch": 91.46, "learning_rate": 4.0911958809561225e-06, "loss": 0.0009, "step": 380860 }, { "epoch": 91.47, "learning_rate": 4.089773909750827e-06, "loss": 0.001, "step": 380870 }, { "epoch": 91.47, "learning_rate": 4.088352175167232e-06, "loss": 0.001, "step": 380880 }, { "epoch": 91.47, "learning_rate": 4.086930677212642e-06, "loss": 0.0008, "step": 380890 }, { "epoch": 91.47, "learning_rate": 4.085509415894406e-06, "loss": 0.0009, "step": 380900 }, { "epoch": 91.47, "learning_rate": 4.084088391219837e-06, "loss": 0.0009, "step": 380910 }, { "epoch": 91.48, "learning_rate": 4.082667603196255e-06, "loss": 0.0009, "step": 380920 }, { "epoch": 91.48, "learning_rate": 4.081247051830983e-06, "loss": 0.0009, "step": 380930 }, { "epoch": 91.48, "learning_rate": 4.079826737131359e-06, "loss": 0.001, "step": 380940 }, { "epoch": 91.48, "learning_rate": 4.0784066591046834e-06, "loss": 0.0009, "step": 380950 }, { "epoch": 91.49, "learning_rate": 4.0769868177582936e-06, "loss": 0.001, "step": 380960 }, { "epoch": 91.49, "learning_rate": 4.075567213099485e-06, "loss": 0.001, "step": 380970 }, { "epoch": 91.49, "learning_rate": 4.074147845135595e-06, "loss": 0.0009, "step": 380980 }, { "epoch": 91.49, "learning_rate": 4.072728713873925e-06, "loss": 0.0009, "step": 380990 }, { "epoch": 91.5, "learning_rate": 4.071309819321806e-06, "loss": 0.0009, "step": 381000 }, { "epoch": 91.5, "learning_rate": 4.0698911614865275e-06, "loss": 0.0008, "step": 381010 }, { "epoch": 91.5, "learning_rate": 4.068472740375423e-06, "loss": 0.0009, "step": 381020 }, { "epoch": 91.5, "learning_rate": 4.067054555995786e-06, "loss": 0.0008, "step": 381030 }, { "epoch": 91.5, "learning_rate": 4.065636608354944e-06, "loss": 0.0009, "step": 381040 }, { "epoch": 91.51, "learning_rate": 4.064218897460192e-06, "loss": 0.0008, "step": 381050 }, { "epoch": 91.51, "learning_rate": 4.062801423318835e-06, "loss": 0.0009, "step": 381060 }, { "epoch": 91.51, "learning_rate": 4.061384185938188e-06, "loss": 0.0009, "step": 381070 }, { "epoch": 91.51, "learning_rate": 4.059967185325547e-06, "loss": 0.0008, "step": 381080 }, { "epoch": 91.52, "learning_rate": 4.058550421488222e-06, "loss": 0.0009, "step": 381090 }, { "epoch": 91.52, "learning_rate": 4.057133894433507e-06, "loss": 0.0009, "step": 381100 }, { "epoch": 91.52, "learning_rate": 4.055717604168719e-06, "loss": 0.0008, "step": 381110 }, { "epoch": 91.52, "learning_rate": 4.054301550701139e-06, "loss": 0.0009, "step": 381120 }, { "epoch": 91.52, "learning_rate": 4.05288573403807e-06, "loss": 0.0009, "step": 381130 }, { "epoch": 91.53, "learning_rate": 4.051470154186821e-06, "loss": 0.001, "step": 381140 }, { "epoch": 91.53, "learning_rate": 4.050054811154669e-06, "loss": 0.0009, "step": 381150 }, { "epoch": 91.53, "learning_rate": 4.048639704948926e-06, "loss": 0.001, "step": 381160 }, { "epoch": 91.53, "learning_rate": 4.047224835576868e-06, "loss": 0.0009, "step": 381170 }, { "epoch": 91.54, "learning_rate": 4.045810203045808e-06, "loss": 0.0009, "step": 381180 }, { "epoch": 91.54, "learning_rate": 4.044395807363028e-06, "loss": 0.0009, "step": 381190 }, { "epoch": 91.54, "learning_rate": 4.042981648535804e-06, "loss": 0.0011, "step": 381200 }, { "epoch": 91.54, "learning_rate": 4.0415677265714495e-06, "loss": 0.001, "step": 381210 }, { "epoch": 91.55, "learning_rate": 4.040154041477223e-06, "loss": 0.0009, "step": 381220 }, { "epoch": 91.55, "learning_rate": 4.038740593260437e-06, "loss": 0.0008, "step": 381230 }, { "epoch": 91.55, "learning_rate": 4.037327381928369e-06, "loss": 0.0009, "step": 381240 }, { "epoch": 91.55, "learning_rate": 4.035914407488289e-06, "loss": 0.0009, "step": 381250 }, { "epoch": 91.55, "learning_rate": 4.034501669947505e-06, "loss": 0.0008, "step": 381260 }, { "epoch": 91.56, "learning_rate": 4.03308916931327e-06, "loss": 0.0008, "step": 381270 }, { "epoch": 91.56, "learning_rate": 4.03167690559289e-06, "loss": 0.001, "step": 381280 }, { "epoch": 91.56, "learning_rate": 4.030264878793622e-06, "loss": 0.001, "step": 381290 }, { "epoch": 91.56, "learning_rate": 4.0288530889227574e-06, "loss": 0.001, "step": 381300 }, { "epoch": 91.57, "learning_rate": 4.0274415359875635e-06, "loss": 0.001, "step": 381310 }, { "epoch": 91.57, "learning_rate": 4.02603021999533e-06, "loss": 0.003, "step": 381320 }, { "epoch": 91.57, "learning_rate": 4.024619140953318e-06, "loss": 0.001, "step": 381330 }, { "epoch": 91.57, "learning_rate": 4.023208298868797e-06, "loss": 0.0009, "step": 381340 }, { "epoch": 91.58, "learning_rate": 4.021797693749052e-06, "loss": 0.001, "step": 381350 }, { "epoch": 91.58, "learning_rate": 4.020387325601338e-06, "loss": 0.0009, "step": 381360 }, { "epoch": 91.58, "learning_rate": 4.018977194432938e-06, "loss": 0.0009, "step": 381370 }, { "epoch": 91.58, "learning_rate": 4.017567300251107e-06, "loss": 0.001, "step": 381380 }, { "epoch": 91.58, "learning_rate": 4.016157643063129e-06, "loss": 0.0008, "step": 381390 }, { "epoch": 91.59, "learning_rate": 4.014748222876258e-06, "loss": 0.001, "step": 381400 }, { "epoch": 91.59, "learning_rate": 4.01333903969775e-06, "loss": 0.001, "step": 381410 }, { "epoch": 91.59, "learning_rate": 4.011930093534882e-06, "loss": 0.0009, "step": 381420 }, { "epoch": 91.59, "learning_rate": 4.010521384394905e-06, "loss": 0.0009, "step": 381430 }, { "epoch": 91.6, "learning_rate": 4.009112912285096e-06, "loss": 0.0009, "step": 381440 }, { "epoch": 91.6, "learning_rate": 4.007704677212692e-06, "loss": 0.001, "step": 381450 }, { "epoch": 91.6, "learning_rate": 4.006296679184973e-06, "loss": 0.0009, "step": 381460 }, { "epoch": 91.6, "learning_rate": 4.004888918209188e-06, "loss": 0.0009, "step": 381470 }, { "epoch": 91.6, "learning_rate": 4.0034813942925744e-06, "loss": 0.0009, "step": 381480 }, { "epoch": 91.61, "learning_rate": 4.002074107442416e-06, "loss": 0.0009, "step": 381490 }, { "epoch": 91.61, "learning_rate": 4.0006670576659414e-06, "loss": 0.0029, "step": 381500 }, { "epoch": 91.61, "learning_rate": 3.999260244970421e-06, "loss": 0.001, "step": 381510 }, { "epoch": 91.61, "learning_rate": 3.997853669363094e-06, "loss": 0.0009, "step": 381520 }, { "epoch": 91.62, "learning_rate": 3.996447330851216e-06, "loss": 0.001, "step": 381530 }, { "epoch": 91.62, "learning_rate": 3.995041229442031e-06, "loss": 0.001, "step": 381540 }, { "epoch": 91.62, "learning_rate": 3.993635365142784e-06, "loss": 0.0009, "step": 381550 }, { "epoch": 91.62, "learning_rate": 3.992229737960735e-06, "loss": 0.001, "step": 381560 }, { "epoch": 91.63, "learning_rate": 3.990824347903105e-06, "loss": 0.0009, "step": 381570 }, { "epoch": 91.63, "learning_rate": 3.989419194977168e-06, "loss": 0.0009, "step": 381580 }, { "epoch": 91.63, "learning_rate": 3.988014279190133e-06, "loss": 0.001, "step": 381590 }, { "epoch": 91.63, "learning_rate": 3.986609600549268e-06, "loss": 0.0009, "step": 381600 }, { "epoch": 91.63, "learning_rate": 3.9852051590618e-06, "loss": 0.001, "step": 381610 }, { "epoch": 91.64, "learning_rate": 3.983800954734968e-06, "loss": 0.001, "step": 381620 }, { "epoch": 91.64, "learning_rate": 3.982396987576009e-06, "loss": 0.001, "step": 381630 }, { "epoch": 91.64, "learning_rate": 3.980993257592158e-06, "loss": 0.0009, "step": 381640 }, { "epoch": 91.64, "learning_rate": 3.979589764790659e-06, "loss": 0.001, "step": 381650 }, { "epoch": 91.65, "learning_rate": 3.978186509178733e-06, "loss": 0.001, "step": 381660 }, { "epoch": 91.65, "learning_rate": 3.9767834907636246e-06, "loss": 0.001, "step": 381670 }, { "epoch": 91.65, "learning_rate": 3.975380709552562e-06, "loss": 0.001, "step": 381680 }, { "epoch": 91.65, "learning_rate": 3.973978165552761e-06, "loss": 0.001, "step": 381690 }, { "epoch": 91.66, "learning_rate": 3.972575858771466e-06, "loss": 0.0009, "step": 381700 }, { "epoch": 91.66, "learning_rate": 3.971173789215898e-06, "loss": 0.001, "step": 381710 }, { "epoch": 91.66, "learning_rate": 3.969771956893287e-06, "loss": 0.0009, "step": 381720 }, { "epoch": 91.66, "learning_rate": 3.968370361810852e-06, "loss": 0.0009, "step": 381730 }, { "epoch": 91.66, "learning_rate": 3.966969003975829e-06, "loss": 0.0009, "step": 381740 }, { "epoch": 91.67, "learning_rate": 3.9655678833954215e-06, "loss": 0.0009, "step": 381750 }, { "epoch": 91.67, "learning_rate": 3.964167000076874e-06, "loss": 0.0009, "step": 381760 }, { "epoch": 91.67, "learning_rate": 3.9627663540273915e-06, "loss": 0.0009, "step": 381770 }, { "epoch": 91.67, "learning_rate": 3.9613659452541915e-06, "loss": 0.0009, "step": 381780 }, { "epoch": 91.68, "learning_rate": 3.959965773764501e-06, "loss": 0.0009, "step": 381790 }, { "epoch": 91.68, "learning_rate": 3.958565839565526e-06, "loss": 0.0008, "step": 381800 }, { "epoch": 91.68, "learning_rate": 3.9571661426644925e-06, "loss": 0.001, "step": 381810 }, { "epoch": 91.68, "learning_rate": 3.955766683068607e-06, "loss": 0.0009, "step": 381820 }, { "epoch": 91.68, "learning_rate": 3.954367460785086e-06, "loss": 0.001, "step": 381830 }, { "epoch": 91.69, "learning_rate": 3.952968475821133e-06, "loss": 0.0009, "step": 381840 }, { "epoch": 91.69, "learning_rate": 3.951569728183979e-06, "loss": 0.0009, "step": 381850 }, { "epoch": 91.69, "learning_rate": 3.950171217880805e-06, "loss": 0.0011, "step": 381860 }, { "epoch": 91.69, "learning_rate": 3.948772944918838e-06, "loss": 0.0009, "step": 381870 }, { "epoch": 91.7, "learning_rate": 3.94737490930529e-06, "loss": 0.0009, "step": 381880 }, { "epoch": 91.7, "learning_rate": 3.9459771110473446e-06, "loss": 0.0009, "step": 381890 }, { "epoch": 91.7, "learning_rate": 3.944579550152228e-06, "loss": 0.0009, "step": 381900 }, { "epoch": 91.7, "learning_rate": 3.943182226627129e-06, "loss": 0.0009, "step": 381910 }, { "epoch": 91.71, "learning_rate": 3.941785140479249e-06, "loss": 0.001, "step": 381920 }, { "epoch": 91.71, "learning_rate": 3.940388291715802e-06, "loss": 0.0009, "step": 381930 }, { "epoch": 91.71, "learning_rate": 3.938991680343968e-06, "loss": 0.001, "step": 381940 }, { "epoch": 91.71, "learning_rate": 3.937595306370967e-06, "loss": 0.001, "step": 381950 }, { "epoch": 91.71, "learning_rate": 3.936199169803978e-06, "loss": 0.0009, "step": 381960 }, { "epoch": 91.72, "learning_rate": 3.9348032706502115e-06, "loss": 0.0009, "step": 381970 }, { "epoch": 91.72, "learning_rate": 3.9334076089168505e-06, "loss": 0.001, "step": 381980 }, { "epoch": 91.72, "learning_rate": 3.932012184611083e-06, "loss": 0.0009, "step": 381990 }, { "epoch": 91.72, "learning_rate": 3.930616997740122e-06, "loss": 0.0009, "step": 382000 }, { "epoch": 91.73, "learning_rate": 3.929222048311132e-06, "loss": 0.0008, "step": 382010 }, { "epoch": 91.73, "learning_rate": 3.9278273363313304e-06, "loss": 0.0009, "step": 382020 }, { "epoch": 91.73, "learning_rate": 3.926432861807883e-06, "loss": 0.0009, "step": 382030 }, { "epoch": 91.73, "learning_rate": 3.925038624747995e-06, "loss": 0.001, "step": 382040 }, { "epoch": 91.74, "learning_rate": 3.92364462515884e-06, "loss": 0.0009, "step": 382050 }, { "epoch": 91.74, "learning_rate": 3.9222508630476e-06, "loss": 0.001, "step": 382060 }, { "epoch": 91.74, "learning_rate": 3.920857338421468e-06, "loss": 0.0009, "step": 382070 }, { "epoch": 91.74, "learning_rate": 3.919464051287619e-06, "loss": 0.001, "step": 382080 }, { "epoch": 91.74, "learning_rate": 3.918071001653239e-06, "loss": 0.0009, "step": 382090 }, { "epoch": 91.75, "learning_rate": 3.916678189525507e-06, "loss": 0.0009, "step": 382100 }, { "epoch": 91.75, "learning_rate": 3.9152856149116016e-06, "loss": 0.0009, "step": 382110 }, { "epoch": 91.75, "learning_rate": 3.913893277818698e-06, "loss": 0.0011, "step": 382120 }, { "epoch": 91.75, "learning_rate": 3.912501178253974e-06, "loss": 0.0009, "step": 382130 }, { "epoch": 91.76, "learning_rate": 3.9111093162246035e-06, "loss": 0.0009, "step": 382140 }, { "epoch": 91.76, "learning_rate": 3.909717691737763e-06, "loss": 0.0009, "step": 382150 }, { "epoch": 91.76, "learning_rate": 3.908326304800619e-06, "loss": 0.0009, "step": 382160 }, { "epoch": 91.76, "learning_rate": 3.906935155420355e-06, "loss": 0.001, "step": 382170 }, { "epoch": 91.76, "learning_rate": 3.90554424360412e-06, "loss": 0.0009, "step": 382180 }, { "epoch": 91.77, "learning_rate": 3.904153569359103e-06, "loss": 0.0008, "step": 382190 }, { "epoch": 91.77, "learning_rate": 3.902763132692461e-06, "loss": 0.0009, "step": 382200 }, { "epoch": 91.77, "learning_rate": 3.901372933611369e-06, "loss": 0.001, "step": 382210 }, { "epoch": 91.77, "learning_rate": 3.899982972122979e-06, "loss": 0.0009, "step": 382220 }, { "epoch": 91.78, "learning_rate": 3.898593248234467e-06, "loss": 0.0008, "step": 382230 }, { "epoch": 91.78, "learning_rate": 3.897203761952983e-06, "loss": 0.001, "step": 382240 }, { "epoch": 91.78, "learning_rate": 3.895814513285706e-06, "loss": 0.0009, "step": 382250 }, { "epoch": 91.78, "learning_rate": 3.89442550223979e-06, "loss": 0.0009, "step": 382260 }, { "epoch": 91.79, "learning_rate": 3.893036728822374e-06, "loss": 0.0009, "step": 382270 }, { "epoch": 91.79, "learning_rate": 3.891648193040648e-06, "loss": 0.0009, "step": 382280 }, { "epoch": 91.79, "learning_rate": 3.890259894901743e-06, "loss": 0.0009, "step": 382290 }, { "epoch": 91.79, "learning_rate": 3.888871834412827e-06, "loss": 0.0009, "step": 382300 }, { "epoch": 91.79, "learning_rate": 3.8874840115810495e-06, "loss": 0.0009, "step": 382310 }, { "epoch": 91.8, "learning_rate": 3.886096426413566e-06, "loss": 0.0009, "step": 382320 }, { "epoch": 91.8, "learning_rate": 3.884709078917531e-06, "loss": 0.0009, "step": 382330 }, { "epoch": 91.8, "learning_rate": 3.883321969100085e-06, "loss": 0.0009, "step": 382340 }, { "epoch": 91.8, "learning_rate": 3.881935096968387e-06, "loss": 0.001, "step": 382350 }, { "epoch": 91.81, "learning_rate": 3.880548462529576e-06, "loss": 0.0009, "step": 382360 }, { "epoch": 91.81, "learning_rate": 3.879162065790809e-06, "loss": 0.0009, "step": 382370 }, { "epoch": 91.81, "learning_rate": 3.877775906759218e-06, "loss": 0.0009, "step": 382380 }, { "epoch": 91.81, "learning_rate": 3.876389985441964e-06, "loss": 0.0009, "step": 382390 }, { "epoch": 91.82, "learning_rate": 3.8750043018461855e-06, "loss": 0.0009, "step": 382400 }, { "epoch": 91.82, "learning_rate": 3.873618855979006e-06, "loss": 0.0009, "step": 382410 }, { "epoch": 91.82, "learning_rate": 3.872233647847595e-06, "loss": 0.001, "step": 382420 }, { "epoch": 91.82, "learning_rate": 3.870848677459066e-06, "loss": 0.0013, "step": 382430 }, { "epoch": 91.82, "learning_rate": 3.869463944820567e-06, "loss": 0.001, "step": 382440 }, { "epoch": 91.83, "learning_rate": 3.868079449939243e-06, "loss": 0.0009, "step": 382450 }, { "epoch": 91.83, "learning_rate": 3.866695192822223e-06, "loss": 0.001, "step": 382460 }, { "epoch": 91.83, "learning_rate": 3.865311173476643e-06, "loss": 0.0009, "step": 382470 }, { "epoch": 91.83, "learning_rate": 3.863927391909627e-06, "loss": 0.001, "step": 382480 }, { "epoch": 91.84, "learning_rate": 3.862543848128325e-06, "loss": 0.0011, "step": 382490 }, { "epoch": 91.84, "learning_rate": 3.8611605421398525e-06, "loss": 0.001, "step": 382500 }, { "epoch": 91.84, "learning_rate": 3.859777473951348e-06, "loss": 0.001, "step": 382510 }, { "epoch": 91.84, "learning_rate": 3.858394643569929e-06, "loss": 0.001, "step": 382520 }, { "epoch": 91.84, "learning_rate": 3.8570120510027345e-06, "loss": 0.0008, "step": 382530 }, { "epoch": 91.85, "learning_rate": 3.85562969625688e-06, "loss": 0.0009, "step": 382540 }, { "epoch": 91.85, "learning_rate": 3.854247579339504e-06, "loss": 0.0009, "step": 382550 }, { "epoch": 91.85, "learning_rate": 3.852865700257724e-06, "loss": 0.0009, "step": 382560 }, { "epoch": 91.85, "learning_rate": 3.851484059018651e-06, "loss": 0.0009, "step": 382570 }, { "epoch": 91.86, "learning_rate": 3.850102655629423e-06, "loss": 0.0011, "step": 382580 }, { "epoch": 91.86, "learning_rate": 3.84872149009714e-06, "loss": 0.0009, "step": 382590 }, { "epoch": 91.86, "learning_rate": 3.847340562428942e-06, "loss": 0.0011, "step": 382600 }, { "epoch": 91.86, "learning_rate": 3.8459598726319326e-06, "loss": 0.0009, "step": 382610 }, { "epoch": 91.87, "learning_rate": 3.844579420713235e-06, "loss": 0.0009, "step": 382620 }, { "epoch": 91.87, "learning_rate": 3.843199206679965e-06, "loss": 0.001, "step": 382630 }, { "epoch": 91.87, "learning_rate": 3.841819230539218e-06, "loss": 0.0009, "step": 382640 }, { "epoch": 91.87, "learning_rate": 3.840439492298131e-06, "loss": 0.001, "step": 382650 }, { "epoch": 91.87, "learning_rate": 3.8390599919638e-06, "loss": 0.0009, "step": 382660 }, { "epoch": 91.88, "learning_rate": 3.837680729543347e-06, "loss": 0.0009, "step": 382670 }, { "epoch": 91.88, "learning_rate": 3.83630170504386e-06, "loss": 0.0009, "step": 382680 }, { "epoch": 91.88, "learning_rate": 3.834922918472472e-06, "loss": 0.0009, "step": 382690 }, { "epoch": 91.88, "learning_rate": 3.833544369836278e-06, "loss": 0.0009, "step": 382700 }, { "epoch": 91.89, "learning_rate": 3.832166059142373e-06, "loss": 0.0009, "step": 382710 }, { "epoch": 91.89, "learning_rate": 3.830787986397877e-06, "loss": 0.0009, "step": 382720 }, { "epoch": 91.89, "learning_rate": 3.82941015160988e-06, "loss": 0.001, "step": 382730 }, { "epoch": 91.89, "learning_rate": 3.828032554785493e-06, "loss": 0.001, "step": 382740 }, { "epoch": 91.9, "learning_rate": 3.826655195931811e-06, "loss": 0.001, "step": 382750 }, { "epoch": 91.9, "learning_rate": 3.825278075055927e-06, "loss": 0.0009, "step": 382760 }, { "epoch": 91.9, "learning_rate": 3.823901192164958e-06, "loss": 0.001, "step": 382770 }, { "epoch": 91.9, "learning_rate": 3.8225245472659764e-06, "loss": 0.0009, "step": 382780 }, { "epoch": 91.9, "learning_rate": 3.821148140366104e-06, "loss": 0.0018, "step": 382790 }, { "epoch": 91.91, "learning_rate": 3.8197719714724075e-06, "loss": 0.0008, "step": 382800 }, { "epoch": 91.91, "learning_rate": 3.818396040591999e-06, "loss": 0.0009, "step": 382810 }, { "epoch": 91.91, "learning_rate": 3.817020347731959e-06, "loss": 0.0009, "step": 382820 }, { "epoch": 91.91, "learning_rate": 3.815644892899384e-06, "loss": 0.0009, "step": 382830 }, { "epoch": 91.92, "learning_rate": 3.8142696761013676e-06, "loss": 0.001, "step": 382840 }, { "epoch": 91.92, "learning_rate": 3.8128946973449818e-06, "loss": 0.0009, "step": 382850 }, { "epoch": 91.92, "learning_rate": 3.8115199566373273e-06, "loss": 0.001, "step": 382860 }, { "epoch": 91.92, "learning_rate": 3.8101454539854807e-06, "loss": 0.0009, "step": 382870 }, { "epoch": 91.92, "learning_rate": 3.808771189396537e-06, "loss": 0.0009, "step": 382880 }, { "epoch": 91.93, "learning_rate": 3.8073971628775683e-06, "loss": 0.0009, "step": 382890 }, { "epoch": 91.93, "learning_rate": 3.8060233744356633e-06, "loss": 0.0009, "step": 382900 }, { "epoch": 91.93, "learning_rate": 3.804649824077905e-06, "loss": 0.0009, "step": 382910 }, { "epoch": 91.93, "learning_rate": 3.8032765118113543e-06, "loss": 0.0008, "step": 382920 }, { "epoch": 91.94, "learning_rate": 3.8019034376431174e-06, "loss": 0.001, "step": 382930 }, { "epoch": 91.94, "learning_rate": 3.800530601580243e-06, "loss": 0.0008, "step": 382940 }, { "epoch": 91.94, "learning_rate": 3.799158003629827e-06, "loss": 0.0009, "step": 382950 }, { "epoch": 91.94, "learning_rate": 3.7977856437989346e-06, "loss": 0.001, "step": 382960 }, { "epoch": 91.95, "learning_rate": 3.796413522094644e-06, "loss": 0.001, "step": 382970 }, { "epoch": 91.95, "learning_rate": 3.7950416385240272e-06, "loss": 0.0009, "step": 382980 }, { "epoch": 91.95, "learning_rate": 3.7936699930941398e-06, "loss": 0.001, "step": 382990 }, { "epoch": 92.0, "learning_rate": 3.7922985858120763e-06, "loss": 0.001, "step": 383000 }, { "epoch": 92.0, "learning_rate": 3.7909274166848807e-06, "loss": 0.0008, "step": 383010 }, { "epoch": 92.01, "learning_rate": 3.789556485719642e-06, "loss": 0.0009, "step": 383020 }, { "epoch": 92.01, "learning_rate": 3.7881857929234045e-06, "loss": 0.001, "step": 383030 }, { "epoch": 92.01, "learning_rate": 3.7868153383032567e-06, "loss": 0.0009, "step": 383040 }, { "epoch": 92.01, "learning_rate": 3.785445121866238e-06, "loss": 0.0008, "step": 383050 }, { "epoch": 92.01, "learning_rate": 3.78407514361942e-06, "loss": 0.0009, "step": 383060 }, { "epoch": 92.02, "learning_rate": 3.782705403569875e-06, "loss": 0.0009, "step": 383070 }, { "epoch": 92.02, "learning_rate": 3.781335901724642e-06, "loss": 0.001, "step": 383080 }, { "epoch": 92.02, "learning_rate": 3.7799666380908038e-06, "loss": 0.001, "step": 383090 }, { "epoch": 92.02, "learning_rate": 3.7785976126753884e-06, "loss": 0.0009, "step": 383100 }, { "epoch": 92.03, "learning_rate": 3.7772288254854793e-06, "loss": 0.0008, "step": 383110 }, { "epoch": 92.03, "learning_rate": 3.7758602765281204e-06, "loss": 0.001, "step": 383120 }, { "epoch": 92.03, "learning_rate": 3.774491965810356e-06, "loss": 0.0009, "step": 383130 }, { "epoch": 92.03, "learning_rate": 3.7731238933392533e-06, "loss": 0.0009, "step": 383140 }, { "epoch": 92.04, "learning_rate": 3.771756059121845e-06, "loss": 0.0008, "step": 383150 }, { "epoch": 92.04, "learning_rate": 3.770388463165209e-06, "loss": 0.001, "step": 383160 }, { "epoch": 92.04, "learning_rate": 3.7690211054763612e-06, "loss": 0.0009, "step": 383170 }, { "epoch": 92.04, "learning_rate": 3.7676539860623748e-06, "loss": 0.0009, "step": 383180 }, { "epoch": 92.04, "learning_rate": 3.7662871049302883e-06, "loss": 0.0009, "step": 383190 }, { "epoch": 92.05, "learning_rate": 3.7649204620871348e-06, "loss": 0.0008, "step": 383200 }, { "epoch": 92.05, "learning_rate": 3.7635540575399754e-06, "loss": 0.0009, "step": 383210 }, { "epoch": 92.05, "learning_rate": 3.7621878912958377e-06, "loss": 0.001, "step": 383220 }, { "epoch": 92.05, "learning_rate": 3.760821963361777e-06, "loss": 0.0009, "step": 383230 }, { "epoch": 92.06, "learning_rate": 3.7594562737448213e-06, "loss": 0.0009, "step": 383240 }, { "epoch": 92.06, "learning_rate": 3.7580908224520204e-06, "loss": 0.0009, "step": 383250 }, { "epoch": 92.06, "learning_rate": 3.756725609490408e-06, "loss": 0.0009, "step": 383260 }, { "epoch": 92.06, "learning_rate": 3.7553606348670058e-06, "loss": 0.0009, "step": 383270 }, { "epoch": 92.06, "learning_rate": 3.7539958985888744e-06, "loss": 0.0009, "step": 383280 }, { "epoch": 92.07, "learning_rate": 3.752631400663026e-06, "loss": 0.0009, "step": 383290 }, { "epoch": 92.07, "learning_rate": 3.751267141096504e-06, "loss": 0.0008, "step": 383300 }, { "epoch": 92.07, "learning_rate": 3.7499031198963365e-06, "loss": 0.0009, "step": 383310 }, { "epoch": 92.07, "learning_rate": 3.7485393370695622e-06, "loss": 0.001, "step": 383320 }, { "epoch": 92.08, "learning_rate": 3.747175792623192e-06, "loss": 0.0009, "step": 383330 }, { "epoch": 92.08, "learning_rate": 3.745812486564271e-06, "loss": 0.0008, "step": 383340 }, { "epoch": 92.08, "learning_rate": 3.7444494188998145e-06, "loss": 0.0009, "step": 383350 }, { "epoch": 92.08, "learning_rate": 3.7430865896368626e-06, "loss": 0.0009, "step": 383360 }, { "epoch": 92.09, "learning_rate": 3.741723998782415e-06, "loss": 0.0008, "step": 383370 }, { "epoch": 92.09, "learning_rate": 3.7403616463435098e-06, "loss": 0.0009, "step": 383380 }, { "epoch": 92.09, "learning_rate": 3.738999532327181e-06, "loss": 0.001, "step": 383390 }, { "epoch": 92.09, "learning_rate": 3.7376376567404227e-06, "loss": 0.001, "step": 383400 }, { "epoch": 92.09, "learning_rate": 3.7362760195902736e-06, "loss": 0.0009, "step": 383410 }, { "epoch": 92.1, "learning_rate": 3.7349146208837447e-06, "loss": 0.0009, "step": 383420 }, { "epoch": 92.1, "learning_rate": 3.733553460627848e-06, "loss": 0.0008, "step": 383430 }, { "epoch": 92.1, "learning_rate": 3.7321925388296098e-06, "loss": 0.0008, "step": 383440 }, { "epoch": 92.1, "learning_rate": 3.730831855496031e-06, "loss": 0.0009, "step": 383450 }, { "epoch": 92.11, "learning_rate": 3.7294714106341387e-06, "loss": 0.0009, "step": 383460 }, { "epoch": 92.11, "learning_rate": 3.728111204250928e-06, "loss": 0.0009, "step": 383470 }, { "epoch": 92.11, "learning_rate": 3.7267512363534264e-06, "loss": 0.0009, "step": 383480 }, { "epoch": 92.11, "learning_rate": 3.725391506948639e-06, "loss": 0.001, "step": 383490 }, { "epoch": 92.12, "learning_rate": 3.7240320160435603e-06, "loss": 0.0009, "step": 383500 }, { "epoch": 92.12, "learning_rate": 3.722672763645213e-06, "loss": 0.0009, "step": 383510 }, { "epoch": 92.12, "learning_rate": 3.7213137497605967e-06, "loss": 0.0009, "step": 383520 }, { "epoch": 92.12, "learning_rate": 3.7199549743967167e-06, "loss": 0.0009, "step": 383530 }, { "epoch": 92.12, "learning_rate": 3.718596437560573e-06, "loss": 0.0009, "step": 383540 }, { "epoch": 92.13, "learning_rate": 3.7172381392591715e-06, "loss": 0.0009, "step": 383550 }, { "epoch": 92.13, "learning_rate": 3.7158800794995175e-06, "loss": 0.0009, "step": 383560 }, { "epoch": 92.13, "learning_rate": 3.714522258288594e-06, "loss": 0.0009, "step": 383570 }, { "epoch": 92.13, "learning_rate": 3.713164675633418e-06, "loss": 0.0009, "step": 383580 }, { "epoch": 92.14, "learning_rate": 3.711807331540973e-06, "loss": 0.0009, "step": 383590 }, { "epoch": 92.14, "learning_rate": 3.7104502260182637e-06, "loss": 0.0008, "step": 383600 }, { "epoch": 92.14, "learning_rate": 3.7090933590722743e-06, "loss": 0.0009, "step": 383610 }, { "epoch": 92.14, "learning_rate": 3.7077367307100153e-06, "loss": 0.001, "step": 383620 }, { "epoch": 92.14, "learning_rate": 3.7063803409384533e-06, "loss": 0.0009, "step": 383630 }, { "epoch": 92.15, "learning_rate": 3.7050241897646108e-06, "loss": 0.0009, "step": 383640 }, { "epoch": 92.15, "learning_rate": 3.7036682771954433e-06, "loss": 0.0008, "step": 383650 }, { "epoch": 92.15, "learning_rate": 3.702312603237973e-06, "loss": 0.0009, "step": 383660 }, { "epoch": 92.15, "learning_rate": 3.700957167899155e-06, "loss": 0.0009, "step": 383670 }, { "epoch": 92.16, "learning_rate": 3.6996019711860065e-06, "loss": 0.0009, "step": 383680 }, { "epoch": 92.16, "learning_rate": 3.6982470131054825e-06, "loss": 0.0009, "step": 383690 }, { "epoch": 92.16, "learning_rate": 3.696892293664589e-06, "loss": 0.0009, "step": 383700 }, { "epoch": 92.16, "learning_rate": 3.695537812870298e-06, "loss": 0.0008, "step": 383710 }, { "epoch": 92.17, "learning_rate": 3.6941835707295923e-06, "loss": 0.0009, "step": 383720 }, { "epoch": 92.17, "learning_rate": 3.692829567249445e-06, "loss": 0.0009, "step": 383730 }, { "epoch": 92.17, "learning_rate": 3.6914758024368503e-06, "loss": 0.0009, "step": 383740 }, { "epoch": 92.17, "learning_rate": 3.690122276298769e-06, "loss": 0.0009, "step": 383750 }, { "epoch": 92.17, "learning_rate": 3.688768988842195e-06, "loss": 0.001, "step": 383760 }, { "epoch": 92.18, "learning_rate": 3.6874159400740902e-06, "loss": 0.0009, "step": 383770 }, { "epoch": 92.18, "learning_rate": 3.6860631300014214e-06, "loss": 0.0008, "step": 383780 }, { "epoch": 92.18, "learning_rate": 3.6847105586311827e-06, "loss": 0.0008, "step": 383790 }, { "epoch": 92.18, "learning_rate": 3.683358225970318e-06, "loss": 0.0009, "step": 383800 }, { "epoch": 92.19, "learning_rate": 3.6820061320258225e-06, "loss": 0.0009, "step": 383810 }, { "epoch": 92.19, "learning_rate": 3.6806542768046516e-06, "loss": 0.0009, "step": 383820 }, { "epoch": 92.19, "learning_rate": 3.679302660313777e-06, "loss": 0.0009, "step": 383830 }, { "epoch": 92.19, "learning_rate": 3.6779512825601715e-06, "loss": 0.0009, "step": 383840 }, { "epoch": 92.2, "learning_rate": 3.6766001435507792e-06, "loss": 0.0009, "step": 383850 }, { "epoch": 92.2, "learning_rate": 3.6752492432925834e-06, "loss": 0.0009, "step": 383860 }, { "epoch": 92.2, "learning_rate": 3.6738985817925343e-06, "loss": 0.0016, "step": 383870 }, { "epoch": 92.2, "learning_rate": 3.6725481590576096e-06, "loss": 0.001, "step": 383880 }, { "epoch": 92.2, "learning_rate": 3.671197975094748e-06, "loss": 0.0008, "step": 383890 }, { "epoch": 92.21, "learning_rate": 3.6698480299109272e-06, "loss": 0.0009, "step": 383900 }, { "epoch": 92.21, "learning_rate": 3.6684983235130975e-06, "loss": 0.0009, "step": 383910 }, { "epoch": 92.21, "learning_rate": 3.6671488559082034e-06, "loss": 0.001, "step": 383920 }, { "epoch": 92.21, "learning_rate": 3.6657996271032225e-06, "loss": 0.0008, "step": 383930 }, { "epoch": 92.22, "learning_rate": 3.6644506371050937e-06, "loss": 0.0008, "step": 383940 }, { "epoch": 92.22, "learning_rate": 3.663101885920767e-06, "loss": 0.0009, "step": 383950 }, { "epoch": 92.22, "learning_rate": 3.6617533735572083e-06, "loss": 0.0009, "step": 383960 }, { "epoch": 92.22, "learning_rate": 3.660405100021358e-06, "loss": 0.0009, "step": 383970 }, { "epoch": 92.22, "learning_rate": 3.6590570653201707e-06, "loss": 0.001, "step": 383980 }, { "epoch": 92.23, "learning_rate": 3.6577092694605854e-06, "loss": 0.0008, "step": 383990 }, { "epoch": 92.23, "learning_rate": 3.6563617124495575e-06, "loss": 0.0011, "step": 384000 }, { "epoch": 92.23, "learning_rate": 3.6550143942940264e-06, "loss": 0.0009, "step": 384010 }, { "epoch": 92.23, "learning_rate": 3.6536673150009415e-06, "loss": 0.0009, "step": 384020 }, { "epoch": 92.24, "learning_rate": 3.6523204745772365e-06, "loss": 0.0008, "step": 384030 }, { "epoch": 92.24, "learning_rate": 3.650973873029867e-06, "loss": 0.001, "step": 384040 }, { "epoch": 92.24, "learning_rate": 3.6496275103657664e-06, "loss": 0.0009, "step": 384050 }, { "epoch": 92.24, "learning_rate": 3.6482813865918676e-06, "loss": 0.0008, "step": 384060 }, { "epoch": 92.25, "learning_rate": 3.646935501715121e-06, "loss": 0.0009, "step": 384070 }, { "epoch": 92.25, "learning_rate": 3.645589855742443e-06, "loss": 0.0009, "step": 384080 }, { "epoch": 92.25, "learning_rate": 3.6442444486807948e-06, "loss": 0.0009, "step": 384090 }, { "epoch": 92.25, "learning_rate": 3.6428992805370877e-06, "loss": 0.001, "step": 384100 }, { "epoch": 92.25, "learning_rate": 3.641554351318277e-06, "loss": 0.0009, "step": 384110 }, { "epoch": 92.26, "learning_rate": 3.6402096610312743e-06, "loss": 0.0009, "step": 384120 }, { "epoch": 92.26, "learning_rate": 3.6388652096830236e-06, "loss": 0.0009, "step": 384130 }, { "epoch": 92.26, "learning_rate": 3.637520997280447e-06, "loss": 0.001, "step": 384140 }, { "epoch": 92.26, "learning_rate": 3.636177023830473e-06, "loss": 0.0009, "step": 384150 }, { "epoch": 92.27, "learning_rate": 3.634833289340034e-06, "loss": 0.0009, "step": 384160 }, { "epoch": 92.27, "learning_rate": 3.633489793816042e-06, "loss": 0.0021, "step": 384170 }, { "epoch": 92.27, "learning_rate": 3.6321465372654462e-06, "loss": 0.0009, "step": 384180 }, { "epoch": 92.27, "learning_rate": 3.630803519695142e-06, "loss": 0.0009, "step": 384190 }, { "epoch": 92.28, "learning_rate": 3.629460741112073e-06, "loss": 0.0008, "step": 384200 }, { "epoch": 92.28, "learning_rate": 3.6281182015231452e-06, "loss": 0.0008, "step": 384210 }, { "epoch": 92.28, "learning_rate": 3.626775900935281e-06, "loss": 0.0008, "step": 384220 }, { "epoch": 92.28, "learning_rate": 3.6254338393554134e-06, "loss": 0.0009, "step": 384230 }, { "epoch": 92.28, "learning_rate": 3.6240920167904312e-06, "loss": 0.0008, "step": 384240 }, { "epoch": 92.29, "learning_rate": 3.6227504332472794e-06, "loss": 0.0009, "step": 384250 }, { "epoch": 92.29, "learning_rate": 3.621409088732852e-06, "loss": 0.0009, "step": 384260 }, { "epoch": 92.29, "learning_rate": 3.6200679832540716e-06, "loss": 0.0008, "step": 384270 }, { "epoch": 92.29, "learning_rate": 3.6187271168178496e-06, "loss": 0.0008, "step": 384280 }, { "epoch": 92.3, "learning_rate": 3.6173864894310905e-06, "loss": 0.0009, "step": 384290 }, { "epoch": 92.3, "learning_rate": 3.616046101100723e-06, "loss": 0.001, "step": 384300 }, { "epoch": 92.3, "learning_rate": 3.6147059518336244e-06, "loss": 0.0009, "step": 384310 }, { "epoch": 92.3, "learning_rate": 3.6133660416367345e-06, "loss": 0.0009, "step": 384320 }, { "epoch": 92.3, "learning_rate": 3.61202637051693e-06, "loss": 0.0009, "step": 384330 }, { "epoch": 92.31, "learning_rate": 3.6106869384811446e-06, "loss": 0.0009, "step": 384340 }, { "epoch": 92.31, "learning_rate": 3.6093477455362623e-06, "loss": 0.0009, "step": 384350 }, { "epoch": 92.31, "learning_rate": 3.6080087916891767e-06, "loss": 0.001, "step": 384360 }, { "epoch": 92.31, "learning_rate": 3.6066700769468164e-06, "loss": 0.001, "step": 384370 }, { "epoch": 92.32, "learning_rate": 3.605331601316053e-06, "loss": 0.0009, "step": 384380 }, { "epoch": 92.32, "learning_rate": 3.6039933648038095e-06, "loss": 0.0008, "step": 384390 }, { "epoch": 92.32, "learning_rate": 3.6026553674169683e-06, "loss": 0.0009, "step": 384400 }, { "epoch": 92.32, "learning_rate": 3.60131760916243e-06, "loss": 0.0009, "step": 384410 }, { "epoch": 92.33, "learning_rate": 3.5999800900470893e-06, "loss": 0.0009, "step": 384420 }, { "epoch": 92.33, "learning_rate": 3.5986428100778345e-06, "loss": 0.0009, "step": 384430 }, { "epoch": 92.33, "learning_rate": 3.5973057692615717e-06, "loss": 0.0009, "step": 384440 }, { "epoch": 92.33, "learning_rate": 3.595968967605168e-06, "loss": 0.0009, "step": 384450 }, { "epoch": 92.33, "learning_rate": 3.5946324051155446e-06, "loss": 0.0009, "step": 384460 }, { "epoch": 92.34, "learning_rate": 3.5932960817995576e-06, "loss": 0.0009, "step": 384470 }, { "epoch": 92.34, "learning_rate": 3.591959997664124e-06, "loss": 0.0008, "step": 384480 }, { "epoch": 92.34, "learning_rate": 3.5906241527161155e-06, "loss": 0.0008, "step": 384490 }, { "epoch": 92.34, "learning_rate": 3.5892885469624105e-06, "loss": 0.0009, "step": 384500 }, { "epoch": 92.35, "learning_rate": 3.587953180409903e-06, "loss": 0.0009, "step": 384510 }, { "epoch": 92.35, "learning_rate": 3.5866180530654712e-06, "loss": 0.0009, "step": 384520 }, { "epoch": 92.35, "learning_rate": 3.585283164936004e-06, "loss": 0.0009, "step": 384530 }, { "epoch": 92.35, "learning_rate": 3.5839485160283624e-06, "loss": 0.0008, "step": 384540 }, { "epoch": 92.36, "learning_rate": 3.5826141063494523e-06, "loss": 0.0009, "step": 384550 }, { "epoch": 92.36, "learning_rate": 3.581279935906129e-06, "loss": 0.0008, "step": 384560 }, { "epoch": 92.36, "learning_rate": 3.5799460047052814e-06, "loss": 0.0009, "step": 384570 }, { "epoch": 92.36, "learning_rate": 3.5786123127537764e-06, "loss": 0.0008, "step": 384580 }, { "epoch": 92.36, "learning_rate": 3.577278860058486e-06, "loss": 0.0009, "step": 384590 }, { "epoch": 92.37, "learning_rate": 3.5759456466262997e-06, "loss": 0.0009, "step": 384600 }, { "epoch": 92.37, "learning_rate": 3.5746126724640727e-06, "loss": 0.0009, "step": 384610 }, { "epoch": 92.37, "learning_rate": 3.573279937578683e-06, "loss": 0.0009, "step": 384620 }, { "epoch": 92.37, "learning_rate": 3.571947441976997e-06, "loss": 0.001, "step": 384630 }, { "epoch": 92.38, "learning_rate": 3.5706151856658764e-06, "loss": 0.0008, "step": 384640 }, { "epoch": 92.38, "learning_rate": 3.5692831686521986e-06, "loss": 0.0009, "step": 384650 }, { "epoch": 92.38, "learning_rate": 3.5679513909428197e-06, "loss": 0.001, "step": 384660 }, { "epoch": 92.38, "learning_rate": 3.5666198525446116e-06, "loss": 0.0009, "step": 384670 }, { "epoch": 92.38, "learning_rate": 3.565288553464424e-06, "loss": 0.0009, "step": 384680 }, { "epoch": 92.39, "learning_rate": 3.5639574937091414e-06, "loss": 0.0009, "step": 384690 }, { "epoch": 92.39, "learning_rate": 3.562626673285602e-06, "loss": 0.0009, "step": 384700 }, { "epoch": 92.39, "learning_rate": 3.561296092200672e-06, "loss": 0.0009, "step": 384710 }, { "epoch": 92.39, "learning_rate": 3.559965750461214e-06, "loss": 0.0009, "step": 384720 }, { "epoch": 92.4, "learning_rate": 3.558635648074071e-06, "loss": 0.0008, "step": 384730 }, { "epoch": 92.4, "learning_rate": 3.557305785046122e-06, "loss": 0.0008, "step": 384740 }, { "epoch": 92.4, "learning_rate": 3.555976161384195e-06, "loss": 0.0008, "step": 384750 }, { "epoch": 92.4, "learning_rate": 3.5546467770951607e-06, "loss": 0.0009, "step": 384760 }, { "epoch": 92.41, "learning_rate": 3.5533176321858707e-06, "loss": 0.0009, "step": 384770 }, { "epoch": 92.41, "learning_rate": 3.5519887266631578e-06, "loss": 0.0031, "step": 384780 }, { "epoch": 92.41, "learning_rate": 3.5506600605338947e-06, "loss": 0.0008, "step": 384790 }, { "epoch": 92.41, "learning_rate": 3.5493316338049086e-06, "loss": 0.0009, "step": 384800 }, { "epoch": 92.41, "learning_rate": 3.5480034464830614e-06, "loss": 0.0011, "step": 384810 }, { "epoch": 92.42, "learning_rate": 3.546675498575186e-06, "loss": 0.0009, "step": 384820 }, { "epoch": 92.42, "learning_rate": 3.5453477900881436e-06, "loss": 0.001, "step": 384830 }, { "epoch": 92.42, "learning_rate": 3.544020321028757e-06, "loss": 0.0008, "step": 384840 }, { "epoch": 92.42, "learning_rate": 3.542693091403887e-06, "loss": 0.0009, "step": 384850 }, { "epoch": 92.43, "learning_rate": 3.541366101220356e-06, "loss": 0.0009, "step": 384860 }, { "epoch": 92.43, "learning_rate": 3.5400393504850193e-06, "loss": 0.0009, "step": 384870 }, { "epoch": 92.43, "learning_rate": 3.538712839204705e-06, "loss": 0.0008, "step": 384880 }, { "epoch": 92.43, "learning_rate": 3.5373865673862473e-06, "loss": 0.0008, "step": 384890 }, { "epoch": 92.44, "learning_rate": 3.5360605350365008e-06, "loss": 0.0009, "step": 384900 }, { "epoch": 92.44, "learning_rate": 3.5347347421622825e-06, "loss": 0.0009, "step": 384910 }, { "epoch": 92.44, "learning_rate": 3.5334091887704203e-06, "loss": 0.0009, "step": 384920 }, { "epoch": 92.44, "learning_rate": 3.5320838748677698e-06, "loss": 0.0009, "step": 384930 }, { "epoch": 92.44, "learning_rate": 3.5307588004611313e-06, "loss": 0.0009, "step": 384940 }, { "epoch": 92.45, "learning_rate": 3.529433965557366e-06, "loss": 0.0008, "step": 384950 }, { "epoch": 92.45, "learning_rate": 3.528109370163274e-06, "loss": 0.001, "step": 384960 }, { "epoch": 92.45, "learning_rate": 3.526785014285705e-06, "loss": 0.0009, "step": 384970 }, { "epoch": 92.45, "learning_rate": 3.525460897931465e-06, "loss": 0.0009, "step": 384980 }, { "epoch": 92.46, "learning_rate": 3.524137021107399e-06, "loss": 0.001, "step": 384990 }, { "epoch": 92.46, "learning_rate": 3.522813383820317e-06, "loss": 0.0009, "step": 385000 }, { "epoch": 92.46, "learning_rate": 3.5214899860770368e-06, "loss": 0.0009, "step": 385010 }, { "epoch": 92.46, "learning_rate": 3.520166827884391e-06, "loss": 0.001, "step": 385020 }, { "epoch": 92.46, "learning_rate": 3.5188439092491865e-06, "loss": 0.0009, "step": 385030 }, { "epoch": 92.47, "learning_rate": 3.5175212301782555e-06, "loss": 0.0023, "step": 385040 }, { "epoch": 92.47, "learning_rate": 3.5161987906784043e-06, "loss": 0.0008, "step": 385050 }, { "epoch": 92.47, "learning_rate": 3.5148765907564606e-06, "loss": 0.0009, "step": 385060 }, { "epoch": 92.47, "learning_rate": 3.51355463041923e-06, "loss": 0.0009, "step": 385070 }, { "epoch": 92.48, "learning_rate": 3.5122329096735185e-06, "loss": 0.0008, "step": 385080 }, { "epoch": 92.48, "learning_rate": 3.510911428526159e-06, "loss": 0.0009, "step": 385090 }, { "epoch": 92.48, "learning_rate": 3.5095901869839355e-06, "loss": 0.0009, "step": 385100 }, { "epoch": 92.48, "learning_rate": 3.5082691850536865e-06, "loss": 0.0008, "step": 385110 }, { "epoch": 92.49, "learning_rate": 3.506948422742201e-06, "loss": 0.001, "step": 385120 }, { "epoch": 92.49, "learning_rate": 3.5056279000562963e-06, "loss": 0.001, "step": 385130 }, { "epoch": 92.49, "learning_rate": 3.5043076170027724e-06, "loss": 0.002, "step": 385140 }, { "epoch": 92.49, "learning_rate": 3.5029875735884286e-06, "loss": 0.0009, "step": 385150 }, { "epoch": 92.49, "learning_rate": 3.501667769820077e-06, "loss": 0.001, "step": 385160 }, { "epoch": 92.5, "learning_rate": 3.500348205704529e-06, "loss": 0.0008, "step": 385170 }, { "epoch": 92.5, "learning_rate": 3.4990288812485617e-06, "loss": 0.0008, "step": 385180 }, { "epoch": 92.5, "learning_rate": 3.4977097964589978e-06, "loss": 0.0008, "step": 385190 }, { "epoch": 92.5, "learning_rate": 3.4963909513426206e-06, "loss": 0.0009, "step": 385200 }, { "epoch": 92.51, "learning_rate": 3.495072345906236e-06, "loss": 0.0009, "step": 385210 }, { "epoch": 92.51, "learning_rate": 3.493753980156633e-06, "loss": 0.0008, "step": 385220 }, { "epoch": 92.51, "learning_rate": 3.4924358541006174e-06, "loss": 0.0009, "step": 385230 }, { "epoch": 92.51, "learning_rate": 3.4911179677449722e-06, "loss": 0.0008, "step": 385240 }, { "epoch": 92.52, "learning_rate": 3.489800321096498e-06, "loss": 0.0009, "step": 385250 }, { "epoch": 92.52, "learning_rate": 3.4884829141619724e-06, "loss": 0.001, "step": 385260 }, { "epoch": 92.52, "learning_rate": 3.4871657469482067e-06, "loss": 0.001, "step": 385270 }, { "epoch": 92.52, "learning_rate": 3.4858488194619734e-06, "loss": 0.0009, "step": 385280 }, { "epoch": 92.52, "learning_rate": 3.484532131710061e-06, "loss": 0.0008, "step": 385290 }, { "epoch": 92.53, "learning_rate": 3.483215683699265e-06, "loss": 0.001, "step": 385300 }, { "epoch": 92.53, "learning_rate": 3.4818994754363566e-06, "loss": 0.0009, "step": 385310 }, { "epoch": 92.53, "learning_rate": 3.480583506928131e-06, "loss": 0.0009, "step": 385320 }, { "epoch": 92.53, "learning_rate": 3.479267778181361e-06, "loss": 0.0009, "step": 385330 }, { "epoch": 92.54, "learning_rate": 3.4779522892028403e-06, "loss": 0.001, "step": 385340 }, { "epoch": 92.54, "learning_rate": 3.4766370399993474e-06, "loss": 0.0008, "step": 385350 }, { "epoch": 92.54, "learning_rate": 3.4753220305776435e-06, "loss": 0.0009, "step": 385360 }, { "epoch": 92.54, "learning_rate": 3.4740072609445283e-06, "loss": 0.0009, "step": 385370 }, { "epoch": 92.54, "learning_rate": 3.4726927311067636e-06, "loss": 0.0009, "step": 385380 }, { "epoch": 92.55, "learning_rate": 3.4713784410711325e-06, "loss": 0.0009, "step": 385390 }, { "epoch": 92.55, "learning_rate": 3.470064390844402e-06, "loss": 0.001, "step": 385400 }, { "epoch": 92.55, "learning_rate": 3.4687505804333497e-06, "loss": 0.0009, "step": 385410 }, { "epoch": 92.55, "learning_rate": 3.467437009844754e-06, "loss": 0.001, "step": 385420 }, { "epoch": 92.56, "learning_rate": 3.4661236790853646e-06, "loss": 0.0009, "step": 385430 }, { "epoch": 92.56, "learning_rate": 3.4648105881619706e-06, "loss": 0.0009, "step": 385440 }, { "epoch": 92.56, "learning_rate": 3.4634977370813225e-06, "loss": 0.001, "step": 385450 }, { "epoch": 92.56, "learning_rate": 3.4621851258502036e-06, "loss": 0.001, "step": 385460 }, { "epoch": 92.57, "learning_rate": 3.4608727544753695e-06, "loss": 0.0009, "step": 385470 }, { "epoch": 92.57, "learning_rate": 3.4595606229635868e-06, "loss": 0.0008, "step": 385480 }, { "epoch": 92.57, "learning_rate": 3.4582487313216227e-06, "loss": 0.001, "step": 385490 }, { "epoch": 92.57, "learning_rate": 3.456937079556222e-06, "loss": 0.0009, "step": 385500 }, { "epoch": 92.57, "learning_rate": 3.455625667674167e-06, "loss": 0.0008, "step": 385510 }, { "epoch": 92.58, "learning_rate": 3.454314495682198e-06, "loss": 0.0009, "step": 385520 }, { "epoch": 92.58, "learning_rate": 3.4530035635870926e-06, "loss": 0.0009, "step": 385530 }, { "epoch": 92.58, "learning_rate": 3.4516928713955843e-06, "loss": 0.001, "step": 385540 }, { "epoch": 92.58, "learning_rate": 3.4503824191144506e-06, "loss": 0.001, "step": 385550 }, { "epoch": 92.59, "learning_rate": 3.4490722067504313e-06, "loss": 0.001, "step": 385560 }, { "epoch": 92.59, "learning_rate": 3.4477622343102756e-06, "loss": 0.001, "step": 385570 }, { "epoch": 92.59, "learning_rate": 3.446452501800751e-06, "loss": 0.0009, "step": 385580 }, { "epoch": 92.59, "learning_rate": 3.4451430092285963e-06, "loss": 0.0009, "step": 385590 }, { "epoch": 92.6, "learning_rate": 3.4438337566005675e-06, "loss": 0.0009, "step": 385600 }, { "epoch": 92.6, "learning_rate": 3.4425247439233978e-06, "loss": 0.0009, "step": 385610 }, { "epoch": 92.6, "learning_rate": 3.4412159712038594e-06, "loss": 0.001, "step": 385620 }, { "epoch": 92.6, "learning_rate": 3.439907438448675e-06, "loss": 0.0009, "step": 385630 }, { "epoch": 92.6, "learning_rate": 3.438599145664595e-06, "loss": 0.0009, "step": 385640 }, { "epoch": 92.61, "learning_rate": 3.437291092858369e-06, "loss": 0.0009, "step": 385650 }, { "epoch": 92.61, "learning_rate": 3.435983280036731e-06, "loss": 0.0009, "step": 385660 }, { "epoch": 92.61, "learning_rate": 3.434675707206425e-06, "loss": 0.0009, "step": 385670 }, { "epoch": 92.61, "learning_rate": 3.433368374374185e-06, "loss": 0.0009, "step": 385680 }, { "epoch": 92.62, "learning_rate": 3.4320612815467612e-06, "loss": 0.001, "step": 385690 }, { "epoch": 92.62, "learning_rate": 3.4307544287308866e-06, "loss": 0.0011, "step": 385700 }, { "epoch": 92.62, "learning_rate": 3.4294478159332788e-06, "loss": 0.0009, "step": 385710 }, { "epoch": 92.62, "learning_rate": 3.4281414431606986e-06, "loss": 0.001, "step": 385720 }, { "epoch": 92.62, "learning_rate": 3.426835310419857e-06, "loss": 0.0009, "step": 385730 }, { "epoch": 92.63, "learning_rate": 3.4255294177175046e-06, "loss": 0.001, "step": 385740 }, { "epoch": 92.63, "learning_rate": 3.4242237650603527e-06, "loss": 0.0009, "step": 385750 }, { "epoch": 92.63, "learning_rate": 3.422918352455151e-06, "loss": 0.0009, "step": 385760 }, { "epoch": 92.63, "learning_rate": 3.4216131799086114e-06, "loss": 0.0008, "step": 385770 }, { "epoch": 92.64, "learning_rate": 3.4203082474274616e-06, "loss": 0.0009, "step": 385780 }, { "epoch": 92.64, "learning_rate": 3.4190035550184463e-06, "loss": 0.0009, "step": 385790 }, { "epoch": 92.64, "learning_rate": 3.4176991026882653e-06, "loss": 0.001, "step": 385800 }, { "epoch": 92.64, "learning_rate": 3.4163948904436584e-06, "loss": 0.0008, "step": 385810 }, { "epoch": 92.65, "learning_rate": 3.415090918291336e-06, "loss": 0.001, "step": 385820 }, { "epoch": 92.65, "learning_rate": 3.413787186238032e-06, "loss": 0.0009, "step": 385830 }, { "epoch": 92.65, "learning_rate": 3.412483694290447e-06, "loss": 0.001, "step": 385840 }, { "epoch": 92.65, "learning_rate": 3.4111804424553196e-06, "loss": 0.001, "step": 385850 }, { "epoch": 92.65, "learning_rate": 3.409877430739361e-06, "loss": 0.0009, "step": 385860 }, { "epoch": 92.66, "learning_rate": 3.4085746591492772e-06, "loss": 0.0009, "step": 385870 }, { "epoch": 92.66, "learning_rate": 3.4072721276917906e-06, "loss": 0.0009, "step": 385880 }, { "epoch": 92.66, "learning_rate": 3.405969836373607e-06, "loss": 0.001, "step": 385890 }, { "epoch": 92.66, "learning_rate": 3.404667785201454e-06, "loss": 0.0009, "step": 385900 }, { "epoch": 92.67, "learning_rate": 3.403365974182027e-06, "loss": 0.0009, "step": 385910 }, { "epoch": 92.67, "learning_rate": 3.4020644033220417e-06, "loss": 0.0008, "step": 385920 }, { "epoch": 92.67, "learning_rate": 3.400763072628216e-06, "loss": 0.0009, "step": 385930 }, { "epoch": 92.67, "learning_rate": 3.399461982107233e-06, "loss": 0.0009, "step": 385940 }, { "epoch": 92.68, "learning_rate": 3.3981611317658203e-06, "loss": 0.0009, "step": 385950 }, { "epoch": 92.68, "learning_rate": 3.3968605216106674e-06, "loss": 0.0008, "step": 385960 }, { "epoch": 92.68, "learning_rate": 3.3955601516484915e-06, "loss": 0.0009, "step": 385970 }, { "epoch": 92.68, "learning_rate": 3.394260021885981e-06, "loss": 0.0009, "step": 385980 }, { "epoch": 92.68, "learning_rate": 3.392960132329853e-06, "loss": 0.0008, "step": 385990 }, { "epoch": 92.69, "learning_rate": 3.391660482986797e-06, "loss": 0.0009, "step": 386000 }, { "epoch": 92.69, "learning_rate": 3.3903610738635072e-06, "loss": 0.001, "step": 386010 }, { "epoch": 92.69, "learning_rate": 3.3890619049666892e-06, "loss": 0.0008, "step": 386020 }, { "epoch": 92.69, "learning_rate": 3.3877629763030328e-06, "loss": 0.001, "step": 386030 }, { "epoch": 92.7, "learning_rate": 3.3864642878792374e-06, "loss": 0.0009, "step": 386040 }, { "epoch": 92.7, "learning_rate": 3.3851658397019926e-06, "loss": 0.001, "step": 386050 }, { "epoch": 92.7, "learning_rate": 3.3838676317779984e-06, "loss": 0.0008, "step": 386060 }, { "epoch": 92.7, "learning_rate": 3.382569664113933e-06, "loss": 0.0009, "step": 386070 }, { "epoch": 92.7, "learning_rate": 3.381271936716496e-06, "loss": 0.0009, "step": 386080 }, { "epoch": 92.71, "learning_rate": 3.3799744495923714e-06, "loss": 0.0009, "step": 386090 }, { "epoch": 92.71, "learning_rate": 3.378677202748248e-06, "loss": 0.0008, "step": 386100 }, { "epoch": 92.71, "learning_rate": 3.377380196190816e-06, "loss": 0.001, "step": 386110 }, { "epoch": 92.71, "learning_rate": 3.376083429926752e-06, "loss": 0.0009, "step": 386120 }, { "epoch": 92.72, "learning_rate": 3.374786903962751e-06, "loss": 0.001, "step": 386130 }, { "epoch": 92.72, "learning_rate": 3.373490618305486e-06, "loss": 0.0009, "step": 386140 }, { "epoch": 92.72, "learning_rate": 3.3721945729616343e-06, "loss": 0.0009, "step": 386150 }, { "epoch": 92.72, "learning_rate": 3.3708987679378858e-06, "loss": 0.0009, "step": 386160 }, { "epoch": 92.73, "learning_rate": 3.369603203240912e-06, "loss": 0.0011, "step": 386170 }, { "epoch": 92.73, "learning_rate": 3.368307878877397e-06, "loss": 0.0009, "step": 386180 }, { "epoch": 92.73, "learning_rate": 3.3670127948540076e-06, "loss": 0.0009, "step": 386190 }, { "epoch": 92.73, "learning_rate": 3.365717951177433e-06, "loss": 0.001, "step": 386200 }, { "epoch": 92.73, "learning_rate": 3.364423347854334e-06, "loss": 0.0008, "step": 386210 }, { "epoch": 92.74, "learning_rate": 3.3631289848913782e-06, "loss": 0.0009, "step": 386220 }, { "epoch": 92.74, "learning_rate": 3.36183486229526e-06, "loss": 0.0009, "step": 386230 }, { "epoch": 92.74, "learning_rate": 3.3605409800726185e-06, "loss": 0.0009, "step": 386240 }, { "epoch": 92.74, "learning_rate": 3.3592473382301536e-06, "loss": 0.0008, "step": 386250 }, { "epoch": 92.75, "learning_rate": 3.357953936774505e-06, "loss": 0.0009, "step": 386260 }, { "epoch": 92.75, "learning_rate": 3.356660775712361e-06, "loss": 0.0009, "step": 386270 }, { "epoch": 92.75, "learning_rate": 3.3553678550503786e-06, "loss": 0.0009, "step": 386280 }, { "epoch": 92.75, "learning_rate": 3.3540751747952125e-06, "loss": 0.0009, "step": 386290 }, { "epoch": 92.76, "learning_rate": 3.352782734953541e-06, "loss": 0.0009, "step": 386300 }, { "epoch": 92.76, "learning_rate": 3.351490535532009e-06, "loss": 0.0009, "step": 386310 }, { "epoch": 92.76, "learning_rate": 3.350198576537289e-06, "loss": 0.0009, "step": 386320 }, { "epoch": 92.76, "learning_rate": 3.3489068579760306e-06, "loss": 0.0011, "step": 386330 }, { "epoch": 92.76, "learning_rate": 3.347615379854907e-06, "loss": 0.0008, "step": 386340 }, { "epoch": 92.77, "learning_rate": 3.346324142180551e-06, "loss": 0.0009, "step": 386350 }, { "epoch": 92.77, "learning_rate": 3.345033144959642e-06, "loss": 0.0009, "step": 386360 }, { "epoch": 92.77, "learning_rate": 3.3437423881988116e-06, "loss": 0.0009, "step": 386370 }, { "epoch": 92.77, "learning_rate": 3.3424518719047284e-06, "loss": 0.0009, "step": 386380 }, { "epoch": 92.78, "learning_rate": 3.3411615960840357e-06, "loss": 0.0009, "step": 386390 }, { "epoch": 92.78, "learning_rate": 3.3398715607433796e-06, "loss": 0.001, "step": 386400 }, { "epoch": 92.78, "learning_rate": 3.3385817658894315e-06, "loss": 0.001, "step": 386410 }, { "epoch": 92.78, "learning_rate": 3.3372922115288196e-06, "loss": 0.001, "step": 386420 }, { "epoch": 92.78, "learning_rate": 3.3360028976681834e-06, "loss": 0.001, "step": 386430 }, { "epoch": 92.79, "learning_rate": 3.3347138243141897e-06, "loss": 0.0009, "step": 386440 }, { "epoch": 92.79, "learning_rate": 3.3334249914734603e-06, "loss": 0.001, "step": 386450 }, { "epoch": 92.79, "learning_rate": 3.3321363991526576e-06, "loss": 0.0009, "step": 386460 }, { "epoch": 92.79, "learning_rate": 3.3308480473584036e-06, "loss": 0.001, "step": 386470 }, { "epoch": 92.8, "learning_rate": 3.3295599360973594e-06, "loss": 0.001, "step": 386480 }, { "epoch": 92.8, "learning_rate": 3.3282720653761535e-06, "loss": 0.0008, "step": 386490 }, { "epoch": 92.8, "learning_rate": 3.3269844352014135e-06, "loss": 0.001, "step": 386500 }, { "epoch": 92.8, "learning_rate": 3.3256970455797953e-06, "loss": 0.0009, "step": 386510 }, { "epoch": 92.81, "learning_rate": 3.3244098965179215e-06, "loss": 0.001, "step": 386520 }, { "epoch": 92.81, "learning_rate": 3.323122988022431e-06, "loss": 0.001, "step": 386530 }, { "epoch": 92.81, "learning_rate": 3.321836320099947e-06, "loss": 0.0009, "step": 386540 }, { "epoch": 92.81, "learning_rate": 3.3205498927571186e-06, "loss": 0.001, "step": 386550 }, { "epoch": 92.81, "learning_rate": 3.319263706000558e-06, "loss": 0.0009, "step": 386560 }, { "epoch": 92.82, "learning_rate": 3.3179777598369098e-06, "loss": 0.0008, "step": 386570 }, { "epoch": 92.82, "learning_rate": 3.3166920542727964e-06, "loss": 0.0009, "step": 386580 }, { "epoch": 92.82, "learning_rate": 3.3154065893148347e-06, "loss": 0.001, "step": 386590 }, { "epoch": 92.82, "learning_rate": 3.3141213649696636e-06, "loss": 0.0009, "step": 386600 }, { "epoch": 92.83, "learning_rate": 3.3128363812438947e-06, "loss": 0.0009, "step": 386610 }, { "epoch": 92.83, "learning_rate": 3.3115516381441615e-06, "loss": 0.001, "step": 386620 }, { "epoch": 92.83, "learning_rate": 3.3102671356770756e-06, "loss": 0.0009, "step": 386630 }, { "epoch": 92.83, "learning_rate": 3.30898287384927e-06, "loss": 0.001, "step": 386640 }, { "epoch": 92.84, "learning_rate": 3.3076988526673626e-06, "loss": 0.0009, "step": 386650 }, { "epoch": 92.84, "learning_rate": 3.3064150721379527e-06, "loss": 0.0009, "step": 386660 }, { "epoch": 92.84, "learning_rate": 3.305131532267669e-06, "loss": 0.0008, "step": 386670 }, { "epoch": 92.84, "learning_rate": 3.303848233063139e-06, "loss": 0.001, "step": 386680 }, { "epoch": 92.84, "learning_rate": 3.302565174530953e-06, "loss": 0.0009, "step": 386690 }, { "epoch": 92.85, "learning_rate": 3.3012823566777483e-06, "loss": 0.0009, "step": 386700 }, { "epoch": 92.85, "learning_rate": 3.2999997795101157e-06, "loss": 0.001, "step": 386710 }, { "epoch": 92.85, "learning_rate": 3.2987174430346823e-06, "loss": 0.0008, "step": 386720 }, { "epoch": 92.85, "learning_rate": 3.297435347258043e-06, "loss": 0.0009, "step": 386730 }, { "epoch": 92.86, "learning_rate": 3.296153492186821e-06, "loss": 0.0009, "step": 386740 }, { "epoch": 92.86, "learning_rate": 3.2948718778276045e-06, "loss": 0.001, "step": 386750 }, { "epoch": 92.86, "learning_rate": 3.2935905041870164e-06, "loss": 0.0009, "step": 386760 }, { "epoch": 92.86, "learning_rate": 3.2923093712716456e-06, "loss": 0.0009, "step": 386770 }, { "epoch": 92.86, "learning_rate": 3.2910284790881096e-06, "loss": 0.0009, "step": 386780 }, { "epoch": 92.87, "learning_rate": 3.2897478276430026e-06, "loss": 0.0009, "step": 386790 }, { "epoch": 92.87, "learning_rate": 3.2884674169429195e-06, "loss": 0.0009, "step": 386800 }, { "epoch": 92.87, "learning_rate": 3.287187246994472e-06, "loss": 0.0009, "step": 386810 }, { "epoch": 92.87, "learning_rate": 3.285907317804249e-06, "loss": 0.001, "step": 386820 }, { "epoch": 92.88, "learning_rate": 3.284627629378856e-06, "loss": 0.001, "step": 386830 }, { "epoch": 92.88, "learning_rate": 3.283348181724871e-06, "loss": 0.0009, "step": 386840 }, { "epoch": 92.88, "learning_rate": 3.282068974848912e-06, "loss": 0.0009, "step": 386850 }, { "epoch": 92.88, "learning_rate": 3.280790008757556e-06, "loss": 0.0009, "step": 386860 }, { "epoch": 92.89, "learning_rate": 3.2795112834573928e-06, "loss": 0.0009, "step": 386870 }, { "epoch": 92.89, "learning_rate": 3.2782327989550275e-06, "loss": 0.0009, "step": 386880 }, { "epoch": 92.89, "learning_rate": 3.2769545552570336e-06, "loss": 0.001, "step": 386890 }, { "epoch": 92.89, "learning_rate": 3.275676552370016e-06, "loss": 0.0009, "step": 386900 }, { "epoch": 92.89, "learning_rate": 3.274398790300537e-06, "loss": 0.0008, "step": 386910 }, { "epoch": 92.9, "learning_rate": 3.2731212690552126e-06, "loss": 0.0008, "step": 386920 }, { "epoch": 92.9, "learning_rate": 3.2718439886406107e-06, "loss": 0.0009, "step": 386930 }, { "epoch": 92.9, "learning_rate": 3.270566949063303e-06, "loss": 0.0008, "step": 386940 }, { "epoch": 92.9, "learning_rate": 3.2692901503298954e-06, "loss": 0.001, "step": 386950 }, { "epoch": 92.91, "learning_rate": 3.26801359244695e-06, "loss": 0.0009, "step": 386960 }, { "epoch": 92.91, "learning_rate": 3.2667372754210556e-06, "loss": 0.0009, "step": 386970 }, { "epoch": 92.91, "learning_rate": 3.2654611992587845e-06, "loss": 0.0009, "step": 386980 }, { "epoch": 92.91, "learning_rate": 3.2641853639667153e-06, "loss": 0.001, "step": 386990 }, { "epoch": 92.91, "learning_rate": 3.2629097695514365e-06, "loss": 0.0009, "step": 387000 }, { "epoch": 92.92, "learning_rate": 3.261634416019499e-06, "loss": 0.0009, "step": 387010 }, { "epoch": 92.92, "learning_rate": 3.2603593033775027e-06, "loss": 0.0011, "step": 387020 }, { "epoch": 92.92, "learning_rate": 3.2590844316319923e-06, "loss": 0.0009, "step": 387030 }, { "epoch": 92.92, "learning_rate": 3.2578098007895575e-06, "loss": 0.001, "step": 387040 }, { "epoch": 92.93, "learning_rate": 3.256535410856759e-06, "loss": 0.0008, "step": 387050 }, { "epoch": 92.93, "learning_rate": 3.2552612618401702e-06, "loss": 0.0009, "step": 387060 }, { "epoch": 92.93, "learning_rate": 3.253987353746363e-06, "loss": 0.0008, "step": 387070 }, { "epoch": 92.93, "learning_rate": 3.252713686581882e-06, "loss": 0.0009, "step": 387080 }, { "epoch": 92.94, "learning_rate": 3.2514402603533113e-06, "loss": 0.0011, "step": 387090 }, { "epoch": 92.94, "learning_rate": 3.2501670750672065e-06, "loss": 0.001, "step": 387100 }, { "epoch": 92.94, "learning_rate": 3.248894130730135e-06, "loss": 0.0011, "step": 387110 }, { "epoch": 92.94, "learning_rate": 3.247621427348646e-06, "loss": 0.0009, "step": 387120 }, { "epoch": 92.94, "learning_rate": 3.2463489649293187e-06, "loss": 0.001, "step": 387130 }, { "epoch": 92.95, "learning_rate": 3.245076743478698e-06, "loss": 0.001, "step": 387140 }, { "epoch": 92.95, "learning_rate": 3.243804763003333e-06, "loss": 0.0009, "step": 387150 } ], "max_steps": 437600, "num_train_epochs": 100, "total_flos": 0.0, "trial_name": null, "trial_params": null }