diff --git "a/trainer_log_history.jsonl" "b/trainer_log_history.jsonl"
new file mode 100644--- /dev/null
+++ "b/trainer_log_history.jsonl"
@@ -0,0 +1,3905 @@
+{"epoch": 0.0, "learning_rate": 2.3999999999999997e-05, "loss": 1.0564, "step": 10}
+{"epoch": 0.0, "learning_rate": 5.399999999999999e-05, "loss": 0.9789, "step": 20}
+{"epoch": 0.0, "learning_rate": 8.4e-05, "loss": 0.9108, "step": 30}
+{"epoch": 0.0, "learning_rate": 0.00011399999999999999, "loss": 0.8764, "step": 40}
+{"epoch": 0.0, "learning_rate": 0.00014399999999999998, "loss": 0.8502, "step": 50}
+{"epoch": 0.0, "learning_rate": 0.00017399999999999997, "loss": 0.8358, "step": 60}
+{"epoch": 0.0, "learning_rate": 0.000204, "loss": 0.751, "step": 70}
+{"epoch": 0.0, "learning_rate": 0.000234, "loss": 0.6918, "step": 80}
+{"epoch": 0.0, "learning_rate": 0.00026399999999999997, "loss": 0.7512, "step": 90}
+{"epoch": 0.0, "learning_rate": 0.000294, "loss": 0.7945, "step": 100}
+{"epoch": 0.0, "learning_rate": 0.00029997152687151495, "loss": 0.7894, "step": 110}
+{"epoch": 0.0, "learning_rate": 0.00029993593546090875, "loss": 0.6707, "step": 120}
+{"epoch": 0.0, "learning_rate": 0.0002999003440503025, "loss": 0.8224, "step": 130}
+{"epoch": 0.0, "learning_rate": 0.0002998647526396962, "loss": 0.7089, "step": 140}
+{"epoch": 0.01, "learning_rate": 0.00029982916122909, "loss": 0.726, "step": 150}
+{"epoch": 0.01, "learning_rate": 0.00029979356981848376, "loss": 0.8548, "step": 160}
+{"epoch": 0.01, "learning_rate": 0.00029975797840787755, "loss": 0.7061, "step": 170}
+{"epoch": 0.01, "learning_rate": 0.0002997223869972713, "loss": 0.7457, "step": 180}
+{"epoch": 0.01, "learning_rate": 0.0002996867955866651, "loss": 0.7526, "step": 190}
+{"epoch": 0.01, "learning_rate": 0.0002996512041760588, "loss": 0.8593, "step": 200}
+{"epoch": 0.01, "learning_rate": 0.00029961561276545257, "loss": 0.7059, "step": 210}
+{"epoch": 0.01, "learning_rate": 0.00029958002135484636, "loss": 0.8394, "step": 220}
+{"epoch": 0.01, "learning_rate": 0.0002995444299442401, "loss": 0.7684, "step": 230}
+{"epoch": 0.01, "learning_rate": 0.00029950883853363384, "loss": 0.72, "step": 240}
+{"epoch": 0.01, "learning_rate": 0.00029947324712302763, "loss": 0.7342, "step": 250}
+{"epoch": 0.01, "learning_rate": 0.00029943765571242137, "loss": 0.6663, "step": 260}
+{"epoch": 0.01, "learning_rate": 0.0002994020643018151, "loss": 0.7824, "step": 270}
+{"epoch": 0.01, "learning_rate": 0.0002993664728912089, "loss": 0.8046, "step": 280}
+{"epoch": 0.01, "learning_rate": 0.00029933088148060264, "loss": 0.8155, "step": 290}
+{"epoch": 0.01, "learning_rate": 0.0002992952900699964, "loss": 0.6827, "step": 300}
+{"epoch": 0.01, "learning_rate": 0.0002992596986593902, "loss": 0.749, "step": 310}
+{"epoch": 0.01, "learning_rate": 0.0002992241072487839, "loss": 0.7145, "step": 320}
+{"epoch": 0.01, "learning_rate": 0.0002991885158381777, "loss": 0.7137, "step": 330}
+{"epoch": 0.01, "learning_rate": 0.00029915292442757145, "loss": 0.6598, "step": 340}
+{"epoch": 0.01, "learning_rate": 0.00029911733301696524, "loss": 0.6857, "step": 350}
+{"epoch": 0.01, "learning_rate": 0.000299081741606359, "loss": 0.7471, "step": 360}
+{"epoch": 0.01, "learning_rate": 0.0002990461501957527, "loss": 0.6752, "step": 370}
+{"epoch": 0.01, "learning_rate": 0.0002990105587851465, "loss": 0.7399, "step": 380}
+{"epoch": 0.01, "learning_rate": 0.00029897496737454026, "loss": 0.7851, "step": 390}
+{"epoch": 0.01, "learning_rate": 0.000298939375963934, "loss": 0.7845, "step": 400}
+{"epoch": 0.01, "learning_rate": 0.0002989037845533278, "loss": 0.7856, "step": 410}
+{"epoch": 0.01, "learning_rate": 0.00029886819314272153, "loss": 0.7442, "step": 420}
+{"epoch": 0.02, "learning_rate": 0.00029883260173211527, "loss": 0.7935, "step": 430}
+{"epoch": 0.02, "learning_rate": 0.000298797010321509, "loss": 0.8512, "step": 440}
+{"epoch": 0.02, "learning_rate": 0.0002987614189109028, "loss": 0.6972, "step": 450}
+{"epoch": 0.02, "learning_rate": 0.00029872582750029654, "loss": 0.7037, "step": 460}
+{"epoch": 0.02, "learning_rate": 0.00029869023608969033, "loss": 0.7217, "step": 470}
+{"epoch": 0.02, "learning_rate": 0.0002986546446790841, "loss": 0.7686, "step": 480}
+{"epoch": 0.02, "learning_rate": 0.00029861905326847787, "loss": 0.7723, "step": 490}
+{"epoch": 0.02, "learning_rate": 0.0002985834618578716, "loss": 0.6703, "step": 500}
+{"epoch": 0.02, "learning_rate": 0.0002985478704472654, "loss": 0.7431, "step": 510}
+{"epoch": 0.02, "learning_rate": 0.00029851227903665914, "loss": 0.8524, "step": 520}
+{"epoch": 0.02, "learning_rate": 0.0002984766876260529, "loss": 0.7808, "step": 530}
+{"epoch": 0.02, "learning_rate": 0.00029844109621544667, "loss": 0.7762, "step": 540}
+{"epoch": 0.02, "learning_rate": 0.0002984055048048404, "loss": 0.6834, "step": 550}
+{"epoch": 0.02, "learning_rate": 0.00029836991339423415, "loss": 0.7705, "step": 560}
+{"epoch": 0.02, "learning_rate": 0.0002983343219836279, "loss": 0.6926, "step": 570}
+{"epoch": 0.02, "learning_rate": 0.0002982987305730217, "loss": 0.6399, "step": 580}
+{"epoch": 0.02, "learning_rate": 0.0002982631391624154, "loss": 0.6441, "step": 590}
+{"epoch": 0.02, "learning_rate": 0.0002982275477518092, "loss": 0.7007, "step": 600}
+{"epoch": 0.02, "learning_rate": 0.00029819195634120296, "loss": 0.7483, "step": 610}
+{"epoch": 0.02, "learning_rate": 0.00029815636493059675, "loss": 0.7792, "step": 620}
+{"epoch": 0.02, "learning_rate": 0.0002981207735199905, "loss": 0.7824, "step": 630}
+{"epoch": 0.02, "learning_rate": 0.0002980851821093843, "loss": 0.8315, "step": 640}
+{"epoch": 0.02, "learning_rate": 0.000298049590698778, "loss": 0.7339, "step": 650}
+{"epoch": 0.02, "learning_rate": 0.00029801399928817176, "loss": 0.5957, "step": 660}
+{"epoch": 0.02, "learning_rate": 0.0002979784078775655, "loss": 0.7083, "step": 670}
+{"epoch": 0.02, "learning_rate": 0.0002979428164669593, "loss": 0.7184, "step": 680}
+{"epoch": 0.02, "learning_rate": 0.00029790722505635304, "loss": 0.6226, "step": 690}
+{"epoch": 0.02, "learning_rate": 0.0002978716336457468, "loss": 0.7426, "step": 700}
+{"epoch": 0.03, "learning_rate": 0.00029783604223514057, "loss": 0.7773, "step": 710}
+{"epoch": 0.03, "learning_rate": 0.0002978004508245343, "loss": 0.7387, "step": 720}
+{"epoch": 0.03, "learning_rate": 0.00029776485941392805, "loss": 0.7358, "step": 730}
+{"epoch": 0.03, "learning_rate": 0.00029772926800332184, "loss": 0.6371, "step": 740}
+{"epoch": 0.03, "learning_rate": 0.0002976936765927156, "loss": 0.7573, "step": 750}
+{"epoch": 0.03, "learning_rate": 0.0002976580851821094, "loss": 0.8435, "step": 760}
+{"epoch": 0.03, "learning_rate": 0.0002976224937715031, "loss": 0.7046, "step": 770}
+{"epoch": 0.03, "learning_rate": 0.0002975869023608969, "loss": 0.834, "step": 780}
+{"epoch": 0.03, "learning_rate": 0.00029755131095029065, "loss": 0.6835, "step": 790}
+{"epoch": 0.03, "learning_rate": 0.0002975157195396844, "loss": 0.7006, "step": 800}
+{"epoch": 0.03, "learning_rate": 0.0002974801281290782, "loss": 0.6872, "step": 810}
+{"epoch": 0.03, "learning_rate": 0.0002974445367184719, "loss": 0.7237, "step": 820}
+{"epoch": 0.03, "learning_rate": 0.00029740894530786566, "loss": 0.6703, "step": 830}
+{"epoch": 0.03, "learning_rate": 0.00029737335389725945, "loss": 0.788, "step": 840}
+{"epoch": 0.03, "learning_rate": 0.0002973377624866532, "loss": 0.6923, "step": 850}
+{"epoch": 0.03, "learning_rate": 0.00029730217107604693, "loss": 0.6793, "step": 860}
+{"epoch": 0.03, "learning_rate": 0.0002972665796654407, "loss": 0.6775, "step": 870}
+{"epoch": 0.03, "learning_rate": 0.00029723098825483446, "loss": 0.6772, "step": 880}
+{"epoch": 0.03, "learning_rate": 0.0002971953968442282, "loss": 0.7651, "step": 890}
+{"epoch": 0.03, "learning_rate": 0.000297159805433622, "loss": 0.6891, "step": 900}
+{"epoch": 0.03, "learning_rate": 0.00029712421402301574, "loss": 0.733, "step": 910}
+{"epoch": 0.03, "learning_rate": 0.00029708862261240953, "loss": 0.7815, "step": 920}
+{"epoch": 0.03, "learning_rate": 0.00029705303120180327, "loss": 0.7949, "step": 930}
+{"epoch": 0.03, "learning_rate": 0.00029701743979119706, "loss": 0.6192, "step": 940}
+{"epoch": 0.03, "learning_rate": 0.0002969818483805908, "loss": 0.7257, "step": 950}
+{"epoch": 0.03, "learning_rate": 0.00029694625696998454, "loss": 0.7321, "step": 960}
+{"epoch": 0.03, "learning_rate": 0.00029691066555937834, "loss": 0.7603, "step": 970}
+{"epoch": 0.03, "learning_rate": 0.0002968750741487721, "loss": 0.8687, "step": 980}
+{"epoch": 0.04, "learning_rate": 0.0002968394827381658, "loss": 0.7521, "step": 990}
+{"epoch": 0.04, "learning_rate": 0.00029680389132755955, "loss": 0.7754, "step": 1000}
+{"epoch": 0.04, "learning_rate": 0.00029676829991695335, "loss": 0.5612, "step": 1010}
+{"epoch": 0.04, "learning_rate": 0.0002967327085063471, "loss": 0.6117, "step": 1020}
+{"epoch": 0.04, "learning_rate": 0.0002966971170957409, "loss": 0.7266, "step": 1030}
+{"epoch": 0.04, "learning_rate": 0.0002966615256851346, "loss": 0.7288, "step": 1040}
+{"epoch": 0.04, "learning_rate": 0.00029662593427452836, "loss": 0.7119, "step": 1050}
+{"epoch": 0.04, "learning_rate": 0.00029659034286392215, "loss": 0.7122, "step": 1060}
+{"epoch": 0.04, "learning_rate": 0.0002965547514533159, "loss": 0.662, "step": 1070}
+{"epoch": 0.04, "learning_rate": 0.0002965191600427097, "loss": 0.6961, "step": 1080}
+{"epoch": 0.04, "learning_rate": 0.0002964835686321034, "loss": 0.6354, "step": 1090}
+{"epoch": 0.04, "learning_rate": 0.0002964479772214972, "loss": 0.7367, "step": 1100}
+{"epoch": 0.04, "learning_rate": 0.00029641238581089096, "loss": 0.7616, "step": 1110}
+{"epoch": 0.04, "learning_rate": 0.0002963767944002847, "loss": 0.7861, "step": 1120}
+{"epoch": 0.04, "learning_rate": 0.00029634120298967844, "loss": 0.7717, "step": 1130}
+{"epoch": 0.04, "learning_rate": 0.00029630561157907223, "loss": 0.6594, "step": 1140}
+{"epoch": 0.04, "learning_rate": 0.00029627002016846597, "loss": 0.6343, "step": 1150}
+{"epoch": 0.04, "learning_rate": 0.0002962344287578597, "loss": 0.7648, "step": 1160}
+{"epoch": 0.04, "learning_rate": 0.0002961988373472535, "loss": 0.6647, "step": 1170}
+{"epoch": 0.04, "learning_rate": 0.00029616324593664724, "loss": 0.6518, "step": 1180}
+{"epoch": 0.04, "learning_rate": 0.00029612765452604104, "loss": 0.768, "step": 1190}
+{"epoch": 0.04, "learning_rate": 0.0002960920631154348, "loss": 0.7371, "step": 1200}
+{"epoch": 0.04, "learning_rate": 0.00029605647170482857, "loss": 0.6907, "step": 1210}
+{"epoch": 0.04, "learning_rate": 0.0002960208802942223, "loss": 0.7132, "step": 1220}
+{"epoch": 0.04, "learning_rate": 0.00029598528888361605, "loss": 0.8197, "step": 1230}
+{"epoch": 0.04, "learning_rate": 0.00029594969747300984, "loss": 0.7333, "step": 1240}
+{"epoch": 0.04, "learning_rate": 0.0002959141060624036, "loss": 0.6143, "step": 1250}
+{"epoch": 0.04, "learning_rate": 0.0002958785146517973, "loss": 0.7494, "step": 1260}
+{"epoch": 0.05, "learning_rate": 0.0002958429232411911, "loss": 0.7385, "step": 1270}
+{"epoch": 0.05, "learning_rate": 0.00029580733183058486, "loss": 0.8033, "step": 1280}
+{"epoch": 0.05, "learning_rate": 0.0002957717404199786, "loss": 0.6221, "step": 1290}
+{"epoch": 0.05, "learning_rate": 0.0002957361490093724, "loss": 0.715, "step": 1300}
+{"epoch": 0.05, "learning_rate": 0.00029570055759876613, "loss": 0.7975, "step": 1310}
+{"epoch": 0.05, "learning_rate": 0.00029566496618815987, "loss": 0.6922, "step": 1320}
+{"epoch": 0.05, "learning_rate": 0.00029562937477755366, "loss": 0.7557, "step": 1330}
+{"epoch": 0.05, "learning_rate": 0.0002955937833669474, "loss": 0.7403, "step": 1340}
+{"epoch": 0.05, "learning_rate": 0.0002955581919563412, "loss": 0.6744, "step": 1350}
+{"epoch": 0.05, "learning_rate": 0.00029552260054573493, "loss": 0.863, "step": 1360}
+{"epoch": 0.05, "learning_rate": 0.00029548700913512873, "loss": 0.6081, "step": 1370}
+{"epoch": 0.05, "learning_rate": 0.00029545141772452247, "loss": 0.637, "step": 1380}
+{"epoch": 0.05, "learning_rate": 0.0002954158263139162, "loss": 0.6088, "step": 1390}
+{"epoch": 0.05, "learning_rate": 0.00029538023490331, "loss": 0.5868, "step": 1400}
+{"epoch": 0.05, "learning_rate": 0.00029534464349270374, "loss": 0.8172, "step": 1410}
+{"epoch": 0.05, "learning_rate": 0.0002953090520820975, "loss": 0.7566, "step": 1420}
+{"epoch": 0.05, "learning_rate": 0.0002952734606714913, "loss": 0.7284, "step": 1430}
+{"epoch": 0.05, "learning_rate": 0.000295237869260885, "loss": 0.6883, "step": 1440}
+{"epoch": 0.05, "learning_rate": 0.00029520227785027875, "loss": 0.685, "step": 1450}
+{"epoch": 0.05, "learning_rate": 0.0002951666864396725, "loss": 0.657, "step": 1460}
+{"epoch": 0.05, "learning_rate": 0.0002951310950290663, "loss": 0.8236, "step": 1470}
+{"epoch": 0.05, "learning_rate": 0.00029509550361846, "loss": 0.656, "step": 1480}
+{"epoch": 0.05, "learning_rate": 0.0002950599122078538, "loss": 0.6151, "step": 1490}
+{"epoch": 0.05, "learning_rate": 0.00029502432079724756, "loss": 0.8033, "step": 1500}
+{"epoch": 0.05, "learning_rate": 0.00029498872938664135, "loss": 0.748, "step": 1510}
+{"epoch": 0.05, "learning_rate": 0.0002949531379760351, "loss": 0.7847, "step": 1520}
+{"epoch": 0.05, "learning_rate": 0.0002949175465654289, "loss": 0.7599, "step": 1530}
+{"epoch": 0.05, "learning_rate": 0.0002948819551548226, "loss": 0.6552, "step": 1540}
+{"epoch": 0.06, "learning_rate": 0.00029484636374421636, "loss": 0.7262, "step": 1550}
+{"epoch": 0.06, "learning_rate": 0.00029481077233361016, "loss": 0.6506, "step": 1560}
+{"epoch": 0.06, "learning_rate": 0.0002947751809230039, "loss": 0.6471, "step": 1570}
+{"epoch": 0.06, "learning_rate": 0.00029473958951239764, "loss": 0.6956, "step": 1580}
+{"epoch": 0.06, "learning_rate": 0.0002947039981017914, "loss": 0.677, "step": 1590}
+{"epoch": 0.06, "learning_rate": 0.00029466840669118517, "loss": 0.6832, "step": 1600}
+{"epoch": 0.06, "learning_rate": 0.0002946328152805789, "loss": 0.7038, "step": 1610}
+{"epoch": 0.06, "learning_rate": 0.0002945972238699727, "loss": 0.6823, "step": 1620}
+{"epoch": 0.06, "learning_rate": 0.00029456163245936644, "loss": 0.7551, "step": 1630}
+{"epoch": 0.06, "learning_rate": 0.00029452604104876024, "loss": 0.8668, "step": 1640}
+{"epoch": 0.06, "learning_rate": 0.000294490449638154, "loss": 0.68, "step": 1650}
+{"epoch": 0.06, "learning_rate": 0.0002944548582275477, "loss": 0.8423, "step": 1660}
+{"epoch": 0.06, "learning_rate": 0.0002944192668169415, "loss": 0.7349, "step": 1670}
+{"epoch": 0.06, "learning_rate": 0.00029438367540633525, "loss": 0.6724, "step": 1680}
+{"epoch": 0.06, "learning_rate": 0.000294348083995729, "loss": 0.652, "step": 1690}
+{"epoch": 0.06, "learning_rate": 0.0002943124925851228, "loss": 0.7264, "step": 1700}
+{"epoch": 0.06, "learning_rate": 0.0002942769011745165, "loss": 0.743, "step": 1710}
+{"epoch": 0.06, "learning_rate": 0.00029424130976391026, "loss": 0.7002, "step": 1720}
+{"epoch": 0.06, "learning_rate": 0.00029420571835330405, "loss": 0.6784, "step": 1730}
+{"epoch": 0.06, "learning_rate": 0.0002941701269426978, "loss": 0.7149, "step": 1740}
+{"epoch": 0.06, "learning_rate": 0.00029413453553209153, "loss": 0.6883, "step": 1750}
+{"epoch": 0.06, "learning_rate": 0.0002940989441214853, "loss": 0.7579, "step": 1760}
+{"epoch": 0.06, "learning_rate": 0.00029406335271087906, "loss": 0.6891, "step": 1770}
+{"epoch": 0.06, "learning_rate": 0.00029402776130027286, "loss": 0.6597, "step": 1780}
+{"epoch": 0.06, "learning_rate": 0.0002939921698896666, "loss": 0.7376, "step": 1790}
+{"epoch": 0.06, "learning_rate": 0.0002939565784790604, "loss": 0.6289, "step": 1800}
+{"epoch": 0.06, "learning_rate": 0.00029392098706845413, "loss": 0.7625, "step": 1810}
+{"epoch": 0.06, "learning_rate": 0.0002938889547989085, "loss": 0.814, "step": 1820}
+{"epoch": 0.07, "learning_rate": 0.00029385336338830226, "loss": 0.8062, "step": 1830}
+{"epoch": 0.07, "learning_rate": 0.00029381777197769605, "loss": 0.7333, "step": 1840}
+{"epoch": 0.07, "learning_rate": 0.0002937821805670898, "loss": 0.7614, "step": 1850}
+{"epoch": 0.07, "learning_rate": 0.00029374658915648353, "loss": 0.5884, "step": 1860}
+{"epoch": 0.07, "learning_rate": 0.0002937109977458773, "loss": 0.7197, "step": 1870}
+{"epoch": 0.07, "learning_rate": 0.00029367540633527106, "loss": 0.7779, "step": 1880}
+{"epoch": 0.07, "learning_rate": 0.0002936398149246648, "loss": 0.719, "step": 1890}
+{"epoch": 0.07, "learning_rate": 0.00029360422351405854, "loss": 0.6475, "step": 1900}
+{"epoch": 0.07, "learning_rate": 0.00029356863210345234, "loss": 0.7283, "step": 1910}
+{"epoch": 0.07, "learning_rate": 0.0002935330406928461, "loss": 0.7922, "step": 1920}
+{"epoch": 0.07, "learning_rate": 0.00029349744928223987, "loss": 0.7844, "step": 1930}
+{"epoch": 0.07, "learning_rate": 0.0002934618578716336, "loss": 0.7782, "step": 1940}
+{"epoch": 0.07, "learning_rate": 0.0002934262664610274, "loss": 0.6992, "step": 1950}
+{"epoch": 0.07, "learning_rate": 0.00029339067505042114, "loss": 0.8458, "step": 1960}
+{"epoch": 0.07, "learning_rate": 0.00029335508363981494, "loss": 0.7222, "step": 1970}
+{"epoch": 0.07, "learning_rate": 0.0002933194922292087, "loss": 0.7072, "step": 1980}
+{"epoch": 0.07, "learning_rate": 0.0002932839008186024, "loss": 0.701, "step": 1990}
+{"epoch": 0.07, "learning_rate": 0.00029324830940799615, "loss": 0.7371, "step": 2000}
+{"epoch": 0.07, "learning_rate": 0.00029321271799738995, "loss": 0.712, "step": 2010}
+{"epoch": 0.07, "learning_rate": 0.0002931771265867837, "loss": 0.6398, "step": 2020}
+{"epoch": 0.07, "learning_rate": 0.0002931415351761774, "loss": 0.7693, "step": 2030}
+{"epoch": 0.07, "learning_rate": 0.0002931059437655712, "loss": 0.8002, "step": 2040}
+{"epoch": 0.07, "learning_rate": 0.00029307035235496496, "loss": 0.7958, "step": 2050}
+{"epoch": 0.07, "learning_rate": 0.00029303476094435875, "loss": 0.6528, "step": 2060}
+{"epoch": 0.07, "learning_rate": 0.0002929991695337525, "loss": 0.6626, "step": 2070}
+{"epoch": 0.07, "learning_rate": 0.00029296357812314623, "loss": 0.8145, "step": 2080}
+{"epoch": 0.07, "learning_rate": 0.00029292798671254, "loss": 0.688, "step": 2090}
+{"epoch": 0.07, "learning_rate": 0.00029289239530193377, "loss": 0.6805, "step": 2100}
+{"epoch": 0.08, "learning_rate": 0.00029285680389132756, "loss": 0.6324, "step": 2110}
+{"epoch": 0.08, "learning_rate": 0.0002928212124807213, "loss": 0.7134, "step": 2120}
+{"epoch": 0.08, "learning_rate": 0.00029278562107011504, "loss": 0.6492, "step": 2130}
+{"epoch": 0.08, "learning_rate": 0.00029275002965950883, "loss": 0.7083, "step": 2140}
+{"epoch": 0.08, "learning_rate": 0.00029271443824890257, "loss": 0.738, "step": 2150}
+{"epoch": 0.08, "learning_rate": 0.0002926788468382963, "loss": 0.8718, "step": 2160}
+{"epoch": 0.08, "learning_rate": 0.0002926432554276901, "loss": 0.6081, "step": 2170}
+{"epoch": 0.08, "learning_rate": 0.00029260766401708384, "loss": 0.7758, "step": 2180}
+{"epoch": 0.08, "learning_rate": 0.0002925720726064776, "loss": 0.7193, "step": 2190}
+{"epoch": 0.08, "learning_rate": 0.0002925364811958714, "loss": 0.6435, "step": 2200}
+{"epoch": 0.08, "learning_rate": 0.0002925008897852651, "loss": 0.6554, "step": 2210}
+{"epoch": 0.08, "learning_rate": 0.0002924652983746589, "loss": 0.6164, "step": 2220}
+{"epoch": 0.08, "learning_rate": 0.00029242970696405265, "loss": 0.8168, "step": 2230}
+{"epoch": 0.08, "learning_rate": 0.00029239411555344644, "loss": 0.7689, "step": 2240}
+{"epoch": 0.08, "learning_rate": 0.0002923585241428402, "loss": 0.8057, "step": 2250}
+{"epoch": 0.08, "learning_rate": 0.0002923229327322339, "loss": 0.5907, "step": 2260}
+{"epoch": 0.08, "learning_rate": 0.0002922873413216277, "loss": 0.7117, "step": 2270}
+{"epoch": 0.08, "learning_rate": 0.00029225174991102145, "loss": 0.6962, "step": 2280}
+{"epoch": 0.08, "learning_rate": 0.0002922161585004152, "loss": 0.6219, "step": 2290}
+{"epoch": 0.08, "learning_rate": 0.000292180567089809, "loss": 0.7221, "step": 2300}
+{"epoch": 0.08, "learning_rate": 0.00029214497567920273, "loss": 0.6648, "step": 2310}
+{"epoch": 0.08, "learning_rate": 0.00029210938426859647, "loss": 0.6797, "step": 2320}
+{"epoch": 0.08, "learning_rate": 0.0002920737928579902, "loss": 0.7903, "step": 2330}
+{"epoch": 0.08, "learning_rate": 0.000292038201447384, "loss": 0.6666, "step": 2340}
+{"epoch": 0.08, "learning_rate": 0.00029200261003677774, "loss": 0.5662, "step": 2350}
+{"epoch": 0.08, "learning_rate": 0.00029196701862617153, "loss": 0.7177, "step": 2360}
+{"epoch": 0.08, "learning_rate": 0.00029193142721556527, "loss": 0.7102, "step": 2370}
+{"epoch": 0.08, "learning_rate": 0.00029189583580495907, "loss": 0.6911, "step": 2380}
+{"epoch": 0.08, "learning_rate": 0.0002918602443943528, "loss": 0.7276, "step": 2390}
+{"epoch": 0.09, "learning_rate": 0.0002918246529837466, "loss": 0.5878, "step": 2400}
+{"epoch": 0.09, "learning_rate": 0.00029178906157314034, "loss": 0.6765, "step": 2410}
+{"epoch": 0.09, "learning_rate": 0.0002917534701625341, "loss": 0.6597, "step": 2420}
+{"epoch": 0.09, "learning_rate": 0.00029171787875192787, "loss": 0.7282, "step": 2430}
+{"epoch": 0.09, "learning_rate": 0.0002916822873413216, "loss": 0.722, "step": 2440}
+{"epoch": 0.09, "learning_rate": 0.00029164669593071535, "loss": 0.5749, "step": 2450}
+{"epoch": 0.09, "learning_rate": 0.0002916111045201091, "loss": 0.7208, "step": 2460}
+{"epoch": 0.09, "learning_rate": 0.0002915755131095029, "loss": 0.8862, "step": 2470}
+{"epoch": 0.09, "learning_rate": 0.0002915399216988966, "loss": 0.6289, "step": 2480}
+{"epoch": 0.09, "learning_rate": 0.00029150433028829036, "loss": 0.6025, "step": 2490}
+{"epoch": 0.09, "learning_rate": 0.00029146873887768416, "loss": 0.8272, "step": 2500}
+{"epoch": 0.09, "learning_rate": 0.0002914331474670779, "loss": 0.7309, "step": 2510}
+{"epoch": 0.09, "learning_rate": 0.0002913975560564717, "loss": 0.8548, "step": 2520}
+{"epoch": 0.09, "learning_rate": 0.00029136196464586543, "loss": 0.643, "step": 2530}
+{"epoch": 0.09, "learning_rate": 0.0002913263732352592, "loss": 0.7233, "step": 2540}
+{"epoch": 0.09, "learning_rate": 0.00029129078182465296, "loss": 0.7321, "step": 2550}
+{"epoch": 0.09, "learning_rate": 0.0002912551904140467, "loss": 0.7556, "step": 2560}
+{"epoch": 0.09, "learning_rate": 0.0002912195990034405, "loss": 0.7046, "step": 2570}
+{"epoch": 0.09, "learning_rate": 0.00029118400759283423, "loss": 0.6583, "step": 2580}
+{"epoch": 0.09, "learning_rate": 0.000291148416182228, "loss": 0.6571, "step": 2590}
+{"epoch": 0.09, "learning_rate": 0.00029111282477162177, "loss": 0.7019, "step": 2600}
+{"epoch": 0.09, "learning_rate": 0.0002910772333610155, "loss": 0.7106, "step": 2610}
+{"epoch": 0.09, "learning_rate": 0.00029104164195040925, "loss": 0.6742, "step": 2620}
+{"epoch": 0.09, "learning_rate": 0.00029100605053980304, "loss": 0.6429, "step": 2630}
+{"epoch": 0.09, "learning_rate": 0.0002909704591291968, "loss": 0.6783, "step": 2640}
+{"epoch": 0.09, "learning_rate": 0.0002909348677185906, "loss": 0.6635, "step": 2650}
+{"epoch": 0.09, "learning_rate": 0.0002908992763079843, "loss": 0.6557, "step": 2660}
+{"epoch": 0.09, "learning_rate": 0.0002908636848973781, "loss": 0.6747, "step": 2670}
+{"epoch": 0.1, "learning_rate": 0.00029082809348677185, "loss": 0.6546, "step": 2680}
+{"epoch": 0.1, "learning_rate": 0.0002907925020761656, "loss": 0.654, "step": 2690}
+{"epoch": 0.1, "learning_rate": 0.0002907569106655594, "loss": 0.6698, "step": 2700}
+{"epoch": 0.1, "learning_rate": 0.0002907213192549531, "loss": 0.6168, "step": 2710}
+{"epoch": 0.1, "learning_rate": 0.00029068572784434686, "loss": 0.8227, "step": 2720}
+{"epoch": 0.1, "learning_rate": 0.00029065013643374065, "loss": 0.6895, "step": 2730}
+{"epoch": 0.1, "learning_rate": 0.0002906145450231344, "loss": 0.5398, "step": 2740}
+{"epoch": 0.1, "learning_rate": 0.00029057895361252813, "loss": 0.7122, "step": 2750}
+{"epoch": 0.1, "learning_rate": 0.0002905433622019219, "loss": 0.6676, "step": 2760}
+{"epoch": 0.1, "learning_rate": 0.00029050777079131566, "loss": 0.7198, "step": 2770}
+{"epoch": 0.1, "learning_rate": 0.0002904721793807094, "loss": 0.6876, "step": 2780}
+{"epoch": 0.1, "learning_rate": 0.0002904365879701032, "loss": 0.6428, "step": 2790}
+{"epoch": 0.1, "learning_rate": 0.00029040099655949694, "loss": 0.6349, "step": 2800}
+{"epoch": 0.1, "learning_rate": 0.00029036540514889073, "loss": 0.6444, "step": 2810}
+{"epoch": 0.1, "learning_rate": 0.00029032981373828447, "loss": 0.8203, "step": 2820}
+{"epoch": 0.1, "learning_rate": 0.00029029422232767826, "loss": 0.7768, "step": 2830}
+{"epoch": 0.1, "learning_rate": 0.000290258630917072, "loss": 0.8246, "step": 2840}
+{"epoch": 0.1, "learning_rate": 0.00029022303950646574, "loss": 0.625, "step": 2850}
+{"epoch": 0.1, "learning_rate": 0.00029018744809585954, "loss": 0.6561, "step": 2860}
+{"epoch": 0.1, "learning_rate": 0.0002901518566852533, "loss": 0.7038, "step": 2870}
+{"epoch": 0.1, "learning_rate": 0.000290116265274647, "loss": 0.7551, "step": 2880}
+{"epoch": 0.1, "learning_rate": 0.0002900806738640408, "loss": 0.8089, "step": 2890}
+{"epoch": 0.1, "learning_rate": 0.00029004508245343455, "loss": 0.6719, "step": 2900}
+{"epoch": 0.1, "learning_rate": 0.0002900094910428283, "loss": 0.6635, "step": 2910}
+{"epoch": 0.1, "learning_rate": 0.000289973899632222, "loss": 0.7078, "step": 2920}
+{"epoch": 0.1, "learning_rate": 0.0002899383082216158, "loss": 0.7614, "step": 2930}
+{"epoch": 0.1, "learning_rate": 0.00028990271681100956, "loss": 0.6785, "step": 2940}
+{"epoch": 0.1, "learning_rate": 0.00028986712540040335, "loss": 0.6359, "step": 2950}
+{"epoch": 0.11, "learning_rate": 0.0002898315339897971, "loss": 0.701, "step": 2960}
+{"epoch": 0.11, "learning_rate": 0.0002897959425791909, "loss": 0.6646, "step": 2970}
+{"epoch": 0.11, "learning_rate": 0.0002897603511685846, "loss": 0.748, "step": 2980}
+{"epoch": 0.11, "learning_rate": 0.0002897247597579784, "loss": 0.6089, "step": 2990}
+{"epoch": 0.11, "learning_rate": 0.00028968916834737216, "loss": 0.6897, "step": 3000}
+{"epoch": 0.11, "learning_rate": 0.0002896535769367659, "loss": 0.6741, "step": 3010}
+{"epoch": 0.11, "learning_rate": 0.00028961798552615964, "loss": 0.7575, "step": 3020}
+{"epoch": 0.11, "learning_rate": 0.00028958239411555343, "loss": 0.6972, "step": 3030}
+{"epoch": 0.11, "learning_rate": 0.00028954680270494717, "loss": 0.7312, "step": 3040}
+{"epoch": 0.11, "learning_rate": 0.0002895112112943409, "loss": 0.6732, "step": 3050}
+{"epoch": 0.11, "learning_rate": 0.0002894756198837347, "loss": 0.8834, "step": 3060}
+{"epoch": 0.11, "learning_rate": 0.00028944002847312844, "loss": 0.7209, "step": 3070}
+{"epoch": 0.11, "learning_rate": 0.0002894044370625222, "loss": 0.7598, "step": 3080}
+{"epoch": 0.11, "learning_rate": 0.000289368845651916, "loss": 0.6389, "step": 3090}
+{"epoch": 0.11, "learning_rate": 0.0002893332542413097, "loss": 0.6792, "step": 3100}
+{"epoch": 0.11, "learning_rate": 0.0002892976628307035, "loss": 0.743, "step": 3110}
+{"epoch": 0.11, "learning_rate": 0.00028926207142009725, "loss": 0.7435, "step": 3120}
+{"epoch": 0.11, "learning_rate": 0.00028922648000949104, "loss": 0.701, "step": 3130}
+{"epoch": 0.11, "learning_rate": 0.0002891908885988848, "loss": 0.732, "step": 3140}
+{"epoch": 0.11, "learning_rate": 0.0002891552971882785, "loss": 0.6616, "step": 3150}
+{"epoch": 0.11, "learning_rate": 0.0002891197057776723, "loss": 0.7537, "step": 3160}
+{"epoch": 0.11, "learning_rate": 0.00028908411436706606, "loss": 0.7532, "step": 3170}
+{"epoch": 0.11, "learning_rate": 0.0002890485229564598, "loss": 0.8112, "step": 3180}
+{"epoch": 0.11, "learning_rate": 0.0002890129315458536, "loss": 0.6904, "step": 3190}
+{"epoch": 0.11, "learning_rate": 0.00028897734013524733, "loss": 0.6614, "step": 3200}
+{"epoch": 0.11, "learning_rate": 0.00028894174872464107, "loss": 0.6224, "step": 3210}
+{"epoch": 0.11, "learning_rate": 0.00028890615731403486, "loss": 0.7146, "step": 3220}
+{"epoch": 0.11, "learning_rate": 0.0002888705659034286, "loss": 0.7428, "step": 3230}
+{"epoch": 0.12, "learning_rate": 0.0002888349744928224, "loss": 0.7138, "step": 3240}
+{"epoch": 0.12, "learning_rate": 0.00028879938308221613, "loss": 0.6817, "step": 3250}
+{"epoch": 0.12, "learning_rate": 0.0002887637916716099, "loss": 0.7095, "step": 3260}
+{"epoch": 0.12, "learning_rate": 0.00028872820026100367, "loss": 0.5924, "step": 3270}
+{"epoch": 0.12, "learning_rate": 0.0002886926088503974, "loss": 0.6337, "step": 3280}
+{"epoch": 0.12, "learning_rate": 0.0002886570174397912, "loss": 0.7494, "step": 3290}
+{"epoch": 0.12, "learning_rate": 0.00028862142602918494, "loss": 0.6771, "step": 3300}
+{"epoch": 0.12, "learning_rate": 0.0002885858346185787, "loss": 0.698, "step": 3310}
+{"epoch": 0.12, "learning_rate": 0.00028855024320797247, "loss": 0.6463, "step": 3320}
+{"epoch": 0.12, "learning_rate": 0.0002885146517973662, "loss": 0.7366, "step": 3330}
+{"epoch": 0.12, "learning_rate": 0.00028847906038675995, "loss": 0.6497, "step": 3340}
+{"epoch": 0.12, "learning_rate": 0.0002884434689761537, "loss": 0.6996, "step": 3350}
+{"epoch": 0.12, "learning_rate": 0.0002884078775655475, "loss": 0.6958, "step": 3360}
+{"epoch": 0.12, "learning_rate": 0.0002883722861549412, "loss": 0.7147, "step": 3370}
+{"epoch": 0.12, "learning_rate": 0.000288336694744335, "loss": 0.6932, "step": 3380}
+{"epoch": 0.12, "learning_rate": 0.00028830110333372876, "loss": 0.7243, "step": 3390}
+{"epoch": 0.12, "learning_rate": 0.00028826551192312255, "loss": 0.703, "step": 3400}
+{"epoch": 0.12, "learning_rate": 0.0002882299205125163, "loss": 0.6408, "step": 3410}
+{"epoch": 0.12, "learning_rate": 0.0002881943291019101, "loss": 0.7289, "step": 3420}
+{"epoch": 0.12, "learning_rate": 0.0002881587376913038, "loss": 0.6828, "step": 3430}
+{"epoch": 0.12, "learning_rate": 0.00028812314628069756, "loss": 0.7103, "step": 3440}
+{"epoch": 0.12, "learning_rate": 0.00028808755487009136, "loss": 0.636, "step": 3450}
+{"epoch": 0.12, "learning_rate": 0.0002880519634594851, "loss": 0.6507, "step": 3460}
+{"epoch": 0.12, "learning_rate": 0.00028801637204887884, "loss": 0.6438, "step": 3470}
+{"epoch": 0.12, "learning_rate": 0.0002879807806382726, "loss": 0.6557, "step": 3480}
+{"epoch": 0.12, "learning_rate": 0.00028794518922766637, "loss": 0.6828, "step": 3490}
+{"epoch": 0.12, "learning_rate": 0.0002879095978170601, "loss": 0.6395, "step": 3500}
+{"epoch": 0.12, "learning_rate": 0.00028787400640645385, "loss": 0.5837, "step": 3510}
+{"epoch": 0.13, "learning_rate": 0.00028783841499584764, "loss": 0.6836, "step": 3520}
+{"epoch": 0.13, "learning_rate": 0.0002878028235852414, "loss": 0.7546, "step": 3530}
+{"epoch": 0.13, "learning_rate": 0.0002877672321746352, "loss": 0.7592, "step": 3540}
+{"epoch": 0.13, "learning_rate": 0.0002877316407640289, "loss": 0.7773, "step": 3550}
+{"epoch": 0.13, "learning_rate": 0.0002876960493534227, "loss": 0.6794, "step": 3560}
+{"epoch": 0.13, "learning_rate": 0.00028766045794281645, "loss": 0.6742, "step": 3570}
+{"epoch": 0.13, "learning_rate": 0.0002876248665322102, "loss": 0.707, "step": 3580}
+{"epoch": 0.13, "learning_rate": 0.000287589275121604, "loss": 0.7419, "step": 3590}
+{"epoch": 0.13, "learning_rate": 0.0002875536837109977, "loss": 0.7305, "step": 3600}
+{"epoch": 0.13, "learning_rate": 0.00028751809230039146, "loss": 0.6657, "step": 3610}
+{"epoch": 0.13, "learning_rate": 0.00028748250088978525, "loss": 0.8198, "step": 3620}
+{"epoch": 0.13, "learning_rate": 0.000287446909479179, "loss": 0.6374, "step": 3630}
+{"epoch": 0.13, "learning_rate": 0.00028741131806857273, "loss": 0.679, "step": 3640}
+{"epoch": 0.13, "learning_rate": 0.0002873757266579665, "loss": 0.5973, "step": 3650}
+{"epoch": 0.13, "learning_rate": 0.00028734013524736026, "loss": 0.6287, "step": 3660}
+{"epoch": 0.13, "learning_rate": 0.00028730454383675406, "loss": 0.7272, "step": 3670}
+{"epoch": 0.13, "learning_rate": 0.0002872689524261478, "loss": 0.6948, "step": 3680}
+{"epoch": 0.13, "learning_rate": 0.00028723336101554154, "loss": 0.6725, "step": 3690}
+{"epoch": 0.13, "learning_rate": 0.00028719776960493533, "loss": 0.7764, "step": 3700}
+{"epoch": 0.13, "learning_rate": 0.00028716217819432907, "loss": 0.6805, "step": 3710}
+{"epoch": 0.13, "learning_rate": 0.00028712658678372286, "loss": 0.649, "step": 3720}
+{"epoch": 0.13, "learning_rate": 0.0002870909953731166, "loss": 0.6683, "step": 3730}
+{"epoch": 0.13, "learning_rate": 0.00028705540396251034, "loss": 0.7738, "step": 3740}
+{"epoch": 0.13, "learning_rate": 0.00028701981255190414, "loss": 0.71, "step": 3750}
+{"epoch": 0.13, "learning_rate": 0.0002869842211412979, "loss": 0.764, "step": 3760}
+{"epoch": 0.13, "learning_rate": 0.0002869486297306916, "loss": 0.6747, "step": 3770}
+{"epoch": 0.13, "learning_rate": 0.0002869130383200854, "loss": 0.7046, "step": 3780}
+{"epoch": 0.13, "learning_rate": 0.00028687744690947915, "loss": 0.7001, "step": 3790}
+{"epoch": 0.14, "learning_rate": 0.0002868418554988729, "loss": 0.6032, "step": 3800}
+{"epoch": 0.14, "learning_rate": 0.0002868062640882667, "loss": 0.7204, "step": 3810}
+{"epoch": 0.14, "learning_rate": 0.0002867706726776604, "loss": 0.5805, "step": 3820}
+{"epoch": 0.14, "learning_rate": 0.0002867350812670542, "loss": 0.7294, "step": 3830}
+{"epoch": 0.14, "learning_rate": 0.00028669948985644795, "loss": 0.6295, "step": 3840}
+{"epoch": 0.14, "learning_rate": 0.00028666389844584175, "loss": 0.5724, "step": 3850}
+{"epoch": 0.14, "learning_rate": 0.0002866283070352355, "loss": 0.7361, "step": 3860}
+{"epoch": 0.14, "learning_rate": 0.0002865927156246292, "loss": 0.6122, "step": 3870}
+{"epoch": 0.14, "learning_rate": 0.000286557124214023, "loss": 0.7171, "step": 3880}
+{"epoch": 0.14, "learning_rate": 0.00028652153280341676, "loss": 0.6982, "step": 3890}
+{"epoch": 0.14, "learning_rate": 0.0002864859413928105, "loss": 0.6306, "step": 3900}
+{"epoch": 0.14, "learning_rate": 0.0002864503499822043, "loss": 0.68, "step": 3910}
+{"epoch": 0.14, "learning_rate": 0.00028641475857159803, "loss": 0.6748, "step": 3920}
+{"epoch": 0.14, "learning_rate": 0.00028637916716099177, "loss": 0.6766, "step": 3930}
+{"epoch": 0.14, "learning_rate": 0.0002863435757503855, "loss": 0.671, "step": 3940}
+{"epoch": 0.14, "learning_rate": 0.0002863079843397793, "loss": 0.739, "step": 3950}
+{"epoch": 0.14, "learning_rate": 0.00028627239292917304, "loss": 0.6141, "step": 3960}
+{"epoch": 0.14, "learning_rate": 0.00028623680151856684, "loss": 0.6486, "step": 3970}
+{"epoch": 0.14, "learning_rate": 0.0002862012101079606, "loss": 0.7817, "step": 3980}
+{"epoch": 0.14, "learning_rate": 0.00028616561869735437, "loss": 0.8103, "step": 3990}
+{"epoch": 0.14, "learning_rate": 0.0002861300272867481, "loss": 0.6599, "step": 4000}
+{"epoch": 0.14, "learning_rate": 0.0002860944358761419, "loss": 0.686, "step": 4010}
+{"epoch": 0.14, "learning_rate": 0.00028605884446553564, "loss": 0.7672, "step": 4020}
+{"epoch": 0.14, "learning_rate": 0.0002860232530549294, "loss": 0.8109, "step": 4030}
+{"epoch": 0.14, "learning_rate": 0.0002859876616443231, "loss": 0.7248, "step": 4040}
+{"epoch": 0.14, "learning_rate": 0.0002859520702337169, "loss": 0.6674, "step": 4050}
+{"epoch": 0.14, "learning_rate": 0.00028591647882311066, "loss": 0.7082, "step": 4060}
+{"epoch": 0.14, "learning_rate": 0.0002858808874125044, "loss": 0.6267, "step": 4070}
+{"epoch": 0.15, "learning_rate": 0.0002858452960018982, "loss": 0.6835, "step": 4080}
+{"epoch": 0.15, "learning_rate": 0.00028580970459129193, "loss": 0.6877, "step": 4090}
+{"epoch": 0.15, "learning_rate": 0.00028577411318068567, "loss": 0.6944, "step": 4100}
+{"epoch": 0.15, "learning_rate": 0.00028573852177007946, "loss": 0.799, "step": 4110}
+{"epoch": 0.15, "learning_rate": 0.0002857029303594732, "loss": 0.6408, "step": 4120}
+{"epoch": 0.15, "learning_rate": 0.000285667338948867, "loss": 0.6874, "step": 4130}
+{"epoch": 0.15, "learning_rate": 0.00028563174753826073, "loss": 0.772, "step": 4140}
+{"epoch": 0.15, "learning_rate": 0.00028559615612765453, "loss": 0.6307, "step": 4150}
+{"epoch": 0.15, "learning_rate": 0.00028556056471704827, "loss": 0.6232, "step": 4160}
+{"epoch": 0.15, "learning_rate": 0.000285524973306442, "loss": 0.7, "step": 4170}
+{"epoch": 0.15, "learning_rate": 0.0002854893818958358, "loss": 0.6334, "step": 4180}
+{"epoch": 0.15, "learning_rate": 0.00028545379048522954, "loss": 0.8453, "step": 4190}
+{"epoch": 0.15, "learning_rate": 0.0002854181990746233, "loss": 0.6225, "step": 4200}
+{"epoch": 0.15, "learning_rate": 0.00028538260766401707, "loss": 0.6716, "step": 4210}
+{"epoch": 0.15, "learning_rate": 0.0002853470162534108, "loss": 0.6603, "step": 4220}
+{"epoch": 0.15, "learning_rate": 0.00028531142484280455, "loss": 0.7166, "step": 4230}
+{"epoch": 0.15, "learning_rate": 0.00028527583343219835, "loss": 0.674, "step": 4240}
+{"epoch": 0.15, "learning_rate": 0.0002852402420215921, "loss": 0.6331, "step": 4250}
+{"epoch": 0.15, "learning_rate": 0.0002852046506109859, "loss": 0.6652, "step": 4260}
+{"epoch": 0.15, "learning_rate": 0.0002851690592003796, "loss": 0.6329, "step": 4270}
+{"epoch": 0.15, "learning_rate": 0.0002851334677897734, "loss": 0.6661, "step": 4280}
+{"epoch": 0.15, "learning_rate": 0.00028509787637916715, "loss": 0.6388, "step": 4290}
+{"epoch": 0.15, "learning_rate": 0.0002850622849685609, "loss": 0.6874, "step": 4300}
+{"epoch": 0.15, "learning_rate": 0.0002850266935579547, "loss": 0.6267, "step": 4310}
+{"epoch": 0.15, "learning_rate": 0.0002849911021473484, "loss": 0.5687, "step": 4320}
+{"epoch": 0.15, "learning_rate": 0.00028495551073674216, "loss": 0.6435, "step": 4330}
+{"epoch": 0.15, "learning_rate": 0.00028491991932613596, "loss": 0.7772, "step": 4340}
+{"epoch": 0.15, "learning_rate": 0.0002848843279155297, "loss": 0.7446, "step": 4350}
+{"epoch": 0.15, "learning_rate": 0.00028484873650492344, "loss": 0.7155, "step": 4360}
+{"epoch": 0.16, "learning_rate": 0.0002848131450943172, "loss": 0.6608, "step": 4370}
+{"epoch": 0.16, "learning_rate": 0.00028477755368371097, "loss": 0.6978, "step": 4380}
+{"epoch": 0.16, "learning_rate": 0.0002847419622731047, "loss": 0.6413, "step": 4390}
+{"epoch": 0.16, "learning_rate": 0.0002847063708624985, "loss": 0.711, "step": 4400}
+{"epoch": 0.16, "learning_rate": 0.00028467077945189224, "loss": 0.7413, "step": 4410}
+{"epoch": 0.16, "learning_rate": 0.00028463518804128603, "loss": 0.7129, "step": 4420}
+{"epoch": 0.16, "learning_rate": 0.0002845995966306798, "loss": 0.7398, "step": 4430}
+{"epoch": 0.16, "learning_rate": 0.00028456400522007357, "loss": 0.7388, "step": 4440}
+{"epoch": 0.16, "learning_rate": 0.0002845284138094673, "loss": 0.6713, "step": 4450}
+{"epoch": 0.16, "learning_rate": 0.00028449282239886105, "loss": 0.6643, "step": 4460}
+{"epoch": 0.16, "learning_rate": 0.00028445723098825484, "loss": 0.6667, "step": 4470}
+{"epoch": 0.16, "learning_rate": 0.0002844216395776486, "loss": 0.6459, "step": 4480}
+{"epoch": 0.16, "learning_rate": 0.0002843860481670423, "loss": 0.6907, "step": 4490}
+{"epoch": 0.16, "learning_rate": 0.00028435045675643606, "loss": 0.7452, "step": 4500}
+{"epoch": 0.16, "learning_rate": 0.00028431486534582985, "loss": 0.6538, "step": 4510}
+{"epoch": 0.16, "learning_rate": 0.0002842792739352236, "loss": 0.6442, "step": 4520}
+{"epoch": 0.16, "learning_rate": 0.00028424368252461733, "loss": 0.6921, "step": 4530}
+{"epoch": 0.16, "learning_rate": 0.0002842080911140111, "loss": 0.7466, "step": 4540}
+{"epoch": 0.16, "learning_rate": 0.00028417249970340486, "loss": 0.6833, "step": 4550}
+{"epoch": 0.16, "learning_rate": 0.00028413690829279866, "loss": 0.7314, "step": 4560}
+{"epoch": 0.16, "learning_rate": 0.0002841013168821924, "loss": 0.684, "step": 4570}
+{"epoch": 0.16, "learning_rate": 0.0002840657254715862, "loss": 0.657, "step": 4580}
+{"epoch": 0.16, "learning_rate": 0.00028403013406097993, "loss": 0.6492, "step": 4590}
+{"epoch": 0.16, "learning_rate": 0.00028399454265037367, "loss": 0.6837, "step": 4600}
+{"epoch": 0.16, "learning_rate": 0.00028395895123976746, "loss": 0.6173, "step": 4610}
+{"epoch": 0.16, "learning_rate": 0.0002839233598291612, "loss": 0.7272, "step": 4620}
+{"epoch": 0.16, "learning_rate": 0.00028388776841855494, "loss": 0.6564, "step": 4630}
+{"epoch": 0.16, "learning_rate": 0.00028385217700794874, "loss": 0.7441, "step": 4640}
+{"epoch": 0.17, "learning_rate": 0.0002838165855973425, "loss": 0.5988, "step": 4650}
+{"epoch": 0.17, "learning_rate": 0.0002837809941867362, "loss": 0.7319, "step": 4660}
+{"epoch": 0.17, "learning_rate": 0.00028374540277613, "loss": 0.7096, "step": 4670}
+{"epoch": 0.17, "learning_rate": 0.00028370981136552375, "loss": 0.6784, "step": 4680}
+{"epoch": 0.17, "learning_rate": 0.0002836742199549175, "loss": 0.8013, "step": 4690}
+{"epoch": 0.17, "learning_rate": 0.0002836386285443113, "loss": 0.6753, "step": 4700}
+{"epoch": 0.17, "learning_rate": 0.000283603037133705, "loss": 0.7424, "step": 4710}
+{"epoch": 0.17, "learning_rate": 0.0002835674457230988, "loss": 0.6778, "step": 4720}
+{"epoch": 0.17, "learning_rate": 0.00028353185431249255, "loss": 0.723, "step": 4730}
+{"epoch": 0.17, "learning_rate": 0.00028349626290188635, "loss": 0.676, "step": 4740}
+{"epoch": 0.17, "learning_rate": 0.0002834606714912801, "loss": 0.6816, "step": 4750}
+{"epoch": 0.17, "learning_rate": 0.0002834250800806738, "loss": 0.6436, "step": 4760}
+{"epoch": 0.17, "learning_rate": 0.0002833894886700676, "loss": 0.666, "step": 4770}
+{"epoch": 0.17, "learning_rate": 0.00028335389725946136, "loss": 0.664, "step": 4780}
+{"epoch": 0.17, "learning_rate": 0.0002833183058488551, "loss": 0.6867, "step": 4790}
+{"epoch": 0.17, "learning_rate": 0.0002832827144382489, "loss": 0.7223, "step": 4800}
+{"epoch": 0.17, "learning_rate": 0.00028324712302764263, "loss": 0.7188, "step": 4810}
+{"epoch": 0.17, "learning_rate": 0.00028321153161703637, "loss": 0.7236, "step": 4820}
+{"epoch": 0.17, "learning_rate": 0.00028317594020643017, "loss": 0.7476, "step": 4830}
+{"epoch": 0.17, "learning_rate": 0.0002831403487958239, "loss": 0.6511, "step": 4840}
+{"epoch": 0.17, "learning_rate": 0.0002831047573852177, "loss": 0.659, "step": 4850}
+{"epoch": 0.17, "learning_rate": 0.00028306916597461144, "loss": 0.7543, "step": 4860}
+{"epoch": 0.17, "learning_rate": 0.00028303357456400523, "loss": 0.662, "step": 4870}
+{"epoch": 0.17, "learning_rate": 0.00028299798315339897, "loss": 0.6815, "step": 4880}
+{"epoch": 0.17, "learning_rate": 0.0002829623917427927, "loss": 0.7013, "step": 4890}
+{"epoch": 0.17, "learning_rate": 0.0002829268003321865, "loss": 0.7242, "step": 4900}
+{"epoch": 0.17, "learning_rate": 0.00028289120892158024, "loss": 0.7088, "step": 4910}
+{"epoch": 0.17, "learning_rate": 0.000282855617510974, "loss": 0.7081, "step": 4920}
+{"epoch": 0.18, "learning_rate": 0.0002828200261003678, "loss": 0.6265, "step": 4930}
+{"epoch": 0.18, "learning_rate": 0.0002827844346897615, "loss": 0.8361, "step": 4940}
+{"epoch": 0.18, "learning_rate": 0.00028274884327915526, "loss": 0.6595, "step": 4950}
+{"epoch": 0.18, "learning_rate": 0.000282713251868549, "loss": 0.6483, "step": 4960}
+{"epoch": 0.18, "learning_rate": 0.0002826776604579428, "loss": 0.6965, "step": 4970}
+{"epoch": 0.18, "learning_rate": 0.00028264206904733653, "loss": 0.7617, "step": 4980}
+{"epoch": 0.18, "learning_rate": 0.0002826064776367303, "loss": 0.7236, "step": 4990}
+{"epoch": 0.18, "learning_rate": 0.00028257088622612406, "loss": 0.7769, "step": 5000}
+{"epoch": 0.18, "learning_rate": 0.00028253529481551786, "loss": 0.6, "step": 5010}
+{"epoch": 0.18, "learning_rate": 0.0002824997034049116, "loss": 0.7488, "step": 5020}
+{"epoch": 0.18, "learning_rate": 0.0002824641119943054, "loss": 0.598, "step": 5030}
+{"epoch": 0.18, "learning_rate": 0.00028242852058369913, "loss": 0.7598, "step": 5040}
+{"epoch": 0.18, "learning_rate": 0.00028239292917309287, "loss": 0.6441, "step": 5050}
+{"epoch": 0.18, "learning_rate": 0.0002823573377624866, "loss": 0.6564, "step": 5060}
+{"epoch": 0.18, "learning_rate": 0.0002823217463518804, "loss": 0.7177, "step": 5070}
+{"epoch": 0.18, "learning_rate": 0.00028228615494127414, "loss": 0.7513, "step": 5080}
+{"epoch": 0.18, "learning_rate": 0.0002822505635306679, "loss": 0.6029, "step": 5090}
+{"epoch": 0.18, "learning_rate": 0.0002822149721200617, "loss": 0.7096, "step": 5100}
+{"epoch": 0.18, "learning_rate": 0.0002821793807094554, "loss": 0.6043, "step": 5110}
+{"epoch": 0.18, "learning_rate": 0.00028214378929884915, "loss": 0.6816, "step": 5120}
+{"epoch": 0.18, "learning_rate": 0.00028210819788824295, "loss": 0.7107, "step": 5130}
+{"epoch": 0.18, "learning_rate": 0.0002820726064776367, "loss": 0.7088, "step": 5140}
+{"epoch": 0.18, "learning_rate": 0.0002820370150670305, "loss": 0.7065, "step": 5150}
+{"epoch": 0.18, "learning_rate": 0.0002820014236564242, "loss": 0.6974, "step": 5160}
+{"epoch": 0.18, "learning_rate": 0.000281965832245818, "loss": 0.6437, "step": 5170}
+{"epoch": 0.18, "learning_rate": 0.00028193024083521175, "loss": 0.7158, "step": 5180}
+{"epoch": 0.18, "learning_rate": 0.0002818946494246055, "loss": 0.6624, "step": 5190}
+{"epoch": 0.18, "learning_rate": 0.0002818590580139993, "loss": 0.6567, "step": 5200}
+{"epoch": 0.19, "learning_rate": 0.000281823466603393, "loss": 0.6789, "step": 5210}
+{"epoch": 0.19, "learning_rate": 0.00028178787519278676, "loss": 0.8325, "step": 5220}
+{"epoch": 0.19, "learning_rate": 0.00028175228378218056, "loss": 0.7748, "step": 5230}
+{"epoch": 0.19, "learning_rate": 0.0002817166923715743, "loss": 0.6514, "step": 5240}
+{"epoch": 0.19, "learning_rate": 0.00028168110096096804, "loss": 0.6611, "step": 5250}
+{"epoch": 0.19, "learning_rate": 0.00028164550955036183, "loss": 0.6803, "step": 5260}
+{"epoch": 0.19, "learning_rate": 0.00028160991813975557, "loss": 0.7386, "step": 5270}
+{"epoch": 0.19, "learning_rate": 0.0002815743267291493, "loss": 0.7056, "step": 5280}
+{"epoch": 0.19, "learning_rate": 0.0002815387353185431, "loss": 0.7716, "step": 5290}
+{"epoch": 0.19, "learning_rate": 0.00028150314390793684, "loss": 0.7421, "step": 5300}
+{"epoch": 0.19, "learning_rate": 0.00028146755249733064, "loss": 0.6784, "step": 5310}
+{"epoch": 0.19, "learning_rate": 0.0002814319610867244, "loss": 0.5822, "step": 5320}
+{"epoch": 0.19, "learning_rate": 0.00028139636967611817, "loss": 0.7016, "step": 5330}
+{"epoch": 0.19, "learning_rate": 0.0002813607782655119, "loss": 0.7684, "step": 5340}
+{"epoch": 0.19, "learning_rate": 0.00028132518685490565, "loss": 0.6963, "step": 5350}
+{"epoch": 0.19, "learning_rate": 0.00028128959544429944, "loss": 0.6931, "step": 5360}
+{"epoch": 0.19, "learning_rate": 0.0002812540040336932, "loss": 0.7024, "step": 5370}
+{"epoch": 0.19, "learning_rate": 0.0002812184126230869, "loss": 0.6701, "step": 5380}
+{"epoch": 0.19, "learning_rate": 0.00028118282121248066, "loss": 0.62, "step": 5390}
+{"epoch": 0.19, "learning_rate": 0.00028114722980187445, "loss": 0.6614, "step": 5400}
+{"epoch": 0.19, "learning_rate": 0.0002811116383912682, "loss": 0.6506, "step": 5410}
+{"epoch": 0.19, "learning_rate": 0.000281076046980662, "loss": 0.6427, "step": 5420}
+{"epoch": 0.19, "learning_rate": 0.0002810404555700557, "loss": 0.6979, "step": 5430}
+{"epoch": 0.19, "learning_rate": 0.0002810048641594495, "loss": 0.7202, "step": 5440}
+{"epoch": 0.19, "learning_rate": 0.00028096927274884326, "loss": 0.7734, "step": 5450}
+{"epoch": 0.19, "learning_rate": 0.00028093368133823705, "loss": 0.7284, "step": 5460}
+{"epoch": 0.19, "learning_rate": 0.0002808980899276308, "loss": 0.5981, "step": 5470}
+{"epoch": 0.19, "learning_rate": 0.00028086249851702453, "loss": 0.7213, "step": 5480}
+{"epoch": 0.2, "learning_rate": 0.0002808269071064183, "loss": 0.7447, "step": 5490}
+{"epoch": 0.2, "learning_rate": 0.00028079131569581206, "loss": 0.65, "step": 5500}
+{"epoch": 0.2, "learning_rate": 0.0002807557242852058, "loss": 0.6703, "step": 5510}
+{"epoch": 0.2, "learning_rate": 0.00028072013287459954, "loss": 0.7258, "step": 5520}
+{"epoch": 0.2, "learning_rate": 0.00028068454146399334, "loss": 0.6441, "step": 5530}
+{"epoch": 0.2, "learning_rate": 0.0002806489500533871, "loss": 0.6666, "step": 5540}
+{"epoch": 0.2, "learning_rate": 0.0002806133586427808, "loss": 0.6953, "step": 5550}
+{"epoch": 0.2, "learning_rate": 0.0002805777672321746, "loss": 0.8032, "step": 5560}
+{"epoch": 0.2, "learning_rate": 0.00028054217582156835, "loss": 0.7212, "step": 5570}
+{"epoch": 0.2, "learning_rate": 0.00028050658441096214, "loss": 0.7961, "step": 5580}
+{"epoch": 0.2, "learning_rate": 0.0002804709930003559, "loss": 0.6428, "step": 5590}
+{"epoch": 0.2, "learning_rate": 0.0002804354015897497, "loss": 0.6827, "step": 5600}
+{"epoch": 0.2, "learning_rate": 0.0002803998101791434, "loss": 0.6803, "step": 5610}
+{"epoch": 0.2, "learning_rate": 0.00028036421876853715, "loss": 0.6114, "step": 5620}
+{"epoch": 0.2, "learning_rate": 0.00028032862735793095, "loss": 0.6894, "step": 5630}
+{"epoch": 0.2, "learning_rate": 0.0002802930359473247, "loss": 0.6454, "step": 5640}
+{"epoch": 0.2, "learning_rate": 0.00028025744453671843, "loss": 0.6649, "step": 5650}
+{"epoch": 0.2, "learning_rate": 0.0002802218531261122, "loss": 0.6526, "step": 5660}
+{"epoch": 0.2, "learning_rate": 0.00028018626171550596, "loss": 0.6863, "step": 5670}
+{"epoch": 0.2, "learning_rate": 0.0002801506703048997, "loss": 0.6503, "step": 5680}
+{"epoch": 0.2, "learning_rate": 0.0002801150788942935, "loss": 0.7383, "step": 5690}
+{"epoch": 0.2, "learning_rate": 0.00028007948748368723, "loss": 0.6345, "step": 5700}
+{"epoch": 0.2, "learning_rate": 0.00028004389607308097, "loss": 0.7334, "step": 5710}
+{"epoch": 0.2, "learning_rate": 0.00028000830466247477, "loss": 0.8069, "step": 5720}
+{"epoch": 0.2, "learning_rate": 0.0002799727132518685, "loss": 0.6889, "step": 5730}
+{"epoch": 0.2, "learning_rate": 0.0002799371218412623, "loss": 0.6738, "step": 5740}
+{"epoch": 0.2, "learning_rate": 0.00027990153043065604, "loss": 0.6819, "step": 5750}
+{"epoch": 0.2, "learning_rate": 0.00027986593902004983, "loss": 0.6372, "step": 5760}
+{"epoch": 0.21, "learning_rate": 0.00027983034760944357, "loss": 0.6791, "step": 5770}
+{"epoch": 0.21, "learning_rate": 0.0002797947561988373, "loss": 0.7331, "step": 5780}
+{"epoch": 0.21, "learning_rate": 0.0002797591647882311, "loss": 0.5917, "step": 5790}
+{"epoch": 0.21, "learning_rate": 0.00027972357337762484, "loss": 0.7269, "step": 5800}
+{"epoch": 0.21, "learning_rate": 0.0002796879819670186, "loss": 0.7028, "step": 5810}
+{"epoch": 0.21, "learning_rate": 0.0002796523905564124, "loss": 0.64, "step": 5820}
+{"epoch": 0.21, "learning_rate": 0.0002796167991458061, "loss": 0.6924, "step": 5830}
+{"epoch": 0.21, "learning_rate": 0.00027958120773519986, "loss": 0.5877, "step": 5840}
+{"epoch": 0.21, "learning_rate": 0.00027954561632459365, "loss": 0.6111, "step": 5850}
+{"epoch": 0.21, "learning_rate": 0.0002795100249139874, "loss": 0.5829, "step": 5860}
+{"epoch": 0.21, "learning_rate": 0.0002794744335033812, "loss": 0.6971, "step": 5870}
+{"epoch": 0.21, "learning_rate": 0.0002794388420927749, "loss": 0.6758, "step": 5880}
+{"epoch": 0.21, "learning_rate": 0.00027940325068216866, "loss": 0.7192, "step": 5890}
+{"epoch": 0.21, "learning_rate": 0.00027936765927156246, "loss": 0.7653, "step": 5900}
+{"epoch": 0.21, "learning_rate": 0.0002793320678609562, "loss": 0.6789, "step": 5910}
+{"epoch": 0.21, "learning_rate": 0.00027929647645035, "loss": 0.7232, "step": 5920}
+{"epoch": 0.21, "learning_rate": 0.00027926088503974373, "loss": 0.6553, "step": 5930}
+{"epoch": 0.21, "learning_rate": 0.00027922529362913747, "loss": 0.662, "step": 5940}
+{"epoch": 0.21, "learning_rate": 0.00027918970221853126, "loss": 0.7693, "step": 5950}
+{"epoch": 0.21, "learning_rate": 0.000279154110807925, "loss": 0.6878, "step": 5960}
+{"epoch": 0.21, "learning_rate": 0.00027911851939731874, "loss": 0.672, "step": 5970}
+{"epoch": 0.21, "learning_rate": 0.0002790829279867125, "loss": 0.6826, "step": 5980}
+{"epoch": 0.21, "learning_rate": 0.0002790473365761063, "loss": 0.6641, "step": 5990}
+{"epoch": 0.21, "learning_rate": 0.0002790117451655, "loss": 0.6687, "step": 6000}
+{"epoch": 0.21, "learning_rate": 0.0002789761537548938, "loss": 0.7214, "step": 6010}
+{"epoch": 0.21, "learning_rate": 0.00027894056234428755, "loss": 0.6375, "step": 6020}
+{"epoch": 0.21, "learning_rate": 0.00027890497093368134, "loss": 0.7117, "step": 6030}
+{"epoch": 0.21, "learning_rate": 0.0002788729386641357, "loss": 0.6257, "step": 6040}
+{"epoch": 0.22, "learning_rate": 0.00027883734725352947, "loss": 0.5788, "step": 6050}
+{"epoch": 0.22, "learning_rate": 0.0002788017558429232, "loss": 0.79, "step": 6060}
+{"epoch": 0.22, "learning_rate": 0.000278766164432317, "loss": 0.6082, "step": 6070}
+{"epoch": 0.22, "learning_rate": 0.00027873057302171074, "loss": 0.673, "step": 6080}
+{"epoch": 0.22, "learning_rate": 0.0002786949816111045, "loss": 0.6672, "step": 6090}
+{"epoch": 0.22, "learning_rate": 0.00027865939020049827, "loss": 0.7397, "step": 6100}
+{"epoch": 0.22, "learning_rate": 0.000278623798789892, "loss": 0.6331, "step": 6110}
+{"epoch": 0.22, "learning_rate": 0.00027858820737928575, "loss": 0.6923, "step": 6120}
+{"epoch": 0.22, "learning_rate": 0.00027855261596867954, "loss": 0.8609, "step": 6130}
+{"epoch": 0.22, "learning_rate": 0.0002785170245580733, "loss": 0.6959, "step": 6140}
+{"epoch": 0.22, "learning_rate": 0.000278481433147467, "loss": 0.7997, "step": 6150}
+{"epoch": 0.22, "learning_rate": 0.0002784458417368608, "loss": 0.6886, "step": 6160}
+{"epoch": 0.22, "learning_rate": 0.00027841025032625456, "loss": 0.6786, "step": 6170}
+{"epoch": 0.22, "learning_rate": 0.00027837465891564835, "loss": 0.616, "step": 6180}
+{"epoch": 0.22, "learning_rate": 0.0002783390675050421, "loss": 0.6354, "step": 6190}
+{"epoch": 0.22, "learning_rate": 0.0002783070352354965, "loss": 0.6364, "step": 6200}
+{"epoch": 0.22, "learning_rate": 0.00027827144382489027, "loss": 0.6525, "step": 6210}
+{"epoch": 0.22, "learning_rate": 0.000278235852414284, "loss": 0.689, "step": 6220}
+{"epoch": 0.22, "learning_rate": 0.00027820026100367775, "loss": 0.691, "step": 6230}
+{"epoch": 0.22, "learning_rate": 0.0002781646695930715, "loss": 0.7241, "step": 6240}
+{"epoch": 0.22, "learning_rate": 0.0002781290781824653, "loss": 0.7144, "step": 6250}
+{"epoch": 0.22, "learning_rate": 0.000278093486771859, "loss": 0.7479, "step": 6260}
+{"epoch": 0.22, "learning_rate": 0.00027805789536125276, "loss": 0.6068, "step": 6270}
+{"epoch": 0.22, "learning_rate": 0.00027802230395064656, "loss": 0.6501, "step": 6280}
+{"epoch": 0.22, "learning_rate": 0.0002779867125400403, "loss": 0.7616, "step": 6290}
+{"epoch": 0.22, "learning_rate": 0.0002779511211294341, "loss": 0.6096, "step": 6300}
+{"epoch": 0.22, "learning_rate": 0.00027791552971882783, "loss": 0.7053, "step": 6310}
+{"epoch": 0.22, "learning_rate": 0.0002778799383082216, "loss": 0.7448, "step": 6320}
+{"epoch": 0.23, "learning_rate": 0.00027784434689761536, "loss": 0.7046, "step": 6330}
+{"epoch": 0.23, "learning_rate": 0.0002778087554870091, "loss": 0.6033, "step": 6340}
+{"epoch": 0.23, "learning_rate": 0.0002777731640764029, "loss": 0.6678, "step": 6350}
+{"epoch": 0.23, "learning_rate": 0.00027773757266579663, "loss": 0.6845, "step": 6360}
+{"epoch": 0.23, "learning_rate": 0.00027770198125519037, "loss": 0.7314, "step": 6370}
+{"epoch": 0.23, "learning_rate": 0.00027766638984458417, "loss": 0.5838, "step": 6380}
+{"epoch": 0.23, "learning_rate": 0.0002776307984339779, "loss": 0.6447, "step": 6390}
+{"epoch": 0.23, "learning_rate": 0.00027759520702337165, "loss": 0.6738, "step": 6400}
+{"epoch": 0.23, "learning_rate": 0.00027755961561276544, "loss": 0.7543, "step": 6410}
+{"epoch": 0.23, "learning_rate": 0.0002775240242021592, "loss": 0.6558, "step": 6420}
+{"epoch": 0.23, "learning_rate": 0.0002774884327915529, "loss": 0.7479, "step": 6430}
+{"epoch": 0.23, "learning_rate": 0.0002774528413809467, "loss": 0.6823, "step": 6440}
+{"epoch": 0.23, "learning_rate": 0.00027741724997034045, "loss": 0.7755, "step": 6450}
+{"epoch": 0.23, "learning_rate": 0.00027738165855973424, "loss": 0.6771, "step": 6460}
+{"epoch": 0.23, "learning_rate": 0.000277346067149128, "loss": 0.6559, "step": 6470}
+{"epoch": 0.23, "learning_rate": 0.0002773104757385218, "loss": 0.746, "step": 6480}
+{"epoch": 0.23, "learning_rate": 0.0002772748843279155, "loss": 0.6439, "step": 6490}
+{"epoch": 0.23, "learning_rate": 0.00027723929291730926, "loss": 0.6347, "step": 6500}
+{"epoch": 0.23, "learning_rate": 0.00027720370150670305, "loss": 0.634, "step": 6510}
+{"epoch": 0.23, "learning_rate": 0.0002771681100960968, "loss": 0.7174, "step": 6520}
+{"epoch": 0.23, "learning_rate": 0.00027713251868549053, "loss": 0.6798, "step": 6530}
+{"epoch": 0.23, "learning_rate": 0.0002770969272748843, "loss": 0.6309, "step": 6540}
+{"epoch": 0.23, "learning_rate": 0.00027706133586427806, "loss": 0.6051, "step": 6550}
+{"epoch": 0.23, "learning_rate": 0.0002770257444536718, "loss": 0.7146, "step": 6560}
+{"epoch": 0.23, "learning_rate": 0.0002769901530430656, "loss": 0.7369, "step": 6570}
+{"epoch": 0.23, "learning_rate": 0.00027695456163245934, "loss": 0.6924, "step": 6580}
+{"epoch": 0.23, "learning_rate": 0.0002769189702218531, "loss": 0.7319, "step": 6590}
+{"epoch": 0.23, "learning_rate": 0.00027688337881124687, "loss": 0.6855, "step": 6600}
+{"epoch": 0.23, "learning_rate": 0.0002768477874006406, "loss": 0.7762, "step": 6610}
+{"epoch": 0.24, "learning_rate": 0.0002768121959900344, "loss": 0.5841, "step": 6620}
+{"epoch": 0.24, "learning_rate": 0.00027677660457942814, "loss": 0.7067, "step": 6630}
+{"epoch": 0.24, "learning_rate": 0.00027674101316882193, "loss": 0.6539, "step": 6640}
+{"epoch": 0.24, "learning_rate": 0.0002767054217582157, "loss": 0.7795, "step": 6650}
+{"epoch": 0.24, "learning_rate": 0.0002766698303476094, "loss": 0.6752, "step": 6660}
+{"epoch": 0.24, "learning_rate": 0.0002766342389370032, "loss": 0.6993, "step": 6670}
+{"epoch": 0.24, "learning_rate": 0.00027659864752639695, "loss": 0.7318, "step": 6680}
+{"epoch": 0.24, "learning_rate": 0.0002765630561157907, "loss": 0.7325, "step": 6690}
+{"epoch": 0.24, "learning_rate": 0.0002765274647051844, "loss": 0.6644, "step": 6700}
+{"epoch": 0.24, "learning_rate": 0.0002764918732945782, "loss": 0.6358, "step": 6710}
+{"epoch": 0.24, "learning_rate": 0.00027645628188397196, "loss": 0.6958, "step": 6720}
+{"epoch": 0.24, "learning_rate": 0.0002764206904733657, "loss": 0.6402, "step": 6730}
+{"epoch": 0.24, "learning_rate": 0.0002763850990627595, "loss": 0.7679, "step": 6740}
+{"epoch": 0.24, "learning_rate": 0.00027634950765215323, "loss": 0.6876, "step": 6750}
+{"epoch": 0.24, "learning_rate": 0.000276313916241547, "loss": 0.6936, "step": 6760}
+{"epoch": 0.24, "learning_rate": 0.00027627832483094076, "loss": 0.6362, "step": 6770}
+{"epoch": 0.24, "learning_rate": 0.00027624273342033456, "loss": 0.7141, "step": 6780}
+{"epoch": 0.24, "learning_rate": 0.0002762071420097283, "loss": 0.6013, "step": 6790}
+{"epoch": 0.24, "learning_rate": 0.00027617155059912204, "loss": 0.6325, "step": 6800}
+{"epoch": 0.24, "learning_rate": 0.00027613595918851583, "loss": 0.5862, "step": 6810}
+{"epoch": 0.24, "learning_rate": 0.00027610036777790957, "loss": 0.6688, "step": 6820}
+{"epoch": 0.24, "learning_rate": 0.0002760647763673033, "loss": 0.685, "step": 6830}
+{"epoch": 0.24, "learning_rate": 0.0002760291849566971, "loss": 0.7214, "step": 6840}
+{"epoch": 0.24, "learning_rate": 0.00027599359354609084, "loss": 0.6369, "step": 6850}
+{"epoch": 0.24, "learning_rate": 0.0002759580021354846, "loss": 0.6174, "step": 6860}
+{"epoch": 0.24, "learning_rate": 0.0002759224107248784, "loss": 0.781, "step": 6870}
+{"epoch": 0.24, "learning_rate": 0.0002758868193142721, "loss": 0.6663, "step": 6880}
+{"epoch": 0.24, "learning_rate": 0.0002758512279036659, "loss": 0.6706, "step": 6890}
+{"epoch": 0.25, "learning_rate": 0.00027581563649305965, "loss": 0.7238, "step": 6900}
+{"epoch": 0.25, "learning_rate": 0.00027578004508245344, "loss": 0.7005, "step": 6910}
+{"epoch": 0.25, "learning_rate": 0.0002757444536718472, "loss": 0.722, "step": 6920}
+{"epoch": 0.25, "learning_rate": 0.0002757088622612409, "loss": 0.6901, "step": 6930}
+{"epoch": 0.25, "learning_rate": 0.0002756732708506347, "loss": 0.6618, "step": 6940}
+{"epoch": 0.25, "learning_rate": 0.00027563767944002845, "loss": 0.6387, "step": 6950}
+{"epoch": 0.25, "learning_rate": 0.0002756020880294222, "loss": 0.6953, "step": 6960}
+{"epoch": 0.25, "learning_rate": 0.000275566496618816, "loss": 0.6862, "step": 6970}
+{"epoch": 0.25, "learning_rate": 0.0002755309052082097, "loss": 0.6424, "step": 6980}
+{"epoch": 0.25, "learning_rate": 0.00027549531379760347, "loss": 0.7637, "step": 6990}
+{"epoch": 0.25, "learning_rate": 0.00027545972238699726, "loss": 0.6712, "step": 7000}
+{"epoch": 0.25, "learning_rate": 0.000275424130976391, "loss": 0.7253, "step": 7010}
+{"epoch": 0.25, "learning_rate": 0.00027538853956578474, "loss": 0.6319, "step": 7020}
+{"epoch": 0.25, "learning_rate": 0.00027535294815517853, "loss": 0.7082, "step": 7030}
+{"epoch": 0.25, "learning_rate": 0.00027531735674457227, "loss": 0.6681, "step": 7040}
+{"epoch": 0.25, "learning_rate": 0.00027528176533396607, "loss": 0.7333, "step": 7050}
+{"epoch": 0.25, "learning_rate": 0.0002752461739233598, "loss": 0.6208, "step": 7060}
+{"epoch": 0.25, "learning_rate": 0.0002752105825127536, "loss": 0.7219, "step": 7070}
+{"epoch": 0.25, "learning_rate": 0.00027517499110214734, "loss": 0.729, "step": 7080}
+{"epoch": 0.25, "learning_rate": 0.0002751393996915411, "loss": 0.699, "step": 7090}
+{"epoch": 0.25, "learning_rate": 0.00027510380828093487, "loss": 0.6561, "step": 7100}
+{"epoch": 0.25, "learning_rate": 0.0002750682168703286, "loss": 0.6682, "step": 7110}
+{"epoch": 0.25, "learning_rate": 0.00027503262545972235, "loss": 0.7022, "step": 7120}
+{"epoch": 0.25, "learning_rate": 0.00027499703404911614, "loss": 0.6909, "step": 7130}
+{"epoch": 0.25, "learning_rate": 0.0002749614426385099, "loss": 0.6412, "step": 7140}
+{"epoch": 0.25, "learning_rate": 0.0002749258512279036, "loss": 0.639, "step": 7150}
+{"epoch": 0.25, "learning_rate": 0.00027489025981729736, "loss": 0.7439, "step": 7160}
+{"epoch": 0.25, "learning_rate": 0.00027485466840669116, "loss": 0.724, "step": 7170}
+{"epoch": 0.26, "learning_rate": 0.0002748190769960849, "loss": 0.6737, "step": 7180}
+{"epoch": 0.26, "learning_rate": 0.0002747834855854787, "loss": 0.6141, "step": 7190}
+{"epoch": 0.26, "learning_rate": 0.00027474789417487243, "loss": 0.7455, "step": 7200}
+{"epoch": 0.26, "learning_rate": 0.0002747123027642662, "loss": 0.7237, "step": 7210}
+{"epoch": 0.26, "learning_rate": 0.00027467671135365996, "loss": 0.6049, "step": 7220}
+{"epoch": 0.26, "learning_rate": 0.00027464111994305375, "loss": 0.7072, "step": 7230}
+{"epoch": 0.26, "learning_rate": 0.0002746055285324475, "loss": 0.7085, "step": 7240}
+{"epoch": 0.26, "learning_rate": 0.00027456993712184123, "loss": 0.7091, "step": 7250}
+{"epoch": 0.26, "learning_rate": 0.000274534345711235, "loss": 0.6661, "step": 7260}
+{"epoch": 0.26, "learning_rate": 0.00027449875430062877, "loss": 0.6861, "step": 7270}
+{"epoch": 0.26, "learning_rate": 0.0002744631628900225, "loss": 0.6816, "step": 7280}
+{"epoch": 0.26, "learning_rate": 0.00027442757147941625, "loss": 0.6438, "step": 7290}
+{"epoch": 0.26, "learning_rate": 0.00027439198006881004, "loss": 0.6755, "step": 7300}
+{"epoch": 0.26, "learning_rate": 0.0002743563886582038, "loss": 0.6797, "step": 7310}
+{"epoch": 0.26, "learning_rate": 0.00027432079724759757, "loss": 0.6453, "step": 7320}
+{"epoch": 0.26, "learning_rate": 0.0002742852058369913, "loss": 0.7137, "step": 7330}
+{"epoch": 0.26, "learning_rate": 0.00027424961442638505, "loss": 0.6215, "step": 7340}
+{"epoch": 0.26, "learning_rate": 0.00027421402301577885, "loss": 0.6754, "step": 7350}
+{"epoch": 0.26, "learning_rate": 0.0002741784316051726, "loss": 0.6035, "step": 7360}
+{"epoch": 0.26, "learning_rate": 0.0002741428401945664, "loss": 0.7422, "step": 7370}
+{"epoch": 0.26, "learning_rate": 0.0002741072487839601, "loss": 0.6829, "step": 7380}
+{"epoch": 0.26, "learning_rate": 0.00027407165737335386, "loss": 0.6616, "step": 7390}
+{"epoch": 0.26, "learning_rate": 0.00027403606596274765, "loss": 0.6977, "step": 7400}
+{"epoch": 0.26, "learning_rate": 0.0002740004745521414, "loss": 0.6686, "step": 7410}
+{"epoch": 0.26, "learning_rate": 0.00027396488314153513, "loss": 0.693, "step": 7420}
+{"epoch": 0.26, "learning_rate": 0.0002739292917309289, "loss": 0.7555, "step": 7430}
+{"epoch": 0.26, "learning_rate": 0.00027389370032032266, "loss": 0.6327, "step": 7440}
+{"epoch": 0.26, "learning_rate": 0.0002738581089097164, "loss": 0.6916, "step": 7450}
+{"epoch": 0.27, "learning_rate": 0.0002738225174991102, "loss": 0.6086, "step": 7460}
+{"epoch": 0.27, "learning_rate": 0.00027378692608850394, "loss": 0.7267, "step": 7470}
+{"epoch": 0.27, "learning_rate": 0.00027375133467789773, "loss": 0.6479, "step": 7480}
+{"epoch": 0.27, "learning_rate": 0.00027371574326729147, "loss": 0.6953, "step": 7490}
+{"epoch": 0.27, "learning_rate": 0.00027368015185668526, "loss": 0.6323, "step": 7500}
+{"epoch": 0.27, "learning_rate": 0.000273644560446079, "loss": 0.6159, "step": 7510}
+{"epoch": 0.27, "learning_rate": 0.00027360896903547274, "loss": 0.7172, "step": 7520}
+{"epoch": 0.27, "learning_rate": 0.00027357337762486653, "loss": 0.7004, "step": 7530}
+{"epoch": 0.27, "learning_rate": 0.0002735377862142603, "loss": 0.66, "step": 7540}
+{"epoch": 0.27, "learning_rate": 0.000273502194803654, "loss": 0.6667, "step": 7550}
+{"epoch": 0.27, "learning_rate": 0.0002734666033930478, "loss": 0.7522, "step": 7560}
+{"epoch": 0.27, "learning_rate": 0.00027343101198244155, "loss": 0.6494, "step": 7570}
+{"epoch": 0.27, "learning_rate": 0.0002733954205718353, "loss": 0.6456, "step": 7580}
+{"epoch": 0.27, "learning_rate": 0.0002733598291612291, "loss": 0.6514, "step": 7590}
+{"epoch": 0.27, "learning_rate": 0.0002733242377506228, "loss": 0.7416, "step": 7600}
+{"epoch": 0.27, "learning_rate": 0.00027328864634001656, "loss": 0.7246, "step": 7610}
+{"epoch": 0.27, "learning_rate": 0.00027325305492941035, "loss": 0.7575, "step": 7620}
+{"epoch": 0.27, "learning_rate": 0.0002732174635188041, "loss": 0.5808, "step": 7630}
+{"epoch": 0.27, "learning_rate": 0.0002731818721081979, "loss": 0.5846, "step": 7640}
+{"epoch": 0.27, "learning_rate": 0.0002731462806975916, "loss": 0.7003, "step": 7650}
+{"epoch": 0.27, "learning_rate": 0.0002731106892869854, "loss": 0.6482, "step": 7660}
+{"epoch": 0.27, "learning_rate": 0.00027307509787637916, "loss": 0.7011, "step": 7670}
+{"epoch": 0.27, "learning_rate": 0.0002730395064657729, "loss": 0.622, "step": 7680}
+{"epoch": 0.27, "learning_rate": 0.0002730039150551667, "loss": 0.7317, "step": 7690}
+{"epoch": 0.27, "learning_rate": 0.00027296832364456043, "loss": 0.6823, "step": 7700}
+{"epoch": 0.27, "learning_rate": 0.00027293273223395417, "loss": 0.6137, "step": 7710}
+{"epoch": 0.27, "learning_rate": 0.0002728971408233479, "loss": 0.662, "step": 7720}
+{"epoch": 0.27, "learning_rate": 0.0002728615494127417, "loss": 0.6742, "step": 7730}
+{"epoch": 0.28, "learning_rate": 0.00027282595800213544, "loss": 0.5736, "step": 7740}
+{"epoch": 0.28, "learning_rate": 0.0002727903665915292, "loss": 0.618, "step": 7750}
+{"epoch": 0.28, "learning_rate": 0.000272754775180923, "loss": 0.6998, "step": 7760}
+{"epoch": 0.28, "learning_rate": 0.0002727191837703167, "loss": 0.7414, "step": 7770}
+{"epoch": 0.28, "learning_rate": 0.0002726835923597105, "loss": 0.7506, "step": 7780}
+{"epoch": 0.28, "learning_rate": 0.00027264800094910425, "loss": 0.7766, "step": 7790}
+{"epoch": 0.28, "learning_rate": 0.00027261240953849804, "loss": 0.635, "step": 7800}
+{"epoch": 0.28, "learning_rate": 0.0002725768181278918, "loss": 0.7063, "step": 7810}
+{"epoch": 0.28, "learning_rate": 0.0002725412267172855, "loss": 0.7736, "step": 7820}
+{"epoch": 0.28, "learning_rate": 0.0002725056353066793, "loss": 0.6714, "step": 7830}
+{"epoch": 0.28, "learning_rate": 0.00027247004389607305, "loss": 0.6729, "step": 7840}
+{"epoch": 0.28, "learning_rate": 0.0002724344524854668, "loss": 0.6707, "step": 7850}
+{"epoch": 0.28, "learning_rate": 0.0002723988610748606, "loss": 0.6163, "step": 7860}
+{"epoch": 0.28, "learning_rate": 0.0002723632696642543, "loss": 0.5852, "step": 7870}
+{"epoch": 0.28, "learning_rate": 0.00027232767825364807, "loss": 0.6661, "step": 7880}
+{"epoch": 0.28, "learning_rate": 0.00027229208684304186, "loss": 0.6629, "step": 7890}
+{"epoch": 0.28, "learning_rate": 0.0002722564954324356, "loss": 0.7385, "step": 7900}
+{"epoch": 0.28, "learning_rate": 0.0002722209040218294, "loss": 0.6147, "step": 7910}
+{"epoch": 0.28, "learning_rate": 0.00027218531261122313, "loss": 0.6261, "step": 7920}
+{"epoch": 0.28, "learning_rate": 0.0002721497212006169, "loss": 0.6707, "step": 7930}
+{"epoch": 0.28, "learning_rate": 0.00027211412979001067, "loss": 0.6723, "step": 7940}
+{"epoch": 0.28, "learning_rate": 0.0002720785383794044, "loss": 0.7113, "step": 7950}
+{"epoch": 0.28, "learning_rate": 0.0002720429469687982, "loss": 0.6316, "step": 7960}
+{"epoch": 0.28, "learning_rate": 0.00027200735555819194, "loss": 0.7423, "step": 7970}
+{"epoch": 0.28, "learning_rate": 0.0002719717641475857, "loss": 0.7018, "step": 7980}
+{"epoch": 0.28, "learning_rate": 0.00027193617273697947, "loss": 0.6973, "step": 7990}
+{"epoch": 0.28, "learning_rate": 0.0002719005813263732, "loss": 0.7192, "step": 8000}
+{"epoch": 0.28, "learning_rate": 0.00027186498991576695, "loss": 0.6437, "step": 8010}
+{"epoch": 0.29, "learning_rate": 0.00027182939850516074, "loss": 0.7277, "step": 8020}
+{"epoch": 0.29, "learning_rate": 0.0002717938070945545, "loss": 0.6786, "step": 8030}
+{"epoch": 0.29, "learning_rate": 0.0002717582156839482, "loss": 0.652, "step": 8040}
+{"epoch": 0.29, "learning_rate": 0.000271722624273342, "loss": 0.6803, "step": 8050}
+{"epoch": 0.29, "learning_rate": 0.00027168703286273576, "loss": 0.787, "step": 8060}
+{"epoch": 0.29, "learning_rate": 0.00027165144145212955, "loss": 0.6576, "step": 8070}
+{"epoch": 0.29, "learning_rate": 0.0002716158500415233, "loss": 0.7551, "step": 8080}
+{"epoch": 0.29, "learning_rate": 0.0002715802586309171, "loss": 0.6326, "step": 8090}
+{"epoch": 0.29, "learning_rate": 0.0002715446672203108, "loss": 0.7833, "step": 8100}
+{"epoch": 0.29, "learning_rate": 0.00027150907580970456, "loss": 0.6458, "step": 8110}
+{"epoch": 0.29, "learning_rate": 0.00027147348439909836, "loss": 0.6222, "step": 8120}
+{"epoch": 0.29, "learning_rate": 0.0002714378929884921, "loss": 0.6498, "step": 8130}
+{"epoch": 0.29, "learning_rate": 0.00027140230157788583, "loss": 0.7359, "step": 8140}
+{"epoch": 0.29, "learning_rate": 0.00027136671016727963, "loss": 0.5633, "step": 8150}
+{"epoch": 0.29, "learning_rate": 0.00027133111875667337, "loss": 0.5984, "step": 8160}
+{"epoch": 0.29, "learning_rate": 0.0002712955273460671, "loss": 0.7422, "step": 8170}
+{"epoch": 0.29, "learning_rate": 0.00027125993593546085, "loss": 0.7077, "step": 8180}
+{"epoch": 0.29, "learning_rate": 0.00027122434452485464, "loss": 0.8808, "step": 8190}
+{"epoch": 0.29, "learning_rate": 0.0002711887531142484, "loss": 0.7417, "step": 8200}
+{"epoch": 0.29, "learning_rate": 0.0002711531617036422, "loss": 0.683, "step": 8210}
+{"epoch": 0.29, "learning_rate": 0.0002711175702930359, "loss": 0.7161, "step": 8220}
+{"epoch": 0.29, "learning_rate": 0.0002710819788824297, "loss": 0.7363, "step": 8230}
+{"epoch": 0.29, "learning_rate": 0.00027104638747182345, "loss": 0.7293, "step": 8240}
+{"epoch": 0.29, "learning_rate": 0.00027101079606121724, "loss": 0.7824, "step": 8250}
+{"epoch": 0.29, "learning_rate": 0.000270975204650611, "loss": 0.6711, "step": 8260}
+{"epoch": 0.29, "learning_rate": 0.0002709396132400047, "loss": 0.6697, "step": 8270}
+{"epoch": 0.29, "learning_rate": 0.00027090402182939846, "loss": 0.6549, "step": 8280}
+{"epoch": 0.29, "learning_rate": 0.00027086843041879225, "loss": 0.5806, "step": 8290}
+{"epoch": 0.3, "learning_rate": 0.000270832839008186, "loss": 0.6773, "step": 8300}
+{"epoch": 0.3, "learning_rate": 0.00027079724759757973, "loss": 0.6777, "step": 8310}
+{"epoch": 0.3, "learning_rate": 0.0002707616561869735, "loss": 0.7535, "step": 8320}
+{"epoch": 0.3, "learning_rate": 0.00027072606477636726, "loss": 0.6484, "step": 8330}
+{"epoch": 0.3, "learning_rate": 0.000270690473365761, "loss": 0.6953, "step": 8340}
+{"epoch": 0.3, "learning_rate": 0.0002706548819551548, "loss": 0.6748, "step": 8350}
+{"epoch": 0.3, "learning_rate": 0.00027061929054454854, "loss": 0.6196, "step": 8360}
+{"epoch": 0.3, "learning_rate": 0.00027058369913394233, "loss": 0.6543, "step": 8370}
+{"epoch": 0.3, "learning_rate": 0.00027054810772333607, "loss": 0.6752, "step": 8380}
+{"epoch": 0.3, "learning_rate": 0.00027051251631272986, "loss": 0.6977, "step": 8390}
+{"epoch": 0.3, "learning_rate": 0.0002704769249021236, "loss": 0.6955, "step": 8400}
+{"epoch": 0.3, "learning_rate": 0.00027044133349151734, "loss": 0.7028, "step": 8410}
+{"epoch": 0.3, "learning_rate": 0.00027040574208091114, "loss": 0.7077, "step": 8420}
+{"epoch": 0.3, "learning_rate": 0.0002703701506703049, "loss": 0.6368, "step": 8430}
+{"epoch": 0.3, "learning_rate": 0.0002703345592596986, "loss": 0.6696, "step": 8440}
+{"epoch": 0.3, "learning_rate": 0.0002702989678490924, "loss": 0.639, "step": 8450}
+{"epoch": 0.3, "learning_rate": 0.00027026337643848615, "loss": 0.7711, "step": 8460}
+{"epoch": 0.3, "learning_rate": 0.0002702277850278799, "loss": 0.7003, "step": 8470}
+{"epoch": 0.3, "learning_rate": 0.0002701921936172737, "loss": 0.7199, "step": 8480}
+{"epoch": 0.3, "learning_rate": 0.0002701566022066674, "loss": 0.6721, "step": 8490}
+{"epoch": 0.3, "learning_rate": 0.0002701210107960612, "loss": 0.6238, "step": 8500}
+{"epoch": 0.3, "learning_rate": 0.00027008541938545495, "loss": 0.6396, "step": 8510}
+{"epoch": 0.3, "learning_rate": 0.00027004982797484875, "loss": 0.7214, "step": 8520}
+{"epoch": 0.3, "learning_rate": 0.0002700142365642425, "loss": 0.7322, "step": 8530}
+{"epoch": 0.3, "learning_rate": 0.0002699786451536362, "loss": 0.6307, "step": 8540}
+{"epoch": 0.3, "learning_rate": 0.00026994305374303, "loss": 0.595, "step": 8550}
+{"epoch": 0.3, "learning_rate": 0.00026990746233242376, "loss": 0.6987, "step": 8560}
+{"epoch": 0.3, "learning_rate": 0.0002698718709218175, "loss": 0.6147, "step": 8570}
+{"epoch": 0.31, "learning_rate": 0.0002698362795112113, "loss": 0.7344, "step": 8580}
+{"epoch": 0.31, "learning_rate": 0.00026980068810060503, "loss": 0.7043, "step": 8590}
+{"epoch": 0.31, "learning_rate": 0.00026976509668999877, "loss": 0.7113, "step": 8600}
+{"epoch": 0.31, "learning_rate": 0.00026972950527939256, "loss": 0.6195, "step": 8610}
+{"epoch": 0.31, "learning_rate": 0.0002696939138687863, "loss": 0.7611, "step": 8620}
+{"epoch": 0.31, "learning_rate": 0.00026965832245818004, "loss": 0.6978, "step": 8630}
+{"epoch": 0.31, "learning_rate": 0.00026962273104757384, "loss": 0.6013, "step": 8640}
+{"epoch": 0.31, "learning_rate": 0.0002695871396369676, "loss": 0.6677, "step": 8650}
+{"epoch": 0.31, "learning_rate": 0.00026955154822636137, "loss": 0.641, "step": 8660}
+{"epoch": 0.31, "learning_rate": 0.0002695159568157551, "loss": 0.7703, "step": 8670}
+{"epoch": 0.31, "learning_rate": 0.0002694803654051489, "loss": 0.7784, "step": 8680}
+{"epoch": 0.31, "learning_rate": 0.00026944477399454264, "loss": 0.6994, "step": 8690}
+{"epoch": 0.31, "learning_rate": 0.0002694091825839364, "loss": 0.6066, "step": 8700}
+{"epoch": 0.31, "learning_rate": 0.0002693735911733302, "loss": 0.5995, "step": 8710}
+{"epoch": 0.31, "learning_rate": 0.0002693379997627239, "loss": 0.6666, "step": 8720}
+{"epoch": 0.31, "learning_rate": 0.00026930240835211765, "loss": 0.608, "step": 8730}
+{"epoch": 0.31, "learning_rate": 0.0002692668169415114, "loss": 0.6598, "step": 8740}
+{"epoch": 0.31, "learning_rate": 0.0002692312255309052, "loss": 0.7329, "step": 8750}
+{"epoch": 0.31, "learning_rate": 0.00026919563412029893, "loss": 0.6537, "step": 8760}
+{"epoch": 0.31, "learning_rate": 0.00026916004270969267, "loss": 0.5875, "step": 8770}
+{"epoch": 0.31, "learning_rate": 0.00026912445129908646, "loss": 0.6592, "step": 8780}
+{"epoch": 0.31, "learning_rate": 0.0002690888598884802, "loss": 0.6463, "step": 8790}
+{"epoch": 0.31, "learning_rate": 0.000269053268477874, "loss": 0.7381, "step": 8800}
+{"epoch": 0.31, "learning_rate": 0.00026901767706726773, "loss": 0.6912, "step": 8810}
+{"epoch": 0.31, "learning_rate": 0.0002689820856566615, "loss": 0.6573, "step": 8820}
+{"epoch": 0.31, "learning_rate": 0.00026894649424605527, "loss": 0.6521, "step": 8830}
+{"epoch": 0.31, "learning_rate": 0.00026891090283544906, "loss": 0.6629, "step": 8840}
+{"epoch": 0.31, "learning_rate": 0.0002688753114248428, "loss": 0.655, "step": 8850}
+{"epoch": 0.31, "learning_rate": 0.00026883972001423654, "loss": 0.6766, "step": 8860}
+{"epoch": 0.32, "learning_rate": 0.0002688041286036303, "loss": 0.6779, "step": 8870}
+{"epoch": 0.32, "learning_rate": 0.00026876853719302407, "loss": 0.6672, "step": 8880}
+{"epoch": 0.32, "learning_rate": 0.0002687329457824178, "loss": 0.8151, "step": 8890}
+{"epoch": 0.32, "learning_rate": 0.00026869735437181155, "loss": 0.5627, "step": 8900}
+{"epoch": 0.32, "learning_rate": 0.00026866176296120534, "loss": 0.7126, "step": 8910}
+{"epoch": 0.32, "learning_rate": 0.0002686261715505991, "loss": 0.7104, "step": 8920}
+{"epoch": 0.32, "learning_rate": 0.0002685905801399929, "loss": 0.7442, "step": 8930}
+{"epoch": 0.32, "learning_rate": 0.0002685549887293866, "loss": 0.8611, "step": 8940}
+{"epoch": 0.32, "learning_rate": 0.00026851939731878036, "loss": 0.6804, "step": 8950}
+{"epoch": 0.32, "learning_rate": 0.00026848380590817415, "loss": 0.6368, "step": 8960}
+{"epoch": 0.32, "learning_rate": 0.0002684482144975679, "loss": 0.6316, "step": 8970}
+{"epoch": 0.32, "learning_rate": 0.0002684126230869617, "loss": 0.6271, "step": 8980}
+{"epoch": 0.32, "learning_rate": 0.0002683770316763554, "loss": 0.7894, "step": 8990}
+{"epoch": 0.32, "learning_rate": 0.00026834144026574916, "loss": 0.6684, "step": 9000}
+{"epoch": 0.32, "learning_rate": 0.00026830584885514296, "loss": 0.6234, "step": 9010}
+{"epoch": 0.32, "learning_rate": 0.0002682702574445367, "loss": 0.6944, "step": 9020}
+{"epoch": 0.32, "learning_rate": 0.00026823466603393043, "loss": 0.7694, "step": 9030}
+{"epoch": 0.32, "learning_rate": 0.00026819907462332423, "loss": 0.6311, "step": 9040}
+{"epoch": 0.32, "learning_rate": 0.00026816348321271797, "loss": 0.7521, "step": 9050}
+{"epoch": 0.32, "learning_rate": 0.0002681278918021117, "loss": 0.7274, "step": 9060}
+{"epoch": 0.32, "learning_rate": 0.0002680923003915055, "loss": 0.6462, "step": 9070}
+{"epoch": 0.32, "learning_rate": 0.00026805670898089924, "loss": 0.5708, "step": 9080}
+{"epoch": 0.32, "learning_rate": 0.00026802111757029303, "loss": 0.6091, "step": 9090}
+{"epoch": 0.32, "learning_rate": 0.0002679855261596868, "loss": 0.6495, "step": 9100}
+{"epoch": 0.32, "learning_rate": 0.00026794993474908057, "loss": 0.6499, "step": 9110}
+{"epoch": 0.32, "learning_rate": 0.0002679143433384743, "loss": 0.6483, "step": 9120}
+{"epoch": 0.32, "learning_rate": 0.00026787875192786805, "loss": 0.5742, "step": 9130}
+{"epoch": 0.32, "learning_rate": 0.00026784316051726184, "loss": 0.7195, "step": 9140}
+{"epoch": 0.33, "learning_rate": 0.0002678075691066556, "loss": 0.7322, "step": 9150}
+{"epoch": 0.33, "learning_rate": 0.0002677719776960493, "loss": 0.6575, "step": 9160}
+{"epoch": 0.33, "learning_rate": 0.0002677363862854431, "loss": 0.6982, "step": 9170}
+{"epoch": 0.33, "learning_rate": 0.00026770079487483685, "loss": 0.6903, "step": 9180}
+{"epoch": 0.33, "learning_rate": 0.0002676652034642306, "loss": 0.758, "step": 9190}
+{"epoch": 0.33, "learning_rate": 0.00026762961205362433, "loss": 0.6349, "step": 9200}
+{"epoch": 0.33, "learning_rate": 0.0002675940206430181, "loss": 0.7335, "step": 9210}
+{"epoch": 0.33, "learning_rate": 0.00026755842923241186, "loss": 0.6959, "step": 9220}
+{"epoch": 0.33, "learning_rate": 0.00026752283782180566, "loss": 0.6329, "step": 9230}
+{"epoch": 0.33, "learning_rate": 0.0002674872464111994, "loss": 0.7161, "step": 9240}
+{"epoch": 0.33, "learning_rate": 0.0002674516550005932, "loss": 0.6257, "step": 9250}
+{"epoch": 0.33, "learning_rate": 0.00026741606358998693, "loss": 0.6758, "step": 9260}
+{"epoch": 0.33, "learning_rate": 0.0002673804721793807, "loss": 0.7651, "step": 9270}
+{"epoch": 0.33, "learning_rate": 0.00026734488076877446, "loss": 0.5855, "step": 9280}
+{"epoch": 0.33, "learning_rate": 0.0002673092893581682, "loss": 0.5963, "step": 9290}
+{"epoch": 0.33, "learning_rate": 0.00026727369794756194, "loss": 0.6991, "step": 9300}
+{"epoch": 0.33, "learning_rate": 0.00026723810653695574, "loss": 0.7755, "step": 9310}
+{"epoch": 0.33, "learning_rate": 0.0002672025151263495, "loss": 0.6623, "step": 9320}
+{"epoch": 0.33, "learning_rate": 0.0002671669237157432, "loss": 0.7013, "step": 9330}
+{"epoch": 0.33, "learning_rate": 0.000267131332305137, "loss": 0.6297, "step": 9340}
+{"epoch": 0.33, "learning_rate": 0.00026709574089453075, "loss": 0.6676, "step": 9350}
+{"epoch": 0.33, "learning_rate": 0.0002670601494839245, "loss": 0.6645, "step": 9360}
+{"epoch": 0.33, "learning_rate": 0.0002670245580733183, "loss": 0.6607, "step": 9370}
+{"epoch": 0.33, "learning_rate": 0.000266988966662712, "loss": 0.7861, "step": 9380}
+{"epoch": 0.33, "learning_rate": 0.0002669533752521058, "loss": 0.7143, "step": 9390}
+{"epoch": 0.33, "learning_rate": 0.00026691778384149955, "loss": 0.6165, "step": 9400}
+{"epoch": 0.33, "learning_rate": 0.00026688219243089335, "loss": 0.6654, "step": 9410}
+{"epoch": 0.33, "learning_rate": 0.0002668466010202871, "loss": 0.754, "step": 9420}
+{"epoch": 0.34, "learning_rate": 0.0002668110096096808, "loss": 0.6519, "step": 9430}
+{"epoch": 0.34, "learning_rate": 0.0002667754181990746, "loss": 0.6906, "step": 9440}
+{"epoch": 0.34, "learning_rate": 0.00026673982678846836, "loss": 0.6446, "step": 9450}
+{"epoch": 0.34, "learning_rate": 0.0002667042353778621, "loss": 0.6815, "step": 9460}
+{"epoch": 0.34, "learning_rate": 0.0002666686439672559, "loss": 0.6959, "step": 9470}
+{"epoch": 0.34, "learning_rate": 0.00026663305255664963, "loss": 0.656, "step": 9480}
+{"epoch": 0.34, "learning_rate": 0.00026659746114604337, "loss": 0.6959, "step": 9490}
+{"epoch": 0.34, "learning_rate": 0.00026656186973543716, "loss": 0.6717, "step": 9500}
+{"epoch": 0.34, "learning_rate": 0.0002665262783248309, "loss": 0.6418, "step": 9510}
+{"epoch": 0.34, "learning_rate": 0.0002664906869142247, "loss": 0.7151, "step": 9520}
+{"epoch": 0.34, "learning_rate": 0.00026645509550361844, "loss": 0.6329, "step": 9530}
+{"epoch": 0.34, "learning_rate": 0.00026641950409301223, "loss": 0.7272, "step": 9540}
+{"epoch": 0.34, "learning_rate": 0.00026638391268240597, "loss": 0.697, "step": 9550}
+{"epoch": 0.34, "learning_rate": 0.0002663483212717997, "loss": 0.6158, "step": 9560}
+{"epoch": 0.34, "learning_rate": 0.0002663127298611935, "loss": 0.7448, "step": 9570}
+{"epoch": 0.34, "learning_rate": 0.00026627713845058724, "loss": 0.6351, "step": 9580}
+{"epoch": 0.34, "learning_rate": 0.000266241547039981, "loss": 0.7799, "step": 9590}
+{"epoch": 0.34, "learning_rate": 0.0002662059556293748, "loss": 0.6192, "step": 9600}
+{"epoch": 0.34, "learning_rate": 0.0002661703642187685, "loss": 0.7461, "step": 9610}
+{"epoch": 0.34, "learning_rate": 0.00026613477280816225, "loss": 0.7044, "step": 9620}
+{"epoch": 0.34, "learning_rate": 0.00026609918139755605, "loss": 0.7068, "step": 9630}
+{"epoch": 0.34, "learning_rate": 0.0002660635899869498, "loss": 0.6686, "step": 9640}
+{"epoch": 0.34, "learning_rate": 0.00026602799857634353, "loss": 0.6377, "step": 9650}
+{"epoch": 0.34, "learning_rate": 0.0002659924071657373, "loss": 0.6554, "step": 9660}
+{"epoch": 0.34, "learning_rate": 0.00026595681575513106, "loss": 0.6232, "step": 9670}
+{"epoch": 0.34, "learning_rate": 0.00026592122434452485, "loss": 0.6906, "step": 9680}
+{"epoch": 0.34, "learning_rate": 0.0002658856329339186, "loss": 0.5595, "step": 9690}
+{"epoch": 0.34, "learning_rate": 0.0002658500415233124, "loss": 0.5811, "step": 9700}
+{"epoch": 0.35, "learning_rate": 0.0002658144501127061, "loss": 0.6864, "step": 9710}
+{"epoch": 0.35, "learning_rate": 0.00026577885870209987, "loss": 0.7228, "step": 9720}
+{"epoch": 0.35, "learning_rate": 0.00026574326729149366, "loss": 0.6747, "step": 9730}
+{"epoch": 0.35, "learning_rate": 0.0002657076758808874, "loss": 0.5234, "step": 9740}
+{"epoch": 0.35, "learning_rate": 0.00026567208447028114, "loss": 0.7332, "step": 9750}
+{"epoch": 0.35, "learning_rate": 0.0002656364930596749, "loss": 0.6973, "step": 9760}
+{"epoch": 0.35, "learning_rate": 0.00026560090164906867, "loss": 0.6691, "step": 9770}
+{"epoch": 0.35, "learning_rate": 0.0002655653102384624, "loss": 0.6731, "step": 9780}
+{"epoch": 0.35, "learning_rate": 0.00026552971882785615, "loss": 0.6794, "step": 9790}
+{"epoch": 0.35, "learning_rate": 0.00026549412741724994, "loss": 0.7355, "step": 9800}
+{"epoch": 0.35, "learning_rate": 0.0002654585360066437, "loss": 0.7245, "step": 9810}
+{"epoch": 0.35, "learning_rate": 0.0002654229445960375, "loss": 0.6417, "step": 9820}
+{"epoch": 0.35, "learning_rate": 0.0002653873531854312, "loss": 0.6887, "step": 9830}
+{"epoch": 0.35, "learning_rate": 0.000265351761774825, "loss": 0.5949, "step": 9840}
+{"epoch": 0.35, "learning_rate": 0.00026531617036421875, "loss": 0.6635, "step": 9850}
+{"epoch": 0.35, "learning_rate": 0.00026528057895361254, "loss": 0.6195, "step": 9860}
+{"epoch": 0.35, "learning_rate": 0.0002652449875430063, "loss": 0.6533, "step": 9870}
+{"epoch": 0.35, "learning_rate": 0.0002652093961324, "loss": 0.6308, "step": 9880}
+{"epoch": 0.35, "learning_rate": 0.00026517380472179376, "loss": 0.595, "step": 9890}
+{"epoch": 0.35, "learning_rate": 0.00026513821331118756, "loss": 0.6465, "step": 9900}
+{"epoch": 0.35, "learning_rate": 0.0002651026219005813, "loss": 0.7322, "step": 9910}
+{"epoch": 0.35, "learning_rate": 0.00026506703048997503, "loss": 0.7787, "step": 9920}
+{"epoch": 0.35, "learning_rate": 0.00026503143907936883, "loss": 0.7538, "step": 9930}
+{"epoch": 0.35, "learning_rate": 0.00026499584766876257, "loss": 0.5519, "step": 9940}
+{"epoch": 0.35, "learning_rate": 0.0002649602562581563, "loss": 0.5726, "step": 9950}
+{"epoch": 0.35, "learning_rate": 0.0002649246648475501, "loss": 0.5972, "step": 9960}
+{"epoch": 0.35, "learning_rate": 0.00026488907343694384, "loss": 0.6526, "step": 9970}
+{"epoch": 0.35, "learning_rate": 0.00026485348202633763, "loss": 0.6898, "step": 9980}
+{"epoch": 0.36, "learning_rate": 0.0002648178906157314, "loss": 0.6362, "step": 9990}
+{"epoch": 0.36, "learning_rate": 0.00026478229920512517, "loss": 0.6991, "step": 10000}
+{"epoch": 0.36, "learning_rate": 0.0002647467077945189, "loss": 0.6635, "step": 10010}
+{"epoch": 0.36, "learning_rate": 0.00026471111638391265, "loss": 0.6357, "step": 10020}
+{"epoch": 0.36, "learning_rate": 0.00026467552497330644, "loss": 0.6655, "step": 10030}
+{"epoch": 0.36, "learning_rate": 0.0002646399335627002, "loss": 0.7764, "step": 10040}
+{"epoch": 0.36, "learning_rate": 0.0002646043421520939, "loss": 0.6729, "step": 10050}
+{"epoch": 0.36, "learning_rate": 0.0002645687507414877, "loss": 0.6758, "step": 10060}
+{"epoch": 0.36, "learning_rate": 0.00026453315933088145, "loss": 0.6199, "step": 10070}
+{"epoch": 0.36, "learning_rate": 0.0002644975679202752, "loss": 0.6462, "step": 10080}
+{"epoch": 0.36, "learning_rate": 0.000264461976509669, "loss": 0.698, "step": 10090}
+{"epoch": 0.36, "learning_rate": 0.0002644263850990627, "loss": 0.6862, "step": 10100}
+{"epoch": 0.36, "learning_rate": 0.0002643907936884565, "loss": 0.7163, "step": 10110}
+{"epoch": 0.36, "learning_rate": 0.00026435520227785026, "loss": 0.5766, "step": 10120}
+{"epoch": 0.36, "learning_rate": 0.00026431961086724405, "loss": 0.6792, "step": 10130}
+{"epoch": 0.36, "learning_rate": 0.0002642840194566378, "loss": 0.6469, "step": 10140}
+{"epoch": 0.36, "learning_rate": 0.00026424842804603153, "loss": 0.6404, "step": 10150}
+{"epoch": 0.36, "learning_rate": 0.0002642128366354253, "loss": 0.6711, "step": 10160}
+{"epoch": 0.36, "learning_rate": 0.00026417724522481906, "loss": 0.7104, "step": 10170}
+{"epoch": 0.36, "learning_rate": 0.0002641416538142128, "loss": 0.5911, "step": 10180}
+{"epoch": 0.36, "learning_rate": 0.0002641060624036066, "loss": 0.6087, "step": 10190}
+{"epoch": 0.36, "learning_rate": 0.00026407047099300034, "loss": 0.6863, "step": 10200}
+{"epoch": 0.36, "learning_rate": 0.0002640348795823941, "loss": 0.6974, "step": 10210}
+{"epoch": 0.36, "learning_rate": 0.0002639992881717878, "loss": 0.6028, "step": 10220}
+{"epoch": 0.36, "learning_rate": 0.0002639636967611816, "loss": 0.5956, "step": 10230}
+{"epoch": 0.36, "learning_rate": 0.00026392810535057535, "loss": 0.7005, "step": 10240}
+{"epoch": 0.36, "learning_rate": 0.00026389251393996914, "loss": 0.6589, "step": 10250}
+{"epoch": 0.36, "learning_rate": 0.0002638569225293629, "loss": 0.646, "step": 10260}
+{"epoch": 0.37, "learning_rate": 0.0002638213311187567, "loss": 0.6825, "step": 10270}
+{"epoch": 0.37, "learning_rate": 0.00026378929884921106, "loss": 0.6398, "step": 10280}
+{"epoch": 0.37, "learning_rate": 0.0002637537074386048, "loss": 0.6914, "step": 10290}
+{"epoch": 0.37, "learning_rate": 0.00026371811602799854, "loss": 0.6285, "step": 10300}
+{"epoch": 0.37, "learning_rate": 0.00026368252461739233, "loss": 0.61, "step": 10310}
+{"epoch": 0.37, "learning_rate": 0.0002636469332067861, "loss": 0.7384, "step": 10320}
+{"epoch": 0.37, "learning_rate": 0.0002636113417961798, "loss": 0.695, "step": 10330}
+{"epoch": 0.37, "learning_rate": 0.0002635757503855736, "loss": 0.6646, "step": 10340}
+{"epoch": 0.37, "learning_rate": 0.00026354015897496735, "loss": 0.6574, "step": 10350}
+{"epoch": 0.37, "learning_rate": 0.0002635045675643611, "loss": 0.6208, "step": 10360}
+{"epoch": 0.37, "learning_rate": 0.0002634689761537549, "loss": 0.6029, "step": 10370}
+{"epoch": 0.37, "learning_rate": 0.0002634333847431486, "loss": 0.7264, "step": 10380}
+{"epoch": 0.37, "learning_rate": 0.00026339779333254236, "loss": 0.7054, "step": 10390}
+{"epoch": 0.37, "learning_rate": 0.00026336220192193615, "loss": 0.6087, "step": 10400}
+{"epoch": 0.37, "learning_rate": 0.0002633266105113299, "loss": 0.7008, "step": 10410}
+{"epoch": 0.37, "learning_rate": 0.0002632910191007237, "loss": 0.6048, "step": 10420}
+{"epoch": 0.37, "learning_rate": 0.0002632554276901174, "loss": 0.6031, "step": 10430}
+{"epoch": 0.37, "learning_rate": 0.0002632198362795112, "loss": 0.6678, "step": 10440}
+{"epoch": 0.37, "learning_rate": 0.00026318424486890496, "loss": 0.6607, "step": 10450}
+{"epoch": 0.37, "learning_rate": 0.0002631486534582987, "loss": 0.6964, "step": 10460}
+{"epoch": 0.37, "learning_rate": 0.0002631130620476925, "loss": 0.6993, "step": 10470}
+{"epoch": 0.37, "learning_rate": 0.00026307747063708623, "loss": 0.7119, "step": 10480}
+{"epoch": 0.37, "learning_rate": 0.00026304187922647997, "loss": 0.641, "step": 10490}
+{"epoch": 0.37, "learning_rate": 0.00026300628781587376, "loss": 0.7175, "step": 10500}
+{"epoch": 0.37, "learning_rate": 0.0002629706964052675, "loss": 0.7156, "step": 10510}
+{"epoch": 0.37, "learning_rate": 0.00026293510499466124, "loss": 0.6344, "step": 10520}
+{"epoch": 0.37, "learning_rate": 0.00026289951358405504, "loss": 0.7467, "step": 10530}
+{"epoch": 0.37, "learning_rate": 0.0002628639221734488, "loss": 0.6675, "step": 10540}
+{"epoch": 0.38, "learning_rate": 0.00026282833076284257, "loss": 0.6612, "step": 10550}
+{"epoch": 0.38, "learning_rate": 0.0002627927393522363, "loss": 0.7396, "step": 10560}
+{"epoch": 0.38, "learning_rate": 0.00026275714794163005, "loss": 0.6916, "step": 10570}
+{"epoch": 0.38, "learning_rate": 0.00026272155653102384, "loss": 0.57, "step": 10580}
+{"epoch": 0.38, "learning_rate": 0.0002626859651204176, "loss": 0.6763, "step": 10590}
+{"epoch": 0.38, "learning_rate": 0.0002626503737098114, "loss": 0.6774, "step": 10600}
+{"epoch": 0.38, "learning_rate": 0.0002626147822992051, "loss": 0.7538, "step": 10610}
+{"epoch": 0.38, "learning_rate": 0.00026257919088859885, "loss": 0.7382, "step": 10620}
+{"epoch": 0.38, "learning_rate": 0.0002625435994779926, "loss": 0.642, "step": 10630}
+{"epoch": 0.38, "learning_rate": 0.0002625080080673864, "loss": 0.6947, "step": 10640}
+{"epoch": 0.38, "learning_rate": 0.0002624724166567801, "loss": 0.732, "step": 10650}
+{"epoch": 0.38, "learning_rate": 0.00026243682524617387, "loss": 0.6579, "step": 10660}
+{"epoch": 0.38, "learning_rate": 0.00026240123383556766, "loss": 0.665, "step": 10670}
+{"epoch": 0.38, "learning_rate": 0.0002623656424249614, "loss": 0.7206, "step": 10680}
+{"epoch": 0.38, "learning_rate": 0.0002623300510143552, "loss": 0.6377, "step": 10690}
+{"epoch": 0.38, "learning_rate": 0.00026229445960374893, "loss": 0.744, "step": 10700}
+{"epoch": 0.38, "learning_rate": 0.0002622588681931427, "loss": 0.6314, "step": 10710}
+{"epoch": 0.38, "learning_rate": 0.00026222327678253647, "loss": 0.5859, "step": 10720}
+{"epoch": 0.38, "learning_rate": 0.00026218768537193026, "loss": 0.6239, "step": 10730}
+{"epoch": 0.38, "learning_rate": 0.000262152093961324, "loss": 0.6289, "step": 10740}
+{"epoch": 0.38, "learning_rate": 0.00026211650255071774, "loss": 0.7771, "step": 10750}
+{"epoch": 0.38, "learning_rate": 0.0002620809111401115, "loss": 0.5974, "step": 10760}
+{"epoch": 0.38, "learning_rate": 0.00026204531972950527, "loss": 0.629, "step": 10770}
+{"epoch": 0.38, "learning_rate": 0.000262009728318899, "loss": 0.7037, "step": 10780}
+{"epoch": 0.38, "learning_rate": 0.00026197413690829275, "loss": 0.6756, "step": 10790}
+{"epoch": 0.38, "learning_rate": 0.00026193854549768654, "loss": 0.6247, "step": 10800}
+{"epoch": 0.38, "learning_rate": 0.0002619029540870803, "loss": 0.562, "step": 10810}
+{"epoch": 0.38, "learning_rate": 0.000261867362676474, "loss": 0.6471, "step": 10820}
+{"epoch": 0.38, "learning_rate": 0.0002618317712658678, "loss": 0.7036, "step": 10830}
+{"epoch": 0.39, "learning_rate": 0.00026179617985526156, "loss": 0.7124, "step": 10840}
+{"epoch": 0.39, "learning_rate": 0.00026176058844465535, "loss": 0.5975, "step": 10850}
+{"epoch": 0.39, "learning_rate": 0.0002617249970340491, "loss": 0.6751, "step": 10860}
+{"epoch": 0.39, "learning_rate": 0.0002616894056234429, "loss": 0.6748, "step": 10870}
+{"epoch": 0.39, "learning_rate": 0.0002616538142128366, "loss": 0.7397, "step": 10880}
+{"epoch": 0.39, "learning_rate": 0.00026161822280223036, "loss": 0.7737, "step": 10890}
+{"epoch": 0.39, "learning_rate": 0.00026158263139162415, "loss": 0.6812, "step": 10900}
+{"epoch": 0.39, "learning_rate": 0.0002615470399810179, "loss": 0.7196, "step": 10910}
+{"epoch": 0.39, "learning_rate": 0.00026151144857041163, "loss": 0.6576, "step": 10920}
+{"epoch": 0.39, "learning_rate": 0.00026147585715980543, "loss": 0.6802, "step": 10930}
+{"epoch": 0.39, "learning_rate": 0.00026144026574919917, "loss": 0.6089, "step": 10940}
+{"epoch": 0.39, "learning_rate": 0.0002614046743385929, "loss": 0.7525, "step": 10950}
+{"epoch": 0.39, "learning_rate": 0.0002613690829279867, "loss": 0.7278, "step": 10960}
+{"epoch": 0.39, "learning_rate": 0.00026133349151738044, "loss": 0.7099, "step": 10970}
+{"epoch": 0.39, "learning_rate": 0.0002612979001067742, "loss": 0.6143, "step": 10980}
+{"epoch": 0.39, "learning_rate": 0.00026126230869616797, "loss": 0.6645, "step": 10990}
+{"epoch": 0.39, "learning_rate": 0.0002612267172855617, "loss": 0.5811, "step": 11000}
+{"epoch": 0.39, "learning_rate": 0.0002611911258749555, "loss": 0.5476, "step": 11010}
+{"epoch": 0.39, "learning_rate": 0.00026115553446434925, "loss": 0.7523, "step": 11020}
+{"epoch": 0.39, "learning_rate": 0.00026111994305374304, "loss": 0.6987, "step": 11030}
+{"epoch": 0.39, "learning_rate": 0.0002610843516431368, "loss": 0.6548, "step": 11040}
+{"epoch": 0.39, "learning_rate": 0.0002610487602325305, "loss": 0.7009, "step": 11050}
+{"epoch": 0.39, "learning_rate": 0.0002610131688219243, "loss": 0.6223, "step": 11060}
+{"epoch": 0.39, "learning_rate": 0.00026097757741131805, "loss": 0.7014, "step": 11070}
+{"epoch": 0.39, "learning_rate": 0.0002609419860007118, "loss": 0.687, "step": 11080}
+{"epoch": 0.39, "learning_rate": 0.00026090639459010553, "loss": 0.669, "step": 11090}
+{"epoch": 0.39, "learning_rate": 0.0002608708031794993, "loss": 0.623, "step": 11100}
+{"epoch": 0.39, "learning_rate": 0.00026083521176889306, "loss": 0.5977, "step": 11110}
+{"epoch": 0.4, "learning_rate": 0.00026079962035828686, "loss": 0.6418, "step": 11120}
+{"epoch": 0.4, "learning_rate": 0.0002607640289476806, "loss": 0.6404, "step": 11130}
+{"epoch": 0.4, "learning_rate": 0.0002607284375370744, "loss": 0.6264, "step": 11140}
+{"epoch": 0.4, "learning_rate": 0.00026069284612646813, "loss": 0.6921, "step": 11150}
+{"epoch": 0.4, "learning_rate": 0.0002606572547158619, "loss": 0.645, "step": 11160}
+{"epoch": 0.4, "learning_rate": 0.00026062166330525566, "loss": 0.5915, "step": 11170}
+{"epoch": 0.4, "learning_rate": 0.0002605860718946494, "loss": 0.6425, "step": 11180}
+{"epoch": 0.4, "learning_rate": 0.00026055048048404314, "loss": 0.6348, "step": 11190}
+{"epoch": 0.4, "learning_rate": 0.00026051488907343693, "loss": 0.7087, "step": 11200}
+{"epoch": 0.4, "learning_rate": 0.0002604792976628307, "loss": 0.7018, "step": 11210}
+{"epoch": 0.4, "learning_rate": 0.0002604437062522244, "loss": 0.6267, "step": 11220}
+{"epoch": 0.4, "learning_rate": 0.0002604081148416182, "loss": 0.6771, "step": 11230}
+{"epoch": 0.4, "learning_rate": 0.00026037252343101195, "loss": 0.5874, "step": 11240}
+{"epoch": 0.4, "learning_rate": 0.0002603369320204057, "loss": 0.6597, "step": 11250}
+{"epoch": 0.4, "learning_rate": 0.0002603013406097995, "loss": 0.6873, "step": 11260}
+{"epoch": 0.4, "learning_rate": 0.0002602657491991932, "loss": 0.6519, "step": 11270}
+{"epoch": 0.4, "learning_rate": 0.000260230157788587, "loss": 0.6338, "step": 11280}
+{"epoch": 0.4, "learning_rate": 0.00026019456637798075, "loss": 0.6631, "step": 11290}
+{"epoch": 0.4, "learning_rate": 0.00026015897496737455, "loss": 0.6482, "step": 11300}
+{"epoch": 0.4, "learning_rate": 0.0002601233835567683, "loss": 0.5208, "step": 11310}
+{"epoch": 0.4, "learning_rate": 0.000260087792146162, "loss": 0.6797, "step": 11320}
+{"epoch": 0.4, "learning_rate": 0.0002600522007355558, "loss": 0.6226, "step": 11330}
+{"epoch": 0.4, "learning_rate": 0.00026001660932494956, "loss": 0.6616, "step": 11340}
+{"epoch": 0.4, "learning_rate": 0.0002599810179143433, "loss": 0.6695, "step": 11350}
+{"epoch": 0.4, "learning_rate": 0.0002599454265037371, "loss": 0.7132, "step": 11360}
+{"epoch": 0.4, "learning_rate": 0.00025990983509313083, "loss": 0.6248, "step": 11370}
+{"epoch": 0.4, "learning_rate": 0.00025987424368252457, "loss": 0.5801, "step": 11380}
+{"epoch": 0.4, "learning_rate": 0.00025983865227191836, "loss": 0.5961, "step": 11390}
+{"epoch": 0.41, "learning_rate": 0.0002598030608613121, "loss": 0.6429, "step": 11400}
+{"epoch": 0.41, "learning_rate": 0.00025976746945070584, "loss": 0.6534, "step": 11410}
+{"epoch": 0.41, "learning_rate": 0.00025973187804009964, "loss": 0.6326, "step": 11420}
+{"epoch": 0.41, "learning_rate": 0.0002596962866294934, "loss": 0.7653, "step": 11430}
+{"epoch": 0.41, "learning_rate": 0.00025966069521888717, "loss": 0.5867, "step": 11440}
+{"epoch": 0.41, "learning_rate": 0.0002596251038082809, "loss": 0.7721, "step": 11450}
+{"epoch": 0.41, "learning_rate": 0.0002595895123976747, "loss": 0.6588, "step": 11460}
+{"epoch": 0.41, "learning_rate": 0.00025955392098706844, "loss": 0.6176, "step": 11470}
+{"epoch": 0.41, "learning_rate": 0.0002595183295764622, "loss": 0.7171, "step": 11480}
+{"epoch": 0.41, "learning_rate": 0.000259482738165856, "loss": 0.7859, "step": 11490}
+{"epoch": 0.41, "learning_rate": 0.0002594471467552497, "loss": 0.7316, "step": 11500}
+{"epoch": 0.41, "learning_rate": 0.00025941155534464345, "loss": 0.7001, "step": 11510}
+{"epoch": 0.41, "learning_rate": 0.00025937596393403725, "loss": 0.603, "step": 11520}
+{"epoch": 0.41, "learning_rate": 0.000259340372523431, "loss": 0.6713, "step": 11530}
+{"epoch": 0.41, "learning_rate": 0.0002593047811128247, "loss": 0.7009, "step": 11540}
+{"epoch": 0.41, "learning_rate": 0.0002592691897022185, "loss": 0.7104, "step": 11550}
+{"epoch": 0.41, "learning_rate": 0.00025923359829161226, "loss": 0.566, "step": 11560}
+{"epoch": 0.41, "learning_rate": 0.000259198006881006, "loss": 0.6219, "step": 11570}
+{"epoch": 0.41, "learning_rate": 0.0002591624154703998, "loss": 0.6206, "step": 11580}
+{"epoch": 0.41, "learning_rate": 0.00025912682405979353, "loss": 0.6477, "step": 11590}
+{"epoch": 0.41, "learning_rate": 0.0002590912326491873, "loss": 0.6757, "step": 11600}
+{"epoch": 0.41, "learning_rate": 0.00025905564123858107, "loss": 0.6812, "step": 11610}
+{"epoch": 0.41, "learning_rate": 0.00025902004982797486, "loss": 0.6335, "step": 11620}
+{"epoch": 0.41, "learning_rate": 0.0002589844584173686, "loss": 0.6062, "step": 11630}
+{"epoch": 0.41, "learning_rate": 0.00025894886700676234, "loss": 0.7371, "step": 11640}
+{"epoch": 0.41, "learning_rate": 0.0002589132755961561, "loss": 0.7567, "step": 11650}
+{"epoch": 0.41, "learning_rate": 0.00025887768418554987, "loss": 0.6705, "step": 11660}
+{"epoch": 0.41, "learning_rate": 0.0002588420927749436, "loss": 0.6781, "step": 11670}
+{"epoch": 0.42, "learning_rate": 0.00025880650136433735, "loss": 0.7395, "step": 11680}
+{"epoch": 0.42, "learning_rate": 0.00025877090995373114, "loss": 0.6354, "step": 11690}
+{"epoch": 0.42, "learning_rate": 0.0002587353185431249, "loss": 0.5913, "step": 11700}
+{"epoch": 0.42, "learning_rate": 0.0002586997271325187, "loss": 0.6296, "step": 11710}
+{"epoch": 0.42, "learning_rate": 0.0002586641357219124, "loss": 0.6539, "step": 11720}
+{"epoch": 0.42, "learning_rate": 0.0002586285443113062, "loss": 0.7085, "step": 11730}
+{"epoch": 0.42, "learning_rate": 0.00025859295290069995, "loss": 0.7424, "step": 11740}
+{"epoch": 0.42, "learning_rate": 0.00025855736149009374, "loss": 0.6588, "step": 11750}
+{"epoch": 0.42, "learning_rate": 0.0002585217700794875, "loss": 0.6806, "step": 11760}
+{"epoch": 0.42, "learning_rate": 0.0002584861786688812, "loss": 0.7187, "step": 11770}
+{"epoch": 0.42, "learning_rate": 0.00025845058725827496, "loss": 0.6923, "step": 11780}
+{"epoch": 0.42, "learning_rate": 0.00025841499584766876, "loss": 0.6112, "step": 11790}
+{"epoch": 0.42, "learning_rate": 0.0002583794044370625, "loss": 0.6067, "step": 11800}
+{"epoch": 0.42, "learning_rate": 0.00025834381302645623, "loss": 0.6562, "step": 11810}
+{"epoch": 0.42, "learning_rate": 0.00025830822161585003, "loss": 0.6703, "step": 11820}
+{"epoch": 0.42, "learning_rate": 0.00025827263020524377, "loss": 0.6112, "step": 11830}
+{"epoch": 0.42, "learning_rate": 0.0002582370387946375, "loss": 0.7401, "step": 11840}
+{"epoch": 0.42, "learning_rate": 0.0002582014473840313, "loss": 0.5951, "step": 11850}
+{"epoch": 0.42, "learning_rate": 0.00025816585597342504, "loss": 0.6889, "step": 11860}
+{"epoch": 0.42, "learning_rate": 0.00025813026456281883, "loss": 0.6453, "step": 11870}
+{"epoch": 0.42, "learning_rate": 0.0002580946731522126, "loss": 0.6925, "step": 11880}
+{"epoch": 0.42, "learning_rate": 0.00025805908174160637, "loss": 0.6293, "step": 11890}
+{"epoch": 0.42, "learning_rate": 0.0002580234903310001, "loss": 0.746, "step": 11900}
+{"epoch": 0.42, "learning_rate": 0.00025798789892039385, "loss": 0.6438, "step": 11910}
+{"epoch": 0.42, "learning_rate": 0.00025795230750978764, "loss": 0.6945, "step": 11920}
+{"epoch": 0.42, "learning_rate": 0.0002579167160991814, "loss": 0.7621, "step": 11930}
+{"epoch": 0.42, "learning_rate": 0.0002578811246885751, "loss": 0.6791, "step": 11940}
+{"epoch": 0.42, "learning_rate": 0.0002578455332779689, "loss": 0.6895, "step": 11950}
+{"epoch": 0.43, "learning_rate": 0.00025780994186736265, "loss": 0.6235, "step": 11960}
+{"epoch": 0.43, "learning_rate": 0.0002577743504567564, "loss": 0.6027, "step": 11970}
+{"epoch": 0.43, "learning_rate": 0.0002577387590461502, "loss": 0.7398, "step": 11980}
+{"epoch": 0.43, "learning_rate": 0.0002577031676355439, "loss": 0.8015, "step": 11990}
+{"epoch": 0.43, "learning_rate": 0.00025766757622493766, "loss": 0.726, "step": 12000}
+{"epoch": 0.43, "learning_rate": 0.00025763198481433146, "loss": 0.7539, "step": 12010}
+{"epoch": 0.43, "learning_rate": 0.0002575963934037252, "loss": 0.5456, "step": 12020}
+{"epoch": 0.43, "learning_rate": 0.000257560801993119, "loss": 0.6644, "step": 12030}
+{"epoch": 0.43, "learning_rate": 0.00025752521058251273, "loss": 0.6225, "step": 12040}
+{"epoch": 0.43, "learning_rate": 0.0002574896191719065, "loss": 0.6593, "step": 12050}
+{"epoch": 0.43, "learning_rate": 0.00025745402776130026, "loss": 0.6988, "step": 12060}
+{"epoch": 0.43, "learning_rate": 0.000257418436350694, "loss": 0.6553, "step": 12070}
+{"epoch": 0.43, "learning_rate": 0.0002573828449400878, "loss": 0.6502, "step": 12080}
+{"epoch": 0.43, "learning_rate": 0.00025734725352948154, "loss": 0.6295, "step": 12090}
+{"epoch": 0.43, "learning_rate": 0.0002573116621188753, "loss": 0.7528, "step": 12100}
+{"epoch": 0.43, "learning_rate": 0.000257276070708269, "loss": 0.6808, "step": 12110}
+{"epoch": 0.43, "learning_rate": 0.0002572404792976628, "loss": 0.7277, "step": 12120}
+{"epoch": 0.43, "learning_rate": 0.00025720488788705655, "loss": 0.6174, "step": 12130}
+{"epoch": 0.43, "learning_rate": 0.00025716929647645034, "loss": 0.7484, "step": 12140}
+{"epoch": 0.43, "learning_rate": 0.0002571337050658441, "loss": 0.602, "step": 12150}
+{"epoch": 0.43, "learning_rate": 0.0002570981136552379, "loss": 0.7096, "step": 12160}
+{"epoch": 0.43, "learning_rate": 0.0002570625222446316, "loss": 0.6005, "step": 12170}
+{"epoch": 0.43, "learning_rate": 0.00025702693083402535, "loss": 0.6596, "step": 12180}
+{"epoch": 0.43, "learning_rate": 0.00025699133942341915, "loss": 0.6502, "step": 12190}
+{"epoch": 0.43, "learning_rate": 0.0002569557480128129, "loss": 0.7322, "step": 12200}
+{"epoch": 0.43, "learning_rate": 0.0002569201566022067, "loss": 0.6488, "step": 12210}
+{"epoch": 0.43, "learning_rate": 0.0002568845651916004, "loss": 0.544, "step": 12220}
+{"epoch": 0.43, "learning_rate": 0.00025684897378099416, "loss": 0.5705, "step": 12230}
+{"epoch": 0.44, "learning_rate": 0.0002568133823703879, "loss": 0.6534, "step": 12240}
+{"epoch": 0.44, "learning_rate": 0.0002567777909597817, "loss": 0.6648, "step": 12250}
+{"epoch": 0.44, "learning_rate": 0.00025674219954917543, "loss": 0.7348, "step": 12260}
+{"epoch": 0.44, "learning_rate": 0.00025670660813856917, "loss": 0.6103, "step": 12270}
+{"epoch": 0.44, "learning_rate": 0.00025667101672796296, "loss": 0.7673, "step": 12280}
+{"epoch": 0.44, "learning_rate": 0.0002566354253173567, "loss": 0.709, "step": 12290}
+{"epoch": 0.44, "learning_rate": 0.0002565998339067505, "loss": 0.6413, "step": 12300}
+{"epoch": 0.44, "learning_rate": 0.00025656424249614424, "loss": 0.6544, "step": 12310}
+{"epoch": 0.44, "learning_rate": 0.00025652865108553803, "loss": 0.6615, "step": 12320}
+{"epoch": 0.44, "learning_rate": 0.00025649305967493177, "loss": 0.6999, "step": 12330}
+{"epoch": 0.44, "learning_rate": 0.00025646102740538616, "loss": 0.7117, "step": 12340}
+{"epoch": 0.44, "learning_rate": 0.0002564254359947799, "loss": 0.7284, "step": 12350}
+{"epoch": 0.44, "learning_rate": 0.0002563898445841737, "loss": 0.608, "step": 12360}
+{"epoch": 0.44, "learning_rate": 0.00025635425317356743, "loss": 0.6565, "step": 12370}
+{"epoch": 0.44, "learning_rate": 0.00025631866176296117, "loss": 0.6898, "step": 12380}
+{"epoch": 0.44, "learning_rate": 0.00025628307035235496, "loss": 0.6654, "step": 12390}
+{"epoch": 0.44, "learning_rate": 0.0002562474789417487, "loss": 0.678, "step": 12400}
+{"epoch": 0.44, "learning_rate": 0.00025621188753114244, "loss": 0.7709, "step": 12410}
+{"epoch": 0.44, "learning_rate": 0.0002561762961205362, "loss": 0.6717, "step": 12420}
+{"epoch": 0.44, "learning_rate": 0.00025614070470993, "loss": 0.6868, "step": 12430}
+{"epoch": 0.44, "learning_rate": 0.0002561051132993237, "loss": 0.6469, "step": 12440}
+{"epoch": 0.44, "learning_rate": 0.0002560695218887175, "loss": 0.6912, "step": 12450}
+{"epoch": 0.44, "learning_rate": 0.00025603393047811125, "loss": 0.6562, "step": 12460}
+{"epoch": 0.44, "learning_rate": 0.00025599833906750504, "loss": 0.6982, "step": 12470}
+{"epoch": 0.44, "learning_rate": 0.0002559627476568988, "loss": 0.7473, "step": 12480}
+{"epoch": 0.44, "learning_rate": 0.0002559271562462926, "loss": 0.6872, "step": 12490}
+{"epoch": 0.44, "learning_rate": 0.0002558915648356863, "loss": 0.6941, "step": 12500}
+{"epoch": 0.44, "learning_rate": 0.00025585597342508005, "loss": 0.6579, "step": 12510}
+{"epoch": 0.45, "learning_rate": 0.0002558203820144738, "loss": 0.6863, "step": 12520}
+{"epoch": 0.45, "learning_rate": 0.0002557847906038676, "loss": 0.6288, "step": 12530}
+{"epoch": 0.45, "learning_rate": 0.0002557491991932613, "loss": 0.5739, "step": 12540}
+{"epoch": 0.45, "learning_rate": 0.00025571360778265507, "loss": 0.6202, "step": 12550}
+{"epoch": 0.45, "learning_rate": 0.00025567801637204886, "loss": 0.7408, "step": 12560}
+{"epoch": 0.45, "learning_rate": 0.0002556424249614426, "loss": 0.5894, "step": 12570}
+{"epoch": 0.45, "learning_rate": 0.0002556068335508364, "loss": 0.7237, "step": 12580}
+{"epoch": 0.45, "learning_rate": 0.00025557124214023013, "loss": 0.6797, "step": 12590}
+{"epoch": 0.45, "learning_rate": 0.00025553565072962387, "loss": 0.6336, "step": 12600}
+{"epoch": 0.45, "learning_rate": 0.00025550005931901766, "loss": 0.5654, "step": 12610}
+{"epoch": 0.45, "learning_rate": 0.0002554644679084114, "loss": 0.7306, "step": 12620}
+{"epoch": 0.45, "learning_rate": 0.0002554288764978052, "loss": 0.7408, "step": 12630}
+{"epoch": 0.45, "learning_rate": 0.00025539328508719894, "loss": 0.7022, "step": 12640}
+{"epoch": 0.45, "learning_rate": 0.0002553576936765927, "loss": 0.7628, "step": 12650}
+{"epoch": 0.45, "learning_rate": 0.00025532210226598647, "loss": 0.7272, "step": 12660}
+{"epoch": 0.45, "learning_rate": 0.0002552865108553802, "loss": 0.6983, "step": 12670}
+{"epoch": 0.45, "learning_rate": 0.00025525091944477395, "loss": 0.7305, "step": 12680}
+{"epoch": 0.45, "learning_rate": 0.00025521532803416774, "loss": 0.6391, "step": 12690}
+{"epoch": 0.45, "learning_rate": 0.0002551797366235615, "loss": 0.6999, "step": 12700}
+{"epoch": 0.45, "learning_rate": 0.0002551441452129552, "loss": 0.7095, "step": 12710}
+{"epoch": 0.45, "learning_rate": 0.000255108553802349, "loss": 0.6445, "step": 12720}
+{"epoch": 0.45, "learning_rate": 0.00025507296239174275, "loss": 0.7364, "step": 12730}
+{"epoch": 0.45, "learning_rate": 0.00025503737098113655, "loss": 0.6244, "step": 12740}
+{"epoch": 0.45, "learning_rate": 0.0002550017795705303, "loss": 0.6553, "step": 12750}
+{"epoch": 0.45, "learning_rate": 0.0002549661881599241, "loss": 0.5593, "step": 12760}
+{"epoch": 0.45, "learning_rate": 0.0002549305967493178, "loss": 0.6772, "step": 12770}
+{"epoch": 0.45, "learning_rate": 0.00025489500533871156, "loss": 0.6262, "step": 12780}
+{"epoch": 0.45, "learning_rate": 0.00025485941392810535, "loss": 0.6741, "step": 12790}
+{"epoch": 0.46, "learning_rate": 0.0002548238225174991, "loss": 0.596, "step": 12800}
+{"epoch": 0.46, "learning_rate": 0.00025478823110689283, "loss": 0.6022, "step": 12810}
+{"epoch": 0.46, "learning_rate": 0.0002547526396962866, "loss": 0.663, "step": 12820}
+{"epoch": 0.46, "learning_rate": 0.00025471704828568037, "loss": 0.5627, "step": 12830}
+{"epoch": 0.46, "learning_rate": 0.0002546814568750741, "loss": 0.7556, "step": 12840}
+{"epoch": 0.46, "learning_rate": 0.0002546458654644679, "loss": 0.7456, "step": 12850}
+{"epoch": 0.46, "learning_rate": 0.00025461027405386164, "loss": 0.6417, "step": 12860}
+{"epoch": 0.46, "learning_rate": 0.0002545746826432554, "loss": 0.6878, "step": 12870}
+{"epoch": 0.46, "learning_rate": 0.00025453909123264917, "loss": 0.5615, "step": 12880}
+{"epoch": 0.46, "learning_rate": 0.0002545034998220429, "loss": 0.6748, "step": 12890}
+{"epoch": 0.46, "learning_rate": 0.0002544679084114367, "loss": 0.6035, "step": 12900}
+{"epoch": 0.46, "learning_rate": 0.00025443231700083044, "loss": 0.6211, "step": 12910}
+{"epoch": 0.46, "learning_rate": 0.00025439672559022424, "loss": 0.7444, "step": 12920}
+{"epoch": 0.46, "learning_rate": 0.0002543646933206786, "loss": 0.7103, "step": 12930}
+{"epoch": 0.46, "learning_rate": 0.00025432910191007236, "loss": 0.5651, "step": 12940}
+{"epoch": 0.46, "learning_rate": 0.0002542935104994661, "loss": 0.7112, "step": 12950}
+{"epoch": 0.46, "learning_rate": 0.00025425791908885984, "loss": 0.6323, "step": 12960}
+{"epoch": 0.46, "learning_rate": 0.00025422232767825364, "loss": 0.5438, "step": 12970}
+{"epoch": 0.46, "learning_rate": 0.0002541867362676474, "loss": 0.7769, "step": 12980}
+{"epoch": 0.46, "learning_rate": 0.0002541511448570411, "loss": 0.6814, "step": 12990}
+{"epoch": 0.46, "learning_rate": 0.0002541155534464349, "loss": 0.6867, "step": 13000}
+{"epoch": 0.46, "learning_rate": 0.00025407996203582865, "loss": 0.7224, "step": 13010}
+{"epoch": 0.46, "learning_rate": 0.0002540443706252224, "loss": 0.6341, "step": 13020}
+{"epoch": 0.46, "learning_rate": 0.0002540087792146162, "loss": 0.5995, "step": 13030}
+{"epoch": 0.46, "learning_rate": 0.0002539731878040099, "loss": 0.7044, "step": 13040}
+{"epoch": 0.46, "learning_rate": 0.0002539375963934037, "loss": 0.6987, "step": 13050}
+{"epoch": 0.46, "learning_rate": 0.00025390200498279746, "loss": 0.6268, "step": 13060}
+{"epoch": 0.46, "learning_rate": 0.00025386641357219125, "loss": 0.6315, "step": 13070}
+{"epoch": 0.46, "learning_rate": 0.000253830822161585, "loss": 0.6597, "step": 13080}
+{"epoch": 0.47, "learning_rate": 0.00025379523075097873, "loss": 0.7198, "step": 13090}
+{"epoch": 0.47, "learning_rate": 0.0002537596393403725, "loss": 0.5952, "step": 13100}
+{"epoch": 0.47, "learning_rate": 0.00025372404792976626, "loss": 0.6484, "step": 13110}
+{"epoch": 0.47, "learning_rate": 0.00025368845651916, "loss": 0.6402, "step": 13120}
+{"epoch": 0.47, "learning_rate": 0.0002536528651085538, "loss": 0.6464, "step": 13130}
+{"epoch": 0.47, "learning_rate": 0.00025361727369794753, "loss": 0.6433, "step": 13140}
+{"epoch": 0.47, "learning_rate": 0.00025358168228734127, "loss": 0.6253, "step": 13150}
+{"epoch": 0.47, "learning_rate": 0.00025354609087673507, "loss": 0.6625, "step": 13160}
+{"epoch": 0.47, "learning_rate": 0.0002535104994661288, "loss": 0.6262, "step": 13170}
+{"epoch": 0.47, "learning_rate": 0.0002534749080555226, "loss": 0.6462, "step": 13180}
+{"epoch": 0.47, "learning_rate": 0.00025343931664491634, "loss": 0.7032, "step": 13190}
+{"epoch": 0.47, "learning_rate": 0.00025340372523431013, "loss": 0.6469, "step": 13200}
+{"epoch": 0.47, "learning_rate": 0.00025336813382370387, "loss": 0.6922, "step": 13210}
+{"epoch": 0.47, "learning_rate": 0.0002533325424130976, "loss": 0.7421, "step": 13220}
+{"epoch": 0.47, "learning_rate": 0.0002532969510024914, "loss": 0.6098, "step": 13230}
+{"epoch": 0.47, "learning_rate": 0.00025326135959188514, "loss": 0.6866, "step": 13240}
+{"epoch": 0.47, "learning_rate": 0.0002532257681812789, "loss": 0.6846, "step": 13250}
+{"epoch": 0.47, "learning_rate": 0.0002531901767706727, "loss": 0.6591, "step": 13260}
+{"epoch": 0.47, "learning_rate": 0.0002531545853600664, "loss": 0.6894, "step": 13270}
+{"epoch": 0.47, "learning_rate": 0.00025311899394946016, "loss": 0.6977, "step": 13280}
+{"epoch": 0.47, "learning_rate": 0.0002530834025388539, "loss": 0.6943, "step": 13290}
+{"epoch": 0.47, "learning_rate": 0.0002530478111282477, "loss": 0.7509, "step": 13300}
+{"epoch": 0.47, "learning_rate": 0.00025301221971764143, "loss": 0.6725, "step": 13310}
+{"epoch": 0.47, "learning_rate": 0.0002529766283070352, "loss": 0.6886, "step": 13320}
+{"epoch": 0.47, "learning_rate": 0.00025294103689642896, "loss": 0.7321, "step": 13330}
+{"epoch": 0.47, "learning_rate": 0.00025290544548582276, "loss": 0.6697, "step": 13340}
+{"epoch": 0.47, "learning_rate": 0.0002528698540752165, "loss": 0.709, "step": 13350}
+{"epoch": 0.47, "learning_rate": 0.0002528342626646103, "loss": 0.6317, "step": 13360}
+{"epoch": 0.48, "learning_rate": 0.00025279867125400403, "loss": 0.6817, "step": 13370}
+{"epoch": 0.48, "learning_rate": 0.00025276307984339777, "loss": 0.6444, "step": 13380}
+{"epoch": 0.48, "learning_rate": 0.00025272748843279156, "loss": 0.6837, "step": 13390}
+{"epoch": 0.48, "learning_rate": 0.0002526918970221853, "loss": 0.5978, "step": 13400}
+{"epoch": 0.48, "learning_rate": 0.00025265630561157904, "loss": 0.6873, "step": 13410}
+{"epoch": 0.48, "learning_rate": 0.0002526207142009728, "loss": 0.6716, "step": 13420}
+{"epoch": 0.48, "learning_rate": 0.0002525851227903666, "loss": 0.638, "step": 13430}
+{"epoch": 0.48, "learning_rate": 0.0002525495313797603, "loss": 0.6422, "step": 13440}
+{"epoch": 0.48, "learning_rate": 0.00025251393996915405, "loss": 0.6885, "step": 13450}
+{"epoch": 0.48, "learning_rate": 0.00025247834855854785, "loss": 0.706, "step": 13460}
+{"epoch": 0.48, "learning_rate": 0.0002524427571479416, "loss": 0.6301, "step": 13470}
+{"epoch": 0.48, "learning_rate": 0.0002524071657373354, "loss": 0.632, "step": 13480}
+{"epoch": 0.48, "learning_rate": 0.0002523715743267291, "loss": 0.5909, "step": 13490}
+{"epoch": 0.48, "learning_rate": 0.0002523359829161229, "loss": 0.6306, "step": 13500}
+{"epoch": 0.48, "learning_rate": 0.00025230039150551665, "loss": 0.5696, "step": 13510}
+{"epoch": 0.48, "learning_rate": 0.0002522648000949104, "loss": 0.6982, "step": 13520}
+{"epoch": 0.48, "learning_rate": 0.0002522292086843042, "loss": 0.6278, "step": 13530}
+{"epoch": 0.48, "learning_rate": 0.0002521936172736979, "loss": 0.73, "step": 13540}
+{"epoch": 0.48, "learning_rate": 0.00025215802586309166, "loss": 0.7321, "step": 13550}
+{"epoch": 0.48, "learning_rate": 0.00025212243445248546, "loss": 0.66, "step": 13560}
+{"epoch": 0.48, "learning_rate": 0.0002520868430418792, "loss": 0.6594, "step": 13570}
+{"epoch": 0.48, "learning_rate": 0.00025205125163127294, "loss": 0.6585, "step": 13580}
+{"epoch": 0.48, "learning_rate": 0.00025201566022066673, "loss": 0.614, "step": 13590}
+{"epoch": 0.48, "learning_rate": 0.00025198006881006047, "loss": 0.6811, "step": 13600}
+{"epoch": 0.48, "learning_rate": 0.00025194447739945426, "loss": 0.7428, "step": 13610}
+{"epoch": 0.48, "learning_rate": 0.000251908885988848, "loss": 0.666, "step": 13620}
+{"epoch": 0.48, "learning_rate": 0.00025187329457824174, "loss": 0.7152, "step": 13630}
+{"epoch": 0.48, "learning_rate": 0.00025183770316763554, "loss": 0.6649, "step": 13640}
+{"epoch": 0.49, "learning_rate": 0.0002518021117570293, "loss": 0.6833, "step": 13650}
+{"epoch": 0.49, "learning_rate": 0.00025176652034642307, "loss": 0.6988, "step": 13660}
+{"epoch": 0.49, "learning_rate": 0.0002517309289358168, "loss": 0.5722, "step": 13670}
+{"epoch": 0.49, "learning_rate": 0.00025169533752521055, "loss": 0.5754, "step": 13680}
+{"epoch": 0.49, "learning_rate": 0.00025165974611460434, "loss": 0.6248, "step": 13690}
+{"epoch": 0.49, "learning_rate": 0.0002516241547039981, "loss": 0.6394, "step": 13700}
+{"epoch": 0.49, "learning_rate": 0.0002515885632933918, "loss": 0.6712, "step": 13710}
+{"epoch": 0.49, "learning_rate": 0.0002515529718827856, "loss": 0.7226, "step": 13720}
+{"epoch": 0.49, "learning_rate": 0.00025151738047217935, "loss": 0.688, "step": 13730}
+{"epoch": 0.49, "learning_rate": 0.0002514817890615731, "loss": 0.7168, "step": 13740}
+{"epoch": 0.49, "learning_rate": 0.0002514461976509669, "loss": 0.663, "step": 13750}
+{"epoch": 0.49, "learning_rate": 0.0002514106062403606, "loss": 0.663, "step": 13760}
+{"epoch": 0.49, "learning_rate": 0.0002513750148297544, "loss": 0.7507, "step": 13770}
+{"epoch": 0.49, "learning_rate": 0.00025133942341914816, "loss": 0.6108, "step": 13780}
+{"epoch": 0.49, "learning_rate": 0.00025130383200854195, "loss": 0.6595, "step": 13790}
+{"epoch": 0.49, "learning_rate": 0.0002512682405979357, "loss": 0.7039, "step": 13800}
+{"epoch": 0.49, "learning_rate": 0.00025123264918732943, "loss": 0.6335, "step": 13810}
+{"epoch": 0.49, "learning_rate": 0.0002511970577767232, "loss": 0.6834, "step": 13820}
+{"epoch": 0.49, "learning_rate": 0.00025116146636611697, "loss": 0.5485, "step": 13830}
+{"epoch": 0.49, "learning_rate": 0.0002511258749555107, "loss": 0.7282, "step": 13840}
+{"epoch": 0.49, "learning_rate": 0.00025109028354490444, "loss": 0.7947, "step": 13850}
+{"epoch": 0.49, "learning_rate": 0.00025105469213429824, "loss": 0.5967, "step": 13860}
+{"epoch": 0.49, "learning_rate": 0.000251019100723692, "loss": 0.6473, "step": 13870}
+{"epoch": 0.49, "learning_rate": 0.0002509835093130857, "loss": 0.6457, "step": 13880}
+{"epoch": 0.49, "learning_rate": 0.0002509479179024795, "loss": 0.7073, "step": 13890}
+{"epoch": 0.49, "learning_rate": 0.00025091232649187325, "loss": 0.5058, "step": 13900}
+{"epoch": 0.49, "learning_rate": 0.00025087673508126704, "loss": 0.6743, "step": 13910}
+{"epoch": 0.49, "learning_rate": 0.0002508411436706608, "loss": 0.624, "step": 13920}
+{"epoch": 0.5, "learning_rate": 0.0002508055522600546, "loss": 0.6708, "step": 13930}
+{"epoch": 0.5, "learning_rate": 0.0002507699608494483, "loss": 0.6928, "step": 13940}
+{"epoch": 0.5, "learning_rate": 0.0002507343694388421, "loss": 0.6269, "step": 13950}
+{"epoch": 0.5, "learning_rate": 0.00025069877802823585, "loss": 0.6982, "step": 13960}
+{"epoch": 0.5, "learning_rate": 0.0002506631866176296, "loss": 0.5909, "step": 13970}
+{"epoch": 0.5, "learning_rate": 0.00025062759520702333, "loss": 0.6451, "step": 13980}
+{"epoch": 0.5, "learning_rate": 0.0002505920037964171, "loss": 0.6961, "step": 13990}
+{"epoch": 0.5, "learning_rate": 0.00025055641238581086, "loss": 0.7153, "step": 14000}
+{"epoch": 0.5, "learning_rate": 0.0002505208209752046, "loss": 0.7103, "step": 14010}
+{"epoch": 0.5, "learning_rate": 0.0002504852295645984, "loss": 0.7147, "step": 14020}
+{"epoch": 0.5, "learning_rate": 0.00025044963815399213, "loss": 0.773, "step": 14030}
+{"epoch": 0.5, "learning_rate": 0.0002504140467433859, "loss": 0.669, "step": 14040}
+{"epoch": 0.5, "learning_rate": 0.00025037845533277967, "loss": 0.6569, "step": 14050}
+{"epoch": 0.5, "learning_rate": 0.0002503428639221734, "loss": 0.7455, "step": 14060}
+{"epoch": 0.5, "learning_rate": 0.0002503072725115672, "loss": 0.5277, "step": 14070}
+{"epoch": 0.5, "learning_rate": 0.00025027168110096094, "loss": 0.58, "step": 14080}
+{"epoch": 0.5, "learning_rate": 0.00025023608969035473, "loss": 0.7198, "step": 14090}
+{"epoch": 0.5, "learning_rate": 0.00025020049827974847, "loss": 0.6862, "step": 14100}
+{"epoch": 0.5, "learning_rate": 0.0002501649068691422, "loss": 0.7313, "step": 14110}
+{"epoch": 0.5, "learning_rate": 0.000250129315458536, "loss": 0.7646, "step": 14120}
+{"epoch": 0.5, "learning_rate": 0.00025009372404792975, "loss": 0.6098, "step": 14130}
+{"epoch": 0.5, "learning_rate": 0.0002500581326373235, "loss": 0.697, "step": 14140}
+{"epoch": 0.5, "learning_rate": 0.0002500225412267173, "loss": 0.6837, "step": 14150}
+{"epoch": 0.5, "learning_rate": 0.000249986949816111, "loss": 0.5986, "step": 14160}
+{"epoch": 0.5, "learning_rate": 0.00024995135840550476, "loss": 0.8238, "step": 14170}
+{"epoch": 0.5, "learning_rate": 0.00024991576699489855, "loss": 0.6794, "step": 14180}
+{"epoch": 0.5, "learning_rate": 0.0002498801755842923, "loss": 0.6985, "step": 14190}
+{"epoch": 0.5, "learning_rate": 0.0002498445841736861, "loss": 0.6153, "step": 14200}
+{"epoch": 0.51, "learning_rate": 0.0002498089927630798, "loss": 0.7146, "step": 14210}
+{"epoch": 0.51, "learning_rate": 0.0002497734013524736, "loss": 0.6049, "step": 14220}
+{"epoch": 0.51, "learning_rate": 0.00024973780994186736, "loss": 0.6025, "step": 14230}
+{"epoch": 0.51, "learning_rate": 0.0002497022185312611, "loss": 0.7142, "step": 14240}
+{"epoch": 0.51, "learning_rate": 0.0002496666271206549, "loss": 0.6612, "step": 14250}
+{"epoch": 0.51, "learning_rate": 0.00024963103571004863, "loss": 0.6589, "step": 14260}
+{"epoch": 0.51, "learning_rate": 0.00024959544429944237, "loss": 0.5938, "step": 14270}
+{"epoch": 0.51, "learning_rate": 0.00024955985288883616, "loss": 0.7197, "step": 14280}
+{"epoch": 0.51, "learning_rate": 0.0002495242614782299, "loss": 0.6527, "step": 14290}
+{"epoch": 0.51, "learning_rate": 0.00024948867006762364, "loss": 0.7443, "step": 14300}
+{"epoch": 0.51, "learning_rate": 0.0002494530786570174, "loss": 0.6561, "step": 14310}
+{"epoch": 0.51, "learning_rate": 0.0002494174872464112, "loss": 0.6946, "step": 14320}
+{"epoch": 0.51, "learning_rate": 0.0002493818958358049, "loss": 0.7613, "step": 14330}
+{"epoch": 0.51, "learning_rate": 0.0002493463044251987, "loss": 0.6176, "step": 14340}
+{"epoch": 0.51, "learning_rate": 0.00024931071301459245, "loss": 0.6723, "step": 14350}
+{"epoch": 0.51, "learning_rate": 0.00024927512160398624, "loss": 0.6893, "step": 14360}
+{"epoch": 0.51, "learning_rate": 0.00024923953019338, "loss": 0.6068, "step": 14370}
+{"epoch": 0.51, "learning_rate": 0.0002492039387827738, "loss": 0.6743, "step": 14380}
+{"epoch": 0.51, "learning_rate": 0.0002491683473721675, "loss": 0.6366, "step": 14390}
+{"epoch": 0.51, "learning_rate": 0.00024913275596156125, "loss": 0.59, "step": 14400}
+{"epoch": 0.51, "learning_rate": 0.00024909716455095505, "loss": 0.6394, "step": 14410}
+{"epoch": 0.51, "learning_rate": 0.0002490615731403488, "loss": 0.7755, "step": 14420}
+{"epoch": 0.51, "learning_rate": 0.0002490259817297425, "loss": 0.5536, "step": 14430}
+{"epoch": 0.51, "learning_rate": 0.00024899039031913626, "loss": 0.6219, "step": 14440}
+{"epoch": 0.51, "learning_rate": 0.00024895479890853006, "loss": 0.6696, "step": 14450}
+{"epoch": 0.51, "learning_rate": 0.0002489192074979238, "loss": 0.6677, "step": 14460}
+{"epoch": 0.51, "learning_rate": 0.00024888361608731754, "loss": 0.6307, "step": 14470}
+{"epoch": 0.51, "learning_rate": 0.00024884802467671133, "loss": 0.6472, "step": 14480}
+{"epoch": 0.52, "learning_rate": 0.00024881243326610507, "loss": 0.6534, "step": 14490}
+{"epoch": 0.52, "learning_rate": 0.00024877684185549886, "loss": 0.6878, "step": 14500}
+{"epoch": 0.52, "learning_rate": 0.0002487412504448926, "loss": 0.7111, "step": 14510}
+{"epoch": 0.52, "learning_rate": 0.0002487056590342864, "loss": 0.6628, "step": 14520}
+{"epoch": 0.52, "learning_rate": 0.00024867006762368014, "loss": 0.6701, "step": 14530}
+{"epoch": 0.52, "learning_rate": 0.0002486344762130739, "loss": 0.6404, "step": 14540}
+{"epoch": 0.52, "learning_rate": 0.00024859888480246767, "loss": 0.6782, "step": 14550}
+{"epoch": 0.52, "learning_rate": 0.0002485632933918614, "loss": 0.7121, "step": 14560}
+{"epoch": 0.52, "learning_rate": 0.00024852770198125515, "loss": 0.6517, "step": 14570}
+{"epoch": 0.52, "learning_rate": 0.00024849211057064894, "loss": 0.646, "step": 14580}
+{"epoch": 0.52, "learning_rate": 0.0002484565191600427, "loss": 0.6125, "step": 14590}
+{"epoch": 0.52, "learning_rate": 0.0002484209277494364, "loss": 0.5713, "step": 14600}
+{"epoch": 0.52, "learning_rate": 0.0002483853363388302, "loss": 0.6996, "step": 14610}
+{"epoch": 0.52, "learning_rate": 0.00024834974492822395, "loss": 0.674, "step": 14620}
+{"epoch": 0.52, "learning_rate": 0.0002483141535176177, "loss": 0.7223, "step": 14630}
+{"epoch": 0.52, "learning_rate": 0.0002482785621070115, "loss": 0.7383, "step": 14640}
+{"epoch": 0.52, "learning_rate": 0.0002482429706964052, "loss": 0.6706, "step": 14650}
+{"epoch": 0.52, "learning_rate": 0.000248207379285799, "loss": 0.6425, "step": 14660}
+{"epoch": 0.52, "learning_rate": 0.00024817178787519276, "loss": 0.6618, "step": 14670}
+{"epoch": 0.52, "learning_rate": 0.00024813619646458655, "loss": 0.7539, "step": 14680}
+{"epoch": 0.52, "learning_rate": 0.0002481006050539803, "loss": 0.6389, "step": 14690}
+{"epoch": 0.52, "learning_rate": 0.00024806501364337403, "loss": 0.6362, "step": 14700}
+{"epoch": 0.52, "learning_rate": 0.0002480294222327678, "loss": 0.7019, "step": 14710}
+{"epoch": 0.52, "learning_rate": 0.00024799383082216157, "loss": 0.737, "step": 14720}
+{"epoch": 0.52, "learning_rate": 0.0002479582394115553, "loss": 0.6228, "step": 14730}
+{"epoch": 0.52, "learning_rate": 0.0002479226480009491, "loss": 0.7023, "step": 14740}
+{"epoch": 0.52, "learning_rate": 0.00024788705659034284, "loss": 0.6379, "step": 14750}
+{"epoch": 0.52, "learning_rate": 0.0002478514651797366, "loss": 0.7517, "step": 14760}
+{"epoch": 0.53, "learning_rate": 0.00024781587376913037, "loss": 0.6845, "step": 14770}
+{"epoch": 0.53, "learning_rate": 0.0002477802823585241, "loss": 0.7448, "step": 14780}
+{"epoch": 0.53, "learning_rate": 0.0002477446909479179, "loss": 0.6916, "step": 14790}
+{"epoch": 0.53, "learning_rate": 0.00024770909953731164, "loss": 0.7748, "step": 14800}
+{"epoch": 0.53, "learning_rate": 0.00024767350812670544, "loss": 0.6597, "step": 14810}
+{"epoch": 0.53, "learning_rate": 0.0002476379167160992, "loss": 0.699, "step": 14820}
+{"epoch": 0.53, "learning_rate": 0.0002476023253054929, "loss": 0.7032, "step": 14830}
+{"epoch": 0.53, "learning_rate": 0.0002475667338948867, "loss": 0.6889, "step": 14840}
+{"epoch": 0.53, "learning_rate": 0.00024753114248428045, "loss": 0.6236, "step": 14850}
+{"epoch": 0.53, "learning_rate": 0.0002474955510736742, "loss": 0.667, "step": 14860}
+{"epoch": 0.53, "learning_rate": 0.00024745995966306793, "loss": 0.6916, "step": 14870}
+{"epoch": 0.53, "learning_rate": 0.0002474243682524617, "loss": 0.7216, "step": 14880}
+{"epoch": 0.53, "learning_rate": 0.00024738877684185546, "loss": 0.6766, "step": 14890}
+{"epoch": 0.53, "learning_rate": 0.0002473531854312492, "loss": 0.6951, "step": 14900}
+{"epoch": 0.53, "learning_rate": 0.000247317594020643, "loss": 0.6766, "step": 14910}
+{"epoch": 0.53, "learning_rate": 0.00024728200261003673, "loss": 0.6693, "step": 14920}
+{"epoch": 0.53, "learning_rate": 0.00024724641119943053, "loss": 0.6616, "step": 14930}
+{"epoch": 0.53, "learning_rate": 0.00024721081978882427, "loss": 0.6795, "step": 14940}
+{"epoch": 0.53, "learning_rate": 0.00024717522837821806, "loss": 0.6114, "step": 14950}
+{"epoch": 0.53, "learning_rate": 0.0002471396369676118, "loss": 0.6599, "step": 14960}
+{"epoch": 0.53, "learning_rate": 0.0002471040455570056, "loss": 0.6986, "step": 14970}
+{"epoch": 0.53, "learning_rate": 0.00024706845414639933, "loss": 0.653, "step": 14980}
+{"epoch": 0.53, "learning_rate": 0.0002470328627357931, "loss": 0.6804, "step": 14990}
+{"epoch": 0.53, "learning_rate": 0.0002469972713251868, "loss": 0.7093, "step": 15000}
+{"epoch": 0.53, "learning_rate": 0.0002469616799145806, "loss": 0.6299, "step": 15010}
+{"epoch": 0.53, "learning_rate": 0.00024692608850397435, "loss": 0.6224, "step": 15020}
+{"epoch": 0.53, "learning_rate": 0.0002468904970933681, "loss": 0.7414, "step": 15030}
+{"epoch": 0.53, "learning_rate": 0.0002468549056827619, "loss": 0.707, "step": 15040}
+{"epoch": 0.54, "learning_rate": 0.0002468193142721556, "loss": 0.7286, "step": 15050}
+{"epoch": 0.54, "learning_rate": 0.00024678372286154936, "loss": 0.7436, "step": 15060}
+{"epoch": 0.54, "learning_rate": 0.00024674813145094315, "loss": 0.671, "step": 15070}
+{"epoch": 0.54, "learning_rate": 0.0002467125400403369, "loss": 0.7036, "step": 15080}
+{"epoch": 0.54, "learning_rate": 0.0002466769486297307, "loss": 0.5889, "step": 15090}
+{"epoch": 0.54, "learning_rate": 0.0002466413572191244, "loss": 0.72, "step": 15100}
+{"epoch": 0.54, "learning_rate": 0.0002466057658085182, "loss": 0.6538, "step": 15110}
+{"epoch": 0.54, "learning_rate": 0.00024657017439791196, "loss": 0.6813, "step": 15120}
+{"epoch": 0.54, "learning_rate": 0.0002465345829873057, "loss": 0.6662, "step": 15130}
+{"epoch": 0.54, "learning_rate": 0.0002464989915766995, "loss": 0.6727, "step": 15140}
+{"epoch": 0.54, "learning_rate": 0.00024646340016609323, "loss": 0.5828, "step": 15150}
+{"epoch": 0.54, "learning_rate": 0.00024642780875548697, "loss": 0.6408, "step": 15160}
+{"epoch": 0.54, "learning_rate": 0.00024639221734488076, "loss": 0.6419, "step": 15170}
+{"epoch": 0.54, "learning_rate": 0.0002463566259342745, "loss": 0.687, "step": 15180}
+{"epoch": 0.54, "learning_rate": 0.00024632103452366824, "loss": 0.6691, "step": 15190}
+{"epoch": 0.54, "learning_rate": 0.00024628544311306204, "loss": 0.7671, "step": 15200}
+{"epoch": 0.54, "learning_rate": 0.0002462498517024558, "loss": 0.6963, "step": 15210}
+{"epoch": 0.54, "learning_rate": 0.0002462142602918495, "loss": 0.6452, "step": 15220}
+{"epoch": 0.54, "learning_rate": 0.0002461786688812433, "loss": 0.7518, "step": 15230}
+{"epoch": 0.54, "learning_rate": 0.00024614307747063705, "loss": 0.6961, "step": 15240}
+{"epoch": 0.54, "learning_rate": 0.00024610748606003084, "loss": 0.6614, "step": 15250}
+{"epoch": 0.54, "learning_rate": 0.0002460718946494246, "loss": 0.6297, "step": 15260}
+{"epoch": 0.54, "learning_rate": 0.0002460363032388184, "loss": 0.7473, "step": 15270}
+{"epoch": 0.54, "learning_rate": 0.0002460007118282121, "loss": 0.6758, "step": 15280}
+{"epoch": 0.54, "learning_rate": 0.00024596512041760585, "loss": 0.6179, "step": 15290}
+{"epoch": 0.54, "learning_rate": 0.00024592952900699965, "loss": 0.631, "step": 15300}
+{"epoch": 0.54, "learning_rate": 0.0002458939375963934, "loss": 0.6952, "step": 15310}
+{"epoch": 0.54, "learning_rate": 0.0002458583461857871, "loss": 0.6148, "step": 15320}
+{"epoch": 0.54, "learning_rate": 0.00024582275477518086, "loss": 0.7256, "step": 15330}
+{"epoch": 0.55, "learning_rate": 0.00024578716336457466, "loss": 0.6646, "step": 15340}
+{"epoch": 0.55, "learning_rate": 0.0002457515719539684, "loss": 0.6832, "step": 15350}
+{"epoch": 0.55, "learning_rate": 0.0002457159805433622, "loss": 0.7076, "step": 15360}
+{"epoch": 0.55, "learning_rate": 0.00024568038913275593, "loss": 0.6201, "step": 15370}
+{"epoch": 0.55, "learning_rate": 0.0002456447977221497, "loss": 0.6015, "step": 15380}
+{"epoch": 0.55, "learning_rate": 0.00024560920631154346, "loss": 0.6716, "step": 15390}
+{"epoch": 0.55, "learning_rate": 0.00024557361490093726, "loss": 0.5865, "step": 15400}
+{"epoch": 0.55, "learning_rate": 0.000245538023490331, "loss": 0.7035, "step": 15410}
+{"epoch": 0.55, "learning_rate": 0.00024550243207972474, "loss": 0.6434, "step": 15420}
+{"epoch": 0.55, "learning_rate": 0.00024546684066911853, "loss": 0.7037, "step": 15430}
+{"epoch": 0.55, "learning_rate": 0.00024543124925851227, "loss": 0.6758, "step": 15440}
+{"epoch": 0.55, "learning_rate": 0.000245395657847906, "loss": 0.6509, "step": 15450}
+{"epoch": 0.55, "learning_rate": 0.00024536006643729975, "loss": 0.6783, "step": 15460}
+{"epoch": 0.55, "learning_rate": 0.00024532447502669354, "loss": 0.6512, "step": 15470}
+{"epoch": 0.55, "learning_rate": 0.0002452888836160873, "loss": 0.682, "step": 15480}
+{"epoch": 0.55, "learning_rate": 0.000245253292205481, "loss": 0.6338, "step": 15490}
+{"epoch": 0.55, "learning_rate": 0.0002452177007948748, "loss": 0.6194, "step": 15500}
+{"epoch": 0.55, "learning_rate": 0.00024518210938426855, "loss": 0.5854, "step": 15510}
+{"epoch": 0.55, "learning_rate": 0.00024514651797366235, "loss": 0.575, "step": 15520}
+{"epoch": 0.55, "learning_rate": 0.0002451109265630561, "loss": 0.768, "step": 15530}
+{"epoch": 0.55, "learning_rate": 0.0002450753351524499, "loss": 0.7963, "step": 15540}
+{"epoch": 0.55, "learning_rate": 0.0002450397437418436, "loss": 0.6532, "step": 15550}
+{"epoch": 0.55, "learning_rate": 0.00024500415233123736, "loss": 0.5938, "step": 15560}
+{"epoch": 0.55, "learning_rate": 0.00024496856092063115, "loss": 0.7571, "step": 15570}
+{"epoch": 0.55, "learning_rate": 0.0002449329695100249, "loss": 0.7252, "step": 15580}
+{"epoch": 0.55, "learning_rate": 0.00024489737809941863, "loss": 0.6731, "step": 15590}
+{"epoch": 0.55, "learning_rate": 0.0002448617866888124, "loss": 0.7083, "step": 15600}
+{"epoch": 0.55, "learning_rate": 0.00024482619527820617, "loss": 0.652, "step": 15610}
+{"epoch": 0.56, "learning_rate": 0.0002447906038675999, "loss": 0.682, "step": 15620}
+{"epoch": 0.56, "learning_rate": 0.0002447550124569937, "loss": 0.6907, "step": 15630}
+{"epoch": 0.56, "learning_rate": 0.00024471942104638744, "loss": 0.6447, "step": 15640}
+{"epoch": 0.56, "learning_rate": 0.0002446838296357812, "loss": 0.7077, "step": 15650}
+{"epoch": 0.56, "learning_rate": 0.00024464823822517497, "loss": 0.7185, "step": 15660}
+{"epoch": 0.56, "learning_rate": 0.0002446126468145687, "loss": 0.6684, "step": 15670}
+{"epoch": 0.56, "learning_rate": 0.0002445770554039625, "loss": 0.6726, "step": 15680}
+{"epoch": 0.56, "learning_rate": 0.00024454146399335624, "loss": 0.693, "step": 15690}
+{"epoch": 0.56, "learning_rate": 0.00024450587258275004, "loss": 0.6531, "step": 15700}
+{"epoch": 0.56, "learning_rate": 0.0002444702811721438, "loss": 0.6829, "step": 15710}
+{"epoch": 0.56, "learning_rate": 0.0002444346897615375, "loss": 0.6906, "step": 15720}
+{"epoch": 0.56, "learning_rate": 0.0002443990983509313, "loss": 0.6097, "step": 15730}
+{"epoch": 0.56, "learning_rate": 0.00024436350694032505, "loss": 0.6018, "step": 15740}
+{"epoch": 0.56, "learning_rate": 0.0002443279155297188, "loss": 0.6812, "step": 15750}
+{"epoch": 0.56, "learning_rate": 0.0002442923241191126, "loss": 0.6864, "step": 15760}
+{"epoch": 0.56, "learning_rate": 0.0002442567327085063, "loss": 0.6853, "step": 15770}
+{"epoch": 0.56, "learning_rate": 0.00024422114129790006, "loss": 0.6916, "step": 15780}
+{"epoch": 0.56, "learning_rate": 0.00024418554988729386, "loss": 0.6241, "step": 15790}
+{"epoch": 0.56, "learning_rate": 0.0002441499584766876, "loss": 0.8003, "step": 15800}
+{"epoch": 0.56, "learning_rate": 0.00024411436706608136, "loss": 0.6329, "step": 15810}
+{"epoch": 0.56, "learning_rate": 0.0002440787756554751, "loss": 0.7585, "step": 15820}
+{"epoch": 0.56, "learning_rate": 0.0002440431842448689, "loss": 0.6591, "step": 15830}
+{"epoch": 0.56, "learning_rate": 0.00024400759283426263, "loss": 0.6838, "step": 15840}
+{"epoch": 0.56, "learning_rate": 0.0002439720014236564, "loss": 0.6254, "step": 15850}
+{"epoch": 0.56, "learning_rate": 0.00024393641001305017, "loss": 0.7214, "step": 15860}
+{"epoch": 0.56, "learning_rate": 0.00024390081860244393, "loss": 0.7125, "step": 15870}
+{"epoch": 0.56, "learning_rate": 0.00024386522719183767, "loss": 0.7192, "step": 15880}
+{"epoch": 0.56, "learning_rate": 0.00024383319492229206, "loss": 0.6695, "step": 15890}
+{"epoch": 0.57, "learning_rate": 0.0002437976035116858, "loss": 0.6677, "step": 15900}
+{"epoch": 0.57, "learning_rate": 0.0002437620121010796, "loss": 0.6524, "step": 15910}
+{"epoch": 0.57, "learning_rate": 0.00024372642069047333, "loss": 0.6934, "step": 15920}
+{"epoch": 0.57, "learning_rate": 0.0002436908292798671, "loss": 0.6521, "step": 15930}
+{"epoch": 0.57, "learning_rate": 0.00024365523786926087, "loss": 0.6595, "step": 15940}
+{"epoch": 0.57, "learning_rate": 0.00024361964645865463, "loss": 0.6675, "step": 15950}
+{"epoch": 0.57, "learning_rate": 0.00024358405504804837, "loss": 0.7328, "step": 15960}
+{"epoch": 0.57, "learning_rate": 0.00024354846363744214, "loss": 0.6115, "step": 15970}
+{"epoch": 0.57, "learning_rate": 0.0002435128722268359, "loss": 0.6868, "step": 15980}
+{"epoch": 0.57, "learning_rate": 0.00024347728081622967, "loss": 0.6666, "step": 15990}
+{"epoch": 0.57, "learning_rate": 0.0002434416894056234, "loss": 0.6702, "step": 16000}
+{"epoch": 0.57, "learning_rate": 0.00024340609799501718, "loss": 0.6715, "step": 16010}
+{"epoch": 0.57, "learning_rate": 0.00024337050658441094, "loss": 0.673, "step": 16020}
+{"epoch": 0.57, "learning_rate": 0.00024333491517380468, "loss": 0.6646, "step": 16030}
+{"epoch": 0.57, "learning_rate": 0.00024329932376319848, "loss": 0.6465, "step": 16040}
+{"epoch": 0.57, "learning_rate": 0.00024326373235259222, "loss": 0.7336, "step": 16050}
+{"epoch": 0.57, "learning_rate": 0.00024322814094198598, "loss": 0.5739, "step": 16060}
+{"epoch": 0.57, "learning_rate": 0.00024319254953137975, "loss": 0.6218, "step": 16070}
+{"epoch": 0.57, "learning_rate": 0.00024315695812077352, "loss": 0.676, "step": 16080}
+{"epoch": 0.57, "learning_rate": 0.00024312136671016726, "loss": 0.609, "step": 16090}
+{"epoch": 0.57, "learning_rate": 0.000243085775299561, "loss": 0.6883, "step": 16100}
+{"epoch": 0.57, "learning_rate": 0.0002430501838889548, "loss": 0.636, "step": 16110}
+{"epoch": 0.57, "learning_rate": 0.00024301459247834853, "loss": 0.6424, "step": 16120}
+{"epoch": 0.57, "learning_rate": 0.0002429790010677423, "loss": 0.7523, "step": 16130}
+{"epoch": 0.57, "learning_rate": 0.00024294340965713606, "loss": 0.7219, "step": 16140}
+{"epoch": 0.57, "learning_rate": 0.00024290781824652983, "loss": 0.6846, "step": 16150}
+{"epoch": 0.57, "learning_rate": 0.00024287222683592357, "loss": 0.6735, "step": 16160}
+{"epoch": 0.57, "learning_rate": 0.00024283663542531736, "loss": 0.6184, "step": 16170}
+{"epoch": 0.58, "learning_rate": 0.0002428010440147111, "loss": 0.6521, "step": 16180}
+{"epoch": 0.58, "learning_rate": 0.00024276545260410484, "loss": 0.5792, "step": 16190}
+{"epoch": 0.58, "learning_rate": 0.0002427298611934986, "loss": 0.6913, "step": 16200}
+{"epoch": 0.58, "learning_rate": 0.00024269426978289237, "loss": 0.6387, "step": 16210}
+{"epoch": 0.58, "learning_rate": 0.00024265867837228614, "loss": 0.6401, "step": 16220}
+{"epoch": 0.58, "learning_rate": 0.00024262308696167988, "loss": 0.7866, "step": 16230}
+{"epoch": 0.58, "learning_rate": 0.00024258749555107367, "loss": 0.6497, "step": 16240}
+{"epoch": 0.58, "learning_rate": 0.0002425519041404674, "loss": 0.6951, "step": 16250}
+{"epoch": 0.58, "learning_rate": 0.00024251631272986115, "loss": 0.6984, "step": 16260}
+{"epoch": 0.58, "learning_rate": 0.00024248072131925495, "loss": 0.6134, "step": 16270}
+{"epoch": 0.58, "learning_rate": 0.00024244512990864869, "loss": 0.5983, "step": 16280}
+{"epoch": 0.58, "learning_rate": 0.00024240953849804245, "loss": 0.6449, "step": 16290}
+{"epoch": 0.58, "learning_rate": 0.00024237394708743622, "loss": 0.6779, "step": 16300}
+{"epoch": 0.58, "learning_rate": 0.00024233835567682998, "loss": 0.6475, "step": 16310}
+{"epoch": 0.58, "learning_rate": 0.00024230276426622372, "loss": 0.7089, "step": 16320}
+{"epoch": 0.58, "learning_rate": 0.00024226717285561746, "loss": 0.74, "step": 16330}
+{"epoch": 0.58, "learning_rate": 0.00024223158144501126, "loss": 0.7564, "step": 16340}
+{"epoch": 0.58, "learning_rate": 0.000242195990034405, "loss": 0.6169, "step": 16350}
+{"epoch": 0.58, "learning_rate": 0.00024216039862379876, "loss": 0.6995, "step": 16360}
+{"epoch": 0.58, "learning_rate": 0.00024212480721319253, "loss": 0.6493, "step": 16370}
+{"epoch": 0.58, "learning_rate": 0.0002420892158025863, "loss": 0.6621, "step": 16380}
+{"epoch": 0.58, "learning_rate": 0.00024205362439198004, "loss": 0.6218, "step": 16390}
+{"epoch": 0.58, "learning_rate": 0.00024201803298137383, "loss": 0.6516, "step": 16400}
+{"epoch": 0.58, "learning_rate": 0.00024198244157076757, "loss": 0.6984, "step": 16410}
+{"epoch": 0.58, "learning_rate": 0.0002419468501601613, "loss": 0.6704, "step": 16420}
+{"epoch": 0.58, "learning_rate": 0.00024191125874955508, "loss": 0.6176, "step": 16430}
+{"epoch": 0.58, "learning_rate": 0.00024187566733894884, "loss": 0.5708, "step": 16440}
+{"epoch": 0.58, "learning_rate": 0.0002418400759283426, "loss": 0.6644, "step": 16450}
+{"epoch": 0.59, "learning_rate": 0.00024180448451773635, "loss": 0.5657, "step": 16460}
+{"epoch": 0.59, "learning_rate": 0.00024176889310713014, "loss": 0.6141, "step": 16470}
+{"epoch": 0.59, "learning_rate": 0.00024173330169652388, "loss": 0.6269, "step": 16480}
+{"epoch": 0.59, "learning_rate": 0.00024169771028591765, "loss": 0.6035, "step": 16490}
+{"epoch": 0.59, "learning_rate": 0.00024166211887531141, "loss": 0.6679, "step": 16500}
+{"epoch": 0.59, "learning_rate": 0.00024162652746470515, "loss": 0.6359, "step": 16510}
+{"epoch": 0.59, "learning_rate": 0.00024159093605409892, "loss": 0.7402, "step": 16520}
+{"epoch": 0.59, "learning_rate": 0.0002415553446434927, "loss": 0.6607, "step": 16530}
+{"epoch": 0.59, "learning_rate": 0.00024151975323288645, "loss": 0.6889, "step": 16540}
+{"epoch": 0.59, "learning_rate": 0.0002414841618222802, "loss": 0.6536, "step": 16550}
+{"epoch": 0.59, "learning_rate": 0.00024144857041167396, "loss": 0.6205, "step": 16560}
+{"epoch": 0.59, "learning_rate": 0.00024141297900106773, "loss": 0.7202, "step": 16570}
+{"epoch": 0.59, "learning_rate": 0.0002413773875904615, "loss": 0.6024, "step": 16580}
+{"epoch": 0.59, "learning_rate": 0.00024134179617985523, "loss": 0.6302, "step": 16590}
+{"epoch": 0.59, "learning_rate": 0.00024130620476924903, "loss": 0.708, "step": 16600}
+{"epoch": 0.59, "learning_rate": 0.00024127061335864276, "loss": 0.6989, "step": 16610}
+{"epoch": 0.59, "learning_rate": 0.0002412350219480365, "loss": 0.674, "step": 16620}
+{"epoch": 0.59, "learning_rate": 0.0002411994305374303, "loss": 0.6691, "step": 16630}
+{"epoch": 0.59, "learning_rate": 0.00024116383912682404, "loss": 0.7193, "step": 16640}
+{"epoch": 0.59, "learning_rate": 0.0002411282477162178, "loss": 0.649, "step": 16650}
+{"epoch": 0.59, "learning_rate": 0.00024109265630561154, "loss": 0.729, "step": 16660}
+{"epoch": 0.59, "learning_rate": 0.00024105706489500534, "loss": 0.8033, "step": 16670}
+{"epoch": 0.59, "learning_rate": 0.00024102147348439908, "loss": 0.6541, "step": 16680}
+{"epoch": 0.59, "learning_rate": 0.00024098588207379282, "loss": 0.6373, "step": 16690}
+{"epoch": 0.59, "learning_rate": 0.0002409502906631866, "loss": 0.6739, "step": 16700}
+{"epoch": 0.59, "learning_rate": 0.00024091469925258035, "loss": 0.6097, "step": 16710}
+{"epoch": 0.59, "learning_rate": 0.00024087910784197412, "loss": 0.6785, "step": 16720}
+{"epoch": 0.59, "learning_rate": 0.00024084351643136788, "loss": 0.6112, "step": 16730}
+{"epoch": 0.6, "learning_rate": 0.00024080792502076165, "loss": 0.6891, "step": 16740}
+{"epoch": 0.6, "learning_rate": 0.0002407723336101554, "loss": 0.6048, "step": 16750}
+{"epoch": 0.6, "learning_rate": 0.00024073674219954918, "loss": 0.7102, "step": 16760}
+{"epoch": 0.6, "learning_rate": 0.00024070115078894292, "loss": 0.6232, "step": 16770}
+{"epoch": 0.6, "learning_rate": 0.00024066555937833666, "loss": 0.5981, "step": 16780}
+{"epoch": 0.6, "learning_rate": 0.00024062996796773043, "loss": 0.6137, "step": 16790}
+{"epoch": 0.6, "learning_rate": 0.0002405943765571242, "loss": 0.6426, "step": 16800}
+{"epoch": 0.6, "learning_rate": 0.00024055878514651796, "loss": 0.631, "step": 16810}
+{"epoch": 0.6, "learning_rate": 0.0002405231937359117, "loss": 0.6843, "step": 16820}
+{"epoch": 0.6, "learning_rate": 0.0002404876023253055, "loss": 0.79, "step": 16830}
+{"epoch": 0.6, "learning_rate": 0.00024045201091469923, "loss": 0.655, "step": 16840}
+{"epoch": 0.6, "learning_rate": 0.00024041641950409297, "loss": 0.6323, "step": 16850}
+{"epoch": 0.6, "learning_rate": 0.00024038082809348677, "loss": 0.6674, "step": 16860}
+{"epoch": 0.6, "learning_rate": 0.0002403452366828805, "loss": 0.6571, "step": 16870}
+{"epoch": 0.6, "learning_rate": 0.00024030964527227427, "loss": 0.6069, "step": 16880}
+{"epoch": 0.6, "learning_rate": 0.000240274053861668, "loss": 0.6858, "step": 16890}
+{"epoch": 0.6, "learning_rate": 0.0002402384624510618, "loss": 0.6182, "step": 16900}
+{"epoch": 0.6, "learning_rate": 0.00024020287104045554, "loss": 0.5668, "step": 16910}
+{"epoch": 0.6, "learning_rate": 0.00024016727962984928, "loss": 0.717, "step": 16920}
+{"epoch": 0.6, "learning_rate": 0.00024013168821924308, "loss": 0.7248, "step": 16930}
+{"epoch": 0.6, "learning_rate": 0.00024009609680863682, "loss": 0.6498, "step": 16940}
+{"epoch": 0.6, "learning_rate": 0.00024006050539803058, "loss": 0.6457, "step": 16950}
+{"epoch": 0.6, "learning_rate": 0.00024002491398742435, "loss": 0.7854, "step": 16960}
+{"epoch": 0.6, "learning_rate": 0.00023998932257681812, "loss": 0.6564, "step": 16970}
+{"epoch": 0.6, "learning_rate": 0.00023995373116621186, "loss": 0.9188, "step": 16980}
+{"epoch": 0.6, "learning_rate": 0.0002399181397556056, "loss": 0.6874, "step": 16990}
+{"epoch": 0.6, "learning_rate": 0.0002398825483449994, "loss": 0.5946, "step": 17000}
+{"epoch": 0.6, "learning_rate": 0.00023984695693439313, "loss": 0.6985, "step": 17010}
+{"epoch": 0.61, "learning_rate": 0.0002398113655237869, "loss": 0.6121, "step": 17020}
+{"epoch": 0.61, "learning_rate": 0.00023977577411318066, "loss": 0.6853, "step": 17030}
+{"epoch": 0.61, "learning_rate": 0.00023974018270257443, "loss": 0.6888, "step": 17040}
+{"epoch": 0.61, "learning_rate": 0.00023970459129196817, "loss": 0.726, "step": 17050}
+{"epoch": 0.61, "learning_rate": 0.00023966899988136196, "loss": 0.7037, "step": 17060}
+{"epoch": 0.61, "learning_rate": 0.0002396334084707557, "loss": 0.6722, "step": 17070}
+{"epoch": 0.61, "learning_rate": 0.00023959781706014947, "loss": 0.7054, "step": 17080}
+{"epoch": 0.61, "learning_rate": 0.00023956222564954323, "loss": 0.6357, "step": 17090}
+{"epoch": 0.61, "learning_rate": 0.00023952663423893697, "loss": 0.6819, "step": 17100}
+{"epoch": 0.61, "learning_rate": 0.00023949104282833074, "loss": 0.7216, "step": 17110}
+{"epoch": 0.61, "learning_rate": 0.00023945545141772448, "loss": 0.824, "step": 17120}
+{"epoch": 0.61, "learning_rate": 0.00023941986000711827, "loss": 0.7002, "step": 17130}
+{"epoch": 0.61, "learning_rate": 0.000239384268596512, "loss": 0.5983, "step": 17140}
+{"epoch": 0.61, "learning_rate": 0.00023934867718590578, "loss": 0.7212, "step": 17150}
+{"epoch": 0.61, "learning_rate": 0.00023931308577529955, "loss": 0.6232, "step": 17160}
+{"epoch": 0.61, "learning_rate": 0.0002392774943646933, "loss": 0.7449, "step": 17170}
+{"epoch": 0.61, "learning_rate": 0.00023924190295408705, "loss": 0.6891, "step": 17180}
+{"epoch": 0.61, "learning_rate": 0.00023920631154348085, "loss": 0.6748, "step": 17190}
+{"epoch": 0.61, "learning_rate": 0.00023917072013287459, "loss": 0.6518, "step": 17200}
+{"epoch": 0.61, "learning_rate": 0.00023913512872226832, "loss": 0.7308, "step": 17210}
+{"epoch": 0.61, "learning_rate": 0.0002390995373116621, "loss": 0.6391, "step": 17220}
+{"epoch": 0.61, "learning_rate": 0.00023906394590105586, "loss": 0.6932, "step": 17230}
+{"epoch": 0.61, "learning_rate": 0.00023902835449044962, "loss": 0.7924, "step": 17240}
+{"epoch": 0.61, "learning_rate": 0.00023899276307984336, "loss": 0.7031, "step": 17250}
+{"epoch": 0.61, "learning_rate": 0.00023895717166923716, "loss": 0.6973, "step": 17260}
+{"epoch": 0.61, "learning_rate": 0.0002389215802586309, "loss": 0.6141, "step": 17270}
+{"epoch": 0.61, "learning_rate": 0.00023888598884802464, "loss": 0.6046, "step": 17280}
+{"epoch": 0.61, "learning_rate": 0.00023885039743741843, "loss": 0.6557, "step": 17290}
+{"epoch": 0.62, "learning_rate": 0.00023881480602681217, "loss": 0.6583, "step": 17300}
+{"epoch": 0.62, "learning_rate": 0.00023877921461620594, "loss": 0.7034, "step": 17310}
+{"epoch": 0.62, "learning_rate": 0.0002387436232055997, "loss": 0.6628, "step": 17320}
+{"epoch": 0.62, "learning_rate": 0.00023870803179499347, "loss": 0.6703, "step": 17330}
+{"epoch": 0.62, "learning_rate": 0.0002386724403843872, "loss": 0.7009, "step": 17340}
+{"epoch": 0.62, "learning_rate": 0.00023863684897378095, "loss": 0.668, "step": 17350}
+{"epoch": 0.62, "learning_rate": 0.00023860125756317474, "loss": 0.6194, "step": 17360}
+{"epoch": 0.62, "learning_rate": 0.00023856566615256848, "loss": 0.7085, "step": 17370}
+{"epoch": 0.62, "learning_rate": 0.00023853007474196225, "loss": 0.6256, "step": 17380}
+{"epoch": 0.62, "learning_rate": 0.00023849448333135601, "loss": 0.608, "step": 17390}
+{"epoch": 0.62, "learning_rate": 0.00023845889192074978, "loss": 0.7403, "step": 17400}
+{"epoch": 0.62, "learning_rate": 0.00023842330051014352, "loss": 0.6186, "step": 17410}
+{"epoch": 0.62, "learning_rate": 0.00023838770909953731, "loss": 0.5992, "step": 17420}
+{"epoch": 0.62, "learning_rate": 0.00023835211768893105, "loss": 0.6174, "step": 17430}
+{"epoch": 0.62, "learning_rate": 0.0002383165262783248, "loss": 0.7687, "step": 17440}
+{"epoch": 0.62, "learning_rate": 0.00023828093486771856, "loss": 0.6416, "step": 17450}
+{"epoch": 0.62, "learning_rate": 0.00023824534345711233, "loss": 0.7833, "step": 17460}
+{"epoch": 0.62, "learning_rate": 0.0002382097520465061, "loss": 0.676, "step": 17470}
+{"epoch": 0.62, "learning_rate": 0.00023817416063589983, "loss": 0.6723, "step": 17480}
+{"epoch": 0.62, "learning_rate": 0.00023813856922529363, "loss": 0.7845, "step": 17490}
+{"epoch": 0.62, "learning_rate": 0.00023810297781468737, "loss": 0.779, "step": 17500}
+{"epoch": 0.62, "learning_rate": 0.0002380673864040811, "loss": 0.6912, "step": 17510}
+{"epoch": 0.62, "learning_rate": 0.0002380317949934749, "loss": 0.6264, "step": 17520}
+{"epoch": 0.62, "learning_rate": 0.00023799620358286864, "loss": 0.6203, "step": 17530}
+{"epoch": 0.62, "learning_rate": 0.0002379606121722624, "loss": 0.6193, "step": 17540}
+{"epoch": 0.62, "learning_rate": 0.00023792502076165617, "loss": 0.6647, "step": 17550}
+{"epoch": 0.62, "learning_rate": 0.00023788942935104994, "loss": 0.6078, "step": 17560}
+{"epoch": 0.62, "learning_rate": 0.00023785383794044368, "loss": 0.6986, "step": 17570}
+{"epoch": 0.62, "learning_rate": 0.00023781824652983744, "loss": 0.7036, "step": 17580}
+{"epoch": 0.63, "learning_rate": 0.0002377826551192312, "loss": 0.6974, "step": 17590}
+{"epoch": 0.63, "learning_rate": 0.00023774706370862495, "loss": 0.5049, "step": 17600}
+{"epoch": 0.63, "learning_rate": 0.00023771147229801872, "loss": 0.7322, "step": 17610}
+{"epoch": 0.63, "learning_rate": 0.00023767588088741248, "loss": 0.6772, "step": 17620}
+{"epoch": 0.63, "learning_rate": 0.00023764028947680625, "loss": 0.6642, "step": 17630}
+{"epoch": 0.63, "learning_rate": 0.0002376046980662, "loss": 0.6999, "step": 17640}
+{"epoch": 0.63, "learning_rate": 0.00023756910665559378, "loss": 0.6289, "step": 17650}
+{"epoch": 0.63, "learning_rate": 0.00023753351524498752, "loss": 0.678, "step": 17660}
+{"epoch": 0.63, "learning_rate": 0.0002374979238343813, "loss": 0.5548, "step": 17670}
+{"epoch": 0.63, "learning_rate": 0.00023746233242377503, "loss": 0.7317, "step": 17680}
+{"epoch": 0.63, "learning_rate": 0.00023742674101316882, "loss": 0.6638, "step": 17690}
+{"epoch": 0.63, "learning_rate": 0.00023739114960256256, "loss": 0.6814, "step": 17700}
+{"epoch": 0.63, "learning_rate": 0.0002373555581919563, "loss": 0.6299, "step": 17710}
+{"epoch": 0.63, "learning_rate": 0.0002373199667813501, "loss": 0.785, "step": 17720}
+{"epoch": 0.63, "learning_rate": 0.00023728437537074383, "loss": 0.6203, "step": 17730}
+{"epoch": 0.63, "learning_rate": 0.0002372487839601376, "loss": 0.6013, "step": 17740}
+{"epoch": 0.63, "learning_rate": 0.00023721319254953137, "loss": 0.7272, "step": 17750}
+{"epoch": 0.63, "learning_rate": 0.00023717760113892513, "loss": 0.6356, "step": 17760}
+{"epoch": 0.63, "learning_rate": 0.00023714200972831887, "loss": 0.6399, "step": 17770}
+{"epoch": 0.63, "learning_rate": 0.00023710641831771267, "loss": 0.7376, "step": 17780}
+{"epoch": 0.63, "learning_rate": 0.0002370708269071064, "loss": 0.7339, "step": 17790}
+{"epoch": 0.63, "learning_rate": 0.00023703523549650015, "loss": 0.6343, "step": 17800}
+{"epoch": 0.63, "learning_rate": 0.0002369996440858939, "loss": 0.7444, "step": 17810}
+{"epoch": 0.63, "learning_rate": 0.00023696405267528768, "loss": 0.7102, "step": 17820}
+{"epoch": 0.63, "learning_rate": 0.00023692846126468144, "loss": 0.6182, "step": 17830}
+{"epoch": 0.63, "learning_rate": 0.00023689286985407518, "loss": 0.6601, "step": 17840}
+{"epoch": 0.63, "learning_rate": 0.00023685727844346898, "loss": 0.6617, "step": 17850}
+{"epoch": 0.63, "learning_rate": 0.00023682168703286272, "loss": 0.7277, "step": 17860}
+{"epoch": 0.64, "learning_rate": 0.00023678609562225646, "loss": 0.6839, "step": 17870}
+{"epoch": 0.64, "learning_rate": 0.00023675050421165025, "loss": 0.655, "step": 17880}
+{"epoch": 0.64, "learning_rate": 0.000236714912801044, "loss": 0.6719, "step": 17890}
+{"epoch": 0.64, "learning_rate": 0.00023667932139043776, "loss": 0.6424, "step": 17900}
+{"epoch": 0.64, "learning_rate": 0.0002366437299798315, "loss": 0.8434, "step": 17910}
+{"epoch": 0.64, "learning_rate": 0.0002366081385692253, "loss": 0.5587, "step": 17920}
+{"epoch": 0.64, "learning_rate": 0.00023657254715861903, "loss": 0.685, "step": 17930}
+{"epoch": 0.64, "learning_rate": 0.00023653695574801277, "loss": 0.7029, "step": 17940}
+{"epoch": 0.64, "learning_rate": 0.00023650136433740656, "loss": 0.6163, "step": 17950}
+{"epoch": 0.64, "learning_rate": 0.0002364657729268003, "loss": 0.6539, "step": 17960}
+{"epoch": 0.64, "learning_rate": 0.00023643018151619407, "loss": 0.5889, "step": 17970}
+{"epoch": 0.64, "learning_rate": 0.00023639459010558783, "loss": 0.804, "step": 17980}
+{"epoch": 0.64, "learning_rate": 0.0002363589986949816, "loss": 0.7608, "step": 17990}
+{"epoch": 0.64, "learning_rate": 0.00023632340728437534, "loss": 0.6514, "step": 18000}
+{"epoch": 0.64, "learning_rate": 0.00023628781587376913, "loss": 0.6232, "step": 18010}
+{"epoch": 0.64, "learning_rate": 0.00023625222446316287, "loss": 0.5585, "step": 18020}
+{"epoch": 0.64, "learning_rate": 0.0002362166330525566, "loss": 0.649, "step": 18030}
+{"epoch": 0.64, "learning_rate": 0.00023618104164195038, "loss": 0.6381, "step": 18040}
+{"epoch": 0.64, "learning_rate": 0.00023614545023134415, "loss": 0.698, "step": 18050}
+{"epoch": 0.64, "learning_rate": 0.0002361098588207379, "loss": 0.7034, "step": 18060}
+{"epoch": 0.64, "learning_rate": 0.00023607426741013165, "loss": 0.6213, "step": 18070}
+{"epoch": 0.64, "learning_rate": 0.00023603867599952545, "loss": 0.6623, "step": 18080}
+{"epoch": 0.64, "learning_rate": 0.00023600308458891919, "loss": 0.6636, "step": 18090}
+{"epoch": 0.64, "learning_rate": 0.00023596749317831293, "loss": 0.6383, "step": 18100}
+{"epoch": 0.64, "learning_rate": 0.00023593190176770672, "loss": 0.6441, "step": 18110}
+{"epoch": 0.64, "learning_rate": 0.00023589631035710046, "loss": 0.6686, "step": 18120}
+{"epoch": 0.64, "learning_rate": 0.00023586071894649422, "loss": 0.7046, "step": 18130}
+{"epoch": 0.64, "learning_rate": 0.00023582512753588796, "loss": 0.7612, "step": 18140}
+{"epoch": 0.65, "learning_rate": 0.00023578953612528176, "loss": 0.5519, "step": 18150}
+{"epoch": 0.65, "learning_rate": 0.0002357539447146755, "loss": 0.6051, "step": 18160}
+{"epoch": 0.65, "learning_rate": 0.00023571835330406926, "loss": 0.6077, "step": 18170}
+{"epoch": 0.65, "learning_rate": 0.00023568276189346303, "loss": 0.6924, "step": 18180}
+{"epoch": 0.65, "learning_rate": 0.0002356471704828568, "loss": 0.755, "step": 18190}
+{"epoch": 0.65, "learning_rate": 0.00023561157907225054, "loss": 0.6421, "step": 18200}
+{"epoch": 0.65, "learning_rate": 0.0002355759876616443, "loss": 0.551, "step": 18210}
+{"epoch": 0.65, "learning_rate": 0.00023554039625103807, "loss": 0.6816, "step": 18220}
+{"epoch": 0.65, "learning_rate": 0.0002355048048404318, "loss": 0.6998, "step": 18230}
+{"epoch": 0.65, "learning_rate": 0.00023546921342982558, "loss": 0.6218, "step": 18240}
+{"epoch": 0.65, "learning_rate": 0.00023543362201921934, "loss": 0.6317, "step": 18250}
+{"epoch": 0.65, "learning_rate": 0.0002353980306086131, "loss": 0.6521, "step": 18260}
+{"epoch": 0.65, "learning_rate": 0.00023536243919800685, "loss": 0.7457, "step": 18270}
+{"epoch": 0.65, "learning_rate": 0.00023532684778740064, "loss": 0.5839, "step": 18280}
+{"epoch": 0.65, "learning_rate": 0.00023529125637679438, "loss": 0.6309, "step": 18290}
+{"epoch": 0.65, "learning_rate": 0.00023525566496618812, "loss": 0.6057, "step": 18300}
+{"epoch": 0.65, "learning_rate": 0.00023522007355558191, "loss": 0.5953, "step": 18310}
+{"epoch": 0.65, "learning_rate": 0.00023518448214497565, "loss": 0.6366, "step": 18320}
+{"epoch": 0.65, "learning_rate": 0.00023514889073436942, "loss": 0.6361, "step": 18330}
+{"epoch": 0.65, "learning_rate": 0.0002351132993237632, "loss": 0.6183, "step": 18340}
+{"epoch": 0.65, "learning_rate": 0.00023507770791315695, "loss": 0.6767, "step": 18350}
+{"epoch": 0.65, "learning_rate": 0.0002350421165025507, "loss": 0.5789, "step": 18360}
+{"epoch": 0.65, "learning_rate": 0.00023500652509194443, "loss": 0.6328, "step": 18370}
+{"epoch": 0.65, "learning_rate": 0.00023497093368133823, "loss": 0.7435, "step": 18380}
+{"epoch": 0.65, "learning_rate": 0.00023493534227073197, "loss": 0.709, "step": 18390}
+{"epoch": 0.65, "learning_rate": 0.00023489975086012573, "loss": 0.7099, "step": 18400}
+{"epoch": 0.65, "learning_rate": 0.0002348641594495195, "loss": 0.6409, "step": 18410}
+{"epoch": 0.65, "learning_rate": 0.00023482856803891327, "loss": 0.6494, "step": 18420}
+{"epoch": 0.66, "learning_rate": 0.000234792976628307, "loss": 0.5604, "step": 18430}
+{"epoch": 0.66, "learning_rate": 0.0002347573852177008, "loss": 0.6061, "step": 18440}
+{"epoch": 0.66, "learning_rate": 0.00023472179380709454, "loss": 0.6116, "step": 18450}
+{"epoch": 0.66, "learning_rate": 0.00023468620239648828, "loss": 0.6071, "step": 18460}
+{"epoch": 0.66, "learning_rate": 0.00023465061098588204, "loss": 0.6972, "step": 18470}
+{"epoch": 0.66, "learning_rate": 0.0002346150195752758, "loss": 0.6298, "step": 18480}
+{"epoch": 0.66, "learning_rate": 0.00023457942816466958, "loss": 0.7004, "step": 18490}
+{"epoch": 0.66, "learning_rate": 0.00023454383675406332, "loss": 0.6554, "step": 18500}
+{"loss": 0.6561, "learning_rate": 0.0002345082453434571, "epoch": 0.66, "step": 18510}
+{"loss": 0.712, "learning_rate": 0.00023447265393285085, "epoch": 0.66, "step": 18520}
+{"loss": 0.7452, "learning_rate": 0.0002344370625222446, "epoch": 0.66, "step": 18530}
+{"loss": 0.6506, "learning_rate": 0.00023440147111163838, "epoch": 0.66, "step": 18540}
+{"loss": 0.6961, "learning_rate": 0.00023436587970103212, "epoch": 0.66, "step": 18550}
+{"loss": 0.6945, "learning_rate": 0.0002343302882904259, "epoch": 0.66, "step": 18560}
+{"loss": 0.6521, "learning_rate": 0.00023429469687981966, "epoch": 0.66, "step": 18570}
+{"loss": 0.6465, "learning_rate": 0.00023425910546921342, "epoch": 0.66, "step": 18580}
+{"loss": 0.5555, "learning_rate": 0.00023422351405860716, "epoch": 0.66, "step": 18590}
+{"loss": 0.6359, "learning_rate": 0.0002341879226480009, "epoch": 0.66, "step": 18600}
+{"loss": 0.5451, "learning_rate": 0.0002341523312373947, "epoch": 0.66, "step": 18610}
+{"loss": 0.6433, "learning_rate": 0.00023411673982678843, "epoch": 0.66, "step": 18620}
+{"loss": 0.6054, "learning_rate": 0.0002340811484161822, "epoch": 0.66, "step": 18630}
+{"loss": 0.6511, "learning_rate": 0.00023404555700557597, "epoch": 0.66, "step": 18640}
+{"loss": 0.7823, "learning_rate": 0.00023400996559496973, "epoch": 0.66, "step": 18650}
+{"loss": 0.6425, "learning_rate": 0.00023397437418436347, "epoch": 0.66, "step": 18660}
+{"loss": 0.5399, "learning_rate": 0.00023393878277375727, "epoch": 0.66, "step": 18670}
+{"loss": 0.5563, "learning_rate": 0.000233903191363151, "epoch": 0.66, "step": 18680}
+{"loss": 0.6647, "learning_rate": 0.00023386759995254477, "epoch": 0.66, "step": 18690}
+{"loss": 0.6004, "learning_rate": 0.0002338320085419385, "epoch": 0.66, "step": 18700}
+{"loss": 0.6395, "learning_rate": 0.00023379641713133228, "epoch": 0.67, "step": 18710}
+{"loss": 0.6454, "learning_rate": 0.00023376082572072605, "epoch": 0.67, "step": 18720}
+{"loss": 0.5879, "learning_rate": 0.00023372523431011978, "epoch": 0.67, "step": 18730}
+{"loss": 0.6499, "learning_rate": 0.00023368964289951358, "epoch": 0.67, "step": 18740}
+{"loss": 0.6918, "learning_rate": 0.00023365405148890732, "epoch": 0.67, "step": 18750}
+{"loss": 0.639, "learning_rate": 0.00023361846007830108, "epoch": 0.67, "step": 18760}
+{"loss": 0.7304, "learning_rate": 0.00023358286866769485, "epoch": 0.67, "step": 18770}
+{"loss": 0.6493, "learning_rate": 0.00023354727725708862, "epoch": 0.67, "step": 18780}
+{"loss": 0.5601, "learning_rate": 0.00023351168584648236, "epoch": 0.67, "step": 18790}
+{"loss": 0.5798, "learning_rate": 0.00023347609443587615, "epoch": 0.67, "step": 18800}
+{"loss": 0.6412, "learning_rate": 0.0002334405030252699, "epoch": 0.67, "step": 18810}
+{"loss": 0.6057, "learning_rate": 0.00023340491161466363, "epoch": 0.67, "step": 18820}
+{"loss": 0.5315, "learning_rate": 0.0002333693202040574, "epoch": 0.67, "step": 18830}
+{"loss": 0.6499, "learning_rate": 0.00023333372879345116, "epoch": 0.67, "step": 18840}
+{"loss": 0.6574, "learning_rate": 0.00023329813738284493, "epoch": 0.67, "step": 18850}
+{"loss": 0.7359, "learning_rate": 0.00023326254597223867, "epoch": 0.67, "step": 18860}
+{"loss": 0.6882, "learning_rate": 0.00023322695456163246, "epoch": 0.67, "step": 18870}
+{"loss": 0.6748, "learning_rate": 0.0002331913631510262, "epoch": 0.67, "step": 18880}
+{"loss": 0.6029, "learning_rate": 0.00023315577174041994, "epoch": 0.67, "step": 18890}
+{"loss": 0.6673, "learning_rate": 0.00023312018032981373, "epoch": 0.67, "step": 18900}
+{"loss": 0.6692, "learning_rate": 0.00023308458891920747, "epoch": 0.67, "step": 18910}
+{"loss": 0.7255, "learning_rate": 0.00023304899750860124, "epoch": 0.67, "step": 18920}
+{"loss": 0.6505, "learning_rate": 0.00023301340609799498, "epoch": 0.67, "step": 18930}
+{"loss": 0.5785, "learning_rate": 0.00023297781468738877, "epoch": 0.67, "step": 18940}
+{"loss": 0.6408, "learning_rate": 0.0002329422232767825, "epoch": 0.67, "step": 18950}
+{"loss": 0.6524, "learning_rate": 0.00023290663186617625, "epoch": 0.67, "step": 18960}
+{"loss": 0.6736, "learning_rate": 0.00023287104045557005, "epoch": 0.67, "step": 18970}
+{"loss": 0.6631, "learning_rate": 0.00023283544904496379, "epoch": 0.67, "step": 18980}
+{"loss": 0.6336, "learning_rate": 0.00023279985763435755, "epoch": 0.68, "step": 18990}
+{"loss": 0.6114, "learning_rate": 0.00023276426622375132, "epoch": 0.68, "step": 19000}
+{"loss": 0.715, "learning_rate": 0.00023272867481314509, "epoch": 0.68, "step": 19010}
+{"loss": 0.6618, "learning_rate": 0.00023269308340253883, "epoch": 0.68, "step": 19020}
+{"loss": 0.5972, "learning_rate": 0.00023265749199193262, "epoch": 0.68, "step": 19030}
+{"loss": 0.6777, "learning_rate": 0.00023262190058132636, "epoch": 0.68, "step": 19040}
+{"loss": 0.6464, "learning_rate": 0.0002325863091707201, "epoch": 0.68, "step": 19050}
+{"loss": 0.685, "learning_rate": 0.00023255071776011386, "epoch": 0.68, "step": 19060}
+{"loss": 0.6758, "learning_rate": 0.00023251512634950763, "epoch": 0.68, "step": 19070}
+{"loss": 0.7147, "learning_rate": 0.0002324795349389014, "epoch": 0.68, "step": 19080}
+{"loss": 0.6866, "learning_rate": 0.00023244394352829514, "epoch": 0.68, "step": 19090}
+{"loss": 0.679, "learning_rate": 0.00023240835211768893, "epoch": 0.68, "step": 19100}
+{"loss": 0.5401, "learning_rate": 0.00023237276070708267, "epoch": 0.68, "step": 19110}
+{"loss": 0.7182, "learning_rate": 0.0002323371692964764, "epoch": 0.68, "step": 19120}
+{"loss": 0.6568, "learning_rate": 0.0002323015778858702, "epoch": 0.68, "step": 19130}
+{"loss": 0.6682, "learning_rate": 0.00023226598647526394, "epoch": 0.68, "step": 19140}
+{"loss": 0.5967, "learning_rate": 0.0002322303950646577, "epoch": 0.68, "step": 19150}
+{"loss": 0.6372, "learning_rate": 0.00023219480365405145, "epoch": 0.68, "step": 19160}
+{"loss": 0.6562, "learning_rate": 0.00023215921224344524, "epoch": 0.68, "step": 19170}
+{"loss": 0.7334, "learning_rate": 0.00023212362083283898, "epoch": 0.68, "step": 19180}
+{"loss": 0.6626, "learning_rate": 0.00023208802942223275, "epoch": 0.68, "step": 19190}
+{"loss": 0.6613, "learning_rate": 0.00023205243801162651, "epoch": 0.68, "step": 19200}
+{"loss": 0.709, "learning_rate": 0.00023201684660102025, "epoch": 0.68, "step": 19210}
+{"loss": 0.6017, "learning_rate": 0.00023198125519041402, "epoch": 0.68, "step": 19220}
+{"loss": 0.6983, "learning_rate": 0.0002319456637798078, "epoch": 0.68, "step": 19230}
+{"loss": 0.6919, "learning_rate": 0.00023191007236920155, "epoch": 0.68, "step": 19240}
+{"loss": 0.6744, "learning_rate": 0.0002318744809585953, "epoch": 0.68, "step": 19250}
+{"loss": 0.6933, "learning_rate": 0.00023183888954798906, "epoch": 0.68, "step": 19260}
+{"loss": 0.6186, "learning_rate": 0.00023180329813738283, "epoch": 0.69, "step": 19270}
+{"loss": 0.6386, "learning_rate": 0.0002317677067267766, "epoch": 0.69, "step": 19280}
+{"loss": 0.6283, "learning_rate": 0.00023173211531617033, "epoch": 0.69, "step": 19290}
+{"loss": 0.5855, "learning_rate": 0.00023169652390556413, "epoch": 0.69, "step": 19300}
+{"loss": 0.6169, "learning_rate": 0.00023166093249495787, "epoch": 0.69, "step": 19310}
+{"loss": 0.6587, "learning_rate": 0.0002316253410843516, "epoch": 0.69, "step": 19320}
+{"loss": 0.6463, "learning_rate": 0.0002315897496737454, "epoch": 0.69, "step": 19330}
+{"loss": 0.6328, "learning_rate": 0.00023155415826313914, "epoch": 0.69, "step": 19340}
+{"loss": 0.6238, "learning_rate": 0.0002315185668525329, "epoch": 0.69, "step": 19350}
+{"loss": 0.6241, "learning_rate": 0.00023148297544192667, "epoch": 0.69, "step": 19360}
+{"loss": 0.6635, "learning_rate": 0.00023144738403132044, "epoch": 0.69, "step": 19370}
+{"loss": 0.5463, "learning_rate": 0.00023141179262071418, "epoch": 0.69, "step": 19380}
+{"loss": 0.8037, "learning_rate": 0.00023137620121010792, "epoch": 0.69, "step": 19390}
+{"loss": 0.6431, "learning_rate": 0.0002313406097995017, "epoch": 0.69, "step": 19400}
+{"loss": 0.6366, "learning_rate": 0.00023130501838889545, "epoch": 0.69, "step": 19410}
+{"loss": 0.602, "learning_rate": 0.00023126942697828922, "epoch": 0.69, "step": 19420}
+{"loss": 0.6757, "learning_rate": 0.00023123383556768298, "epoch": 0.69, "step": 19430}
+{"loss": 0.7078, "learning_rate": 0.00023119824415707675, "epoch": 0.69, "step": 19440}
+{"loss": 0.7049, "learning_rate": 0.0002311626527464705, "epoch": 0.69, "step": 19450}
+{"loss": 0.6411, "learning_rate": 0.00023112706133586428, "epoch": 0.69, "step": 19460}
+{"loss": 0.6704, "learning_rate": 0.00023109146992525802, "epoch": 0.69, "step": 19470}
+{"loss": 0.6019, "learning_rate": 0.00023105587851465176, "epoch": 0.69, "step": 19480}
+{"loss": 0.644, "learning_rate": 0.00023102028710404553, "epoch": 0.69, "step": 19490}
+{"loss": 0.6781, "learning_rate": 0.0002309846956934393, "epoch": 0.69, "step": 19500}
+{"loss": 0.6416, "learning_rate": 0.00023094910428283306, "epoch": 0.69, "step": 19510}
+{"loss": 0.7016, "learning_rate": 0.0002309135128722268, "epoch": 0.69, "step": 19520}
+{"loss": 0.6446, "learning_rate": 0.0002308779214616206, "epoch": 0.69, "step": 19530}
+{"loss": 0.5951, "learning_rate": 0.00023084233005101433, "epoch": 0.69, "step": 19540}
+{"loss": 0.6995, "learning_rate": 0.00023080673864040807, "epoch": 0.69, "step": 19550}
+{"loss": 0.7051, "learning_rate": 0.00023077114722980187, "epoch": 0.7, "step": 19560}
+{"loss": 0.5402, "learning_rate": 0.0002307355558191956, "epoch": 0.7, "step": 19570}
+{"loss": 0.691, "learning_rate": 0.00023069996440858937, "epoch": 0.7, "step": 19580}
+{"loss": 0.6954, "learning_rate": 0.00023066793213904376, "epoch": 0.7, "step": 19590}
+{"loss": 0.6712, "learning_rate": 0.0002306323407284375, "epoch": 0.7, "step": 19600}
+{"loss": 0.7072, "learning_rate": 0.0002305967493178313, "epoch": 0.7, "step": 19610}
+{"loss": 0.634, "learning_rate": 0.00023056115790722503, "epoch": 0.7, "step": 19620}
+{"loss": 0.6561, "learning_rate": 0.00023052556649661877, "epoch": 0.7, "step": 19630}
+{"loss": 0.6982, "learning_rate": 0.00023048997508601257, "epoch": 0.7, "step": 19640}
+{"loss": 0.6414, "learning_rate": 0.0002304543836754063, "epoch": 0.7, "step": 19650}
+{"loss": 0.6651, "learning_rate": 0.00023041879226480007, "epoch": 0.7, "step": 19660}
+{"loss": 0.6791, "learning_rate": 0.00023038320085419384, "epoch": 0.7, "step": 19670}
+{"loss": 0.7104, "learning_rate": 0.0002303476094435876, "epoch": 0.7, "step": 19680}
+{"loss": 0.6449, "learning_rate": 0.00023031201803298134, "epoch": 0.7, "step": 19690}
+{"loss": 0.6245, "learning_rate": 0.0002302764266223751, "epoch": 0.7, "step": 19700}
+{"loss": 0.6934, "learning_rate": 0.00023024083521176888, "epoch": 0.7, "step": 19710}
+{"loss": 0.6353, "learning_rate": 0.00023020524380116264, "epoch": 0.7, "step": 19720}
+{"loss": 0.6019, "learning_rate": 0.00023016965239055638, "epoch": 0.7, "step": 19730}
+{"loss": 0.7251, "learning_rate": 0.00023013406097995015, "epoch": 0.7, "step": 19740}
+{"loss": 0.5592, "learning_rate": 0.00023009846956934392, "epoch": 0.7, "step": 19750}
+{"loss": 0.6104, "learning_rate": 0.00023006287815873766, "epoch": 0.7, "step": 19760}
+{"loss": 0.6394, "learning_rate": 0.00023002728674813145, "epoch": 0.7, "step": 19770}
+{"loss": 0.6707, "learning_rate": 0.0002299916953375252, "epoch": 0.7, "step": 19780}
+{"loss": 0.6402, "learning_rate": 0.00022995610392691896, "epoch": 0.7, "step": 19790}
+{"loss": 0.782, "learning_rate": 0.0002299205125163127, "epoch": 0.7, "step": 19800}
+{"loss": 0.6372, "learning_rate": 0.0002298849211057065, "epoch": 0.7, "step": 19810}
+{"loss": 0.7639, "learning_rate": 0.00022984932969510023, "epoch": 0.7, "step": 19820}
+{"loss": 0.6159, "learning_rate": 0.00022981373828449397, "epoch": 0.7, "step": 19830}
+{"loss": 0.6632, "learning_rate": 0.00022977814687388776, "epoch": 0.71, "step": 19840}
+{"loss": 0.7924, "learning_rate": 0.0002297425554632815, "epoch": 0.71, "step": 19850}
+{"loss": 0.6808, "learning_rate": 0.00022970696405267527, "epoch": 0.71, "step": 19860}
+{"loss": 0.6661, "learning_rate": 0.00022967137264206903, "epoch": 0.71, "step": 19870}
+{"loss": 0.7144, "learning_rate": 0.0002296357812314628, "epoch": 0.71, "step": 19880}
+{"loss": 0.6898, "learning_rate": 0.00022960018982085654, "epoch": 0.71, "step": 19890}
+{"loss": 0.681, "learning_rate": 0.00022956459841025033, "epoch": 0.71, "step": 19900}
+{"loss": 0.7596, "learning_rate": 0.00022952900699964407, "epoch": 0.71, "step": 19910}
+{"loss": 0.616, "learning_rate": 0.0002294934155890378, "epoch": 0.71, "step": 19920}
+{"loss": 0.6178, "learning_rate": 0.00022945782417843158, "epoch": 0.71, "step": 19930}
+{"loss": 0.6443, "learning_rate": 0.00022942223276782535, "epoch": 0.71, "step": 19940}
+{"loss": 0.5472, "learning_rate": 0.0002293866413572191, "epoch": 0.71, "step": 19950}
+{"loss": 0.6182, "learning_rate": 0.00022935104994661285, "epoch": 0.71, "step": 19960}
+{"loss": 0.7005, "learning_rate": 0.00022931901767706724, "epoch": 0.71, "step": 19970}
+{"loss": 0.642, "learning_rate": 0.00022928342626646103, "epoch": 0.71, "step": 19980}
+{"loss": 0.6855, "learning_rate": 0.00022924783485585477, "epoch": 0.71, "step": 19990}
+{"loss": 0.6917, "learning_rate": 0.0002292122434452485, "epoch": 0.71, "step": 20000}
+{"loss": 0.7462, "learning_rate": 0.00022917665203464228, "epoch": 0.71, "step": 20010}
+{"loss": 0.5595, "learning_rate": 0.00022914106062403604, "epoch": 0.71, "step": 20020}
+{"loss": 0.6667, "learning_rate": 0.0002291054692134298, "epoch": 0.71, "step": 20030}
+{"loss": 0.6866, "learning_rate": 0.00022906987780282355, "epoch": 0.71, "step": 20040}
+{"loss": 0.6738, "learning_rate": 0.00022903428639221734, "epoch": 0.71, "step": 20050}
+{"loss": 0.7155, "learning_rate": 0.00022899869498161108, "epoch": 0.71, "step": 20060}
+{"loss": 0.675, "learning_rate": 0.00022896310357100482, "epoch": 0.71, "step": 20070}
+{"loss": 0.57, "learning_rate": 0.00022892751216039862, "epoch": 0.71, "step": 20080}
+{"loss": 0.6655, "learning_rate": 0.00022889192074979236, "epoch": 0.71, "step": 20090}
+{"loss": 0.6502, "learning_rate": 0.00022885632933918612, "epoch": 0.71, "step": 20100}
+{"loss": 0.722, "learning_rate": 0.00022882073792857986, "epoch": 0.71, "step": 20110}
+{"loss": 0.6463, "learning_rate": 0.00022878514651797366, "epoch": 0.72, "step": 20120}
+{"loss": 0.7275, "learning_rate": 0.0002287495551073674, "epoch": 0.72, "step": 20130}
+{"loss": 0.6045, "learning_rate": 0.00022871396369676116, "epoch": 0.72, "step": 20140}
+{"loss": 0.6648, "learning_rate": 0.00022867837228615493, "epoch": 0.72, "step": 20150}
+{"loss": 0.6522, "learning_rate": 0.00022864278087554867, "epoch": 0.72, "step": 20160}
+{"loss": 0.6463, "learning_rate": 0.00022860718946494243, "epoch": 0.72, "step": 20170}
+{"loss": 0.6922, "learning_rate": 0.0002285715980543362, "epoch": 0.72, "step": 20180}
+{"loss": 0.8122, "learning_rate": 0.00022853600664372997, "epoch": 0.72, "step": 20190}
+{"loss": 0.626, "learning_rate": 0.0002285004152331237, "epoch": 0.72, "step": 20200}
+{"loss": 0.6516, "learning_rate": 0.0002284648238225175, "epoch": 0.72, "step": 20210}
+{"loss": 0.6461, "learning_rate": 0.00022842923241191124, "epoch": 0.72, "step": 20220}
+{"loss": 0.6284, "learning_rate": 0.000228393641001305, "epoch": 0.72, "step": 20230}
+{"loss": 0.6514, "learning_rate": 0.00022835804959069875, "epoch": 0.72, "step": 20240}
+{"loss": 0.6398, "learning_rate": 0.00022832245818009254, "epoch": 0.72, "step": 20250}
+{"loss": 0.8107, "learning_rate": 0.00022828686676948628, "epoch": 0.72, "step": 20260}
+{"loss": 0.656, "learning_rate": 0.00022825127535888002, "epoch": 0.72, "step": 20270}
+{"loss": 0.6242, "learning_rate": 0.0002282156839482738, "epoch": 0.72, "step": 20280}
+{"loss": 0.5611, "learning_rate": 0.00022818009253766755, "epoch": 0.72, "step": 20290}
+{"loss": 0.6623, "learning_rate": 0.00022814450112706132, "epoch": 0.72, "step": 20300}
+{"loss": 0.7116, "learning_rate": 0.00022810890971645509, "epoch": 0.72, "step": 20310}
+{"loss": 0.7271, "learning_rate": 0.00022807331830584885, "epoch": 0.72, "step": 20320}
+{"loss": 0.6944, "learning_rate": 0.0002280377268952426, "epoch": 0.72, "step": 20330}
+{"loss": 0.6581, "learning_rate": 0.00022800213548463633, "epoch": 0.72, "step": 20340}
+{"loss": 0.5974, "learning_rate": 0.00022796654407403012, "epoch": 0.72, "step": 20350}
+{"loss": 0.7046, "learning_rate": 0.00022793095266342386, "epoch": 0.72, "step": 20360}
+{"loss": 0.6562, "learning_rate": 0.00022789536125281763, "epoch": 0.72, "step": 20370}
+{"loss": 0.6347, "learning_rate": 0.0002278597698422114, "epoch": 0.72, "step": 20380}
+{"loss": 0.7294, "learning_rate": 0.00022782417843160516, "epoch": 0.72, "step": 20390}
+{"loss": 0.659, "learning_rate": 0.0002277885870209989, "epoch": 0.73, "step": 20400}
+{"loss": 0.6288, "learning_rate": 0.0002277529956103927, "epoch": 0.73, "step": 20410}
+{"loss": 0.6708, "learning_rate": 0.00022771740419978644, "epoch": 0.73, "step": 20420}
+{"loss": 0.6003, "learning_rate": 0.00022768181278918018, "epoch": 0.73, "step": 20430}
+{"loss": 0.5782, "learning_rate": 0.00022764622137857397, "epoch": 0.73, "step": 20440}
+{"loss": 0.6199, "learning_rate": 0.0002276106299679677, "epoch": 0.73, "step": 20450}
+{"loss": 0.6037, "learning_rate": 0.00022757503855736148, "epoch": 0.73, "step": 20460}
+{"loss": 0.6377, "learning_rate": 0.00022753944714675521, "epoch": 0.73, "step": 20470}
+{"loss": 0.6462, "learning_rate": 0.000227503855736149, "epoch": 0.73, "step": 20480}
+{"loss": 0.6154, "learning_rate": 0.00022746826432554275, "epoch": 0.73, "step": 20490}
+{"loss": 0.6506, "learning_rate": 0.0002274326729149365, "epoch": 0.73, "step": 20500}
+{"loss": 0.6676, "learning_rate": 0.00022739708150433028, "epoch": 0.73, "step": 20510}
+{"loss": 0.7379, "learning_rate": 0.00022736149009372402, "epoch": 0.73, "step": 20520}
+{"loss": 0.7759, "learning_rate": 0.0002273258986831178, "epoch": 0.73, "step": 20530}
+{"loss": 0.7138, "learning_rate": 0.00022729030727251155, "epoch": 0.73, "step": 20540}
+{"loss": 0.6242, "learning_rate": 0.00022725471586190532, "epoch": 0.73, "step": 20550}
+{"loss": 0.6462, "learning_rate": 0.00022721912445129906, "epoch": 0.73, "step": 20560}
+{"loss": 0.6444, "learning_rate": 0.0002271835330406928, "epoch": 0.73, "step": 20570}
+{"loss": 0.6105, "learning_rate": 0.0002271479416300866, "epoch": 0.73, "step": 20580}
+{"loss": 0.6967, "learning_rate": 0.00022711235021948033, "epoch": 0.73, "step": 20590}
+{"loss": 0.7439, "learning_rate": 0.0002270767588088741, "epoch": 0.73, "step": 20600}
+{"loss": 0.6773, "learning_rate": 0.00022704116739826787, "epoch": 0.73, "step": 20610}
+{"loss": 0.6473, "learning_rate": 0.00022700557598766163, "epoch": 0.73, "step": 20620}
+{"loss": 0.6519, "learning_rate": 0.00022696998457705537, "epoch": 0.73, "step": 20630}
+{"loss": 0.6662, "learning_rate": 0.00022693439316644916, "epoch": 0.73, "step": 20640}
+{"loss": 0.6533, "learning_rate": 0.0002268988017558429, "epoch": 0.73, "step": 20650}
+{"loss": 0.6194, "learning_rate": 0.00022686321034523664, "epoch": 0.73, "step": 20660}
+{"loss": 0.6648, "learning_rate": 0.0002268276189346304, "epoch": 0.73, "step": 20670}
+{"loss": 0.6999, "learning_rate": 0.00022679202752402418, "epoch": 0.74, "step": 20680}
+{"loss": 0.7355, "learning_rate": 0.00022675643611341794, "epoch": 0.74, "step": 20690}
+{"loss": 0.8183, "learning_rate": 0.00022672084470281168, "epoch": 0.74, "step": 20700}
+{"loss": 0.6669, "learning_rate": 0.00022668525329220548, "epoch": 0.74, "step": 20710}
+{"loss": 0.6699, "learning_rate": 0.00022664966188159922, "epoch": 0.74, "step": 20720}
+{"loss": 0.6213, "learning_rate": 0.00022661407047099298, "epoch": 0.74, "step": 20730}
+{"loss": 0.712, "learning_rate": 0.00022657847906038675, "epoch": 0.74, "step": 20740}
+{"loss": 0.6427, "learning_rate": 0.00022654288764978052, "epoch": 0.74, "step": 20750}
+{"loss": 0.7187, "learning_rate": 0.00022650729623917426, "epoch": 0.74, "step": 20760}
+{"loss": 0.7066, "learning_rate": 0.00022647170482856802, "epoch": 0.74, "step": 20770}
+{"loss": 0.7484, "learning_rate": 0.0002264361134179618, "epoch": 0.74, "step": 20780}
+{"loss": 0.6576, "learning_rate": 0.00022640052200735553, "epoch": 0.74, "step": 20790}
+{"loss": 0.6458, "learning_rate": 0.0002263649305967493, "epoch": 0.74, "step": 20800}
+{"loss": 0.6914, "learning_rate": 0.00022632933918614306, "epoch": 0.74, "step": 20810}
+{"loss": 0.6687, "learning_rate": 0.00022629374777553683, "epoch": 0.74, "step": 20820}
+{"loss": 0.7222, "learning_rate": 0.00022625815636493057, "epoch": 0.74, "step": 20830}
+{"loss": 0.7683, "learning_rate": 0.00022622256495432436, "epoch": 0.74, "step": 20840}
+{"loss": 0.64, "learning_rate": 0.0002261869735437181, "epoch": 0.74, "step": 20850}
+{"loss": 0.6753, "learning_rate": 0.00022615138213311184, "epoch": 0.74, "step": 20860}
+{"loss": 0.6746, "learning_rate": 0.00022611579072250563, "epoch": 0.74, "step": 20870}
+{"loss": 0.677, "learning_rate": 0.00022608019931189937, "epoch": 0.74, "step": 20880}
+{"loss": 0.6285, "learning_rate": 0.00022604460790129314, "epoch": 0.74, "step": 20890}
+{"loss": 0.6377, "learning_rate": 0.00022600901649068688, "epoch": 0.74, "step": 20900}
+{"loss": 0.7048, "learning_rate": 0.00022597342508008067, "epoch": 0.74, "step": 20910}
+{"loss": 0.7889, "learning_rate": 0.0002259378336694744, "epoch": 0.74, "step": 20920}
+{"loss": 0.6158, "learning_rate": 0.00022590224225886815, "epoch": 0.74, "step": 20930}
+{"loss": 0.6217, "learning_rate": 0.00022586665084826194, "epoch": 0.74, "step": 20940}
+{"loss": 0.6617, "learning_rate": 0.00022583105943765568, "epoch": 0.74, "step": 20950}
+{"loss": 0.618, "learning_rate": 0.00022579546802704945, "epoch": 0.75, "step": 20960}
+{"loss": 0.7708, "learning_rate": 0.00022575987661644322, "epoch": 0.75, "step": 20970}
+{"loss": 0.7523, "learning_rate": 0.00022572428520583698, "epoch": 0.75, "step": 20980}
+{"loss": 0.5512, "learning_rate": 0.00022568869379523072, "epoch": 0.75, "step": 20990}
+{"loss": 0.7961, "learning_rate": 0.00022565310238462452, "epoch": 0.75, "step": 21000}
+{"loss": 0.6394, "learning_rate": 0.00022561751097401826, "epoch": 0.75, "step": 21010}
+{"loss": 0.605, "learning_rate": 0.000225581919563412, "epoch": 0.75, "step": 21020}
+{"loss": 0.6933, "learning_rate": 0.00022554632815280576, "epoch": 0.75, "step": 21030}
+{"loss": 0.691, "learning_rate": 0.00022551073674219953, "epoch": 0.75, "step": 21040}
+{"loss": 0.6184, "learning_rate": 0.0002254751453315933, "epoch": 0.75, "step": 21050}
+{"loss": 0.6156, "learning_rate": 0.00022543955392098704, "epoch": 0.75, "step": 21060}
+{"loss": 0.6559, "learning_rate": 0.00022540396251038083, "epoch": 0.75, "step": 21070}
+{"loss": 0.6691, "learning_rate": 0.00022536837109977457, "epoch": 0.75, "step": 21080}
+{"loss": 0.6425, "learning_rate": 0.0002253327796891683, "epoch": 0.75, "step": 21090}
+{"loss": 0.7222, "learning_rate": 0.0002252971882785621, "epoch": 0.75, "step": 21100}
+{"loss": 0.6686, "learning_rate": 0.00022526159686795584, "epoch": 0.75, "step": 21110}
+{"loss": 0.6461, "learning_rate": 0.0002252260054573496, "epoch": 0.75, "step": 21120}
+{"loss": 0.713, "learning_rate": 0.00022519041404674335, "epoch": 0.75, "step": 21130}
+{"loss": 0.7068, "learning_rate": 0.00022515482263613714, "epoch": 0.75, "step": 21140}
+{"loss": 0.738, "learning_rate": 0.00022511923122553088, "epoch": 0.75, "step": 21150}
+{"loss": 0.6787, "learning_rate": 0.00022508363981492462, "epoch": 0.75, "step": 21160}
+{"loss": 0.5874, "learning_rate": 0.0002250480484043184, "epoch": 0.75, "step": 21170}
+{"loss": 0.5772, "learning_rate": 0.00022501245699371215, "epoch": 0.75, "step": 21180}
+{"loss": 0.5926, "learning_rate": 0.00022497686558310592, "epoch": 0.75, "step": 21190}
+{"loss": 0.7182, "learning_rate": 0.00022494127417249969, "epoch": 0.75, "step": 21200}
+{"loss": 0.6939, "learning_rate": 0.00022490568276189345, "epoch": 0.75, "step": 21210}
+{"loss": 0.6401, "learning_rate": 0.0002248700913512872, "epoch": 0.75, "step": 21220}
+{"loss": 0.6344, "learning_rate": 0.00022483449994068099, "epoch": 0.75, "step": 21230}
+{"loss": 0.6844, "learning_rate": 0.00022479890853007472, "epoch": 0.76, "step": 21240}
+{"loss": 0.6147, "learning_rate": 0.0002247633171194685, "epoch": 0.76, "step": 21250}
+{"loss": 0.6807, "learning_rate": 0.00022472772570886223, "epoch": 0.76, "step": 21260}
+{"loss": 0.585, "learning_rate": 0.000224692134298256, "epoch": 0.76, "step": 21270}
+{"loss": 0.6365, "learning_rate": 0.00022465654288764976, "epoch": 0.76, "step": 21280}
+{"loss": 0.7233, "learning_rate": 0.0002246209514770435, "epoch": 0.76, "step": 21290}
+{"loss": 0.6798, "learning_rate": 0.0002245853600664373, "epoch": 0.76, "step": 21300}
+{"loss": 0.6734, "learning_rate": 0.00022454976865583104, "epoch": 0.76, "step": 21310}
+{"loss": 0.6018, "learning_rate": 0.0002245141772452248, "epoch": 0.76, "step": 21320}
+{"loss": 0.6911, "learning_rate": 0.00022447858583461857, "epoch": 0.76, "step": 21330}
+{"loss": 0.7042, "learning_rate": 0.00022444299442401234, "epoch": 0.76, "step": 21340}
+{"loss": 0.7912, "learning_rate": 0.00022440740301340608, "epoch": 0.76, "step": 21350}
+{"loss": 0.6508, "learning_rate": 0.00022437181160279982, "epoch": 0.76, "step": 21360}
+{"loss": 0.6119, "learning_rate": 0.0002243362201921936, "epoch": 0.76, "step": 21370}
+{"loss": 0.6678, "learning_rate": 0.00022430062878158735, "epoch": 0.76, "step": 21380}
+{"loss": 0.6884, "learning_rate": 0.00022426503737098111, "epoch": 0.76, "step": 21390}
+{"loss": 0.6549, "learning_rate": 0.00022422944596037488, "epoch": 0.76, "step": 21400}
+{"loss": 0.6042, "learning_rate": 0.00022419385454976865, "epoch": 0.76, "step": 21410}
+{"loss": 0.7057, "learning_rate": 0.0002241582631391624, "epoch": 0.76, "step": 21420}
+{"loss": 0.7154, "learning_rate": 0.00022412267172855618, "epoch": 0.76, "step": 21430}
+{"loss": 0.6302, "learning_rate": 0.00022408708031794992, "epoch": 0.76, "step": 21440}
+{"loss": 0.6844, "learning_rate": 0.00022405148890734366, "epoch": 0.76, "step": 21450}
+{"loss": 0.6593, "learning_rate": 0.00022401589749673745, "epoch": 0.76, "step": 21460}
+{"loss": 0.575, "learning_rate": 0.0002239803060861312, "epoch": 0.76, "step": 21470}
+{"loss": 0.7661, "learning_rate": 0.00022394471467552496, "epoch": 0.76, "step": 21480}
+{"loss": 0.6389, "learning_rate": 0.0002239091232649187, "epoch": 0.76, "step": 21490}
+{"loss": 0.7234, "learning_rate": 0.0002238735318543125, "epoch": 0.76, "step": 21500}
+{"loss": 0.7059, "learning_rate": 0.00022383794044370623, "epoch": 0.76, "step": 21510}
+{"loss": 0.6627, "learning_rate": 0.00022380234903309997, "epoch": 0.77, "step": 21520}
+{"loss": 0.7917, "learning_rate": 0.00022376675762249377, "epoch": 0.77, "step": 21530}
+{"loss": 0.7276, "learning_rate": 0.0002237311662118875, "epoch": 0.77, "step": 21540}
+{"loss": 0.7118, "learning_rate": 0.00022369557480128127, "epoch": 0.77, "step": 21550}
+{"loss": 0.6611, "learning_rate": 0.00022365998339067504, "epoch": 0.77, "step": 21560}
+{"loss": 0.6855, "learning_rate": 0.0002236243919800688, "epoch": 0.77, "step": 21570}
+{"loss": 0.6333, "learning_rate": 0.00022358880056946254, "epoch": 0.77, "step": 21580}
+{"loss": 0.6405, "learning_rate": 0.00022355320915885628, "epoch": 0.77, "step": 21590}
+{"loss": 0.694, "learning_rate": 0.00022351761774825008, "epoch": 0.77, "step": 21600}
+{"loss": 0.6741, "learning_rate": 0.00022348202633764382, "epoch": 0.77, "step": 21610}
+{"loss": 0.6241, "learning_rate": 0.00022344643492703758, "epoch": 0.77, "step": 21620}
+{"loss": 0.6782, "learning_rate": 0.00022341084351643135, "epoch": 0.77, "step": 21630}
+{"loss": 0.7203, "learning_rate": 0.00022337525210582512, "epoch": 0.77, "step": 21640}
+{"loss": 0.7264, "learning_rate": 0.00022333966069521886, "epoch": 0.77, "step": 21650}
+{"loss": 0.6397, "learning_rate": 0.00022330406928461265, "epoch": 0.77, "step": 21660}
+{"loss": 0.6174, "learning_rate": 0.0002232684778740064, "epoch": 0.77, "step": 21670}
+{"loss": 0.6127, "learning_rate": 0.00022323288646340013, "epoch": 0.77, "step": 21680}
+{"loss": 0.6089, "learning_rate": 0.0002231972950527939, "epoch": 0.77, "step": 21690}
+{"loss": 0.7288, "learning_rate": 0.00022316170364218766, "epoch": 0.77, "step": 21700}
+{"loss": 0.7038, "learning_rate": 0.00022312611223158143, "epoch": 0.77, "step": 21710}
+{"loss": 0.6144, "learning_rate": 0.00022309052082097517, "epoch": 0.77, "step": 21720}
+{"loss": 0.7353, "learning_rate": 0.00022305492941036896, "epoch": 0.77, "step": 21730}
+{"loss": 0.5906, "learning_rate": 0.0002230193379997627, "epoch": 0.77, "step": 21740}
+{"loss": 0.704, "learning_rate": 0.00022298374658915647, "epoch": 0.77, "step": 21750}
+{"loss": 0.6354, "learning_rate": 0.00022294815517855023, "epoch": 0.77, "step": 21760}
+{"loss": 0.6431, "learning_rate": 0.00022291256376794397, "epoch": 0.77, "step": 21770}
+{"loss": 0.6342, "learning_rate": 0.00022287697235733774, "epoch": 0.77, "step": 21780}
+{"loss": 0.697, "learning_rate": 0.0002228413809467315, "epoch": 0.77, "step": 21790}
+{"loss": 0.6362, "learning_rate": 0.00022280578953612527, "epoch": 0.77, "step": 21800}
+{"loss": 0.7236, "learning_rate": 0.000222770198125519, "epoch": 0.78, "step": 21810}
+{"loss": 0.7482, "learning_rate": 0.00022273460671491278, "epoch": 0.78, "step": 21820}
+{"loss": 0.7031, "learning_rate": 0.00022269901530430655, "epoch": 0.78, "step": 21830}
+{"loss": 0.6303, "learning_rate": 0.0002226634238937003, "epoch": 0.78, "step": 21840}
+{"loss": 0.6204, "learning_rate": 0.00022262783248309405, "epoch": 0.78, "step": 21850}
+{"loss": 0.6819, "learning_rate": 0.00022259224107248784, "epoch": 0.78, "step": 21860}
+{"loss": 0.7482, "learning_rate": 0.00022255664966188158, "epoch": 0.78, "step": 21870}
+{"loss": 0.7001, "learning_rate": 0.00022252105825127532, "epoch": 0.78, "step": 21880}
+{"loss": 0.5931, "learning_rate": 0.00022248546684066912, "epoch": 0.78, "step": 21890}
+{"loss": 0.6268, "learning_rate": 0.00022244987543006286, "epoch": 0.78, "step": 21900}
+{"loss": 0.6059, "learning_rate": 0.00022241428401945662, "epoch": 0.78, "step": 21910}
+{"loss": 0.6061, "learning_rate": 0.00022237869260885036, "epoch": 0.78, "step": 21920}
+{"loss": 0.6952, "learning_rate": 0.00022234310119824416, "epoch": 0.78, "step": 21930}
+{"loss": 0.7549, "learning_rate": 0.0002223075097876379, "epoch": 0.78, "step": 21940}
+{"loss": 0.6742, "learning_rate": 0.00022227191837703164, "epoch": 0.78, "step": 21950}
+{"loss": 0.7529, "learning_rate": 0.00022223632696642543, "epoch": 0.78, "step": 21960}
+{"loss": 0.613, "learning_rate": 0.00022220073555581917, "epoch": 0.78, "step": 21970}
+{"loss": 0.6903, "learning_rate": 0.00022216514414521294, "epoch": 0.78, "step": 21980}
+{"loss": 0.5902, "learning_rate": 0.0002221295527346067, "epoch": 0.78, "step": 21990}
+{"loss": 0.6025, "learning_rate": 0.00022209396132400047, "epoch": 0.78, "step": 22000}
+{"loss": 0.6908, "learning_rate": 0.0002220583699133942, "epoch": 0.78, "step": 22010}
+{"loss": 0.6366, "learning_rate": 0.000222022778502788, "epoch": 0.78, "step": 22020}
+{"loss": 0.6271, "learning_rate": 0.00022198718709218174, "epoch": 0.78, "step": 22030}
+{"loss": 0.6397, "learning_rate": 0.00022195159568157548, "epoch": 0.78, "step": 22040}
+{"loss": 0.582, "learning_rate": 0.00022191600427096925, "epoch": 0.78, "step": 22050}
+{"loss": 0.5925, "learning_rate": 0.000221880412860363, "epoch": 0.78, "step": 22060}
+{"loss": 0.5928, "learning_rate": 0.00022184482144975678, "epoch": 0.78, "step": 22070}
+{"loss": 0.5699, "learning_rate": 0.00022180923003915052, "epoch": 0.78, "step": 22080}
+{"loss": 0.6549, "learning_rate": 0.0002217736386285443, "epoch": 0.79, "step": 22090}
+{"loss": 0.5977, "learning_rate": 0.00022173804721793805, "epoch": 0.79, "step": 22100}
+{"loss": 0.6567, "learning_rate": 0.0002217024558073318, "epoch": 0.79, "step": 22110}
+{"loss": 0.7211, "learning_rate": 0.00022166686439672559, "epoch": 0.79, "step": 22120}
+{"loss": 0.7105, "learning_rate": 0.00022163127298611933, "epoch": 0.79, "step": 22130}
+{"loss": 0.7407, "learning_rate": 0.0002215956815755131, "epoch": 0.79, "step": 22140}
+{"loss": 0.622, "learning_rate": 0.00022156009016490683, "epoch": 0.79, "step": 22150}
+{"loss": 0.7253, "learning_rate": 0.00022152449875430062, "epoch": 0.79, "step": 22160}
+{"loss": 0.6544, "learning_rate": 0.00022148890734369436, "epoch": 0.79, "step": 22170}
+{"loss": 0.6621, "learning_rate": 0.0002214533159330881, "epoch": 0.79, "step": 22180}
+{"loss": 0.6408, "learning_rate": 0.0002214177245224819, "epoch": 0.79, "step": 22190}
+{"loss": 0.6616, "learning_rate": 0.00022138213311187564, "epoch": 0.79, "step": 22200}
+{"loss": 0.6375, "learning_rate": 0.0002213465417012694, "epoch": 0.79, "step": 22210}
+{"loss": 0.6129, "learning_rate": 0.00022131095029066317, "epoch": 0.79, "step": 22220}
+{"loss": 0.7209, "learning_rate": 0.00022127535888005694, "epoch": 0.79, "step": 22230}
+{"loss": 0.6351, "learning_rate": 0.00022123976746945068, "epoch": 0.79, "step": 22240}
+{"loss": 0.6695, "learning_rate": 0.00022120417605884447, "epoch": 0.79, "step": 22250}
+{"loss": 0.6799, "learning_rate": 0.0002211685846482382, "epoch": 0.79, "step": 22260}
+{"loss": 0.6838, "learning_rate": 0.00022113299323763195, "epoch": 0.79, "step": 22270}
+{"loss": 0.7017, "learning_rate": 0.00022109740182702572, "epoch": 0.79, "step": 22280}
+{"loss": 0.6515, "learning_rate": 0.00022106181041641948, "epoch": 0.79, "step": 22290}
+{"loss": 0.7148, "learning_rate": 0.00022102621900581325, "epoch": 0.79, "step": 22300}
+{"loss": 0.644, "learning_rate": 0.000220990627595207, "epoch": 0.79, "step": 22310}
+{"loss": 0.7058, "learning_rate": 0.00022095503618460078, "epoch": 0.79, "step": 22320}
+{"loss": 0.723, "learning_rate": 0.00022091944477399452, "epoch": 0.79, "step": 22330}
+{"loss": 0.7131, "learning_rate": 0.0002208838533633883, "epoch": 0.79, "step": 22340}
+{"loss": 0.6011, "learning_rate": 0.00022084826195278205, "epoch": 0.79, "step": 22350}
+{"loss": 0.5587, "learning_rate": 0.0002208126705421758, "epoch": 0.79, "step": 22360}
+{"loss": 0.6083, "learning_rate": 0.00022077707913156956, "epoch": 0.8, "step": 22370}
+{"loss": 0.7306, "learning_rate": 0.0002207414877209633, "epoch": 0.8, "step": 22380}
+{"loss": 0.5984, "learning_rate": 0.0002207058963103571, "epoch": 0.8, "step": 22390}
+{"loss": 0.6928, "learning_rate": 0.00022067030489975083, "epoch": 0.8, "step": 22400}
+{"loss": 0.5628, "learning_rate": 0.0002206347134891446, "epoch": 0.8, "step": 22410}
+{"loss": 0.7584, "learning_rate": 0.00022059912207853837, "epoch": 0.8, "step": 22420}
+{"loss": 0.5712, "learning_rate": 0.00022056353066793213, "epoch": 0.8, "step": 22430}
+{"loss": 0.5928, "learning_rate": 0.00022052793925732587, "epoch": 0.8, "step": 22440}
+{"loss": 0.6635, "learning_rate": 0.00022049234784671967, "epoch": 0.8, "step": 22450}
+{"loss": 0.7736, "learning_rate": 0.0002204567564361134, "epoch": 0.8, "step": 22460}
+{"loss": 0.712, "learning_rate": 0.00022042116502550714, "epoch": 0.8, "step": 22470}
+{"loss": 0.6705, "learning_rate": 0.00022038557361490094, "epoch": 0.8, "step": 22480}
+{"loss": 0.6164, "learning_rate": 0.00022034998220429468, "epoch": 0.8, "step": 22490}
+{"loss": 0.6774, "learning_rate": 0.00022031439079368844, "epoch": 0.8, "step": 22500}
+{"loss": 0.688, "learning_rate": 0.00022027879938308218, "epoch": 0.8, "step": 22510}
+{"loss": 0.5857, "learning_rate": 0.00022024320797247598, "epoch": 0.8, "step": 22520}
+{"loss": 0.6271, "learning_rate": 0.00022020761656186972, "epoch": 0.8, "step": 22530}
+{"loss": 0.7079, "learning_rate": 0.00022017202515126346, "epoch": 0.8, "step": 22540}
+{"loss": 0.7367, "learning_rate": 0.00022013643374065725, "epoch": 0.8, "step": 22550}
+{"loss": 0.7031, "learning_rate": 0.000220100842330051, "epoch": 0.8, "step": 22560}
+{"loss": 0.7114, "learning_rate": 0.00022006525091944476, "epoch": 0.8, "step": 22570}
+{"loss": 0.6925, "learning_rate": 0.00022002965950883852, "epoch": 0.8, "step": 22580}
+{"loss": 0.5954, "learning_rate": 0.0002199940680982323, "epoch": 0.8, "step": 22590}
+{"loss": 0.6636, "learning_rate": 0.00021995847668762603, "epoch": 0.8, "step": 22600}
+{"loss": 0.7198, "learning_rate": 0.00021992288527701977, "epoch": 0.8, "step": 22610}
+{"loss": 0.6426, "learning_rate": 0.00021988729386641356, "epoch": 0.8, "step": 22620}
+{"loss": 0.6602, "learning_rate": 0.0002198517024558073, "epoch": 0.8, "step": 22630}
+{"loss": 0.6446, "learning_rate": 0.00021981611104520107, "epoch": 0.8, "step": 22640}
+{"loss": 0.6166, "learning_rate": 0.00021978051963459483, "epoch": 0.81, "step": 22650}
+{"loss": 0.6427, "learning_rate": 0.0002197449282239886, "epoch": 0.81, "step": 22660}
+{"loss": 0.6831, "learning_rate": 0.00021970933681338234, "epoch": 0.81, "step": 22670}
+{"loss": 0.7164, "learning_rate": 0.00021967374540277613, "epoch": 0.81, "step": 22680}
+{"loss": 0.6409, "learning_rate": 0.00021963815399216987, "epoch": 0.81, "step": 22690}
+{"loss": 0.6726, "learning_rate": 0.0002196025625815636, "epoch": 0.81, "step": 22700}
+{"loss": 0.6248, "learning_rate": 0.00021956697117095738, "epoch": 0.81, "step": 22710}
+{"loss": 0.7968, "learning_rate": 0.00021953137976035115, "epoch": 0.81, "step": 22720}
+{"loss": 0.746, "learning_rate": 0.0002194957883497449, "epoch": 0.81, "step": 22730}
+{"loss": 0.6355, "learning_rate": 0.00021946019693913865, "epoch": 0.81, "step": 22740}
+{"loss": 0.7184, "learning_rate": 0.00021942460552853245, "epoch": 0.81, "step": 22750}
+{"loss": 0.6026, "learning_rate": 0.00021938901411792618, "epoch": 0.81, "step": 22760}
+{"loss": 0.6736, "learning_rate": 0.00021935342270731992, "epoch": 0.81, "step": 22770}
+{"loss": 0.6708, "learning_rate": 0.00021931783129671372, "epoch": 0.81, "step": 22780}
+{"loss": 0.5723, "learning_rate": 0.00021928223988610746, "epoch": 0.81, "step": 22790}
+{"loss": 0.5899, "learning_rate": 0.00021924664847550122, "epoch": 0.81, "step": 22800}
+{"loss": 0.6618, "learning_rate": 0.000219211057064895, "epoch": 0.81, "step": 22810}
+{"loss": 0.5732, "learning_rate": 0.00021917546565428876, "epoch": 0.81, "step": 22820}
+{"loss": 0.6333, "learning_rate": 0.0002191398742436825, "epoch": 0.81, "step": 22830}
+{"loss": 0.7018, "learning_rate": 0.00021910428283307626, "epoch": 0.81, "step": 22840}
+{"loss": 0.5962, "learning_rate": 0.00021906869142247003, "epoch": 0.81, "step": 22850}
+{"loss": 0.6515, "learning_rate": 0.00021903310001186377, "epoch": 0.81, "step": 22860}
+{"loss": 0.6849, "learning_rate": 0.00021899750860125754, "epoch": 0.81, "step": 22870}
+{"loss": 0.6241, "learning_rate": 0.0002189619171906513, "epoch": 0.81, "step": 22880}
+{"loss": 0.6589, "learning_rate": 0.00021892632578004507, "epoch": 0.81, "step": 22890}
+{"loss": 0.7201, "learning_rate": 0.0002188907343694388, "epoch": 0.81, "step": 22900}
+{"loss": 0.6962, "learning_rate": 0.0002188551429588326, "epoch": 0.81, "step": 22910}
+{"loss": 0.5817, "learning_rate": 0.00021881955154822634, "epoch": 0.81, "step": 22920}
+{"loss": 0.6587, "learning_rate": 0.0002187839601376201, "epoch": 0.82, "step": 22930}
+{"loss": 0.7155, "learning_rate": 0.00021874836872701385, "epoch": 0.82, "step": 22940}
+{"loss": 0.7024, "learning_rate": 0.00021871277731640764, "epoch": 0.82, "step": 22950}
+{"loss": 0.6567, "learning_rate": 0.00021867718590580138, "epoch": 0.82, "step": 22960}
+{"loss": 0.6889, "learning_rate": 0.00021864159449519512, "epoch": 0.82, "step": 22970}
+{"loss": 0.6675, "learning_rate": 0.0002186060030845889, "epoch": 0.82, "step": 22980}
+{"loss": 0.6704, "learning_rate": 0.00021857041167398265, "epoch": 0.82, "step": 22990}
+{"loss": 0.7088, "learning_rate": 0.00021853482026337642, "epoch": 0.82, "step": 23000}
+{"loss": 0.7261, "learning_rate": 0.00021849922885277019, "epoch": 0.82, "step": 23010}
+{"loss": 0.6212, "learning_rate": 0.00021846363744216395, "epoch": 0.82, "step": 23020}
+{"loss": 0.6683, "learning_rate": 0.0002184280460315577, "epoch": 0.82, "step": 23030}
+{"loss": 0.6688, "learning_rate": 0.00021839245462095149, "epoch": 0.82, "step": 23040}
+{"loss": 0.711, "learning_rate": 0.00021835686321034523, "epoch": 0.82, "step": 23050}
+{"loss": 0.7493, "learning_rate": 0.00021832127179973896, "epoch": 0.82, "step": 23060}
+{"loss": 0.6598, "learning_rate": 0.00021828568038913273, "epoch": 0.82, "step": 23070}
+{"loss": 0.661, "learning_rate": 0.0002182500889785265, "epoch": 0.82, "step": 23080}
+{"loss": 0.6, "learning_rate": 0.00021821449756792026, "epoch": 0.82, "step": 23090}
+{"loss": 0.6686, "learning_rate": 0.000218178906157314, "epoch": 0.82, "step": 23100}
+{"loss": 0.5928, "learning_rate": 0.0002181433147467078, "epoch": 0.82, "step": 23110}
+{"loss": 0.6861, "learning_rate": 0.00021810772333610154, "epoch": 0.82, "step": 23120}
+{"loss": 0.6099, "learning_rate": 0.00021807213192549528, "epoch": 0.82, "step": 23130}
+{"loss": 0.6501, "learning_rate": 0.00021803654051488907, "epoch": 0.82, "step": 23140}
+{"loss": 0.6379, "learning_rate": 0.0002180009491042828, "epoch": 0.82, "step": 23150}
+{"loss": 0.5497, "learning_rate": 0.00021796535769367658, "epoch": 0.82, "step": 23160}
+{"loss": 0.6391, "learning_rate": 0.00021792976628307032, "epoch": 0.82, "step": 23170}
+{"loss": 0.6955, "learning_rate": 0.0002178941748724641, "epoch": 0.82, "step": 23180}
+{"loss": 0.6144, "learning_rate": 0.00021785858346185785, "epoch": 0.82, "step": 23190}
+{"loss": 0.6872, "learning_rate": 0.0002178229920512516, "epoch": 0.82, "step": 23200}
+{"loss": 0.6293, "learning_rate": 0.00021778740064064538, "epoch": 0.83, "step": 23210}
+{"loss": 0.7028, "learning_rate": 0.00021775180923003912, "epoch": 0.83, "step": 23220}
+{"loss": 0.6583, "learning_rate": 0.0002177162178194329, "epoch": 0.83, "step": 23230}
+{"loss": 0.7602, "learning_rate": 0.00021768062640882665, "epoch": 0.83, "step": 23240}
+{"loss": 0.629, "learning_rate": 0.00021764503499822042, "epoch": 0.83, "step": 23250}
+{"loss": 0.6693, "learning_rate": 0.00021760944358761416, "epoch": 0.83, "step": 23260}
+{"loss": 0.6421, "learning_rate": 0.00021757385217700795, "epoch": 0.83, "step": 23270}
+{"loss": 0.6615, "learning_rate": 0.0002175382607664017, "epoch": 0.83, "step": 23280}
+{"loss": 0.6098, "learning_rate": 0.00021750266935579543, "epoch": 0.83, "step": 23290}
+{"loss": 0.8521, "learning_rate": 0.0002174670779451892, "epoch": 0.83, "step": 23300}
+{"loss": 0.623, "learning_rate": 0.00021743148653458297, "epoch": 0.83, "step": 23310}
+{"loss": 0.5615, "learning_rate": 0.00021739589512397673, "epoch": 0.83, "step": 23320}
+{"loss": 0.6875, "learning_rate": 0.00021736030371337047, "epoch": 0.83, "step": 23330}
+{"loss": 0.6646, "learning_rate": 0.00021732471230276427, "epoch": 0.83, "step": 23340}
+{"loss": 0.6809, "learning_rate": 0.000217289120892158, "epoch": 0.83, "step": 23350}
+{"loss": 0.6204, "learning_rate": 0.00021725352948155174, "epoch": 0.83, "step": 23360}
+{"loss": 0.7022, "learning_rate": 0.00021721793807094554, "epoch": 0.83, "step": 23370}
+{"loss": 0.6835, "learning_rate": 0.00021718234666033928, "epoch": 0.83, "step": 23380}
+{"loss": 0.688, "learning_rate": 0.00021714675524973304, "epoch": 0.83, "step": 23390}
+{"loss": 0.7093, "learning_rate": 0.00021711116383912678, "epoch": 0.83, "step": 23400}
+{"loss": 0.7176, "learning_rate": 0.00021707557242852058, "epoch": 0.83, "step": 23410}
+{"loss": 0.5609, "learning_rate": 0.00021703998101791432, "epoch": 0.83, "step": 23420}
+{"loss": 0.7258, "learning_rate": 0.00021700438960730808, "epoch": 0.83, "step": 23430}
+{"loss": 0.6654, "learning_rate": 0.00021696879819670185, "epoch": 0.83, "step": 23440}
+{"loss": 0.6018, "learning_rate": 0.00021693320678609562, "epoch": 0.83, "step": 23450}
+{"loss": 0.6934, "learning_rate": 0.00021689761537548936, "epoch": 0.83, "step": 23460}
+{"loss": 0.6124, "learning_rate": 0.00021686202396488312, "epoch": 0.83, "step": 23470}
+{"loss": 0.6355, "learning_rate": 0.0002168264325542769, "epoch": 0.83, "step": 23480}
+{"loss": 0.7241, "learning_rate": 0.00021679084114367063, "epoch": 0.84, "step": 23490}
+{"loss": 0.6915, "learning_rate": 0.00021675524973306442, "epoch": 0.84, "step": 23500}
+{"loss": 0.6674, "learning_rate": 0.00021671965832245816, "epoch": 0.84, "step": 23510}
+{"loss": 0.6517, "learning_rate": 0.00021668406691185193, "epoch": 0.84, "step": 23520}
+{"loss": 0.7194, "learning_rate": 0.00021664847550124567, "epoch": 0.84, "step": 23530}
+{"loss": 0.6935, "learning_rate": 0.00021661288409063946, "epoch": 0.84, "step": 23540}
+{"loss": 0.7225, "learning_rate": 0.0002165772926800332, "epoch": 0.84, "step": 23550}
+{"loss": 0.71, "learning_rate": 0.00021654170126942694, "epoch": 0.84, "step": 23560}
+{"loss": 0.6087, "learning_rate": 0.00021650610985882073, "epoch": 0.84, "step": 23570}
+{"loss": 0.6463, "learning_rate": 0.00021647051844821447, "epoch": 0.84, "step": 23580}
+{"loss": 0.6577, "learning_rate": 0.00021643492703760824, "epoch": 0.84, "step": 23590}
+{"loss": 0.6488, "learning_rate": 0.000216399335627002, "epoch": 0.84, "step": 23600}
+{"loss": 0.6637, "learning_rate": 0.00021636374421639577, "epoch": 0.84, "step": 23610}
+{"loss": 0.6177, "learning_rate": 0.0002163281528057895, "epoch": 0.84, "step": 23620}
+{"loss": 0.659, "learning_rate": 0.00021629256139518325, "epoch": 0.84, "step": 23630}
+{"loss": 0.6429, "learning_rate": 0.00021625696998457705, "epoch": 0.84, "step": 23640}
+{"loss": 0.574, "learning_rate": 0.00021622137857397079, "epoch": 0.84, "step": 23650}
+{"loss": 0.6259, "learning_rate": 0.00021618578716336455, "epoch": 0.84, "step": 23660}
+{"loss": 0.5686, "learning_rate": 0.00021615019575275832, "epoch": 0.84, "step": 23670}
+{"loss": 0.6295, "learning_rate": 0.00021611460434215208, "epoch": 0.84, "step": 23680}
+{"loss": 0.6249, "learning_rate": 0.00021607901293154582, "epoch": 0.84, "step": 23690}
+{"loss": 0.8182, "learning_rate": 0.00021604342152093962, "epoch": 0.84, "step": 23700}
+{"loss": 0.6668, "learning_rate": 0.00021600783011033336, "epoch": 0.84, "step": 23710}
+{"loss": 0.6005, "learning_rate": 0.0002159722386997271, "epoch": 0.84, "step": 23720}
+{"loss": 0.7095, "learning_rate": 0.0002159366472891209, "epoch": 0.84, "step": 23730}
+{"loss": 0.6505, "learning_rate": 0.00021590105587851463, "epoch": 0.84, "step": 23740}
+{"loss": 0.6339, "learning_rate": 0.0002158654644679084, "epoch": 0.84, "step": 23750}
+{"loss": 0.6027, "learning_rate": 0.00021582987305730214, "epoch": 0.84, "step": 23760}
+{"loss": 0.7002, "learning_rate": 0.00021579428164669593, "epoch": 0.85, "step": 23770}
+{"loss": 0.7061, "learning_rate": 0.00021575869023608967, "epoch": 0.85, "step": 23780}
+{"loss": 0.5693, "learning_rate": 0.0002157230988254834, "epoch": 0.85, "step": 23790}
+{"loss": 0.6641, "learning_rate": 0.0002156875074148772, "epoch": 0.85, "step": 23800}
+{"loss": 0.6497, "learning_rate": 0.00021565191600427094, "epoch": 0.85, "step": 23810}
+{"loss": 0.6601, "learning_rate": 0.0002156163245936647, "epoch": 0.85, "step": 23820}
+{"loss": 0.657, "learning_rate": 0.00021558073318305847, "epoch": 0.85, "step": 23830}
+{"loss": 0.6743, "learning_rate": 0.00021554514177245224, "epoch": 0.85, "step": 23840}
+{"loss": 0.6167, "learning_rate": 0.00021550955036184598, "epoch": 0.85, "step": 23850}
+{"loss": 0.5797, "learning_rate": 0.00021547395895123972, "epoch": 0.85, "step": 23860}
+{"loss": 0.5988, "learning_rate": 0.00021543836754063351, "epoch": 0.85, "step": 23870}
+{"loss": 0.6667, "learning_rate": 0.00021540277613002725, "epoch": 0.85, "step": 23880}
+{"loss": 0.6856, "learning_rate": 0.00021536718471942102, "epoch": 0.85, "step": 23890}
+{"loss": 0.5389, "learning_rate": 0.00021533159330881479, "epoch": 0.85, "step": 23900}
+{"loss": 0.594, "learning_rate": 0.00021529600189820855, "epoch": 0.85, "step": 23910}
+{"loss": 0.661, "learning_rate": 0.0002152604104876023, "epoch": 0.85, "step": 23920}
+{"loss": 0.6726, "learning_rate": 0.00021522481907699609, "epoch": 0.85, "step": 23930}
+{"loss": 0.6056, "learning_rate": 0.00021518922766638983, "epoch": 0.85, "step": 23940}
+{"loss": 0.659, "learning_rate": 0.0002151536362557836, "epoch": 0.85, "step": 23950}
+{"loss": 0.6191, "learning_rate": 0.00021511804484517733, "epoch": 0.85, "step": 23960}
+{"loss": 0.6118, "learning_rate": 0.0002150824534345711, "epoch": 0.85, "step": 23970}
+{"loss": 0.639, "learning_rate": 0.00021504686202396486, "epoch": 0.85, "step": 23980}
+{"loss": 0.6646, "learning_rate": 0.0002150112706133586, "epoch": 0.85, "step": 23990}
+{"loss": 0.7752, "learning_rate": 0.0002149756792027524, "epoch": 0.85, "step": 24000}
+{"loss": 0.6936, "learning_rate": 0.00021494008779214614, "epoch": 0.85, "step": 24010}
+{"loss": 0.6972, "learning_rate": 0.0002149044963815399, "epoch": 0.85, "step": 24020}
+{"loss": 0.7192, "learning_rate": 0.00021486890497093367, "epoch": 0.85, "step": 24030}
+{"loss": 0.7002, "learning_rate": 0.00021483331356032744, "epoch": 0.85, "step": 24040}
+{"loss": 0.671, "learning_rate": 0.00021479772214972118, "epoch": 0.85, "step": 24050}
+{"loss": 0.6143, "learning_rate": 0.00021476213073911497, "epoch": 0.86, "step": 24060}
+{"loss": 0.6781, "learning_rate": 0.0002147265393285087, "epoch": 0.86, "step": 24070}
+{"loss": 0.5778, "learning_rate": 0.00021469094791790245, "epoch": 0.86, "step": 24080}
+{"loss": 0.6537, "learning_rate": 0.00021465535650729622, "epoch": 0.86, "step": 24090}
+{"loss": 0.732, "learning_rate": 0.00021461976509668998, "epoch": 0.86, "step": 24100}
+{"loss": 0.7184, "learning_rate": 0.00021458417368608375, "epoch": 0.86, "step": 24110}
+{"loss": 0.6724, "learning_rate": 0.0002145485822754775, "epoch": 0.86, "step": 24120}
+{"loss": 0.617, "learning_rate": 0.00021451299086487128, "epoch": 0.86, "step": 24130}
+{"loss": 0.6749, "learning_rate": 0.00021447739945426502, "epoch": 0.86, "step": 24140}
+{"loss": 0.6895, "learning_rate": 0.00021444180804365876, "epoch": 0.86, "step": 24150}
+{"loss": 0.6203, "learning_rate": 0.00021440621663305255, "epoch": 0.86, "step": 24160}
+{"loss": 0.6452, "learning_rate": 0.0002143706252224463, "epoch": 0.86, "step": 24170}
+{"loss": 0.6399, "learning_rate": 0.00021433503381184006, "epoch": 0.86, "step": 24180}
+{"loss": 0.6841, "learning_rate": 0.0002142994424012338, "epoch": 0.86, "step": 24190}
+{"loss": 0.6895, "learning_rate": 0.0002142638509906276, "epoch": 0.86, "step": 24200}
+{"loss": 0.618, "learning_rate": 0.00021422825958002133, "epoch": 0.86, "step": 24210}
+{"loss": 0.6563, "learning_rate": 0.00021419266816941507, "epoch": 0.86, "step": 24220}
+{"loss": 0.6964, "learning_rate": 0.00021415707675880887, "epoch": 0.86, "step": 24230}
+{"loss": 0.6146, "learning_rate": 0.0002141214853482026, "epoch": 0.86, "step": 24240}
+{"loss": 0.6711, "learning_rate": 0.00021408589393759637, "epoch": 0.86, "step": 24250}
+{"loss": 0.6778, "learning_rate": 0.00021405030252699014, "epoch": 0.86, "step": 24260}
+{"loss": 0.6479, "learning_rate": 0.0002140147111163839, "epoch": 0.86, "step": 24270}
+{"loss": 0.7096, "learning_rate": 0.00021397911970577764, "epoch": 0.86, "step": 24280}
+{"loss": 0.6512, "learning_rate": 0.00021394352829517144, "epoch": 0.86, "step": 24290}
+{"loss": 0.6121, "learning_rate": 0.00021390793688456518, "epoch": 0.86, "step": 24300}
+{"loss": 0.6608, "learning_rate": 0.00021387234547395892, "epoch": 0.86, "step": 24310}
+{"loss": 0.6588, "learning_rate": 0.00021383675406335268, "epoch": 0.86, "step": 24320}
+{"loss": 0.6457, "learning_rate": 0.00021380116265274645, "epoch": 0.86, "step": 24330}
+{"loss": 0.68, "learning_rate": 0.00021376557124214022, "epoch": 0.87, "step": 24340}
+{"loss": 0.6817, "learning_rate": 0.00021372997983153396, "epoch": 0.87, "step": 24350}
+{"loss": 0.6561, "learning_rate": 0.00021369438842092775, "epoch": 0.87, "step": 24360}
+{"loss": 0.7018, "learning_rate": 0.0002136587970103215, "epoch": 0.87, "step": 24370}
+{"loss": 0.5937, "learning_rate": 0.00021362320559971523, "epoch": 0.87, "step": 24380}
+{"loss": 0.6661, "learning_rate": 0.00021358761418910902, "epoch": 0.87, "step": 24390}
+{"loss": 0.6834, "learning_rate": 0.00021355202277850276, "epoch": 0.87, "step": 24400}
+{"loss": 0.6064, "learning_rate": 0.00021351643136789653, "epoch": 0.87, "step": 24410}
+{"loss": 0.7056, "learning_rate": 0.00021348083995729027, "epoch": 0.87, "step": 24420}
+{"loss": 0.6306, "learning_rate": 0.00021344524854668406, "epoch": 0.87, "step": 24430}
+{"loss": 0.7785, "learning_rate": 0.0002134096571360778, "epoch": 0.87, "step": 24440}
+{"loss": 0.7589, "learning_rate": 0.00021337406572547157, "epoch": 0.87, "step": 24450}
+{"loss": 0.672, "learning_rate": 0.00021333847431486533, "epoch": 0.87, "step": 24460}
+{"loss": 0.6247, "learning_rate": 0.00021330288290425907, "epoch": 0.87, "step": 24470}
+{"loss": 0.571, "learning_rate": 0.00021326729149365284, "epoch": 0.87, "step": 24480}
+{"loss": 0.6371, "learning_rate": 0.0002132317000830466, "epoch": 0.87, "step": 24490}
+{"loss": 0.6205, "learning_rate": 0.00021319610867244037, "epoch": 0.87, "step": 24500}
+{"loss": 0.6545, "learning_rate": 0.0002131605172618341, "epoch": 0.87, "step": 24510}
+{"loss": 0.6522, "learning_rate": 0.0002131249258512279, "epoch": 0.87, "step": 24520}
+{"loss": 0.6607, "learning_rate": 0.00021308933444062165, "epoch": 0.87, "step": 24530}
+{"loss": 0.7228, "learning_rate": 0.0002130537430300154, "epoch": 0.87, "step": 24540}
+{"loss": 0.6036, "learning_rate": 0.00021301815161940915, "epoch": 0.87, "step": 24550}
+{"loss": 0.7375, "learning_rate": 0.00021298256020880295, "epoch": 0.87, "step": 24560}
+{"loss": 0.5867, "learning_rate": 0.00021294696879819669, "epoch": 0.87, "step": 24570}
+{"loss": 0.6492, "learning_rate": 0.00021291137738759042, "epoch": 0.87, "step": 24580}
+{"loss": 0.8046, "learning_rate": 0.00021287578597698422, "epoch": 0.87, "step": 24590}
+{"loss": 0.6346, "learning_rate": 0.00021284019456637796, "epoch": 0.87, "step": 24600}
+{"loss": 0.6588, "learning_rate": 0.00021280460315577172, "epoch": 0.87, "step": 24610}
+{"loss": 0.6426, "learning_rate": 0.0002127690117451655, "epoch": 0.88, "step": 24620}
+{"loss": 0.8215, "learning_rate": 0.00021273342033455926, "epoch": 0.88, "step": 24630}
+{"loss": 0.6988, "learning_rate": 0.000212697828923953, "epoch": 0.88, "step": 24640}
+{"loss": 0.6879, "learning_rate": 0.00021266223751334674, "epoch": 0.88, "step": 24650}
+{"loss": 0.6661, "learning_rate": 0.00021262664610274053, "epoch": 0.88, "step": 24660}
+{"loss": 0.6869, "learning_rate": 0.00021259105469213427, "epoch": 0.88, "step": 24670}
+{"loss": 0.6005, "learning_rate": 0.00021255546328152804, "epoch": 0.88, "step": 24680}
+{"loss": 0.7094, "learning_rate": 0.0002125198718709218, "epoch": 0.88, "step": 24690}
+{"loss": 0.6434, "learning_rate": 0.00021248428046031557, "epoch": 0.88, "step": 24700}
+{"loss": 0.7092, "learning_rate": 0.0002124486890497093, "epoch": 0.88, "step": 24710}
+{"loss": 0.6788, "learning_rate": 0.0002124130976391031, "epoch": 0.88, "step": 24720}
+{"loss": 0.6604, "learning_rate": 0.00021237750622849684, "epoch": 0.88, "step": 24730}
+{"loss": 0.6514, "learning_rate": 0.00021234191481789058, "epoch": 0.88, "step": 24740}
+{"loss": 0.5851, "learning_rate": 0.00021230632340728437, "epoch": 0.88, "step": 24750}
+{"loss": 0.615, "learning_rate": 0.00021227073199667811, "epoch": 0.88, "step": 24760}
+{"loss": 0.6591, "learning_rate": 0.00021223514058607188, "epoch": 0.88, "step": 24770}
+{"loss": 0.5754, "learning_rate": 0.00021219954917546562, "epoch": 0.88, "step": 24780}
+{"loss": 0.6369, "learning_rate": 0.00021216395776485941, "epoch": 0.88, "step": 24790}
+{"loss": 0.5483, "learning_rate": 0.00021212836635425315, "epoch": 0.88, "step": 24800}
+{"loss": 0.5318, "learning_rate": 0.0002120927749436469, "epoch": 0.88, "step": 24810}
+{"loss": 0.6116, "learning_rate": 0.0002120571835330407, "epoch": 0.88, "step": 24820}
+{"loss": 0.6153, "learning_rate": 0.00021202159212243443, "epoch": 0.88, "step": 24830}
+{"loss": 0.6181, "learning_rate": 0.0002119860007118282, "epoch": 0.88, "step": 24840}
+{"loss": 0.6992, "learning_rate": 0.00021195040930122196, "epoch": 0.88, "step": 24850}
+{"loss": 0.6264, "learning_rate": 0.00021191481789061573, "epoch": 0.88, "step": 24860}
+{"loss": 0.647, "learning_rate": 0.00021187922648000947, "epoch": 0.88, "step": 24870}
+{"loss": 0.7102, "learning_rate": 0.0002118436350694032, "epoch": 0.88, "step": 24880}
+{"loss": 0.706, "learning_rate": 0.000211808043658797, "epoch": 0.88, "step": 24890}
+{"loss": 0.7109, "learning_rate": 0.00021177245224819074, "epoch": 0.89, "step": 24900}
+{"loss": 0.674, "learning_rate": 0.0002117368608375845, "epoch": 0.89, "step": 24910}
+{"loss": 0.5747, "learning_rate": 0.00021170126942697827, "epoch": 0.89, "step": 24920}
+{"loss": 0.5869, "learning_rate": 0.00021166567801637204, "epoch": 0.89, "step": 24930}
+{"loss": 0.6326, "learning_rate": 0.00021163008660576578, "epoch": 0.89, "step": 24940}
+{"loss": 0.604, "learning_rate": 0.00021159449519515957, "epoch": 0.89, "step": 24950}
+{"loss": 0.5984, "learning_rate": 0.0002115589037845533, "epoch": 0.89, "step": 24960}
+{"loss": 0.6848, "learning_rate": 0.00021152331237394705, "epoch": 0.89, "step": 24970}
+{"loss": 0.6002, "learning_rate": 0.00021148772096334082, "epoch": 0.89, "step": 24980}
+{"loss": 0.6652, "learning_rate": 0.00021145212955273458, "epoch": 0.89, "step": 24990}
+{"loss": 0.6565, "learning_rate": 0.00021141653814212835, "epoch": 0.89, "step": 25000}
+{"loss": 0.5294, "learning_rate": 0.0002113809467315221, "epoch": 0.89, "step": 25010}
+{"loss": 0.6235, "learning_rate": 0.00021134535532091588, "epoch": 0.89, "step": 25020}
+{"loss": 0.693, "learning_rate": 0.00021130976391030962, "epoch": 0.89, "step": 25030}
+{"loss": 0.6202, "learning_rate": 0.0002112741724997034, "epoch": 0.89, "step": 25040}
+{"loss": 0.6329, "learning_rate": 0.00021123858108909715, "epoch": 0.89, "step": 25050}
+{"loss": 0.6508, "learning_rate": 0.00021120298967849092, "epoch": 0.89, "step": 25060}
+{"loss": 0.665, "learning_rate": 0.00021116739826788466, "epoch": 0.89, "step": 25070}
+{"loss": 0.6903, "learning_rate": 0.00021113180685727843, "epoch": 0.89, "step": 25080}
+{"loss": 0.5951, "learning_rate": 0.0002110962154466722, "epoch": 0.89, "step": 25090}
+{"loss": 0.6147, "learning_rate": 0.00021106062403606593, "epoch": 0.89, "step": 25100}
+{"loss": 0.6204, "learning_rate": 0.00021102859176652032, "epoch": 0.89, "step": 25110}
+{"loss": 0.5971, "learning_rate": 0.0002109930003559141, "epoch": 0.89, "step": 25120}
+{"loss": 0.7054, "learning_rate": 0.00021095740894530785, "epoch": 0.89, "step": 25130}
+{"loss": 0.6839, "learning_rate": 0.00021092181753470162, "epoch": 0.89, "step": 25140}
+{"loss": 0.7601, "learning_rate": 0.00021088622612409536, "epoch": 0.89, "step": 25150}
+{"loss": 0.6126, "learning_rate": 0.00021085063471348915, "epoch": 0.89, "step": 25160}
+{"loss": 0.666, "learning_rate": 0.0002108150433028829, "epoch": 0.89, "step": 25170}
+{"loss": 0.5879, "learning_rate": 0.00021077945189227663, "epoch": 0.9, "step": 25180}
+{"loss": 0.5566, "learning_rate": 0.0002107438604816704, "epoch": 0.9, "step": 25190}
+{"loss": 0.5532, "learning_rate": 0.00021070826907106417, "epoch": 0.9, "step": 25200}
+{"loss": 0.5103, "learning_rate": 0.00021067267766045793, "epoch": 0.9, "step": 25210}
+{"loss": 0.7056, "learning_rate": 0.00021063708624985167, "epoch": 0.9, "step": 25220}
+{"loss": 0.6174, "learning_rate": 0.00021060149483924546, "epoch": 0.9, "step": 25230}
+{"loss": 0.6695, "learning_rate": 0.0002105659034286392, "epoch": 0.9, "step": 25240}
+{"loss": 0.6743, "learning_rate": 0.00021053031201803294, "epoch": 0.9, "step": 25250}
+{"loss": 0.7128, "learning_rate": 0.00021049472060742674, "epoch": 0.9, "step": 25260}
+{"loss": 0.7096, "learning_rate": 0.00021045912919682048, "epoch": 0.9, "step": 25270}
+{"loss": 0.6342, "learning_rate": 0.00021042353778621424, "epoch": 0.9, "step": 25280}
+{"loss": 0.6372, "learning_rate": 0.00021038794637560798, "epoch": 0.9, "step": 25290}
+{"loss": 0.6164, "learning_rate": 0.00021035235496500178, "epoch": 0.9, "step": 25300}
+{"loss": 0.7463, "learning_rate": 0.00021031676355439552, "epoch": 0.9, "step": 25310}
+{"loss": 0.5984, "learning_rate": 0.00021028117214378926, "epoch": 0.9, "step": 25320}
+{"loss": 0.6135, "learning_rate": 0.00021024558073318305, "epoch": 0.9, "step": 25330}
+{"loss": 0.599, "learning_rate": 0.0002102099893225768, "epoch": 0.9, "step": 25340}
+{"loss": 0.544, "learning_rate": 0.00021017439791197056, "epoch": 0.9, "step": 25350}
+{"loss": 0.6356, "learning_rate": 0.00021013880650136432, "epoch": 0.9, "step": 25360}
+{"loss": 0.6155, "learning_rate": 0.0002101032150907581, "epoch": 0.9, "step": 25370}
+{"loss": 0.6026, "learning_rate": 0.00021006762368015183, "epoch": 0.9, "step": 25380}
+{"loss": 0.7397, "learning_rate": 0.00021003203226954562, "epoch": 0.9, "step": 25390}
+{"loss": 0.7323, "learning_rate": 0.00020999644085893936, "epoch": 0.9, "step": 25400}
+{"loss": 0.6009, "learning_rate": 0.0002099608494483331, "epoch": 0.9, "step": 25410}
+{"loss": 0.7188, "learning_rate": 0.00020992525803772687, "epoch": 0.9, "step": 25420}
+{"loss": 0.6921, "learning_rate": 0.00020988966662712063, "epoch": 0.9, "step": 25430}
+{"loss": 0.6335, "learning_rate": 0.0002098540752165144, "epoch": 0.9, "step": 25440}
+{"loss": 0.6102, "learning_rate": 0.00020981848380590814, "epoch": 0.9, "step": 25450}
+{"loss": 0.5553, "learning_rate": 0.00020978289239530193, "epoch": 0.91, "step": 25460}
+{"loss": 0.5685, "learning_rate": 0.00020974730098469567, "epoch": 0.91, "step": 25470}
+{"loss": 0.6116, "learning_rate": 0.00020971170957408944, "epoch": 0.91, "step": 25480}
+{"loss": 0.6517, "learning_rate": 0.0002096761181634832, "epoch": 0.91, "step": 25490}
+{"loss": 0.6218, "learning_rate": 0.00020964052675287695, "epoch": 0.91, "step": 25500}
+{"loss": 0.6992, "learning_rate": 0.0002096049353422707, "epoch": 0.91, "step": 25510}
+{"loss": 0.6841, "learning_rate": 0.00020956934393166445, "epoch": 0.91, "step": 25520}
+{"loss": 0.7155, "learning_rate": 0.00020953375252105824, "epoch": 0.91, "step": 25530}
+{"loss": 0.6672, "learning_rate": 0.00020949816111045198, "epoch": 0.91, "step": 25540}
+{"loss": 0.6233, "learning_rate": 0.00020946256969984575, "epoch": 0.91, "step": 25550}
+{"loss": 0.5852, "learning_rate": 0.00020942697828923952, "epoch": 0.91, "step": 25560}
+{"loss": 0.6086, "learning_rate": 0.00020939138687863328, "epoch": 0.91, "step": 25570}
+{"loss": 0.6582, "learning_rate": 0.00020935579546802702, "epoch": 0.91, "step": 25580}
+{"loss": 0.6266, "learning_rate": 0.00020932020405742082, "epoch": 0.91, "step": 25590}
+{"loss": 0.5886, "learning_rate": 0.00020928461264681456, "epoch": 0.91, "step": 25600}
+{"loss": 0.5479, "learning_rate": 0.0002092490212362083, "epoch": 0.91, "step": 25610}
+{"loss": 0.576, "learning_rate": 0.0002092134298256021, "epoch": 0.91, "step": 25620}
+{"loss": 0.7268, "learning_rate": 0.00020917783841499583, "epoch": 0.91, "step": 25630}
+{"loss": 0.6456, "learning_rate": 0.0002091422470043896, "epoch": 0.91, "step": 25640}
+{"loss": 0.6997, "learning_rate": 0.00020910665559378334, "epoch": 0.91, "step": 25650}
+{"loss": 0.6492, "learning_rate": 0.00020907106418317713, "epoch": 0.91, "step": 25660}
+{"loss": 0.6925, "learning_rate": 0.00020903547277257087, "epoch": 0.91, "step": 25670}
+{"loss": 0.5458, "learning_rate": 0.0002089998813619646, "epoch": 0.91, "step": 25680}
+{"loss": 0.7299, "learning_rate": 0.0002089642899513584, "epoch": 0.91, "step": 25690}
+{"loss": 0.7081, "learning_rate": 0.00020892869854075214, "epoch": 0.91, "step": 25700}
+{"loss": 0.6795, "learning_rate": 0.0002088931071301459, "epoch": 0.91, "step": 25710}
+{"loss": 0.5751, "learning_rate": 0.00020885751571953967, "epoch": 0.91, "step": 25720}
+{"loss": 0.6375, "learning_rate": 0.00020882192430893344, "epoch": 0.91, "step": 25730}
+{"loss": 0.7122, "learning_rate": 0.00020878633289832718, "epoch": 0.92, "step": 25740}
+{"loss": 0.5829, "learning_rate": 0.00020875074148772092, "epoch": 0.92, "step": 25750}
+{"loss": 0.6133, "learning_rate": 0.0002087151500771147, "epoch": 0.92, "step": 25760}
+{"loss": 0.6149, "learning_rate": 0.00020867955866650845, "epoch": 0.92, "step": 25770}
+{"loss": 0.5053, "learning_rate": 0.00020864396725590222, "epoch": 0.92, "step": 25780}
+{"loss": 0.6298, "learning_rate": 0.00020860837584529599, "epoch": 0.92, "step": 25790}
+{"loss": 0.591, "learning_rate": 0.00020857278443468975, "epoch": 0.92, "step": 25800}
+{"loss": 0.5814, "learning_rate": 0.0002085371930240835, "epoch": 0.92, "step": 25810}
+{"loss": 0.6186, "learning_rate": 0.00020850160161347729, "epoch": 0.92, "step": 25820}
+{"loss": 0.6398, "learning_rate": 0.00020846601020287102, "epoch": 0.92, "step": 25830}
+{"loss": 0.6231, "learning_rate": 0.00020843041879226476, "epoch": 0.92, "step": 25840}
+{"loss": 0.6087, "learning_rate": 0.00020839482738165856, "epoch": 0.92, "step": 25850}
+{"loss": 0.685, "learning_rate": 0.0002083592359710523, "epoch": 0.92, "step": 25860}
+{"loss": 0.5726, "learning_rate": 0.00020832364456044606, "epoch": 0.92, "step": 25870}
+{"loss": 0.5558, "learning_rate": 0.0002082880531498398, "epoch": 0.92, "step": 25880}
+{"loss": 0.6361, "learning_rate": 0.0002082524617392336, "epoch": 0.92, "step": 25890}
+{"loss": 0.7315, "learning_rate": 0.00020821687032862734, "epoch": 0.92, "step": 25900}
+{"loss": 0.7273, "learning_rate": 0.00020818127891802108, "epoch": 0.92, "step": 25910}
+{"loss": 0.6599, "learning_rate": 0.00020814568750741487, "epoch": 0.92, "step": 25920}
+{"loss": 0.6681, "learning_rate": 0.0002081100960968086, "epoch": 0.92, "step": 25930}
+{"loss": 0.6932, "learning_rate": 0.00020807450468620238, "epoch": 0.92, "step": 25940}
+{"loss": 0.6618, "learning_rate": 0.00020803891327559614, "epoch": 0.92, "step": 25950}
+{"loss": 0.6164, "learning_rate": 0.0002080033218649899, "epoch": 0.92, "step": 25960}
+{"loss": 0.6372, "learning_rate": 0.00020796773045438365, "epoch": 0.92, "step": 25970}
+{"loss": 0.6694, "learning_rate": 0.00020793213904377741, "epoch": 0.92, "step": 25980}
+{"loss": 0.5338, "learning_rate": 0.00020789654763317118, "epoch": 0.92, "step": 25990}
+{"loss": 0.7207, "learning_rate": 0.00020786095622256492, "epoch": 0.92, "step": 26000}
+{"loss": 0.5842, "learning_rate": 0.0002078253648119587, "epoch": 0.92, "step": 26010}
+{"loss": 0.576, "learning_rate": 0.00020778977340135245, "epoch": 0.92, "step": 26020}
+{"loss": 0.7333, "learning_rate": 0.00020775418199074622, "epoch": 0.93, "step": 26030}
+{"loss": 0.6898, "learning_rate": 0.00020771859058013996, "epoch": 0.93, "step": 26040}
+{"loss": 0.7037, "learning_rate": 0.00020768299916953375, "epoch": 0.93, "step": 26050}
+{"loss": 0.6515, "learning_rate": 0.0002076474077589275, "epoch": 0.93, "step": 26060}
+{"loss": 0.5971, "learning_rate": 0.00020761181634832126, "epoch": 0.93, "step": 26070}
+{"loss": 0.6318, "learning_rate": 0.000207576224937715, "epoch": 0.93, "step": 26080}
+{"loss": 0.8018, "learning_rate": 0.0002075406335271088, "epoch": 0.93, "step": 26090}
+{"loss": 0.7297, "learning_rate": 0.00020750504211650253, "epoch": 0.93, "step": 26100}
+{"loss": 0.6522, "learning_rate": 0.00020746945070589627, "epoch": 0.93, "step": 26110}
+{"loss": 0.6638, "learning_rate": 0.00020743385929529007, "epoch": 0.93, "step": 26120}
+{"loss": 0.6081, "learning_rate": 0.0002073982678846838, "epoch": 0.93, "step": 26130}
+{"loss": 0.7137, "learning_rate": 0.00020736267647407757, "epoch": 0.93, "step": 26140}
+{"loss": 0.6705, "learning_rate": 0.00020732708506347134, "epoch": 0.93, "step": 26150}
+{"loss": 0.6482, "learning_rate": 0.0002072914936528651, "epoch": 0.93, "step": 26160}
+{"loss": 0.5674, "learning_rate": 0.00020725590224225884, "epoch": 0.93, "step": 26170}
+{"loss": 0.6184, "learning_rate": 0.00020722031083165264, "epoch": 0.93, "step": 26180}
+{"loss": 0.6329, "learning_rate": 0.00020718471942104638, "epoch": 0.93, "step": 26190}
+{"loss": 0.5367, "learning_rate": 0.00020714912801044012, "epoch": 0.93, "step": 26200}
+{"loss": 0.6797, "learning_rate": 0.00020711353659983388, "epoch": 0.93, "step": 26210}
+{"loss": 0.6757, "learning_rate": 0.00020707794518922765, "epoch": 0.93, "step": 26220}
+{"loss": 0.5862, "learning_rate": 0.00020704235377862142, "epoch": 0.93, "step": 26230}
+{"loss": 0.6135, "learning_rate": 0.00020700676236801516, "epoch": 0.93, "step": 26240}
+{"loss": 0.7624, "learning_rate": 0.00020697117095740895, "epoch": 0.93, "step": 26250}
+{"loss": 0.6736, "learning_rate": 0.0002069355795468027, "epoch": 0.93, "step": 26260}
+{"loss": 0.5605, "learning_rate": 0.00020689998813619643, "epoch": 0.93, "step": 26270}
+{"loss": 0.7557, "learning_rate": 0.00020686439672559022, "epoch": 0.93, "step": 26280}
+{"loss": 0.51, "learning_rate": 0.00020682880531498396, "epoch": 0.93, "step": 26290}
+{"loss": 0.6603, "learning_rate": 0.00020679321390437773, "epoch": 0.93, "step": 26300}
+{"loss": 0.6667, "learning_rate": 0.00020675762249377147, "epoch": 0.94, "step": 26310}
+{"loss": 0.5928, "learning_rate": 0.00020672203108316526, "epoch": 0.94, "step": 26320}
+{"loss": 0.5362, "learning_rate": 0.000206686439672559, "epoch": 0.94, "step": 26330}
+{"loss": 0.7326, "learning_rate": 0.00020665084826195274, "epoch": 0.94, "step": 26340}
+{"loss": 0.5695, "learning_rate": 0.00020661525685134653, "epoch": 0.94, "step": 26350}
+{"loss": 0.7449, "learning_rate": 0.00020657966544074027, "epoch": 0.94, "step": 26360}
+{"loss": 0.6409, "learning_rate": 0.00020654407403013404, "epoch": 0.94, "step": 26370}
+{"loss": 0.6279, "learning_rate": 0.0002065084826195278, "epoch": 0.94, "step": 26380}
+{"loss": 0.6915, "learning_rate": 0.00020647289120892157, "epoch": 0.94, "step": 26390}
+{"loss": 0.6275, "learning_rate": 0.0002064372997983153, "epoch": 0.94, "step": 26400}
+{"loss": 0.6435, "learning_rate": 0.0002064017083877091, "epoch": 0.94, "step": 26410}
+{"loss": 0.5778, "learning_rate": 0.00020636611697710285, "epoch": 0.94, "step": 26420}
+{"loss": 0.7292, "learning_rate": 0.00020633052556649658, "epoch": 0.94, "step": 26430}
+{"loss": 0.5922, "learning_rate": 0.00020629493415589035, "epoch": 0.94, "step": 26440}
+{"loss": 0.6766, "learning_rate": 0.00020625934274528412, "epoch": 0.94, "step": 26450}
+{"loss": 0.5949, "learning_rate": 0.00020622375133467788, "epoch": 0.94, "step": 26460}
+{"loss": 0.7015, "learning_rate": 0.00020618815992407162, "epoch": 0.94, "step": 26470}
+{"loss": 0.5744, "learning_rate": 0.00020615256851346542, "epoch": 0.94, "step": 26480}
+{"loss": 0.862, "learning_rate": 0.00020611697710285916, "epoch": 0.94, "step": 26490}
+{"loss": 0.6688, "learning_rate": 0.0002060813856922529, "epoch": 0.94, "step": 26500}
+{"loss": 0.5885, "learning_rate": 0.0002060457942816467, "epoch": 0.94, "step": 26510}
+{"loss": 0.6128, "learning_rate": 0.00020601020287104043, "epoch": 0.94, "step": 26520}
+{"loss": 0.5724, "learning_rate": 0.0002059746114604342, "epoch": 0.94, "step": 26530}
+{"loss": 0.6691, "learning_rate": 0.00020593902004982794, "epoch": 0.94, "step": 26540}
+{"loss": 0.6181, "learning_rate": 0.00020590342863922173, "epoch": 0.94, "step": 26550}
+{"loss": 0.6309, "learning_rate": 0.00020586783722861547, "epoch": 0.94, "step": 26560}
+{"loss": 0.7534, "learning_rate": 0.00020583224581800924, "epoch": 0.94, "step": 26570}
+{"loss": 0.5758, "learning_rate": 0.000205796654407403, "epoch": 0.94, "step": 26580}
+{"loss": 0.6409, "learning_rate": 0.00020576106299679677, "epoch": 0.95, "step": 26590}
+{"loss": 0.6712, "learning_rate": 0.0002057254715861905, "epoch": 0.95, "step": 26600}
+{"loss": 0.721, "learning_rate": 0.00020568988017558427, "epoch": 0.95, "step": 26610}
+{"loss": 0.7174, "learning_rate": 0.00020565428876497804, "epoch": 0.95, "step": 26620}
+{"loss": 0.5943, "learning_rate": 0.00020561869735437178, "epoch": 0.95, "step": 26630}
+{"loss": 0.616, "learning_rate": 0.00020558310594376557, "epoch": 0.95, "step": 26640}
+{"loss": 0.6261, "learning_rate": 0.0002055475145331593, "epoch": 0.95, "step": 26650}
+{"loss": 0.7557, "learning_rate": 0.00020551192312255308, "epoch": 0.95, "step": 26660}
+{"loss": 0.7811, "learning_rate": 0.00020547633171194682, "epoch": 0.95, "step": 26670}
+{"loss": 0.6167, "learning_rate": 0.0002054407403013406, "epoch": 0.95, "step": 26680}
+{"loss": 0.738, "learning_rate": 0.00020540514889073435, "epoch": 0.95, "step": 26690}
+{"loss": 0.6525, "learning_rate": 0.0002053695574801281, "epoch": 0.95, "step": 26700}
+{"loss": 0.6053, "learning_rate": 0.00020533396606952189, "epoch": 0.95, "step": 26710}
+{"loss": 0.762, "learning_rate": 0.00020529837465891563, "epoch": 0.95, "step": 26720}
+{"loss": 0.6098, "learning_rate": 0.0002052627832483094, "epoch": 0.95, "step": 26730}
+{"loss": 0.6802, "learning_rate": 0.00020522719183770316, "epoch": 0.95, "step": 26740}
+{"loss": 0.6567, "learning_rate": 0.00020519160042709692, "epoch": 0.95, "step": 26750}
+{"loss": 0.6614, "learning_rate": 0.00020515600901649066, "epoch": 0.95, "step": 26760}
+{"loss": 0.7237, "learning_rate": 0.0002051204176058844, "epoch": 0.95, "step": 26770}
+{"loss": 0.6868, "learning_rate": 0.0002050848261952782, "epoch": 0.95, "step": 26780}
+{"loss": 0.7121, "learning_rate": 0.00020504923478467194, "epoch": 0.95, "step": 26790}
+{"loss": 0.7011, "learning_rate": 0.0002050136433740657, "epoch": 0.95, "step": 26800}
+{"loss": 0.6464, "learning_rate": 0.00020497805196345947, "epoch": 0.95, "step": 26810}
+{"loss": 0.742, "learning_rate": 0.00020494246055285324, "epoch": 0.95, "step": 26820}
+{"loss": 0.694, "learning_rate": 0.00020490686914224698, "epoch": 0.95, "step": 26830}
+{"loss": 0.6971, "learning_rate": 0.00020487127773164077, "epoch": 0.95, "step": 26840}
+{"loss": 0.7087, "learning_rate": 0.0002048356863210345, "epoch": 0.95, "step": 26850}
+{"loss": 0.6163, "learning_rate": 0.00020480009491042825, "epoch": 0.95, "step": 26860}
+{"loss": 0.6463, "learning_rate": 0.00020476450349982204, "epoch": 0.96, "step": 26870}
+{"loss": 0.787, "learning_rate": 0.00020472891208921578, "epoch": 0.96, "step": 26880}
+{"loss": 0.6716, "learning_rate": 0.00020469332067860955, "epoch": 0.96, "step": 26890}
+{"loss": 0.6185, "learning_rate": 0.0002046577292680033, "epoch": 0.96, "step": 26900}
+{"loss": 0.5922, "learning_rate": 0.00020462213785739708, "epoch": 0.96, "step": 26910}
+{"loss": 0.524, "learning_rate": 0.00020458654644679082, "epoch": 0.96, "step": 26920}
+{"loss": 0.6935, "learning_rate": 0.00020455095503618456, "epoch": 0.96, "step": 26930}
+{"loss": 0.605, "learning_rate": 0.00020451536362557835, "epoch": 0.96, "step": 26940}
+{"loss": 0.5761, "learning_rate": 0.0002044797722149721, "epoch": 0.96, "step": 26950}
+{"loss": 0.6525, "learning_rate": 0.00020444418080436586, "epoch": 0.96, "step": 26960}
+{"loss": 0.6534, "learning_rate": 0.00020440858939375963, "epoch": 0.96, "step": 26970}
+{"loss": 0.674, "learning_rate": 0.0002043729979831534, "epoch": 0.96, "step": 26980}
+{"loss": 0.5688, "learning_rate": 0.00020433740657254713, "epoch": 0.96, "step": 26990}
+{"loss": 0.6869, "learning_rate": 0.00020430181516194087, "epoch": 0.96, "step": 27000}
+{"loss": 0.7077, "learning_rate": 0.00020426622375133467, "epoch": 0.96, "step": 27010}
+{"loss": 0.6277, "learning_rate": 0.0002042306323407284, "epoch": 0.96, "step": 27020}
+{"loss": 0.6084, "learning_rate": 0.00020419504093012217, "epoch": 0.96, "step": 27030}
+{"loss": 0.6069, "learning_rate": 0.00020415944951951594, "epoch": 0.96, "step": 27040}
+{"loss": 0.7101, "learning_rate": 0.0002041238581089097, "epoch": 0.96, "step": 27050}
+{"loss": 0.7001, "learning_rate": 0.00020408826669830344, "epoch": 0.96, "step": 27060}
+{"loss": 0.7447, "learning_rate": 0.00020405267528769724, "epoch": 0.96, "step": 27070}
+{"loss": 0.6495, "learning_rate": 0.00020401708387709098, "epoch": 0.96, "step": 27080}
+{"loss": 0.6171, "learning_rate": 0.00020398149246648474, "epoch": 0.96, "step": 27090}
+{"loss": 0.5767, "learning_rate": 0.0002039459010558785, "epoch": 0.96, "step": 27100}
+{"loss": 0.6179, "learning_rate": 0.00020391030964527225, "epoch": 0.96, "step": 27110}
+{"loss": 0.6114, "learning_rate": 0.00020387471823466602, "epoch": 0.96, "step": 27120}
+{"loss": 0.6196, "learning_rate": 0.00020383912682405976, "epoch": 0.96, "step": 27130}
+{"loss": 0.5652, "learning_rate": 0.00020380353541345355, "epoch": 0.96, "step": 27140}
+{"loss": 0.7054, "learning_rate": 0.0002037679440028473, "epoch": 0.97, "step": 27150}
+{"loss": 0.691, "learning_rate": 0.00020373235259224106, "epoch": 0.97, "step": 27160}
+{"loss": 0.6268, "learning_rate": 0.00020369676118163482, "epoch": 0.97, "step": 27170}
+{"loss": 0.7375, "learning_rate": 0.0002036611697710286, "epoch": 0.97, "step": 27180}
+{"loss": 0.6059, "learning_rate": 0.00020362557836042233, "epoch": 0.97, "step": 27190}
+{"loss": 0.6291, "learning_rate": 0.00020358998694981612, "epoch": 0.97, "step": 27200}
+{"loss": 0.6086, "learning_rate": 0.00020355439553920986, "epoch": 0.97, "step": 27210}
+{"loss": 0.4827, "learning_rate": 0.0002035188041286036, "epoch": 0.97, "step": 27220}
+{"loss": 0.7278, "learning_rate": 0.00020348321271799737, "epoch": 0.97, "step": 27230}
+{"loss": 0.6589, "learning_rate": 0.00020344762130739113, "epoch": 0.97, "step": 27240}
+{"loss": 0.7108, "learning_rate": 0.0002034120298967849, "epoch": 0.97, "step": 27250}
+{"loss": 0.7147, "learning_rate": 0.00020337643848617864, "epoch": 0.97, "step": 27260}
+{"loss": 0.6623, "learning_rate": 0.00020334084707557243, "epoch": 0.97, "step": 27270}
+{"loss": 0.6269, "learning_rate": 0.00020330525566496617, "epoch": 0.97, "step": 27280}
+{"loss": 0.6308, "learning_rate": 0.0002032696642543599, "epoch": 0.97, "step": 27290}
+{"loss": 0.6481, "learning_rate": 0.0002032340728437537, "epoch": 0.97, "step": 27300}
+{"loss": 0.6844, "learning_rate": 0.00020319848143314745, "epoch": 0.97, "step": 27310}
+{"loss": 0.7158, "learning_rate": 0.0002031628900225412, "epoch": 0.97, "step": 27320}
+{"loss": 0.707, "learning_rate": 0.00020312729861193495, "epoch": 0.97, "step": 27330}
+{"loss": 0.6504, "learning_rate": 0.00020309170720132875, "epoch": 0.97, "step": 27340}
+{"loss": 0.5878, "learning_rate": 0.00020305611579072248, "epoch": 0.97, "step": 27350}
+{"loss": 0.6616, "learning_rate": 0.00020302052438011622, "epoch": 0.97, "step": 27360}
+{"loss": 0.6946, "learning_rate": 0.00020298493296951002, "epoch": 0.97, "step": 27370}
+{"loss": 0.705, "learning_rate": 0.00020294934155890376, "epoch": 0.97, "step": 27380}
+{"loss": 0.7303, "learning_rate": 0.00020291375014829752, "epoch": 0.97, "step": 27390}
+{"loss": 0.6954, "learning_rate": 0.0002028781587376913, "epoch": 0.97, "step": 27400}
+{"loss": 0.6319, "learning_rate": 0.00020284256732708506, "epoch": 0.97, "step": 27410}
+{"loss": 0.6644, "learning_rate": 0.0002028069759164788, "epoch": 0.97, "step": 27420}
+{"loss": 0.5741, "learning_rate": 0.0002027713845058726, "epoch": 0.98, "step": 27430}
+{"loss": 0.6206, "learning_rate": 0.00020273579309526633, "epoch": 0.98, "step": 27440}
+{"loss": 0.7001, "learning_rate": 0.00020270020168466007, "epoch": 0.98, "step": 27450}
+{"loss": 0.6392, "learning_rate": 0.00020266461027405384, "epoch": 0.98, "step": 27460}
+{"loss": 0.5602, "learning_rate": 0.0002026290188634476, "epoch": 0.98, "step": 27470}
+{"loss": 0.5764, "learning_rate": 0.00020259342745284137, "epoch": 0.98, "step": 27480}
+{"loss": 0.6606, "learning_rate": 0.0002025578360422351, "epoch": 0.98, "step": 27490}
+{"loss": 0.7072, "learning_rate": 0.0002025222446316289, "epoch": 0.98, "step": 27500}
+{"loss": 0.7065, "learning_rate": 0.00020248665322102264, "epoch": 0.98, "step": 27510}
+{"loss": 0.6665, "learning_rate": 0.00020245106181041638, "epoch": 0.98, "step": 27520}
+{"loss": 0.5677, "learning_rate": 0.00020241547039981017, "epoch": 0.98, "step": 27530}
+{"loss": 0.6295, "learning_rate": 0.00020237987898920391, "epoch": 0.98, "step": 27540}
+{"loss": 0.6355, "learning_rate": 0.00020234428757859768, "epoch": 0.98, "step": 27550}
+{"loss": 0.5665, "learning_rate": 0.00020230869616799142, "epoch": 0.98, "step": 27560}
+{"loss": 0.6433, "learning_rate": 0.00020227310475738521, "epoch": 0.98, "step": 27570}
+{"loss": 0.5624, "learning_rate": 0.00020223751334677895, "epoch": 0.98, "step": 27580}
+{"loss": 0.6971, "learning_rate": 0.00020220192193617272, "epoch": 0.98, "step": 27590}
+{"loss": 0.689, "learning_rate": 0.00020216633052556649, "epoch": 0.98, "step": 27600}
+{"loss": 0.6623, "learning_rate": 0.00020213073911496023, "epoch": 0.98, "step": 27610}
+{"loss": 0.771, "learning_rate": 0.000202095147704354, "epoch": 0.98, "step": 27620}
+{"loss": 0.6584, "learning_rate": 0.00020205955629374776, "epoch": 0.98, "step": 27630}
+{"loss": 0.7589, "learning_rate": 0.00020202396488314153, "epoch": 0.98, "step": 27640}
+{"loss": 0.5451, "learning_rate": 0.00020198837347253526, "epoch": 0.98, "step": 27650}
+{"loss": 0.6312, "learning_rate": 0.00020195278206192906, "epoch": 0.98, "step": 27660}
+{"loss": 0.588, "learning_rate": 0.0002019171906513228, "epoch": 0.98, "step": 27670}
+{"loss": 0.662, "learning_rate": 0.00020188159924071656, "epoch": 0.98, "step": 27680}
+{"loss": 0.551, "learning_rate": 0.0002018460078301103, "epoch": 0.98, "step": 27690}
+{"loss": 0.7277, "learning_rate": 0.0002018104164195041, "epoch": 0.98, "step": 27700}
+{"loss": 0.6379, "learning_rate": 0.00020177482500889784, "epoch": 0.99, "step": 27710}
+{"loss": 0.703, "learning_rate": 0.00020173923359829158, "epoch": 0.99, "step": 27720}
+{"loss": 0.6775, "learning_rate": 0.00020170364218768537, "epoch": 0.99, "step": 27730}
+{"loss": 0.6896, "learning_rate": 0.0002016680507770791, "epoch": 0.99, "step": 27740}
+{"loss": 0.7108, "learning_rate": 0.00020163245936647288, "epoch": 0.99, "step": 27750}
+{"loss": 0.627, "learning_rate": 0.00020159686795586664, "epoch": 0.99, "step": 27760}
+{"loss": 0.6355, "learning_rate": 0.0002015612765452604, "epoch": 0.99, "step": 27770}
+{"loss": 0.5611, "learning_rate": 0.00020152568513465415, "epoch": 0.99, "step": 27780}
+{"loss": 0.5786, "learning_rate": 0.0002014900937240479, "epoch": 0.99, "step": 27790}
+{"loss": 0.7293, "learning_rate": 0.00020145450231344168, "epoch": 0.99, "step": 27800}
+{"loss": 0.5865, "learning_rate": 0.00020141891090283542, "epoch": 0.99, "step": 27810}
+{"loss": 0.6886, "learning_rate": 0.0002013833194922292, "epoch": 0.99, "step": 27820}
+{"loss": 0.5695, "learning_rate": 0.00020134772808162295, "epoch": 0.99, "step": 27830}
+{"loss": 0.7456, "learning_rate": 0.00020131213667101672, "epoch": 0.99, "step": 27840}
+{"loss": 0.7422, "learning_rate": 0.00020127654526041046, "epoch": 0.99, "step": 27850}
+{"loss": 0.6441, "learning_rate": 0.00020124095384980425, "epoch": 0.99, "step": 27860}
+{"loss": 0.6496, "learning_rate": 0.000201205362439198, "epoch": 0.99, "step": 27870}
+{"loss": 0.5499, "learning_rate": 0.00020116977102859173, "epoch": 0.99, "step": 27880}
+{"loss": 0.5501, "learning_rate": 0.00020113417961798553, "epoch": 0.99, "step": 27890}
+{"loss": 0.6419, "learning_rate": 0.00020109858820737927, "epoch": 0.99, "step": 27900}
+{"loss": 0.6405, "learning_rate": 0.00020106299679677303, "epoch": 0.99, "step": 27910}
+{"loss": 0.5286, "learning_rate": 0.00020102740538616677, "epoch": 0.99, "step": 27920}
+{"loss": 0.6556, "learning_rate": 0.00020099181397556057, "epoch": 0.99, "step": 27930}
+{"loss": 0.6558, "learning_rate": 0.0002009562225649543, "epoch": 0.99, "step": 27940}
+{"loss": 0.5947, "learning_rate": 0.00020092063115434804, "epoch": 0.99, "step": 27950}
+{"loss": 0.6813, "learning_rate": 0.00020088503974374184, "epoch": 0.99, "step": 27960}
+{"loss": 0.7141, "learning_rate": 0.00020084944833313558, "epoch": 0.99, "step": 27970}
+{"loss": 0.6779, "learning_rate": 0.00020081385692252934, "epoch": 0.99, "step": 27980}
+{"loss": 0.6857, "learning_rate": 0.0002007782655119231, "epoch": 1.0, "step": 27990}
+{"loss": 0.662, "learning_rate": 0.00020074267410131688, "epoch": 1.0, "step": 28000}
+{"loss": 0.5596, "learning_rate": 0.00020070708269071062, "epoch": 1.0, "step": 28010}
+{"loss": 0.6393, "learning_rate": 0.00020067149128010436, "epoch": 1.0, "step": 28020}
+{"loss": 0.7231, "learning_rate": 0.00020063589986949815, "epoch": 1.0, "step": 28030}
+{"loss": 0.6233, "learning_rate": 0.0002006003084588919, "epoch": 1.0, "step": 28040}
+{"loss": 0.5444, "learning_rate": 0.00020056471704828566, "epoch": 1.0, "step": 28050}
+{"loss": 0.5914, "learning_rate": 0.00020052912563767942, "epoch": 1.0, "step": 28060}
+{"loss": 0.5731, "learning_rate": 0.0002004935342270732, "epoch": 1.0, "step": 28070}
+{"loss": 0.606, "learning_rate": 0.00020045794281646693, "epoch": 1.0, "step": 28080}
+{"loss": 0.6294, "learning_rate": 0.00020042235140586072, "epoch": 1.0, "step": 28090}
+{"loss": 0.605, "learning_rate": 0.00020038675999525446, "epoch": 1.0, "step": 28100}
+{"loss": 0.7581, "learning_rate": 0.0002003511685846482, "epoch": 1.0, "step": 28110}
+{"loss": 0.5733, "learning_rate": 0.000200315577174042, "epoch": 1.0, "step": 28120}
+{"loss": 0.7206, "learning_rate": 0.00020027998576343573, "epoch": 1.0, "step": 28130}
+{"loss": 0.5966, "learning_rate": 0.0002002443943528295, "epoch": 1.0, "step": 28140}
+{"loss": 0.59, "learning_rate": 0.00020020880294222324, "epoch": 1.0, "step": 28150}
+{"loss": 0.5038, "learning_rate": 0.00020017321153161703, "epoch": 1.0, "step": 28160}
+{"loss": 0.5659, "learning_rate": 0.00020013762012101077, "epoch": 1.0, "step": 28170}
+{"loss": 0.6425, "learning_rate": 0.00020010202871040454, "epoch": 1.0, "step": 28180}
+{"loss": 0.5297, "learning_rate": 0.0002000664372997983, "epoch": 1.0, "step": 28190}
+{"loss": 0.6559, "learning_rate": 0.00020003084588919205, "epoch": 1.0, "step": 28200}
+{"loss": 0.7653, "learning_rate": 0.0001999952544785858, "epoch": 1.0, "step": 28210}
+{"loss": 0.6657, "learning_rate": 0.00019995966306797958, "epoch": 1.0, "step": 28220}
+{"loss": 0.6222, "learning_rate": 0.00019992407165737335, "epoch": 1.0, "step": 28230}
+{"loss": 0.5282, "learning_rate": 0.00019988848024676709, "epoch": 1.0, "step": 28240}
+{"loss": 0.651, "learning_rate": 0.00019985288883616085, "epoch": 1.0, "step": 28250}
+{"loss": 0.5301, "learning_rate": 0.00019981729742555462, "epoch": 1.0, "step": 28260}
+{"loss": 0.7477, "learning_rate": 0.00019978170601494838, "epoch": 1.0, "step": 28270}
+{"loss": 0.6336, "learning_rate": 0.00019974611460434212, "epoch": 1.01, "step": 28280}
+{"loss": 0.5094, "learning_rate": 0.00019971052319373592, "epoch": 1.01, "step": 28290}
+{"loss": 0.6093, "learning_rate": 0.00019967493178312966, "epoch": 1.01, "step": 28300}
+{"loss": 0.5328, "learning_rate": 0.0001996393403725234, "epoch": 1.01, "step": 28310}
+{"loss": 0.6482, "learning_rate": 0.0001996037489619172, "epoch": 1.01, "step": 28320}
+{"loss": 0.582, "learning_rate": 0.00019956815755131093, "epoch": 1.01, "step": 28330}
+{"loss": 0.6296, "learning_rate": 0.0001995325661407047, "epoch": 1.01, "step": 28340}
+{"loss": 0.6128, "learning_rate": 0.00019949697473009844, "epoch": 1.01, "step": 28350}
+{"loss": 0.6229, "learning_rate": 0.00019946138331949223, "epoch": 1.01, "step": 28360}
+{"loss": 0.6707, "learning_rate": 0.00019942579190888597, "epoch": 1.01, "step": 28370}
+{"loss": 0.5611, "learning_rate": 0.0001993902004982797, "epoch": 1.01, "step": 28380}
+{"loss": 0.5661, "learning_rate": 0.0001993546090876735, "epoch": 1.01, "step": 28390}
+{"loss": 0.5204, "learning_rate": 0.00019931901767706724, "epoch": 1.01, "step": 28400}
+{"loss": 0.657, "learning_rate": 0.000199283426266461, "epoch": 1.01, "step": 28410}
+{"loss": 0.5813, "learning_rate": 0.00019924783485585477, "epoch": 1.01, "step": 28420}
+{"loss": 0.6144, "learning_rate": 0.00019921224344524854, "epoch": 1.01, "step": 28430}
+{"loss": 0.5808, "learning_rate": 0.00019917665203464228, "epoch": 1.01, "step": 28440}
+{"loss": 0.6813, "learning_rate": 0.00019914106062403607, "epoch": 1.01, "step": 28450}
+{"loss": 0.6955, "learning_rate": 0.00019910546921342981, "epoch": 1.01, "step": 28460}
+{"loss": 0.6562, "learning_rate": 0.00019906987780282355, "epoch": 1.01, "step": 28470}
+{"loss": 0.7348, "learning_rate": 0.00019903428639221732, "epoch": 1.01, "step": 28480}
+{"loss": 0.6497, "learning_rate": 0.0001989986949816111, "epoch": 1.01, "step": 28490}
+{"loss": 0.5262, "learning_rate": 0.00019896310357100485, "epoch": 1.01, "step": 28500}
+{"loss": 0.6663, "learning_rate": 0.0001989275121603986, "epoch": 1.01, "step": 28510}
+{"loss": 0.6218, "learning_rate": 0.00019889192074979239, "epoch": 1.01, "step": 28520}
+{"loss": 0.6694, "learning_rate": 0.00019885632933918613, "epoch": 1.01, "step": 28530}
+{"loss": 0.6031, "learning_rate": 0.00019882073792857987, "epoch": 1.01, "step": 28540}
+{"loss": 0.6519, "learning_rate": 0.00019878514651797366, "epoch": 1.01, "step": 28550}
+{"loss": 0.7603, "learning_rate": 0.0001987495551073674, "epoch": 1.02, "step": 28560}
+{"loss": 0.553, "learning_rate": 0.00019871396369676116, "epoch": 1.02, "step": 28570}
+{"loss": 0.5838, "learning_rate": 0.0001986783722861549, "epoch": 1.02, "step": 28580}
+{"loss": 0.6756, "learning_rate": 0.0001986427808755487, "epoch": 1.02, "step": 28590}
+{"loss": 0.5814, "learning_rate": 0.00019860718946494244, "epoch": 1.02, "step": 28600}
+{"loss": 0.6594, "learning_rate": 0.00019857159805433618, "epoch": 1.02, "step": 28610}
+{"loss": 0.6274, "learning_rate": 0.00019853600664372997, "epoch": 1.02, "step": 28620}
+{"loss": 0.5459, "learning_rate": 0.0001985004152331237, "epoch": 1.02, "step": 28630}
+{"loss": 0.6561, "learning_rate": 0.00019846482382251748, "epoch": 1.02, "step": 28640}
+{"loss": 0.5954, "learning_rate": 0.00019842923241191124, "epoch": 1.02, "step": 28650}
+{"loss": 0.6076, "learning_rate": 0.000198393641001305, "epoch": 1.02, "step": 28660}
+{"loss": 0.5277, "learning_rate": 0.00019835804959069875, "epoch": 1.02, "step": 28670}
+{"loss": 0.7147, "learning_rate": 0.00019832245818009254, "epoch": 1.02, "step": 28680}
+{"loss": 0.5694, "learning_rate": 0.00019828686676948628, "epoch": 1.02, "step": 28690}
+{"loss": 0.6536, "learning_rate": 0.00019825127535888002, "epoch": 1.02, "step": 28700}
+{"loss": 0.7101, "learning_rate": 0.0001982156839482738, "epoch": 1.02, "step": 28710}
+{"loss": 0.563, "learning_rate": 0.00019818009253766755, "epoch": 1.02, "step": 28720}
+{"loss": 0.5785, "learning_rate": 0.00019814450112706132, "epoch": 1.02, "step": 28730}
+{"loss": 0.5594, "learning_rate": 0.00019810890971645506, "epoch": 1.02, "step": 28740}
+{"loss": 0.5593, "learning_rate": 0.00019807331830584885, "epoch": 1.02, "step": 28750}
+{"loss": 0.6456, "learning_rate": 0.0001980377268952426, "epoch": 1.02, "step": 28760}
+{"loss": 0.6331, "learning_rate": 0.00019800213548463636, "epoch": 1.02, "step": 28770}
+{"loss": 0.6078, "learning_rate": 0.00019796654407403013, "epoch": 1.02, "step": 28780}
+{"loss": 0.6091, "learning_rate": 0.0001979309526634239, "epoch": 1.02, "step": 28790}
+{"loss": 0.5555, "learning_rate": 0.00019789536125281763, "epoch": 1.02, "step": 28800}
+{"loss": 0.652, "learning_rate": 0.00019785976984221137, "epoch": 1.02, "step": 28810}
+{"loss": 0.5708, "learning_rate": 0.00019782417843160517, "epoch": 1.02, "step": 28820}
+{"loss": 0.554, "learning_rate": 0.0001977885870209989, "epoch": 1.02, "step": 28830}
+{"loss": 0.5766, "learning_rate": 0.00019775299561039267, "epoch": 1.03, "step": 28840}
+{"loss": 0.627, "learning_rate": 0.00019771740419978644, "epoch": 1.03, "step": 28850}
+{"loss": 0.5692, "learning_rate": 0.0001976818127891802, "epoch": 1.03, "step": 28860}
+{"loss": 0.6086, "learning_rate": 0.00019764622137857394, "epoch": 1.03, "step": 28870}
+{"loss": 0.6443, "learning_rate": 0.00019761062996796774, "epoch": 1.03, "step": 28880}
+{"loss": 0.5224, "learning_rate": 0.00019757503855736148, "epoch": 1.03, "step": 28890}
+{"loss": 0.6631, "learning_rate": 0.00019753944714675522, "epoch": 1.03, "step": 28900}
+{"loss": 0.6056, "learning_rate": 0.000197503855736149, "epoch": 1.03, "step": 28910}
+{"loss": 0.6264, "learning_rate": 0.00019746826432554275, "epoch": 1.03, "step": 28920}
+{"loss": 0.5449, "learning_rate": 0.00019743267291493652, "epoch": 1.03, "step": 28930}
+{"loss": 0.5239, "learning_rate": 0.00019739708150433026, "epoch": 1.03, "step": 28940}
+{"loss": 0.5933, "learning_rate": 0.00019736149009372405, "epoch": 1.03, "step": 28950}
+{"loss": 0.6511, "learning_rate": 0.0001973258986831178, "epoch": 1.03, "step": 28960}
+{"loss": 0.5593, "learning_rate": 0.00019729030727251153, "epoch": 1.03, "step": 28970}
+{"loss": 0.5306, "learning_rate": 0.00019725471586190532, "epoch": 1.03, "step": 28980}
+{"loss": 0.5435, "learning_rate": 0.00019721912445129906, "epoch": 1.03, "step": 28990}
+{"loss": 0.6044, "learning_rate": 0.00019718353304069283, "epoch": 1.03, "step": 29000}
+{"loss": 0.5722, "learning_rate": 0.0001971479416300866, "epoch": 1.03, "step": 29010}
+{"loss": 0.6026, "learning_rate": 0.00019711235021948036, "epoch": 1.03, "step": 29020}
+{"loss": 0.6134, "learning_rate": 0.0001970767588088741, "epoch": 1.03, "step": 29030}
+{"loss": 0.5894, "learning_rate": 0.00019704116739826784, "epoch": 1.03, "step": 29040}
+{"loss": 0.6285, "learning_rate": 0.00019700557598766163, "epoch": 1.03, "step": 29050}
+{"loss": 0.6018, "learning_rate": 0.00019696998457705537, "epoch": 1.03, "step": 29060}
+{"loss": 0.5791, "learning_rate": 0.00019693439316644914, "epoch": 1.03, "step": 29070}
+{"loss": 0.6415, "learning_rate": 0.0001968988017558429, "epoch": 1.03, "step": 29080}
+{"loss": 0.8141, "learning_rate": 0.00019686321034523667, "epoch": 1.03, "step": 29090}
+{"loss": 0.5848, "learning_rate": 0.0001968276189346304, "epoch": 1.03, "step": 29100}
+{"loss": 0.6386, "learning_rate": 0.0001967920275240242, "epoch": 1.03, "step": 29110}
+{"loss": 0.6422, "learning_rate": 0.00019675643611341795, "epoch": 1.04, "step": 29120}
+{"loss": 0.6203, "learning_rate": 0.00019672084470281169, "epoch": 1.04, "step": 29130}
+{"loss": 0.7088, "learning_rate": 0.00019668525329220548, "epoch": 1.04, "step": 29140}
+{"loss": 0.6892, "learning_rate": 0.00019664966188159922, "epoch": 1.04, "step": 29150}
+{"loss": 0.5799, "learning_rate": 0.00019661407047099299, "epoch": 1.04, "step": 29160}
+{"loss": 0.6491, "learning_rate": 0.00019657847906038672, "epoch": 1.04, "step": 29170}
+{"loss": 0.5799, "learning_rate": 0.00019654288764978052, "epoch": 1.04, "step": 29180}
+{"loss": 0.6544, "learning_rate": 0.00019650729623917426, "epoch": 1.04, "step": 29190}
+{"loss": 0.4886, "learning_rate": 0.000196471704828568, "epoch": 1.04, "step": 29200}
+{"loss": 0.7112, "learning_rate": 0.0001964361134179618, "epoch": 1.04, "step": 29210}
+{"loss": 0.608, "learning_rate": 0.00019640052200735553, "epoch": 1.04, "step": 29220}
+{"loss": 0.5511, "learning_rate": 0.0001963649305967493, "epoch": 1.04, "step": 29230}
+{"loss": 0.5738, "learning_rate": 0.00019632933918614306, "epoch": 1.04, "step": 29240}
+{"loss": 0.6637, "learning_rate": 0.00019629374777553683, "epoch": 1.04, "step": 29250}
+{"loss": 0.677, "learning_rate": 0.00019625815636493057, "epoch": 1.04, "step": 29260}
+{"loss": 0.6311, "learning_rate": 0.00019622256495432434, "epoch": 1.04, "step": 29270}
+{"loss": 0.7086, "learning_rate": 0.0001961869735437181, "epoch": 1.04, "step": 29280}
+{"loss": 0.6743, "learning_rate": 0.00019615138213311187, "epoch": 1.04, "step": 29290}
+{"loss": 0.5836, "learning_rate": 0.0001961157907225056, "epoch": 1.04, "step": 29300}
+{"loss": 0.6241, "learning_rate": 0.00019608019931189938, "epoch": 1.04, "step": 29310}
+{"loss": 0.5797, "learning_rate": 0.00019604460790129314, "epoch": 1.04, "step": 29320}
+{"loss": 0.7705, "learning_rate": 0.00019600901649068688, "epoch": 1.04, "step": 29330}
+{"loss": 0.597, "learning_rate": 0.00019597342508008067, "epoch": 1.04, "step": 29340}
+{"loss": 0.6414, "learning_rate": 0.00019593783366947441, "epoch": 1.04, "step": 29350}
+{"loss": 0.5742, "learning_rate": 0.00019590224225886818, "epoch": 1.04, "step": 29360}
+{"loss": 0.6124, "learning_rate": 0.00019587020998932257, "epoch": 1.04, "step": 29370}
+{"loss": 0.6807, "learning_rate": 0.0001958346185787163, "epoch": 1.04, "step": 29380}
+{"loss": 0.7224, "learning_rate": 0.0001957990271681101, "epoch": 1.04, "step": 29390}
+{"loss": 0.6915, "learning_rate": 0.00019576343575750384, "epoch": 1.05, "step": 29400}
+{"loss": 0.5763, "learning_rate": 0.00019572784434689758, "epoch": 1.05, "step": 29410}
+{"loss": 0.5492, "learning_rate": 0.00019569225293629137, "epoch": 1.05, "step": 29420}
+{"loss": 0.6291, "learning_rate": 0.0001956566615256851, "epoch": 1.05, "step": 29430}
+{"loss": 0.6692, "learning_rate": 0.00019562107011507888, "epoch": 1.05, "step": 29440}
+{"loss": 0.6334, "learning_rate": 0.00019558547870447265, "epoch": 1.05, "step": 29450}
+{"loss": 0.5618, "learning_rate": 0.0001955498872938664, "epoch": 1.05, "step": 29460}
+{"loss": 0.669, "learning_rate": 0.00019551429588326015, "epoch": 1.05, "step": 29470}
+{"loss": 0.5792, "learning_rate": 0.0001954787044726539, "epoch": 1.05, "step": 29480}
+{"loss": 0.5664, "learning_rate": 0.00019544311306204769, "epoch": 1.05, "step": 29490}
+{"loss": 0.6126, "learning_rate": 0.00019540752165144142, "epoch": 1.05, "step": 29500}
+{"loss": 0.5098, "learning_rate": 0.0001953719302408352, "epoch": 1.05, "step": 29510}
+{"loss": 0.5635, "learning_rate": 0.00019533633883022896, "epoch": 1.05, "step": 29520}
+{"loss": 0.5499, "learning_rate": 0.00019530074741962272, "epoch": 1.05, "step": 29530}
+{"loss": 0.5739, "learning_rate": 0.00019526515600901646, "epoch": 1.05, "step": 29540}
+{"loss": 0.6652, "learning_rate": 0.00019522956459841026, "epoch": 1.05, "step": 29550}
+{"loss": 0.599, "learning_rate": 0.000195193973187804, "epoch": 1.05, "step": 29560}
+{"loss": 0.666, "learning_rate": 0.00019515838177719774, "epoch": 1.05, "step": 29570}
+{"loss": 0.6752, "learning_rate": 0.0001951227903665915, "epoch": 1.05, "step": 29580}
+{"loss": 0.6749, "learning_rate": 0.00019508719895598527, "epoch": 1.05, "step": 29590}
+{"loss": 0.5859, "learning_rate": 0.00019505160754537904, "epoch": 1.05, "step": 29600}
+{"loss": 0.6023, "learning_rate": 0.00019501601613477278, "epoch": 1.05, "step": 29610}
+{"loss": 0.5729, "learning_rate": 0.00019498042472416657, "epoch": 1.05, "step": 29620}
+{"loss": 0.5465, "learning_rate": 0.0001949448333135603, "epoch": 1.05, "step": 29630}
+{"loss": 0.6709, "learning_rate": 0.00019490924190295405, "epoch": 1.05, "step": 29640}
+{"loss": 0.6552, "learning_rate": 0.00019487365049234784, "epoch": 1.05, "step": 29650}
+{"loss": 0.5259, "learning_rate": 0.00019483805908174158, "epoch": 1.05, "step": 29660}
+{"loss": 0.5458, "learning_rate": 0.00019480246767113535, "epoch": 1.05, "step": 29670}
+{"loss": 0.5634, "learning_rate": 0.0001947668762605291, "epoch": 1.06, "step": 29680}
+{"loss": 0.5401, "learning_rate": 0.00019473128484992288, "epoch": 1.06, "step": 29690}
+{"loss": 0.5727, "learning_rate": 0.00019469569343931662, "epoch": 1.06, "step": 29700}
+{"loss": 0.5539, "learning_rate": 0.0001946601020287104, "epoch": 1.06, "step": 29710}
+{"loss": 0.6099, "learning_rate": 0.00019462451061810415, "epoch": 1.06, "step": 29720}
+{"loss": 0.6921, "learning_rate": 0.0001945889192074979, "epoch": 1.06, "step": 29730}
+{"loss": 0.6187, "learning_rate": 0.00019455332779689166, "epoch": 1.06, "step": 29740}
+{"loss": 0.6416, "learning_rate": 0.00019451773638628543, "epoch": 1.06, "step": 29750}
+{"loss": 0.6761, "learning_rate": 0.0001944821449756792, "epoch": 1.06, "step": 29760}
+{"loss": 0.6494, "learning_rate": 0.00019444655356507293, "epoch": 1.06, "step": 29770}
+{"loss": 0.6762, "learning_rate": 0.00019441096215446673, "epoch": 1.06, "step": 29780}
+{"loss": 0.6592, "learning_rate": 0.00019437537074386047, "epoch": 1.06, "step": 29790}
+{"loss": 0.65, "learning_rate": 0.00019433977933325423, "epoch": 1.06, "step": 29800}
+{"loss": 0.6523, "learning_rate": 0.00019430418792264797, "epoch": 1.06, "step": 29810}
+{"loss": 0.6337, "learning_rate": 0.00019426859651204177, "epoch": 1.06, "step": 29820}
+{"loss": 0.5405, "learning_rate": 0.0001942330051014355, "epoch": 1.06, "step": 29830}
+{"loss": 0.6695, "learning_rate": 0.00019419741369082924, "epoch": 1.06, "step": 29840}
+{"loss": 0.5708, "learning_rate": 0.00019416182228022304, "epoch": 1.06, "step": 29850}
+{"loss": 0.6517, "learning_rate": 0.00019412623086961678, "epoch": 1.06, "step": 29860}
+{"loss": 0.6473, "learning_rate": 0.00019409063945901054, "epoch": 1.06, "step": 29870}
+{"loss": 0.6628, "learning_rate": 0.0001940550480484043, "epoch": 1.06, "step": 29880}
+{"loss": 0.592, "learning_rate": 0.00019401945663779808, "epoch": 1.06, "step": 29890}
+{"loss": 0.6215, "learning_rate": 0.00019398386522719182, "epoch": 1.06, "step": 29900}
+{"loss": 0.5818, "learning_rate": 0.00019394827381658556, "epoch": 1.06, "step": 29910}
+{"loss": 0.5959, "learning_rate": 0.00019391268240597935, "epoch": 1.06, "step": 29920}
+{"loss": 0.5689, "learning_rate": 0.0001938770909953731, "epoch": 1.06, "step": 29930}
+{"loss": 0.5582, "learning_rate": 0.00019384149958476686, "epoch": 1.06, "step": 29940}
+{"loss": 0.5278, "learning_rate": 0.00019380590817416062, "epoch": 1.06, "step": 29950}
+{"loss": 0.5955, "learning_rate": 0.0001937703167635544, "epoch": 1.07, "step": 29960}
+{"loss": 0.607, "learning_rate": 0.00019373472535294813, "epoch": 1.07, "step": 29970}
+{"loss": 0.7097, "learning_rate": 0.00019369913394234192, "epoch": 1.07, "step": 29980}
+{"loss": 0.5955, "learning_rate": 0.00019366354253173566, "epoch": 1.07, "step": 29990}
+{"loss": 0.6152, "learning_rate": 0.0001936279511211294, "epoch": 1.07, "step": 30000}
+{"loss": 0.6122, "learning_rate": 0.0001935923597105232, "epoch": 1.07, "step": 30010}
+{"loss": 0.7045, "learning_rate": 0.00019355676829991693, "epoch": 1.07, "step": 30020}
+{"loss": 0.6079, "learning_rate": 0.0001935211768893107, "epoch": 1.07, "step": 30030}
+{"loss": 0.6126, "learning_rate": 0.00019348558547870444, "epoch": 1.07, "step": 30040}
+{"loss": 0.5262, "learning_rate": 0.00019344999406809823, "epoch": 1.07, "step": 30050}
+{"loss": 0.6714, "learning_rate": 0.00019341440265749197, "epoch": 1.07, "step": 30060}
+{"loss": 0.6276, "learning_rate": 0.0001933788112468857, "epoch": 1.07, "step": 30070}
+{"loss": 0.5706, "learning_rate": 0.0001933432198362795, "epoch": 1.07, "step": 30080}
+{"loss": 0.5729, "learning_rate": 0.00019330762842567325, "epoch": 1.07, "step": 30090}
+{"loss": 0.6276, "learning_rate": 0.000193272037015067, "epoch": 1.07, "step": 30100}
+{"loss": 0.5996, "learning_rate": 0.00019323644560446078, "epoch": 1.07, "step": 30110}
+{"loss": 0.5797, "learning_rate": 0.00019320085419385455, "epoch": 1.07, "step": 30120}
+{"loss": 0.5938, "learning_rate": 0.00019316526278324828, "epoch": 1.07, "step": 30130}
+{"loss": 0.6318, "learning_rate": 0.00019312967137264202, "epoch": 1.07, "step": 30140}
+{"loss": 0.5628, "learning_rate": 0.00019309407996203582, "epoch": 1.07, "step": 30150}
+{"loss": 0.536, "learning_rate": 0.00019305848855142956, "epoch": 1.07, "step": 30160}
+{"loss": 0.6441, "learning_rate": 0.00019302289714082332, "epoch": 1.07, "step": 30170}
+{"loss": 0.5948, "learning_rate": 0.0001929873057302171, "epoch": 1.07, "step": 30180}
+{"loss": 0.6447, "learning_rate": 0.00019295171431961086, "epoch": 1.07, "step": 30190}
+{"loss": 0.5741, "learning_rate": 0.0001929161229090046, "epoch": 1.07, "step": 30200}
+{"loss": 0.5729, "learning_rate": 0.0001928805314983984, "epoch": 1.07, "step": 30210}
+{"loss": 0.6507, "learning_rate": 0.00019284494008779213, "epoch": 1.07, "step": 30220}
+{"loss": 0.6223, "learning_rate": 0.00019280934867718587, "epoch": 1.07, "step": 30230}
+{"loss": 0.6154, "learning_rate": 0.00019277375726657966, "epoch": 1.08, "step": 30240}
+{"loss": 0.6246, "learning_rate": 0.0001927381658559734, "epoch": 1.08, "step": 30250}
+{"loss": 0.6071, "learning_rate": 0.00019270257444536717, "epoch": 1.08, "step": 30260}
+{"loss": 0.6656, "learning_rate": 0.0001926669830347609, "epoch": 1.08, "step": 30270}
+{"loss": 0.6727, "learning_rate": 0.0001926313916241547, "epoch": 1.08, "step": 30280}
+{"loss": 0.6625, "learning_rate": 0.00019259580021354844, "epoch": 1.08, "step": 30290}
+{"loss": 0.5885, "learning_rate": 0.0001925602088029422, "epoch": 1.08, "step": 30300}
+{"loss": 0.6322, "learning_rate": 0.00019252461739233597, "epoch": 1.08, "step": 30310}
+{"loss": 0.5777, "learning_rate": 0.00019248902598172974, "epoch": 1.08, "step": 30320}
+{"loss": 0.5824, "learning_rate": 0.00019245343457112348, "epoch": 1.08, "step": 30330}
+{"loss": 0.7026, "learning_rate": 0.00019241784316051725, "epoch": 1.08, "step": 30340}
+{"loss": 0.6116, "learning_rate": 0.000192382251749911, "epoch": 1.08, "step": 30350}
+{"loss": 0.573, "learning_rate": 0.00019234666033930475, "epoch": 1.08, "step": 30360}
+{"loss": 0.5644, "learning_rate": 0.00019231106892869852, "epoch": 1.08, "step": 30370}
+{"loss": 0.516, "learning_rate": 0.00019227547751809229, "epoch": 1.08, "step": 30380}
+{"loss": 0.6469, "learning_rate": 0.00019223988610748605, "epoch": 1.08, "step": 30390}
+{"loss": 0.5876, "learning_rate": 0.0001922042946968798, "epoch": 1.08, "step": 30400}
+{"loss": 0.6664, "learning_rate": 0.00019216870328627359, "epoch": 1.08, "step": 30410}
+{"loss": 0.6819, "learning_rate": 0.00019213311187566732, "epoch": 1.08, "step": 30420}
+{"loss": 0.6065, "learning_rate": 0.00019209752046506106, "epoch": 1.08, "step": 30430}
+{"loss": 0.5705, "learning_rate": 0.00019206192905445486, "epoch": 1.08, "step": 30440}
+{"loss": 0.596, "learning_rate": 0.0001920263376438486, "epoch": 1.08, "step": 30450}
+{"loss": 0.6182, "learning_rate": 0.00019199074623324236, "epoch": 1.08, "step": 30460}
+{"loss": 0.6622, "learning_rate": 0.00019195515482263613, "epoch": 1.08, "step": 30470}
+{"loss": 0.6638, "learning_rate": 0.0001919195634120299, "epoch": 1.08, "step": 30480}
+{"loss": 0.7151, "learning_rate": 0.00019188397200142364, "epoch": 1.08, "step": 30490}
+{"loss": 0.5788, "learning_rate": 0.00019184838059081738, "epoch": 1.08, "step": 30500}
+{"loss": 0.6483, "learning_rate": 0.00019181278918021117, "epoch": 1.08, "step": 30510}
+{"loss": 0.5185, "learning_rate": 0.0001917771977696049, "epoch": 1.08, "step": 30520}
+{"loss": 0.6717, "learning_rate": 0.00019174160635899868, "epoch": 1.09, "step": 30530}
+{"loss": 0.6547, "learning_rate": 0.00019170601494839244, "epoch": 1.09, "step": 30540}
+{"loss": 0.6774, "learning_rate": 0.0001916704235377862, "epoch": 1.09, "step": 30550}
+{"loss": 0.595, "learning_rate": 0.00019163483212717995, "epoch": 1.09, "step": 30560}
+{"loss": 0.6523, "learning_rate": 0.00019159924071657374, "epoch": 1.09, "step": 30570}
+{"loss": 0.5798, "learning_rate": 0.00019156364930596748, "epoch": 1.09, "step": 30580}
+{"loss": 0.5794, "learning_rate": 0.00019152805789536122, "epoch": 1.09, "step": 30590}
+{"loss": 0.6824, "learning_rate": 0.000191492466484755, "epoch": 1.09, "step": 30600}
+{"loss": 0.6457, "learning_rate": 0.00019145687507414875, "epoch": 1.09, "step": 30610}
+{"loss": 0.5968, "learning_rate": 0.00019142128366354252, "epoch": 1.09, "step": 30620}
+{"loss": 0.5473, "learning_rate": 0.00019138569225293626, "epoch": 1.09, "step": 30630}
+{"loss": 0.6169, "learning_rate": 0.00019135010084233005, "epoch": 1.09, "step": 30640}
+{"loss": 0.6106, "learning_rate": 0.0001913145094317238, "epoch": 1.09, "step": 30650}
+{"loss": 0.609, "learning_rate": 0.00019127891802111753, "epoch": 1.09, "step": 30660}
+{"loss": 0.5997, "learning_rate": 0.00019124332661051133, "epoch": 1.09, "step": 30670}
+{"loss": 0.6476, "learning_rate": 0.00019120773519990507, "epoch": 1.09, "step": 30680}
+{"loss": 0.6854, "learning_rate": 0.00019117214378929883, "epoch": 1.09, "step": 30690}
+{"loss": 0.6241, "learning_rate": 0.00019113655237869257, "epoch": 1.09, "step": 30700}
+{"loss": 0.5748, "learning_rate": 0.00019110096096808637, "epoch": 1.09, "step": 30710}
+{"loss": 0.5583, "learning_rate": 0.0001910653695574801, "epoch": 1.09, "step": 30720}
+{"loss": 0.586, "learning_rate": 0.00019102977814687384, "epoch": 1.09, "step": 30730}
+{"loss": 0.673, "learning_rate": 0.00019099418673626764, "epoch": 1.09, "step": 30740}
+{"loss": 0.7133, "learning_rate": 0.00019095859532566138, "epoch": 1.09, "step": 30750}
+{"loss": 0.6676, "learning_rate": 0.00019092300391505514, "epoch": 1.09, "step": 30760}
+{"loss": 0.6081, "learning_rate": 0.0001908874125044489, "epoch": 1.09, "step": 30770}
+{"loss": 0.619, "learning_rate": 0.00019085182109384268, "epoch": 1.09, "step": 30780}
+{"loss": 0.6002, "learning_rate": 0.00019081622968323642, "epoch": 1.09, "step": 30790}
+{"loss": 0.6361, "learning_rate": 0.0001907806382726302, "epoch": 1.09, "step": 30800}
+{"loss": 0.684, "learning_rate": 0.00019074504686202395, "epoch": 1.1, "step": 30810}
+{"loss": 0.6789, "learning_rate": 0.00019070945545141772, "epoch": 1.1, "step": 30820}
+{"loss": 0.5953, "learning_rate": 0.00019067386404081146, "epoch": 1.1, "step": 30830}
+{"loss": 0.6358, "learning_rate": 0.00019063827263020522, "epoch": 1.1, "step": 30840}
+{"loss": 0.6736, "learning_rate": 0.000190602681219599, "epoch": 1.1, "step": 30850}
+{"loss": 0.5862, "learning_rate": 0.00019056708980899273, "epoch": 1.1, "step": 30860}
+{"loss": 0.6267, "learning_rate": 0.00019053149839838652, "epoch": 1.1, "step": 30870}
+{"loss": 0.5714, "learning_rate": 0.00019049590698778026, "epoch": 1.1, "step": 30880}
+{"loss": 0.6286, "learning_rate": 0.00019046031557717403, "epoch": 1.1, "step": 30890}
+{"loss": 0.5203, "learning_rate": 0.0001904247241665678, "epoch": 1.1, "step": 30900}
+{"loss": 0.5733, "learning_rate": 0.00019038913275596156, "epoch": 1.1, "step": 30910}
+{"loss": 0.5402, "learning_rate": 0.0001903535413453553, "epoch": 1.1, "step": 30920}
+{"loss": 0.5563, "learning_rate": 0.00019031794993474904, "epoch": 1.1, "step": 30930}
+{"loss": 0.6556, "learning_rate": 0.00019028235852414283, "epoch": 1.1, "step": 30940}
+{"loss": 0.68, "learning_rate": 0.00019024676711353657, "epoch": 1.1, "step": 30950}
+{"loss": 0.6529, "learning_rate": 0.00019021117570293034, "epoch": 1.1, "step": 30960}
+{"loss": 0.6043, "learning_rate": 0.0001901755842923241, "epoch": 1.1, "step": 30970}
+{"loss": 0.5667, "learning_rate": 0.00019013999288171787, "epoch": 1.1, "step": 30980}
+{"loss": 0.6946, "learning_rate": 0.0001901044014711116, "epoch": 1.1, "step": 30990}
+{"loss": 0.6208, "learning_rate": 0.0001900688100605054, "epoch": 1.1, "step": 31000}
+{"loss": 0.6348, "learning_rate": 0.00019003321864989915, "epoch": 1.1, "step": 31010}
+{"loss": 0.6067, "learning_rate": 0.00018999762723929288, "epoch": 1.1, "step": 31020}
+{"loss": 0.6481, "learning_rate": 0.00018996203582868668, "epoch": 1.1, "step": 31030}
+{"loss": 0.6563, "learning_rate": 0.00018992644441808042, "epoch": 1.1, "step": 31040}
+{"loss": 0.5584, "learning_rate": 0.00018989085300747418, "epoch": 1.1, "step": 31050}
+{"loss": 0.6712, "learning_rate": 0.00018985526159686792, "epoch": 1.1, "step": 31060}
+{"loss": 0.5644, "learning_rate": 0.00018981967018626172, "epoch": 1.1, "step": 31070}
+{"loss": 0.6973, "learning_rate": 0.00018978407877565546, "epoch": 1.1, "step": 31080}
+{"loss": 0.6659, "learning_rate": 0.0001897484873650492, "epoch": 1.11, "step": 31090}
+{"loss": 0.6289, "learning_rate": 0.000189712895954443, "epoch": 1.11, "step": 31100}
+{"loss": 0.5485, "learning_rate": 0.00018967730454383673, "epoch": 1.11, "step": 31110}
+{"loss": 0.5416, "learning_rate": 0.0001896417131332305, "epoch": 1.11, "step": 31120}
+{"loss": 0.634, "learning_rate": 0.00018960612172262426, "epoch": 1.11, "step": 31130}
+{"loss": 0.589, "learning_rate": 0.00018957053031201803, "epoch": 1.11, "step": 31140}
+{"loss": 0.5771, "learning_rate": 0.00018953493890141177, "epoch": 1.11, "step": 31150}
+{"loss": 0.6364, "learning_rate": 0.0001894993474908055, "epoch": 1.11, "step": 31160}
+{"loss": 0.554, "learning_rate": 0.0001894637560801993, "epoch": 1.11, "step": 31170}
+{"loss": 0.6121, "learning_rate": 0.00018942816466959304, "epoch": 1.11, "step": 31180}
+{"loss": 0.6219, "learning_rate": 0.0001893925732589868, "epoch": 1.11, "step": 31190}
+{"loss": 0.5954, "learning_rate": 0.00018935698184838057, "epoch": 1.11, "step": 31200}
+{"loss": 0.6046, "learning_rate": 0.00018932139043777434, "epoch": 1.11, "step": 31210}
+{"loss": 0.5894, "learning_rate": 0.00018928579902716808, "epoch": 1.11, "step": 31220}
+{"loss": 0.616, "learning_rate": 0.00018925020761656187, "epoch": 1.11, "step": 31230}
+{"loss": 0.6432, "learning_rate": 0.00018921461620595561, "epoch": 1.11, "step": 31240}
+{"loss": 0.6032, "learning_rate": 0.00018917902479534935, "epoch": 1.11, "step": 31250}
+{"loss": 0.6726, "learning_rate": 0.00018914343338474315, "epoch": 1.11, "step": 31260}
+{"loss": 0.5796, "learning_rate": 0.00018910784197413689, "epoch": 1.11, "step": 31270}
+{"loss": 0.4966, "learning_rate": 0.00018907225056353065, "epoch": 1.11, "step": 31280}
+{"loss": 0.5782, "learning_rate": 0.0001890366591529244, "epoch": 1.11, "step": 31290}
+{"loss": 0.6468, "learning_rate": 0.00018900106774231819, "epoch": 1.11, "step": 31300}
+{"loss": 0.6178, "learning_rate": 0.00018896547633171193, "epoch": 1.11, "step": 31310}
+{"loss": 0.6163, "learning_rate": 0.0001889298849211057, "epoch": 1.11, "step": 31320}
+{"loss": 0.6408, "learning_rate": 0.00018889429351049946, "epoch": 1.11, "step": 31330}
+{"loss": 0.5468, "learning_rate": 0.0001888587020998932, "epoch": 1.11, "step": 31340}
+{"loss": 0.6014, "learning_rate": 0.00018882311068928696, "epoch": 1.11, "step": 31350}
+{"loss": 0.5388, "learning_rate": 0.00018878751927868073, "epoch": 1.11, "step": 31360}
+{"loss": 0.599, "learning_rate": 0.0001887519278680745, "epoch": 1.12, "step": 31370}
+{"loss": 0.7771, "learning_rate": 0.00018871989559852888, "epoch": 1.12, "step": 31380}
+{"loss": 0.6362, "learning_rate": 0.00018868430418792262, "epoch": 1.12, "step": 31390}
+{"loss": 0.6653, "learning_rate": 0.0001886487127773164, "epoch": 1.12, "step": 31400}
+{"loss": 0.5234, "learning_rate": 0.00018861312136671016, "epoch": 1.12, "step": 31410}
+{"loss": 0.6835, "learning_rate": 0.00018857752995610392, "epoch": 1.12, "step": 31420}
+{"loss": 0.5704, "learning_rate": 0.00018854193854549766, "epoch": 1.12, "step": 31430}
+{"loss": 0.6448, "learning_rate": 0.00018850634713489146, "epoch": 1.12, "step": 31440}
+{"loss": 0.5872, "learning_rate": 0.0001884707557242852, "epoch": 1.12, "step": 31450}
+{"loss": 0.6878, "learning_rate": 0.00018843516431367894, "epoch": 1.12, "step": 31460}
+{"loss": 0.6881, "learning_rate": 0.0001883995729030727, "epoch": 1.12, "step": 31470}
+{"loss": 0.5858, "learning_rate": 0.00018836398149246647, "epoch": 1.12, "step": 31480}
+{"loss": 0.5946, "learning_rate": 0.00018832839008186024, "epoch": 1.12, "step": 31490}
+{"loss": 0.5911, "learning_rate": 0.00018829279867125398, "epoch": 1.12, "step": 31500}
+{"loss": 0.6424, "learning_rate": 0.00018825720726064777, "epoch": 1.12, "step": 31510}
+{"loss": 0.6112, "learning_rate": 0.0001882216158500415, "epoch": 1.12, "step": 31520}
+{"loss": 0.5837, "learning_rate": 0.00018818602443943525, "epoch": 1.12, "step": 31530}
+{"loss": 0.6755, "learning_rate": 0.00018815043302882904, "epoch": 1.12, "step": 31540}
+{"loss": 0.5554, "learning_rate": 0.00018811484161822278, "epoch": 1.12, "step": 31550}
+{"loss": 0.5791, "learning_rate": 0.00018807925020761655, "epoch": 1.12, "step": 31560}
+{"loss": 0.5715, "learning_rate": 0.00018804365879701031, "epoch": 1.12, "step": 31570}
+{"loss": 0.6105, "learning_rate": 0.00018800806738640408, "epoch": 1.12, "step": 31580}
+{"loss": 0.5968, "learning_rate": 0.00018797247597579782, "epoch": 1.12, "step": 31590}
+{"loss": 0.5584, "learning_rate": 0.00018793688456519156, "epoch": 1.12, "step": 31600}
+{"loss": 0.6295, "learning_rate": 0.00018790129315458535, "epoch": 1.12, "step": 31610}
+{"loss": 0.6482, "learning_rate": 0.0001878657017439791, "epoch": 1.12, "step": 31620}
+{"loss": 0.589, "learning_rate": 0.00018783011033337286, "epoch": 1.12, "step": 31630}
+{"loss": 0.6268, "learning_rate": 0.00018779451892276663, "epoch": 1.12, "step": 31640}
+{"loss": 0.6331, "learning_rate": 0.0001877589275121604, "epoch": 1.13, "step": 31650}
+{"loss": 0.6903, "learning_rate": 0.00018772333610155413, "epoch": 1.13, "step": 31660}
+{"loss": 0.651, "learning_rate": 0.00018768774469094793, "epoch": 1.13, "step": 31670}
+{"loss": 0.6041, "learning_rate": 0.00018765215328034166, "epoch": 1.13, "step": 31680}
+{"loss": 0.6155, "learning_rate": 0.0001876165618697354, "epoch": 1.13, "step": 31690}
+{"loss": 0.6285, "learning_rate": 0.00018758097045912917, "epoch": 1.13, "step": 31700}
+{"loss": 0.5604, "learning_rate": 0.00018754537904852294, "epoch": 1.13, "step": 31710}
+{"loss": 0.6576, "learning_rate": 0.0001875097876379167, "epoch": 1.13, "step": 31720}
+{"loss": 0.6277, "learning_rate": 0.00018747419622731044, "epoch": 1.13, "step": 31730}
+{"loss": 0.5915, "learning_rate": 0.00018743860481670424, "epoch": 1.13, "step": 31740}
+{"loss": 0.5546, "learning_rate": 0.00018740301340609798, "epoch": 1.13, "step": 31750}
+{"loss": 0.6625, "learning_rate": 0.00018736742199549172, "epoch": 1.13, "step": 31760}
+{"loss": 0.5997, "learning_rate": 0.0001873318305848855, "epoch": 1.13, "step": 31770}
+{"loss": 0.5392, "learning_rate": 0.00018729623917427925, "epoch": 1.13, "step": 31780}
+{"loss": 0.5222, "learning_rate": 0.00018726064776367302, "epoch": 1.13, "step": 31790}
+{"loss": 0.5332, "learning_rate": 0.00018722505635306676, "epoch": 1.13, "step": 31800}
+{"loss": 0.66, "learning_rate": 0.00018718946494246055, "epoch": 1.13, "step": 31810}
+{"loss": 0.5814, "learning_rate": 0.0001871538735318543, "epoch": 1.13, "step": 31820}
+{"loss": 0.6608, "learning_rate": 0.00018711828212124805, "epoch": 1.13, "step": 31830}
+{"loss": 0.5929, "learning_rate": 0.00018708269071064182, "epoch": 1.13, "step": 31840}
+{"loss": 0.6067, "learning_rate": 0.0001870470993000356, "epoch": 1.13, "step": 31850}
+{"loss": 0.6957, "learning_rate": 0.00018701150788942933, "epoch": 1.13, "step": 31860}
+{"loss": 0.5435, "learning_rate": 0.0001869759164788231, "epoch": 1.13, "step": 31870}
+{"loss": 0.6778, "learning_rate": 0.00018694032506821686, "epoch": 1.13, "step": 31880}
+{"loss": 0.6716, "learning_rate": 0.0001869047336576106, "epoch": 1.13, "step": 31890}
+{"loss": 0.5864, "learning_rate": 0.0001868691422470044, "epoch": 1.13, "step": 31900}
+{"loss": 0.6951, "learning_rate": 0.00018683355083639813, "epoch": 1.13, "step": 31910}
+{"loss": 0.6377, "learning_rate": 0.0001867979594257919, "epoch": 1.13, "step": 31920}
+{"loss": 0.6124, "learning_rate": 0.00018676236801518564, "epoch": 1.14, "step": 31930}
+{"loss": 0.5202, "learning_rate": 0.00018672677660457943, "epoch": 1.14, "step": 31940}
+{"loss": 0.788, "learning_rate": 0.00018669118519397317, "epoch": 1.14, "step": 31950}
+{"loss": 0.612, "learning_rate": 0.0001866555937833669, "epoch": 1.14, "step": 31960}
+{"loss": 0.6215, "learning_rate": 0.0001866200023727607, "epoch": 1.14, "step": 31970}
+{"loss": 0.6006, "learning_rate": 0.00018658441096215444, "epoch": 1.14, "step": 31980}
+{"loss": 0.6522, "learning_rate": 0.0001865488195515482, "epoch": 1.14, "step": 31990}
+{"loss": 0.7201, "learning_rate": 0.00018651322814094198, "epoch": 1.14, "step": 32000}
+{"loss": 0.6283, "learning_rate": 0.00018647763673033574, "epoch": 1.14, "step": 32010}
+{"loss": 0.7636, "learning_rate": 0.00018644204531972948, "epoch": 1.14, "step": 32020}
+{"loss": 0.5267, "learning_rate": 0.00018640645390912322, "epoch": 1.14, "step": 32030}
+{"loss": 0.6133, "learning_rate": 0.00018637086249851702, "epoch": 1.14, "step": 32040}
+{"loss": 0.464, "learning_rate": 0.00018633527108791076, "epoch": 1.14, "step": 32050}
+{"loss": 0.6047, "learning_rate": 0.00018629967967730452, "epoch": 1.14, "step": 32060}
+{"loss": 0.556, "learning_rate": 0.0001862640882666983, "epoch": 1.14, "step": 32070}
+{"loss": 0.661, "learning_rate": 0.00018622849685609206, "epoch": 1.14, "step": 32080}
+{"loss": 0.6919, "learning_rate": 0.0001861929054454858, "epoch": 1.14, "step": 32090}
+{"loss": 0.6544, "learning_rate": 0.0001861573140348796, "epoch": 1.14, "step": 32100}
+{"loss": 0.5914, "learning_rate": 0.00018612172262427333, "epoch": 1.14, "step": 32110}
+{"loss": 0.5636, "learning_rate": 0.00018608613121366707, "epoch": 1.14, "step": 32120}
+{"loss": 0.5786, "learning_rate": 0.00018605053980306086, "epoch": 1.14, "step": 32130}
+{"loss": 0.6001, "learning_rate": 0.0001860149483924546, "epoch": 1.14, "step": 32140}
+{"loss": 0.5692, "learning_rate": 0.00018597935698184837, "epoch": 1.14, "step": 32150}
+{"loss": 0.6065, "learning_rate": 0.0001859437655712421, "epoch": 1.14, "step": 32160}
+{"loss": 0.6789, "learning_rate": 0.0001859081741606359, "epoch": 1.14, "step": 32170}
+{"loss": 0.635, "learning_rate": 0.00018587258275002964, "epoch": 1.14, "step": 32180}
+{"loss": 0.5824, "learning_rate": 0.00018583699133942338, "epoch": 1.14, "step": 32190}
+{"loss": 0.5386, "learning_rate": 0.00018580139992881717, "epoch": 1.14, "step": 32200}
+{"loss": 0.5915, "learning_rate": 0.0001857658085182109, "epoch": 1.15, "step": 32210}
+{"loss": 0.6075, "learning_rate": 0.00018573021710760468, "epoch": 1.15, "step": 32220}
+{"loss": 0.5791, "learning_rate": 0.00018569462569699845, "epoch": 1.15, "step": 32230}
+{"loss": 0.6135, "learning_rate": 0.0001856590342863922, "epoch": 1.15, "step": 32240}
+{"loss": 0.5579, "learning_rate": 0.00018562344287578595, "epoch": 1.15, "step": 32250}
+{"loss": 0.6392, "learning_rate": 0.0001855878514651797, "epoch": 1.15, "step": 32260}
+{"loss": 0.6123, "learning_rate": 0.00018555226005457349, "epoch": 1.15, "step": 32270}
+{"loss": 0.6541, "learning_rate": 0.00018551666864396722, "epoch": 1.15, "step": 32280}
+{"loss": 0.6483, "learning_rate": 0.000185481077233361, "epoch": 1.15, "step": 32290}
+{"loss": 0.6971, "learning_rate": 0.00018544548582275476, "epoch": 1.15, "step": 32300}
+{"loss": 0.7035, "learning_rate": 0.00018540989441214852, "epoch": 1.15, "step": 32310}
+{"loss": 0.53, "learning_rate": 0.00018537430300154226, "epoch": 1.15, "step": 32320}
+{"loss": 0.5919, "learning_rate": 0.00018533871159093606, "epoch": 1.15, "step": 32330}
+{"loss": 0.612, "learning_rate": 0.0001853031201803298, "epoch": 1.15, "step": 32340}
+{"loss": 0.645, "learning_rate": 0.00018526752876972356, "epoch": 1.15, "step": 32350}
+{"loss": 0.6166, "learning_rate": 0.00018523193735911733, "epoch": 1.15, "step": 32360}
+{"loss": 0.6795, "learning_rate": 0.00018519634594851107, "epoch": 1.15, "step": 32370}
+{"loss": 0.6391, "learning_rate": 0.00018516075453790484, "epoch": 1.15, "step": 32380}
+{"loss": 0.6132, "learning_rate": 0.00018512516312729858, "epoch": 1.15, "step": 32390}
+{"loss": 0.6031, "learning_rate": 0.00018508957171669237, "epoch": 1.15, "step": 32400}
+{"loss": 0.5784, "learning_rate": 0.0001850539803060861, "epoch": 1.15, "step": 32410}
+{"loss": 0.6042, "learning_rate": 0.00018501838889547988, "epoch": 1.15, "step": 32420}
+{"loss": 0.5264, "learning_rate": 0.00018498279748487364, "epoch": 1.15, "step": 32430}
+{"loss": 0.629, "learning_rate": 0.0001849472060742674, "epoch": 1.15, "step": 32440}
+{"loss": 0.5702, "learning_rate": 0.00018491161466366115, "epoch": 1.15, "step": 32450}
+{"loss": 0.659, "learning_rate": 0.00018487602325305494, "epoch": 1.15, "step": 32460}
+{"loss": 0.6369, "learning_rate": 0.00018484043184244868, "epoch": 1.15, "step": 32470}
+{"loss": 0.5802, "learning_rate": 0.00018480484043184242, "epoch": 1.15, "step": 32480}
+{"loss": 0.5751, "learning_rate": 0.0001847692490212362, "epoch": 1.15, "step": 32490}
+{"loss": 0.6506, "learning_rate": 0.00018473365761062995, "epoch": 1.16, "step": 32500}
+{"loss": 0.6221, "learning_rate": 0.00018469806620002372, "epoch": 1.16, "step": 32510}
+{"loss": 0.6299, "learning_rate": 0.00018466247478941746, "epoch": 1.16, "step": 32520}
+{"loss": 0.585, "learning_rate": 0.00018462688337881125, "epoch": 1.16, "step": 32530}
+{"loss": 0.616, "learning_rate": 0.000184591291968205, "epoch": 1.16, "step": 32540}
+{"loss": 0.5664, "learning_rate": 0.00018455570055759873, "epoch": 1.16, "step": 32550}
+{"loss": 0.6559, "learning_rate": 0.00018452010914699253, "epoch": 1.16, "step": 32560}
+{"loss": 0.6587, "learning_rate": 0.00018448451773638627, "epoch": 1.16, "step": 32570}
+{"loss": 0.6059, "learning_rate": 0.00018444892632578003, "epoch": 1.16, "step": 32580}
+{"loss": 0.6542, "learning_rate": 0.0001844133349151738, "epoch": 1.16, "step": 32590}
+{"loss": 0.6728, "learning_rate": 0.00018437774350456756, "epoch": 1.16, "step": 32600}
+{"loss": 0.6334, "learning_rate": 0.0001843421520939613, "epoch": 1.16, "step": 32610}
+{"loss": 0.5968, "learning_rate": 0.00018430656068335504, "epoch": 1.16, "step": 32620}
+{"loss": 0.6071, "learning_rate": 0.00018427096927274884, "epoch": 1.16, "step": 32630}
+{"loss": 0.6046, "learning_rate": 0.00018423537786214258, "epoch": 1.16, "step": 32640}
+{"loss": 0.5641, "learning_rate": 0.00018419978645153634, "epoch": 1.16, "step": 32650}
+{"loss": 0.5985, "learning_rate": 0.0001841641950409301, "epoch": 1.16, "step": 32660}
+{"loss": 0.5761, "learning_rate": 0.00018412860363032388, "epoch": 1.16, "step": 32670}
+{"loss": 0.661, "learning_rate": 0.00018409301221971762, "epoch": 1.16, "step": 32680}
+{"loss": 0.6681, "learning_rate": 0.0001840574208091114, "epoch": 1.16, "step": 32690}
+{"loss": 0.5929, "learning_rate": 0.00018402182939850515, "epoch": 1.16, "step": 32700}
+{"loss": 0.6298, "learning_rate": 0.0001839862379878989, "epoch": 1.16, "step": 32710}
+{"loss": 0.5373, "learning_rate": 0.00018395064657729266, "epoch": 1.16, "step": 32720}
+{"loss": 0.6077, "learning_rate": 0.00018391505516668642, "epoch": 1.16, "step": 32730}
+{"loss": 0.6707, "learning_rate": 0.0001838794637560802, "epoch": 1.16, "step": 32740}
+{"loss": 0.6899, "learning_rate": 0.00018384387234547393, "epoch": 1.16, "step": 32750}
+{"loss": 0.6628, "learning_rate": 0.00018380828093486772, "epoch": 1.16, "step": 32760}
+{"loss": 0.5342, "learning_rate": 0.00018377268952426146, "epoch": 1.16, "step": 32770}
+{"loss": 0.7048, "learning_rate": 0.0001837370981136552, "epoch": 1.17, "step": 32780}
+{"loss": 0.5897, "learning_rate": 0.000183701506703049, "epoch": 1.17, "step": 32790}
+{"loss": 0.6144, "learning_rate": 0.00018366591529244273, "epoch": 1.17, "step": 32800}
+{"loss": 0.5443, "learning_rate": 0.0001836303238818365, "epoch": 1.17, "step": 32810}
+{"loss": 0.5402, "learning_rate": 0.00018359473247123027, "epoch": 1.17, "step": 32820}
+{"loss": 0.6291, "learning_rate": 0.00018355914106062403, "epoch": 1.17, "step": 32830}
+{"loss": 0.5933, "learning_rate": 0.00018352354965001777, "epoch": 1.17, "step": 32840}
+{"loss": 0.5603, "learning_rate": 0.00018348795823941154, "epoch": 1.17, "step": 32850}
+{"loss": 0.6125, "learning_rate": 0.0001834523668288053, "epoch": 1.17, "step": 32860}
+{"loss": 0.5784, "learning_rate": 0.00018341677541819905, "epoch": 1.17, "step": 32870}
+{"loss": 0.6617, "learning_rate": 0.0001833811840075928, "epoch": 1.17, "step": 32880}
+{"loss": 0.6192, "learning_rate": 0.00018334559259698658, "epoch": 1.17, "step": 32890}
+{"loss": 0.6708, "learning_rate": 0.00018331000118638034, "epoch": 1.17, "step": 32900}
+{"loss": 0.6606, "learning_rate": 0.00018327440977577408, "epoch": 1.17, "step": 32910}
+{"loss": 0.6642, "learning_rate": 0.00018323881836516788, "epoch": 1.17, "step": 32920}
+{"loss": 0.5525, "learning_rate": 0.00018320322695456162, "epoch": 1.17, "step": 32930}
+{"loss": 0.5653, "learning_rate": 0.00018316763554395538, "epoch": 1.17, "step": 32940}
+{"loss": 0.652, "learning_rate": 0.00018313204413334912, "epoch": 1.17, "step": 32950}
+{"loss": 0.5572, "learning_rate": 0.00018309645272274292, "epoch": 1.17, "step": 32960}
+{"loss": 0.5222, "learning_rate": 0.00018306086131213666, "epoch": 1.17, "step": 32970}
+{"loss": 0.6703, "learning_rate": 0.0001830252699015304, "epoch": 1.17, "step": 32980}
+{"loss": 0.6858, "learning_rate": 0.0001829896784909242, "epoch": 1.17, "step": 32990}
+{"loss": 0.6153, "learning_rate": 0.00018295408708031793, "epoch": 1.17, "step": 33000}
+{"loss": 0.5675, "learning_rate": 0.0001829184956697117, "epoch": 1.17, "step": 33010}
+{"loss": 0.5905, "learning_rate": 0.00018288290425910546, "epoch": 1.17, "step": 33020}
+{"loss": 0.6414, "learning_rate": 0.00018284731284849923, "epoch": 1.17, "step": 33030}
+{"loss": 0.5974, "learning_rate": 0.00018281172143789297, "epoch": 1.17, "step": 33040}
+{"loss": 0.6254, "learning_rate": 0.0001827761300272867, "epoch": 1.17, "step": 33050}
+{"loss": 0.6567, "learning_rate": 0.0001827405386166805, "epoch": 1.18, "step": 33060}
+{"loss": 0.6914, "learning_rate": 0.00018270494720607424, "epoch": 1.18, "step": 33070}
+{"loss": 0.6322, "learning_rate": 0.000182669355795468, "epoch": 1.18, "step": 33080}
+{"loss": 0.5958, "learning_rate": 0.00018263376438486177, "epoch": 1.18, "step": 33090}
+{"loss": 0.6443, "learning_rate": 0.00018259817297425554, "epoch": 1.18, "step": 33100}
+{"loss": 0.5448, "learning_rate": 0.00018256258156364928, "epoch": 1.18, "step": 33110}
+{"loss": 0.6193, "learning_rate": 0.00018252699015304307, "epoch": 1.18, "step": 33120}
+{"loss": 0.703, "learning_rate": 0.0001824913987424368, "epoch": 1.18, "step": 33130}
+{"loss": 0.6919, "learning_rate": 0.00018245580733183055, "epoch": 1.18, "step": 33140}
+{"loss": 0.5957, "learning_rate": 0.00018242021592122435, "epoch": 1.18, "step": 33150}
+{"loss": 0.5019, "learning_rate": 0.00018238462451061809, "epoch": 1.18, "step": 33160}
+{"loss": 0.5574, "learning_rate": 0.00018234903310001185, "epoch": 1.18, "step": 33170}
+{"loss": 0.6947, "learning_rate": 0.0001823134416894056, "epoch": 1.18, "step": 33180}
+{"loss": 0.6355, "learning_rate": 0.00018227785027879939, "epoch": 1.18, "step": 33190}
+{"loss": 0.5957, "learning_rate": 0.00018224225886819312, "epoch": 1.18, "step": 33200}
+{"loss": 0.6044, "learning_rate": 0.00018220666745758686, "epoch": 1.18, "step": 33210}
+{"loss": 0.5609, "learning_rate": 0.00018217107604698066, "epoch": 1.18, "step": 33220}
+{"loss": 0.5992, "learning_rate": 0.0001821354846363744, "epoch": 1.18, "step": 33230}
+{"loss": 0.6972, "learning_rate": 0.00018209989322576816, "epoch": 1.18, "step": 33240}
+{"loss": 0.6488, "learning_rate": 0.00018206430181516193, "epoch": 1.18, "step": 33250}
+{"loss": 0.7164, "learning_rate": 0.0001820287104045557, "epoch": 1.18, "step": 33260}
+{"loss": 0.6044, "learning_rate": 0.00018199311899394944, "epoch": 1.18, "step": 33270}
+{"loss": 0.5762, "learning_rate": 0.00018195752758334318, "epoch": 1.18, "step": 33280}
+{"loss": 0.5715, "learning_rate": 0.00018192193617273697, "epoch": 1.18, "step": 33290}
+{"loss": 0.5597, "learning_rate": 0.0001818863447621307, "epoch": 1.18, "step": 33300}
+{"loss": 0.6488, "learning_rate": 0.00018185075335152448, "epoch": 1.18, "step": 33310}
+{"loss": 0.5351, "learning_rate": 0.00018181516194091824, "epoch": 1.18, "step": 33320}
+{"loss": 0.6402, "learning_rate": 0.000181779570530312, "epoch": 1.18, "step": 33330}
+{"loss": 0.6542, "learning_rate": 0.00018174397911970575, "epoch": 1.19, "step": 33340}
+{"loss": 0.6288, "learning_rate": 0.00018170838770909954, "epoch": 1.19, "step": 33350}
+{"loss": 0.594, "learning_rate": 0.00018167279629849328, "epoch": 1.19, "step": 33360}
+{"loss": 0.5057, "learning_rate": 0.00018163720488788702, "epoch": 1.19, "step": 33370}
+{"loss": 0.6633, "learning_rate": 0.00018160161347728081, "epoch": 1.19, "step": 33380}
+{"loss": 0.6429, "learning_rate": 0.00018156602206667455, "epoch": 1.19, "step": 33390}
+{"loss": 0.6355, "learning_rate": 0.00018153043065606832, "epoch": 1.19, "step": 33400}
+{"loss": 0.5896, "learning_rate": 0.00018149483924546206, "epoch": 1.19, "step": 33410}
+{"loss": 0.6558, "learning_rate": 0.00018145924783485585, "epoch": 1.19, "step": 33420}
+{"loss": 0.6432, "learning_rate": 0.0001814236564242496, "epoch": 1.19, "step": 33430}
+{"loss": 0.6185, "learning_rate": 0.00018138806501364336, "epoch": 1.19, "step": 33440}
+{"loss": 0.6005, "learning_rate": 0.00018135247360303713, "epoch": 1.19, "step": 33450}
+{"loss": 0.6265, "learning_rate": 0.00018131688219243087, "epoch": 1.19, "step": 33460}
+{"loss": 0.618, "learning_rate": 0.00018128129078182463, "epoch": 1.19, "step": 33470}
+{"loss": 0.5359, "learning_rate": 0.0001812456993712184, "epoch": 1.19, "step": 33480}
+{"loss": 0.655, "learning_rate": 0.00018121366710167276, "epoch": 1.19, "step": 33490}
+{"loss": 0.6602, "learning_rate": 0.00018117807569106655, "epoch": 1.19, "step": 33500}
+{"loss": 0.5523, "learning_rate": 0.0001811424842804603, "epoch": 1.19, "step": 33510}
+{"loss": 0.5736, "learning_rate": 0.00018110689286985406, "epoch": 1.19, "step": 33520}
+{"loss": 0.5712, "learning_rate": 0.00018107130145924782, "epoch": 1.19, "step": 33530}
+{"loss": 0.6814, "learning_rate": 0.0001810357100486416, "epoch": 1.19, "step": 33540}
+{"loss": 0.7061, "learning_rate": 0.00018100011863803533, "epoch": 1.19, "step": 33550}
+{"loss": 0.6695, "learning_rate": 0.00018096452722742912, "epoch": 1.19, "step": 33560}
+{"loss": 0.579, "learning_rate": 0.00018092893581682286, "epoch": 1.19, "step": 33570}
+{"loss": 0.6537, "learning_rate": 0.0001808933444062166, "epoch": 1.19, "step": 33580}
+{"loss": 0.6494, "learning_rate": 0.00018085775299561037, "epoch": 1.19, "step": 33590}
+{"loss": 0.5447, "learning_rate": 0.00018082216158500414, "epoch": 1.19, "step": 33600}
+{"loss": 0.7083, "learning_rate": 0.0001807865701743979, "epoch": 1.19, "step": 33610}
+{"loss": 0.6694, "learning_rate": 0.00018075097876379164, "epoch": 1.2, "step": 33620}
+{"loss": 0.6047, "learning_rate": 0.00018071538735318544, "epoch": 1.2, "step": 33630}
+{"loss": 0.586, "learning_rate": 0.00018067979594257918, "epoch": 1.2, "step": 33640}
+{"loss": 0.5902, "learning_rate": 0.00018064420453197292, "epoch": 1.2, "step": 33650}
+{"loss": 0.6112, "learning_rate": 0.0001806086131213667, "epoch": 1.2, "step": 33660}
+{"loss": 0.6323, "learning_rate": 0.00018057302171076045, "epoch": 1.2, "step": 33670}
+{"loss": 0.5426, "learning_rate": 0.00018053743030015421, "epoch": 1.2, "step": 33680}
+{"loss": 0.5764, "learning_rate": 0.00018050183888954798, "epoch": 1.2, "step": 33690}
+{"loss": 0.6374, "learning_rate": 0.00018046624747894175, "epoch": 1.2, "step": 33700}
+{"loss": 0.6675, "learning_rate": 0.0001804306560683355, "epoch": 1.2, "step": 33710}
+{"loss": 0.681, "learning_rate": 0.00018039506465772923, "epoch": 1.2, "step": 33720}
+{"loss": 0.6083, "learning_rate": 0.00018035947324712302, "epoch": 1.2, "step": 33730}
+{"loss": 0.5993, "learning_rate": 0.00018032388183651676, "epoch": 1.2, "step": 33740}
+{"loss": 0.7208, "learning_rate": 0.00018028829042591053, "epoch": 1.2, "step": 33750}
+{"loss": 0.6094, "learning_rate": 0.0001802526990153043, "epoch": 1.2, "step": 33760}
+{"loss": 0.6612, "learning_rate": 0.00018021710760469806, "epoch": 1.2, "step": 33770}
+{"loss": 0.6659, "learning_rate": 0.0001801815161940918, "epoch": 1.2, "step": 33780}
+{"loss": 0.5837, "learning_rate": 0.0001801459247834856, "epoch": 1.2, "step": 33790}
+{"loss": 0.5903, "learning_rate": 0.00018011033337287933, "epoch": 1.2, "step": 33800}
+{"loss": 0.745, "learning_rate": 0.00018007474196227307, "epoch": 1.2, "step": 33810}
+{"loss": 0.6172, "learning_rate": 0.00018003915055166684, "epoch": 1.2, "step": 33820}
+{"loss": 0.6034, "learning_rate": 0.0001800035591410606, "epoch": 1.2, "step": 33830}
+{"loss": 0.5568, "learning_rate": 0.00017996796773045437, "epoch": 1.2, "step": 33840}
+{"loss": 0.7227, "learning_rate": 0.0001799323763198481, "epoch": 1.2, "step": 33850}
+{"loss": 0.7274, "learning_rate": 0.0001798967849092419, "epoch": 1.2, "step": 33860}
+{"loss": 0.6121, "learning_rate": 0.00017986119349863564, "epoch": 1.2, "step": 33870}
+{"loss": 0.6195, "learning_rate": 0.00017982560208802938, "epoch": 1.2, "step": 33880}
+{"loss": 0.6621, "learning_rate": 0.00017979001067742318, "epoch": 1.2, "step": 33890}
+{"loss": 0.6413, "learning_rate": 0.00017975441926681692, "epoch": 1.21, "step": 33900}
+{"loss": 0.6694, "learning_rate": 0.00017971882785621068, "epoch": 1.21, "step": 33910}
+{"loss": 0.6867, "learning_rate": 0.00017968323644560445, "epoch": 1.21, "step": 33920}
+{"loss": 0.7622, "learning_rate": 0.00017964764503499822, "epoch": 1.21, "step": 33930}
+{"loss": 0.5562, "learning_rate": 0.00017961205362439196, "epoch": 1.21, "step": 33940}
+{"loss": 0.6508, "learning_rate": 0.00017957646221378572, "epoch": 1.21, "step": 33950}
+{"loss": 0.5687, "learning_rate": 0.0001795408708031795, "epoch": 1.21, "step": 33960}
+{"loss": 0.6203, "learning_rate": 0.00017950527939257326, "epoch": 1.21, "step": 33970}
+{"loss": 0.6242, "learning_rate": 0.000179469687981967, "epoch": 1.21, "step": 33980}
+{"loss": 0.5707, "learning_rate": 0.00017943409657136076, "epoch": 1.21, "step": 33990}
+{"loss": 0.6166, "learning_rate": 0.00017939850516075453, "epoch": 1.21, "step": 34000}
+{"loss": 0.5797, "learning_rate": 0.00017936291375014827, "epoch": 1.21, "step": 34010}
+{"loss": 0.5798, "learning_rate": 0.00017932732233954206, "epoch": 1.21, "step": 34020}
+{"loss": 0.5398, "learning_rate": 0.0001792917309289358, "epoch": 1.21, "step": 34030}
+{"loss": 0.5489, "learning_rate": 0.00017925613951832957, "epoch": 1.21, "step": 34040}
+{"loss": 0.5271, "learning_rate": 0.0001792205481077233, "epoch": 1.21, "step": 34050}
+{"loss": 0.6222, "learning_rate": 0.0001791849566971171, "epoch": 1.21, "step": 34060}
+{"loss": 0.6482, "learning_rate": 0.00017914936528651084, "epoch": 1.21, "step": 34070}
+{"loss": 0.5883, "learning_rate": 0.00017911377387590458, "epoch": 1.21, "step": 34080}
+{"loss": 0.5076, "learning_rate": 0.00017907818246529837, "epoch": 1.21, "step": 34090}
+{"loss": 0.7126, "learning_rate": 0.0001790425910546921, "epoch": 1.21, "step": 34100}
+{"loss": 0.6297, "learning_rate": 0.00017900699964408588, "epoch": 1.21, "step": 34110}
+{"loss": 0.5615, "learning_rate": 0.0001789785265156009, "epoch": 1.21, "step": 34120}
+{"loss": 0.6069, "learning_rate": 0.00017894293510499465, "epoch": 1.21, "step": 34130}
+{"loss": 0.6186, "learning_rate": 0.0001789073436943884, "epoch": 1.21, "step": 34140}
+{"loss": 0.5059, "learning_rate": 0.00017887175228378219, "epoch": 1.21, "step": 34150}
+{"loss": 0.6379, "learning_rate": 0.00017883616087317593, "epoch": 1.21, "step": 34160}
+{"loss": 0.6156, "learning_rate": 0.00017880056946256967, "epoch": 1.21, "step": 34170}
+{"loss": 0.7217, "learning_rate": 0.00017876497805196346, "epoch": 1.22, "step": 34180}
+{"loss": 0.5996, "learning_rate": 0.0001787293866413572, "epoch": 1.22, "step": 34190}
+{"loss": 0.6325, "learning_rate": 0.00017869379523075096, "epoch": 1.22, "step": 34200}
+{"loss": 0.6992, "learning_rate": 0.0001786582038201447, "epoch": 1.22, "step": 34210}
+{"loss": 0.5919, "learning_rate": 0.0001786226124095385, "epoch": 1.22, "step": 34220}
+{"loss": 0.5612, "learning_rate": 0.00017858702099893224, "epoch": 1.22, "step": 34230}
+{"loss": 0.6702, "learning_rate": 0.00017855142958832598, "epoch": 1.22, "step": 34240}
+{"loss": 0.5283, "learning_rate": 0.00017851583817771977, "epoch": 1.22, "step": 34250}
+{"loss": 0.602, "learning_rate": 0.0001784802467671135, "epoch": 1.22, "step": 34260}
+{"loss": 0.5963, "learning_rate": 0.00017844465535650728, "epoch": 1.22, "step": 34270}
+{"loss": 0.7406, "learning_rate": 0.00017840906394590104, "epoch": 1.22, "step": 34280}
+{"loss": 0.5287, "learning_rate": 0.0001783734725352948, "epoch": 1.22, "step": 34290}
+{"loss": 0.6692, "learning_rate": 0.00017833788112468855, "epoch": 1.22, "step": 34300}
+{"loss": 0.5996, "learning_rate": 0.00017830228971408232, "epoch": 1.22, "step": 34310}
+{"loss": 0.5591, "learning_rate": 0.00017826669830347608, "epoch": 1.22, "step": 34320}
+{"loss": 0.6203, "learning_rate": 0.00017823110689286982, "epoch": 1.22, "step": 34330}
+{"loss": 0.6526, "learning_rate": 0.0001781955154822636, "epoch": 1.22, "step": 34340}
+{"loss": 0.681, "learning_rate": 0.00017815992407165735, "epoch": 1.22, "step": 34350}
+{"loss": 0.5821, "learning_rate": 0.00017812433266105112, "epoch": 1.22, "step": 34360}
+{"loss": 0.6636, "learning_rate": 0.00017808874125044486, "epoch": 1.22, "step": 34370}
+{"loss": 0.7057, "learning_rate": 0.00017805314983983865, "epoch": 1.22, "step": 34380}
+{"loss": 0.5769, "learning_rate": 0.0001780175584292324, "epoch": 1.22, "step": 34390}
+{"loss": 0.6173, "learning_rate": 0.00017798196701862616, "epoch": 1.22, "step": 34400}
+{"loss": 0.6631, "learning_rate": 0.00017794637560801993, "epoch": 1.22, "step": 34410}
+{"loss": 0.6114, "learning_rate": 0.0001779107841974137, "epoch": 1.22, "step": 34420}
+{"loss": 0.5739, "learning_rate": 0.00017787519278680743, "epoch": 1.22, "step": 34430}
+{"loss": 0.6282, "learning_rate": 0.00017783960137620117, "epoch": 1.22, "step": 34440}
+{"loss": 0.6898, "learning_rate": 0.00017780400996559497, "epoch": 1.22, "step": 34450}
+{"loss": 0.5748, "learning_rate": 0.0001777684185549887, "epoch": 1.23, "step": 34460}
+{"loss": 0.6064, "learning_rate": 0.00017773282714438247, "epoch": 1.23, "step": 34470}
+{"loss": 0.6415, "learning_rate": 0.00017769723573377624, "epoch": 1.23, "step": 34480}
+{"loss": 0.6279, "learning_rate": 0.00017766164432317, "epoch": 1.23, "step": 34490}
+{"loss": 0.6234, "learning_rate": 0.00017762605291256374, "epoch": 1.23, "step": 34500}
+{"loss": 0.7118, "learning_rate": 0.00017759046150195754, "epoch": 1.23, "step": 34510}
+{"loss": 0.5518, "learning_rate": 0.00017755487009135128, "epoch": 1.23, "step": 34520}
+{"loss": 0.5394, "learning_rate": 0.00017751927868074502, "epoch": 1.23, "step": 34530}
+{"loss": 0.516, "learning_rate": 0.00017748368727013878, "epoch": 1.23, "step": 34540}
+{"loss": 0.6158, "learning_rate": 0.00017744809585953255, "epoch": 1.23, "step": 34550}
+{"loss": 0.5519, "learning_rate": 0.00017741250444892632, "epoch": 1.23, "step": 34560}
+{"loss": 0.6187, "learning_rate": 0.00017737691303832006, "epoch": 1.23, "step": 34570}
+{"loss": 0.586, "learning_rate": 0.00017734132162771385, "epoch": 1.23, "step": 34580}
+{"loss": 0.5116, "learning_rate": 0.0001773057302171076, "epoch": 1.23, "step": 34590}
+{"loss": 0.5188, "learning_rate": 0.00017727013880650133, "epoch": 1.23, "step": 34600}
+{"loss": 0.7858, "learning_rate": 0.00017723454739589512, "epoch": 1.23, "step": 34610}
+{"loss": 0.5352, "learning_rate": 0.00017719895598528886, "epoch": 1.23, "step": 34620}
+{"loss": 0.635, "learning_rate": 0.00017716336457468263, "epoch": 1.23, "step": 34630}
+{"loss": 0.7007, "learning_rate": 0.0001771277731640764, "epoch": 1.23, "step": 34640}
+{"loss": 0.6168, "learning_rate": 0.00017709218175347016, "epoch": 1.23, "step": 34650}
+{"loss": 0.5854, "learning_rate": 0.0001770565903428639, "epoch": 1.23, "step": 34660}
+{"loss": 0.6019, "learning_rate": 0.00017702099893225764, "epoch": 1.23, "step": 34670}
+{"loss": 0.5687, "learning_rate": 0.00017698540752165143, "epoch": 1.23, "step": 34680}
+{"loss": 0.5601, "learning_rate": 0.00017694981611104517, "epoch": 1.23, "step": 34690}
+{"loss": 0.6441, "learning_rate": 0.00017691422470043894, "epoch": 1.23, "step": 34700}
+{"loss": 0.6256, "learning_rate": 0.0001768786332898327, "epoch": 1.23, "step": 34710}
+{"loss": 0.6179, "learning_rate": 0.00017684304187922647, "epoch": 1.23, "step": 34720}
+{"loss": 0.5836, "learning_rate": 0.0001768074504686202, "epoch": 1.23, "step": 34730}
+{"loss": 0.6985, "learning_rate": 0.000176771859058014, "epoch": 1.23, "step": 34740}
+{"loss": 0.5912, "learning_rate": 0.00017673626764740775, "epoch": 1.24, "step": 34750}
+{"loss": 0.5808, "learning_rate": 0.00017670067623680149, "epoch": 1.24, "step": 34760}
+{"loss": 0.5467, "learning_rate": 0.00017666508482619525, "epoch": 1.24, "step": 34770}
+{"loss": 0.5888, "learning_rate": 0.00017662949341558902, "epoch": 1.24, "step": 34780}
+{"loss": 0.6884, "learning_rate": 0.00017659390200498279, "epoch": 1.24, "step": 34790}
+{"loss": 0.6265, "learning_rate": 0.00017655831059437652, "epoch": 1.24, "step": 34800}
+{"loss": 0.6266, "learning_rate": 0.00017652271918377032, "epoch": 1.24, "step": 34810}
+{"loss": 0.6485, "learning_rate": 0.00017648712777316406, "epoch": 1.24, "step": 34820}
+{"loss": 0.592, "learning_rate": 0.0001764515363625578, "epoch": 1.24, "step": 34830}
+{"loss": 0.5474, "learning_rate": 0.0001764159449519516, "epoch": 1.24, "step": 34840}
+{"loss": 0.6784, "learning_rate": 0.00017638035354134533, "epoch": 1.24, "step": 34850}
+{"loss": 0.5738, "learning_rate": 0.0001763447621307391, "epoch": 1.24, "step": 34860}
+{"loss": 0.6016, "learning_rate": 0.00017630917072013286, "epoch": 1.24, "step": 34870}
+{"loss": 0.6417, "learning_rate": 0.00017627357930952663, "epoch": 1.24, "step": 34880}
+{"loss": 0.5677, "learning_rate": 0.00017623798789892037, "epoch": 1.24, "step": 34890}
+{"loss": 0.6381, "learning_rate": 0.00017620239648831414, "epoch": 1.24, "step": 34900}
+{"loss": 0.6315, "learning_rate": 0.0001761668050777079, "epoch": 1.24, "step": 34910}
+{"loss": 0.7025, "learning_rate": 0.00017613121366710167, "epoch": 1.24, "step": 34920}
+{"loss": 0.5007, "learning_rate": 0.0001760956222564954, "epoch": 1.24, "step": 34930}
+{"loss": 0.6842, "learning_rate": 0.00017606003084588918, "epoch": 1.24, "step": 34940}
+{"loss": 0.5468, "learning_rate": 0.00017602443943528294, "epoch": 1.24, "step": 34950}
+{"loss": 0.5222, "learning_rate": 0.00017598884802467668, "epoch": 1.24, "step": 34960}
+{"loss": 0.545, "learning_rate": 0.00017595325661407047, "epoch": 1.24, "step": 34970}
+{"loss": 0.5539, "learning_rate": 0.00017591766520346421, "epoch": 1.24, "step": 34980}
+{"loss": 0.6645, "learning_rate": 0.00017588207379285798, "epoch": 1.24, "step": 34990}
+{"loss": 0.6729, "learning_rate": 0.00017584648238225172, "epoch": 1.24, "step": 35000}
+{"loss": 0.564, "learning_rate": 0.00017581089097164551, "epoch": 1.24, "step": 35010}
+{"loss": 0.6072, "learning_rate": 0.00017577529956103925, "epoch": 1.24, "step": 35020}
+{"loss": 0.6382, "learning_rate": 0.000175739708150433, "epoch": 1.25, "step": 35030}
+{"loss": 0.5577, "learning_rate": 0.0001757041167398268, "epoch": 1.25, "step": 35040}
+{"loss": 0.5998, "learning_rate": 0.00017566852532922053, "epoch": 1.25, "step": 35050}
+{"loss": 0.6007, "learning_rate": 0.0001756329339186143, "epoch": 1.25, "step": 35060}
+{"loss": 0.6123, "learning_rate": 0.00017559734250800806, "epoch": 1.25, "step": 35070}
+{"loss": 0.5719, "learning_rate": 0.00017556175109740183, "epoch": 1.25, "step": 35080}
+{"loss": 0.6146, "learning_rate": 0.00017552615968679557, "epoch": 1.25, "step": 35090}
+{"loss": 0.5799, "learning_rate": 0.00017549056827618936, "epoch": 1.25, "step": 35100}
+{"loss": 0.6302, "learning_rate": 0.0001754549768655831, "epoch": 1.25, "step": 35110}
+{"loss": 0.6366, "learning_rate": 0.00017541938545497684, "epoch": 1.25, "step": 35120}
+{"loss": 0.687, "learning_rate": 0.0001753837940443706, "epoch": 1.25, "step": 35130}
+{"loss": 0.5285, "learning_rate": 0.00017534820263376437, "epoch": 1.25, "step": 35140}
+{"loss": 0.6264, "learning_rate": 0.00017531261122315814, "epoch": 1.25, "step": 35150}
+{"loss": 0.6108, "learning_rate": 0.00017527701981255188, "epoch": 1.25, "step": 35160}
+{"loss": 0.5217, "learning_rate": 0.00017524142840194567, "epoch": 1.25, "step": 35170}
+{"loss": 0.6241, "learning_rate": 0.0001752058369913394, "epoch": 1.25, "step": 35180}
+{"loss": 0.5877, "learning_rate": 0.00017517024558073315, "epoch": 1.25, "step": 35190}
+{"loss": 0.628, "learning_rate": 0.00017513465417012694, "epoch": 1.25, "step": 35200}
+{"loss": 0.5322, "learning_rate": 0.00017509906275952068, "epoch": 1.25, "step": 35210}
+{"loss": 0.5287, "learning_rate": 0.00017506347134891445, "epoch": 1.25, "step": 35220}
+{"loss": 0.6168, "learning_rate": 0.0001750278799383082, "epoch": 1.25, "step": 35230}
+{"loss": 0.5809, "learning_rate": 0.00017499228852770198, "epoch": 1.25, "step": 35240}
+{"loss": 0.5863, "learning_rate": 0.00017495669711709572, "epoch": 1.25, "step": 35250}
+{"loss": 0.6099, "learning_rate": 0.00017492110570648946, "epoch": 1.25, "step": 35260}
+{"loss": 0.5736, "learning_rate": 0.00017488551429588325, "epoch": 1.25, "step": 35270}
+{"loss": 0.5413, "learning_rate": 0.000174849922885277, "epoch": 1.25, "step": 35280}
+{"loss": 0.6549, "learning_rate": 0.00017481433147467076, "epoch": 1.25, "step": 35290}
+{"loss": 0.6414, "learning_rate": 0.00017477874006406453, "epoch": 1.25, "step": 35300}
+{"loss": 0.5341, "learning_rate": 0.0001747431486534583, "epoch": 1.26, "step": 35310}
+{"loss": 0.7005, "learning_rate": 0.00017470755724285203, "epoch": 1.26, "step": 35320}
+{"loss": 0.5184, "learning_rate": 0.00017467196583224583, "epoch": 1.26, "step": 35330}
+{"loss": 0.5416, "learning_rate": 0.00017463637442163957, "epoch": 1.26, "step": 35340}
+{"loss": 0.5534, "learning_rate": 0.0001746007830110333, "epoch": 1.26, "step": 35350}
+{"loss": 0.6309, "learning_rate": 0.00017456519160042707, "epoch": 1.26, "step": 35360}
+{"loss": 0.6217, "learning_rate": 0.00017452960018982084, "epoch": 1.26, "step": 35370}
+{"loss": 0.6795, "learning_rate": 0.0001744940087792146, "epoch": 1.26, "step": 35380}
+{"loss": 0.5418, "learning_rate": 0.00017445841736860835, "epoch": 1.26, "step": 35390}
+{"loss": 0.6551, "learning_rate": 0.00017442282595800214, "epoch": 1.26, "step": 35400}
+{"loss": 0.6562, "learning_rate": 0.00017438723454739588, "epoch": 1.26, "step": 35410}
+{"loss": 0.5856, "learning_rate": 0.00017435164313678964, "epoch": 1.26, "step": 35420}
+{"loss": 0.6489, "learning_rate": 0.0001743160517261834, "epoch": 1.26, "step": 35430}
+{"loss": 0.5691, "learning_rate": 0.00017428046031557715, "epoch": 1.26, "step": 35440}
+{"loss": 0.66, "learning_rate": 0.00017424486890497092, "epoch": 1.26, "step": 35450}
+{"loss": 0.5538, "learning_rate": 0.00017420927749436466, "epoch": 1.26, "step": 35460}
+{"loss": 0.6236, "learning_rate": 0.00017417368608375845, "epoch": 1.26, "step": 35470}
+{"loss": 0.5936, "learning_rate": 0.0001741380946731522, "epoch": 1.26, "step": 35480}
+{"loss": 0.5961, "learning_rate": 0.00017410250326254596, "epoch": 1.26, "step": 35490}
+{"loss": 0.5615, "learning_rate": 0.00017406691185193972, "epoch": 1.26, "step": 35500}
+{"loss": 0.64, "learning_rate": 0.0001740313204413335, "epoch": 1.26, "step": 35510}
+{"loss": 0.6744, "learning_rate": 0.00017399572903072723, "epoch": 1.26, "step": 35520}
+{"loss": 0.665, "learning_rate": 0.00017396013762012102, "epoch": 1.26, "step": 35530}
+{"loss": 0.5765, "learning_rate": 0.00017392454620951476, "epoch": 1.26, "step": 35540}
+{"loss": 0.6261, "learning_rate": 0.0001738889547989085, "epoch": 1.26, "step": 35550}
+{"loss": 0.6324, "learning_rate": 0.00017385336338830227, "epoch": 1.26, "step": 35560}
+{"loss": 0.5916, "learning_rate": 0.00017381777197769603, "epoch": 1.26, "step": 35570}
+{"loss": 0.667, "learning_rate": 0.0001737821805670898, "epoch": 1.26, "step": 35580}
+{"loss": 0.6032, "learning_rate": 0.00017374658915648354, "epoch": 1.27, "step": 35590}
+{"loss": 0.5934, "learning_rate": 0.00017371099774587733, "epoch": 1.27, "step": 35600}
+{"loss": 0.6625, "learning_rate": 0.00017367540633527107, "epoch": 1.27, "step": 35610}
+{"loss": 0.5713, "learning_rate": 0.0001736398149246648, "epoch": 1.27, "step": 35620}
+{"loss": 0.5756, "learning_rate": 0.0001736042235140586, "epoch": 1.27, "step": 35630}
+{"loss": 0.5164, "learning_rate": 0.00017356863210345235, "epoch": 1.27, "step": 35640}
+{"loss": 0.5321, "learning_rate": 0.0001735330406928461, "epoch": 1.27, "step": 35650}
+{"loss": 0.6054, "learning_rate": 0.00017349744928223988, "epoch": 1.27, "step": 35660}
+{"loss": 0.5949, "learning_rate": 0.00017346185787163365, "epoch": 1.27, "step": 35670}
+{"loss": 0.6288, "learning_rate": 0.00017342626646102739, "epoch": 1.27, "step": 35680}
+{"loss": 0.6339, "learning_rate": 0.00017339067505042113, "epoch": 1.27, "step": 35690}
+{"loss": 0.6201, "learning_rate": 0.00017335508363981492, "epoch": 1.27, "step": 35700}
+{"loss": 0.6531, "learning_rate": 0.00017331949222920866, "epoch": 1.27, "step": 35710}
+{"loss": 0.599, "learning_rate": 0.00017328390081860242, "epoch": 1.27, "step": 35720}
+{"loss": 0.521, "learning_rate": 0.0001732483094079962, "epoch": 1.27, "step": 35730}
+{"loss": 0.6082, "learning_rate": 0.00017321271799738996, "epoch": 1.27, "step": 35740}
+{"loss": 0.5898, "learning_rate": 0.0001731771265867837, "epoch": 1.27, "step": 35750}
+{"loss": 0.7437, "learning_rate": 0.0001731415351761775, "epoch": 1.27, "step": 35760}
+{"loss": 0.5672, "learning_rate": 0.00017310594376557123, "epoch": 1.27, "step": 35770}
+{"loss": 0.5288, "learning_rate": 0.00017307035235496497, "epoch": 1.27, "step": 35780}
+{"loss": 0.5916, "learning_rate": 0.00017303476094435874, "epoch": 1.27, "step": 35790}
+{"loss": 0.5892, "learning_rate": 0.0001729991695337525, "epoch": 1.27, "step": 35800}
+{"loss": 0.6411, "learning_rate": 0.00017296357812314627, "epoch": 1.27, "step": 35810}
+{"loss": 0.6004, "learning_rate": 0.00017292798671254, "epoch": 1.27, "step": 35820}
+{"loss": 0.6444, "learning_rate": 0.0001728923953019338, "epoch": 1.27, "step": 35830}
+{"loss": 0.5217, "learning_rate": 0.00017285680389132754, "epoch": 1.27, "step": 35840}
+{"loss": 0.6596, "learning_rate": 0.00017282121248072128, "epoch": 1.27, "step": 35850}
+{"loss": 0.5288, "learning_rate": 0.00017278562107011508, "epoch": 1.27, "step": 35860}
+{"loss": 0.5804, "learning_rate": 0.00017275002965950881, "epoch": 1.28, "step": 35870}
+{"loss": 0.6687, "learning_rate": 0.00017271443824890258, "epoch": 1.28, "step": 35880}
+{"loss": 0.6379, "learning_rate": 0.00017267884683829635, "epoch": 1.28, "step": 35890}
+{"loss": 0.6385, "learning_rate": 0.00017264325542769011, "epoch": 1.28, "step": 35900}
+{"loss": 0.6302, "learning_rate": 0.00017260766401708385, "epoch": 1.28, "step": 35910}
+{"loss": 0.4826, "learning_rate": 0.00017257207260647762, "epoch": 1.28, "step": 35920}
+{"loss": 0.5856, "learning_rate": 0.0001725364811958714, "epoch": 1.28, "step": 35930}
+{"loss": 0.6481, "learning_rate": 0.00017250088978526513, "epoch": 1.28, "step": 35940}
+{"loss": 0.5813, "learning_rate": 0.0001724652983746589, "epoch": 1.28, "step": 35950}
+{"loss": 0.5414, "learning_rate": 0.00017242970696405266, "epoch": 1.28, "step": 35960}
+{"loss": 0.5318, "learning_rate": 0.00017239411555344643, "epoch": 1.28, "step": 35970}
+{"loss": 0.739, "learning_rate": 0.00017235852414284017, "epoch": 1.28, "step": 35980}
+{"loss": 0.6323, "learning_rate": 0.00017232293273223396, "epoch": 1.28, "step": 35990}
+{"loss": 0.6266, "learning_rate": 0.0001722873413216277, "epoch": 1.28, "step": 36000}
+{"loss": 0.6285, "learning_rate": 0.00017225174991102147, "epoch": 1.28, "step": 36010}
+{"loss": 0.619, "learning_rate": 0.0001722161585004152, "epoch": 1.28, "step": 36020}
+{"loss": 0.6538, "learning_rate": 0.000172180567089809, "epoch": 1.28, "step": 36030}
+{"loss": 0.6417, "learning_rate": 0.00017214497567920274, "epoch": 1.28, "step": 36040}
+{"loss": 0.5667, "learning_rate": 0.00017210938426859648, "epoch": 1.28, "step": 36050}
+{"loss": 0.5555, "learning_rate": 0.00017207379285799027, "epoch": 1.28, "step": 36060}
+{"loss": 0.5365, "learning_rate": 0.000172038201447384, "epoch": 1.28, "step": 36070}
+{"loss": 0.5798, "learning_rate": 0.00017200261003677778, "epoch": 1.28, "step": 36080}
+{"loss": 0.64, "learning_rate": 0.00017196701862617154, "epoch": 1.28, "step": 36090}
+{"loss": 0.5595, "learning_rate": 0.0001719314272155653, "epoch": 1.28, "step": 36100}
+{"loss": 0.633, "learning_rate": 0.00017189583580495905, "epoch": 1.28, "step": 36110}
+{"loss": 0.6322, "learning_rate": 0.00017186024439435284, "epoch": 1.28, "step": 36120}
+{"loss": 0.6041, "learning_rate": 0.00017182465298374658, "epoch": 1.28, "step": 36130}
+{"loss": 0.5973, "learning_rate": 0.00017178906157314032, "epoch": 1.28, "step": 36140}
+{"loss": 0.5494, "learning_rate": 0.0001717534701625341, "epoch": 1.29, "step": 36150}
+{"loss": 0.6574, "learning_rate": 0.00017171787875192786, "epoch": 1.29, "step": 36160}
+{"loss": 0.59, "learning_rate": 0.00017168228734132162, "epoch": 1.29, "step": 36170}
+{"loss": 0.6757, "learning_rate": 0.00017164669593071536, "epoch": 1.29, "step": 36180}
+{"loss": 0.5482, "learning_rate": 0.00017161110452010915, "epoch": 1.29, "step": 36190}
+{"loss": 0.6004, "learning_rate": 0.0001715755131095029, "epoch": 1.29, "step": 36200}
+{"loss": 0.6071, "learning_rate": 0.00017153992169889663, "epoch": 1.29, "step": 36210}
+{"loss": 0.5847, "learning_rate": 0.00017150433028829043, "epoch": 1.29, "step": 36220}
+{"loss": 0.5477, "learning_rate": 0.00017146873887768417, "epoch": 1.29, "step": 36230}
+{"loss": 0.6186, "learning_rate": 0.00017143314746707793, "epoch": 1.29, "step": 36240}
+{"loss": 0.5453, "learning_rate": 0.00017139755605647167, "epoch": 1.29, "step": 36250}
+{"loss": 0.5113, "learning_rate": 0.00017136196464586547, "epoch": 1.29, "step": 36260}
+{"loss": 0.5824, "learning_rate": 0.0001713263732352592, "epoch": 1.29, "step": 36270}
+{"loss": 0.6613, "learning_rate": 0.00017129078182465295, "epoch": 1.29, "step": 36280}
+{"loss": 0.6176, "learning_rate": 0.00017125519041404674, "epoch": 1.29, "step": 36290}
+{"loss": 0.5936, "learning_rate": 0.00017121959900344048, "epoch": 1.29, "step": 36300}
+{"loss": 0.6983, "learning_rate": 0.00017118400759283425, "epoch": 1.29, "step": 36310}
+{"loss": 0.6346, "learning_rate": 0.000171148416182228, "epoch": 1.29, "step": 36320}
+{"loss": 0.6482, "learning_rate": 0.00017111282477162178, "epoch": 1.29, "step": 36330}
+{"loss": 0.5746, "learning_rate": 0.00017107723336101552, "epoch": 1.29, "step": 36340}
+{"loss": 0.6006, "learning_rate": 0.0001710416419504093, "epoch": 1.29, "step": 36350}
+{"loss": 0.6274, "learning_rate": 0.00017100605053980305, "epoch": 1.29, "step": 36360}
+{"loss": 0.693, "learning_rate": 0.0001709704591291968, "epoch": 1.29, "step": 36370}
+{"loss": 0.6332, "learning_rate": 0.00017093486771859056, "epoch": 1.29, "step": 36380}
+{"loss": 0.5767, "learning_rate": 0.00017089927630798432, "epoch": 1.29, "step": 36390}
+{"loss": 0.5879, "learning_rate": 0.0001708636848973781, "epoch": 1.29, "step": 36400}
+{"loss": 0.6397, "learning_rate": 0.00017082809348677183, "epoch": 1.29, "step": 36410}
+{"loss": 0.5569, "learning_rate": 0.00017079250207616562, "epoch": 1.29, "step": 36420}
+{"loss": 0.6219, "learning_rate": 0.00017075691066555936, "epoch": 1.3, "step": 36430}
+{"loss": 0.7114, "learning_rate": 0.0001707213192549531, "epoch": 1.3, "step": 36440}
+{"loss": 0.6532, "learning_rate": 0.0001706857278443469, "epoch": 1.3, "step": 36450}
+{"loss": 0.6401, "learning_rate": 0.00017065013643374064, "epoch": 1.3, "step": 36460}
+{"loss": 0.6031, "learning_rate": 0.0001706145450231344, "epoch": 1.3, "step": 36470}
+{"loss": 0.5322, "learning_rate": 0.00017057895361252814, "epoch": 1.3, "step": 36480}
+{"loss": 0.5923, "learning_rate": 0.00017054336220192193, "epoch": 1.3, "step": 36490}
+{"loss": 0.6229, "learning_rate": 0.00017050777079131567, "epoch": 1.3, "step": 36500}
+{"loss": 0.5956, "learning_rate": 0.00017047217938070944, "epoch": 1.3, "step": 36510}
+{"loss": 0.7061, "learning_rate": 0.0001704365879701032, "epoch": 1.3, "step": 36520}
+{"loss": 0.6813, "learning_rate": 0.00017040099655949697, "epoch": 1.3, "step": 36530}
+{"loss": 0.5965, "learning_rate": 0.0001703654051488907, "epoch": 1.3, "step": 36540}
+{"loss": 0.6617, "learning_rate": 0.00017032981373828448, "epoch": 1.3, "step": 36550}
+{"loss": 0.6197, "learning_rate": 0.00017029422232767825, "epoch": 1.3, "step": 36560}
+{"loss": 0.5923, "learning_rate": 0.00017025863091707199, "epoch": 1.3, "step": 36570}
+{"loss": 0.6407, "learning_rate": 0.00017022303950646575, "epoch": 1.3, "step": 36580}
+{"loss": 0.7491, "learning_rate": 0.00017018744809585952, "epoch": 1.3, "step": 36590}
+{"loss": 0.5788, "learning_rate": 0.00017015185668525329, "epoch": 1.3, "step": 36600}
+{"loss": 0.5912, "learning_rate": 0.00017011626527464703, "epoch": 1.3, "step": 36610}
+{"loss": 0.6158, "learning_rate": 0.00017008067386404082, "epoch": 1.3, "step": 36620}
+{"loss": 0.5639, "learning_rate": 0.00017004508245343456, "epoch": 1.3, "step": 36630}
+{"loss": 0.6204, "learning_rate": 0.0001700094910428283, "epoch": 1.3, "step": 36640}
+{"loss": 0.542, "learning_rate": 0.0001699738996322221, "epoch": 1.3, "step": 36650}
+{"loss": 0.5382, "learning_rate": 0.00016993830822161583, "epoch": 1.3, "step": 36660}
+{"loss": 0.6179, "learning_rate": 0.0001699027168110096, "epoch": 1.3, "step": 36670}
+{"loss": 0.5101, "learning_rate": 0.00016986712540040336, "epoch": 1.3, "step": 36680}
+{"loss": 0.6837, "learning_rate": 0.00016983153398979713, "epoch": 1.3, "step": 36690}
+{"loss": 0.66, "learning_rate": 0.00016979594257919087, "epoch": 1.3, "step": 36700}
+{"loss": 0.5087, "learning_rate": 0.0001697603511685846, "epoch": 1.31, "step": 36710}
+{"loss": 0.662, "learning_rate": 0.0001697247597579784, "epoch": 1.31, "step": 36720}
+{"loss": 0.6966, "learning_rate": 0.00016968916834737214, "epoch": 1.31, "step": 36730}
+{"loss": 0.6055, "learning_rate": 0.0001696535769367659, "epoch": 1.31, "step": 36740}
+{"loss": 0.5968, "learning_rate": 0.00016961798552615968, "epoch": 1.31, "step": 36750}
+{"loss": 0.6237, "learning_rate": 0.00016958239411555344, "epoch": 1.31, "step": 36760}
+{"loss": 0.5716, "learning_rate": 0.00016954680270494718, "epoch": 1.31, "step": 36770}
+{"loss": 0.5689, "learning_rate": 0.00016951121129434098, "epoch": 1.31, "step": 36780}
+{"loss": 0.6113, "learning_rate": 0.00016947561988373471, "epoch": 1.31, "step": 36790}
+{"loss": 0.6078, "learning_rate": 0.00016944002847312845, "epoch": 1.31, "step": 36800}
+{"loss": 0.5904, "learning_rate": 0.00016940443706252222, "epoch": 1.31, "step": 36810}
+{"loss": 0.606, "learning_rate": 0.000169368845651916, "epoch": 1.31, "step": 36820}
+{"loss": 0.6208, "learning_rate": 0.00016933325424130975, "epoch": 1.31, "step": 36830}
+{"loss": 0.723, "learning_rate": 0.0001692976628307035, "epoch": 1.31, "step": 36840}
+{"loss": 0.638, "learning_rate": 0.0001692620714200973, "epoch": 1.31, "step": 36850}
+{"loss": 0.7124, "learning_rate": 0.00016922648000949103, "epoch": 1.31, "step": 36860}
+{"loss": 0.5899, "learning_rate": 0.00016919088859888477, "epoch": 1.31, "step": 36870}
+{"loss": 0.5808, "learning_rate": 0.00016915529718827856, "epoch": 1.31, "step": 36880}
+{"loss": 0.4925, "learning_rate": 0.0001691197057776723, "epoch": 1.31, "step": 36890}
+{"loss": 0.5048, "learning_rate": 0.00016908411436706607, "epoch": 1.31, "step": 36900}
+{"loss": 0.5432, "learning_rate": 0.00016904852295645983, "epoch": 1.31, "step": 36910}
+{"loss": 0.6509, "learning_rate": 0.0001690129315458536, "epoch": 1.31, "step": 36920}
+{"loss": 0.5877, "learning_rate": 0.00016897734013524734, "epoch": 1.31, "step": 36930}
+{"loss": 0.5515, "learning_rate": 0.00016894174872464108, "epoch": 1.31, "step": 36940}
+{"loss": 0.6036, "learning_rate": 0.00016890615731403487, "epoch": 1.31, "step": 36950}
+{"loss": 0.66, "learning_rate": 0.0001688705659034286, "epoch": 1.31, "step": 36960}
+{"loss": 0.5511, "learning_rate": 0.00016883497449282238, "epoch": 1.31, "step": 36970}
+{"loss": 0.6044, "learning_rate": 0.00016879938308221614, "epoch": 1.31, "step": 36980}
+{"loss": 0.7099, "learning_rate": 0.0001687637916716099, "epoch": 1.31, "step": 36990}
+{"loss": 0.6027, "learning_rate": 0.00016872820026100365, "epoch": 1.32, "step": 37000}
+{"loss": 0.5572, "learning_rate": 0.00016869260885039744, "epoch": 1.32, "step": 37010}
+{"loss": 0.6017, "learning_rate": 0.00016865701743979118, "epoch": 1.32, "step": 37020}
+{"loss": 0.6449, "learning_rate": 0.00016862142602918495, "epoch": 1.32, "step": 37030}
+{"loss": 0.5116, "learning_rate": 0.0001685858346185787, "epoch": 1.32, "step": 37040}
+{"loss": 0.653, "learning_rate": 0.00016855024320797246, "epoch": 1.32, "step": 37050}
+{"loss": 0.5415, "learning_rate": 0.00016851465179736622, "epoch": 1.32, "step": 37060}
+{"loss": 0.6105, "learning_rate": 0.00016847906038675996, "epoch": 1.32, "step": 37070}
+{"loss": 0.6459, "learning_rate": 0.00016844346897615376, "epoch": 1.32, "step": 37080}
+{"loss": 0.6447, "learning_rate": 0.0001684078775655475, "epoch": 1.32, "step": 37090}
+{"loss": 0.6761, "learning_rate": 0.00016837228615494126, "epoch": 1.32, "step": 37100}
+{"loss": 0.5986, "learning_rate": 0.00016833669474433503, "epoch": 1.32, "step": 37110}
+{"loss": 0.6495, "learning_rate": 0.0001683011033337288, "epoch": 1.32, "step": 37120}
+{"loss": 0.5321, "learning_rate": 0.00016826551192312253, "epoch": 1.32, "step": 37130}
+{"loss": 0.5852, "learning_rate": 0.00016822992051251633, "epoch": 1.32, "step": 37140}
+{"loss": 0.5463, "learning_rate": 0.00016819432910191007, "epoch": 1.32, "step": 37150}
+{"loss": 0.676, "learning_rate": 0.0001681587376913038, "epoch": 1.32, "step": 37160}
+{"loss": 0.6045, "learning_rate": 0.00016812314628069757, "epoch": 1.32, "step": 37170}
+{"loss": 0.6173, "learning_rate": 0.00016808755487009134, "epoch": 1.32, "step": 37180}
+{"loss": 0.6602, "learning_rate": 0.0001680519634594851, "epoch": 1.32, "step": 37190}
+{"loss": 0.6244, "learning_rate": 0.00016801637204887885, "epoch": 1.32, "step": 37200}
+{"loss": 0.6517, "learning_rate": 0.00016798078063827264, "epoch": 1.32, "step": 37210}
+{"loss": 0.6033, "learning_rate": 0.00016794518922766638, "epoch": 1.32, "step": 37220}
+{"loss": 0.594, "learning_rate": 0.00016790959781706012, "epoch": 1.32, "step": 37230}
+{"loss": 0.6216, "learning_rate": 0.0001678740064064539, "epoch": 1.32, "step": 37240}
+{"loss": 0.6204, "learning_rate": 0.00016783841499584765, "epoch": 1.32, "step": 37250}
+{"loss": 0.564, "learning_rate": 0.00016780282358524142, "epoch": 1.32, "step": 37260}
+{"loss": 0.6548, "learning_rate": 0.00016776723217463516, "epoch": 1.32, "step": 37270}
+{"loss": 0.5397, "learning_rate": 0.00016773164076402895, "epoch": 1.33, "step": 37280}
+{"loss": 0.666, "learning_rate": 0.0001676960493534227, "epoch": 1.33, "step": 37290}
+{"loss": 0.7033, "learning_rate": 0.00016766045794281643, "epoch": 1.33, "step": 37300}
+{"loss": 0.6451, "learning_rate": 0.00016762486653221022, "epoch": 1.33, "step": 37310}
+{"loss": 0.6316, "learning_rate": 0.00016758927512160396, "epoch": 1.33, "step": 37320}
+{"loss": 0.606, "learning_rate": 0.00016755368371099773, "epoch": 1.33, "step": 37330}
+{"loss": 0.6093, "learning_rate": 0.0001675180923003915, "epoch": 1.33, "step": 37340}
+{"loss": 0.5978, "learning_rate": 0.00016748250088978526, "epoch": 1.33, "step": 37350}
+{"loss": 0.5997, "learning_rate": 0.000167446909479179, "epoch": 1.33, "step": 37360}
+{"loss": 0.5662, "learning_rate": 0.0001674113180685728, "epoch": 1.33, "step": 37370}
+{"loss": 0.5696, "learning_rate": 0.00016737572665796654, "epoch": 1.33, "step": 37380}
+{"loss": 0.5701, "learning_rate": 0.00016734013524736027, "epoch": 1.33, "step": 37390}
+{"loss": 0.5345, "learning_rate": 0.00016730454383675404, "epoch": 1.33, "step": 37400}
+{"loss": 0.6047, "learning_rate": 0.0001672689524261478, "epoch": 1.33, "step": 37410}
+{"loss": 0.6684, "learning_rate": 0.00016723336101554157, "epoch": 1.33, "step": 37420}
+{"loss": 0.6394, "learning_rate": 0.00016719776960493531, "epoch": 1.33, "step": 37430}
+{"loss": 0.6469, "learning_rate": 0.0001671621781943291, "epoch": 1.33, "step": 37440}
+{"loss": 0.526, "learning_rate": 0.00016712658678372285, "epoch": 1.33, "step": 37450}
+{"loss": 0.5772, "learning_rate": 0.00016709099537311659, "epoch": 1.33, "step": 37460}
+{"loss": 0.61, "learning_rate": 0.00016705540396251038, "epoch": 1.33, "step": 37470}
+{"loss": 0.5937, "learning_rate": 0.00016701981255190412, "epoch": 1.33, "step": 37480}
+{"loss": 0.6498, "learning_rate": 0.00016698422114129789, "epoch": 1.33, "step": 37490}
+{"loss": 0.5828, "learning_rate": 0.00016694862973069163, "epoch": 1.33, "step": 37500}
+{"loss": 0.6154, "learning_rate": 0.00016691303832008542, "epoch": 1.33, "step": 37510}
+{"loss": 0.5776, "learning_rate": 0.00016687744690947916, "epoch": 1.33, "step": 37520}
+{"loss": 0.6514, "learning_rate": 0.00016684185549887293, "epoch": 1.33, "step": 37530}
+{"loss": 0.6176, "learning_rate": 0.0001668062640882667, "epoch": 1.33, "step": 37540}
+{"loss": 0.6143, "learning_rate": 0.00016677067267766043, "epoch": 1.33, "step": 37550}
+{"loss": 0.5776, "learning_rate": 0.0001667350812670542, "epoch": 1.34, "step": 37560}
+{"loss": 0.6282, "learning_rate": 0.00016669948985644796, "epoch": 1.34, "step": 37570}
+{"loss": 0.7094, "learning_rate": 0.00016666389844584173, "epoch": 1.34, "step": 37580}
+{"loss": 0.6112, "learning_rate": 0.00016662830703523547, "epoch": 1.34, "step": 37590}
+{"loss": 0.6485, "learning_rate": 0.00016659271562462924, "epoch": 1.34, "step": 37600}
+{"loss": 0.5092, "learning_rate": 0.000166557124214023, "epoch": 1.34, "step": 37610}
+{"loss": 0.648, "learning_rate": 0.00016652153280341677, "epoch": 1.34, "step": 37620}
+{"loss": 0.669, "learning_rate": 0.0001664859413928105, "epoch": 1.34, "step": 37630}
+{"loss": 0.5825, "learning_rate": 0.0001664503499822043, "epoch": 1.34, "step": 37640}
+{"loss": 0.7019, "learning_rate": 0.00016641475857159804, "epoch": 1.34, "step": 37650}
+{"loss": 0.6895, "learning_rate": 0.00016637916716099178, "epoch": 1.34, "step": 37660}
+{"loss": 0.6605, "learning_rate": 0.00016634357575038558, "epoch": 1.34, "step": 37670}
+{"loss": 0.6304, "learning_rate": 0.00016630798433977932, "epoch": 1.34, "step": 37680}
+{"loss": 0.5878, "learning_rate": 0.00016627239292917308, "epoch": 1.34, "step": 37690}
+{"loss": 0.5567, "learning_rate": 0.00016623680151856685, "epoch": 1.34, "step": 37700}
+{"loss": 0.7252, "learning_rate": 0.00016620121010796061, "epoch": 1.34, "step": 37710}
+{"loss": 0.5765, "learning_rate": 0.00016616561869735435, "epoch": 1.34, "step": 37720}
+{"loss": 0.6325, "learning_rate": 0.0001661300272867481, "epoch": 1.34, "step": 37730}
+{"loss": 0.6906, "learning_rate": 0.0001660944358761419, "epoch": 1.34, "step": 37740}
+{"loss": 0.6197, "learning_rate": 0.00016605884446553563, "epoch": 1.34, "step": 37750}
+{"loss": 0.6186, "learning_rate": 0.0001660232530549294, "epoch": 1.34, "step": 37760}
+{"loss": 0.6073, "learning_rate": 0.00016598766164432316, "epoch": 1.34, "step": 37770}
+{"loss": 0.7429, "learning_rate": 0.00016595207023371693, "epoch": 1.34, "step": 37780}
+{"loss": 0.6595, "learning_rate": 0.00016591647882311067, "epoch": 1.34, "step": 37790}
+{"loss": 0.6925, "learning_rate": 0.00016588088741250446, "epoch": 1.34, "step": 37800}
+{"loss": 0.6715, "learning_rate": 0.0001658452960018982, "epoch": 1.34, "step": 37810}
+{"loss": 0.6119, "learning_rate": 0.00016580970459129194, "epoch": 1.34, "step": 37820}
+{"loss": 0.6941, "learning_rate": 0.0001657741131806857, "epoch": 1.34, "step": 37830}
+{"loss": 0.5321, "learning_rate": 0.00016573852177007947, "epoch": 1.35, "step": 37840}
+{"loss": 0.5437, "learning_rate": 0.00016570293035947324, "epoch": 1.35, "step": 37850}
+{"loss": 0.6818, "learning_rate": 0.00016566733894886698, "epoch": 1.35, "step": 37860}
+{"loss": 0.5539, "learning_rate": 0.00016563174753826077, "epoch": 1.35, "step": 37870}
+{"loss": 0.5567, "learning_rate": 0.0001655961561276545, "epoch": 1.35, "step": 37880}
+{"loss": 0.5346, "learning_rate": 0.00016556056471704825, "epoch": 1.35, "step": 37890}
+{"loss": 0.6578, "learning_rate": 0.00016552497330644204, "epoch": 1.35, "step": 37900}
+{"loss": 0.621, "learning_rate": 0.00016548938189583578, "epoch": 1.35, "step": 37910}
+{"loss": 0.6001, "learning_rate": 0.00016545379048522955, "epoch": 1.35, "step": 37920}
+{"loss": 0.6444, "learning_rate": 0.00016541819907462332, "epoch": 1.35, "step": 37930}
+{"loss": 0.6457, "learning_rate": 0.00016538260766401708, "epoch": 1.35, "step": 37940}
+{"loss": 0.6677, "learning_rate": 0.00016534701625341082, "epoch": 1.35, "step": 37950}
+{"loss": 0.6791, "learning_rate": 0.00016531142484280456, "epoch": 1.35, "step": 37960}
+{"loss": 0.5871, "learning_rate": 0.00016527583343219836, "epoch": 1.35, "step": 37970}
+{"loss": 0.5761, "learning_rate": 0.0001652402420215921, "epoch": 1.35, "step": 37980}
+{"loss": 0.5987, "learning_rate": 0.00016520465061098586, "epoch": 1.35, "step": 37990}
+{"loss": 0.7028, "learning_rate": 0.00016516905920037963, "epoch": 1.35, "step": 38000}
+{"loss": 0.4932, "learning_rate": 0.0001651334677897734, "epoch": 1.35, "step": 38010}
+{"loss": 0.6094, "learning_rate": 0.00016509787637916713, "epoch": 1.35, "step": 38020}
+{"loss": 0.5965, "learning_rate": 0.00016506228496856093, "epoch": 1.35, "step": 38030}
+{"loss": 0.5805, "learning_rate": 0.00016502669355795467, "epoch": 1.35, "step": 38040}
+{"loss": 0.5983, "learning_rate": 0.0001649911021473484, "epoch": 1.35, "step": 38050}
+{"loss": 0.5337, "learning_rate": 0.00016495551073674217, "epoch": 1.35, "step": 38060}
+{"loss": 0.605, "learning_rate": 0.00016491991932613594, "epoch": 1.35, "step": 38070}
+{"loss": 0.6278, "learning_rate": 0.0001648843279155297, "epoch": 1.35, "step": 38080}
+{"loss": 0.5465, "learning_rate": 0.00016484873650492345, "epoch": 1.35, "step": 38090}
+{"loss": 0.609, "learning_rate": 0.00016481314509431724, "epoch": 1.35, "step": 38100}
+{"loss": 0.5686, "learning_rate": 0.00016477755368371098, "epoch": 1.35, "step": 38110}
+{"loss": 0.7291, "learning_rate": 0.00016474196227310475, "epoch": 1.36, "step": 38120}
+{"loss": 0.6359, "learning_rate": 0.0001647063708624985, "epoch": 1.36, "step": 38130}
+{"loss": 0.5942, "learning_rate": 0.00016467077945189225, "epoch": 1.36, "step": 38140}
+{"loss": 0.6549, "learning_rate": 0.00016463518804128602, "epoch": 1.36, "step": 38150}
+{"loss": 0.5157, "learning_rate": 0.00016459959663067978, "epoch": 1.36, "step": 38160}
+{"loss": 0.5522, "learning_rate": 0.00016456400522007355, "epoch": 1.36, "step": 38170}
+{"loss": 0.6147, "learning_rate": 0.0001645284138094673, "epoch": 1.36, "step": 38180}
+{"loss": 0.6557, "learning_rate": 0.00016449282239886106, "epoch": 1.36, "step": 38190}
+{"loss": 0.71, "learning_rate": 0.00016445723098825482, "epoch": 1.36, "step": 38200}
+{"loss": 0.469, "learning_rate": 0.0001644216395776486, "epoch": 1.36, "step": 38210}
+{"loss": 0.6635, "learning_rate": 0.00016438604816704233, "epoch": 1.36, "step": 38220}
+{"loss": 0.6331, "learning_rate": 0.00016435045675643612, "epoch": 1.36, "step": 38230}
+{"loss": 0.5411, "learning_rate": 0.00016431486534582986, "epoch": 1.36, "step": 38240}
+{"loss": 0.5569, "learning_rate": 0.0001642792739352236, "epoch": 1.36, "step": 38250}
+{"loss": 0.7296, "learning_rate": 0.0001642436825246174, "epoch": 1.36, "step": 38260}
+{"loss": 0.5555, "learning_rate": 0.00016420809111401114, "epoch": 1.36, "step": 38270}
+{"loss": 0.6592, "learning_rate": 0.0001641724997034049, "epoch": 1.36, "step": 38280}
+{"loss": 0.5971, "learning_rate": 0.00016413690829279864, "epoch": 1.36, "step": 38290}
+{"loss": 0.5677, "learning_rate": 0.00016410131688219244, "epoch": 1.36, "step": 38300}
+{"loss": 0.6217, "learning_rate": 0.00016406572547158617, "epoch": 1.36, "step": 38310}
+{"loss": 0.622, "learning_rate": 0.00016403013406097991, "epoch": 1.36, "step": 38320}
+{"loss": 0.6465, "learning_rate": 0.0001639945426503737, "epoch": 1.36, "step": 38330}
+{"loss": 0.5848, "learning_rate": 0.00016395895123976745, "epoch": 1.36, "step": 38340}
+{"loss": 0.6005, "learning_rate": 0.00016392335982916121, "epoch": 1.36, "step": 38350}
+{"loss": 0.6728, "learning_rate": 0.00016388776841855498, "epoch": 1.36, "step": 38360}
+{"loss": 0.5593, "learning_rate": 0.00016385217700794875, "epoch": 1.36, "step": 38370}
+{"loss": 0.5825, "learning_rate": 0.0001638165855973425, "epoch": 1.36, "step": 38380}
+{"loss": 0.6818, "learning_rate": 0.00016378099418673628, "epoch": 1.36, "step": 38390}
+{"loss": 0.6416, "learning_rate": 0.00016374540277613002, "epoch": 1.37, "step": 38400}
+{"loss": 0.7466, "learning_rate": 0.00016370981136552376, "epoch": 1.37, "step": 38410}
+{"loss": 0.596, "learning_rate": 0.00016367421995491753, "epoch": 1.37, "step": 38420}
+{"loss": 0.574, "learning_rate": 0.0001636386285443113, "epoch": 1.37, "step": 38430}
+{"loss": 0.6595, "learning_rate": 0.00016360303713370506, "epoch": 1.37, "step": 38440}
+{"loss": 0.6545, "learning_rate": 0.0001635674457230988, "epoch": 1.37, "step": 38450}
+{"loss": 0.6703, "learning_rate": 0.0001635318543124926, "epoch": 1.37, "step": 38460}
+{"loss": 0.6218, "learning_rate": 0.00016349626290188633, "epoch": 1.37, "step": 38470}
+{"loss": 0.6813, "learning_rate": 0.00016346067149128007, "epoch": 1.37, "step": 38480}
+{"loss": 0.5914, "learning_rate": 0.00016342508008067386, "epoch": 1.37, "step": 38490}
+{"loss": 0.5602, "learning_rate": 0.0001633894886700676, "epoch": 1.37, "step": 38500}
+{"loss": 0.5716, "learning_rate": 0.00016335389725946137, "epoch": 1.37, "step": 38510}
+{"loss": 0.4835, "learning_rate": 0.0001633183058488551, "epoch": 1.37, "step": 38520}
+{"loss": 0.5643, "learning_rate": 0.0001632827144382489, "epoch": 1.37, "step": 38530}
+{"loss": 0.6415, "learning_rate": 0.00016324712302764264, "epoch": 1.37, "step": 38540}
+{"loss": 0.5389, "learning_rate": 0.00016321153161703638, "epoch": 1.37, "step": 38550}
+{"loss": 0.53, "learning_rate": 0.00016317594020643018, "epoch": 1.37, "step": 38560}
+{"loss": 0.653, "learning_rate": 0.00016314034879582392, "epoch": 1.37, "step": 38570}
+{"loss": 0.6952, "learning_rate": 0.00016310475738521768, "epoch": 1.37, "step": 38580}
+{"loss": 0.587, "learning_rate": 0.00016306916597461145, "epoch": 1.37, "step": 38590}
+{"loss": 0.6972, "learning_rate": 0.00016303357456400522, "epoch": 1.37, "step": 38600}
+{"loss": 0.5588, "learning_rate": 0.00016299798315339895, "epoch": 1.37, "step": 38610}
+{"loss": 0.5923, "learning_rate": 0.00016296239174279275, "epoch": 1.37, "step": 38620}
+{"loss": 0.5814, "learning_rate": 0.0001629268003321865, "epoch": 1.37, "step": 38630}
+{"loss": 0.5603, "learning_rate": 0.00016289120892158023, "epoch": 1.37, "step": 38640}
+{"loss": 0.7134, "learning_rate": 0.000162855617510974, "epoch": 1.37, "step": 38650}
+{"loss": 0.6625, "learning_rate": 0.00016282002610036776, "epoch": 1.37, "step": 38660}
+{"loss": 0.6164, "learning_rate": 0.00016278443468976153, "epoch": 1.37, "step": 38670}
+{"loss": 0.5891, "learning_rate": 0.00016274884327915527, "epoch": 1.38, "step": 38680}
+{"loss": 0.6687, "learning_rate": 0.00016271325186854906, "epoch": 1.38, "step": 38690}
+{"loss": 0.6397, "learning_rate": 0.0001626776604579428, "epoch": 1.38, "step": 38700}
+{"loss": 0.6173, "learning_rate": 0.00016264206904733657, "epoch": 1.38, "step": 38710}
+{"loss": 0.6145, "learning_rate": 0.00016260647763673033, "epoch": 1.38, "step": 38720}
+{"loss": 0.5998, "learning_rate": 0.0001625708862261241, "epoch": 1.38, "step": 38730}
+{"loss": 0.6278, "learning_rate": 0.00016253529481551784, "epoch": 1.38, "step": 38740}
+{"loss": 0.5276, "learning_rate": 0.00016249970340491158, "epoch": 1.38, "step": 38750}
+{"loss": 0.5773, "learning_rate": 0.00016246411199430537, "epoch": 1.38, "step": 38760}
+{"loss": 0.5389, "learning_rate": 0.0001624285205836991, "epoch": 1.38, "step": 38770}
+{"loss": 0.5396, "learning_rate": 0.00016239292917309288, "epoch": 1.38, "step": 38780}
+{"loss": 0.6357, "learning_rate": 0.00016235733776248664, "epoch": 1.38, "step": 38790}
+{"loss": 0.6555, "learning_rate": 0.0001623217463518804, "epoch": 1.38, "step": 38800}
+{"loss": 0.6004, "learning_rate": 0.00016228615494127415, "epoch": 1.38, "step": 38810}
+{"loss": 0.6563, "learning_rate": 0.00016225056353066794, "epoch": 1.38, "step": 38820}
+{"loss": 0.5752, "learning_rate": 0.00016221497212006168, "epoch": 1.38, "step": 38830}
+{"loss": 0.5483, "learning_rate": 0.00016217938070945542, "epoch": 1.38, "step": 38840}
+{"loss": 0.6046, "learning_rate": 0.0001621437892988492, "epoch": 1.38, "step": 38850}
+{"loss": 0.6429, "learning_rate": 0.00016210819788824296, "epoch": 1.38, "step": 38860}
+{"loss": 0.6216, "learning_rate": 0.00016207260647763672, "epoch": 1.38, "step": 38870}
+{"loss": 0.6383, "learning_rate": 0.00016203701506703046, "epoch": 1.38, "step": 38880}
+{"loss": 0.569, "learning_rate": 0.00016200142365642426, "epoch": 1.38, "step": 38890}
+{"loss": 0.5757, "learning_rate": 0.000161965832245818, "epoch": 1.38, "step": 38900}
+{"loss": 0.562, "learning_rate": 0.00016193024083521173, "epoch": 1.38, "step": 38910}
+{"loss": 0.6005, "learning_rate": 0.00016189464942460553, "epoch": 1.38, "step": 38920}
+{"loss": 0.6711, "learning_rate": 0.00016185905801399927, "epoch": 1.38, "step": 38930}
+{"loss": 0.545, "learning_rate": 0.00016182346660339303, "epoch": 1.38, "step": 38940}
+{"loss": 0.5323, "learning_rate": 0.0001617878751927868, "epoch": 1.38, "step": 38950}
+{"loss": 0.5466, "learning_rate": 0.00016175228378218057, "epoch": 1.38, "step": 38960}
+{"loss": 0.6332, "learning_rate": 0.0001617166923715743, "epoch": 1.39, "step": 38970}
+{"loss": 0.6207, "learning_rate": 0.00016168110096096805, "epoch": 1.39, "step": 38980}
+{"loss": 0.7036, "learning_rate": 0.00016164550955036184, "epoch": 1.39, "step": 38990}
+{"loss": 0.6836, "learning_rate": 0.00016160991813975558, "epoch": 1.39, "step": 39000}
+{"loss": 0.6006, "learning_rate": 0.00016157432672914935, "epoch": 1.39, "step": 39010}
+{"loss": 0.639, "learning_rate": 0.0001615387353185431, "epoch": 1.39, "step": 39020}
+{"loss": 0.5982, "learning_rate": 0.00016150314390793688, "epoch": 1.39, "step": 39030}
+{"loss": 0.5631, "learning_rate": 0.00016146755249733062, "epoch": 1.39, "step": 39040}
+{"train_runtime": 4104.6765, "train_samples_per_second": 20.559, "train_steps_per_second": 20.559, "total_flos": 3.48290350453162e+17, "train_loss": 0.333335518724021, "epoch": 1.39, "step": 39049}
\ No newline at end of file