{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 3402, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008818342151675485, "grad_norm": 1.4955648753589619, "learning_rate": 3.883495145631068e-06, "loss": 0.4452, "step": 10 }, { "epoch": 0.01763668430335097, "grad_norm": 0.8166020313583234, "learning_rate": 7.766990291262136e-06, "loss": 0.3563, "step": 20 }, { "epoch": 0.026455026455026454, "grad_norm": 1.0139812433784159, "learning_rate": 1.1650485436893204e-05, "loss": 0.2954, "step": 30 }, { "epoch": 0.03527336860670194, "grad_norm": 1.121332128031883, "learning_rate": 1.5533980582524273e-05, "loss": 0.264, "step": 40 }, { "epoch": 0.04409171075837742, "grad_norm": 1.5248485572756025, "learning_rate": 1.9417475728155343e-05, "loss": 0.2515, "step": 50 }, { "epoch": 0.05291005291005291, "grad_norm": 0.7086102688104752, "learning_rate": 2.330097087378641e-05, "loss": 0.2384, "step": 60 }, { "epoch": 0.06172839506172839, "grad_norm": 0.6620513303312378, "learning_rate": 2.718446601941748e-05, "loss": 0.2371, "step": 70 }, { "epoch": 0.07054673721340388, "grad_norm": 1.1439083265825398, "learning_rate": 3.1067961165048545e-05, "loss": 0.2316, "step": 80 }, { "epoch": 0.07936507936507936, "grad_norm": 0.8671080906528094, "learning_rate": 3.4951456310679615e-05, "loss": 0.2243, "step": 90 }, { "epoch": 0.08818342151675485, "grad_norm": 0.8521737444390105, "learning_rate": 3.8834951456310685e-05, "loss": 0.2216, "step": 100 }, { "epoch": 0.09700176366843033, "grad_norm": 0.820039351853962, "learning_rate": 3.9999555645496425e-05, "loss": 0.2181, "step": 110 }, { "epoch": 0.10582010582010581, "grad_norm": 0.4284687555753216, "learning_rate": 3.999737926280763e-05, "loss": 0.2123, "step": 120 }, { "epoch": 0.1146384479717813, "grad_norm": 1.0310561704789347, "learning_rate": 3.999338943291723e-05, "loss": 0.2072, "step": 130 }, { "epoch": 0.12345679012345678, "grad_norm": 0.48329839911504663, "learning_rate": 3.998758651763991e-05, "loss": 0.2046, "step": 140 }, { "epoch": 0.13227513227513227, "grad_norm": 0.43509409688235956, "learning_rate": 3.9979971043208656e-05, "loss": 0.2017, "step": 150 }, { "epoch": 0.14109347442680775, "grad_norm": 0.3421062202275864, "learning_rate": 3.997054370022701e-05, "loss": 0.2026, "step": 160 }, { "epoch": 0.14991181657848324, "grad_norm": 0.41797655307441983, "learning_rate": 3.995930534360642e-05, "loss": 0.1972, "step": 170 }, { "epoch": 0.15873015873015872, "grad_norm": 0.40272951427585846, "learning_rate": 3.994625699248876e-05, "loss": 0.1947, "step": 180 }, { "epoch": 0.1675485008818342, "grad_norm": 0.35340459426606163, "learning_rate": 3.993139983015388e-05, "loss": 0.1971, "step": 190 }, { "epoch": 0.1763668430335097, "grad_norm": 0.7994951274374914, "learning_rate": 3.9914735203912274e-05, "loss": 0.1925, "step": 200 }, { "epoch": 0.18518518518518517, "grad_norm": 0.40411453618039694, "learning_rate": 3.989626462498299e-05, "loss": 0.192, "step": 210 }, { "epoch": 0.19400352733686066, "grad_norm": 0.31941758385605157, "learning_rate": 3.9875989768356474e-05, "loss": 0.1868, "step": 220 }, { "epoch": 0.20282186948853614, "grad_norm": 0.3142908369196689, "learning_rate": 3.9853912472642766e-05, "loss": 0.1893, "step": 230 }, { "epoch": 0.21164021164021163, "grad_norm": 0.3241679786689458, "learning_rate": 3.9830034739904716e-05, "loss": 0.1863, "step": 240 }, { "epoch": 0.2204585537918871, "grad_norm": 0.31178995966174394, "learning_rate": 3.980435873547643e-05, "loss": 0.1862, "step": 250 }, { "epoch": 0.2292768959435626, "grad_norm": 0.47323032502490103, "learning_rate": 3.977688678776695e-05, "loss": 0.1851, "step": 260 }, { "epoch": 0.23809523809523808, "grad_norm": 0.3265364244937022, "learning_rate": 3.974762138804906e-05, "loss": 0.1865, "step": 270 }, { "epoch": 0.24691358024691357, "grad_norm": 0.34222373145685614, "learning_rate": 3.971656519023337e-05, "loss": 0.1817, "step": 280 }, { "epoch": 0.25573192239858905, "grad_norm": 0.3739773461101385, "learning_rate": 3.9683721010627666e-05, "loss": 0.1818, "step": 290 }, { "epoch": 0.26455026455026454, "grad_norm": 0.30430093336446573, "learning_rate": 3.964909182768153e-05, "loss": 0.18, "step": 300 }, { "epoch": 0.27336860670194, "grad_norm": 0.34663011155426887, "learning_rate": 3.9612680781716203e-05, "loss": 0.1803, "step": 310 }, { "epoch": 0.2821869488536155, "grad_norm": 0.298542445104257, "learning_rate": 3.9574491174639824e-05, "loss": 0.1789, "step": 320 }, { "epoch": 0.291005291005291, "grad_norm": 0.2685161967289745, "learning_rate": 3.9534526469648e-05, "loss": 0.178, "step": 330 }, { "epoch": 0.2998236331569665, "grad_norm": 0.39999602620736396, "learning_rate": 3.949279029090976e-05, "loss": 0.179, "step": 340 }, { "epoch": 0.30864197530864196, "grad_norm": 0.36622856228147127, "learning_rate": 3.944928642323887e-05, "loss": 0.1786, "step": 350 }, { "epoch": 0.31746031746031744, "grad_norm": 0.4663556460380618, "learning_rate": 3.940401881175065e-05, "loss": 0.18, "step": 360 }, { "epoch": 0.3262786596119929, "grad_norm": 0.3720323085775275, "learning_rate": 3.9356991561504177e-05, "loss": 0.1776, "step": 370 }, { "epoch": 0.3350970017636684, "grad_norm": 0.302010044803705, "learning_rate": 3.9308208937130046e-05, "loss": 0.1763, "step": 380 }, { "epoch": 0.3439153439153439, "grad_norm": 0.31665097292956457, "learning_rate": 3.925767536244362e-05, "loss": 0.1751, "step": 390 }, { "epoch": 0.3527336860670194, "grad_norm": 0.3228908226384742, "learning_rate": 3.920539542004387e-05, "loss": 0.1745, "step": 400 }, { "epoch": 0.36155202821869487, "grad_norm": 0.2799415607873476, "learning_rate": 3.915137385089781e-05, "loss": 0.1749, "step": 410 }, { "epoch": 0.37037037037037035, "grad_norm": 0.24387451434550744, "learning_rate": 3.909561555391053e-05, "loss": 0.174, "step": 420 }, { "epoch": 0.37918871252204583, "grad_norm": 0.2726005390731001, "learning_rate": 3.903812558548099e-05, "loss": 0.1734, "step": 430 }, { "epoch": 0.3880070546737213, "grad_norm": 0.3028874282302824, "learning_rate": 3.8978909159043465e-05, "loss": 0.174, "step": 440 }, { "epoch": 0.3968253968253968, "grad_norm": 0.2512628489766056, "learning_rate": 3.891797164459477e-05, "loss": 0.1715, "step": 450 }, { "epoch": 0.4056437389770723, "grad_norm": 0.23809767948700475, "learning_rate": 3.885531856820726e-05, "loss": 0.1707, "step": 460 }, { "epoch": 0.4144620811287478, "grad_norm": 0.27178090104851893, "learning_rate": 3.8790955611527754e-05, "loss": 0.1702, "step": 470 }, { "epoch": 0.42328042328042326, "grad_norm": 0.3849347266422906, "learning_rate": 3.872488861126226e-05, "loss": 0.1688, "step": 480 }, { "epoch": 0.43209876543209874, "grad_norm": 0.3597097968078764, "learning_rate": 3.865712355864668e-05, "loss": 0.169, "step": 490 }, { "epoch": 0.4409171075837742, "grad_norm": 0.26535671712243575, "learning_rate": 3.8587666598903526e-05, "loss": 0.1672, "step": 500 }, { "epoch": 0.4497354497354497, "grad_norm": 0.27483599851665746, "learning_rate": 3.851652403068461e-05, "loss": 0.1726, "step": 510 }, { "epoch": 0.4585537918871252, "grad_norm": 0.27278517138668995, "learning_rate": 3.8443702305499886e-05, "loss": 0.1704, "step": 520 }, { "epoch": 0.4673721340388007, "grad_norm": 0.24988566985125385, "learning_rate": 3.836920802713238e-05, "loss": 0.1671, "step": 530 }, { "epoch": 0.47619047619047616, "grad_norm": 0.34671624980077004, "learning_rate": 3.829304795103933e-05, "loss": 0.1672, "step": 540 }, { "epoch": 0.48500881834215165, "grad_norm": 0.309822758612831, "learning_rate": 3.82152289837396e-05, "loss": 0.1666, "step": 550 }, { "epoch": 0.49382716049382713, "grad_norm": 0.2735497475576908, "learning_rate": 3.813575818218732e-05, "loss": 0.1686, "step": 560 }, { "epoch": 0.5026455026455027, "grad_norm": 0.29690091794159296, "learning_rate": 3.8054642753132e-05, "loss": 0.1669, "step": 570 }, { "epoch": 0.5114638447971781, "grad_norm": 0.25476479109627226, "learning_rate": 3.797189005246489e-05, "loss": 0.1622, "step": 580 }, { "epoch": 0.5202821869488536, "grad_norm": 0.21847320529770614, "learning_rate": 3.788750758455204e-05, "loss": 0.1629, "step": 590 }, { "epoch": 0.5291005291005291, "grad_norm": 0.22282921245577492, "learning_rate": 3.7801503001553664e-05, "loss": 0.1682, "step": 600 }, { "epoch": 0.5379188712522046, "grad_norm": 0.2964689468325172, "learning_rate": 3.771388410273027e-05, "loss": 0.1672, "step": 610 }, { "epoch": 0.54673721340388, "grad_norm": 0.2828883507477133, "learning_rate": 3.762465883373539e-05, "loss": 0.1618, "step": 620 }, { "epoch": 0.5555555555555556, "grad_norm": 0.2856702713626834, "learning_rate": 3.753383528589499e-05, "loss": 0.1639, "step": 630 }, { "epoch": 0.564373897707231, "grad_norm": 0.25603423467383013, "learning_rate": 3.744142169547376e-05, "loss": 0.1603, "step": 640 }, { "epoch": 0.5731922398589065, "grad_norm": 0.24322397045686334, "learning_rate": 3.734742644292821e-05, "loss": 0.1627, "step": 650 }, { "epoch": 0.582010582010582, "grad_norm": 0.21120093154802644, "learning_rate": 3.725185805214665e-05, "loss": 0.1639, "step": 660 }, { "epoch": 0.5908289241622575, "grad_norm": 0.2455862358583795, "learning_rate": 3.7154725189676264e-05, "loss": 0.1619, "step": 670 }, { "epoch": 0.599647266313933, "grad_norm": 0.2665765386539727, "learning_rate": 3.7056036663937164e-05, "loss": 0.165, "step": 680 }, { "epoch": 0.6084656084656085, "grad_norm": 0.23935749033120898, "learning_rate": 3.695580142442361e-05, "loss": 0.1614, "step": 690 }, { "epoch": 0.6172839506172839, "grad_norm": 0.23327066612729097, "learning_rate": 3.685402856089242e-05, "loss": 0.1618, "step": 700 }, { "epoch": 0.6261022927689595, "grad_norm": 0.2295032987661733, "learning_rate": 3.675072730253868e-05, "loss": 0.1655, "step": 710 }, { "epoch": 0.6349206349206349, "grad_norm": 0.2597641502201965, "learning_rate": 3.6645907017158814e-05, "loss": 0.1608, "step": 720 }, { "epoch": 0.6437389770723104, "grad_norm": 0.24169971877971796, "learning_rate": 3.653957721030107e-05, "loss": 0.1606, "step": 730 }, { "epoch": 0.6525573192239859, "grad_norm": 0.23805929987756733, "learning_rate": 3.64317475244035e-05, "loss": 0.1624, "step": 740 }, { "epoch": 0.6613756613756614, "grad_norm": 0.21337182553159947, "learning_rate": 3.632242773791952e-05, "loss": 0.1605, "step": 750 }, { "epoch": 0.6701940035273368, "grad_norm": 0.2086929717616856, "learning_rate": 3.621162776443125e-05, "loss": 0.1597, "step": 760 }, { "epoch": 0.6790123456790124, "grad_norm": 0.20642071715098376, "learning_rate": 3.60993576517504e-05, "loss": 0.1609, "step": 770 }, { "epoch": 0.6878306878306878, "grad_norm": 0.19167244052151497, "learning_rate": 3.598562758100716e-05, "loss": 0.1607, "step": 780 }, { "epoch": 0.6966490299823633, "grad_norm": 0.2285439297223176, "learning_rate": 3.5870447865726913e-05, "loss": 0.1606, "step": 790 }, { "epoch": 0.7054673721340388, "grad_norm": 0.2173697770388281, "learning_rate": 3.575382895089495e-05, "loss": 0.161, "step": 800 }, { "epoch": 0.7142857142857143, "grad_norm": 0.2831703519646522, "learning_rate": 3.563578141200929e-05, "loss": 0.1592, "step": 810 }, { "epoch": 0.7231040564373897, "grad_norm": 0.23525021695459578, "learning_rate": 3.551631595412164e-05, "loss": 0.1596, "step": 820 }, { "epoch": 0.7319223985890653, "grad_norm": 0.254325105892367, "learning_rate": 3.539544341086663e-05, "loss": 0.1565, "step": 830 }, { "epoch": 0.7407407407407407, "grad_norm": 0.20727493642114397, "learning_rate": 3.5273174743479336e-05, "loss": 0.1581, "step": 840 }, { "epoch": 0.7495590828924162, "grad_norm": 0.25745565286011807, "learning_rate": 3.514952103980132e-05, "loss": 0.1598, "step": 850 }, { "epoch": 0.7583774250440917, "grad_norm": 0.19482500821770854, "learning_rate": 3.50244935132751e-05, "loss": 0.1586, "step": 860 }, { "epoch": 0.7671957671957672, "grad_norm": 0.20509823998997453, "learning_rate": 3.489810350192729e-05, "loss": 0.1559, "step": 870 }, { "epoch": 0.7760141093474426, "grad_norm": 0.20895652988918806, "learning_rate": 3.477036246734038e-05, "loss": 0.1563, "step": 880 }, { "epoch": 0.7848324514991182, "grad_norm": 0.27987607099152345, "learning_rate": 3.4641281993613406e-05, "loss": 0.1596, "step": 890 }, { "epoch": 0.7936507936507936, "grad_norm": 0.19730219851608477, "learning_rate": 3.451087378631143e-05, "loss": 0.1579, "step": 900 }, { "epoch": 0.8024691358024691, "grad_norm": 0.20906456760570116, "learning_rate": 3.437914967140401e-05, "loss": 0.1571, "step": 910 }, { "epoch": 0.8112874779541446, "grad_norm": 0.22886723809980594, "learning_rate": 3.4246121594192814e-05, "loss": 0.157, "step": 920 }, { "epoch": 0.8201058201058201, "grad_norm": 0.19417100843050594, "learning_rate": 3.411180161822831e-05, "loss": 0.1554, "step": 930 }, { "epoch": 0.8289241622574955, "grad_norm": 0.26409165069315016, "learning_rate": 3.3976201924215854e-05, "loss": 0.1557, "step": 940 }, { "epoch": 0.8377425044091711, "grad_norm": 0.25269001142437164, "learning_rate": 3.3839334808911057e-05, "loss": 0.155, "step": 950 }, { "epoch": 0.8465608465608465, "grad_norm": 0.28787596764707246, "learning_rate": 3.370121268400467e-05, "loss": 0.1554, "step": 960 }, { "epoch": 0.855379188712522, "grad_norm": 0.20073900051671914, "learning_rate": 3.356184807499705e-05, "loss": 0.1543, "step": 970 }, { "epoch": 0.8641975308641975, "grad_norm": 0.19523250730479108, "learning_rate": 3.342125362006226e-05, "loss": 0.1552, "step": 980 }, { "epoch": 0.873015873015873, "grad_norm": 0.2332670363257663, "learning_rate": 3.3279442068902024e-05, "loss": 0.155, "step": 990 }, { "epoch": 0.8818342151675485, "grad_norm": 0.21314128725157566, "learning_rate": 3.3136426281589525e-05, "loss": 0.1559, "step": 1000 }, { "epoch": 0.890652557319224, "grad_norm": 0.2073616768080302, "learning_rate": 3.299221922740318e-05, "loss": 0.1555, "step": 1010 }, { "epoch": 0.8994708994708994, "grad_norm": 0.20612629267891894, "learning_rate": 3.284683398365053e-05, "loss": 0.1544, "step": 1020 }, { "epoch": 0.908289241622575, "grad_norm": 0.192587617407336, "learning_rate": 3.270028373448237e-05, "loss": 0.156, "step": 1030 }, { "epoch": 0.9171075837742504, "grad_norm": 0.20076697321476172, "learning_rate": 3.255258176969711e-05, "loss": 0.1525, "step": 1040 }, { "epoch": 0.9259259259259259, "grad_norm": 0.20063292329444252, "learning_rate": 3.2403741483535624e-05, "loss": 0.1579, "step": 1050 }, { "epoch": 0.9347442680776014, "grad_norm": 0.2188372918686337, "learning_rate": 3.22537763734666e-05, "loss": 0.1545, "step": 1060 }, { "epoch": 0.9435626102292769, "grad_norm": 0.2348876410690357, "learning_rate": 3.210270003896254e-05, "loss": 0.1523, "step": 1070 }, { "epoch": 0.9523809523809523, "grad_norm": 0.21610514112165158, "learning_rate": 3.195052618026646e-05, "loss": 0.1498, "step": 1080 }, { "epoch": 0.9611992945326279, "grad_norm": 0.17805564179617644, "learning_rate": 3.1797268597149575e-05, "loss": 0.1533, "step": 1090 }, { "epoch": 0.9700176366843033, "grad_norm": 0.19468985685608828, "learning_rate": 3.1642941187659784e-05, "loss": 0.1505, "step": 1100 }, { "epoch": 0.9788359788359788, "grad_norm": 0.17922597209513355, "learning_rate": 3.1487557946861413e-05, "loss": 0.154, "step": 1110 }, { "epoch": 0.9876543209876543, "grad_norm": 0.20699394719540626, "learning_rate": 3.133113296556603e-05, "loss": 0.1495, "step": 1120 }, { "epoch": 0.9964726631393298, "grad_norm": 0.18289020763400496, "learning_rate": 3.117368042905466e-05, "loss": 0.1517, "step": 1130 }, { "epoch": 1.0052910052910053, "grad_norm": 0.2145241959606213, "learning_rate": 3.101521461579139e-05, "loss": 0.1409, "step": 1140 }, { "epoch": 1.0141093474426808, "grad_norm": 0.20230933218493735, "learning_rate": 3.085574989612856e-05, "loss": 0.1321, "step": 1150 }, { "epoch": 1.0229276895943562, "grad_norm": 0.18244350688332062, "learning_rate": 3.069530073100356e-05, "loss": 0.1313, "step": 1160 }, { "epoch": 1.0317460317460316, "grad_norm": 0.19783195547267102, "learning_rate": 3.053388167062747e-05, "loss": 0.1321, "step": 1170 }, { "epoch": 1.0405643738977073, "grad_norm": 0.2047114005081859, "learning_rate": 3.037150735316561e-05, "loss": 0.1332, "step": 1180 }, { "epoch": 1.0493827160493827, "grad_norm": 0.24595017471664576, "learning_rate": 3.0208192503410046e-05, "loss": 0.131, "step": 1190 }, { "epoch": 1.0582010582010581, "grad_norm": 0.23144086447587278, "learning_rate": 3.0043951931444302e-05, "loss": 0.1327, "step": 1200 }, { "epoch": 1.0670194003527338, "grad_norm": 0.16985629437769836, "learning_rate": 2.9878800531300335e-05, "loss": 0.1337, "step": 1210 }, { "epoch": 1.0758377425044092, "grad_norm": 0.19256405636053653, "learning_rate": 2.9712753279607852e-05, "loss": 0.1364, "step": 1220 }, { "epoch": 1.0846560846560847, "grad_norm": 0.18555434282413438, "learning_rate": 2.9545825234236187e-05, "loss": 0.1306, "step": 1230 }, { "epoch": 1.09347442680776, "grad_norm": 0.1847579476124522, "learning_rate": 2.937803153292878e-05, "loss": 0.1342, "step": 1240 }, { "epoch": 1.1022927689594355, "grad_norm": 0.1834216574450437, "learning_rate": 2.9209387391930425e-05, "loss": 0.1341, "step": 1250 }, { "epoch": 1.1111111111111112, "grad_norm": 0.18665818389653582, "learning_rate": 2.9039908104607395e-05, "loss": 0.1333, "step": 1260 }, { "epoch": 1.1199294532627866, "grad_norm": 0.22873933014699052, "learning_rate": 2.8869609040060572e-05, "loss": 0.1336, "step": 1270 }, { "epoch": 1.128747795414462, "grad_norm": 0.2183113906263531, "learning_rate": 2.869850564173172e-05, "loss": 0.1323, "step": 1280 }, { "epoch": 1.1375661375661377, "grad_norm": 0.19099060399929857, "learning_rate": 2.8526613426002998e-05, "loss": 0.1319, "step": 1290 }, { "epoch": 1.146384479717813, "grad_norm": 0.23917372520488436, "learning_rate": 2.835394798078988e-05, "loss": 0.1321, "step": 1300 }, { "epoch": 1.1552028218694885, "grad_norm": 0.18407428002576853, "learning_rate": 2.8180524964127573e-05, "loss": 0.1317, "step": 1310 }, { "epoch": 1.164021164021164, "grad_norm": 0.18430803378192598, "learning_rate": 2.8006360102751064e-05, "loss": 0.1322, "step": 1320 }, { "epoch": 1.1728395061728394, "grad_norm": 0.1865135026451199, "learning_rate": 2.7831469190668974e-05, "loss": 0.133, "step": 1330 }, { "epoch": 1.181657848324515, "grad_norm": 0.1884073237139698, "learning_rate": 2.7655868087731295e-05, "loss": 0.1317, "step": 1340 }, { "epoch": 1.1904761904761905, "grad_norm": 0.20367415474239536, "learning_rate": 2.7479572718191108e-05, "loss": 0.1333, "step": 1350 }, { "epoch": 1.199294532627866, "grad_norm": 0.17284748829644184, "learning_rate": 2.7302599069260572e-05, "loss": 0.1309, "step": 1360 }, { "epoch": 1.2081128747795415, "grad_norm": 0.19491278141231555, "learning_rate": 2.712496318966108e-05, "loss": 0.1314, "step": 1370 }, { "epoch": 1.216931216931217, "grad_norm": 0.18728688430541293, "learning_rate": 2.69466811881679e-05, "loss": 0.1334, "step": 1380 }, { "epoch": 1.2257495590828924, "grad_norm": 0.17142414955172516, "learning_rate": 2.67677692321494e-05, "loss": 0.1331, "step": 1390 }, { "epoch": 1.2345679012345678, "grad_norm": 0.20066666678092135, "learning_rate": 2.6588243546100882e-05, "loss": 0.1313, "step": 1400 }, { "epoch": 1.2433862433862433, "grad_norm": 0.17159972944285481, "learning_rate": 2.6408120410173296e-05, "loss": 0.1287, "step": 1410 }, { "epoch": 1.252204585537919, "grad_norm": 0.19860628522583873, "learning_rate": 2.6227416158696884e-05, "loss": 0.1297, "step": 1420 }, { "epoch": 1.2610229276895943, "grad_norm": 0.18008904396878098, "learning_rate": 2.60461471786999e-05, "loss": 0.1309, "step": 1430 }, { "epoch": 1.2698412698412698, "grad_norm": 0.19386888274171976, "learning_rate": 2.5864329908422597e-05, "loss": 0.1292, "step": 1440 }, { "epoch": 1.2786596119929454, "grad_norm": 0.17303097118338565, "learning_rate": 2.5681980835826503e-05, "loss": 0.1295, "step": 1450 }, { "epoch": 1.2874779541446209, "grad_norm": 0.2348921814277289, "learning_rate": 2.5499116497099224e-05, "loss": 0.1314, "step": 1460 }, { "epoch": 1.2962962962962963, "grad_norm": 0.1778768891302646, "learning_rate": 2.531575347515492e-05, "loss": 0.1318, "step": 1470 }, { "epoch": 1.3051146384479717, "grad_norm": 0.17862605604327308, "learning_rate": 2.5131908398130426e-05, "loss": 0.1291, "step": 1480 }, { "epoch": 1.3139329805996471, "grad_norm": 0.1840381159551672, "learning_rate": 2.49475979378774e-05, "loss": 0.1299, "step": 1490 }, { "epoch": 1.3227513227513228, "grad_norm": 0.20235876379158219, "learning_rate": 2.476283880845042e-05, "loss": 0.1333, "step": 1500 }, { "epoch": 1.3315696649029982, "grad_norm": 0.17181294480397433, "learning_rate": 2.4577647764591276e-05, "loss": 0.1311, "step": 1510 }, { "epoch": 1.3403880070546736, "grad_norm": 0.17352177231303226, "learning_rate": 2.4392041600209608e-05, "loss": 0.1298, "step": 1520 }, { "epoch": 1.3492063492063493, "grad_norm": 0.16851418392357184, "learning_rate": 2.4206037146859944e-05, "loss": 0.1266, "step": 1530 }, { "epoch": 1.3580246913580247, "grad_norm": 0.18412108629041574, "learning_rate": 2.4019651272215338e-05, "loss": 0.131, "step": 1540 }, { "epoch": 1.3668430335097002, "grad_norm": 0.1643456743151178, "learning_rate": 2.383290087853775e-05, "loss": 0.1327, "step": 1550 }, { "epoch": 1.3756613756613756, "grad_norm": 0.16300381228966188, "learning_rate": 2.364580290114527e-05, "loss": 0.1328, "step": 1560 }, { "epoch": 1.384479717813051, "grad_norm": 0.19794647549566596, "learning_rate": 2.3458374306876355e-05, "loss": 0.1337, "step": 1570 }, { "epoch": 1.3932980599647267, "grad_norm": 0.17467360938800394, "learning_rate": 2.327063209255121e-05, "loss": 0.128, "step": 1580 }, { "epoch": 1.402116402116402, "grad_norm": 0.16534045366329517, "learning_rate": 2.308259328343042e-05, "loss": 0.1294, "step": 1590 }, { "epoch": 1.4109347442680775, "grad_norm": 0.17164884564245564, "learning_rate": 2.289427493167107e-05, "loss": 0.1291, "step": 1600 }, { "epoch": 1.4197530864197532, "grad_norm": 0.17685950000349324, "learning_rate": 2.270569411478033e-05, "loss": 0.1274, "step": 1610 }, { "epoch": 1.4285714285714286, "grad_norm": 0.1831151884550037, "learning_rate": 2.251686793406684e-05, "loss": 0.1297, "step": 1620 }, { "epoch": 1.437389770723104, "grad_norm": 0.17974969366439886, "learning_rate": 2.2327813513089875e-05, "loss": 0.1302, "step": 1630 }, { "epoch": 1.4462081128747795, "grad_norm": 0.16155993308368063, "learning_rate": 2.213854799610649e-05, "loss": 0.1285, "step": 1640 }, { "epoch": 1.455026455026455, "grad_norm": 0.1654535308338956, "learning_rate": 2.194908854651683e-05, "loss": 0.1289, "step": 1650 }, { "epoch": 1.4638447971781305, "grad_norm": 0.16507648912276562, "learning_rate": 2.1759452345307675e-05, "loss": 0.1275, "step": 1660 }, { "epoch": 1.472663139329806, "grad_norm": 0.1676790489693593, "learning_rate": 2.1569656589494386e-05, "loss": 0.1266, "step": 1670 }, { "epoch": 1.4814814814814814, "grad_norm": 0.1644355202426517, "learning_rate": 2.137971849056142e-05, "loss": 0.1271, "step": 1680 }, { "epoch": 1.490299823633157, "grad_norm": 0.16767396631965428, "learning_rate": 2.1189655272901498e-05, "loss": 0.1288, "step": 1690 }, { "epoch": 1.4991181657848325, "grad_norm": 0.16721154360000728, "learning_rate": 2.0999484172253654e-05, "loss": 0.1274, "step": 1700 }, { "epoch": 1.507936507936508, "grad_norm": 0.17218284188058708, "learning_rate": 2.08092224341402e-05, "loss": 0.1268, "step": 1710 }, { "epoch": 1.5167548500881836, "grad_norm": 0.16455812323793684, "learning_rate": 2.0618887312302838e-05, "loss": 0.1269, "step": 1720 }, { "epoch": 1.5255731922398588, "grad_norm": 0.18830223142596714, "learning_rate": 2.042849606713802e-05, "loss": 0.1327, "step": 1730 }, { "epoch": 1.5343915343915344, "grad_norm": 0.16569892684919732, "learning_rate": 2.02380659641317e-05, "loss": 0.1289, "step": 1740 }, { "epoch": 1.5432098765432098, "grad_norm": 0.16686242636674062, "learning_rate": 2.004761427229363e-05, "loss": 0.1241, "step": 1750 }, { "epoch": 1.5520282186948853, "grad_norm": 0.17007064306268857, "learning_rate": 1.985715826259131e-05, "loss": 0.1283, "step": 1760 }, { "epoch": 1.560846560846561, "grad_norm": 0.17887859439191145, "learning_rate": 1.966671520638383e-05, "loss": 0.1268, "step": 1770 }, { "epoch": 1.5696649029982364, "grad_norm": 0.17041240102360516, "learning_rate": 1.947630237385558e-05, "loss": 0.1281, "step": 1780 }, { "epoch": 1.5784832451499118, "grad_norm": 0.16320063163341206, "learning_rate": 1.9285937032450146e-05, "loss": 0.128, "step": 1790 }, { "epoch": 1.5873015873015874, "grad_norm": 0.17846835386270518, "learning_rate": 1.909563644530443e-05, "loss": 0.1264, "step": 1800 }, { "epoch": 1.5961199294532626, "grad_norm": 0.1506424501330394, "learning_rate": 1.8905417869683113e-05, "loss": 0.1268, "step": 1810 }, { "epoch": 1.6049382716049383, "grad_norm": 0.15586172611133045, "learning_rate": 1.871529855541375e-05, "loss": 0.1249, "step": 1820 }, { "epoch": 1.6137566137566137, "grad_norm": 0.16774679274129406, "learning_rate": 1.8525295743322453e-05, "loss": 0.1269, "step": 1830 }, { "epoch": 1.6225749559082892, "grad_norm": 0.1727635954009701, "learning_rate": 1.8335426663670397e-05, "loss": 0.1273, "step": 1840 }, { "epoch": 1.6313932980599648, "grad_norm": 0.1892975495137155, "learning_rate": 1.8145708534591377e-05, "loss": 0.1255, "step": 1850 }, { "epoch": 1.6402116402116402, "grad_norm": 0.16857751294190276, "learning_rate": 1.79561585605303e-05, "loss": 0.1283, "step": 1860 }, { "epoch": 1.6490299823633157, "grad_norm": 0.1718737988430891, "learning_rate": 1.7766793930683094e-05, "loss": 0.1254, "step": 1870 }, { "epoch": 1.6578483245149913, "grad_norm": 0.1588131771656951, "learning_rate": 1.7577631817437888e-05, "loss": 0.1244, "step": 1880 }, { "epoch": 1.6666666666666665, "grad_norm": 0.16479791762147233, "learning_rate": 1.7388689374817722e-05, "loss": 0.1232, "step": 1890 }, { "epoch": 1.6754850088183422, "grad_norm": 0.20327562061299326, "learning_rate": 1.719998373692499e-05, "loss": 0.1259, "step": 1900 }, { "epoch": 1.6843033509700176, "grad_norm": 0.17445146984586163, "learning_rate": 1.7011532016387637e-05, "loss": 0.1241, "step": 1910 }, { "epoch": 1.693121693121693, "grad_norm": 0.15172765768609214, "learning_rate": 1.682335130280728e-05, "loss": 0.1248, "step": 1920 }, { "epoch": 1.7019400352733687, "grad_norm": 0.15540418406256226, "learning_rate": 1.663545866120949e-05, "loss": 0.1209, "step": 1930 }, { "epoch": 1.710758377425044, "grad_norm": 0.1614644793216772, "learning_rate": 1.6447871130496257e-05, "loss": 0.1239, "step": 1940 }, { "epoch": 1.7195767195767195, "grad_norm": 0.15504804793224192, "learning_rate": 1.62606057219008e-05, "loss": 0.1261, "step": 1950 }, { "epoch": 1.7283950617283952, "grad_norm": 0.17006738174447467, "learning_rate": 1.6073679417444946e-05, "loss": 0.1266, "step": 1960 }, { "epoch": 1.7372134038800704, "grad_norm": 0.17505387505969047, "learning_rate": 1.588710916839914e-05, "loss": 0.1225, "step": 1970 }, { "epoch": 1.746031746031746, "grad_norm": 0.1612549181660387, "learning_rate": 1.570091189374518e-05, "loss": 0.1249, "step": 1980 }, { "epoch": 1.7548500881834215, "grad_norm": 0.16112907861897668, "learning_rate": 1.5515104478641975e-05, "loss": 0.1254, "step": 1990 }, { "epoch": 1.763668430335097, "grad_norm": 0.15922476014447312, "learning_rate": 1.5329703772894327e-05, "loss": 0.1236, "step": 2000 }, { "epoch": 1.7724867724867726, "grad_norm": 0.17212069125892313, "learning_rate": 1.51447265894249e-05, "loss": 0.1242, "step": 2010 }, { "epoch": 1.781305114638448, "grad_norm": 0.1740636826222426, "learning_rate": 1.4960189702749551e-05, "loss": 0.1245, "step": 2020 }, { "epoch": 1.7901234567901234, "grad_norm": 0.15528067596347245, "learning_rate": 1.4776109847456173e-05, "loss": 0.1226, "step": 2030 }, { "epoch": 1.798941798941799, "grad_norm": 0.15722708188146675, "learning_rate": 1.4592503716687107e-05, "loss": 0.1243, "step": 2040 }, { "epoch": 1.8077601410934743, "grad_norm": 0.15918925574073986, "learning_rate": 1.4409387960625331e-05, "loss": 0.1216, "step": 2050 }, { "epoch": 1.81657848324515, "grad_norm": 0.1576457624630644, "learning_rate": 1.422677918498459e-05, "loss": 0.1249, "step": 2060 }, { "epoch": 1.8253968253968254, "grad_norm": 0.18618951180895943, "learning_rate": 1.4044693949503465e-05, "loss": 0.1251, "step": 2070 }, { "epoch": 1.8342151675485008, "grad_norm": 0.15865872308397924, "learning_rate": 1.3863148766443723e-05, "loss": 0.1228, "step": 2080 }, { "epoch": 1.8430335097001764, "grad_norm": 0.15045663896792358, "learning_rate": 1.368216009909286e-05, "loss": 0.1221, "step": 2090 }, { "epoch": 1.8518518518518519, "grad_norm": 0.15818210790519696, "learning_rate": 1.3501744360271177e-05, "loss": 0.123, "step": 2100 }, { "epoch": 1.8606701940035273, "grad_norm": 0.16422734107091674, "learning_rate": 1.3321917910843394e-05, "loss": 0.1187, "step": 2110 }, { "epoch": 1.869488536155203, "grad_norm": 0.15177335025772304, "learning_rate": 1.3142697058234952e-05, "loss": 0.1222, "step": 2120 }, { "epoch": 1.8783068783068781, "grad_norm": 0.15321330650093545, "learning_rate": 1.2964098054953209e-05, "loss": 0.1205, "step": 2130 }, { "epoch": 1.8871252204585538, "grad_norm": 0.16140622128902943, "learning_rate": 1.2786137097113594e-05, "loss": 0.1194, "step": 2140 }, { "epoch": 1.8959435626102292, "grad_norm": 0.15735771104485857, "learning_rate": 1.2608830322970865e-05, "loss": 0.1234, "step": 2150 }, { "epoch": 1.9047619047619047, "grad_norm": 0.15949016923062945, "learning_rate": 1.2432193811455609e-05, "loss": 0.1237, "step": 2160 }, { "epoch": 1.9135802469135803, "grad_norm": 0.16001139592539343, "learning_rate": 1.2256243580716187e-05, "loss": 0.1216, "step": 2170 }, { "epoch": 1.9223985890652557, "grad_norm": 0.14752520035248345, "learning_rate": 1.2080995586666085e-05, "loss": 0.122, "step": 2180 }, { "epoch": 1.9312169312169312, "grad_norm": 0.15247438606628488, "learning_rate": 1.1906465721536984e-05, "loss": 0.1236, "step": 2190 }, { "epoch": 1.9400352733686068, "grad_norm": 0.15289569423666619, "learning_rate": 1.17326698124376e-05, "loss": 0.1214, "step": 2200 }, { "epoch": 1.948853615520282, "grad_norm": 0.17526380738963238, "learning_rate": 1.1559623619918396e-05, "loss": 0.1212, "step": 2210 }, { "epoch": 1.9576719576719577, "grad_norm": 0.16261170275972142, "learning_rate": 1.1387342836542353e-05, "loss": 0.1203, "step": 2220 }, { "epoch": 1.966490299823633, "grad_norm": 0.16169651658483872, "learning_rate": 1.1215843085461912e-05, "loss": 0.1187, "step": 2230 }, { "epoch": 1.9753086419753085, "grad_norm": 0.1595833660103317, "learning_rate": 1.1045139919002181e-05, "loss": 0.1185, "step": 2240 }, { "epoch": 1.9841269841269842, "grad_norm": 0.15303519805668522, "learning_rate": 1.087524881725059e-05, "loss": 0.1223, "step": 2250 }, { "epoch": 1.9929453262786596, "grad_norm": 0.16239859350306318, "learning_rate": 1.0706185186653108e-05, "loss": 0.1195, "step": 2260 }, { "epoch": 2.001763668430335, "grad_norm": 0.1948721740831915, "learning_rate": 1.0537964358617114e-05, "loss": 0.1145, "step": 2270 }, { "epoch": 2.0105820105820107, "grad_norm": 0.17072323405727977, "learning_rate": 1.0370601588121052e-05, "loss": 0.0971, "step": 2280 }, { "epoch": 2.019400352733686, "grad_norm": 0.1730651246941294, "learning_rate": 1.0204112052331097e-05, "loss": 0.0983, "step": 2290 }, { "epoch": 2.0282186948853616, "grad_norm": 0.15846505516821519, "learning_rate": 1.0038510849224758e-05, "loss": 0.097, "step": 2300 }, { "epoch": 2.037037037037037, "grad_norm": 0.18557277607745912, "learning_rate": 9.87381299622181e-06, "loss": 0.0942, "step": 2310 }, { "epoch": 2.0458553791887124, "grad_norm": 0.16362091724207117, "learning_rate": 9.710033428822368e-06, "loss": 0.0952, "step": 2320 }, { "epoch": 2.054673721340388, "grad_norm": 0.16144197990009226, "learning_rate": 9.547186999252538e-06, "loss": 0.0966, "step": 2330 }, { "epoch": 2.0634920634920633, "grad_norm": 0.1703392645828158, "learning_rate": 9.385288475117526e-06, "loss": 0.0947, "step": 2340 }, { "epoch": 2.072310405643739, "grad_norm": 0.18472104722259497, "learning_rate": 9.224352538062441e-06, "loss": 0.0961, "step": 2350 }, { "epoch": 2.0811287477954146, "grad_norm": 0.16657694584089722, "learning_rate": 9.06439378244091e-06, "loss": 0.0935, "step": 2360 }, { "epoch": 2.0899470899470898, "grad_norm": 0.1640060501350356, "learning_rate": 8.905426713991609e-06, "loss": 0.098, "step": 2370 }, { "epoch": 2.0987654320987654, "grad_norm": 0.155343849676478, "learning_rate": 8.747465748522824e-06, "loss": 0.0929, "step": 2380 }, { "epoch": 2.107583774250441, "grad_norm": 0.16657876804825647, "learning_rate": 8.590525210605125e-06, "loss": 0.0938, "step": 2390 }, { "epoch": 2.1164021164021163, "grad_norm": 0.1626875240950099, "learning_rate": 8.434619332272412e-06, "loss": 0.0933, "step": 2400 }, { "epoch": 2.125220458553792, "grad_norm": 0.1613598792215022, "learning_rate": 8.279762251731246e-06, "loss": 0.0944, "step": 2410 }, { "epoch": 2.1340388007054676, "grad_norm": 0.1638238651603253, "learning_rate": 8.125968012078745e-06, "loss": 0.092, "step": 2420 }, { "epoch": 2.142857142857143, "grad_norm": 0.16977220285542402, "learning_rate": 7.973250560029132e-06, "loss": 0.0939, "step": 2430 }, { "epoch": 2.1516754850088184, "grad_norm": 0.16753471017264823, "learning_rate": 7.821623744648952e-06, "loss": 0.0917, "step": 2440 }, { "epoch": 2.1604938271604937, "grad_norm": 0.16181368054619877, "learning_rate": 7.671101316101172e-06, "loss": 0.0942, "step": 2450 }, { "epoch": 2.1693121693121693, "grad_norm": 0.16568414134323833, "learning_rate": 7.521696924398303e-06, "loss": 0.0947, "step": 2460 }, { "epoch": 2.178130511463845, "grad_norm": 0.15925917816119767, "learning_rate": 7.373424118164501e-06, "loss": 0.0944, "step": 2470 }, { "epoch": 2.18694885361552, "grad_norm": 0.16349944720912132, "learning_rate": 7.226296343406974e-06, "loss": 0.0941, "step": 2480 }, { "epoch": 2.195767195767196, "grad_norm": 0.16785075128125135, "learning_rate": 7.0803269422966135e-06, "loss": 0.0922, "step": 2490 }, { "epoch": 2.204585537918871, "grad_norm": 0.15912892496071598, "learning_rate": 6.935529151958065e-06, "loss": 0.0948, "step": 2500 }, { "epoch": 2.2134038800705467, "grad_norm": 0.16142401500311457, "learning_rate": 6.791916103269333e-06, "loss": 0.0932, "step": 2510 }, { "epoch": 2.2222222222222223, "grad_norm": 0.1664762727497597, "learning_rate": 6.649500819671047e-06, "loss": 0.0955, "step": 2520 }, { "epoch": 2.2310405643738975, "grad_norm": 0.16004719129428444, "learning_rate": 6.5082962159853834e-06, "loss": 0.0898, "step": 2530 }, { "epoch": 2.239858906525573, "grad_norm": 0.1615455245606165, "learning_rate": 6.368315097244955e-06, "loss": 0.0917, "step": 2540 }, { "epoch": 2.248677248677249, "grad_norm": 0.16743450359900008, "learning_rate": 6.2295701575315594e-06, "loss": 0.0916, "step": 2550 }, { "epoch": 2.257495590828924, "grad_norm": 0.16544121841662957, "learning_rate": 6.092073978825022e-06, "loss": 0.0927, "step": 2560 }, { "epoch": 2.2663139329805997, "grad_norm": 0.16180251542385612, "learning_rate": 5.955839029862245e-06, "loss": 0.0946, "step": 2570 }, { "epoch": 2.2751322751322753, "grad_norm": 0.15338708773074522, "learning_rate": 5.820877665006441e-06, "loss": 0.0926, "step": 2580 }, { "epoch": 2.2839506172839505, "grad_norm": 0.15957923017749945, "learning_rate": 5.687202123126832e-06, "loss": 0.0952, "step": 2590 }, { "epoch": 2.292768959435626, "grad_norm": 0.15484396525882926, "learning_rate": 5.5548245264887515e-06, "loss": 0.0929, "step": 2600 }, { "epoch": 2.3015873015873014, "grad_norm": 0.15944927489262736, "learning_rate": 5.423756879654343e-06, "loss": 0.092, "step": 2610 }, { "epoch": 2.310405643738977, "grad_norm": 0.1555885456859465, "learning_rate": 5.294011068393945e-06, "loss": 0.0932, "step": 2620 }, { "epoch": 2.3192239858906527, "grad_norm": 0.1616989709098896, "learning_rate": 5.1655988586082535e-06, "loss": 0.0944, "step": 2630 }, { "epoch": 2.328042328042328, "grad_norm": 0.15595636612871588, "learning_rate": 5.038531895261301e-06, "loss": 0.094, "step": 2640 }, { "epoch": 2.3368606701940036, "grad_norm": 0.1773185191439187, "learning_rate": 4.912821701324479e-06, "loss": 0.0924, "step": 2650 }, { "epoch": 2.3456790123456788, "grad_norm": 0.16579054625602957, "learning_rate": 4.788479676731581e-06, "loss": 0.0936, "step": 2660 }, { "epoch": 2.3544973544973544, "grad_norm": 0.15352554844705696, "learning_rate": 4.665517097344976e-06, "loss": 0.0935, "step": 2670 }, { "epoch": 2.36331569664903, "grad_norm": 0.15451348902863254, "learning_rate": 4.543945113933099e-06, "loss": 0.0931, "step": 2680 }, { "epoch": 2.3721340388007053, "grad_norm": 0.16299047928042187, "learning_rate": 4.423774751159247e-06, "loss": 0.0937, "step": 2690 }, { "epoch": 2.380952380952381, "grad_norm": 0.15558927808811412, "learning_rate": 4.305016906581811e-06, "loss": 0.0906, "step": 2700 }, { "epoch": 2.3897707231040566, "grad_norm": 0.15763428447923092, "learning_rate": 4.1876823496660245e-06, "loss": 0.0919, "step": 2710 }, { "epoch": 2.398589065255732, "grad_norm": 0.1614586373848465, "learning_rate": 4.071781720807375e-06, "loss": 0.0929, "step": 2720 }, { "epoch": 2.4074074074074074, "grad_norm": 0.15663328679730767, "learning_rate": 3.9573255303666554e-06, "loss": 0.0911, "step": 2730 }, { "epoch": 2.416225749559083, "grad_norm": 0.15190824093071106, "learning_rate": 3.844324157716857e-06, "loss": 0.0906, "step": 2740 }, { "epoch": 2.4250440917107583, "grad_norm": 0.15885908725225142, "learning_rate": 3.7327878503019243e-06, "loss": 0.0903, "step": 2750 }, { "epoch": 2.433862433862434, "grad_norm": 0.15186092891507827, "learning_rate": 3.622726722707479e-06, "loss": 0.09, "step": 2760 }, { "epoch": 2.442680776014109, "grad_norm": 0.15364028795008292, "learning_rate": 3.5141507557435504e-06, "loss": 0.093, "step": 2770 }, { "epoch": 2.451499118165785, "grad_norm": 0.15589229219750106, "learning_rate": 3.4070697955395326e-06, "loss": 0.0897, "step": 2780 }, { "epoch": 2.4603174603174605, "grad_norm": 0.15718297314700777, "learning_rate": 3.3014935526512383e-06, "loss": 0.0922, "step": 2790 }, { "epoch": 2.4691358024691357, "grad_norm": 0.15723729478788426, "learning_rate": 3.197431601180343e-06, "loss": 0.0924, "step": 2800 }, { "epoch": 2.4779541446208113, "grad_norm": 0.1600488009457486, "learning_rate": 3.094893377906143e-06, "loss": 0.0897, "step": 2810 }, { "epoch": 2.4867724867724865, "grad_norm": 0.1545448158355294, "learning_rate": 2.9938881814298002e-06, "loss": 0.0901, "step": 2820 }, { "epoch": 2.495590828924162, "grad_norm": 0.15517515088748454, "learning_rate": 2.894425171331112e-06, "loss": 0.0918, "step": 2830 }, { "epoch": 2.504409171075838, "grad_norm": 0.15614342046875468, "learning_rate": 2.796513367337854e-06, "loss": 0.0883, "step": 2840 }, { "epoch": 2.5132275132275135, "grad_norm": 0.1532975772545578, "learning_rate": 2.7001616485078553e-06, "loss": 0.0937, "step": 2850 }, { "epoch": 2.5220458553791887, "grad_norm": 0.15407944254916026, "learning_rate": 2.6053787524238084e-06, "loss": 0.0881, "step": 2860 }, { "epoch": 2.5308641975308643, "grad_norm": 0.15187561548545364, "learning_rate": 2.512173274400904e-06, "loss": 0.0883, "step": 2870 }, { "epoch": 2.5396825396825395, "grad_norm": 0.15129893026103466, "learning_rate": 2.4205536667073572e-06, "loss": 0.0914, "step": 2880 }, { "epoch": 2.548500881834215, "grad_norm": 0.15387910729749937, "learning_rate": 2.330528237797949e-06, "loss": 0.0916, "step": 2890 }, { "epoch": 2.557319223985891, "grad_norm": 0.15310039839687165, "learning_rate": 2.242105151560554e-06, "loss": 0.0897, "step": 2900 }, { "epoch": 2.566137566137566, "grad_norm": 0.15660569630223034, "learning_rate": 2.1552924265758102e-06, "loss": 0.0883, "step": 2910 }, { "epoch": 2.5749559082892417, "grad_norm": 0.15625668536136728, "learning_rate": 2.070097935389974e-06, "loss": 0.088, "step": 2920 }, { "epoch": 2.583774250440917, "grad_norm": 0.16440666779797036, "learning_rate": 1.9865294038009984e-06, "loss": 0.09, "step": 2930 }, { "epoch": 2.5925925925925926, "grad_norm": 0.15497386680361938, "learning_rate": 1.9045944101579073e-06, "loss": 0.0896, "step": 2940 }, { "epoch": 2.601410934744268, "grad_norm": 0.1528557591079046, "learning_rate": 1.8243003846735807e-06, "loss": 0.0916, "step": 2950 }, { "epoch": 2.6102292768959434, "grad_norm": 0.14797025757103924, "learning_rate": 1.7456546087509419e-06, "loss": 0.0882, "step": 2960 }, { "epoch": 2.619047619047619, "grad_norm": 0.15101812244580526, "learning_rate": 1.6686642143226484e-06, "loss": 0.0892, "step": 2970 }, { "epoch": 2.6278659611992943, "grad_norm": 0.14853644829002635, "learning_rate": 1.593336183204346e-06, "loss": 0.0884, "step": 2980 }, { "epoch": 2.63668430335097, "grad_norm": 0.1547300718526592, "learning_rate": 1.5196773464615167e-06, "loss": 0.0902, "step": 2990 }, { "epoch": 2.6455026455026456, "grad_norm": 0.14824004323134074, "learning_rate": 1.4476943837900105e-06, "loss": 0.0915, "step": 3000 }, { "epoch": 2.6543209876543212, "grad_norm": 0.15162108864434684, "learning_rate": 1.377393822910318e-06, "loss": 0.0904, "step": 3010 }, { "epoch": 2.6631393298059964, "grad_norm": 0.1539793202148526, "learning_rate": 1.30878203897558e-06, "loss": 0.0883, "step": 3020 }, { "epoch": 2.671957671957672, "grad_norm": 0.15086750725756884, "learning_rate": 1.241865253993495e-06, "loss": 0.0899, "step": 3030 }, { "epoch": 2.6807760141093473, "grad_norm": 0.1555053078276991, "learning_rate": 1.1766495362620555e-06, "loss": 0.09, "step": 3040 }, { "epoch": 2.689594356261023, "grad_norm": 0.15052416992823459, "learning_rate": 1.1131407998192567e-06, "loss": 0.089, "step": 3050 }, { "epoch": 2.6984126984126986, "grad_norm": 0.1504945657873999, "learning_rate": 1.0513448039067954e-06, "loss": 0.0892, "step": 3060 }, { "epoch": 2.707231040564374, "grad_norm": 0.1478376395173767, "learning_rate": 9.91267152447779e-07, "loss": 0.0878, "step": 3070 }, { "epoch": 2.7160493827160495, "grad_norm": 0.1509329096731571, "learning_rate": 9.329132935385577e-07, "loss": 0.0899, "step": 3080 }, { "epoch": 2.7248677248677247, "grad_norm": 0.15222497781820243, "learning_rate": 8.7628851895466e-07, "loss": 0.0916, "step": 3090 }, { "epoch": 2.7336860670194003, "grad_norm": 0.15030672400304343, "learning_rate": 8.213979636709046e-07, "loss": 0.0922, "step": 3100 }, { "epoch": 2.742504409171076, "grad_norm": 0.15512035164112659, "learning_rate": 7.682466053957438e-07, "loss": 0.0888, "step": 3110 }, { "epoch": 2.751322751322751, "grad_norm": 0.14852112467156292, "learning_rate": 7.168392641198796e-07, "loss": 0.0869, "step": 3120 }, { "epoch": 2.760141093474427, "grad_norm": 0.15336396025005739, "learning_rate": 6.671806016791337e-07, "loss": 0.0877, "step": 3130 }, { "epoch": 2.768959435626102, "grad_norm": 0.1503484462634625, "learning_rate": 6.192751213317261e-07, "loss": 0.0869, "step": 3140 }, { "epoch": 2.7777777777777777, "grad_norm": 0.15301298135075012, "learning_rate": 5.731271673498807e-07, "loss": 0.0876, "step": 3150 }, { "epoch": 2.7865961199294533, "grad_norm": 0.14946491260070807, "learning_rate": 5.287409246258724e-07, "loss": 0.0867, "step": 3160 }, { "epoch": 2.795414462081129, "grad_norm": 0.15544234491849743, "learning_rate": 4.861204182925238e-07, "loss": 0.0861, "step": 3170 }, { "epoch": 2.804232804232804, "grad_norm": 0.14786323558106976, "learning_rate": 4.452695133581908e-07, "loss": 0.0897, "step": 3180 }, { "epoch": 2.81305114638448, "grad_norm": 0.15035294545385944, "learning_rate": 4.0619191435626647e-07, "loss": 0.0898, "step": 3190 }, { "epoch": 2.821869488536155, "grad_norm": 0.14702281322330948, "learning_rate": 3.688911650092375e-07, "loss": 0.0892, "step": 3200 }, { "epoch": 2.8306878306878307, "grad_norm": 0.1490187614425559, "learning_rate": 3.333706479073229e-07, "loss": 0.0904, "step": 3210 }, { "epoch": 2.8395061728395063, "grad_norm": 0.14599915262723653, "learning_rate": 2.996335842017306e-07, "loss": 0.0915, "step": 3220 }, { "epoch": 2.8483245149911816, "grad_norm": 0.1472537352263344, "learning_rate": 2.676830333125424e-07, "loss": 0.089, "step": 3230 }, { "epoch": 2.857142857142857, "grad_norm": 0.1444247131200575, "learning_rate": 2.3752189265128234e-07, "loss": 0.0868, "step": 3240 }, { "epoch": 2.8659611992945324, "grad_norm": 0.15100512121725188, "learning_rate": 2.0915289735816247e-07, "loss": 0.0891, "step": 3250 }, { "epoch": 2.874779541446208, "grad_norm": 0.14909989384814895, "learning_rate": 1.8257862005404802e-07, "loss": 0.0898, "step": 3260 }, { "epoch": 2.8835978835978837, "grad_norm": 0.1501123498119351, "learning_rate": 1.5780147060715955e-07, "loss": 0.0877, "step": 3270 }, { "epoch": 2.892416225749559, "grad_norm": 0.14724312312335958, "learning_rate": 1.3482369591453882e-07, "loss": 0.0911, "step": 3280 }, { "epoch": 2.9012345679012346, "grad_norm": 0.14800693250740457, "learning_rate": 1.1364737969829176e-07, "loss": 0.0909, "step": 3290 }, { "epoch": 2.91005291005291, "grad_norm": 0.14676977153334295, "learning_rate": 9.427444231662863e-08, "loss": 0.0862, "step": 3300 }, { "epoch": 2.9188712522045854, "grad_norm": 0.14812710257168704, "learning_rate": 7.670664058970545e-08, "loss": 0.0875, "step": 3310 }, { "epoch": 2.927689594356261, "grad_norm": 0.1488187956001474, "learning_rate": 6.094556764032922e-08, "loss": 0.0886, "step": 3320 }, { "epoch": 2.9365079365079367, "grad_norm": 0.14589793378350213, "learning_rate": 4.699265274946907e-08, "loss": 0.0865, "step": 3330 }, { "epoch": 2.945326278659612, "grad_norm": 0.14997064517034403, "learning_rate": 3.484916122664883e-08, "loss": 0.0889, "step": 3340 }, { "epoch": 2.9541446208112876, "grad_norm": 0.14722441270349446, "learning_rate": 2.4516194295205466e-08, "loss": 0.0899, "step": 3350 }, { "epoch": 2.962962962962963, "grad_norm": 0.14896127171056997, "learning_rate": 1.5994688992424513e-08, "loss": 0.0895, "step": 3360 }, { "epoch": 2.9717813051146384, "grad_norm": 0.14761644929430634, "learning_rate": 9.285418084565845e-09, "loss": 0.0886, "step": 3370 }, { "epoch": 2.980599647266314, "grad_norm": 0.14489081475734752, "learning_rate": 4.3889899967797244e-09, "loss": 0.0886, "step": 3380 }, { "epoch": 2.9894179894179893, "grad_norm": 0.1482366815617573, "learning_rate": 1.3058487579420409e-09, "loss": 0.0888, "step": 3390 }, { "epoch": 2.998236331569665, "grad_norm": 0.15214422750713533, "learning_rate": 3.627396038208275e-11, "loss": 0.0869, "step": 3400 }, { "epoch": 3.0, "step": 3402, "total_flos": 7122048987955200.0, "train_loss": 0.13241534099762473, "train_runtime": 27380.0053, "train_samples_per_second": 19.876, "train_steps_per_second": 0.124 } ], "logging_steps": 10, "max_steps": 3402, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7122048987955200.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }