{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.434782608695652, "eval_steps": 500, "global_step": 5000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.010869565217391304, "grad_norm": 6.545120716094971, "learning_rate": 4.000000000000001e-06, "loss": 1.0169, "step": 10 }, { "epoch": 0.021739130434782608, "grad_norm": 31.165016174316406, "learning_rate": 8.000000000000001e-06, "loss": 0.994, "step": 20 }, { "epoch": 0.03260869565217391, "grad_norm": 3.4593701362609863, "learning_rate": 1.2e-05, "loss": 0.7425, "step": 30 }, { "epoch": 0.043478260869565216, "grad_norm": 1.7162226438522339, "learning_rate": 1.6000000000000003e-05, "loss": 0.426, "step": 40 }, { "epoch": 0.05434782608695652, "grad_norm": 1.7646105289459229, "learning_rate": 2e-05, "loss": 0.2894, "step": 50 }, { "epoch": 0.06521739130434782, "grad_norm": 1.069878101348877, "learning_rate": 2.4e-05, "loss": 0.2568, "step": 60 }, { "epoch": 0.07608695652173914, "grad_norm": 0.7048421502113342, "learning_rate": 2.8000000000000003e-05, "loss": 0.2031, "step": 70 }, { "epoch": 0.08695652173913043, "grad_norm": 0.8065099120140076, "learning_rate": 3.2000000000000005e-05, "loss": 0.1889, "step": 80 }, { "epoch": 0.09782608695652174, "grad_norm": 0.5573766231536865, "learning_rate": 3.6e-05, "loss": 0.1703, "step": 90 }, { "epoch": 0.10869565217391304, "grad_norm": 0.7829588055610657, "learning_rate": 4e-05, "loss": 0.1541, "step": 100 }, { "epoch": 0.11956521739130435, "grad_norm": 0.7068309783935547, "learning_rate": 4.4000000000000006e-05, "loss": 0.1548, "step": 110 }, { "epoch": 0.13043478260869565, "grad_norm": 0.8238246440887451, "learning_rate": 4.8e-05, "loss": 0.1285, "step": 120 }, { "epoch": 0.14130434782608695, "grad_norm": 0.6554062962532043, "learning_rate": 5.2000000000000004e-05, "loss": 0.1248, "step": 130 }, { "epoch": 0.15217391304347827, "grad_norm": 0.7113671898841858, "learning_rate": 5.6000000000000006e-05, "loss": 0.1257, "step": 140 }, { "epoch": 0.16304347826086957, "grad_norm": 0.5627883672714233, "learning_rate": 6e-05, "loss": 0.1154, "step": 150 }, { "epoch": 0.17391304347826086, "grad_norm": 0.5287997722625732, "learning_rate": 6.400000000000001e-05, "loss": 0.108, "step": 160 }, { "epoch": 0.18478260869565216, "grad_norm": 0.5217707753181458, "learning_rate": 6.800000000000001e-05, "loss": 0.1046, "step": 170 }, { "epoch": 0.1956521739130435, "grad_norm": 0.834353506565094, "learning_rate": 7.2e-05, "loss": 0.1027, "step": 180 }, { "epoch": 0.20652173913043478, "grad_norm": 0.6808788776397705, "learning_rate": 7.6e-05, "loss": 0.0856, "step": 190 }, { "epoch": 0.21739130434782608, "grad_norm": 0.639272153377533, "learning_rate": 8e-05, "loss": 0.0938, "step": 200 }, { "epoch": 0.22826086956521738, "grad_norm": 0.7152073383331299, "learning_rate": 8.4e-05, "loss": 0.0951, "step": 210 }, { "epoch": 0.2391304347826087, "grad_norm": 0.47022637724876404, "learning_rate": 8.800000000000001e-05, "loss": 0.0893, "step": 220 }, { "epoch": 0.25, "grad_norm": 0.7306397557258606, "learning_rate": 9.200000000000001e-05, "loss": 0.084, "step": 230 }, { "epoch": 0.2608695652173913, "grad_norm": 0.5324788093566895, "learning_rate": 9.6e-05, "loss": 0.082, "step": 240 }, { "epoch": 0.2717391304347826, "grad_norm": 0.46213847398757935, "learning_rate": 0.0001, "loss": 0.0781, "step": 250 }, { "epoch": 0.2826086956521739, "grad_norm": 0.6270459294319153, "learning_rate": 9.999890641901125e-05, "loss": 0.0761, "step": 260 }, { "epoch": 0.29347826086956524, "grad_norm": 0.6771764159202576, "learning_rate": 9.99956257238817e-05, "loss": 0.0807, "step": 270 }, { "epoch": 0.30434782608695654, "grad_norm": 0.4983552396297455, "learning_rate": 9.999015805811965e-05, "loss": 0.0785, "step": 280 }, { "epoch": 0.31521739130434784, "grad_norm": 0.6947988271713257, "learning_rate": 9.998250366089848e-05, "loss": 0.0819, "step": 290 }, { "epoch": 0.32608695652173914, "grad_norm": 0.7602576017379761, "learning_rate": 9.997266286704631e-05, "loss": 0.0718, "step": 300 }, { "epoch": 0.33695652173913043, "grad_norm": 0.5555041432380676, "learning_rate": 9.996063610703137e-05, "loss": 0.0763, "step": 310 }, { "epoch": 0.34782608695652173, "grad_norm": 0.4837249219417572, "learning_rate": 9.994642390694308e-05, "loss": 0.0713, "step": 320 }, { "epoch": 0.358695652173913, "grad_norm": 0.3204691410064697, "learning_rate": 9.993002688846913e-05, "loss": 0.0702, "step": 330 }, { "epoch": 0.3695652173913043, "grad_norm": 0.522548258304596, "learning_rate": 9.991144576886823e-05, "loss": 0.0664, "step": 340 }, { "epoch": 0.3804347826086957, "grad_norm": 0.43463149666786194, "learning_rate": 9.989068136093873e-05, "loss": 0.0589, "step": 350 }, { "epoch": 0.391304347826087, "grad_norm": 0.509681761264801, "learning_rate": 9.986773457298311e-05, "loss": 0.0664, "step": 360 }, { "epoch": 0.40217391304347827, "grad_norm": 0.4732968509197235, "learning_rate": 9.984260640876821e-05, "loss": 0.0654, "step": 370 }, { "epoch": 0.41304347826086957, "grad_norm": 0.3513120114803314, "learning_rate": 9.981529796748134e-05, "loss": 0.0591, "step": 380 }, { "epoch": 0.42391304347826086, "grad_norm": 0.33960211277008057, "learning_rate": 9.97858104436822e-05, "loss": 0.0574, "step": 390 }, { "epoch": 0.43478260869565216, "grad_norm": 0.4988704025745392, "learning_rate": 9.975414512725057e-05, "loss": 0.056, "step": 400 }, { "epoch": 0.44565217391304346, "grad_norm": 0.41242533922195435, "learning_rate": 9.972030340333001e-05, "loss": 0.0625, "step": 410 }, { "epoch": 0.45652173913043476, "grad_norm": 0.48576557636260986, "learning_rate": 9.968428675226714e-05, "loss": 0.0574, "step": 420 }, { "epoch": 0.4673913043478261, "grad_norm": 0.7005183696746826, "learning_rate": 9.964609674954696e-05, "loss": 0.057, "step": 430 }, { "epoch": 0.4782608695652174, "grad_norm": 0.37756964564323425, "learning_rate": 9.96057350657239e-05, "loss": 0.0559, "step": 440 }, { "epoch": 0.4891304347826087, "grad_norm": 0.4204326868057251, "learning_rate": 9.956320346634876e-05, "loss": 0.0547, "step": 450 }, { "epoch": 0.5, "grad_norm": 0.3505024015903473, "learning_rate": 9.95185038118915e-05, "loss": 0.061, "step": 460 }, { "epoch": 0.5108695652173914, "grad_norm": 0.3341296315193176, "learning_rate": 9.94716380576598e-05, "loss": 0.06, "step": 470 }, { "epoch": 0.5217391304347826, "grad_norm": 0.5188870429992676, "learning_rate": 9.942260825371358e-05, "loss": 0.0572, "step": 480 }, { "epoch": 0.532608695652174, "grad_norm": 0.42490994930267334, "learning_rate": 9.937141654477528e-05, "loss": 0.0537, "step": 490 }, { "epoch": 0.5434782608695652, "grad_norm": 0.4381064474582672, "learning_rate": 9.931806517013612e-05, "loss": 0.0507, "step": 500 }, { "epoch": 0.5543478260869565, "grad_norm": 0.3873785436153412, "learning_rate": 9.926255646355804e-05, "loss": 0.0521, "step": 510 }, { "epoch": 0.5652173913043478, "grad_norm": 0.3180992007255554, "learning_rate": 9.92048928531717e-05, "loss": 0.0482, "step": 520 }, { "epoch": 0.5760869565217391, "grad_norm": 0.34632715582847595, "learning_rate": 9.914507686137019e-05, "loss": 0.0526, "step": 530 }, { "epoch": 0.5869565217391305, "grad_norm": 0.4718571603298187, "learning_rate": 9.90831111046988e-05, "loss": 0.0486, "step": 540 }, { "epoch": 0.5978260869565217, "grad_norm": 0.36883848905563354, "learning_rate": 9.901899829374047e-05, "loss": 0.0461, "step": 550 }, { "epoch": 0.6086956521739131, "grad_norm": 0.36269769072532654, "learning_rate": 9.895274123299723e-05, "loss": 0.0439, "step": 560 }, { "epoch": 0.6195652173913043, "grad_norm": 0.3643960654735565, "learning_rate": 9.888434282076758e-05, "loss": 0.0448, "step": 570 }, { "epoch": 0.6304347826086957, "grad_norm": 0.2864445745944977, "learning_rate": 9.881380604901964e-05, "loss": 0.0459, "step": 580 }, { "epoch": 0.6413043478260869, "grad_norm": 0.41547855734825134, "learning_rate": 9.87411340032603e-05, "loss": 0.0493, "step": 590 }, { "epoch": 0.6521739130434783, "grad_norm": 0.23883788287639618, "learning_rate": 9.86663298624003e-05, "loss": 0.05, "step": 600 }, { "epoch": 0.6630434782608695, "grad_norm": 0.3606937527656555, "learning_rate": 9.858939689861506e-05, "loss": 0.0552, "step": 610 }, { "epoch": 0.6739130434782609, "grad_norm": 0.3378564715385437, "learning_rate": 9.851033847720166e-05, "loss": 0.0445, "step": 620 }, { "epoch": 0.6847826086956522, "grad_norm": 0.3886934816837311, "learning_rate": 9.842915805643155e-05, "loss": 0.0398, "step": 630 }, { "epoch": 0.6956521739130435, "grad_norm": 0.34393632411956787, "learning_rate": 9.834585918739936e-05, "loss": 0.0423, "step": 640 }, { "epoch": 0.7065217391304348, "grad_norm": 0.37075570225715637, "learning_rate": 9.826044551386744e-05, "loss": 0.0474, "step": 650 }, { "epoch": 0.717391304347826, "grad_norm": 0.45477569103240967, "learning_rate": 9.817292077210659e-05, "loss": 0.0491, "step": 660 }, { "epoch": 0.7282608695652174, "grad_norm": 0.3451235890388489, "learning_rate": 9.808328879073251e-05, "loss": 0.0532, "step": 670 }, { "epoch": 0.7391304347826086, "grad_norm": 0.31069430708885193, "learning_rate": 9.799155349053851e-05, "loss": 0.0481, "step": 680 }, { "epoch": 0.75, "grad_norm": 0.33381545543670654, "learning_rate": 9.789771888432375e-05, "loss": 0.0439, "step": 690 }, { "epoch": 0.7608695652173914, "grad_norm": 0.3076520264148712, "learning_rate": 9.780178907671789e-05, "loss": 0.0413, "step": 700 }, { "epoch": 0.7717391304347826, "grad_norm": 0.4080972969532013, "learning_rate": 9.77037682640015e-05, "loss": 0.0524, "step": 710 }, { "epoch": 0.782608695652174, "grad_norm": 0.4061325490474701, "learning_rate": 9.760366073392246e-05, "loss": 0.0436, "step": 720 }, { "epoch": 0.7934782608695652, "grad_norm": 0.32753169536590576, "learning_rate": 9.750147086550844e-05, "loss": 0.0456, "step": 730 }, { "epoch": 0.8043478260869565, "grad_norm": 0.255860835313797, "learning_rate": 9.739720312887535e-05, "loss": 0.0368, "step": 740 }, { "epoch": 0.8152173913043478, "grad_norm": 0.3491983115673065, "learning_rate": 9.729086208503174e-05, "loss": 0.0419, "step": 750 }, { "epoch": 0.8260869565217391, "grad_norm": 0.38648349046707153, "learning_rate": 9.718245238567939e-05, "loss": 0.0377, "step": 760 }, { "epoch": 0.8369565217391305, "grad_norm": 0.28146737813949585, "learning_rate": 9.707197877300974e-05, "loss": 0.0391, "step": 770 }, { "epoch": 0.8478260869565217, "grad_norm": 0.32342949509620667, "learning_rate": 9.695944607949649e-05, "loss": 0.0393, "step": 780 }, { "epoch": 0.8586956521739131, "grad_norm": 0.320584774017334, "learning_rate": 9.684485922768422e-05, "loss": 0.0387, "step": 790 }, { "epoch": 0.8695652173913043, "grad_norm": 0.34208914637565613, "learning_rate": 9.672822322997305e-05, "loss": 0.0417, "step": 800 }, { "epoch": 0.8804347826086957, "grad_norm": 0.27788016200065613, "learning_rate": 9.660954318839933e-05, "loss": 0.044, "step": 810 }, { "epoch": 0.8913043478260869, "grad_norm": 0.3619558811187744, "learning_rate": 9.648882429441257e-05, "loss": 0.0418, "step": 820 }, { "epoch": 0.9021739130434783, "grad_norm": 0.3278563618659973, "learning_rate": 9.636607182864827e-05, "loss": 0.0439, "step": 830 }, { "epoch": 0.9130434782608695, "grad_norm": 0.3712303936481476, "learning_rate": 9.624129116069694e-05, "loss": 0.0404, "step": 840 }, { "epoch": 0.9239130434782609, "grad_norm": 0.23256783187389374, "learning_rate": 9.611448774886924e-05, "loss": 0.0463, "step": 850 }, { "epoch": 0.9347826086956522, "grad_norm": 0.3841691017150879, "learning_rate": 9.598566713995718e-05, "loss": 0.038, "step": 860 }, { "epoch": 0.9456521739130435, "grad_norm": 0.4116934835910797, "learning_rate": 9.58548349689915e-05, "loss": 0.0397, "step": 870 }, { "epoch": 0.9565217391304348, "grad_norm": 0.3569575846195221, "learning_rate": 9.572199695899522e-05, "loss": 0.0373, "step": 880 }, { "epoch": 0.967391304347826, "grad_norm": 0.32062098383903503, "learning_rate": 9.558715892073323e-05, "loss": 0.0382, "step": 890 }, { "epoch": 0.9782608695652174, "grad_norm": 0.3369348347187042, "learning_rate": 9.545032675245813e-05, "loss": 0.0469, "step": 900 }, { "epoch": 0.9891304347826086, "grad_norm": 0.3673070967197418, "learning_rate": 9.531150643965223e-05, "loss": 0.0328, "step": 910 }, { "epoch": 1.0, "grad_norm": 0.4159371554851532, "learning_rate": 9.517070405476575e-05, "loss": 0.0403, "step": 920 }, { "epoch": 1.0108695652173914, "grad_norm": 0.19767124950885773, "learning_rate": 9.502792575695112e-05, "loss": 0.0322, "step": 930 }, { "epoch": 1.0217391304347827, "grad_norm": 0.32694023847579956, "learning_rate": 9.488317779179361e-05, "loss": 0.0345, "step": 940 }, { "epoch": 1.0326086956521738, "grad_norm": 0.2887076735496521, "learning_rate": 9.473646649103818e-05, "loss": 0.0407, "step": 950 }, { "epoch": 1.0434782608695652, "grad_norm": 0.22730398178100586, "learning_rate": 9.458779827231237e-05, "loss": 0.0302, "step": 960 }, { "epoch": 1.0543478260869565, "grad_norm": 0.3960530757904053, "learning_rate": 9.443717963884569e-05, "loss": 0.0317, "step": 970 }, { "epoch": 1.065217391304348, "grad_norm": 0.21886062622070312, "learning_rate": 9.428461717918511e-05, "loss": 0.0336, "step": 980 }, { "epoch": 1.0760869565217392, "grad_norm": 0.2685090899467468, "learning_rate": 9.413011756690685e-05, "loss": 0.0367, "step": 990 }, { "epoch": 1.0869565217391304, "grad_norm": 0.2610633373260498, "learning_rate": 9.397368756032445e-05, "loss": 0.0343, "step": 1000 }, { "epoch": 1.0978260869565217, "grad_norm": 0.2550532817840576, "learning_rate": 9.381533400219318e-05, "loss": 0.0338, "step": 1010 }, { "epoch": 1.108695652173913, "grad_norm": 0.2943401038646698, "learning_rate": 9.365506381941066e-05, "loss": 0.0336, "step": 1020 }, { "epoch": 1.1195652173913044, "grad_norm": 0.22352245450019836, "learning_rate": 9.349288402271388e-05, "loss": 0.0311, "step": 1030 }, { "epoch": 1.1304347826086956, "grad_norm": 0.2989339828491211, "learning_rate": 9.332880170637252e-05, "loss": 0.0352, "step": 1040 }, { "epoch": 1.141304347826087, "grad_norm": 0.28045058250427246, "learning_rate": 9.316282404787871e-05, "loss": 0.0305, "step": 1050 }, { "epoch": 1.1521739130434783, "grad_norm": 0.3019992709159851, "learning_rate": 9.299495830763286e-05, "loss": 0.0392, "step": 1060 }, { "epoch": 1.1630434782608696, "grad_norm": 0.17657537758350372, "learning_rate": 9.282521182862629e-05, "loss": 0.0361, "step": 1070 }, { "epoch": 1.1739130434782608, "grad_norm": 0.30781546235084534, "learning_rate": 9.265359203611987e-05, "loss": 0.0337, "step": 1080 }, { "epoch": 1.184782608695652, "grad_norm": 0.2609535753726959, "learning_rate": 9.248010643731935e-05, "loss": 0.0269, "step": 1090 }, { "epoch": 1.1956521739130435, "grad_norm": 0.28583014011383057, "learning_rate": 9.230476262104677e-05, "loss": 0.0306, "step": 1100 }, { "epoch": 1.2065217391304348, "grad_norm": 0.4076569974422455, "learning_rate": 9.212756825740873e-05, "loss": 0.0359, "step": 1110 }, { "epoch": 1.2173913043478262, "grad_norm": 0.41756731271743774, "learning_rate": 9.194853109746074e-05, "loss": 0.0338, "step": 1120 }, { "epoch": 1.2282608695652173, "grad_norm": 0.363546222448349, "learning_rate": 9.176765897286813e-05, "loss": 0.0386, "step": 1130 }, { "epoch": 1.2391304347826086, "grad_norm": 0.3960663378238678, "learning_rate": 9.158495979556358e-05, "loss": 0.0369, "step": 1140 }, { "epoch": 1.25, "grad_norm": 0.260600209236145, "learning_rate": 9.140044155740101e-05, "loss": 0.0357, "step": 1150 }, { "epoch": 1.2608695652173914, "grad_norm": 0.24292735755443573, "learning_rate": 9.121411232980588e-05, "loss": 0.0339, "step": 1160 }, { "epoch": 1.2717391304347827, "grad_norm": 0.27685248851776123, "learning_rate": 9.102598026342222e-05, "loss": 0.0341, "step": 1170 }, { "epoch": 1.2826086956521738, "grad_norm": 0.26668187975883484, "learning_rate": 9.083605358775612e-05, "loss": 0.032, "step": 1180 }, { "epoch": 1.2934782608695652, "grad_norm": 0.27872323989868164, "learning_rate": 9.064434061081562e-05, "loss": 0.033, "step": 1190 }, { "epoch": 1.3043478260869565, "grad_norm": 0.2735164761543274, "learning_rate": 9.045084971874738e-05, "loss": 0.0354, "step": 1200 }, { "epoch": 1.315217391304348, "grad_norm": 0.28554099798202515, "learning_rate": 9.025558937546988e-05, "loss": 0.0318, "step": 1210 }, { "epoch": 1.3260869565217392, "grad_norm": 0.30446696281433105, "learning_rate": 9.005856812230304e-05, "loss": 0.0285, "step": 1220 }, { "epoch": 1.3369565217391304, "grad_norm": 0.3049046993255615, "learning_rate": 8.98597945775948e-05, "loss": 0.0345, "step": 1230 }, { "epoch": 1.3478260869565217, "grad_norm": 0.29424118995666504, "learning_rate": 8.965927743634391e-05, "loss": 0.0304, "step": 1240 }, { "epoch": 1.358695652173913, "grad_norm": 0.350027471780777, "learning_rate": 8.945702546981969e-05, "loss": 0.037, "step": 1250 }, { "epoch": 1.3695652173913042, "grad_norm": 0.24161510169506073, "learning_rate": 8.92530475251784e-05, "loss": 0.0296, "step": 1260 }, { "epoch": 1.3804347826086958, "grad_norm": 0.28369140625, "learning_rate": 8.90473525250761e-05, "loss": 0.0338, "step": 1270 }, { "epoch": 1.391304347826087, "grad_norm": 0.2735034227371216, "learning_rate": 8.883994946727849e-05, "loss": 0.0327, "step": 1280 }, { "epoch": 1.4021739130434783, "grad_norm": 0.26561832427978516, "learning_rate": 8.863084742426719e-05, "loss": 0.0357, "step": 1290 }, { "epoch": 1.4130434782608696, "grad_norm": 0.22670572996139526, "learning_rate": 8.842005554284296e-05, "loss": 0.0309, "step": 1300 }, { "epoch": 1.4239130434782608, "grad_norm": 0.3178609311580658, "learning_rate": 8.820758304372557e-05, "loss": 0.0307, "step": 1310 }, { "epoch": 1.434782608695652, "grad_norm": 0.2610357999801636, "learning_rate": 8.799343922115044e-05, "loss": 0.0321, "step": 1320 }, { "epoch": 1.4456521739130435, "grad_norm": 0.2457573115825653, "learning_rate": 8.77776334424621e-05, "loss": 0.0279, "step": 1330 }, { "epoch": 1.4565217391304348, "grad_norm": 0.28615960478782654, "learning_rate": 8.756017514770443e-05, "loss": 0.0312, "step": 1340 }, { "epoch": 1.4673913043478262, "grad_norm": 0.24879348278045654, "learning_rate": 8.73410738492077e-05, "loss": 0.026, "step": 1350 }, { "epoch": 1.4782608695652173, "grad_norm": 0.31809213757514954, "learning_rate": 8.71203391311725e-05, "loss": 0.0304, "step": 1360 }, { "epoch": 1.4891304347826086, "grad_norm": 0.28537970781326294, "learning_rate": 8.689798064925049e-05, "loss": 0.0234, "step": 1370 }, { "epoch": 1.5, "grad_norm": 0.2417411208152771, "learning_rate": 8.6674008130122e-05, "loss": 0.0294, "step": 1380 }, { "epoch": 1.5108695652173914, "grad_norm": 0.3035632371902466, "learning_rate": 8.644843137107059e-05, "loss": 0.0261, "step": 1390 }, { "epoch": 1.5217391304347827, "grad_norm": 0.2237926870584488, "learning_rate": 8.622126023955446e-05, "loss": 0.0321, "step": 1400 }, { "epoch": 1.5326086956521738, "grad_norm": 0.23017100989818573, "learning_rate": 8.599250467277483e-05, "loss": 0.0261, "step": 1410 }, { "epoch": 1.5434782608695652, "grad_norm": 0.3059643805027008, "learning_rate": 8.576217467724128e-05, "loss": 0.0317, "step": 1420 }, { "epoch": 1.5543478260869565, "grad_norm": 0.24075447022914886, "learning_rate": 8.553028032833397e-05, "loss": 0.03, "step": 1430 }, { "epoch": 1.5652173913043477, "grad_norm": 0.2758166491985321, "learning_rate": 8.529683176986295e-05, "loss": 0.0292, "step": 1440 }, { "epoch": 1.5760869565217392, "grad_norm": 0.3072378933429718, "learning_rate": 8.506183921362443e-05, "loss": 0.0304, "step": 1450 }, { "epoch": 1.5869565217391304, "grad_norm": 0.31627902388572693, "learning_rate": 8.482531293895412e-05, "loss": 0.0305, "step": 1460 }, { "epoch": 1.5978260869565217, "grad_norm": 0.2496868222951889, "learning_rate": 8.458726329227747e-05, "loss": 0.0294, "step": 1470 }, { "epoch": 1.608695652173913, "grad_norm": 0.22909675538539886, "learning_rate": 8.434770068665723e-05, "loss": 0.037, "step": 1480 }, { "epoch": 1.6195652173913042, "grad_norm": 0.2690674960613251, "learning_rate": 8.410663560133784e-05, "loss": 0.0295, "step": 1490 }, { "epoch": 1.6304347826086958, "grad_norm": 0.24377554655075073, "learning_rate": 8.386407858128706e-05, "loss": 0.0352, "step": 1500 }, { "epoch": 1.641304347826087, "grad_norm": 0.2325594425201416, "learning_rate": 8.362004023673474e-05, "loss": 0.0306, "step": 1510 }, { "epoch": 1.6521739130434783, "grad_norm": 0.2231265902519226, "learning_rate": 8.337453124270863e-05, "loss": 0.0283, "step": 1520 }, { "epoch": 1.6630434782608696, "grad_norm": 0.23302611708641052, "learning_rate": 8.31275623385675e-05, "loss": 0.0312, "step": 1530 }, { "epoch": 1.6739130434782608, "grad_norm": 0.27481865882873535, "learning_rate": 8.287914432753123e-05, "loss": 0.0325, "step": 1540 }, { "epoch": 1.6847826086956523, "grad_norm": 0.2550845742225647, "learning_rate": 8.262928807620843e-05, "loss": 0.031, "step": 1550 }, { "epoch": 1.6956521739130435, "grad_norm": 0.22116337716579437, "learning_rate": 8.237800451412095e-05, "loss": 0.0279, "step": 1560 }, { "epoch": 1.7065217391304348, "grad_norm": 0.3845021724700928, "learning_rate": 8.212530463322583e-05, "loss": 0.0297, "step": 1570 }, { "epoch": 1.7173913043478262, "grad_norm": 0.3023184835910797, "learning_rate": 8.18711994874345e-05, "loss": 0.0284, "step": 1580 }, { "epoch": 1.7282608695652173, "grad_norm": 0.21632587909698486, "learning_rate": 8.161570019212921e-05, "loss": 0.0292, "step": 1590 }, { "epoch": 1.7391304347826086, "grad_norm": 0.2863970398902893, "learning_rate": 8.135881792367686e-05, "loss": 0.0287, "step": 1600 }, { "epoch": 1.75, "grad_norm": 0.20062358677387238, "learning_rate": 8.110056391894005e-05, "loss": 0.0246, "step": 1610 }, { "epoch": 1.7608695652173914, "grad_norm": 0.2996312379837036, "learning_rate": 8.084094947478556e-05, "loss": 0.0234, "step": 1620 }, { "epoch": 1.7717391304347827, "grad_norm": 0.2715204060077667, "learning_rate": 8.057998594759022e-05, "loss": 0.0267, "step": 1630 }, { "epoch": 1.7826086956521738, "grad_norm": 0.27594679594039917, "learning_rate": 8.031768475274413e-05, "loss": 0.0274, "step": 1640 }, { "epoch": 1.7934782608695652, "grad_norm": 0.25428059697151184, "learning_rate": 8.005405736415126e-05, "loss": 0.0326, "step": 1650 }, { "epoch": 1.8043478260869565, "grad_norm": 0.241542249917984, "learning_rate": 7.978911531372765e-05, "loss": 0.0209, "step": 1660 }, { "epoch": 1.8152173913043477, "grad_norm": 0.2677355408668518, "learning_rate": 7.952287019089685e-05, "loss": 0.0268, "step": 1670 }, { "epoch": 1.8260869565217392, "grad_norm": 0.19579513370990753, "learning_rate": 7.925533364208309e-05, "loss": 0.0284, "step": 1680 }, { "epoch": 1.8369565217391304, "grad_norm": 0.21474671363830566, "learning_rate": 7.898651737020166e-05, "loss": 0.0274, "step": 1690 }, { "epoch": 1.8478260869565217, "grad_norm": 0.24959373474121094, "learning_rate": 7.871643313414718e-05, "loss": 0.0257, "step": 1700 }, { "epoch": 1.858695652173913, "grad_norm": 0.24523958563804626, "learning_rate": 7.844509274827907e-05, "loss": 0.0253, "step": 1710 }, { "epoch": 1.8695652173913042, "grad_norm": 0.29573023319244385, "learning_rate": 7.817250808190483e-05, "loss": 0.0298, "step": 1720 }, { "epoch": 1.8804347826086958, "grad_norm": 0.3292531669139862, "learning_rate": 7.789869105876083e-05, "loss": 0.029, "step": 1730 }, { "epoch": 1.891304347826087, "grad_norm": 0.24724705517292023, "learning_rate": 7.762365365649067e-05, "loss": 0.0244, "step": 1740 }, { "epoch": 1.9021739130434783, "grad_norm": 0.21725831925868988, "learning_rate": 7.734740790612136e-05, "loss": 0.0286, "step": 1750 }, { "epoch": 1.9130434782608696, "grad_norm": 0.2548612058162689, "learning_rate": 7.70699658915369e-05, "loss": 0.0298, "step": 1760 }, { "epoch": 1.9239130434782608, "grad_norm": 0.27427971363067627, "learning_rate": 7.679133974894983e-05, "loss": 0.0285, "step": 1770 }, { "epoch": 1.9347826086956523, "grad_norm": 0.2469799667596817, "learning_rate": 7.651154166637025e-05, "loss": 0.0285, "step": 1780 }, { "epoch": 1.9456521739130435, "grad_norm": 0.27580276131629944, "learning_rate": 7.623058388307269e-05, "loss": 0.0295, "step": 1790 }, { "epoch": 1.9565217391304348, "grad_norm": 0.2752760350704193, "learning_rate": 7.594847868906076e-05, "loss": 0.0293, "step": 1800 }, { "epoch": 1.9673913043478262, "grad_norm": 0.24122604727745056, "learning_rate": 7.566523842452958e-05, "loss": 0.028, "step": 1810 }, { "epoch": 1.9782608695652173, "grad_norm": 0.34590691328048706, "learning_rate": 7.538087547932585e-05, "loss": 0.023, "step": 1820 }, { "epoch": 1.9891304347826086, "grad_norm": 0.217288076877594, "learning_rate": 7.509540229240601e-05, "loss": 0.0241, "step": 1830 }, { "epoch": 2.0, "grad_norm": 0.2541623115539551, "learning_rate": 7.480883135129211e-05, "loss": 0.0241, "step": 1840 }, { "epoch": 2.010869565217391, "grad_norm": 0.27332010865211487, "learning_rate": 7.452117519152542e-05, "loss": 0.0232, "step": 1850 }, { "epoch": 2.0217391304347827, "grad_norm": 0.18972714245319366, "learning_rate": 7.423244639611826e-05, "loss": 0.0273, "step": 1860 }, { "epoch": 2.032608695652174, "grad_norm": 0.19656722247600555, "learning_rate": 7.394265759500348e-05, "loss": 0.027, "step": 1870 }, { "epoch": 2.0434782608695654, "grad_norm": 0.22846871614456177, "learning_rate": 7.365182146448205e-05, "loss": 0.0225, "step": 1880 }, { "epoch": 2.0543478260869565, "grad_norm": 0.21889623999595642, "learning_rate": 7.335995072666848e-05, "loss": 0.0212, "step": 1890 }, { "epoch": 2.0652173913043477, "grad_norm": 0.15208809077739716, "learning_rate": 7.30670581489344e-05, "loss": 0.0284, "step": 1900 }, { "epoch": 2.0760869565217392, "grad_norm": 0.30196961760520935, "learning_rate": 7.277315654334997e-05, "loss": 0.0256, "step": 1910 }, { "epoch": 2.0869565217391304, "grad_norm": 0.3277256190776825, "learning_rate": 7.247825876612353e-05, "loss": 0.0234, "step": 1920 }, { "epoch": 2.097826086956522, "grad_norm": 0.24114277958869934, "learning_rate": 7.218237771703921e-05, "loss": 0.0251, "step": 1930 }, { "epoch": 2.108695652173913, "grad_norm": 0.27464061975479126, "learning_rate": 7.188552633889259e-05, "loss": 0.0272, "step": 1940 }, { "epoch": 2.119565217391304, "grad_norm": 0.24296048283576965, "learning_rate": 7.158771761692464e-05, "loss": 0.024, "step": 1950 }, { "epoch": 2.130434782608696, "grad_norm": 0.17170515656471252, "learning_rate": 7.128896457825364e-05, "loss": 0.0198, "step": 1960 }, { "epoch": 2.141304347826087, "grad_norm": 0.20415639877319336, "learning_rate": 7.09892802913053e-05, "loss": 0.0278, "step": 1970 }, { "epoch": 2.1521739130434785, "grad_norm": 0.20857463777065277, "learning_rate": 7.068867786524116e-05, "loss": 0.0314, "step": 1980 }, { "epoch": 2.1630434782608696, "grad_norm": 0.293731153011322, "learning_rate": 7.038717044938519e-05, "loss": 0.0227, "step": 1990 }, { "epoch": 2.1739130434782608, "grad_norm": 0.18717971444129944, "learning_rate": 7.008477123264848e-05, "loss": 0.0195, "step": 2000 }, { "epoch": 2.1847826086956523, "grad_norm": 0.22212952375411987, "learning_rate": 6.978149344295242e-05, "loss": 0.0216, "step": 2010 }, { "epoch": 2.1956521739130435, "grad_norm": 0.2290237843990326, "learning_rate": 6.947735034665002e-05, "loss": 0.0255, "step": 2020 }, { "epoch": 2.2065217391304346, "grad_norm": 0.1830049455165863, "learning_rate": 6.917235524794558e-05, "loss": 0.0294, "step": 2030 }, { "epoch": 2.217391304347826, "grad_norm": 0.16847161948680878, "learning_rate": 6.886652148831279e-05, "loss": 0.0277, "step": 2040 }, { "epoch": 2.2282608695652173, "grad_norm": 0.17339234054088593, "learning_rate": 6.855986244591104e-05, "loss": 0.0236, "step": 2050 }, { "epoch": 2.239130434782609, "grad_norm": 0.19348445534706116, "learning_rate": 6.825239153500029e-05, "loss": 0.0216, "step": 2060 }, { "epoch": 2.25, "grad_norm": 0.2270950973033905, "learning_rate": 6.794412220535426e-05, "loss": 0.0206, "step": 2070 }, { "epoch": 2.260869565217391, "grad_norm": 0.20214591920375824, "learning_rate": 6.763506794167208e-05, "loss": 0.0218, "step": 2080 }, { "epoch": 2.2717391304347827, "grad_norm": 0.16403691470623016, "learning_rate": 6.732524226298841e-05, "loss": 0.02, "step": 2090 }, { "epoch": 2.282608695652174, "grad_norm": 0.17673853039741516, "learning_rate": 6.701465872208216e-05, "loss": 0.0207, "step": 2100 }, { "epoch": 2.2934782608695654, "grad_norm": 0.21534697711467743, "learning_rate": 6.670333090488356e-05, "loss": 0.0189, "step": 2110 }, { "epoch": 2.3043478260869565, "grad_norm": 0.165096253156662, "learning_rate": 6.639127242987988e-05, "loss": 0.0195, "step": 2120 }, { "epoch": 2.3152173913043477, "grad_norm": 0.27260059118270874, "learning_rate": 6.607849694751977e-05, "loss": 0.0231, "step": 2130 }, { "epoch": 2.3260869565217392, "grad_norm": 0.2327706515789032, "learning_rate": 6.576501813961609e-05, "loss": 0.0226, "step": 2140 }, { "epoch": 2.3369565217391304, "grad_norm": 0.17362096905708313, "learning_rate": 6.545084971874738e-05, "loss": 0.0264, "step": 2150 }, { "epoch": 2.3478260869565215, "grad_norm": 0.24459755420684814, "learning_rate": 6.513600542765817e-05, "loss": 0.023, "step": 2160 }, { "epoch": 2.358695652173913, "grad_norm": 0.20271766185760498, "learning_rate": 6.48204990386577e-05, "loss": 0.0208, "step": 2170 }, { "epoch": 2.369565217391304, "grad_norm": 0.2861473560333252, "learning_rate": 6.450434435301751e-05, "loss": 0.0237, "step": 2180 }, { "epoch": 2.380434782608696, "grad_norm": 0.2328135222196579, "learning_rate": 6.418755520036775e-05, "loss": 0.0219, "step": 2190 }, { "epoch": 2.391304347826087, "grad_norm": 0.2409750074148178, "learning_rate": 6.387014543809223e-05, "loss": 0.0222, "step": 2200 }, { "epoch": 2.4021739130434785, "grad_norm": 0.20612117648124695, "learning_rate": 6.355212895072223e-05, "loss": 0.0217, "step": 2210 }, { "epoch": 2.4130434782608696, "grad_norm": 0.2607957720756531, "learning_rate": 6.323351964932908e-05, "loss": 0.0197, "step": 2220 }, { "epoch": 2.4239130434782608, "grad_norm": 0.2704881727695465, "learning_rate": 6.291433147091583e-05, "loss": 0.0213, "step": 2230 }, { "epoch": 2.4347826086956523, "grad_norm": 0.22981029748916626, "learning_rate": 6.259457837780742e-05, "loss": 0.0205, "step": 2240 }, { "epoch": 2.4456521739130435, "grad_norm": 0.19447964429855347, "learning_rate": 6.227427435703997e-05, "loss": 0.0248, "step": 2250 }, { "epoch": 2.4565217391304346, "grad_norm": 0.31986603140830994, "learning_rate": 6.195343341974899e-05, "loss": 0.0246, "step": 2260 }, { "epoch": 2.467391304347826, "grad_norm": 0.20756466686725616, "learning_rate": 6.163206960055651e-05, "loss": 0.0207, "step": 2270 }, { "epoch": 2.4782608695652173, "grad_norm": 0.22251754999160767, "learning_rate": 6.131019695695702e-05, "loss": 0.0265, "step": 2280 }, { "epoch": 2.489130434782609, "grad_norm": 0.16655093431472778, "learning_rate": 6.0987829568702656e-05, "loss": 0.0207, "step": 2290 }, { "epoch": 2.5, "grad_norm": 0.2425738126039505, "learning_rate": 6.066498153718735e-05, "loss": 0.0176, "step": 2300 }, { "epoch": 2.5108695652173916, "grad_norm": 0.23594196140766144, "learning_rate": 6.034166698482984e-05, "loss": 0.0253, "step": 2310 }, { "epoch": 2.5217391304347827, "grad_norm": 0.17139174044132233, "learning_rate": 6.001790005445607e-05, "loss": 0.0191, "step": 2320 }, { "epoch": 2.532608695652174, "grad_norm": 0.17908968031406403, "learning_rate": 5.969369490868042e-05, "loss": 0.0259, "step": 2330 }, { "epoch": 2.5434782608695654, "grad_norm": 0.24141980707645416, "learning_rate": 5.9369065729286245e-05, "loss": 0.0246, "step": 2340 }, { "epoch": 2.5543478260869565, "grad_norm": 0.23516008257865906, "learning_rate": 5.90440267166055e-05, "loss": 0.0256, "step": 2350 }, { "epoch": 2.5652173913043477, "grad_norm": 0.2081535905599594, "learning_rate": 5.871859208889759e-05, "loss": 0.0203, "step": 2360 }, { "epoch": 2.5760869565217392, "grad_norm": 0.2254313826560974, "learning_rate": 5.8392776081727385e-05, "loss": 0.0216, "step": 2370 }, { "epoch": 2.5869565217391304, "grad_norm": 0.22026807069778442, "learning_rate": 5.8066592947342555e-05, "loss": 0.0188, "step": 2380 }, { "epoch": 2.5978260869565215, "grad_norm": 0.2628653943538666, "learning_rate": 5.7740056954050084e-05, "loss": 0.0224, "step": 2390 }, { "epoch": 2.608695652173913, "grad_norm": 0.22398746013641357, "learning_rate": 5.74131823855921e-05, "loss": 0.0238, "step": 2400 }, { "epoch": 2.619565217391304, "grad_norm": 0.20215076208114624, "learning_rate": 5.7085983540521216e-05, "loss": 0.0197, "step": 2410 }, { "epoch": 2.630434782608696, "grad_norm": 0.19902300834655762, "learning_rate": 5.675847473157485e-05, "loss": 0.021, "step": 2420 }, { "epoch": 2.641304347826087, "grad_norm": 0.21893462538719177, "learning_rate": 5.6430670285049314e-05, "loss": 0.0202, "step": 2430 }, { "epoch": 2.6521739130434785, "grad_norm": 0.21789760887622833, "learning_rate": 5.6102584540173006e-05, "loss": 0.0227, "step": 2440 }, { "epoch": 2.6630434782608696, "grad_norm": 0.12057076394557953, "learning_rate": 5.577423184847932e-05, "loss": 0.0199, "step": 2450 }, { "epoch": 2.6739130434782608, "grad_norm": 0.2071666419506073, "learning_rate": 5.544562657317863e-05, "loss": 0.0236, "step": 2460 }, { "epoch": 2.6847826086956523, "grad_norm": 0.2847704291343689, "learning_rate": 5.511678308853026e-05, "loss": 0.0186, "step": 2470 }, { "epoch": 2.6956521739130435, "grad_norm": 0.17881885170936584, "learning_rate": 5.478771577921351e-05, "loss": 0.0191, "step": 2480 }, { "epoch": 2.7065217391304346, "grad_norm": 0.19653011858463287, "learning_rate": 5.445843903969854e-05, "loss": 0.0137, "step": 2490 }, { "epoch": 2.717391304347826, "grad_norm": 0.2046557366847992, "learning_rate": 5.4128967273616625e-05, "loss": 0.0209, "step": 2500 }, { "epoch": 2.7282608695652173, "grad_norm": 0.21046030521392822, "learning_rate": 5.379931489313016e-05, "loss": 0.0207, "step": 2510 }, { "epoch": 2.7391304347826084, "grad_norm": 0.2215111255645752, "learning_rate": 5.3469496318302204e-05, "loss": 0.019, "step": 2520 }, { "epoch": 2.75, "grad_norm": 0.22360099852085114, "learning_rate": 5.313952597646568e-05, "loss": 0.0158, "step": 2530 }, { "epoch": 2.7608695652173916, "grad_norm": 0.1709163635969162, "learning_rate": 5.280941830159227e-05, "loss": 0.0214, "step": 2540 }, { "epoch": 2.7717391304347827, "grad_norm": 0.211487278342247, "learning_rate": 5.247918773366112e-05, "loss": 0.0242, "step": 2550 }, { "epoch": 2.782608695652174, "grad_norm": 0.3075908422470093, "learning_rate": 5.214884871802703e-05, "loss": 0.0213, "step": 2560 }, { "epoch": 2.7934782608695654, "grad_norm": 0.22945576906204224, "learning_rate": 5.1818415704788725e-05, "loss": 0.0187, "step": 2570 }, { "epoch": 2.8043478260869565, "grad_norm": 0.21798940002918243, "learning_rate": 5.148790314815663e-05, "loss": 0.0202, "step": 2580 }, { "epoch": 2.8152173913043477, "grad_norm": 0.14597228169441223, "learning_rate": 5.1157325505820694e-05, "loss": 0.0221, "step": 2590 }, { "epoch": 2.8260869565217392, "grad_norm": 0.24173279106616974, "learning_rate": 5.0826697238317935e-05, "loss": 0.0177, "step": 2600 }, { "epoch": 2.8369565217391304, "grad_norm": 0.16206835210323334, "learning_rate": 5.0496032808399815e-05, "loss": 0.0167, "step": 2610 }, { "epoch": 2.8478260869565215, "grad_norm": 0.20870648324489594, "learning_rate": 5.016534668039976e-05, "loss": 0.0208, "step": 2620 }, { "epoch": 2.858695652173913, "grad_norm": 0.13695970177650452, "learning_rate": 4.9834653319600246e-05, "loss": 0.0155, "step": 2630 }, { "epoch": 2.869565217391304, "grad_norm": 0.16413715481758118, "learning_rate": 4.950396719160018e-05, "loss": 0.0151, "step": 2640 }, { "epoch": 2.880434782608696, "grad_norm": 0.2725026607513428, "learning_rate": 4.917330276168208e-05, "loss": 0.0228, "step": 2650 }, { "epoch": 2.891304347826087, "grad_norm": 0.19408078491687775, "learning_rate": 4.884267449417931e-05, "loss": 0.0255, "step": 2660 }, { "epoch": 2.9021739130434785, "grad_norm": 0.15220940113067627, "learning_rate": 4.851209685184338e-05, "loss": 0.0191, "step": 2670 }, { "epoch": 2.9130434782608696, "grad_norm": 0.24963606894016266, "learning_rate": 4.818158429521129e-05, "loss": 0.0228, "step": 2680 }, { "epoch": 2.9239130434782608, "grad_norm": 0.2193748503923416, "learning_rate": 4.785115128197298e-05, "loss": 0.0184, "step": 2690 }, { "epoch": 2.9347826086956523, "grad_norm": 0.28289085626602173, "learning_rate": 4.7520812266338885e-05, "loss": 0.0225, "step": 2700 }, { "epoch": 2.9456521739130435, "grad_norm": 0.2755283713340759, "learning_rate": 4.7190581698407725e-05, "loss": 0.0198, "step": 2710 }, { "epoch": 2.9565217391304346, "grad_norm": 0.2590217888355255, "learning_rate": 4.6860474023534335e-05, "loss": 0.0197, "step": 2720 }, { "epoch": 2.967391304347826, "grad_norm": 0.2700153887271881, "learning_rate": 4.65305036816978e-05, "loss": 0.0198, "step": 2730 }, { "epoch": 2.9782608695652173, "grad_norm": 0.21997500956058502, "learning_rate": 4.620068510686985e-05, "loss": 0.02, "step": 2740 }, { "epoch": 2.9891304347826084, "grad_norm": 0.23885446786880493, "learning_rate": 4.5871032726383386e-05, "loss": 0.0166, "step": 2750 }, { "epoch": 3.0, "grad_norm": 0.26925128698349, "learning_rate": 4.554156096030149e-05, "loss": 0.0187, "step": 2760 }, { "epoch": 3.010869565217391, "grad_norm": 0.20031136274337769, "learning_rate": 4.5212284220786494e-05, "loss": 0.0169, "step": 2770 }, { "epoch": 3.0217391304347827, "grad_norm": 0.2370258867740631, "learning_rate": 4.488321691146975e-05, "loss": 0.0194, "step": 2780 }, { "epoch": 3.032608695652174, "grad_norm": 0.14988850057125092, "learning_rate": 4.4554373426821374e-05, "loss": 0.0149, "step": 2790 }, { "epoch": 3.0434782608695654, "grad_norm": 0.1604338139295578, "learning_rate": 4.4225768151520694e-05, "loss": 0.018, "step": 2800 }, { "epoch": 3.0543478260869565, "grad_norm": 0.1709444671869278, "learning_rate": 4.3897415459827e-05, "loss": 0.018, "step": 2810 }, { "epoch": 3.0652173913043477, "grad_norm": 0.1633748561143875, "learning_rate": 4.3569329714950704e-05, "loss": 0.0139, "step": 2820 }, { "epoch": 3.0760869565217392, "grad_norm": 0.18419773876667023, "learning_rate": 4.324152526842517e-05, "loss": 0.018, "step": 2830 }, { "epoch": 3.0869565217391304, "grad_norm": 0.1465953290462494, "learning_rate": 4.291401645947879e-05, "loss": 0.0195, "step": 2840 }, { "epoch": 3.097826086956522, "grad_norm": 0.21373240649700165, "learning_rate": 4.2586817614407895e-05, "loss": 0.0165, "step": 2850 }, { "epoch": 3.108695652173913, "grad_norm": 0.13149115443229675, "learning_rate": 4.2259943045949934e-05, "loss": 0.0191, "step": 2860 }, { "epoch": 3.119565217391304, "grad_norm": 0.22037185728549957, "learning_rate": 4.1933407052657456e-05, "loss": 0.015, "step": 2870 }, { "epoch": 3.130434782608696, "grad_norm": 0.17351217567920685, "learning_rate": 4.160722391827262e-05, "loss": 0.0153, "step": 2880 }, { "epoch": 3.141304347826087, "grad_norm": 0.1752108484506607, "learning_rate": 4.1281407911102425e-05, "loss": 0.0162, "step": 2890 }, { "epoch": 3.1521739130434785, "grad_norm": 0.11886758357286453, "learning_rate": 4.095597328339452e-05, "loss": 0.0154, "step": 2900 }, { "epoch": 3.1630434782608696, "grad_norm": 0.22312021255493164, "learning_rate": 4.063093427071376e-05, "loss": 0.0249, "step": 2910 }, { "epoch": 3.1739130434782608, "grad_norm": 0.18036895990371704, "learning_rate": 4.0306305091319595e-05, "loss": 0.0152, "step": 2920 }, { "epoch": 3.1847826086956523, "grad_norm": 0.13070718944072723, "learning_rate": 3.9982099945543945e-05, "loss": 0.0152, "step": 2930 }, { "epoch": 3.1956521739130435, "grad_norm": 0.1445332020521164, "learning_rate": 3.965833301517017e-05, "loss": 0.0154, "step": 2940 }, { "epoch": 3.2065217391304346, "grad_norm": 0.14855942130088806, "learning_rate": 3.933501846281267e-05, "loss": 0.0146, "step": 2950 }, { "epoch": 3.217391304347826, "grad_norm": 0.13377995789051056, "learning_rate": 3.901217043129735e-05, "loss": 0.0213, "step": 2960 }, { "epoch": 3.2282608695652173, "grad_norm": 0.1453462839126587, "learning_rate": 3.8689803043043e-05, "loss": 0.0173, "step": 2970 }, { "epoch": 3.239130434782609, "grad_norm": 0.12768065929412842, "learning_rate": 3.836793039944349e-05, "loss": 0.0145, "step": 2980 }, { "epoch": 3.25, "grad_norm": 0.176410511136055, "learning_rate": 3.8046566580251e-05, "loss": 0.0129, "step": 2990 }, { "epoch": 3.260869565217391, "grad_norm": 0.21856428682804108, "learning_rate": 3.772572564296005e-05, "loss": 0.0169, "step": 3000 }, { "epoch": 3.2717391304347827, "grad_norm": 0.16268354654312134, "learning_rate": 3.74054216221926e-05, "loss": 0.0146, "step": 3010 }, { "epoch": 3.282608695652174, "grad_norm": 0.17902961373329163, "learning_rate": 3.7085668529084184e-05, "loss": 0.0189, "step": 3020 }, { "epoch": 3.2934782608695654, "grad_norm": 0.2093406766653061, "learning_rate": 3.676648035067093e-05, "loss": 0.0159, "step": 3030 }, { "epoch": 3.3043478260869565, "grad_norm": 0.18729008734226227, "learning_rate": 3.6447871049277796e-05, "loss": 0.0133, "step": 3040 }, { "epoch": 3.3152173913043477, "grad_norm": 0.21578620374202728, "learning_rate": 3.612985456190778e-05, "loss": 0.0185, "step": 3050 }, { "epoch": 3.3260869565217392, "grad_norm": 0.1456160843372345, "learning_rate": 3.581244479963225e-05, "loss": 0.0179, "step": 3060 }, { "epoch": 3.3369565217391304, "grad_norm": 0.15574467182159424, "learning_rate": 3.5495655646982505e-05, "loss": 0.0191, "step": 3070 }, { "epoch": 3.3478260869565215, "grad_norm": 0.21840086579322815, "learning_rate": 3.517950096134232e-05, "loss": 0.0167, "step": 3080 }, { "epoch": 3.358695652173913, "grad_norm": 0.1252320110797882, "learning_rate": 3.4863994572341843e-05, "loss": 0.0156, "step": 3090 }, { "epoch": 3.369565217391304, "grad_norm": 0.1790045201778412, "learning_rate": 3.4549150281252636e-05, "loss": 0.0153, "step": 3100 }, { "epoch": 3.380434782608696, "grad_norm": 0.21787020564079285, "learning_rate": 3.423498186038393e-05, "loss": 0.0203, "step": 3110 }, { "epoch": 3.391304347826087, "grad_norm": 0.17932236194610596, "learning_rate": 3.392150305248024e-05, "loss": 0.0145, "step": 3120 }, { "epoch": 3.4021739130434785, "grad_norm": 0.1460498571395874, "learning_rate": 3.360872757012011e-05, "loss": 0.0168, "step": 3130 }, { "epoch": 3.4130434782608696, "grad_norm": 0.20171473920345306, "learning_rate": 3.329666909511645e-05, "loss": 0.0188, "step": 3140 }, { "epoch": 3.4239130434782608, "grad_norm": 0.1880096197128296, "learning_rate": 3.298534127791785e-05, "loss": 0.0162, "step": 3150 }, { "epoch": 3.4347826086956523, "grad_norm": 0.21033500134944916, "learning_rate": 3.267475773701161e-05, "loss": 0.0152, "step": 3160 }, { "epoch": 3.4456521739130435, "grad_norm": 0.18287412822246552, "learning_rate": 3.236493205832795e-05, "loss": 0.0183, "step": 3170 }, { "epoch": 3.4565217391304346, "grad_norm": 0.1669587939977646, "learning_rate": 3.205587779464576e-05, "loss": 0.0145, "step": 3180 }, { "epoch": 3.467391304347826, "grad_norm": 0.2002091407775879, "learning_rate": 3.1747608464999725e-05, "loss": 0.0152, "step": 3190 }, { "epoch": 3.4782608695652173, "grad_norm": 0.20512893795967102, "learning_rate": 3.144013755408895e-05, "loss": 0.0209, "step": 3200 }, { "epoch": 3.489130434782609, "grad_norm": 0.164790078997612, "learning_rate": 3.113347851168721e-05, "loss": 0.0179, "step": 3210 }, { "epoch": 3.5, "grad_norm": 0.1478477120399475, "learning_rate": 3.082764475205442e-05, "loss": 0.0143, "step": 3220 }, { "epoch": 3.5108695652173916, "grad_norm": 0.1484198421239853, "learning_rate": 3.052264965335e-05, "loss": 0.0151, "step": 3230 }, { "epoch": 3.5217391304347827, "grad_norm": 0.1396767646074295, "learning_rate": 3.0218506557047598e-05, "loss": 0.012, "step": 3240 }, { "epoch": 3.532608695652174, "grad_norm": 0.12337210774421692, "learning_rate": 2.991522876735154e-05, "loss": 0.0118, "step": 3250 }, { "epoch": 3.5434782608695654, "grad_norm": 0.15380887687206268, "learning_rate": 2.9612829550614836e-05, "loss": 0.0217, "step": 3260 }, { "epoch": 3.5543478260869565, "grad_norm": 0.13729456067085266, "learning_rate": 2.931132213475884e-05, "loss": 0.0151, "step": 3270 }, { "epoch": 3.5652173913043477, "grad_norm": 0.12622790038585663, "learning_rate": 2.9010719708694722e-05, "loss": 0.0127, "step": 3280 }, { "epoch": 3.5760869565217392, "grad_norm": 0.17325228452682495, "learning_rate": 2.8711035421746367e-05, "loss": 0.0158, "step": 3290 }, { "epoch": 3.5869565217391304, "grad_norm": 0.13225744664669037, "learning_rate": 2.8412282383075363e-05, "loss": 0.0125, "step": 3300 }, { "epoch": 3.5978260869565215, "grad_norm": 0.17985399067401886, "learning_rate": 2.811447366110741e-05, "loss": 0.0137, "step": 3310 }, { "epoch": 3.608695652173913, "grad_norm": 0.09231913089752197, "learning_rate": 2.7817622282960815e-05, "loss": 0.0127, "step": 3320 }, { "epoch": 3.619565217391304, "grad_norm": 0.17219118773937225, "learning_rate": 2.7521741233876496e-05, "loss": 0.014, "step": 3330 }, { "epoch": 3.630434782608696, "grad_norm": 0.2218349128961563, "learning_rate": 2.7226843456650037e-05, "loss": 0.0141, "step": 3340 }, { "epoch": 3.641304347826087, "grad_norm": 0.2514891028404236, "learning_rate": 2.693294185106562e-05, "loss": 0.0181, "step": 3350 }, { "epoch": 3.6521739130434785, "grad_norm": 0.1861620843410492, "learning_rate": 2.6640049273331515e-05, "loss": 0.0135, "step": 3360 }, { "epoch": 3.6630434782608696, "grad_norm": 0.11425938457250595, "learning_rate": 2.6348178535517966e-05, "loss": 0.0193, "step": 3370 }, { "epoch": 3.6739130434782608, "grad_norm": 0.18965540826320648, "learning_rate": 2.6057342404996522e-05, "loss": 0.0187, "step": 3380 }, { "epoch": 3.6847826086956523, "grad_norm": 0.19534063339233398, "learning_rate": 2.5767553603881767e-05, "loss": 0.0158, "step": 3390 }, { "epoch": 3.6956521739130435, "grad_norm": 0.17224030196666718, "learning_rate": 2.547882480847461e-05, "loss": 0.0182, "step": 3400 }, { "epoch": 3.7065217391304346, "grad_norm": 0.13765761256217957, "learning_rate": 2.5191168648707887e-05, "loss": 0.0144, "step": 3410 }, { "epoch": 3.717391304347826, "grad_norm": 0.20135529339313507, "learning_rate": 2.490459770759398e-05, "loss": 0.0161, "step": 3420 }, { "epoch": 3.7282608695652173, "grad_norm": 0.14608322083950043, "learning_rate": 2.4619124520674146e-05, "loss": 0.0143, "step": 3430 }, { "epoch": 3.7391304347826084, "grad_norm": 0.2197912484407425, "learning_rate": 2.433476157547044e-05, "loss": 0.0155, "step": 3440 }, { "epoch": 3.75, "grad_norm": 0.1401628851890564, "learning_rate": 2.405152131093926e-05, "loss": 0.014, "step": 3450 }, { "epoch": 3.7608695652173916, "grad_norm": 0.14256739616394043, "learning_rate": 2.3769416116927335e-05, "loss": 0.0178, "step": 3460 }, { "epoch": 3.7717391304347827, "grad_norm": 0.15367449820041656, "learning_rate": 2.3488458333629777e-05, "loss": 0.0131, "step": 3470 }, { "epoch": 3.782608695652174, "grad_norm": 0.15327581763267517, "learning_rate": 2.3208660251050158e-05, "loss": 0.015, "step": 3480 }, { "epoch": 3.7934782608695654, "grad_norm": 0.11331693828105927, "learning_rate": 2.29300341084631e-05, "loss": 0.0139, "step": 3490 }, { "epoch": 3.8043478260869565, "grad_norm": 0.15740583837032318, "learning_rate": 2.2652592093878666e-05, "loss": 0.0201, "step": 3500 }, { "epoch": 3.8152173913043477, "grad_norm": 0.1463966816663742, "learning_rate": 2.237634634350934e-05, "loss": 0.0154, "step": 3510 }, { "epoch": 3.8260869565217392, "grad_norm": 0.12818191945552826, "learning_rate": 2.2101308941239203e-05, "loss": 0.0127, "step": 3520 }, { "epoch": 3.8369565217391304, "grad_norm": 0.15985611081123352, "learning_rate": 2.182749191809518e-05, "loss": 0.0134, "step": 3530 }, { "epoch": 3.8478260869565215, "grad_norm": 0.2131720781326294, "learning_rate": 2.1554907251720945e-05, "loss": 0.0171, "step": 3540 }, { "epoch": 3.858695652173913, "grad_norm": 0.10271260142326355, "learning_rate": 2.128356686585282e-05, "loss": 0.0143, "step": 3550 }, { "epoch": 3.869565217391304, "grad_norm": 0.12285394221544266, "learning_rate": 2.1013482629798333e-05, "loss": 0.0135, "step": 3560 }, { "epoch": 3.880434782608696, "grad_norm": 0.18301796913146973, "learning_rate": 2.0744666357916925e-05, "loss": 0.017, "step": 3570 }, { "epoch": 3.891304347826087, "grad_norm": 0.20998628437519073, "learning_rate": 2.0477129809103147e-05, "loss": 0.0171, "step": 3580 }, { "epoch": 3.9021739130434785, "grad_norm": 0.15842413902282715, "learning_rate": 2.0210884686272368e-05, "loss": 0.0134, "step": 3590 }, { "epoch": 3.9130434782608696, "grad_norm": 0.12548497319221497, "learning_rate": 1.9945942635848748e-05, "loss": 0.0149, "step": 3600 }, { "epoch": 3.9239130434782608, "grad_norm": 0.1245172843337059, "learning_rate": 1.9682315247255894e-05, "loss": 0.012, "step": 3610 }, { "epoch": 3.9347826086956523, "grad_norm": 0.14383450150489807, "learning_rate": 1.942001405240979e-05, "loss": 0.0146, "step": 3620 }, { "epoch": 3.9456521739130435, "grad_norm": 0.11160749197006226, "learning_rate": 1.9159050525214452e-05, "loss": 0.0143, "step": 3630 }, { "epoch": 3.9565217391304346, "grad_norm": 0.12985584139823914, "learning_rate": 1.8899436081059975e-05, "loss": 0.0144, "step": 3640 }, { "epoch": 3.967391304347826, "grad_norm": 0.2041911780834198, "learning_rate": 1.8641182076323148e-05, "loss": 0.0163, "step": 3650 }, { "epoch": 3.9782608695652173, "grad_norm": 0.11336560547351837, "learning_rate": 1.838429980787081e-05, "loss": 0.011, "step": 3660 }, { "epoch": 3.9891304347826084, "grad_norm": 0.13748924434185028, "learning_rate": 1.8128800512565513e-05, "loss": 0.0144, "step": 3670 }, { "epoch": 4.0, "grad_norm": 0.24345290660858154, "learning_rate": 1.787469536677419e-05, "loss": 0.0155, "step": 3680 }, { "epoch": 4.010869565217392, "grad_norm": 0.21563570201396942, "learning_rate": 1.7621995485879062e-05, "loss": 0.0155, "step": 3690 }, { "epoch": 4.021739130434782, "grad_norm": 0.21253818273544312, "learning_rate": 1.7370711923791567e-05, "loss": 0.0116, "step": 3700 }, { "epoch": 4.032608695652174, "grad_norm": 0.1393989771604538, "learning_rate": 1.712085567246878e-05, "loss": 0.0183, "step": 3710 }, { "epoch": 4.043478260869565, "grad_norm": 0.11780686676502228, "learning_rate": 1.6872437661432517e-05, "loss": 0.0136, "step": 3720 }, { "epoch": 4.054347826086956, "grad_norm": 0.12765192985534668, "learning_rate": 1.662546875729138e-05, "loss": 0.0118, "step": 3730 }, { "epoch": 4.065217391304348, "grad_norm": 0.1177617758512497, "learning_rate": 1.637995976326527e-05, "loss": 0.0153, "step": 3740 }, { "epoch": 4.076086956521739, "grad_norm": 0.16909116506576538, "learning_rate": 1.6135921418712956e-05, "loss": 0.0143, "step": 3750 }, { "epoch": 4.086956521739131, "grad_norm": 0.21315212547779083, "learning_rate": 1.5893364398662176e-05, "loss": 0.0135, "step": 3760 }, { "epoch": 4.0978260869565215, "grad_norm": 0.190399169921875, "learning_rate": 1.5652299313342773e-05, "loss": 0.0172, "step": 3770 }, { "epoch": 4.108695652173913, "grad_norm": 0.12744581699371338, "learning_rate": 1.5412736707722537e-05, "loss": 0.0126, "step": 3780 }, { "epoch": 4.119565217391305, "grad_norm": 0.09308245778083801, "learning_rate": 1.517468706104589e-05, "loss": 0.01, "step": 3790 }, { "epoch": 4.130434782608695, "grad_norm": 0.15305502712726593, "learning_rate": 1.4938160786375572e-05, "loss": 0.0147, "step": 3800 }, { "epoch": 4.141304347826087, "grad_norm": 0.10666476935148239, "learning_rate": 1.470316823013707e-05, "loss": 0.0117, "step": 3810 }, { "epoch": 4.1521739130434785, "grad_norm": 0.1367276906967163, "learning_rate": 1.4469719671666043e-05, "loss": 0.0172, "step": 3820 }, { "epoch": 4.163043478260869, "grad_norm": 0.08581943809986115, "learning_rate": 1.4237825322758736e-05, "loss": 0.0152, "step": 3830 }, { "epoch": 4.173913043478261, "grad_norm": 0.15358705818653107, "learning_rate": 1.4007495327225162e-05, "loss": 0.0122, "step": 3840 }, { "epoch": 4.184782608695652, "grad_norm": 0.126980260014534, "learning_rate": 1.3778739760445552e-05, "loss": 0.0124, "step": 3850 }, { "epoch": 4.195652173913044, "grad_norm": 0.1939040869474411, "learning_rate": 1.3551568628929434e-05, "loss": 0.0153, "step": 3860 }, { "epoch": 4.206521739130435, "grad_norm": 0.18035009503364563, "learning_rate": 1.3325991869878013e-05, "loss": 0.013, "step": 3870 }, { "epoch": 4.217391304347826, "grad_norm": 0.07998842000961304, "learning_rate": 1.3102019350749528e-05, "loss": 0.0139, "step": 3880 }, { "epoch": 4.228260869565218, "grad_norm": 0.18314486742019653, "learning_rate": 1.2879660868827508e-05, "loss": 0.0114, "step": 3890 }, { "epoch": 4.239130434782608, "grad_norm": 0.09441019594669342, "learning_rate": 1.2658926150792322e-05, "loss": 0.0132, "step": 3900 }, { "epoch": 4.25, "grad_norm": 0.12457236647605896, "learning_rate": 1.243982485229559e-05, "loss": 0.0122, "step": 3910 }, { "epoch": 4.260869565217392, "grad_norm": 0.1543866991996765, "learning_rate": 1.2222366557537911e-05, "loss": 0.0121, "step": 3920 }, { "epoch": 4.271739130434782, "grad_norm": 0.11423374712467194, "learning_rate": 1.2006560778849578e-05, "loss": 0.013, "step": 3930 }, { "epoch": 4.282608695652174, "grad_norm": 0.10043908655643463, "learning_rate": 1.1792416956274444e-05, "loss": 0.0141, "step": 3940 }, { "epoch": 4.293478260869565, "grad_norm": 0.20762887597084045, "learning_rate": 1.157994445715706e-05, "loss": 0.0164, "step": 3950 }, { "epoch": 4.304347826086957, "grad_norm": 0.1447887122631073, "learning_rate": 1.1369152575732822e-05, "loss": 0.0116, "step": 3960 }, { "epoch": 4.315217391304348, "grad_norm": 0.20277662575244904, "learning_rate": 1.1160050532721528e-05, "loss": 0.0133, "step": 3970 }, { "epoch": 4.326086956521739, "grad_norm": 0.18211638927459717, "learning_rate": 1.095264747492391e-05, "loss": 0.0111, "step": 3980 }, { "epoch": 4.336956521739131, "grad_norm": 0.13810472190380096, "learning_rate": 1.0746952474821614e-05, "loss": 0.0118, "step": 3990 }, { "epoch": 4.3478260869565215, "grad_norm": 0.14950840175151825, "learning_rate": 1.0542974530180327e-05, "loss": 0.0123, "step": 4000 }, { "epoch": 4.358695652173913, "grad_norm": 0.10527154058218002, "learning_rate": 1.0340722563656107e-05, "loss": 0.0114, "step": 4010 }, { "epoch": 4.369565217391305, "grad_norm": 0.1756809651851654, "learning_rate": 1.0140205422405214e-05, "loss": 0.0116, "step": 4020 }, { "epoch": 4.380434782608695, "grad_norm": 0.11897595226764679, "learning_rate": 9.941431877696955e-06, "loss": 0.0122, "step": 4030 }, { "epoch": 4.391304347826087, "grad_norm": 0.13338477909564972, "learning_rate": 9.744410624530148e-06, "loss": 0.0152, "step": 4040 }, { "epoch": 4.4021739130434785, "grad_norm": 0.16387279331684113, "learning_rate": 9.549150281252633e-06, "loss": 0.0098, "step": 4050 }, { "epoch": 4.413043478260869, "grad_norm": 0.18097949028015137, "learning_rate": 9.355659389184396e-06, "loss": 0.0139, "step": 4060 }, { "epoch": 4.423913043478261, "grad_norm": 0.10248986631631851, "learning_rate": 9.163946412243896e-06, "loss": 0.0137, "step": 4070 }, { "epoch": 4.434782608695652, "grad_norm": 0.09879454970359802, "learning_rate": 8.974019736577777e-06, "loss": 0.0108, "step": 4080 }, { "epoch": 4.445652173913043, "grad_norm": 0.14235499501228333, "learning_rate": 8.785887670194138e-06, "loss": 0.0109, "step": 4090 }, { "epoch": 4.456521739130435, "grad_norm": 0.12883390486240387, "learning_rate": 8.599558442598998e-06, "loss": 0.0142, "step": 4100 }, { "epoch": 4.467391304347826, "grad_norm": 0.13557647168636322, "learning_rate": 8.415040204436426e-06, "loss": 0.0131, "step": 4110 }, { "epoch": 4.478260869565218, "grad_norm": 0.2233034372329712, "learning_rate": 8.232341027131885e-06, "loss": 0.014, "step": 4120 }, { "epoch": 4.489130434782608, "grad_norm": 0.11671403050422668, "learning_rate": 8.051468902539272e-06, "loss": 0.0116, "step": 4130 }, { "epoch": 4.5, "grad_norm": 0.16856342554092407, "learning_rate": 7.872431742591268e-06, "loss": 0.0154, "step": 4140 }, { "epoch": 4.510869565217392, "grad_norm": 0.2033834606409073, "learning_rate": 7.695237378953223e-06, "loss": 0.0131, "step": 4150 }, { "epoch": 4.521739130434782, "grad_norm": 0.1596093475818634, "learning_rate": 7.519893562680663e-06, "loss": 0.0087, "step": 4160 }, { "epoch": 4.532608695652174, "grad_norm": 0.0803675428032875, "learning_rate": 7.3464079638801365e-06, "loss": 0.0153, "step": 4170 }, { "epoch": 4.543478260869565, "grad_norm": 0.17898015677928925, "learning_rate": 7.174788171373731e-06, "loss": 0.0145, "step": 4180 }, { "epoch": 4.554347826086957, "grad_norm": 0.11737199872732162, "learning_rate": 7.005041692367154e-06, "loss": 0.0146, "step": 4190 }, { "epoch": 4.565217391304348, "grad_norm": 0.10241485387086868, "learning_rate": 6.837175952121306e-06, "loss": 0.0113, "step": 4200 }, { "epoch": 4.576086956521739, "grad_norm": 0.12728244066238403, "learning_rate": 6.671198293627479e-06, "loss": 0.0094, "step": 4210 }, { "epoch": 4.586956521739131, "grad_norm": 0.10032593458890915, "learning_rate": 6.5071159772861436e-06, "loss": 0.01, "step": 4220 }, { "epoch": 4.5978260869565215, "grad_norm": 0.12760287523269653, "learning_rate": 6.344936180589351e-06, "loss": 0.0093, "step": 4230 }, { "epoch": 4.608695652173913, "grad_norm": 0.16303271055221558, "learning_rate": 6.184665997806832e-06, "loss": 0.0133, "step": 4240 }, { "epoch": 4.619565217391305, "grad_norm": 0.12212922424077988, "learning_rate": 6.026312439675552e-06, "loss": 0.013, "step": 4250 }, { "epoch": 4.630434782608695, "grad_norm": 0.128180593252182, "learning_rate": 5.869882433093155e-06, "loss": 0.0158, "step": 4260 }, { "epoch": 4.641304347826087, "grad_norm": 0.0874294564127922, "learning_rate": 5.715382820814885e-06, "loss": 0.0107, "step": 4270 }, { "epoch": 4.6521739130434785, "grad_norm": 0.14639824628829956, "learning_rate": 5.562820361154314e-06, "loss": 0.0113, "step": 4280 }, { "epoch": 4.663043478260869, "grad_norm": 0.12464270740747452, "learning_rate": 5.412201727687644e-06, "loss": 0.0103, "step": 4290 }, { "epoch": 4.673913043478261, "grad_norm": 0.1470411717891693, "learning_rate": 5.263533508961827e-06, "loss": 0.0117, "step": 4300 }, { "epoch": 4.684782608695652, "grad_norm": 0.10918842256069183, "learning_rate": 5.116822208206396e-06, "loss": 0.0088, "step": 4310 }, { "epoch": 4.695652173913043, "grad_norm": 0.10830997675657272, "learning_rate": 4.972074243048897e-06, "loss": 0.0118, "step": 4320 }, { "epoch": 4.706521739130435, "grad_norm": 0.06698288768529892, "learning_rate": 4.829295945234258e-06, "loss": 0.0105, "step": 4330 }, { "epoch": 4.717391304347826, "grad_norm": 0.15622438490390778, "learning_rate": 4.688493560347773e-06, "loss": 0.0105, "step": 4340 }, { "epoch": 4.728260869565218, "grad_norm": 0.13942964375019073, "learning_rate": 4.549673247541875e-06, "loss": 0.0105, "step": 4350 }, { "epoch": 4.739130434782608, "grad_norm": 0.11007948219776154, "learning_rate": 4.412841079266777e-06, "loss": 0.0093, "step": 4360 }, { "epoch": 4.75, "grad_norm": 0.1278226226568222, "learning_rate": 4.27800304100478e-06, "loss": 0.0105, "step": 4370 }, { "epoch": 4.760869565217392, "grad_norm": 0.1259925812482834, "learning_rate": 4.145165031008508e-06, "loss": 0.0102, "step": 4380 }, { "epoch": 4.771739130434782, "grad_norm": 0.11253256350755692, "learning_rate": 4.01433286004283e-06, "loss": 0.0138, "step": 4390 }, { "epoch": 4.782608695652174, "grad_norm": 0.1246488019824028, "learning_rate": 3.885512251130763e-06, "loss": 0.0144, "step": 4400 }, { "epoch": 4.793478260869565, "grad_norm": 0.1902555227279663, "learning_rate": 3.75870883930306e-06, "loss": 0.0148, "step": 4410 }, { "epoch": 4.804347826086957, "grad_norm": 0.0815320685505867, "learning_rate": 3.6339281713517303e-06, "loss": 0.0139, "step": 4420 }, { "epoch": 4.815217391304348, "grad_norm": 0.20405898988246918, "learning_rate": 3.511175705587433e-06, "loss": 0.0144, "step": 4430 }, { "epoch": 4.826086956521739, "grad_norm": 0.17824992537498474, "learning_rate": 3.390456811600673e-06, "loss": 0.0156, "step": 4440 }, { "epoch": 4.836956521739131, "grad_norm": 0.12627997994422913, "learning_rate": 3.271776770026963e-06, "loss": 0.0119, "step": 4450 }, { "epoch": 4.8478260869565215, "grad_norm": 0.16256245970726013, "learning_rate": 3.155140772315773e-06, "loss": 0.0116, "step": 4460 }, { "epoch": 4.858695652173913, "grad_norm": 0.14503680169582367, "learning_rate": 3.040553920503503e-06, "loss": 0.0103, "step": 4470 }, { "epoch": 4.869565217391305, "grad_norm": 0.16697053611278534, "learning_rate": 2.928021226990263e-06, "loss": 0.0115, "step": 4480 }, { "epoch": 4.880434782608695, "grad_norm": 0.12260522693395615, "learning_rate": 2.817547614320615e-06, "loss": 0.0127, "step": 4490 }, { "epoch": 4.891304347826087, "grad_norm": 0.11083414405584335, "learning_rate": 2.7091379149682685e-06, "loss": 0.0122, "step": 4500 }, { "epoch": 4.9021739130434785, "grad_norm": 0.08423303812742233, "learning_rate": 2.602796871124663e-06, "loss": 0.0139, "step": 4510 }, { "epoch": 4.913043478260869, "grad_norm": 0.11884451657533646, "learning_rate": 2.4985291344915674e-06, "loss": 0.011, "step": 4520 }, { "epoch": 4.923913043478261, "grad_norm": 0.12083287537097931, "learning_rate": 2.3963392660775575e-06, "loss": 0.0118, "step": 4530 }, { "epoch": 4.934782608695652, "grad_norm": 0.10024096816778183, "learning_rate": 2.296231735998511e-06, "loss": 0.0105, "step": 4540 }, { "epoch": 4.945652173913043, "grad_norm": 0.09267722815275192, "learning_rate": 2.1982109232821178e-06, "loss": 0.0109, "step": 4550 }, { "epoch": 4.956521739130435, "grad_norm": 0.10499723255634308, "learning_rate": 2.102281115676258e-06, "loss": 0.0091, "step": 4560 }, { "epoch": 4.967391304347826, "grad_norm": 0.08696238696575165, "learning_rate": 2.008446509461498e-06, "loss": 0.0116, "step": 4570 }, { "epoch": 4.978260869565218, "grad_norm": 0.17206984758377075, "learning_rate": 1.91671120926748e-06, "loss": 0.0113, "step": 4580 }, { "epoch": 4.989130434782608, "grad_norm": 0.12113843113183975, "learning_rate": 1.8270792278934302e-06, "loss": 0.0104, "step": 4590 }, { "epoch": 5.0, "grad_norm": 0.22009101510047913, "learning_rate": 1.7395544861325718e-06, "loss": 0.01, "step": 4600 }, { "epoch": 5.010869565217392, "grad_norm": 0.16371949017047882, "learning_rate": 1.6541408126006463e-06, "loss": 0.0135, "step": 4610 }, { "epoch": 5.021739130434782, "grad_norm": 0.16570837795734406, "learning_rate": 1.5708419435684462e-06, "loss": 0.013, "step": 4620 }, { "epoch": 5.032608695652174, "grad_norm": 0.1099071279168129, "learning_rate": 1.4896615227983468e-06, "loss": 0.0107, "step": 4630 }, { "epoch": 5.043478260869565, "grad_norm": 0.19537553191184998, "learning_rate": 1.4106031013849496e-06, "loss": 0.0122, "step": 4640 }, { "epoch": 5.054347826086956, "grad_norm": 0.1724758744239807, "learning_rate": 1.333670137599713e-06, "loss": 0.0117, "step": 4650 }, { "epoch": 5.065217391304348, "grad_norm": 0.12308087944984436, "learning_rate": 1.2588659967397e-06, "loss": 0.0192, "step": 4660 }, { "epoch": 5.076086956521739, "grad_norm": 0.11377613991498947, "learning_rate": 1.1861939509803687e-06, "loss": 0.0121, "step": 4670 }, { "epoch": 5.086956521739131, "grad_norm": 0.10649964958429337, "learning_rate": 1.1156571792324211e-06, "loss": 0.0088, "step": 4680 }, { "epoch": 5.0978260869565215, "grad_norm": 0.11878595501184464, "learning_rate": 1.0472587670027678e-06, "loss": 0.0127, "step": 4690 }, { "epoch": 5.108695652173913, "grad_norm": 0.07565627247095108, "learning_rate": 9.810017062595322e-07, "loss": 0.0164, "step": 4700 }, { "epoch": 5.119565217391305, "grad_norm": 0.1543477326631546, "learning_rate": 9.168888953011989e-07, "loss": 0.0108, "step": 4710 }, { "epoch": 5.130434782608695, "grad_norm": 0.170787513256073, "learning_rate": 8.549231386298151e-07, "loss": 0.0132, "step": 4720 }, { "epoch": 5.141304347826087, "grad_norm": 0.09899775683879852, "learning_rate": 7.951071468283167e-07, "loss": 0.0112, "step": 4730 }, { "epoch": 5.1521739130434785, "grad_norm": 0.11870214343070984, "learning_rate": 7.374435364419674e-07, "loss": 0.0095, "step": 4740 }, { "epoch": 5.163043478260869, "grad_norm": 0.11212939023971558, "learning_rate": 6.819348298638839e-07, "loss": 0.0089, "step": 4750 }, { "epoch": 5.173913043478261, "grad_norm": 0.20279225707054138, "learning_rate": 6.285834552247128e-07, "loss": 0.0129, "step": 4760 }, { "epoch": 5.184782608695652, "grad_norm": 0.09186626970767975, "learning_rate": 5.773917462864264e-07, "loss": 0.011, "step": 4770 }, { "epoch": 5.195652173913044, "grad_norm": 0.11231357604265213, "learning_rate": 5.283619423401998e-07, "loss": 0.0125, "step": 4780 }, { "epoch": 5.206521739130435, "grad_norm": 0.16140662133693695, "learning_rate": 4.814961881085045e-07, "loss": 0.0097, "step": 4790 }, { "epoch": 5.217391304347826, "grad_norm": 0.10995183140039444, "learning_rate": 4.367965336512403e-07, "loss": 0.013, "step": 4800 }, { "epoch": 5.228260869565218, "grad_norm": 0.13332118093967438, "learning_rate": 3.9426493427611177e-07, "loss": 0.0097, "step": 4810 }, { "epoch": 5.239130434782608, "grad_norm": 0.1429547816514969, "learning_rate": 3.5390325045304706e-07, "loss": 0.0082, "step": 4820 }, { "epoch": 5.25, "grad_norm": 0.17897242307662964, "learning_rate": 3.157132477328628e-07, "loss": 0.012, "step": 4830 }, { "epoch": 5.260869565217392, "grad_norm": 0.08187426626682281, "learning_rate": 2.796965966699927e-07, "loss": 0.0204, "step": 4840 }, { "epoch": 5.271739130434782, "grad_norm": 0.10710621625185013, "learning_rate": 2.458548727494292e-07, "loss": 0.0119, "step": 4850 }, { "epoch": 5.282608695652174, "grad_norm": 0.08736681938171387, "learning_rate": 2.1418955631781202e-07, "loss": 0.0116, "step": 4860 }, { "epoch": 5.293478260869565, "grad_norm": 0.09124402701854706, "learning_rate": 1.847020325186577e-07, "loss": 0.0111, "step": 4870 }, { "epoch": 5.304347826086957, "grad_norm": 0.12248014658689499, "learning_rate": 1.5739359123178587e-07, "loss": 0.0137, "step": 4880 }, { "epoch": 5.315217391304348, "grad_norm": 0.1349477767944336, "learning_rate": 1.3226542701689215e-07, "loss": 0.0103, "step": 4890 }, { "epoch": 5.326086956521739, "grad_norm": 0.19862999022006989, "learning_rate": 1.0931863906127327e-07, "loss": 0.0121, "step": 4900 }, { "epoch": 5.336956521739131, "grad_norm": 0.11860275268554688, "learning_rate": 8.855423113177664e-08, "loss": 0.0104, "step": 4910 }, { "epoch": 5.3478260869565215, "grad_norm": 0.1107594221830368, "learning_rate": 6.997311153086883e-08, "loss": 0.0096, "step": 4920 }, { "epoch": 5.358695652173913, "grad_norm": 0.08218859881162643, "learning_rate": 5.3576093056922906e-08, "loss": 0.0115, "step": 4930 }, { "epoch": 5.369565217391305, "grad_norm": 0.16671264171600342, "learning_rate": 3.936389296864129e-08, "loss": 0.0101, "step": 4940 }, { "epoch": 5.380434782608695, "grad_norm": 0.1079106330871582, "learning_rate": 2.7337132953697554e-08, "loss": 0.012, "step": 4950 }, { "epoch": 5.391304347826087, "grad_norm": 0.0908968448638916, "learning_rate": 1.749633910153592e-08, "loss": 0.0086, "step": 4960 }, { "epoch": 5.4021739130434785, "grad_norm": 0.14503175020217896, "learning_rate": 9.841941880361916e-09, "loss": 0.0148, "step": 4970 }, { "epoch": 5.413043478260869, "grad_norm": 0.12894049286842346, "learning_rate": 4.3742761183018784e-09, "loss": 0.0149, "step": 4980 }, { "epoch": 5.423913043478261, "grad_norm": 0.11368037760257721, "learning_rate": 1.0935809887702154e-09, "loss": 0.011, "step": 4990 }, { "epoch": 5.434782608695652, "grad_norm": 0.10479787737131119, "learning_rate": 0.0, "loss": 0.0124, "step": 5000 } ], "logging_steps": 10, "max_steps": 5000, "num_input_tokens_seen": 0, "num_train_epochs": 6, "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": 4.9488596845979616e+17, "train_batch_size": 32, "trial_name": null, "trial_params": null }