{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.961636828644501, "eval_steps": 500, "global_step": 485, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.010230179028132993, "grad_norm": 2.9681825955274577, "learning_rate": 8.163265306122449e-07, "loss": 1.4918, "step": 1 }, { "epoch": 0.020460358056265986, "grad_norm": 2.979280560750724, "learning_rate": 1.6326530612244897e-06, "loss": 1.4922, "step": 2 }, { "epoch": 0.030690537084398978, "grad_norm": 2.9696929689528426, "learning_rate": 2.4489795918367347e-06, "loss": 1.5053, "step": 3 }, { "epoch": 0.04092071611253197, "grad_norm": 2.8854047896767385, "learning_rate": 3.2653061224489794e-06, "loss": 1.4888, "step": 4 }, { "epoch": 0.05115089514066496, "grad_norm": 2.678302997542699, "learning_rate": 4.081632653061225e-06, "loss": 1.4875, "step": 5 }, { "epoch": 0.061381074168797956, "grad_norm": 2.009190448670929, "learning_rate": 4.897959183673469e-06, "loss": 1.4641, "step": 6 }, { "epoch": 0.07161125319693094, "grad_norm": 1.88642976129468, "learning_rate": 5.7142857142857145e-06, "loss": 1.4581, "step": 7 }, { "epoch": 0.08184143222506395, "grad_norm": 1.7967293041212427, "learning_rate": 6.530612244897959e-06, "loss": 1.449, "step": 8 }, { "epoch": 0.09207161125319693, "grad_norm": 1.7785294097373827, "learning_rate": 7.346938775510205e-06, "loss": 1.4581, "step": 9 }, { "epoch": 0.10230179028132992, "grad_norm": 1.6260935195266601, "learning_rate": 8.16326530612245e-06, "loss": 1.4392, "step": 10 }, { "epoch": 0.11253196930946291, "grad_norm": 2.146271221045358, "learning_rate": 8.979591836734695e-06, "loss": 1.4024, "step": 11 }, { "epoch": 0.12276214833759591, "grad_norm": 2.0958251479872074, "learning_rate": 9.795918367346939e-06, "loss": 1.4099, "step": 12 }, { "epoch": 0.1329923273657289, "grad_norm": 1.724599487721133, "learning_rate": 1.0612244897959186e-05, "loss": 1.3819, "step": 13 }, { "epoch": 0.1432225063938619, "grad_norm": 1.239236642237635, "learning_rate": 1.1428571428571429e-05, "loss": 1.3781, "step": 14 }, { "epoch": 0.1534526854219949, "grad_norm": 1.2207433921526918, "learning_rate": 1.2244897959183674e-05, "loss": 1.3687, "step": 15 }, { "epoch": 0.1636828644501279, "grad_norm": 0.9437502848687276, "learning_rate": 1.3061224489795918e-05, "loss": 1.3696, "step": 16 }, { "epoch": 0.17391304347826086, "grad_norm": 0.9523349841268315, "learning_rate": 1.3877551020408165e-05, "loss": 1.3309, "step": 17 }, { "epoch": 0.18414322250639387, "grad_norm": 0.7176841886284677, "learning_rate": 1.469387755102041e-05, "loss": 1.3108, "step": 18 }, { "epoch": 0.19437340153452684, "grad_norm": 0.748654666968633, "learning_rate": 1.5510204081632655e-05, "loss": 1.3173, "step": 19 }, { "epoch": 0.20460358056265984, "grad_norm": 0.8282956756972626, "learning_rate": 1.63265306122449e-05, "loss": 1.2995, "step": 20 }, { "epoch": 0.21483375959079284, "grad_norm": 0.6386096725540146, "learning_rate": 1.7142857142857142e-05, "loss": 1.29, "step": 21 }, { "epoch": 0.22506393861892582, "grad_norm": 0.5668726658163956, "learning_rate": 1.795918367346939e-05, "loss": 1.3132, "step": 22 }, { "epoch": 0.23529411764705882, "grad_norm": 0.5869296468757045, "learning_rate": 1.8775510204081636e-05, "loss": 1.299, "step": 23 }, { "epoch": 0.24552429667519182, "grad_norm": 0.5423506249567581, "learning_rate": 1.9591836734693877e-05, "loss": 1.2893, "step": 24 }, { "epoch": 0.2557544757033248, "grad_norm": 0.5239888331885344, "learning_rate": 2.0408163265306126e-05, "loss": 1.2678, "step": 25 }, { "epoch": 0.2659846547314578, "grad_norm": 0.5019007006756177, "learning_rate": 2.122448979591837e-05, "loss": 1.2619, "step": 26 }, { "epoch": 0.27621483375959077, "grad_norm": 0.41432744914634223, "learning_rate": 2.2040816326530613e-05, "loss": 1.2486, "step": 27 }, { "epoch": 0.2864450127877238, "grad_norm": 0.4130335504517712, "learning_rate": 2.2857142857142858e-05, "loss": 1.2659, "step": 28 }, { "epoch": 0.2966751918158568, "grad_norm": 0.41612204477854087, "learning_rate": 2.3673469387755103e-05, "loss": 1.2436, "step": 29 }, { "epoch": 0.3069053708439898, "grad_norm": 0.43051651693759135, "learning_rate": 2.448979591836735e-05, "loss": 1.2603, "step": 30 }, { "epoch": 0.3171355498721228, "grad_norm": 0.34370693253506146, "learning_rate": 2.5306122448979597e-05, "loss": 1.2432, "step": 31 }, { "epoch": 0.3273657289002558, "grad_norm": 0.34133030422494026, "learning_rate": 2.6122448979591835e-05, "loss": 1.2337, "step": 32 }, { "epoch": 0.3375959079283887, "grad_norm": 0.3319005067539689, "learning_rate": 2.6938775510204084e-05, "loss": 1.2463, "step": 33 }, { "epoch": 0.34782608695652173, "grad_norm": 0.28074046613650866, "learning_rate": 2.775510204081633e-05, "loss": 1.2461, "step": 34 }, { "epoch": 0.35805626598465473, "grad_norm": 0.28965604103544107, "learning_rate": 2.8571428571428574e-05, "loss": 1.2385, "step": 35 }, { "epoch": 0.36828644501278773, "grad_norm": 0.30050391691065137, "learning_rate": 2.938775510204082e-05, "loss": 1.2226, "step": 36 }, { "epoch": 0.37851662404092073, "grad_norm": 0.28906957290955254, "learning_rate": 3.020408163265306e-05, "loss": 1.232, "step": 37 }, { "epoch": 0.3887468030690537, "grad_norm": 0.29183163383217575, "learning_rate": 3.102040816326531e-05, "loss": 1.2136, "step": 38 }, { "epoch": 0.3989769820971867, "grad_norm": 0.2599626281733114, "learning_rate": 3.183673469387755e-05, "loss": 1.221, "step": 39 }, { "epoch": 0.4092071611253197, "grad_norm": 0.327304024463649, "learning_rate": 3.26530612244898e-05, "loss": 1.2194, "step": 40 }, { "epoch": 0.4194373401534527, "grad_norm": 0.2911485255388066, "learning_rate": 3.346938775510204e-05, "loss": 1.2046, "step": 41 }, { "epoch": 0.4296675191815857, "grad_norm": 0.29268540087741196, "learning_rate": 3.4285714285714284e-05, "loss": 1.2045, "step": 42 }, { "epoch": 0.4398976982097187, "grad_norm": 0.31270910748231523, "learning_rate": 3.510204081632653e-05, "loss": 1.2036, "step": 43 }, { "epoch": 0.45012787723785164, "grad_norm": 0.29599656789271006, "learning_rate": 3.591836734693878e-05, "loss": 1.2225, "step": 44 }, { "epoch": 0.46035805626598464, "grad_norm": 0.2887067574371518, "learning_rate": 3.673469387755102e-05, "loss": 1.1973, "step": 45 }, { "epoch": 0.47058823529411764, "grad_norm": 0.2844897888029014, "learning_rate": 3.755102040816327e-05, "loss": 1.2085, "step": 46 }, { "epoch": 0.48081841432225064, "grad_norm": 0.2611634186171313, "learning_rate": 3.836734693877551e-05, "loss": 1.2054, "step": 47 }, { "epoch": 0.49104859335038364, "grad_norm": 0.25084361258479243, "learning_rate": 3.9183673469387755e-05, "loss": 1.1818, "step": 48 }, { "epoch": 0.5012787723785166, "grad_norm": 0.2862616155779687, "learning_rate": 4e-05, "loss": 1.1852, "step": 49 }, { "epoch": 0.5115089514066496, "grad_norm": 0.39535570876845794, "learning_rate": 3.9999480811710956e-05, "loss": 1.1889, "step": 50 }, { "epoch": 0.5217391304347826, "grad_norm": 0.5916412741996568, "learning_rate": 3.999792327379947e-05, "loss": 1.1752, "step": 51 }, { "epoch": 0.5319693094629157, "grad_norm": 1.1115600291818732, "learning_rate": 3.9995327467131074e-05, "loss": 1.1904, "step": 52 }, { "epoch": 0.5421994884910486, "grad_norm": 1.0604217218035932, "learning_rate": 3.999169352647703e-05, "loss": 1.1788, "step": 53 }, { "epoch": 0.5524296675191815, "grad_norm": 0.6884296946514226, "learning_rate": 3.998702164050726e-05, "loss": 1.1726, "step": 54 }, { "epoch": 0.5626598465473146, "grad_norm": 1.5122828259949803, "learning_rate": 3.998131205178063e-05, "loss": 1.1736, "step": 55 }, { "epoch": 0.5728900255754475, "grad_norm": 0.47007930659675656, "learning_rate": 3.9974565056732294e-05, "loss": 1.1643, "step": 56 }, { "epoch": 0.5831202046035806, "grad_norm": 0.9345647863258172, "learning_rate": 3.9966781005658336e-05, "loss": 1.1726, "step": 57 }, { "epoch": 0.5933503836317136, "grad_norm": 0.8348753081451585, "learning_rate": 3.995796030269756e-05, "loss": 1.1743, "step": 58 }, { "epoch": 0.6035805626598465, "grad_norm": 0.9024671765460063, "learning_rate": 3.994810340581056e-05, "loss": 1.1561, "step": 59 }, { "epoch": 0.6138107416879796, "grad_norm": 0.6023978152299045, "learning_rate": 3.993721082675585e-05, "loss": 1.1589, "step": 60 }, { "epoch": 0.6240409207161125, "grad_norm": 0.5081862666771035, "learning_rate": 3.992528313106339e-05, "loss": 1.1751, "step": 61 }, { "epoch": 0.6342710997442456, "grad_norm": 0.4649367060091047, "learning_rate": 3.991232093800517e-05, "loss": 1.1787, "step": 62 }, { "epoch": 0.6445012787723785, "grad_norm": 0.6341340622670154, "learning_rate": 3.989832492056308e-05, "loss": 1.1766, "step": 63 }, { "epoch": 0.6547314578005116, "grad_norm": 0.5455776295116087, "learning_rate": 3.988329580539395e-05, "loss": 1.1709, "step": 64 }, { "epoch": 0.6649616368286445, "grad_norm": 0.4484425559213346, "learning_rate": 3.9867234372791834e-05, "loss": 1.17, "step": 65 }, { "epoch": 0.6751918158567775, "grad_norm": 0.4272907650523753, "learning_rate": 3.9850141456647515e-05, "loss": 1.1589, "step": 66 }, { "epoch": 0.6854219948849105, "grad_norm": 0.5465581943156248, "learning_rate": 3.983201794440517e-05, "loss": 1.1612, "step": 67 }, { "epoch": 0.6956521739130435, "grad_norm": 0.5735349455725025, "learning_rate": 3.981286477701635e-05, "loss": 1.1587, "step": 68 }, { "epoch": 0.7058823529411765, "grad_norm": 0.35440151647593743, "learning_rate": 3.979268294889105e-05, "loss": 1.1602, "step": 69 }, { "epoch": 0.7161125319693095, "grad_norm": 0.42938469828017, "learning_rate": 3.977147350784617e-05, "loss": 1.167, "step": 70 }, { "epoch": 0.7263427109974424, "grad_norm": 0.44982383314843716, "learning_rate": 3.974923755505104e-05, "loss": 1.1431, "step": 71 }, { "epoch": 0.7365728900255755, "grad_norm": 0.38572351027704815, "learning_rate": 3.972597624497029e-05, "loss": 1.1521, "step": 72 }, { "epoch": 0.7468030690537084, "grad_norm": 0.34847411905908265, "learning_rate": 3.97016907853039e-05, "loss": 1.152, "step": 73 }, { "epoch": 0.7570332480818415, "grad_norm": 0.3429209017839145, "learning_rate": 3.96763824369245e-05, "loss": 1.1413, "step": 74 }, { "epoch": 0.7672634271099744, "grad_norm": 0.38510484098230807, "learning_rate": 3.96500525138119e-05, "loss": 1.1602, "step": 75 }, { "epoch": 0.7774936061381074, "grad_norm": 0.42419320032589797, "learning_rate": 3.962270238298486e-05, "loss": 1.1493, "step": 76 }, { "epoch": 0.7877237851662404, "grad_norm": 0.3647785669418163, "learning_rate": 3.9594333464430155e-05, "loss": 1.1371, "step": 77 }, { "epoch": 0.7979539641943734, "grad_norm": 0.35893196150825196, "learning_rate": 3.9564947231028805e-05, "loss": 1.1555, "step": 78 }, { "epoch": 0.8081841432225064, "grad_norm": 0.339848648449806, "learning_rate": 3.9534545208479645e-05, "loss": 1.1385, "step": 79 }, { "epoch": 0.8184143222506394, "grad_norm": 0.3084301810191317, "learning_rate": 3.9503128975220075e-05, "loss": 1.143, "step": 80 }, { "epoch": 0.8286445012787724, "grad_norm": 0.24566098501561676, "learning_rate": 3.947070016234414e-05, "loss": 1.1506, "step": 81 }, { "epoch": 0.8388746803069054, "grad_norm": 0.22444717684350196, "learning_rate": 3.943726045351782e-05, "loss": 1.1492, "step": 82 }, { "epoch": 0.8491048593350383, "grad_norm": 0.2559344393913777, "learning_rate": 3.940281158489163e-05, "loss": 1.1522, "step": 83 }, { "epoch": 0.8593350383631714, "grad_norm": 0.22647402747782316, "learning_rate": 3.936735534501051e-05, "loss": 1.1337, "step": 84 }, { "epoch": 0.8695652173913043, "grad_norm": 0.2600014177792275, "learning_rate": 3.933089357472089e-05, "loss": 1.1499, "step": 85 }, { "epoch": 0.8797953964194374, "grad_norm": 0.3098466535491745, "learning_rate": 3.929342816707519e-05, "loss": 1.1401, "step": 86 }, { "epoch": 0.8900255754475703, "grad_norm": 0.35360326492885225, "learning_rate": 3.92549610672335e-05, "loss": 1.1406, "step": 87 }, { "epoch": 0.9002557544757033, "grad_norm": 0.3862401334500793, "learning_rate": 3.92154942723626e-05, "loss": 1.1412, "step": 88 }, { "epoch": 0.9104859335038363, "grad_norm": 0.39352928547649063, "learning_rate": 3.917502983153225e-05, "loss": 1.1338, "step": 89 }, { "epoch": 0.9207161125319693, "grad_norm": 0.4399181035792021, "learning_rate": 3.913356984560883e-05, "loss": 1.1418, "step": 90 }, { "epoch": 0.9309462915601023, "grad_norm": 0.5085746700220705, "learning_rate": 3.909111646714627e-05, "loss": 1.1333, "step": 91 }, { "epoch": 0.9411764705882353, "grad_norm": 0.5735818807274115, "learning_rate": 3.9047671900274256e-05, "loss": 1.1552, "step": 92 }, { "epoch": 0.9514066496163683, "grad_norm": 0.5681370826641924, "learning_rate": 3.900323840058382e-05, "loss": 1.1455, "step": 93 }, { "epoch": 0.9616368286445013, "grad_norm": 0.5444974187249378, "learning_rate": 3.895781827501022e-05, "loss": 1.1453, "step": 94 }, { "epoch": 0.9718670076726342, "grad_norm": 0.5190262675407392, "learning_rate": 3.8911413881713204e-05, "loss": 1.1353, "step": 95 }, { "epoch": 0.9820971867007673, "grad_norm": 0.653852135882697, "learning_rate": 3.8864027629954517e-05, "loss": 1.1325, "step": 96 }, { "epoch": 0.9923273657289002, "grad_norm": 0.8580787081484961, "learning_rate": 3.881566197997286e-05, "loss": 1.1578, "step": 97 }, { "epoch": 1.0025575447570332, "grad_norm": 1.0310995219860968, "learning_rate": 3.8766319442856134e-05, "loss": 1.4304, "step": 98 }, { "epoch": 1.0127877237851663, "grad_norm": 1.0480726196507673, "learning_rate": 3.8716002580411084e-05, "loss": 1.1262, "step": 99 }, { "epoch": 1.0230179028132993, "grad_norm": 0.6574690748508139, "learning_rate": 3.866471400503029e-05, "loss": 1.1496, "step": 100 }, { "epoch": 1.0332480818414322, "grad_norm": 0.2813394335679964, "learning_rate": 3.861245637955651e-05, "loss": 1.132, "step": 101 }, { "epoch": 1.0434782608695652, "grad_norm": 0.7766927528299393, "learning_rate": 3.855923241714447e-05, "loss": 1.1349, "step": 102 }, { "epoch": 1.0537084398976981, "grad_norm": 0.8169866806335725, "learning_rate": 3.850504488111996e-05, "loss": 1.1087, "step": 103 }, { "epoch": 1.0639386189258313, "grad_norm": 0.2919889881481981, "learning_rate": 3.844989658483639e-05, "loss": 1.1425, "step": 104 }, { "epoch": 1.0741687979539642, "grad_norm": 0.5035670797221828, "learning_rate": 3.8393790391528726e-05, "loss": 1.1255, "step": 105 }, { "epoch": 1.0843989769820972, "grad_norm": 0.6224946592118362, "learning_rate": 3.833672921416482e-05, "loss": 1.1225, "step": 106 }, { "epoch": 1.0946291560102301, "grad_norm": 0.2950181376931291, "learning_rate": 3.827871601529417e-05, "loss": 1.1117, "step": 107 }, { "epoch": 1.104859335038363, "grad_norm": 0.5051007741582696, "learning_rate": 3.821975380689413e-05, "loss": 1.1461, "step": 108 }, { "epoch": 1.1150895140664963, "grad_norm": 0.5221568786817201, "learning_rate": 3.81598456502135e-05, "loss": 1.1234, "step": 109 }, { "epoch": 1.1253196930946292, "grad_norm": 0.30392380764460536, "learning_rate": 3.809899465561363e-05, "loss": 1.1115, "step": 110 }, { "epoch": 1.1355498721227621, "grad_norm": 0.4761276317198434, "learning_rate": 3.803720398240688e-05, "loss": 1.1201, "step": 111 }, { "epoch": 1.145780051150895, "grad_norm": 0.45611189056644913, "learning_rate": 3.7974476838692656e-05, "loss": 1.1069, "step": 112 }, { "epoch": 1.156010230179028, "grad_norm": 0.2525244059682488, "learning_rate": 3.791081648119079e-05, "loss": 1.1279, "step": 113 }, { "epoch": 1.1662404092071612, "grad_norm": 0.39044628608560245, "learning_rate": 3.7846226215072495e-05, "loss": 1.1164, "step": 114 }, { "epoch": 1.1764705882352942, "grad_norm": 0.4362516631576207, "learning_rate": 3.778070939378875e-05, "loss": 1.1134, "step": 115 }, { "epoch": 1.186700767263427, "grad_norm": 0.33136604726952473, "learning_rate": 3.771426941889619e-05, "loss": 1.1281, "step": 116 }, { "epoch": 1.19693094629156, "grad_norm": 0.36696496343076784, "learning_rate": 3.7646909739880486e-05, "loss": 1.1272, "step": 117 }, { "epoch": 1.207161125319693, "grad_norm": 0.3827254193877039, "learning_rate": 3.757863385397731e-05, "loss": 1.1087, "step": 118 }, { "epoch": 1.2173913043478262, "grad_norm": 0.3190444403313643, "learning_rate": 3.750944530599069e-05, "loss": 1.1126, "step": 119 }, { "epoch": 1.227621483375959, "grad_norm": 0.3233262046048155, "learning_rate": 3.743934768810902e-05, "loss": 1.1331, "step": 120 }, { "epoch": 1.237851662404092, "grad_norm": 0.33936286036272806, "learning_rate": 3.7368344639718516e-05, "loss": 1.1232, "step": 121 }, { "epoch": 1.248081841432225, "grad_norm": 0.2330398049477242, "learning_rate": 3.729643984721431e-05, "loss": 1.1175, "step": 122 }, { "epoch": 1.258312020460358, "grad_norm": 0.1924936271545763, "learning_rate": 3.722363704380902e-05, "loss": 1.1285, "step": 123 }, { "epoch": 1.2685421994884911, "grad_norm": 0.2861361865892163, "learning_rate": 3.714994000933893e-05, "loss": 1.1196, "step": 124 }, { "epoch": 1.278772378516624, "grad_norm": 0.24566821538926786, "learning_rate": 3.707535257006777e-05, "loss": 1.1027, "step": 125 }, { "epoch": 1.289002557544757, "grad_norm": 0.22928637475781566, "learning_rate": 3.6999878598488054e-05, "loss": 1.1174, "step": 126 }, { "epoch": 1.29923273657289, "grad_norm": 0.3310648086514136, "learning_rate": 3.6923522013119964e-05, "loss": 1.1147, "step": 127 }, { "epoch": 1.309462915601023, "grad_norm": 0.31367935383189405, "learning_rate": 3.684628677830802e-05, "loss": 1.1198, "step": 128 }, { "epoch": 1.319693094629156, "grad_norm": 0.22961205416611935, "learning_rate": 3.676817690401516e-05, "loss": 1.0972, "step": 129 }, { "epoch": 1.329923273657289, "grad_norm": 0.3139943962517946, "learning_rate": 3.668919644561457e-05, "loss": 1.1201, "step": 130 }, { "epoch": 1.340153452685422, "grad_norm": 0.26295743838749697, "learning_rate": 3.6609349503679166e-05, "loss": 1.128, "step": 131 }, { "epoch": 1.350383631713555, "grad_norm": 0.2591587617561099, "learning_rate": 3.652864022376866e-05, "loss": 1.1281, "step": 132 }, { "epoch": 1.3606138107416879, "grad_norm": 0.2753137519512843, "learning_rate": 3.6447072796214354e-05, "loss": 1.0979, "step": 133 }, { "epoch": 1.370843989769821, "grad_norm": 0.27455797603906246, "learning_rate": 3.636465145590156e-05, "loss": 1.1383, "step": 134 }, { "epoch": 1.381074168797954, "grad_norm": 0.2527457090917438, "learning_rate": 3.6281380482049743e-05, "loss": 1.1139, "step": 135 }, { "epoch": 1.391304347826087, "grad_norm": 0.3319234526053082, "learning_rate": 3.619726419799035e-05, "loss": 1.119, "step": 136 }, { "epoch": 1.40153452685422, "grad_norm": 0.3281079811844079, "learning_rate": 3.6112306970942334e-05, "loss": 1.107, "step": 137 }, { "epoch": 1.4117647058823528, "grad_norm": 0.2471643062647397, "learning_rate": 3.602651321178544e-05, "loss": 1.1135, "step": 138 }, { "epoch": 1.421994884910486, "grad_norm": 0.20931674384579108, "learning_rate": 3.593988737483115e-05, "loss": 1.1133, "step": 139 }, { "epoch": 1.432225063938619, "grad_norm": 0.2552571100096864, "learning_rate": 3.58524339575915e-05, "loss": 1.1054, "step": 140 }, { "epoch": 1.4424552429667519, "grad_norm": 0.2651644163666779, "learning_rate": 3.576415750054548e-05, "loss": 1.1195, "step": 141 }, { "epoch": 1.452685421994885, "grad_norm": 0.24017688656974193, "learning_rate": 3.567506258690338e-05, "loss": 1.1085, "step": 142 }, { "epoch": 1.4629156010230178, "grad_norm": 0.23564531173628686, "learning_rate": 3.558515384236875e-05, "loss": 1.1106, "step": 143 }, { "epoch": 1.473145780051151, "grad_norm": 0.22280005044127463, "learning_rate": 3.549443593489832e-05, "loss": 1.1206, "step": 144 }, { "epoch": 1.4833759590792839, "grad_norm": 0.2552643337416725, "learning_rate": 3.540291357445961e-05, "loss": 1.1122, "step": 145 }, { "epoch": 1.4936061381074168, "grad_norm": 0.2894540149054441, "learning_rate": 3.53105915127864e-05, "loss": 1.1222, "step": 146 }, { "epoch": 1.50383631713555, "grad_norm": 0.28713663691696745, "learning_rate": 3.521747454313201e-05, "loss": 1.108, "step": 147 }, { "epoch": 1.5140664961636827, "grad_norm": 0.2908212131310711, "learning_rate": 3.512356750002046e-05, "loss": 1.0991, "step": 148 }, { "epoch": 1.5242966751918159, "grad_norm": 0.2925035403624845, "learning_rate": 3.502887525899544e-05, "loss": 1.0932, "step": 149 }, { "epoch": 1.5345268542199488, "grad_norm": 0.26246100152488794, "learning_rate": 3.4933402736367224e-05, "loss": 1.1308, "step": 150 }, { "epoch": 1.5447570332480818, "grad_norm": 0.2849216122829947, "learning_rate": 3.483715488895738e-05, "loss": 1.0991, "step": 151 }, { "epoch": 1.554987212276215, "grad_norm": 0.3168255567811887, "learning_rate": 3.4740136713841416e-05, "loss": 1.1004, "step": 152 }, { "epoch": 1.5652173913043477, "grad_norm": 0.3781368448201129, "learning_rate": 3.464235324808938e-05, "loss": 1.103, "step": 153 }, { "epoch": 1.5754475703324808, "grad_norm": 0.44427850902760707, "learning_rate": 3.4543809568504286e-05, "loss": 1.1156, "step": 154 }, { "epoch": 1.5856777493606138, "grad_norm": 0.5178677272089415, "learning_rate": 3.4444510791358596e-05, "loss": 1.0895, "step": 155 }, { "epoch": 1.5959079283887467, "grad_norm": 0.5587035996281683, "learning_rate": 3.4344462072128514e-05, "loss": 1.1305, "step": 156 }, { "epoch": 1.60613810741688, "grad_norm": 0.5156063184980773, "learning_rate": 3.424366860522638e-05, "loss": 1.1157, "step": 157 }, { "epoch": 1.6163682864450126, "grad_norm": 0.3838651653522541, "learning_rate": 3.4142135623730954e-05, "loss": 1.0952, "step": 158 }, { "epoch": 1.6265984654731458, "grad_norm": 0.27179604609847285, "learning_rate": 3.4039868399115736e-05, "loss": 1.1086, "step": 159 }, { "epoch": 1.6368286445012787, "grad_norm": 0.3879595327319385, "learning_rate": 3.393687224097526e-05, "loss": 1.1117, "step": 160 }, { "epoch": 1.6470588235294117, "grad_norm": 0.4326630668165547, "learning_rate": 3.383315249674944e-05, "loss": 1.1127, "step": 161 }, { "epoch": 1.6572890025575449, "grad_norm": 0.31231629284695467, "learning_rate": 3.372871455144593e-05, "loss": 1.0903, "step": 162 }, { "epoch": 1.6675191815856778, "grad_norm": 0.20497771494775785, "learning_rate": 3.3623563827360546e-05, "loss": 1.1132, "step": 163 }, { "epoch": 1.6777493606138107, "grad_norm": 0.29045667744476295, "learning_rate": 3.351770578379573e-05, "loss": 1.1092, "step": 164 }, { "epoch": 1.6879795396419437, "grad_norm": 0.29117745990148775, "learning_rate": 3.341114591677715e-05, "loss": 1.1161, "step": 165 }, { "epoch": 1.6982097186700766, "grad_norm": 0.24664682064365182, "learning_rate": 3.33038897587683e-05, "loss": 1.1125, "step": 166 }, { "epoch": 1.7084398976982098, "grad_norm": 0.24877676736337231, "learning_rate": 3.31959428783833e-05, "loss": 1.105, "step": 167 }, { "epoch": 1.7186700767263428, "grad_norm": 0.3226852479294108, "learning_rate": 3.308731088009776e-05, "loss": 1.1061, "step": 168 }, { "epoch": 1.7289002557544757, "grad_norm": 0.3142794136000598, "learning_rate": 3.297799940395781e-05, "loss": 1.1149, "step": 169 }, { "epoch": 1.7391304347826086, "grad_norm": 0.24181665165558022, "learning_rate": 3.286801412528728e-05, "loss": 1.0987, "step": 170 }, { "epoch": 1.7493606138107416, "grad_norm": 0.20788838484035646, "learning_rate": 3.275736075439305e-05, "loss": 1.1093, "step": 171 }, { "epoch": 1.7595907928388748, "grad_norm": 0.28451153851181277, "learning_rate": 3.264604503626853e-05, "loss": 1.1174, "step": 172 }, { "epoch": 1.7698209718670077, "grad_norm": 0.2817148207336252, "learning_rate": 3.2534072750295456e-05, "loss": 1.1008, "step": 173 }, { "epoch": 1.7800511508951407, "grad_norm": 0.24212317366361924, "learning_rate": 3.242144970994377e-05, "loss": 1.1023, "step": 174 }, { "epoch": 1.7902813299232738, "grad_norm": 0.21266663692713014, "learning_rate": 3.230818176246986e-05, "loss": 1.1036, "step": 175 }, { "epoch": 1.8005115089514065, "grad_norm": 0.2520301735794147, "learning_rate": 3.219427478861289e-05, "loss": 1.1037, "step": 176 }, { "epoch": 1.8107416879795397, "grad_norm": 0.3161241021569891, "learning_rate": 3.2079734702289555e-05, "loss": 1.0877, "step": 177 }, { "epoch": 1.8209718670076727, "grad_norm": 0.3060944028715776, "learning_rate": 3.1964567450286996e-05, "loss": 1.1124, "step": 178 }, { "epoch": 1.8312020460358056, "grad_norm": 0.2402334607687787, "learning_rate": 3.1848779011954076e-05, "loss": 1.0935, "step": 179 }, { "epoch": 1.8414322250639388, "grad_norm": 0.25553002034702404, "learning_rate": 3.1732375398890894e-05, "loss": 1.0998, "step": 180 }, { "epoch": 1.8516624040920715, "grad_norm": 0.2637783695396801, "learning_rate": 3.1615362654636743e-05, "loss": 1.1019, "step": 181 }, { "epoch": 1.8618925831202047, "grad_norm": 0.2669661575820072, "learning_rate": 3.149774685435626e-05, "loss": 1.0894, "step": 182 }, { "epoch": 1.8721227621483376, "grad_norm": 0.255574218735534, "learning_rate": 3.1379534104524055e-05, "loss": 1.1011, "step": 183 }, { "epoch": 1.8823529411764706, "grad_norm": 0.23865147293496133, "learning_rate": 3.126073054260765e-05, "loss": 1.1071, "step": 184 }, { "epoch": 1.8925831202046037, "grad_norm": 0.2281192334405852, "learning_rate": 3.114134233674888e-05, "loss": 1.097, "step": 185 }, { "epoch": 1.9028132992327365, "grad_norm": 0.2445536496332577, "learning_rate": 3.102137568544355e-05, "loss": 1.09, "step": 186 }, { "epoch": 1.9130434782608696, "grad_norm": 0.26628100347904377, "learning_rate": 3.090083681721972e-05, "loss": 1.0994, "step": 187 }, { "epoch": 1.9232736572890026, "grad_norm": 0.23796462821260594, "learning_rate": 3.077973199031426e-05, "loss": 1.1025, "step": 188 }, { "epoch": 1.9335038363171355, "grad_norm": 0.18580900093331343, "learning_rate": 3.065806749234795e-05, "loss": 1.0881, "step": 189 }, { "epoch": 1.9437340153452687, "grad_norm": 0.14724438957495017, "learning_rate": 3.053584963999906e-05, "loss": 1.1136, "step": 190 }, { "epoch": 1.9539641943734014, "grad_norm": 0.1787489908444512, "learning_rate": 3.041308477867534e-05, "loss": 1.1114, "step": 191 }, { "epoch": 1.9641943734015346, "grad_norm": 0.17483575594969333, "learning_rate": 3.0289779282184627e-05, "loss": 1.0857, "step": 192 }, { "epoch": 1.9744245524296675, "grad_norm": 0.18752733592586796, "learning_rate": 3.0165939552403896e-05, "loss": 1.0959, "step": 193 }, { "epoch": 1.9846547314578005, "grad_norm": 0.18287948931304057, "learning_rate": 3.004157201894689e-05, "loss": 1.1027, "step": 194 }, { "epoch": 1.9948849104859336, "grad_norm": 0.15472876003283184, "learning_rate": 2.9916683138830297e-05, "loss": 1.1892, "step": 195 }, { "epoch": 2.0051150895140664, "grad_norm": 0.1470524629982156, "learning_rate": 2.979127939613852e-05, "loss": 1.2693, "step": 196 }, { "epoch": 2.0153452685421995, "grad_norm": 0.16340888105879744, "learning_rate": 2.966536730168702e-05, "loss": 1.1078, "step": 197 }, { "epoch": 2.0255754475703327, "grad_norm": 0.13956232969474247, "learning_rate": 2.9538953392684275e-05, "loss": 1.0891, "step": 198 }, { "epoch": 2.0358056265984654, "grad_norm": 0.18457989014871123, "learning_rate": 2.9412044232392416e-05, "loss": 1.0677, "step": 199 }, { "epoch": 2.0460358056265986, "grad_norm": 0.12136529636023749, "learning_rate": 2.9284646409786405e-05, "loss": 1.1144, "step": 200 }, { "epoch": 2.0562659846547313, "grad_norm": 0.15904769414931777, "learning_rate": 2.9156766539212008e-05, "loss": 1.0836, "step": 201 }, { "epoch": 2.0664961636828645, "grad_norm": 0.16599758972337367, "learning_rate": 2.902841126004234e-05, "loss": 1.1089, "step": 202 }, { "epoch": 2.0767263427109977, "grad_norm": 0.17311993519081115, "learning_rate": 2.8899587236333188e-05, "loss": 1.0842, "step": 203 }, { "epoch": 2.0869565217391304, "grad_norm": 0.1631230863619124, "learning_rate": 2.8770301156476985e-05, "loss": 1.0835, "step": 204 }, { "epoch": 2.0971867007672635, "grad_norm": 0.18216951988841093, "learning_rate": 2.8640559732855595e-05, "loss": 1.0814, "step": 205 }, { "epoch": 2.1074168797953963, "grad_norm": 0.17594697478195306, "learning_rate": 2.85103697014918e-05, "loss": 1.0934, "step": 206 }, { "epoch": 2.1176470588235294, "grad_norm": 0.14718498295049004, "learning_rate": 2.8379737821699557e-05, "loss": 1.0985, "step": 207 }, { "epoch": 2.1278772378516626, "grad_norm": 0.13561120318845796, "learning_rate": 2.824867087573308e-05, "loss": 1.1002, "step": 208 }, { "epoch": 2.1381074168797953, "grad_norm": 0.15417265909747283, "learning_rate": 2.8117175668434713e-05, "loss": 1.11, "step": 209 }, { "epoch": 2.1483375959079285, "grad_norm": 0.14865372282114261, "learning_rate": 2.7985259026881637e-05, "loss": 1.0856, "step": 210 }, { "epoch": 2.1585677749360612, "grad_norm": 0.16736680455155972, "learning_rate": 2.785292780003138e-05, "loss": 1.1135, "step": 211 }, { "epoch": 2.1687979539641944, "grad_norm": 0.200442267707597, "learning_rate": 2.7720188858366275e-05, "loss": 1.0825, "step": 212 }, { "epoch": 2.1790281329923276, "grad_norm": 0.17119486207208676, "learning_rate": 2.7587049093536716e-05, "loss": 1.1028, "step": 213 }, { "epoch": 2.1892583120204603, "grad_norm": 0.11508803833277609, "learning_rate": 2.7453515418003385e-05, "loss": 1.0768, "step": 214 }, { "epoch": 2.1994884910485935, "grad_norm": 0.1609204349104562, "learning_rate": 2.7319594764678325e-05, "loss": 1.1199, "step": 215 }, { "epoch": 2.209718670076726, "grad_norm": 0.1728842328378067, "learning_rate": 2.7185294086565028e-05, "loss": 1.097, "step": 216 }, { "epoch": 2.2199488491048593, "grad_norm": 0.13266979279006888, "learning_rate": 2.7050620356397413e-05, "loss": 1.0851, "step": 217 }, { "epoch": 2.2301790281329925, "grad_norm": 0.12940248460884995, "learning_rate": 2.6915580566277855e-05, "loss": 1.0931, "step": 218 }, { "epoch": 2.2404092071611252, "grad_norm": 0.1439492369769675, "learning_rate": 2.6780181727314096e-05, "loss": 1.093, "step": 219 }, { "epoch": 2.2506393861892584, "grad_norm": 0.1483731463378574, "learning_rate": 2.6644430869255294e-05, "loss": 1.0738, "step": 220 }, { "epoch": 2.260869565217391, "grad_norm": 0.14343260571586547, "learning_rate": 2.650833504012702e-05, "loss": 1.0789, "step": 221 }, { "epoch": 2.2710997442455243, "grad_norm": 0.11799733853944923, "learning_rate": 2.6371901305865346e-05, "loss": 1.0832, "step": 222 }, { "epoch": 2.2813299232736575, "grad_norm": 0.1406470804992471, "learning_rate": 2.623513674994998e-05, "loss": 1.0975, "step": 223 }, { "epoch": 2.29156010230179, "grad_norm": 0.14491784783967254, "learning_rate": 2.6098048473036487e-05, "loss": 1.0997, "step": 224 }, { "epoch": 2.3017902813299234, "grad_norm": 0.14083210573593827, "learning_rate": 2.5960643592587676e-05, "loss": 1.0828, "step": 225 }, { "epoch": 2.312020460358056, "grad_norm": 0.12171907591395076, "learning_rate": 2.582292924250402e-05, "loss": 1.078, "step": 226 }, { "epoch": 2.3222506393861893, "grad_norm": 0.1600109191933891, "learning_rate": 2.56849125727533e-05, "loss": 1.0861, "step": 227 }, { "epoch": 2.3324808184143224, "grad_norm": 0.1348612804045715, "learning_rate": 2.5546600748999374e-05, "loss": 1.0833, "step": 228 }, { "epoch": 2.342710997442455, "grad_norm": 0.1406359687196, "learning_rate": 2.5408000952230158e-05, "loss": 1.1027, "step": 229 }, { "epoch": 2.3529411764705883, "grad_norm": 0.1287079233395601, "learning_rate": 2.526912037838479e-05, "loss": 1.0661, "step": 230 }, { "epoch": 2.363171355498721, "grad_norm": 0.1294708592669769, "learning_rate": 2.512996623798002e-05, "loss": 1.0783, "step": 231 }, { "epoch": 2.373401534526854, "grad_norm": 0.13498636958723126, "learning_rate": 2.499054575573585e-05, "loss": 1.0928, "step": 232 }, { "epoch": 2.3836317135549874, "grad_norm": 0.12993498298639505, "learning_rate": 2.485086617020045e-05, "loss": 1.0966, "step": 233 }, { "epoch": 2.39386189258312, "grad_norm": 0.11522478571851609, "learning_rate": 2.4710934733374313e-05, "loss": 1.0691, "step": 234 }, { "epoch": 2.4040920716112533, "grad_norm": 0.12094185174881988, "learning_rate": 2.4570758710333787e-05, "loss": 1.0953, "step": 235 }, { "epoch": 2.414322250639386, "grad_norm": 0.11606589738085801, "learning_rate": 2.4430345378853804e-05, "loss": 1.0782, "step": 236 }, { "epoch": 2.424552429667519, "grad_norm": 0.13141797037490036, "learning_rate": 2.428970202903011e-05, "loss": 1.0753, "step": 237 }, { "epoch": 2.4347826086956523, "grad_norm": 0.12182089290540926, "learning_rate": 2.4148835962900723e-05, "loss": 1.0753, "step": 238 }, { "epoch": 2.445012787723785, "grad_norm": 0.1359534290897358, "learning_rate": 2.4007754494066822e-05, "loss": 1.0921, "step": 239 }, { "epoch": 2.455242966751918, "grad_norm": 0.10904913395439578, "learning_rate": 2.3866464947313053e-05, "loss": 1.0547, "step": 240 }, { "epoch": 2.4654731457800514, "grad_norm": 0.13309500630761395, "learning_rate": 2.3724974658227212e-05, "loss": 1.1068, "step": 241 }, { "epoch": 2.475703324808184, "grad_norm": 0.12066785161235018, "learning_rate": 2.358329097281942e-05, "loss": 1.0802, "step": 242 }, { "epoch": 2.4859335038363173, "grad_norm": 0.13339546005675912, "learning_rate": 2.34414212471407e-05, "loss": 1.0862, "step": 243 }, { "epoch": 2.49616368286445, "grad_norm": 0.12228540791049847, "learning_rate": 2.329937284690106e-05, "loss": 1.0742, "step": 244 }, { "epoch": 2.506393861892583, "grad_norm": 0.11172003153677204, "learning_rate": 2.3157153147087082e-05, "loss": 1.0779, "step": 245 }, { "epoch": 2.516624040920716, "grad_norm": 0.11702007894458077, "learning_rate": 2.301476953157904e-05, "loss": 1.0638, "step": 246 }, { "epoch": 2.526854219948849, "grad_norm": 0.11877470002968875, "learning_rate": 2.2872229392767497e-05, "loss": 1.0809, "step": 247 }, { "epoch": 2.5370843989769822, "grad_norm": 0.12490052394075732, "learning_rate": 2.2729540131169543e-05, "loss": 1.0877, "step": 248 }, { "epoch": 2.547314578005115, "grad_norm": 0.1182539684285276, "learning_rate": 2.258670915504453e-05, "loss": 1.0767, "step": 249 }, { "epoch": 2.557544757033248, "grad_norm": 0.11963420629161502, "learning_rate": 2.2443743880009462e-05, "loss": 1.0724, "step": 250 }, { "epoch": 2.5677749360613813, "grad_norm": 0.13132710667557007, "learning_rate": 2.2300651728654005e-05, "loss": 1.0908, "step": 251 }, { "epoch": 2.578005115089514, "grad_norm": 0.10901480185780218, "learning_rate": 2.2157440130155084e-05, "loss": 1.0913, "step": 252 }, { "epoch": 2.588235294117647, "grad_norm": 0.11228194273312657, "learning_rate": 2.2014116519891168e-05, "loss": 1.0804, "step": 253 }, { "epoch": 2.59846547314578, "grad_norm": 0.12177802474185097, "learning_rate": 2.1870688339056265e-05, "loss": 1.0781, "step": 254 }, { "epoch": 2.608695652173913, "grad_norm": 0.12199809949597626, "learning_rate": 2.172716303427355e-05, "loss": 1.0676, "step": 255 }, { "epoch": 2.618925831202046, "grad_norm": 0.11670283232616911, "learning_rate": 2.158354805720877e-05, "loss": 1.082, "step": 256 }, { "epoch": 2.629156010230179, "grad_norm": 0.12106121800949032, "learning_rate": 2.1439850864183343e-05, "loss": 1.0848, "step": 257 }, { "epoch": 2.639386189258312, "grad_norm": 0.12231654575938986, "learning_rate": 2.1296078915787253e-05, "loss": 1.0768, "step": 258 }, { "epoch": 2.649616368286445, "grad_norm": 0.11373859460806582, "learning_rate": 2.1152239676491687e-05, "loss": 1.0888, "step": 259 }, { "epoch": 2.659846547314578, "grad_norm": 0.11211651873819324, "learning_rate": 2.10083406142615e-05, "loss": 1.0876, "step": 260 }, { "epoch": 2.670076726342711, "grad_norm": 0.10934217060064429, "learning_rate": 2.086438920016748e-05, "loss": 1.0713, "step": 261 }, { "epoch": 2.680306905370844, "grad_norm": 0.12164887060397138, "learning_rate": 2.0720392907998473e-05, "loss": 1.0708, "step": 262 }, { "epoch": 2.690537084398977, "grad_norm": 0.12282073219094865, "learning_rate": 2.0576359213873332e-05, "loss": 1.0747, "step": 263 }, { "epoch": 2.70076726342711, "grad_norm": 0.12605604958059977, "learning_rate": 2.0432295595852774e-05, "loss": 1.0759, "step": 264 }, { "epoch": 2.710997442455243, "grad_norm": 0.12466311463835318, "learning_rate": 2.0288209533551147e-05, "loss": 1.0806, "step": 265 }, { "epoch": 2.7212276214833757, "grad_norm": 0.11255757417253677, "learning_rate": 2.0144108507748053e-05, "loss": 1.1006, "step": 266 }, { "epoch": 2.731457800511509, "grad_norm": 0.15322943731563027, "learning_rate": 2e-05, "loss": 1.0829, "step": 267 }, { "epoch": 2.741687979539642, "grad_norm": 0.1304835093057825, "learning_rate": 1.985589149225195e-05, "loss": 1.0802, "step": 268 }, { "epoch": 2.7519181585677748, "grad_norm": 0.12672163520230004, "learning_rate": 1.9711790466448863e-05, "loss": 1.0968, "step": 269 }, { "epoch": 2.762148337595908, "grad_norm": 0.13576798662606873, "learning_rate": 1.956770440414723e-05, "loss": 1.0694, "step": 270 }, { "epoch": 2.772378516624041, "grad_norm": 0.1525922049487341, "learning_rate": 1.9423640786126675e-05, "loss": 1.0775, "step": 271 }, { "epoch": 2.782608695652174, "grad_norm": 0.1186311249071846, "learning_rate": 1.9279607092001534e-05, "loss": 1.0716, "step": 272 }, { "epoch": 2.792838874680307, "grad_norm": 0.13518949934347838, "learning_rate": 1.913561079983252e-05, "loss": 1.0703, "step": 273 }, { "epoch": 2.80306905370844, "grad_norm": 0.13878953649926296, "learning_rate": 1.899165938573851e-05, "loss": 1.0859, "step": 274 }, { "epoch": 2.813299232736573, "grad_norm": 0.11259480551616749, "learning_rate": 1.8847760323508317e-05, "loss": 1.091, "step": 275 }, { "epoch": 2.8235294117647056, "grad_norm": 0.13830998104112405, "learning_rate": 1.870392108421275e-05, "loss": 1.088, "step": 276 }, { "epoch": 2.833759590792839, "grad_norm": 0.12222587785953827, "learning_rate": 1.856014913581666e-05, "loss": 1.0834, "step": 277 }, { "epoch": 2.843989769820972, "grad_norm": 0.10424466590019475, "learning_rate": 1.8416451942791236e-05, "loss": 1.0841, "step": 278 }, { "epoch": 2.8542199488491047, "grad_norm": 0.11790633325813425, "learning_rate": 1.827283696572646e-05, "loss": 1.0757, "step": 279 }, { "epoch": 2.864450127877238, "grad_norm": 0.12540163476199387, "learning_rate": 1.8129311660943742e-05, "loss": 1.0802, "step": 280 }, { "epoch": 2.874680306905371, "grad_norm": 0.10358970206456232, "learning_rate": 1.7985883480108836e-05, "loss": 1.0822, "step": 281 }, { "epoch": 2.8849104859335037, "grad_norm": 0.11343908267751618, "learning_rate": 1.7842559869844926e-05, "loss": 1.0796, "step": 282 }, { "epoch": 2.895140664961637, "grad_norm": 0.10351299736005762, "learning_rate": 1.7699348271345998e-05, "loss": 1.0704, "step": 283 }, { "epoch": 2.90537084398977, "grad_norm": 0.11097409126060695, "learning_rate": 1.7556256119990538e-05, "loss": 1.0704, "step": 284 }, { "epoch": 2.915601023017903, "grad_norm": 0.12854951600340017, "learning_rate": 1.7413290844955478e-05, "loss": 1.0817, "step": 285 }, { "epoch": 2.9258312020460355, "grad_norm": 0.11447418867835699, "learning_rate": 1.727045986883046e-05, "loss": 1.0777, "step": 286 }, { "epoch": 2.9360613810741687, "grad_norm": 0.12131623507552429, "learning_rate": 1.7127770607232506e-05, "loss": 1.0814, "step": 287 }, { "epoch": 2.946291560102302, "grad_norm": 0.10961862101144348, "learning_rate": 1.6985230468420966e-05, "loss": 1.0863, "step": 288 }, { "epoch": 2.9565217391304346, "grad_norm": 0.14041722223190908, "learning_rate": 1.684284685291292e-05, "loss": 1.094, "step": 289 }, { "epoch": 2.9667519181585678, "grad_norm": 0.10470209688096103, "learning_rate": 1.6700627153098953e-05, "loss": 1.0787, "step": 290 }, { "epoch": 2.976982097186701, "grad_norm": 0.12405187862664697, "learning_rate": 1.6558578752859307e-05, "loss": 1.075, "step": 291 }, { "epoch": 2.9872122762148337, "grad_norm": 0.1062237776271728, "learning_rate": 1.641670902718058e-05, "loss": 1.0953, "step": 292 }, { "epoch": 2.997442455242967, "grad_norm": 0.1546602160568262, "learning_rate": 1.6275025341772794e-05, "loss": 1.2545, "step": 293 }, { "epoch": 3.0076726342710995, "grad_norm": 0.15461002835316104, "learning_rate": 1.6133535052686953e-05, "loss": 1.1921, "step": 294 }, { "epoch": 3.0179028132992327, "grad_norm": 0.12006729211164312, "learning_rate": 1.599224550593319e-05, "loss": 1.0719, "step": 295 }, { "epoch": 3.028132992327366, "grad_norm": 0.127921841944554, "learning_rate": 1.5851164037099284e-05, "loss": 1.0838, "step": 296 }, { "epoch": 3.0383631713554986, "grad_norm": 0.1219968953848957, "learning_rate": 1.5710297970969893e-05, "loss": 1.0599, "step": 297 }, { "epoch": 3.0485933503836318, "grad_norm": 0.10480823093718085, "learning_rate": 1.5569654621146203e-05, "loss": 1.0627, "step": 298 }, { "epoch": 3.0588235294117645, "grad_norm": 0.14490139400367194, "learning_rate": 1.542924128966622e-05, "loss": 1.076, "step": 299 }, { "epoch": 3.0690537084398977, "grad_norm": 0.13706282121272828, "learning_rate": 1.5289065266625684e-05, "loss": 1.0797, "step": 300 }, { "epoch": 3.079283887468031, "grad_norm": 0.10928310239533814, "learning_rate": 1.5149133829799558e-05, "loss": 1.0777, "step": 301 }, { "epoch": 3.0895140664961636, "grad_norm": 0.12754549894011027, "learning_rate": 1.5009454244264156e-05, "loss": 1.1038, "step": 302 }, { "epoch": 3.0997442455242967, "grad_norm": 0.1097873110986652, "learning_rate": 1.4870033762019991e-05, "loss": 1.0605, "step": 303 }, { "epoch": 3.10997442455243, "grad_norm": 0.12822864000131382, "learning_rate": 1.4730879621615217e-05, "loss": 1.0889, "step": 304 }, { "epoch": 3.1202046035805626, "grad_norm": 0.11100886546498183, "learning_rate": 1.4591999047769842e-05, "loss": 1.0863, "step": 305 }, { "epoch": 3.130434782608696, "grad_norm": 0.12431975728173858, "learning_rate": 1.4453399251000635e-05, "loss": 1.0527, "step": 306 }, { "epoch": 3.1406649616368285, "grad_norm": 0.11166537458522897, "learning_rate": 1.4315087427246706e-05, "loss": 1.074, "step": 307 }, { "epoch": 3.1508951406649617, "grad_norm": 0.09969458216151995, "learning_rate": 1.4177070757495983e-05, "loss": 1.0802, "step": 308 }, { "epoch": 3.1611253196930944, "grad_norm": 0.10085277615175393, "learning_rate": 1.4039356407412329e-05, "loss": 1.0987, "step": 309 }, { "epoch": 3.1713554987212276, "grad_norm": 0.0961287589157251, "learning_rate": 1.3901951526963516e-05, "loss": 1.0673, "step": 310 }, { "epoch": 3.1815856777493607, "grad_norm": 0.09873940509853912, "learning_rate": 1.3764863250050031e-05, "loss": 1.0549, "step": 311 }, { "epoch": 3.1918158567774935, "grad_norm": 0.10353837499788582, "learning_rate": 1.362809869413466e-05, "loss": 1.0699, "step": 312 }, { "epoch": 3.2020460358056266, "grad_norm": 0.10347314047302905, "learning_rate": 1.3491664959872984e-05, "loss": 1.0725, "step": 313 }, { "epoch": 3.21227621483376, "grad_norm": 0.10325519520594714, "learning_rate": 1.3355569130744717e-05, "loss": 1.0497, "step": 314 }, { "epoch": 3.2225063938618925, "grad_norm": 0.1110774028975957, "learning_rate": 1.3219818272685912e-05, "loss": 1.0808, "step": 315 }, { "epoch": 3.2327365728900257, "grad_norm": 0.10304642359798406, "learning_rate": 1.3084419433722148e-05, "loss": 1.0643, "step": 316 }, { "epoch": 3.2429667519181584, "grad_norm": 0.0971682646427868, "learning_rate": 1.294937964360259e-05, "loss": 1.0542, "step": 317 }, { "epoch": 3.2531969309462916, "grad_norm": 0.11145603146856517, "learning_rate": 1.2814705913434979e-05, "loss": 1.0706, "step": 318 }, { "epoch": 3.2634271099744243, "grad_norm": 0.09674713472958632, "learning_rate": 1.2680405235321684e-05, "loss": 1.0637, "step": 319 }, { "epoch": 3.2736572890025575, "grad_norm": 0.10843006589984941, "learning_rate": 1.2546484581996623e-05, "loss": 1.0874, "step": 320 }, { "epoch": 3.2838874680306906, "grad_norm": 0.09363255737392259, "learning_rate": 1.2412950906463287e-05, "loss": 1.0748, "step": 321 }, { "epoch": 3.2941176470588234, "grad_norm": 0.11030662559756653, "learning_rate": 1.2279811141633735e-05, "loss": 1.0706, "step": 322 }, { "epoch": 3.3043478260869565, "grad_norm": 0.09729921774753335, "learning_rate": 1.2147072199968629e-05, "loss": 1.0601, "step": 323 }, { "epoch": 3.3145780051150897, "grad_norm": 0.10106384596888374, "learning_rate": 1.201474097311837e-05, "loss": 1.0567, "step": 324 }, { "epoch": 3.3248081841432224, "grad_norm": 0.10693870820352067, "learning_rate": 1.188282433156529e-05, "loss": 1.0725, "step": 325 }, { "epoch": 3.3350383631713556, "grad_norm": 0.09690530048216456, "learning_rate": 1.1751329124266924e-05, "loss": 1.0677, "step": 326 }, { "epoch": 3.3452685421994883, "grad_norm": 0.10339032018288434, "learning_rate": 1.1620262178300456e-05, "loss": 1.0544, "step": 327 }, { "epoch": 3.3554987212276215, "grad_norm": 0.08825003481069207, "learning_rate": 1.1489630298508205e-05, "loss": 1.0769, "step": 328 }, { "epoch": 3.3657289002557547, "grad_norm": 0.08787461260474569, "learning_rate": 1.1359440267144413e-05, "loss": 1.0612, "step": 329 }, { "epoch": 3.3759590792838874, "grad_norm": 0.09823756696049714, "learning_rate": 1.1229698843523027e-05, "loss": 1.0732, "step": 330 }, { "epoch": 3.3861892583120206, "grad_norm": 0.09531296658931637, "learning_rate": 1.1100412763666819e-05, "loss": 1.0568, "step": 331 }, { "epoch": 3.3964194373401533, "grad_norm": 0.09984299313983538, "learning_rate": 1.0971588739957656e-05, "loss": 1.0635, "step": 332 }, { "epoch": 3.4066496163682864, "grad_norm": 0.09489239193383751, "learning_rate": 1.0843233460788e-05, "loss": 1.0803, "step": 333 }, { "epoch": 3.4168797953964196, "grad_norm": 0.09159844593827017, "learning_rate": 1.0715353590213597e-05, "loss": 1.0757, "step": 334 }, { "epoch": 3.4271099744245523, "grad_norm": 0.0894738894680945, "learning_rate": 1.0587955767607594e-05, "loss": 1.0686, "step": 335 }, { "epoch": 3.4373401534526855, "grad_norm": 0.09921878316185964, "learning_rate": 1.0461046607315723e-05, "loss": 1.0765, "step": 336 }, { "epoch": 3.4475703324808182, "grad_norm": 0.0957429216895665, "learning_rate": 1.033463269831299e-05, "loss": 1.0747, "step": 337 }, { "epoch": 3.4578005115089514, "grad_norm": 0.08414571850711541, "learning_rate": 1.0208720603861488e-05, "loss": 1.0961, "step": 338 }, { "epoch": 3.4680306905370846, "grad_norm": 0.10168015813114815, "learning_rate": 1.0083316861169704e-05, "loss": 1.0606, "step": 339 }, { "epoch": 3.4782608695652173, "grad_norm": 0.09551584703983902, "learning_rate": 9.958427981053116e-06, "loss": 1.0804, "step": 340 }, { "epoch": 3.4884910485933505, "grad_norm": 0.09831692314317865, "learning_rate": 9.834060447596114e-06, "loss": 1.0677, "step": 341 }, { "epoch": 3.498721227621483, "grad_norm": 0.09383345577537172, "learning_rate": 9.710220717815378e-06, "loss": 1.0787, "step": 342 }, { "epoch": 3.5089514066496164, "grad_norm": 0.09247292995353687, "learning_rate": 9.586915221324668e-06, "loss": 1.0959, "step": 343 }, { "epoch": 3.5191815856777495, "grad_norm": 0.08744993240245372, "learning_rate": 9.464150360000946e-06, "loss": 1.0543, "step": 344 }, { "epoch": 3.5294117647058822, "grad_norm": 0.08739863273178501, "learning_rate": 9.341932507652053e-06, "loss": 1.079, "step": 345 }, { "epoch": 3.5396419437340154, "grad_norm": 0.08591934564082804, "learning_rate": 9.220268009685752e-06, "loss": 1.0917, "step": 346 }, { "epoch": 3.5498721227621486, "grad_norm": 0.08530982771585134, "learning_rate": 9.099163182780284e-06, "loss": 1.0698, "step": 347 }, { "epoch": 3.5601023017902813, "grad_norm": 0.08396702129279394, "learning_rate": 8.978624314556454e-06, "loss": 1.078, "step": 348 }, { "epoch": 3.5703324808184145, "grad_norm": 0.07547800696072196, "learning_rate": 8.85865766325113e-06, "loss": 1.0763, "step": 349 }, { "epoch": 3.580562659846547, "grad_norm": 0.08350840674801444, "learning_rate": 8.73926945739235e-06, "loss": 1.0749, "step": 350 }, { "epoch": 3.5907928388746804, "grad_norm": 0.08144508914012105, "learning_rate": 8.620465895475958e-06, "loss": 1.0647, "step": 351 }, { "epoch": 3.601023017902813, "grad_norm": 0.0840979229088987, "learning_rate": 8.502253145643752e-06, "loss": 1.0814, "step": 352 }, { "epoch": 3.6112531969309463, "grad_norm": 0.07895251042079375, "learning_rate": 8.384637345363262e-06, "loss": 1.0638, "step": 353 }, { "epoch": 3.6214833759590794, "grad_norm": 0.08686156430173361, "learning_rate": 8.26762460110911e-06, "loss": 1.0654, "step": 354 }, { "epoch": 3.631713554987212, "grad_norm": 0.07746103803729665, "learning_rate": 8.151220988045929e-06, "loss": 1.0713, "step": 355 }, { "epoch": 3.6419437340153453, "grad_norm": 0.08436880420354408, "learning_rate": 8.035432549713006e-06, "loss": 1.0657, "step": 356 }, { "epoch": 3.6521739130434785, "grad_norm": 0.07565659638802982, "learning_rate": 7.920265297710451e-06, "loss": 1.0686, "step": 357 }, { "epoch": 3.662404092071611, "grad_norm": 0.08286700475384223, "learning_rate": 7.805725211387113e-06, "loss": 1.081, "step": 358 }, { "epoch": 3.6726342710997444, "grad_norm": 0.07781514667340442, "learning_rate": 7.691818237530147e-06, "loss": 1.0596, "step": 359 }, { "epoch": 3.682864450127877, "grad_norm": 0.0951431734041778, "learning_rate": 7.5785502900562324e-06, "loss": 1.0732, "step": 360 }, { "epoch": 3.6930946291560103, "grad_norm": 0.08042329644112586, "learning_rate": 7.46592724970455e-06, "loss": 1.0567, "step": 361 }, { "epoch": 3.703324808184143, "grad_norm": 0.07601661591847954, "learning_rate": 7.353954963731475e-06, "loss": 1.071, "step": 362 }, { "epoch": 3.713554987212276, "grad_norm": 0.08573966219122138, "learning_rate": 7.242639245606959e-06, "loss": 1.0611, "step": 363 }, { "epoch": 3.7237851662404093, "grad_norm": 0.08953027088566128, "learning_rate": 7.131985874712717e-06, "loss": 1.0634, "step": 364 }, { "epoch": 3.734015345268542, "grad_norm": 0.0818226085978608, "learning_rate": 7.022000596042196e-06, "loss": 1.0806, "step": 365 }, { "epoch": 3.7442455242966752, "grad_norm": 0.08574090319665176, "learning_rate": 6.912689119902245e-06, "loss": 1.0626, "step": 366 }, { "epoch": 3.7544757033248084, "grad_norm": 0.07209784093188339, "learning_rate": 6.804057121616714e-06, "loss": 1.0648, "step": 367 }, { "epoch": 3.764705882352941, "grad_norm": 0.08392846348248735, "learning_rate": 6.696110241231708e-06, "loss": 1.0695, "step": 368 }, { "epoch": 3.7749360613810743, "grad_norm": 0.0822595260959984, "learning_rate": 6.588854083222851e-06, "loss": 1.0676, "step": 369 }, { "epoch": 3.785166240409207, "grad_norm": 0.07549500754650335, "learning_rate": 6.48229421620427e-06, "loss": 1.053, "step": 370 }, { "epoch": 3.79539641943734, "grad_norm": 0.08466247105944975, "learning_rate": 6.3764361726394616e-06, "loss": 1.0871, "step": 371 }, { "epoch": 3.805626598465473, "grad_norm": 0.0807054858352925, "learning_rate": 6.271285448554072e-06, "loss": 1.0859, "step": 372 }, { "epoch": 3.815856777493606, "grad_norm": 0.08262247758415588, "learning_rate": 6.166847503250563e-06, "loss": 1.0706, "step": 373 }, { "epoch": 3.8260869565217392, "grad_norm": 0.08269932344248264, "learning_rate": 6.063127759024745e-06, "loss": 1.0834, "step": 374 }, { "epoch": 3.836317135549872, "grad_norm": 0.07428197959727556, "learning_rate": 5.960131600884274e-06, "loss": 1.0636, "step": 375 }, { "epoch": 3.846547314578005, "grad_norm": 0.0767789669165535, "learning_rate": 5.857864376269051e-06, "loss": 1.067, "step": 376 }, { "epoch": 3.8567774936061383, "grad_norm": 0.08437769692277076, "learning_rate": 5.756331394773624e-06, "loss": 1.0867, "step": 377 }, { "epoch": 3.867007672634271, "grad_norm": 0.07475241555743972, "learning_rate": 5.6555379278714905e-06, "loss": 1.0618, "step": 378 }, { "epoch": 3.877237851662404, "grad_norm": 0.07633061893990638, "learning_rate": 5.555489208641412e-06, "loss": 1.0632, "step": 379 }, { "epoch": 3.887468030690537, "grad_norm": 0.08149043676785563, "learning_rate": 5.4561904314957185e-06, "loss": 1.1028, "step": 380 }, { "epoch": 3.89769820971867, "grad_norm": 0.07550834347044144, "learning_rate": 5.357646751910628e-06, "loss": 1.0396, "step": 381 }, { "epoch": 3.907928388746803, "grad_norm": 0.07625084385983938, "learning_rate": 5.259863286158591e-06, "loss": 1.0857, "step": 382 }, { "epoch": 3.918158567774936, "grad_norm": 0.07083035914802652, "learning_rate": 5.162845111042632e-06, "loss": 1.0643, "step": 383 }, { "epoch": 3.928388746803069, "grad_norm": 0.07229307043437665, "learning_rate": 5.0665972636327775e-06, "loss": 1.0725, "step": 384 }, { "epoch": 3.938618925831202, "grad_norm": 0.07807735906667276, "learning_rate": 4.971124741004558e-06, "loss": 1.0631, "step": 385 }, { "epoch": 3.948849104859335, "grad_norm": 0.0756641766450725, "learning_rate": 4.8764324999795486e-06, "loss": 1.0541, "step": 386 }, { "epoch": 3.959079283887468, "grad_norm": 0.0659598011873379, "learning_rate": 4.78252545686799e-06, "loss": 1.0598, "step": 387 }, { "epoch": 3.969309462915601, "grad_norm": 0.0731709328116761, "learning_rate": 4.6894084872136026e-06, "loss": 1.0998, "step": 388 }, { "epoch": 3.979539641943734, "grad_norm": 0.07839036679642926, "learning_rate": 4.597086425540389e-06, "loss": 1.0854, "step": 389 }, { "epoch": 3.9897698209718673, "grad_norm": 0.07687064365683145, "learning_rate": 4.505564065101689e-06, "loss": 1.0706, "step": 390 }, { "epoch": 4.0, "grad_norm": 0.08924423512701447, "learning_rate": 4.414846157631265e-06, "loss": 1.3509, "step": 391 }, { "epoch": 4.010230179028133, "grad_norm": 0.07578600533231729, "learning_rate": 4.324937413096628e-06, "loss": 1.0539, "step": 392 }, { "epoch": 4.020460358056266, "grad_norm": 0.08368995024205941, "learning_rate": 4.2358424994545165e-06, "loss": 1.0684, "step": 393 }, { "epoch": 4.030690537084399, "grad_norm": 0.06847620596188483, "learning_rate": 4.147566042408502e-06, "loss": 1.0605, "step": 394 }, { "epoch": 4.040920716112532, "grad_norm": 0.07674538598184749, "learning_rate": 4.060112625168848e-06, "loss": 1.0681, "step": 395 }, { "epoch": 4.051150895140665, "grad_norm": 0.07411955836062326, "learning_rate": 3.973486788214571e-06, "loss": 1.0544, "step": 396 }, { "epoch": 4.061381074168798, "grad_norm": 0.08032300973660715, "learning_rate": 3.887693029057675e-06, "loss": 1.0571, "step": 397 }, { "epoch": 4.071611253196931, "grad_norm": 0.06963288218234127, "learning_rate": 3.8027358020096584e-06, "loss": 1.0829, "step": 398 }, { "epoch": 4.081841432225064, "grad_norm": 0.07658885525810889, "learning_rate": 3.7186195179502636e-06, "loss": 1.0841, "step": 399 }, { "epoch": 4.092071611253197, "grad_norm": 0.07191505898188405, "learning_rate": 3.6353485440984427e-06, "loss": 1.0552, "step": 400 }, { "epoch": 4.10230179028133, "grad_norm": 0.0708946929272983, "learning_rate": 3.5529272037856497e-06, "loss": 1.0613, "step": 401 }, { "epoch": 4.112531969309463, "grad_norm": 0.06812388336417115, "learning_rate": 3.471359776231347e-06, "loss": 1.0613, "step": 402 }, { "epoch": 4.122762148337596, "grad_norm": 0.06855644563541499, "learning_rate": 3.3906504963208396e-06, "loss": 1.0636, "step": 403 }, { "epoch": 4.132992327365729, "grad_norm": 0.06712586888451333, "learning_rate": 3.310803554385438e-06, "loss": 1.0719, "step": 404 }, { "epoch": 4.143222506393862, "grad_norm": 0.06886864694467747, "learning_rate": 3.2318230959848517e-06, "loss": 1.0639, "step": 405 }, { "epoch": 4.153452685421995, "grad_norm": 0.06942897747798116, "learning_rate": 3.153713221691983e-06, "loss": 1.0707, "step": 406 }, { "epoch": 4.163682864450128, "grad_norm": 0.07379761044326129, "learning_rate": 3.0764779868800398e-06, "loss": 1.0711, "step": 407 }, { "epoch": 4.173913043478261, "grad_norm": 0.06865918848541905, "learning_rate": 3.0001214015119593e-06, "loss": 1.0792, "step": 408 }, { "epoch": 4.1841432225063935, "grad_norm": 0.06780846203483021, "learning_rate": 2.924647429932228e-06, "loss": 1.0788, "step": 409 }, { "epoch": 4.194373401534527, "grad_norm": 0.06536242133183677, "learning_rate": 2.8500599906610736e-06, "loss": 1.0641, "step": 410 }, { "epoch": 4.20460358056266, "grad_norm": 0.06663074408761491, "learning_rate": 2.776362956190983e-06, "loss": 1.0596, "step": 411 }, { "epoch": 4.2148337595907925, "grad_norm": 0.06654906098672408, "learning_rate": 2.7035601527856914e-06, "loss": 1.0583, "step": 412 }, { "epoch": 4.225063938618926, "grad_norm": 0.06688729515895334, "learning_rate": 2.6316553602814864e-06, "loss": 1.057, "step": 413 }, { "epoch": 4.235294117647059, "grad_norm": 0.06447264384050708, "learning_rate": 2.560652311890981e-06, "loss": 1.0739, "step": 414 }, { "epoch": 4.245524296675192, "grad_norm": 0.0639965101079602, "learning_rate": 2.4905546940093086e-06, "loss": 1.0715, "step": 415 }, { "epoch": 4.255754475703325, "grad_norm": 0.06519279446292395, "learning_rate": 2.4213661460226925e-06, "loss": 1.0679, "step": 416 }, { "epoch": 4.265984654731458, "grad_norm": 0.07304580911858156, "learning_rate": 2.353090260119515e-06, "loss": 1.0538, "step": 417 }, { "epoch": 4.276214833759591, "grad_norm": 0.06648155278938164, "learning_rate": 2.28573058110382e-06, "loss": 1.0634, "step": 418 }, { "epoch": 4.286445012787723, "grad_norm": 0.06345271546432055, "learning_rate": 2.219290606211253e-06, "loss": 1.0502, "step": 419 }, { "epoch": 4.296675191815857, "grad_norm": 0.06383006338193715, "learning_rate": 2.153773784927511e-06, "loss": 1.0738, "step": 420 }, { "epoch": 4.30690537084399, "grad_norm": 0.06508082687651225, "learning_rate": 2.0891835188092146e-06, "loss": 1.0823, "step": 421 }, { "epoch": 4.3171355498721224, "grad_norm": 0.07239447442607977, "learning_rate": 2.025523161307348e-06, "loss": 1.0527, "step": 422 }, { "epoch": 4.327365728900256, "grad_norm": 0.06452893499877213, "learning_rate": 1.962796017593125e-06, "loss": 1.0697, "step": 423 }, { "epoch": 4.337595907928389, "grad_norm": 0.06560977198213125, "learning_rate": 1.9010053443863796e-06, "loss": 1.0713, "step": 424 }, { "epoch": 4.3478260869565215, "grad_norm": 0.062487187825821404, "learning_rate": 1.8401543497865026e-06, "loss": 1.0588, "step": 425 }, { "epoch": 4.358056265984655, "grad_norm": 0.06339129403278677, "learning_rate": 1.7802461931058767e-06, "loss": 1.0648, "step": 426 }, { "epoch": 4.368286445012788, "grad_norm": 0.06463556573173153, "learning_rate": 1.721283984705835e-06, "loss": 1.0692, "step": 427 }, { "epoch": 4.378516624040921, "grad_norm": 0.072369422172923, "learning_rate": 1.663270785835187e-06, "loss": 1.086, "step": 428 }, { "epoch": 4.388746803069053, "grad_norm": 0.06033519185047689, "learning_rate": 1.6062096084712786e-06, "loss": 1.0699, "step": 429 }, { "epoch": 4.398976982097187, "grad_norm": 0.05818331949145165, "learning_rate": 1.5501034151636129e-06, "loss": 1.0689, "step": 430 }, { "epoch": 4.40920716112532, "grad_norm": 0.06010088825612501, "learning_rate": 1.4949551188800504e-06, "loss": 1.0806, "step": 431 }, { "epoch": 4.419437340153452, "grad_norm": 0.05937706435469435, "learning_rate": 1.4407675828555378e-06, "loss": 1.0627, "step": 432 }, { "epoch": 4.429667519181586, "grad_norm": 0.062013786763132926, "learning_rate": 1.3875436204434922e-06, "loss": 1.0651, "step": 433 }, { "epoch": 4.439897698209719, "grad_norm": 0.06451175713491827, "learning_rate": 1.3352859949697127e-06, "loss": 1.0777, "step": 434 }, { "epoch": 4.450127877237851, "grad_norm": 0.06162813979422373, "learning_rate": 1.283997419588916e-06, "loss": 1.0605, "step": 435 }, { "epoch": 4.460358056265985, "grad_norm": 0.05846138400522631, "learning_rate": 1.2336805571438703e-06, "loss": 1.0679, "step": 436 }, { "epoch": 4.470588235294118, "grad_norm": 0.05888401783431065, "learning_rate": 1.1843380200271426e-06, "loss": 1.0684, "step": 437 }, { "epoch": 4.4808184143222505, "grad_norm": 0.061124238857325645, "learning_rate": 1.135972370045486e-06, "loss": 1.0746, "step": 438 }, { "epoch": 4.491048593350383, "grad_norm": 0.06281073611812223, "learning_rate": 1.0885861182867985e-06, "loss": 1.0764, "step": 439 }, { "epoch": 4.501278772378517, "grad_norm": 0.06312481995359293, "learning_rate": 1.0421817249897791e-06, "loss": 1.0625, "step": 440 }, { "epoch": 4.5115089514066495, "grad_norm": 0.06295729104665382, "learning_rate": 9.96761599416185e-07, "loss": 1.0768, "step": 441 }, { "epoch": 4.521739130434782, "grad_norm": 0.0611693601875824, "learning_rate": 9.5232809972575e-07, "loss": 1.0741, "step": 442 }, { "epoch": 4.531969309462916, "grad_norm": 0.05782501757385847, "learning_rate": 9.088835328537304e-07, "loss": 1.0595, "step": 443 }, { "epoch": 4.542199488491049, "grad_norm": 0.059694394249882904, "learning_rate": 8.66430154391169e-07, "loss": 1.0532, "step": 444 }, { "epoch": 4.552429667519181, "grad_norm": 0.060814177486017695, "learning_rate": 8.249701684677558e-07, "loss": 1.0716, "step": 445 }, { "epoch": 4.562659846547315, "grad_norm": 0.0598830892634924, "learning_rate": 7.84505727637408e-07, "loss": 1.0798, "step": 446 }, { "epoch": 4.572890025575448, "grad_norm": 0.059434528694292506, "learning_rate": 7.450389327665042e-07, "loss": 1.0513, "step": 447 }, { "epoch": 4.58312020460358, "grad_norm": 0.057039156272022225, "learning_rate": 7.065718329248139e-07, "loss": 1.0768, "step": 448 }, { "epoch": 4.593350383631714, "grad_norm": 0.05723133802281261, "learning_rate": 6.691064252791158e-07, "loss": 1.0599, "step": 449 }, { "epoch": 4.603580562659847, "grad_norm": 0.06105882434399679, "learning_rate": 6.326446549894983e-07, "loss": 1.0654, "step": 450 }, { "epoch": 4.6138107416879794, "grad_norm": 0.05956113794100574, "learning_rate": 5.971884151083696e-07, "loss": 1.0432, "step": 451 }, { "epoch": 4.624040920716112, "grad_norm": 0.05942349583501023, "learning_rate": 5.627395464821894e-07, "loss": 1.0714, "step": 452 }, { "epoch": 4.634271099744246, "grad_norm": 0.05635707532109553, "learning_rate": 5.292998376558656e-07, "loss": 1.0766, "step": 453 }, { "epoch": 4.6445012787723785, "grad_norm": 0.05903620745333425, "learning_rate": 4.96871024779928e-07, "loss": 1.0793, "step": 454 }, { "epoch": 4.654731457800511, "grad_norm": 0.0577153505352874, "learning_rate": 4.654547915203589e-07, "loss": 1.0659, "step": 455 }, { "epoch": 4.664961636828645, "grad_norm": 0.06484907212671626, "learning_rate": 4.3505276897119586e-07, "loss": 1.0594, "step": 456 }, { "epoch": 4.675191815856778, "grad_norm": 0.060071269047249715, "learning_rate": 4.056665355698508e-07, "loss": 1.0543, "step": 457 }, { "epoch": 4.68542199488491, "grad_norm": 0.05833236997333743, "learning_rate": 3.7729761701514655e-07, "loss": 1.0729, "step": 458 }, { "epoch": 4.695652173913043, "grad_norm": 0.05754385761647327, "learning_rate": 3.499474861881069e-07, "loss": 1.0852, "step": 459 }, { "epoch": 4.705882352941177, "grad_norm": 0.057359147029672014, "learning_rate": 3.236175630755023e-07, "loss": 1.0603, "step": 460 }, { "epoch": 4.716112531969309, "grad_norm": 0.05502312699425405, "learning_rate": 2.98309214696102e-07, "loss": 1.0606, "step": 461 }, { "epoch": 4.726342710997442, "grad_norm": 0.05848906997188855, "learning_rate": 2.740237550297131e-07, "loss": 1.0758, "step": 462 }, { "epoch": 4.736572890025576, "grad_norm": 0.05693974727449699, "learning_rate": 2.507624449489665e-07, "loss": 1.0703, "step": 463 }, { "epoch": 4.746803069053708, "grad_norm": 0.060117370456376766, "learning_rate": 2.2852649215383548e-07, "loss": 1.0745, "step": 464 }, { "epoch": 4.757033248081841, "grad_norm": 0.056574241819605915, "learning_rate": 2.0731705110895284e-07, "loss": 1.0702, "step": 465 }, { "epoch": 4.767263427109975, "grad_norm": 0.05850407146566137, "learning_rate": 1.8713522298365428e-07, "loss": 1.0817, "step": 466 }, { "epoch": 4.7774936061381075, "grad_norm": 0.058789889531343384, "learning_rate": 1.679820555948264e-07, "loss": 1.0645, "step": 467 }, { "epoch": 4.78772378516624, "grad_norm": 0.05716794561138148, "learning_rate": 1.4985854335248572e-07, "loss": 1.075, "step": 468 }, { "epoch": 4.797953964194374, "grad_norm": 0.055191974019031344, "learning_rate": 1.3276562720816677e-07, "loss": 1.0488, "step": 469 }, { "epoch": 4.8081841432225065, "grad_norm": 0.055562342833215025, "learning_rate": 1.1670419460605431e-07, "loss": 1.0611, "step": 470 }, { "epoch": 4.818414322250639, "grad_norm": 0.05680580694018153, "learning_rate": 1.0167507943692478e-07, "loss": 1.0556, "step": 471 }, { "epoch": 4.828644501278772, "grad_norm": 0.05619366643069308, "learning_rate": 8.767906199483422e-08, "loss": 1.0708, "step": 472 }, { "epoch": 4.838874680306906, "grad_norm": 0.054452430626228114, "learning_rate": 7.471686893661734e-08, "loss": 1.0533, "step": 473 }, { "epoch": 4.849104859335038, "grad_norm": 0.0576401286384887, "learning_rate": 6.27891732441599e-08, "loss": 1.0595, "step": 474 }, { "epoch": 4.859335038363171, "grad_norm": 0.05429173265004916, "learning_rate": 5.1896594189448925e-08, "loss": 1.0735, "step": 475 }, { "epoch": 4.869565217391305, "grad_norm": 0.05834244532356458, "learning_rate": 4.20396973024384e-08, "loss": 1.0695, "step": 476 }, { "epoch": 4.879795396419437, "grad_norm": 0.05739572029230359, "learning_rate": 3.321899434166831e-08, "loss": 1.077, "step": 477 }, { "epoch": 4.89002557544757, "grad_norm": 0.05580807335685245, "learning_rate": 2.5434943267705902e-08, "loss": 1.0723, "step": 478 }, { "epoch": 4.900255754475703, "grad_norm": 0.05685796268467914, "learning_rate": 1.8687948219371367e-08, "loss": 1.0774, "step": 479 }, { "epoch": 4.910485933503836, "grad_norm": 0.05491643772037376, "learning_rate": 1.2978359492741288e-08, "loss": 1.0546, "step": 480 }, { "epoch": 4.920716112531969, "grad_norm": 0.05519615934013274, "learning_rate": 8.306473522976532e-09, "loss": 1.062, "step": 481 }, { "epoch": 4.930946291560103, "grad_norm": 0.055812202915964615, "learning_rate": 4.672532868927882e-09, "loss": 1.0809, "step": 482 }, { "epoch": 4.9411764705882355, "grad_norm": 0.05536585739894165, "learning_rate": 2.0767262005372267e-09, "loss": 1.086, "step": 483 }, { "epoch": 4.951406649616368, "grad_norm": 0.055426487124572474, "learning_rate": 5.191882890454025e-10, "loss": 1.0569, "step": 484 }, { "epoch": 4.961636828644501, "grad_norm": 0.05560606954338175, "learning_rate": 0.0, "loss": 1.0654, "step": 485 }, { "epoch": 4.961636828644501, "step": 485, "total_flos": 7065760181780480.0, "train_loss": 1.1163312366328288, "train_runtime": 42603.8864, "train_samples_per_second": 11.736, "train_steps_per_second": 0.011 } ], "logging_steps": 1.0, "max_steps": 485, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 7065760181780480.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }