{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1210, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008264462809917355, "grad_norm": 35.12614822387695, "learning_rate": 1.639344262295082e-07, "loss": 1.2941, "step": 1 }, { "epoch": 0.001652892561983471, "grad_norm": 36.89109420776367, "learning_rate": 3.278688524590164e-07, "loss": 1.4524, "step": 2 }, { "epoch": 0.0024793388429752068, "grad_norm": 39.57857131958008, "learning_rate": 4.918032786885246e-07, "loss": 1.4642, "step": 3 }, { "epoch": 0.003305785123966942, "grad_norm": 47.02167510986328, "learning_rate": 6.557377049180328e-07, "loss": 1.5826, "step": 4 }, { "epoch": 0.004132231404958678, "grad_norm": 45.124114990234375, "learning_rate": 8.196721311475409e-07, "loss": 1.8503, "step": 5 }, { "epoch": 0.0049586776859504135, "grad_norm": 374.71484375, "learning_rate": 9.836065573770493e-07, "loss": 4.8292, "step": 6 }, { "epoch": 0.005785123966942148, "grad_norm": 376.0966796875, "learning_rate": 1.1475409836065575e-06, "loss": 4.7879, "step": 7 }, { "epoch": 0.006611570247933884, "grad_norm": 374.0869445800781, "learning_rate": 1.3114754098360657e-06, "loss": 4.8364, "step": 8 }, { "epoch": 0.00743801652892562, "grad_norm": 360.5589294433594, "learning_rate": 1.4754098360655739e-06, "loss": 4.3553, "step": 9 }, { "epoch": 0.008264462809917356, "grad_norm": 349.61932373046875, "learning_rate": 1.6393442622950819e-06, "loss": 4.0703, "step": 10 }, { "epoch": 0.00909090909090909, "grad_norm": 336.42889404296875, "learning_rate": 1.8032786885245903e-06, "loss": 3.8107, "step": 11 }, { "epoch": 0.009917355371900827, "grad_norm": 198.629638671875, "learning_rate": 1.9672131147540985e-06, "loss": 2.7545, "step": 12 }, { "epoch": 0.010743801652892562, "grad_norm": 147.47877502441406, "learning_rate": 2.1311475409836067e-06, "loss": 2.589, "step": 13 }, { "epoch": 0.011570247933884297, "grad_norm": 90.01700592041016, "learning_rate": 2.295081967213115e-06, "loss": 2.5207, "step": 14 }, { "epoch": 0.012396694214876033, "grad_norm": 43.3622932434082, "learning_rate": 2.459016393442623e-06, "loss": 2.3798, "step": 15 }, { "epoch": 0.013223140495867768, "grad_norm": 33.97830581665039, "learning_rate": 2.6229508196721314e-06, "loss": 2.1262, "step": 16 }, { "epoch": 0.014049586776859505, "grad_norm": 31.877763748168945, "learning_rate": 2.786885245901639e-06, "loss": 2.437, "step": 17 }, { "epoch": 0.01487603305785124, "grad_norm": 44.69379425048828, "learning_rate": 2.9508196721311478e-06, "loss": 2.7615, "step": 18 }, { "epoch": 0.015702479338842976, "grad_norm": 43.80733108520508, "learning_rate": 3.114754098360656e-06, "loss": 2.5191, "step": 19 }, { "epoch": 0.01652892561983471, "grad_norm": 35.15926742553711, "learning_rate": 3.2786885245901638e-06, "loss": 2.3142, "step": 20 }, { "epoch": 0.017355371900826446, "grad_norm": 33.019527435302734, "learning_rate": 3.4426229508196724e-06, "loss": 2.0956, "step": 21 }, { "epoch": 0.01818181818181818, "grad_norm": 28.401559829711914, "learning_rate": 3.6065573770491806e-06, "loss": 1.7151, "step": 22 }, { "epoch": 0.019008264462809916, "grad_norm": 25.92833137512207, "learning_rate": 3.7704918032786884e-06, "loss": 1.8749, "step": 23 }, { "epoch": 0.019834710743801654, "grad_norm": 23.572309494018555, "learning_rate": 3.934426229508197e-06, "loss": 1.906, "step": 24 }, { "epoch": 0.02066115702479339, "grad_norm": 22.781951904296875, "learning_rate": 4.098360655737705e-06, "loss": 1.8617, "step": 25 }, { "epoch": 0.021487603305785124, "grad_norm": 7.054357528686523, "learning_rate": 4.2622950819672135e-06, "loss": 0.8932, "step": 26 }, { "epoch": 0.02231404958677686, "grad_norm": 6.233171463012695, "learning_rate": 4.426229508196722e-06, "loss": 1.012, "step": 27 }, { "epoch": 0.023140495867768594, "grad_norm": 5.4683051109313965, "learning_rate": 4.59016393442623e-06, "loss": 1.0207, "step": 28 }, { "epoch": 0.023966942148760332, "grad_norm": 5.118521213531494, "learning_rate": 4.754098360655738e-06, "loss": 1.0721, "step": 29 }, { "epoch": 0.024793388429752067, "grad_norm": 5.259830951690674, "learning_rate": 4.918032786885246e-06, "loss": 1.176, "step": 30 }, { "epoch": 0.0256198347107438, "grad_norm": 31.10423469543457, "learning_rate": 5.0819672131147545e-06, "loss": 1.4009, "step": 31 }, { "epoch": 0.026446280991735537, "grad_norm": 21.79800033569336, "learning_rate": 5.245901639344263e-06, "loss": 1.2526, "step": 32 }, { "epoch": 0.02727272727272727, "grad_norm": 20.524797439575195, "learning_rate": 5.409836065573772e-06, "loss": 1.1859, "step": 33 }, { "epoch": 0.02809917355371901, "grad_norm": 17.946226119995117, "learning_rate": 5.573770491803278e-06, "loss": 1.1133, "step": 34 }, { "epoch": 0.028925619834710745, "grad_norm": 16.537263870239258, "learning_rate": 5.737704918032787e-06, "loss": 1.0933, "step": 35 }, { "epoch": 0.02975206611570248, "grad_norm": 16.203887939453125, "learning_rate": 5.9016393442622956e-06, "loss": 1.051, "step": 36 }, { "epoch": 0.030578512396694214, "grad_norm": 15.776374816894531, "learning_rate": 6.065573770491804e-06, "loss": 1.0397, "step": 37 }, { "epoch": 0.03140495867768595, "grad_norm": 15.78660774230957, "learning_rate": 6.229508196721312e-06, "loss": 1.0247, "step": 38 }, { "epoch": 0.032231404958677684, "grad_norm": 16.88052749633789, "learning_rate": 6.393442622950821e-06, "loss": 1.0407, "step": 39 }, { "epoch": 0.03305785123966942, "grad_norm": 15.079468727111816, "learning_rate": 6.5573770491803276e-06, "loss": 0.9895, "step": 40 }, { "epoch": 0.033884297520661154, "grad_norm": 16.4204044342041, "learning_rate": 6.721311475409837e-06, "loss": 0.9551, "step": 41 }, { "epoch": 0.03471074380165289, "grad_norm": 13.154854774475098, "learning_rate": 6.885245901639345e-06, "loss": 1.0659, "step": 42 }, { "epoch": 0.03553719008264463, "grad_norm": 14.134108543395996, "learning_rate": 7.049180327868853e-06, "loss": 1.1975, "step": 43 }, { "epoch": 0.03636363636363636, "grad_norm": 11.584863662719727, "learning_rate": 7.213114754098361e-06, "loss": 1.1057, "step": 44 }, { "epoch": 0.0371900826446281, "grad_norm": 9.628296852111816, "learning_rate": 7.3770491803278695e-06, "loss": 1.0823, "step": 45 }, { "epoch": 0.03801652892561983, "grad_norm": 9.617013931274414, "learning_rate": 7.540983606557377e-06, "loss": 1.0447, "step": 46 }, { "epoch": 0.03884297520661157, "grad_norm": 9.079089164733887, "learning_rate": 7.704918032786886e-06, "loss": 0.9984, "step": 47 }, { "epoch": 0.03966942148760331, "grad_norm": 11.923172950744629, "learning_rate": 7.868852459016394e-06, "loss": 1.2281, "step": 48 }, { "epoch": 0.04049586776859504, "grad_norm": 15.181923866271973, "learning_rate": 8.032786885245902e-06, "loss": 1.2481, "step": 49 }, { "epoch": 0.04132231404958678, "grad_norm": 14.02413272857666, "learning_rate": 8.19672131147541e-06, "loss": 1.2116, "step": 50 }, { "epoch": 0.04214876033057851, "grad_norm": 8.739473342895508, "learning_rate": 8.360655737704919e-06, "loss": 0.7494, "step": 51 }, { "epoch": 0.04297520661157025, "grad_norm": 5.860500335693359, "learning_rate": 8.524590163934427e-06, "loss": 0.879, "step": 52 }, { "epoch": 0.043801652892561986, "grad_norm": 4.310902118682861, "learning_rate": 8.688524590163935e-06, "loss": 0.7679, "step": 53 }, { "epoch": 0.04462809917355372, "grad_norm": 3.633057117462158, "learning_rate": 8.852459016393443e-06, "loss": 0.8117, "step": 54 }, { "epoch": 0.045454545454545456, "grad_norm": 3.607675313949585, "learning_rate": 9.016393442622952e-06, "loss": 0.8434, "step": 55 }, { "epoch": 0.04628099173553719, "grad_norm": 7.013420581817627, "learning_rate": 9.18032786885246e-06, "loss": 0.9177, "step": 56 }, { "epoch": 0.047107438016528926, "grad_norm": 10.00487995147705, "learning_rate": 9.344262295081968e-06, "loss": 0.8644, "step": 57 }, { "epoch": 0.047933884297520664, "grad_norm": 10.111504554748535, "learning_rate": 9.508196721311476e-06, "loss": 0.8552, "step": 58 }, { "epoch": 0.048760330578512395, "grad_norm": 10.907903671264648, "learning_rate": 9.672131147540984e-06, "loss": 0.8684, "step": 59 }, { "epoch": 0.049586776859504134, "grad_norm": 9.939312934875488, "learning_rate": 9.836065573770493e-06, "loss": 0.8511, "step": 60 }, { "epoch": 0.050413223140495865, "grad_norm": 10.330282211303711, "learning_rate": 1e-05, "loss": 0.853, "step": 61 }, { "epoch": 0.0512396694214876, "grad_norm": 10.615926742553711, "learning_rate": 9.99998131042498e-06, "loss": 0.8483, "step": 62 }, { "epoch": 0.05206611570247934, "grad_norm": 11.617918014526367, "learning_rate": 9.99992524183964e-06, "loss": 0.8302, "step": 63 }, { "epoch": 0.05289256198347107, "grad_norm": 10.836939811706543, "learning_rate": 9.99983179466314e-06, "loss": 0.825, "step": 64 }, { "epoch": 0.05371900826446281, "grad_norm": 10.899372100830078, "learning_rate": 9.999700969594073e-06, "loss": 0.821, "step": 65 }, { "epoch": 0.05454545454545454, "grad_norm": 11.234271049499512, "learning_rate": 9.999532767610465e-06, "loss": 0.8093, "step": 66 }, { "epoch": 0.05537190082644628, "grad_norm": 8.552489280700684, "learning_rate": 9.999327189969768e-06, "loss": 0.8969, "step": 67 }, { "epoch": 0.05619834710743802, "grad_norm": 7.510222911834717, "learning_rate": 9.999084238208843e-06, "loss": 0.874, "step": 68 }, { "epoch": 0.05702479338842975, "grad_norm": 7.619356632232666, "learning_rate": 9.99880391414396e-06, "loss": 0.9021, "step": 69 }, { "epoch": 0.05785123966942149, "grad_norm": 6.904785633087158, "learning_rate": 9.998486219870769e-06, "loss": 0.8768, "step": 70 }, { "epoch": 0.05867768595041322, "grad_norm": 8.251214981079102, "learning_rate": 9.998131157764301e-06, "loss": 0.8833, "step": 71 }, { "epoch": 0.05950413223140496, "grad_norm": 7.453232765197754, "learning_rate": 9.997738730478938e-06, "loss": 0.8544, "step": 72 }, { "epoch": 0.0603305785123967, "grad_norm": 10.829845428466797, "learning_rate": 9.997308940948405e-06, "loss": 0.929, "step": 73 }, { "epoch": 0.06115702479338843, "grad_norm": 12.777321815490723, "learning_rate": 9.996841792385728e-06, "loss": 0.9576, "step": 74 }, { "epoch": 0.06198347107438017, "grad_norm": 13.181741714477539, "learning_rate": 9.996337288283236e-06, "loss": 0.9274, "step": 75 }, { "epoch": 0.0628099173553719, "grad_norm": 22.688045501708984, "learning_rate": 9.995795432412513e-06, "loss": 1.1367, "step": 76 }, { "epoch": 0.06363636363636363, "grad_norm": 9.36829662322998, "learning_rate": 9.995216228824383e-06, "loss": 0.9509, "step": 77 }, { "epoch": 0.06446280991735537, "grad_norm": 5.943204879760742, "learning_rate": 9.994599681848873e-06, "loss": 0.8382, "step": 78 }, { "epoch": 0.0652892561983471, "grad_norm": 4.420541763305664, "learning_rate": 9.993945796095183e-06, "loss": 0.7509, "step": 79 }, { "epoch": 0.06611570247933884, "grad_norm": 3.4656481742858887, "learning_rate": 9.993254576451652e-06, "loss": 0.7744, "step": 80 }, { "epoch": 0.06694214876033058, "grad_norm": 7.592845916748047, "learning_rate": 9.992526028085721e-06, "loss": 0.6749, "step": 81 }, { "epoch": 0.06776859504132231, "grad_norm": 13.7494535446167, "learning_rate": 9.991760156443892e-06, "loss": 0.697, "step": 82 }, { "epoch": 0.06859504132231405, "grad_norm": 14.44515323638916, "learning_rate": 9.990956967251692e-06, "loss": 0.7142, "step": 83 }, { "epoch": 0.06942148760330578, "grad_norm": 14.63835334777832, "learning_rate": 9.990116466513628e-06, "loss": 0.6709, "step": 84 }, { "epoch": 0.07024793388429752, "grad_norm": 15.553050994873047, "learning_rate": 9.989238660513141e-06, "loss": 0.7016, "step": 85 }, { "epoch": 0.07107438016528926, "grad_norm": 15.484620094299316, "learning_rate": 9.988323555812558e-06, "loss": 0.684, "step": 86 }, { "epoch": 0.07190082644628099, "grad_norm": 15.376058578491211, "learning_rate": 9.987371159253047e-06, "loss": 0.6672, "step": 87 }, { "epoch": 0.07272727272727272, "grad_norm": 15.391505241394043, "learning_rate": 9.98638147795456e-06, "loss": 0.6632, "step": 88 }, { "epoch": 0.07355371900826446, "grad_norm": 16.409034729003906, "learning_rate": 9.98535451931579e-06, "loss": 0.6393, "step": 89 }, { "epoch": 0.0743801652892562, "grad_norm": 15.590607643127441, "learning_rate": 9.984290291014105e-06, "loss": 0.6383, "step": 90 }, { "epoch": 0.07520661157024794, "grad_norm": 10.495964050292969, "learning_rate": 9.983188801005492e-06, "loss": 0.7488, "step": 91 }, { "epoch": 0.07603305785123966, "grad_norm": 9.75681209564209, "learning_rate": 9.982050057524505e-06, "loss": 0.7838, "step": 92 }, { "epoch": 0.0768595041322314, "grad_norm": 9.70681381225586, "learning_rate": 9.980874069084197e-06, "loss": 0.7908, "step": 93 }, { "epoch": 0.07768595041322314, "grad_norm": 9.451353073120117, "learning_rate": 9.979660844476056e-06, "loss": 0.7204, "step": 94 }, { "epoch": 0.07851239669421488, "grad_norm": 8.870857238769531, "learning_rate": 9.978410392769943e-06, "loss": 0.7342, "step": 95 }, { "epoch": 0.07933884297520662, "grad_norm": 8.990922927856445, "learning_rate": 9.977122723314026e-06, "loss": 0.6932, "step": 96 }, { "epoch": 0.08016528925619834, "grad_norm": 9.571405410766602, "learning_rate": 9.975797845734699e-06, "loss": 0.7034, "step": 97 }, { "epoch": 0.08099173553719008, "grad_norm": 15.28164005279541, "learning_rate": 9.974435769936523e-06, "loss": 0.8082, "step": 98 }, { "epoch": 0.08181818181818182, "grad_norm": 15.263097763061523, "learning_rate": 9.973036506102145e-06, "loss": 0.7938, "step": 99 }, { "epoch": 0.08264462809917356, "grad_norm": 14.575544357299805, "learning_rate": 9.971600064692222e-06, "loss": 0.7302, "step": 100 }, { "epoch": 0.0834710743801653, "grad_norm": 9.692093849182129, "learning_rate": 9.970126456445348e-06, "loss": 0.7892, "step": 101 }, { "epoch": 0.08429752066115702, "grad_norm": 6.960953235626221, "learning_rate": 9.96861569237797e-06, "loss": 0.8115, "step": 102 }, { "epoch": 0.08512396694214876, "grad_norm": 6.310975074768066, "learning_rate": 9.967067783784297e-06, "loss": 0.87, "step": 103 }, { "epoch": 0.0859504132231405, "grad_norm": 5.528263568878174, "learning_rate": 9.965482742236234e-06, "loss": 0.8227, "step": 104 }, { "epoch": 0.08677685950413223, "grad_norm": 5.674769878387451, "learning_rate": 9.963860579583284e-06, "loss": 0.8033, "step": 105 }, { "epoch": 0.08760330578512397, "grad_norm": 9.012608528137207, "learning_rate": 9.962201307952455e-06, "loss": 0.6766, "step": 106 }, { "epoch": 0.0884297520661157, "grad_norm": 14.8609619140625, "learning_rate": 9.960504939748184e-06, "loss": 0.5175, "step": 107 }, { "epoch": 0.08925619834710743, "grad_norm": 15.575093269348145, "learning_rate": 9.95877148765223e-06, "loss": 0.4785, "step": 108 }, { "epoch": 0.09008264462809917, "grad_norm": 15.258967399597168, "learning_rate": 9.957000964623585e-06, "loss": 0.4621, "step": 109 }, { "epoch": 0.09090909090909091, "grad_norm": 15.684150695800781, "learning_rate": 9.955193383898376e-06, "loss": 0.4981, "step": 110 }, { "epoch": 0.09173553719008265, "grad_norm": 14.834244728088379, "learning_rate": 9.953348758989774e-06, "loss": 0.4395, "step": 111 }, { "epoch": 0.09256198347107437, "grad_norm": 15.187931060791016, "learning_rate": 9.951467103687879e-06, "loss": 0.462, "step": 112 }, { "epoch": 0.09338842975206611, "grad_norm": 16.399118423461914, "learning_rate": 9.949548432059627e-06, "loss": 0.4867, "step": 113 }, { "epoch": 0.09421487603305785, "grad_norm": 15.177169799804688, "learning_rate": 9.94759275844868e-06, "loss": 0.4434, "step": 114 }, { "epoch": 0.09504132231404959, "grad_norm": 14.918987274169922, "learning_rate": 9.945600097475322e-06, "loss": 0.4212, "step": 115 }, { "epoch": 0.09586776859504133, "grad_norm": 15.301935195922852, "learning_rate": 9.943570464036347e-06, "loss": 0.4336, "step": 116 }, { "epoch": 0.09669421487603305, "grad_norm": 14.648711204528809, "learning_rate": 9.94150387330495e-06, "loss": 0.4064, "step": 117 }, { "epoch": 0.09752066115702479, "grad_norm": 9.166203498840332, "learning_rate": 9.939400340730611e-06, "loss": 0.6176, "step": 118 }, { "epoch": 0.09834710743801653, "grad_norm": 8.874405860900879, "learning_rate": 9.937259882038986e-06, "loss": 0.5856, "step": 119 }, { "epoch": 0.09917355371900827, "grad_norm": 9.233952522277832, "learning_rate": 9.935082513231776e-06, "loss": 0.6215, "step": 120 }, { "epoch": 0.1, "grad_norm": 8.666190147399902, "learning_rate": 9.932868250586619e-06, "loss": 0.5833, "step": 121 }, { "epoch": 0.10082644628099173, "grad_norm": 8.544061660766602, "learning_rate": 9.93061711065697e-06, "loss": 0.5457, "step": 122 }, { "epoch": 0.10165289256198347, "grad_norm": 13.043021202087402, "learning_rate": 9.928329110271967e-06, "loss": 0.6034, "step": 123 }, { "epoch": 0.1024793388429752, "grad_norm": 13.846759796142578, "learning_rate": 9.926004266536314e-06, "loss": 0.559, "step": 124 }, { "epoch": 0.10330578512396695, "grad_norm": 13.205362319946289, "learning_rate": 9.923642596830142e-06, "loss": 0.4789, "step": 125 }, { "epoch": 0.10413223140495868, "grad_norm": 4.691654205322266, "learning_rate": 9.921244118808896e-06, "loss": 0.5618, "step": 126 }, { "epoch": 0.10495867768595041, "grad_norm": 4.73344612121582, "learning_rate": 9.918808850403192e-06, "loss": 0.6367, "step": 127 }, { "epoch": 0.10578512396694215, "grad_norm": 4.595221042633057, "learning_rate": 9.916336809818679e-06, "loss": 0.6359, "step": 128 }, { "epoch": 0.10661157024793388, "grad_norm": 4.814165115356445, "learning_rate": 9.913828015535914e-06, "loss": 0.6589, "step": 129 }, { "epoch": 0.10743801652892562, "grad_norm": 4.562165260314941, "learning_rate": 9.911282486310214e-06, "loss": 0.6342, "step": 130 }, { "epoch": 0.10826446280991736, "grad_norm": 4.110449314117432, "learning_rate": 9.908700241171528e-06, "loss": 0.5926, "step": 131 }, { "epoch": 0.10909090909090909, "grad_norm": 15.924474716186523, "learning_rate": 9.906081299424276e-06, "loss": 0.3306, "step": 132 }, { "epoch": 0.10991735537190082, "grad_norm": 16.74171257019043, "learning_rate": 9.903425680647225e-06, "loss": 0.3228, "step": 133 }, { "epoch": 0.11074380165289256, "grad_norm": 16.331884384155273, "learning_rate": 9.900733404693328e-06, "loss": 0.2947, "step": 134 }, { "epoch": 0.1115702479338843, "grad_norm": 14.321427345275879, "learning_rate": 9.898004491689582e-06, "loss": 0.2559, "step": 135 }, { "epoch": 0.11239669421487604, "grad_norm": 13.67010498046875, "learning_rate": 9.895238962036878e-06, "loss": 0.2296, "step": 136 }, { "epoch": 0.11322314049586776, "grad_norm": 13.051318168640137, "learning_rate": 9.892436836409845e-06, "loss": 0.2229, "step": 137 }, { "epoch": 0.1140495867768595, "grad_norm": 13.087048530578613, "learning_rate": 9.8895981357567e-06, "loss": 0.2184, "step": 138 }, { "epoch": 0.11487603305785124, "grad_norm": 12.81165885925293, "learning_rate": 9.88672288129908e-06, "loss": 0.1808, "step": 139 }, { "epoch": 0.11570247933884298, "grad_norm": 12.778697967529297, "learning_rate": 9.883811094531906e-06, "loss": 0.1955, "step": 140 }, { "epoch": 0.11652892561983472, "grad_norm": 12.421398162841797, "learning_rate": 9.880862797223197e-06, "loss": 0.1762, "step": 141 }, { "epoch": 0.11735537190082644, "grad_norm": 12.256722450256348, "learning_rate": 9.877878011413924e-06, "loss": 0.1802, "step": 142 }, { "epoch": 0.11818181818181818, "grad_norm": 10.989577293395996, "learning_rate": 9.874856759417837e-06, "loss": 0.2245, "step": 143 }, { "epoch": 0.11900826446280992, "grad_norm": 7.684560775756836, "learning_rate": 9.871799063821303e-06, "loss": 0.4634, "step": 144 }, { "epoch": 0.11983471074380166, "grad_norm": 6.932048320770264, "learning_rate": 9.868704947483134e-06, "loss": 0.454, "step": 145 }, { "epoch": 0.1206611570247934, "grad_norm": 6.686558246612549, "learning_rate": 9.86557443353442e-06, "loss": 0.4499, "step": 146 }, { "epoch": 0.12148760330578512, "grad_norm": 5.892101764678955, "learning_rate": 9.862407545378348e-06, "loss": 0.4378, "step": 147 }, { "epoch": 0.12231404958677686, "grad_norm": 5.772195816040039, "learning_rate": 9.859204306690038e-06, "loss": 0.4666, "step": 148 }, { "epoch": 0.1231404958677686, "grad_norm": 10.375298500061035, "learning_rate": 9.855964741416355e-06, "loss": 0.3677, "step": 149 }, { "epoch": 0.12396694214876033, "grad_norm": 8.872918128967285, "learning_rate": 9.852688873775741e-06, "loss": 0.3167, "step": 150 }, { "epoch": 0.12479338842975207, "grad_norm": 6.068610668182373, "learning_rate": 9.849376728258024e-06, "loss": 0.5171, "step": 151 }, { "epoch": 0.1256198347107438, "grad_norm": 6.121888160705566, "learning_rate": 9.846028329624242e-06, "loss": 0.55, "step": 152 }, { "epoch": 0.12644628099173555, "grad_norm": 5.789841651916504, "learning_rate": 9.842643702906453e-06, "loss": 0.5124, "step": 153 }, { "epoch": 0.12727272727272726, "grad_norm": 5.199845314025879, "learning_rate": 9.839222873407553e-06, "loss": 0.5206, "step": 154 }, { "epoch": 0.128099173553719, "grad_norm": 4.326947212219238, "learning_rate": 9.835765866701079e-06, "loss": 0.5173, "step": 155 }, { "epoch": 0.12892561983471074, "grad_norm": 3.3200628757476807, "learning_rate": 9.832272708631027e-06, "loss": 0.3047, "step": 156 }, { "epoch": 0.12975206611570247, "grad_norm": 6.605825424194336, "learning_rate": 9.828743425311654e-06, "loss": 0.1155, "step": 157 }, { "epoch": 0.1305785123966942, "grad_norm": 5.040175914764404, "learning_rate": 9.825178043127279e-06, "loss": 0.0726, "step": 158 }, { "epoch": 0.13140495867768595, "grad_norm": 4.458925724029541, "learning_rate": 9.821576588732095e-06, "loss": 0.0671, "step": 159 }, { "epoch": 0.1322314049586777, "grad_norm": 4.0228776931762695, "learning_rate": 9.817939089049964e-06, "loss": 0.0618, "step": 160 }, { "epoch": 0.13305785123966943, "grad_norm": 3.98579740524292, "learning_rate": 9.814265571274215e-06, "loss": 0.0447, "step": 161 }, { "epoch": 0.13388429752066117, "grad_norm": 3.2810285091400146, "learning_rate": 9.81055606286744e-06, "loss": 0.0549, "step": 162 }, { "epoch": 0.1347107438016529, "grad_norm": 2.91422176361084, "learning_rate": 9.806810591561295e-06, "loss": 0.0535, "step": 163 }, { "epoch": 0.13553719008264462, "grad_norm": 2.663398265838623, "learning_rate": 9.803029185356286e-06, "loss": 0.0418, "step": 164 }, { "epoch": 0.13636363636363635, "grad_norm": 4.249295234680176, "learning_rate": 9.799211872521564e-06, "loss": 0.0704, "step": 165 }, { "epoch": 0.1371900826446281, "grad_norm": 4.342033863067627, "learning_rate": 9.795358681594712e-06, "loss": 0.071, "step": 166 }, { "epoch": 0.13801652892561983, "grad_norm": 5.222247123718262, "learning_rate": 9.791469641381526e-06, "loss": 0.0443, "step": 167 }, { "epoch": 0.13884297520661157, "grad_norm": 6.7554473876953125, "learning_rate": 9.787544780955815e-06, "loss": 0.5837, "step": 168 }, { "epoch": 0.1396694214876033, "grad_norm": 5.858948707580566, "learning_rate": 9.783584129659162e-06, "loss": 0.5041, "step": 169 }, { "epoch": 0.14049586776859505, "grad_norm": 3.3874192237854004, "learning_rate": 9.779587717100729e-06, "loss": 0.4407, "step": 170 }, { "epoch": 0.14132231404958678, "grad_norm": 3.474137306213379, "learning_rate": 9.775555573157016e-06, "loss": 0.4318, "step": 171 }, { "epoch": 0.14214876033057852, "grad_norm": 3.252941370010376, "learning_rate": 9.771487727971642e-06, "loss": 0.4322, "step": 172 }, { "epoch": 0.14297520661157026, "grad_norm": 3.3677756786346436, "learning_rate": 9.767384211955126e-06, "loss": 0.4496, "step": 173 }, { "epoch": 0.14380165289256197, "grad_norm": 6.583395957946777, "learning_rate": 9.763245055784663e-06, "loss": 0.3269, "step": 174 }, { "epoch": 0.1446280991735537, "grad_norm": 4.727723121643066, "learning_rate": 9.759070290403873e-06, "loss": 0.2061, "step": 175 }, { "epoch": 0.14545454545454545, "grad_norm": 6.042111873626709, "learning_rate": 9.754859947022596e-06, "loss": 0.5294, "step": 176 }, { "epoch": 0.14628099173553719, "grad_norm": 6.286961555480957, "learning_rate": 9.750614057116642e-06, "loss": 0.5713, "step": 177 }, { "epoch": 0.14710743801652892, "grad_norm": 6.675935745239258, "learning_rate": 9.746332652427566e-06, "loss": 0.5804, "step": 178 }, { "epoch": 0.14793388429752066, "grad_norm": 6.587425231933594, "learning_rate": 9.742015764962418e-06, "loss": 0.547, "step": 179 }, { "epoch": 0.1487603305785124, "grad_norm": 6.034268856048584, "learning_rate": 9.737663426993514e-06, "loss": 0.5808, "step": 180 }, { "epoch": 0.14958677685950414, "grad_norm": 3.43208384513855, "learning_rate": 9.733275671058195e-06, "loss": 0.0556, "step": 181 }, { "epoch": 0.15041322314049588, "grad_norm": 1.2211329936981201, "learning_rate": 9.728852529958579e-06, "loss": 0.0543, "step": 182 }, { "epoch": 0.15123966942148762, "grad_norm": 4.956982135772705, "learning_rate": 9.724394036761316e-06, "loss": 0.0459, "step": 183 }, { "epoch": 0.15206611570247933, "grad_norm": 2.556718587875366, "learning_rate": 9.71990022479734e-06, "loss": 0.0404, "step": 184 }, { "epoch": 0.15289256198347106, "grad_norm": 1.8153376579284668, "learning_rate": 9.715371127661632e-06, "loss": 0.0317, "step": 185 }, { "epoch": 0.1537190082644628, "grad_norm": 0.7108684778213501, "learning_rate": 9.710806779212947e-06, "loss": 0.0277, "step": 186 }, { "epoch": 0.15454545454545454, "grad_norm": 2.305515766143799, "learning_rate": 9.70620721357358e-06, "loss": 0.0455, "step": 187 }, { "epoch": 0.15537190082644628, "grad_norm": 1.716363787651062, "learning_rate": 9.7015724651291e-06, "loss": 0.0349, "step": 188 }, { "epoch": 0.15619834710743802, "grad_norm": 5.611410140991211, "learning_rate": 9.696902568528103e-06, "loss": 0.0857, "step": 189 }, { "epoch": 0.15702479338842976, "grad_norm": 2.8802907466888428, "learning_rate": 9.69219755868194e-06, "loss": 0.0507, "step": 190 }, { "epoch": 0.1578512396694215, "grad_norm": 3.974024534225464, "learning_rate": 9.68745747076446e-06, "loss": 0.2486, "step": 191 }, { "epoch": 0.15867768595041323, "grad_norm": 4.467517375946045, "learning_rate": 9.682682340211763e-06, "loss": 0.4189, "step": 192 }, { "epoch": 0.15950413223140497, "grad_norm": 4.234643459320068, "learning_rate": 9.677872202721906e-06, "loss": 0.4185, "step": 193 }, { "epoch": 0.16033057851239668, "grad_norm": 2.5838871002197266, "learning_rate": 9.673027094254663e-06, "loss": 0.3809, "step": 194 }, { "epoch": 0.16115702479338842, "grad_norm": 3.291666030883789, "learning_rate": 9.66814705103124e-06, "loss": 0.4241, "step": 195 }, { "epoch": 0.16198347107438016, "grad_norm": 2.974576473236084, "learning_rate": 9.663232109534011e-06, "loss": 0.3915, "step": 196 }, { "epoch": 0.1628099173553719, "grad_norm": 2.9471116065979004, "learning_rate": 9.658282306506242e-06, "loss": 0.3889, "step": 197 }, { "epoch": 0.16363636363636364, "grad_norm": 5.0516815185546875, "learning_rate": 9.653297678951822e-06, "loss": 0.3213, "step": 198 }, { "epoch": 0.16446280991735537, "grad_norm": 6.269105434417725, "learning_rate": 9.648278264134977e-06, "loss": 0.2461, "step": 199 }, { "epoch": 0.1652892561983471, "grad_norm": 7.234027862548828, "learning_rate": 9.643224099579997e-06, "loss": 0.2729, "step": 200 }, { "epoch": 0.16611570247933885, "grad_norm": 3.872319221496582, "learning_rate": 9.63813522307096e-06, "loss": 0.4332, "step": 201 }, { "epoch": 0.1669421487603306, "grad_norm": 3.694383382797241, "learning_rate": 9.633011672651443e-06, "loss": 0.4327, "step": 202 }, { "epoch": 0.16776859504132233, "grad_norm": 4.5347819328308105, "learning_rate": 9.627853486624234e-06, "loss": 0.3973, "step": 203 }, { "epoch": 0.16859504132231404, "grad_norm": 5.72538948059082, "learning_rate": 9.622660703551059e-06, "loss": 0.4392, "step": 204 }, { "epoch": 0.16942148760330578, "grad_norm": 5.8939409255981445, "learning_rate": 9.617433362252277e-06, "loss": 0.4358, "step": 205 }, { "epoch": 0.17024793388429751, "grad_norm": 63.848697662353516, "learning_rate": 9.612171501806606e-06, "loss": 0.5083, "step": 206 }, { "epoch": 0.17107438016528925, "grad_norm": 9.372079849243164, "learning_rate": 9.606875161550819e-06, "loss": 0.2324, "step": 207 }, { "epoch": 0.171900826446281, "grad_norm": 9.741740226745605, "learning_rate": 9.601544381079457e-06, "loss": 0.1739, "step": 208 }, { "epoch": 0.17272727272727273, "grad_norm": 5.752349376678467, "learning_rate": 9.596179200244527e-06, "loss": 0.089, "step": 209 }, { "epoch": 0.17355371900826447, "grad_norm": 1.3193517923355103, "learning_rate": 9.59077965915521e-06, "loss": 0.0507, "step": 210 }, { "epoch": 0.1743801652892562, "grad_norm": 3.0285868644714355, "learning_rate": 9.585345798177557e-06, "loss": 0.0498, "step": 211 }, { "epoch": 0.17520661157024794, "grad_norm": 9.561731338500977, "learning_rate": 9.579877657934187e-06, "loss": 0.0875, "step": 212 }, { "epoch": 0.17603305785123968, "grad_norm": 1.7362544536590576, "learning_rate": 9.574375279303989e-06, "loss": 0.0471, "step": 213 }, { "epoch": 0.1768595041322314, "grad_norm": 0.43394935131073, "learning_rate": 9.56883870342181e-06, "loss": 0.0437, "step": 214 }, { "epoch": 0.17768595041322313, "grad_norm": 1.7832210063934326, "learning_rate": 9.563267971678152e-06, "loss": 0.0515, "step": 215 }, { "epoch": 0.17851239669421487, "grad_norm": 0.40522071719169617, "learning_rate": 9.557663125718855e-06, "loss": 0.0301, "step": 216 }, { "epoch": 0.1793388429752066, "grad_norm": 1.7870750427246094, "learning_rate": 9.552024207444794e-06, "loss": 0.0491, "step": 217 }, { "epoch": 0.18016528925619835, "grad_norm": 3.0770976543426514, "learning_rate": 9.546351259011569e-06, "loss": 0.3519, "step": 218 }, { "epoch": 0.18099173553719008, "grad_norm": 1.7763985395431519, "learning_rate": 9.540644322829173e-06, "loss": 0.4262, "step": 219 }, { "epoch": 0.18181818181818182, "grad_norm": 2.929096221923828, "learning_rate": 9.534903441561693e-06, "loss": 0.4233, "step": 220 }, { "epoch": 0.18264462809917356, "grad_norm": 2.5705196857452393, "learning_rate": 9.52912865812698e-06, "loss": 0.3956, "step": 221 }, { "epoch": 0.1834710743801653, "grad_norm": 3.308143377304077, "learning_rate": 9.523320015696336e-06, "loss": 0.396, "step": 222 }, { "epoch": 0.18429752066115704, "grad_norm": 3.0954201221466064, "learning_rate": 9.517477557694182e-06, "loss": 0.3624, "step": 223 }, { "epoch": 0.18512396694214875, "grad_norm": 4.504317760467529, "learning_rate": 9.51160132779774e-06, "loss": 0.2108, "step": 224 }, { "epoch": 0.1859504132231405, "grad_norm": 4.281580924987793, "learning_rate": 9.50569136993671e-06, "loss": 0.22, "step": 225 }, { "epoch": 0.18677685950413223, "grad_norm": 5.512481689453125, "learning_rate": 9.499747728292928e-06, "loss": 0.4468, "step": 226 }, { "epoch": 0.18760330578512396, "grad_norm": 6.550302982330322, "learning_rate": 9.49377044730005e-06, "loss": 0.4252, "step": 227 }, { "epoch": 0.1884297520661157, "grad_norm": 6.840104103088379, "learning_rate": 9.48775957164321e-06, "loss": 0.431, "step": 228 }, { "epoch": 0.18925619834710744, "grad_norm": 7.467294692993164, "learning_rate": 9.481715146258699e-06, "loss": 0.4236, "step": 229 }, { "epoch": 0.19008264462809918, "grad_norm": 6.159290790557861, "learning_rate": 9.475637216333611e-06, "loss": 0.3231, "step": 230 }, { "epoch": 0.19090909090909092, "grad_norm": 0.58745276927948, "learning_rate": 9.469525827305514e-06, "loss": 0.0298, "step": 231 }, { "epoch": 0.19173553719008266, "grad_norm": 1.123795747756958, "learning_rate": 9.463381024862116e-06, "loss": 0.0211, "step": 232 }, { "epoch": 0.1925619834710744, "grad_norm": 0.49130845069885254, "learning_rate": 9.457202854940915e-06, "loss": 0.0295, "step": 233 }, { "epoch": 0.1933884297520661, "grad_norm": 0.43577098846435547, "learning_rate": 9.450991363728858e-06, "loss": 0.0192, "step": 234 }, { "epoch": 0.19421487603305784, "grad_norm": 0.9045920372009277, "learning_rate": 9.444746597662e-06, "loss": 0.0313, "step": 235 }, { "epoch": 0.19504132231404958, "grad_norm": 1.6747899055480957, "learning_rate": 9.438468603425147e-06, "loss": 0.0433, "step": 236 }, { "epoch": 0.19586776859504132, "grad_norm": 3.9514214992523193, "learning_rate": 9.432157427951521e-06, "loss": 0.0764, "step": 237 }, { "epoch": 0.19669421487603306, "grad_norm": 1.2828267812728882, "learning_rate": 9.425813118422393e-06, "loss": 0.0396, "step": 238 }, { "epoch": 0.1975206611570248, "grad_norm": 1.3975738286972046, "learning_rate": 9.419435722266745e-06, "loss": 0.0446, "step": 239 }, { "epoch": 0.19834710743801653, "grad_norm": 0.3374120891094208, "learning_rate": 9.413025287160904e-06, "loss": 0.0423, "step": 240 }, { "epoch": 0.19917355371900827, "grad_norm": 1.6610523462295532, "learning_rate": 9.406581861028199e-06, "loss": 0.0446, "step": 241 }, { "epoch": 0.2, "grad_norm": 2.999248504638672, "learning_rate": 9.40010549203858e-06, "loss": 0.1462, "step": 242 }, { "epoch": 0.20082644628099172, "grad_norm": 3.1203508377075195, "learning_rate": 9.393596228608289e-06, "loss": 0.4149, "step": 243 }, { "epoch": 0.20165289256198346, "grad_norm": 3.1315393447875977, "learning_rate": 9.387054119399466e-06, "loss": 0.4055, "step": 244 }, { "epoch": 0.2024793388429752, "grad_norm": 1.9984904527664185, "learning_rate": 9.38047921331981e-06, "loss": 0.3894, "step": 245 }, { "epoch": 0.20330578512396694, "grad_norm": 2.6335408687591553, "learning_rate": 9.373871559522203e-06, "loss": 0.3866, "step": 246 }, { "epoch": 0.20413223140495868, "grad_norm": 4.331795692443848, "learning_rate": 9.36723120740434e-06, "loss": 0.4232, "step": 247 }, { "epoch": 0.2049586776859504, "grad_norm": 3.634972333908081, "learning_rate": 9.360558206608363e-06, "loss": 0.3621, "step": 248 }, { "epoch": 0.20578512396694215, "grad_norm": 7.504141330718994, "learning_rate": 9.353852607020496e-06, "loss": 0.2442, "step": 249 }, { "epoch": 0.2066115702479339, "grad_norm": 4.689815521240234, "learning_rate": 9.347114458770656e-06, "loss": 0.2701, "step": 250 }, { "epoch": 0.20743801652892563, "grad_norm": 4.537595748901367, "learning_rate": 9.340343812232097e-06, "loss": 0.2763, "step": 251 }, { "epoch": 0.20826446280991737, "grad_norm": 5.105134010314941, "learning_rate": 9.333540718021024e-06, "loss": 0.3415, "step": 252 }, { "epoch": 0.20909090909090908, "grad_norm": 5.4744672775268555, "learning_rate": 9.326705226996207e-06, "loss": 0.3494, "step": 253 }, { "epoch": 0.20991735537190082, "grad_norm": 5.980065822601318, "learning_rate": 9.319837390258619e-06, "loss": 0.3448, "step": 254 }, { "epoch": 0.21074380165289255, "grad_norm": 5.463247776031494, "learning_rate": 9.31293725915104e-06, "loss": 0.377, "step": 255 }, { "epoch": 0.2115702479338843, "grad_norm": 2.519472360610962, "learning_rate": 9.306004885257675e-06, "loss": 0.195, "step": 256 }, { "epoch": 0.21239669421487603, "grad_norm": 4.671911716461182, "learning_rate": 9.299040320403775e-06, "loss": 0.056, "step": 257 }, { "epoch": 0.21322314049586777, "grad_norm": 4.731037616729736, "learning_rate": 9.29204361665524e-06, "loss": 0.051, "step": 258 }, { "epoch": 0.2140495867768595, "grad_norm": 2.2982873916625977, "learning_rate": 9.28501482631824e-06, "loss": 0.0481, "step": 259 }, { "epoch": 0.21487603305785125, "grad_norm": 1.7563531398773193, "learning_rate": 9.277954001938819e-06, "loss": 0.0406, "step": 260 }, { "epoch": 0.21570247933884298, "grad_norm": 1.352148413658142, "learning_rate": 9.270861196302494e-06, "loss": 0.0319, "step": 261 }, { "epoch": 0.21652892561983472, "grad_norm": 1.9197131395339966, "learning_rate": 9.26373646243388e-06, "loss": 0.0522, "step": 262 }, { "epoch": 0.21735537190082643, "grad_norm": 0.9207364916801453, "learning_rate": 9.256579853596273e-06, "loss": 0.0385, "step": 263 }, { "epoch": 0.21818181818181817, "grad_norm": 0.5068424940109253, "learning_rate": 9.249391423291263e-06, "loss": 0.0193, "step": 264 }, { "epoch": 0.2190082644628099, "grad_norm": 0.37090161442756653, "learning_rate": 9.242171225258336e-06, "loss": 0.019, "step": 265 }, { "epoch": 0.21983471074380165, "grad_norm": 3.5917792320251465, "learning_rate": 9.234919313474463e-06, "loss": 0.0792, "step": 266 }, { "epoch": 0.2206611570247934, "grad_norm": 3.6245150566101074, "learning_rate": 9.227635742153706e-06, "loss": 0.0796, "step": 267 }, { "epoch": 0.22148760330578512, "grad_norm": 4.045724391937256, "learning_rate": 9.220320565746806e-06, "loss": 0.3782, "step": 268 }, { "epoch": 0.22231404958677686, "grad_norm": 2.375504493713379, "learning_rate": 9.212973838940775e-06, "loss": 0.3738, "step": 269 }, { "epoch": 0.2231404958677686, "grad_norm": 3.42677903175354, "learning_rate": 9.205595616658495e-06, "loss": 0.384, "step": 270 }, { "epoch": 0.22396694214876034, "grad_norm": 2.2642056941986084, "learning_rate": 9.198185954058305e-06, "loss": 0.3928, "step": 271 }, { "epoch": 0.22479338842975208, "grad_norm": 1.6667097806930542, "learning_rate": 9.190744906533578e-06, "loss": 0.3812, "step": 272 }, { "epoch": 0.2256198347107438, "grad_norm": 2.662670373916626, "learning_rate": 9.183272529712324e-06, "loss": 0.3177, "step": 273 }, { "epoch": 0.22644628099173553, "grad_norm": 5.033318519592285, "learning_rate": 9.175768879456759e-06, "loss": 0.2818, "step": 274 }, { "epoch": 0.22727272727272727, "grad_norm": 4.880688667297363, "learning_rate": 9.168234011862899e-06, "loss": 0.3027, "step": 275 }, { "epoch": 0.228099173553719, "grad_norm": 4.188443660736084, "learning_rate": 9.160667983260133e-06, "loss": 0.2788, "step": 276 }, { "epoch": 0.22892561983471074, "grad_norm": 4.407473564147949, "learning_rate": 9.153070850210803e-06, "loss": 0.3406, "step": 277 }, { "epoch": 0.22975206611570248, "grad_norm": 4.778233051300049, "learning_rate": 9.145442669509787e-06, "loss": 0.3387, "step": 278 }, { "epoch": 0.23057851239669422, "grad_norm": 5.0951948165893555, "learning_rate": 9.137783498184065e-06, "loss": 0.265, "step": 279 }, { "epoch": 0.23140495867768596, "grad_norm": 4.966414928436279, "learning_rate": 9.130093393492302e-06, "loss": 0.328, "step": 280 }, { "epoch": 0.2322314049586777, "grad_norm": 2.2104508876800537, "learning_rate": 9.122372412924409e-06, "loss": 0.1631, "step": 281 }, { "epoch": 0.23305785123966943, "grad_norm": 1.512752652168274, "learning_rate": 9.11462061420113e-06, "loss": 0.0115, "step": 282 }, { "epoch": 0.23388429752066114, "grad_norm": 0.32136648893356323, "learning_rate": 9.106838055273589e-06, "loss": 0.0283, "step": 283 }, { "epoch": 0.23471074380165288, "grad_norm": 2.3555853366851807, "learning_rate": 9.099024794322874e-06, "loss": 0.0563, "step": 284 }, { "epoch": 0.23553719008264462, "grad_norm": 0.3243228495121002, "learning_rate": 9.091180889759602e-06, "loss": 0.0285, "step": 285 }, { "epoch": 0.23636363636363636, "grad_norm": 0.7489374876022339, "learning_rate": 9.083306400223465e-06, "loss": 0.0369, "step": 286 }, { "epoch": 0.2371900826446281, "grad_norm": 1.0486401319503784, "learning_rate": 9.07540138458281e-06, "loss": 0.021, "step": 287 }, { "epoch": 0.23801652892561984, "grad_norm": 2.7049810886383057, "learning_rate": 9.067465901934187e-06, "loss": 0.0607, "step": 288 }, { "epoch": 0.23884297520661157, "grad_norm": 0.3670910596847534, "learning_rate": 9.059500011601919e-06, "loss": 0.0366, "step": 289 }, { "epoch": 0.2396694214876033, "grad_norm": 0.8055985569953918, "learning_rate": 9.051503773137647e-06, "loss": 0.03, "step": 290 }, { "epoch": 0.24049586776859505, "grad_norm": 1.4885363578796387, "learning_rate": 9.043477246319888e-06, "loss": 0.0497, "step": 291 }, { "epoch": 0.2413223140495868, "grad_norm": 1.1092013120651245, "learning_rate": 9.035420491153596e-06, "loss": 0.03, "step": 292 }, { "epoch": 0.2421487603305785, "grad_norm": 2.9742510318756104, "learning_rate": 9.0273335678697e-06, "loss": 0.3492, "step": 293 }, { "epoch": 0.24297520661157024, "grad_norm": 5.270508766174316, "learning_rate": 9.019216536924667e-06, "loss": 0.4273, "step": 294 }, { "epoch": 0.24380165289256198, "grad_norm": 3.1606504917144775, "learning_rate": 9.011069459000035e-06, "loss": 0.4114, "step": 295 }, { "epoch": 0.24462809917355371, "grad_norm": 1.8900291919708252, "learning_rate": 9.002892395001978e-06, "loss": 0.3572, "step": 296 }, { "epoch": 0.24545454545454545, "grad_norm": 2.238032817840576, "learning_rate": 8.994685406060837e-06, "loss": 0.3574, "step": 297 }, { "epoch": 0.2462809917355372, "grad_norm": 92.95574951171875, "learning_rate": 8.986448553530665e-06, "loss": 0.3824, "step": 298 }, { "epoch": 0.24710743801652893, "grad_norm": 5.979159355163574, "learning_rate": 8.978181898988769e-06, "loss": 0.3624, "step": 299 }, { "epoch": 0.24793388429752067, "grad_norm": 6.447382926940918, "learning_rate": 8.969885504235257e-06, "loss": 0.2805, "step": 300 }, { "epoch": 0.2487603305785124, "grad_norm": 3.386467456817627, "learning_rate": 8.961559431292562e-06, "loss": 0.3139, "step": 301 }, { "epoch": 0.24958677685950414, "grad_norm": 3.9054369926452637, "learning_rate": 8.953203742404992e-06, "loss": 0.295, "step": 302 }, { "epoch": 0.25041322314049586, "grad_norm": 4.136813163757324, "learning_rate": 8.944818500038257e-06, "loss": 0.3177, "step": 303 }, { "epoch": 0.2512396694214876, "grad_norm": 4.501168251037598, "learning_rate": 8.936403766879003e-06, "loss": 0.3008, "step": 304 }, { "epoch": 0.25206611570247933, "grad_norm": 3.8915162086486816, "learning_rate": 8.927959605834347e-06, "loss": 0.3187, "step": 305 }, { "epoch": 0.2528925619834711, "grad_norm": 1.2882620096206665, "learning_rate": 8.919486080031396e-06, "loss": 0.0303, "step": 306 }, { "epoch": 0.2537190082644628, "grad_norm": 0.6544731855392456, "learning_rate": 8.910983252816794e-06, "loss": 0.042, "step": 307 }, { "epoch": 0.2545454545454545, "grad_norm": 3.0191237926483154, "learning_rate": 8.902451187756228e-06, "loss": 0.0595, "step": 308 }, { "epoch": 0.2553719008264463, "grad_norm": 0.4694916009902954, "learning_rate": 8.893889948633968e-06, "loss": 0.0364, "step": 309 }, { "epoch": 0.256198347107438, "grad_norm": 2.781498670578003, "learning_rate": 8.885299599452381e-06, "loss": 0.0192, "step": 310 }, { "epoch": 0.25702479338842976, "grad_norm": 2.27006459236145, "learning_rate": 8.87668020443146e-06, "loss": 0.055, "step": 311 }, { "epoch": 0.2578512396694215, "grad_norm": 1.341349482536316, "learning_rate": 8.868031828008335e-06, "loss": 0.0481, "step": 312 }, { "epoch": 0.25867768595041324, "grad_norm": 0.654566764831543, "learning_rate": 8.859354534836797e-06, "loss": 0.0345, "step": 313 }, { "epoch": 0.25950413223140495, "grad_norm": 0.23261475563049316, "learning_rate": 8.850648389786816e-06, "loss": 0.0412, "step": 314 }, { "epoch": 0.2603305785123967, "grad_norm": 0.9180927872657776, "learning_rate": 8.841913457944053e-06, "loss": 0.0364, "step": 315 }, { "epoch": 0.2611570247933884, "grad_norm": 1.1271486282348633, "learning_rate": 8.833149804609372e-06, "loss": 0.1013, "step": 316 }, { "epoch": 0.2619834710743802, "grad_norm": 2.27287220954895, "learning_rate": 8.824357495298357e-06, "loss": 0.382, "step": 317 }, { "epoch": 0.2628099173553719, "grad_norm": 1.9736340045928955, "learning_rate": 8.815536595740817e-06, "loss": 0.3783, "step": 318 }, { "epoch": 0.2636363636363636, "grad_norm": 1.994823932647705, "learning_rate": 8.806687171880298e-06, "loss": 0.3282, "step": 319 }, { "epoch": 0.2644628099173554, "grad_norm": 2.0439600944519043, "learning_rate": 8.797809289873587e-06, "loss": 0.3704, "step": 320 }, { "epoch": 0.2652892561983471, "grad_norm": 2.0953407287597656, "learning_rate": 8.788903016090222e-06, "loss": 0.3623, "step": 321 }, { "epoch": 0.26611570247933886, "grad_norm": 2.216618061065674, "learning_rate": 8.779968417111991e-06, "loss": 0.3766, "step": 322 }, { "epoch": 0.26694214876033057, "grad_norm": 3.6057472229003906, "learning_rate": 8.77100555973244e-06, "loss": 0.2765, "step": 323 }, { "epoch": 0.26776859504132233, "grad_norm": 5.107512474060059, "learning_rate": 8.762014510956364e-06, "loss": 0.1966, "step": 324 }, { "epoch": 0.26859504132231404, "grad_norm": 4.891761302947998, "learning_rate": 8.752995337999316e-06, "loss": 0.2237, "step": 325 }, { "epoch": 0.2694214876033058, "grad_norm": 3.0789847373962402, "learning_rate": 8.7439481082871e-06, "loss": 0.2562, "step": 326 }, { "epoch": 0.2702479338842975, "grad_norm": 3.5382838249206543, "learning_rate": 8.734872889455268e-06, "loss": 0.3514, "step": 327 }, { "epoch": 0.27107438016528923, "grad_norm": 3.313929319381714, "learning_rate": 8.725769749348612e-06, "loss": 0.2989, "step": 328 }, { "epoch": 0.271900826446281, "grad_norm": 3.3161957263946533, "learning_rate": 8.716638756020661e-06, "loss": 0.2757, "step": 329 }, { "epoch": 0.2727272727272727, "grad_norm": 2.9451427459716797, "learning_rate": 8.70747997773317e-06, "loss": 0.2653, "step": 330 }, { "epoch": 0.2735537190082645, "grad_norm": 1.3499524593353271, "learning_rate": 8.698293482955605e-06, "loss": 0.1402, "step": 331 }, { "epoch": 0.2743801652892562, "grad_norm": 0.2829076647758484, "learning_rate": 8.689079340364644e-06, "loss": 0.0275, "step": 332 }, { "epoch": 0.27520661157024795, "grad_norm": 1.4667352437973022, "learning_rate": 8.679837618843646e-06, "loss": 0.0432, "step": 333 }, { "epoch": 0.27603305785123966, "grad_norm": 0.31224325299263, "learning_rate": 8.670568387482153e-06, "loss": 0.0289, "step": 334 }, { "epoch": 0.2768595041322314, "grad_norm": 0.32508960366249084, "learning_rate": 8.661271715575364e-06, "loss": 0.0285, "step": 335 }, { "epoch": 0.27768595041322314, "grad_norm": 1.3324801921844482, "learning_rate": 8.651947672623613e-06, "loss": 0.0428, "step": 336 }, { "epoch": 0.2785123966942149, "grad_norm": 2.0843026638031006, "learning_rate": 8.642596328331864e-06, "loss": 0.0513, "step": 337 }, { "epoch": 0.2793388429752066, "grad_norm": 2.3382153511047363, "learning_rate": 8.633217752609177e-06, "loss": 0.0531, "step": 338 }, { "epoch": 0.2801652892561983, "grad_norm": 1.6505120992660522, "learning_rate": 8.62381201556819e-06, "loss": 0.0308, "step": 339 }, { "epoch": 0.2809917355371901, "grad_norm": 0.4468664824962616, "learning_rate": 8.614379187524593e-06, "loss": 0.0395, "step": 340 }, { "epoch": 0.2818181818181818, "grad_norm": 0.6637183427810669, "learning_rate": 8.604919338996604e-06, "loss": 0.0419, "step": 341 }, { "epoch": 0.28264462809917357, "grad_norm": 1.43661367893219, "learning_rate": 8.595432540704446e-06, "loss": 0.0762, "step": 342 }, { "epoch": 0.2834710743801653, "grad_norm": 6.637901306152344, "learning_rate": 8.585918863569806e-06, "loss": 0.4814, "step": 343 }, { "epoch": 0.28429752066115704, "grad_norm": 3.622053861618042, "learning_rate": 8.576378378715322e-06, "loss": 0.4324, "step": 344 }, { "epoch": 0.28512396694214875, "grad_norm": 3.3516077995300293, "learning_rate": 8.566811157464032e-06, "loss": 0.3595, "step": 345 }, { "epoch": 0.2859504132231405, "grad_norm": 2.02554988861084, "learning_rate": 8.55721727133886e-06, "loss": 0.358, "step": 346 }, { "epoch": 0.28677685950413223, "grad_norm": 1.4861034154891968, "learning_rate": 8.547596792062064e-06, "loss": 0.3432, "step": 347 }, { "epoch": 0.28760330578512394, "grad_norm": 2.7921857833862305, "learning_rate": 8.537949791554714e-06, "loss": 0.348, "step": 348 }, { "epoch": 0.2884297520661157, "grad_norm": 2.5079729557037354, "learning_rate": 8.528276341936146e-06, "loss": 0.1366, "step": 349 }, { "epoch": 0.2892561983471074, "grad_norm": 2.7155003547668457, "learning_rate": 8.518576515523423e-06, "loss": 0.0867, "step": 350 }, { "epoch": 0.2900826446280992, "grad_norm": 3.2388157844543457, "learning_rate": 8.5088503848308e-06, "loss": 0.3211, "step": 351 }, { "epoch": 0.2909090909090909, "grad_norm": 3.136592388153076, "learning_rate": 8.499098022569177e-06, "loss": 0.3195, "step": 352 }, { "epoch": 0.29173553719008266, "grad_norm": 2.751568555831909, "learning_rate": 8.489319501645555e-06, "loss": 0.3294, "step": 353 }, { "epoch": 0.29256198347107437, "grad_norm": 2.539821147918701, "learning_rate": 8.479514895162495e-06, "loss": 0.3024, "step": 354 }, { "epoch": 0.29338842975206614, "grad_norm": 2.4179089069366455, "learning_rate": 8.469684276417568e-06, "loss": 0.2638, "step": 355 }, { "epoch": 0.29421487603305785, "grad_norm": 1.5124740600585938, "learning_rate": 8.459827718902809e-06, "loss": 0.1416, "step": 356 }, { "epoch": 0.2950413223140496, "grad_norm": 0.4755104184150696, "learning_rate": 8.449945296304168e-06, "loss": 0.0341, "step": 357 }, { "epoch": 0.2958677685950413, "grad_norm": 1.8088937997817993, "learning_rate": 8.440037082500953e-06, "loss": 0.0441, "step": 358 }, { "epoch": 0.29669421487603304, "grad_norm": 0.7109810709953308, "learning_rate": 8.430103151565288e-06, "loss": 0.0354, "step": 359 }, { "epoch": 0.2975206611570248, "grad_norm": 1.2697234153747559, "learning_rate": 8.420143577761551e-06, "loss": 0.0484, "step": 360 }, { "epoch": 0.2983471074380165, "grad_norm": 3.0426182746887207, "learning_rate": 8.410158435545825e-06, "loss": 0.0266, "step": 361 }, { "epoch": 0.2991735537190083, "grad_norm": 1.5594433546066284, "learning_rate": 8.400147799565334e-06, "loss": 0.0401, "step": 362 }, { "epoch": 0.3, "grad_norm": 0.2366088181734085, "learning_rate": 8.390111744657892e-06, "loss": 0.0389, "step": 363 }, { "epoch": 0.30082644628099175, "grad_norm": 2.7218143939971924, "learning_rate": 8.380050345851338e-06, "loss": 0.0249, "step": 364 }, { "epoch": 0.30165289256198347, "grad_norm": 1.1584035158157349, "learning_rate": 8.369963678362978e-06, "loss": 0.0298, "step": 365 }, { "epoch": 0.30247933884297523, "grad_norm": 1.1925641298294067, "learning_rate": 8.359851817599027e-06, "loss": 0.0384, "step": 366 }, { "epoch": 0.30330578512396694, "grad_norm": 12.5698823928833, "learning_rate": 8.349714839154035e-06, "loss": 0.697, "step": 367 }, { "epoch": 0.30413223140495865, "grad_norm": 7.502256393432617, "learning_rate": 8.33955281881033e-06, "loss": 0.5348, "step": 368 }, { "epoch": 0.3049586776859504, "grad_norm": 4.12613582611084, "learning_rate": 8.329365832537448e-06, "loss": 0.4117, "step": 369 }, { "epoch": 0.30578512396694213, "grad_norm": 3.4762847423553467, "learning_rate": 8.319153956491567e-06, "loss": 0.3757, "step": 370 }, { "epoch": 0.3066115702479339, "grad_norm": 2.2697415351867676, "learning_rate": 8.30891726701494e-06, "loss": 0.3732, "step": 371 }, { "epoch": 0.3074380165289256, "grad_norm": 1.9594049453735352, "learning_rate": 8.298655840635312e-06, "loss": 0.3448, "step": 372 }, { "epoch": 0.3082644628099174, "grad_norm": 3.9964828491210938, "learning_rate": 8.288369754065362e-06, "loss": 0.2701, "step": 373 }, { "epoch": 0.3090909090909091, "grad_norm": 13.04822826385498, "learning_rate": 8.27805908420213e-06, "loss": 0.2767, "step": 374 }, { "epoch": 0.30991735537190085, "grad_norm": 3.762925386428833, "learning_rate": 8.267723908126429e-06, "loss": 0.1487, "step": 375 }, { "epoch": 0.31074380165289256, "grad_norm": 3.9099831581115723, "learning_rate": 8.257364303102275e-06, "loss": 0.3413, "step": 376 }, { "epoch": 0.31157024793388427, "grad_norm": 3.8278796672821045, "learning_rate": 8.246980346576318e-06, "loss": 0.413, "step": 377 }, { "epoch": 0.31239669421487604, "grad_norm": 3.016062021255493, "learning_rate": 8.236572116177249e-06, "loss": 0.3472, "step": 378 }, { "epoch": 0.31322314049586775, "grad_norm": 2.7905495166778564, "learning_rate": 8.226139689715233e-06, "loss": 0.3401, "step": 379 }, { "epoch": 0.3140495867768595, "grad_norm": 2.2101759910583496, "learning_rate": 8.215683145181312e-06, "loss": 0.3386, "step": 380 }, { "epoch": 0.3148760330578512, "grad_norm": 2.5770349502563477, "learning_rate": 8.205202560746839e-06, "loss": 0.2139, "step": 381 }, { "epoch": 0.315702479338843, "grad_norm": 4.9263176918029785, "learning_rate": 8.19469801476288e-06, "loss": 0.0844, "step": 382 }, { "epoch": 0.3165289256198347, "grad_norm": 4.758224964141846, "learning_rate": 8.184169585759637e-06, "loss": 0.0798, "step": 383 }, { "epoch": 0.31735537190082647, "grad_norm": 2.611168384552002, "learning_rate": 8.173617352445853e-06, "loss": 0.0515, "step": 384 }, { "epoch": 0.3181818181818182, "grad_norm": 0.4771171510219574, "learning_rate": 8.16304139370823e-06, "loss": 0.0329, "step": 385 }, { "epoch": 0.31900826446280994, "grad_norm": 0.5978302955627441, "learning_rate": 8.152441788610843e-06, "loss": 0.0378, "step": 386 }, { "epoch": 0.31983471074380165, "grad_norm": 1.672168493270874, "learning_rate": 8.14181861639453e-06, "loss": 0.0294, "step": 387 }, { "epoch": 0.32066115702479336, "grad_norm": 1.892396092414856, "learning_rate": 8.131171956476328e-06, "loss": 0.0346, "step": 388 }, { "epoch": 0.32148760330578513, "grad_norm": 1.5014523267745972, "learning_rate": 8.120501888448853e-06, "loss": 0.0335, "step": 389 }, { "epoch": 0.32231404958677684, "grad_norm": 0.538657009601593, "learning_rate": 8.109808492079718e-06, "loss": 0.0443, "step": 390 }, { "epoch": 0.3231404958677686, "grad_norm": 1.1847418546676636, "learning_rate": 8.09909184731094e-06, "loss": 0.0446, "step": 391 }, { "epoch": 0.3239669421487603, "grad_norm": 1.2937194108963013, "learning_rate": 8.088352034258331e-06, "loss": 0.0664, "step": 392 }, { "epoch": 0.3247933884297521, "grad_norm": 3.5774083137512207, "learning_rate": 8.07758913321091e-06, "loss": 0.4166, "step": 393 }, { "epoch": 0.3256198347107438, "grad_norm": 2.8276569843292236, "learning_rate": 8.066803224630295e-06, "loss": 0.3945, "step": 394 }, { "epoch": 0.32644628099173556, "grad_norm": 2.874321460723877, "learning_rate": 8.055994389150103e-06, "loss": 0.3916, "step": 395 }, { "epoch": 0.32727272727272727, "grad_norm": 2.9290878772735596, "learning_rate": 8.045162707575354e-06, "loss": 0.3915, "step": 396 }, { "epoch": 0.328099173553719, "grad_norm": 2.229264736175537, "learning_rate": 8.034308260881854e-06, "loss": 0.376, "step": 397 }, { "epoch": 0.32892561983471075, "grad_norm": 2.684750556945801, "learning_rate": 8.023431130215605e-06, "loss": 0.2773, "step": 398 }, { "epoch": 0.32975206611570246, "grad_norm": 4.131373882293701, "learning_rate": 8.012531396892185e-06, "loss": 0.1928, "step": 399 }, { "epoch": 0.3305785123966942, "grad_norm": 4.172529220581055, "learning_rate": 8.00160914239615e-06, "loss": 0.1928, "step": 400 }, { "epoch": 0.33140495867768593, "grad_norm": 3.6504626274108887, "learning_rate": 7.990664448380412e-06, "loss": 0.3092, "step": 401 }, { "epoch": 0.3322314049586777, "grad_norm": 3.3628780841827393, "learning_rate": 7.979697396665649e-06, "loss": 0.3061, "step": 402 }, { "epoch": 0.3330578512396694, "grad_norm": 2.5712125301361084, "learning_rate": 7.968708069239672e-06, "loss": 0.3091, "step": 403 }, { "epoch": 0.3338842975206612, "grad_norm": 2.4374077320098877, "learning_rate": 7.957696548256828e-06, "loss": 0.3066, "step": 404 }, { "epoch": 0.3347107438016529, "grad_norm": 1.896844506263733, "learning_rate": 7.946662916037373e-06, "loss": 0.2612, "step": 405 }, { "epoch": 0.33553719008264465, "grad_norm": 2.1051249504089355, "learning_rate": 7.935607255066867e-06, "loss": 0.2337, "step": 406 }, { "epoch": 0.33636363636363636, "grad_norm": 2.1041512489318848, "learning_rate": 7.924529647995549e-06, "loss": 0.0331, "step": 407 }, { "epoch": 0.3371900826446281, "grad_norm": 0.5802683234214783, "learning_rate": 7.91343017763773e-06, "loss": 0.0364, "step": 408 }, { "epoch": 0.33801652892561984, "grad_norm": 1.2897307872772217, "learning_rate": 7.902308926971166e-06, "loss": 0.0326, "step": 409 }, { "epoch": 0.33884297520661155, "grad_norm": 0.9003844857215881, "learning_rate": 7.891165979136429e-06, "loss": 0.0304, "step": 410 }, { "epoch": 0.3396694214876033, "grad_norm": 1.9420896768569946, "learning_rate": 7.880001417436309e-06, "loss": 0.0398, "step": 411 }, { "epoch": 0.34049586776859503, "grad_norm": 0.36469870805740356, "learning_rate": 7.868815325335168e-06, "loss": 0.0266, "step": 412 }, { "epoch": 0.3413223140495868, "grad_norm": 2.06129789352417, "learning_rate": 7.857607786458333e-06, "loss": 0.0349, "step": 413 }, { "epoch": 0.3421487603305785, "grad_norm": 0.9527754187583923, "learning_rate": 7.846378884591453e-06, "loss": 0.0349, "step": 414 }, { "epoch": 0.34297520661157027, "grad_norm": 0.9972708225250244, "learning_rate": 7.835128703679896e-06, "loss": 0.0303, "step": 415 }, { "epoch": 0.343801652892562, "grad_norm": 0.874220609664917, "learning_rate": 7.823857327828099e-06, "loss": 0.0369, "step": 416 }, { "epoch": 0.3446280991735537, "grad_norm": 1.980294942855835, "learning_rate": 7.812564841298951e-06, "loss": 0.2549, "step": 417 }, { "epoch": 0.34545454545454546, "grad_norm": 2.404195785522461, "learning_rate": 7.801251328513164e-06, "loss": 0.356, "step": 418 }, { "epoch": 0.34628099173553717, "grad_norm": 1.9718644618988037, "learning_rate": 7.789916874048635e-06, "loss": 0.3155, "step": 419 }, { "epoch": 0.34710743801652894, "grad_norm": 1.9457886219024658, "learning_rate": 7.778561562639818e-06, "loss": 0.3523, "step": 420 }, { "epoch": 0.34793388429752065, "grad_norm": 1.6577038764953613, "learning_rate": 7.767185479177092e-06, "loss": 0.3394, "step": 421 }, { "epoch": 0.3487603305785124, "grad_norm": 2.429166316986084, "learning_rate": 7.755788708706124e-06, "loss": 0.3466, "step": 422 }, { "epoch": 0.3495867768595041, "grad_norm": 2.4249932765960693, "learning_rate": 7.744371336427232e-06, "loss": 0.3099, "step": 423 }, { "epoch": 0.3504132231404959, "grad_norm": 4.010801792144775, "learning_rate": 7.732933447694748e-06, "loss": 0.1718, "step": 424 }, { "epoch": 0.3512396694214876, "grad_norm": 4.168816089630127, "learning_rate": 7.721475128016388e-06, "loss": 0.1702, "step": 425 }, { "epoch": 0.35206611570247937, "grad_norm": 4.439835548400879, "learning_rate": 7.709996463052595e-06, "loss": 0.3233, "step": 426 }, { "epoch": 0.3528925619834711, "grad_norm": 2.153748035430908, "learning_rate": 7.698497538615928e-06, "loss": 0.2434, "step": 427 }, { "epoch": 0.3537190082644628, "grad_norm": 2.1145215034484863, "learning_rate": 7.68697844067038e-06, "loss": 0.2965, "step": 428 }, { "epoch": 0.35454545454545455, "grad_norm": 2.3973615169525146, "learning_rate": 7.675439255330778e-06, "loss": 0.3022, "step": 429 }, { "epoch": 0.35537190082644626, "grad_norm": 1.741687297821045, "learning_rate": 7.663880068862106e-06, "loss": 0.268, "step": 430 }, { "epoch": 0.35619834710743803, "grad_norm": 1.714586615562439, "learning_rate": 7.652300967678873e-06, "loss": 0.2504, "step": 431 }, { "epoch": 0.35702479338842974, "grad_norm": 4.339986324310303, "learning_rate": 7.64070203834448e-06, "loss": 0.0494, "step": 432 }, { "epoch": 0.3578512396694215, "grad_norm": 1.6370694637298584, "learning_rate": 7.629083367570547e-06, "loss": 0.0485, "step": 433 }, { "epoch": 0.3586776859504132, "grad_norm": 1.0893810987472534, "learning_rate": 7.617445042216278e-06, "loss": 0.0538, "step": 434 }, { "epoch": 0.359504132231405, "grad_norm": 0.8672933578491211, "learning_rate": 7.605787149287819e-06, "loss": 0.0374, "step": 435 }, { "epoch": 0.3603305785123967, "grad_norm": 1.5140106678009033, "learning_rate": 7.594109775937595e-06, "loss": 0.0381, "step": 436 }, { "epoch": 0.3611570247933884, "grad_norm": 0.7423667311668396, "learning_rate": 7.582413009463664e-06, "loss": 0.0254, "step": 437 }, { "epoch": 0.36198347107438017, "grad_norm": 1.1572518348693848, "learning_rate": 7.570696937309063e-06, "loss": 0.0403, "step": 438 }, { "epoch": 0.3628099173553719, "grad_norm": 0.2780013382434845, "learning_rate": 7.558961647061156e-06, "loss": 0.028, "step": 439 }, { "epoch": 0.36363636363636365, "grad_norm": 0.9868566393852234, "learning_rate": 7.54720722645098e-06, "loss": 0.0397, "step": 440 }, { "epoch": 0.36446280991735536, "grad_norm": 0.16371887922286987, "learning_rate": 7.535433763352582e-06, "loss": 0.0299, "step": 441 }, { "epoch": 0.3652892561983471, "grad_norm": 0.5445317029953003, "learning_rate": 7.5236413457823745e-06, "loss": 0.0297, "step": 442 }, { "epoch": 0.36611570247933883, "grad_norm": 1.8789058923721313, "learning_rate": 7.5118300618984626e-06, "loss": 0.1932, "step": 443 }, { "epoch": 0.3669421487603306, "grad_norm": 3.1089491844177246, "learning_rate": 7.500000000000001e-06, "loss": 0.3663, "step": 444 }, { "epoch": 0.3677685950413223, "grad_norm": 2.2975223064422607, "learning_rate": 7.488151248526518e-06, "loss": 0.3487, "step": 445 }, { "epoch": 0.3685950413223141, "grad_norm": 1.9807140827178955, "learning_rate": 7.476283896057267e-06, "loss": 0.3603, "step": 446 }, { "epoch": 0.3694214876033058, "grad_norm": 2.565408945083618, "learning_rate": 7.464398031310557e-06, "loss": 0.3417, "step": 447 }, { "epoch": 0.3702479338842975, "grad_norm": 1.854609727859497, "learning_rate": 7.452493743143092e-06, "loss": 0.3216, "step": 448 }, { "epoch": 0.37107438016528926, "grad_norm": 3.2579827308654785, "learning_rate": 7.440571120549309e-06, "loss": 0.2039, "step": 449 }, { "epoch": 0.371900826446281, "grad_norm": 3.3291921615600586, "learning_rate": 7.428630252660705e-06, "loss": 0.1672, "step": 450 }, { "epoch": 0.37272727272727274, "grad_norm": 3.157149314880371, "learning_rate": 7.416671228745181e-06, "loss": 0.2773, "step": 451 }, { "epoch": 0.37355371900826445, "grad_norm": 3.1166951656341553, "learning_rate": 7.404694138206365e-06, "loss": 0.3119, "step": 452 }, { "epoch": 0.3743801652892562, "grad_norm": 2.574794292449951, "learning_rate": 7.392699070582951e-06, "loss": 0.2579, "step": 453 }, { "epoch": 0.3752066115702479, "grad_norm": 2.3687548637390137, "learning_rate": 7.380686115548024e-06, "loss": 0.2731, "step": 454 }, { "epoch": 0.3760330578512397, "grad_norm": 2.1777918338775635, "learning_rate": 7.368655362908394e-06, "loss": 0.2474, "step": 455 }, { "epoch": 0.3768595041322314, "grad_norm": 2.160825252532959, "learning_rate": 7.356606902603924e-06, "loss": 0.0972, "step": 456 }, { "epoch": 0.3776859504132231, "grad_norm": 2.5094244480133057, "learning_rate": 7.344540824706855e-06, "loss": 0.0494, "step": 457 }, { "epoch": 0.3785123966942149, "grad_norm": 2.2549567222595215, "learning_rate": 7.332457219421132e-06, "loss": 0.0236, "step": 458 }, { "epoch": 0.3793388429752066, "grad_norm": 1.3993778228759766, "learning_rate": 7.320356177081737e-06, "loss": 0.0475, "step": 459 }, { "epoch": 0.38016528925619836, "grad_norm": 0.7870197296142578, "learning_rate": 7.3082377881540025e-06, "loss": 0.0415, "step": 460 }, { "epoch": 0.38099173553719007, "grad_norm": 2.217742681503296, "learning_rate": 7.296102143232948e-06, "loss": 0.0312, "step": 461 }, { "epoch": 0.38181818181818183, "grad_norm": 2.3126964569091797, "learning_rate": 7.283949333042586e-06, "loss": 0.0421, "step": 462 }, { "epoch": 0.38264462809917354, "grad_norm": 0.3075319826602936, "learning_rate": 7.271779448435265e-06, "loss": 0.0286, "step": 463 }, { "epoch": 0.3834710743801653, "grad_norm": 0.5313308835029602, "learning_rate": 7.259592580390973e-06, "loss": 0.0358, "step": 464 }, { "epoch": 0.384297520661157, "grad_norm": 1.1876845359802246, "learning_rate": 7.247388820016662e-06, "loss": 0.0233, "step": 465 }, { "epoch": 0.3851239669421488, "grad_norm": 1.1241205930709839, "learning_rate": 7.235168258545569e-06, "loss": 0.022, "step": 466 }, { "epoch": 0.3859504132231405, "grad_norm": 2.0038743019104004, "learning_rate": 7.222930987336537e-06, "loss": 0.3091, "step": 467 }, { "epoch": 0.3867768595041322, "grad_norm": 2.349743366241455, "learning_rate": 7.2106770978733245e-06, "loss": 0.3662, "step": 468 }, { "epoch": 0.387603305785124, "grad_norm": 2.8394381999969482, "learning_rate": 7.198406681763925e-06, "loss": 0.3628, "step": 469 }, { "epoch": 0.3884297520661157, "grad_norm": 1.7794013023376465, "learning_rate": 7.186119830739883e-06, "loss": 0.3424, "step": 470 }, { "epoch": 0.38925619834710745, "grad_norm": 2.329651117324829, "learning_rate": 7.173816636655611e-06, "loss": 0.3216, "step": 471 }, { "epoch": 0.39008264462809916, "grad_norm": 1.83986496925354, "learning_rate": 7.161497191487693e-06, "loss": 0.3321, "step": 472 }, { "epoch": 0.39090909090909093, "grad_norm": 5.495357513427734, "learning_rate": 7.149161587334209e-06, "loss": 0.2219, "step": 473 }, { "epoch": 0.39173553719008264, "grad_norm": 4.695106506347656, "learning_rate": 7.136809916414039e-06, "loss": 0.1977, "step": 474 }, { "epoch": 0.3925619834710744, "grad_norm": 3.4635348320007324, "learning_rate": 7.124442271066174e-06, "loss": 0.1271, "step": 475 }, { "epoch": 0.3933884297520661, "grad_norm": 2.077944278717041, "learning_rate": 7.112058743749029e-06, "loss": 0.2443, "step": 476 }, { "epoch": 0.3942148760330578, "grad_norm": 2.1625986099243164, "learning_rate": 7.099659427039748e-06, "loss": 0.2568, "step": 477 }, { "epoch": 0.3950413223140496, "grad_norm": 1.8367973566055298, "learning_rate": 7.087244413633516e-06, "loss": 0.2249, "step": 478 }, { "epoch": 0.3958677685950413, "grad_norm": 1.918242335319519, "learning_rate": 7.074813796342862e-06, "loss": 0.2373, "step": 479 }, { "epoch": 0.39669421487603307, "grad_norm": 1.9061918258666992, "learning_rate": 7.062367668096968e-06, "loss": 0.2482, "step": 480 }, { "epoch": 0.3975206611570248, "grad_norm": 2.2743890285491943, "learning_rate": 7.049906121940974e-06, "loss": 0.0971, "step": 481 }, { "epoch": 0.39834710743801655, "grad_norm": 3.9464023113250732, "learning_rate": 7.037429251035279e-06, "loss": 0.0721, "step": 482 }, { "epoch": 0.39917355371900826, "grad_norm": 2.1820228099823, "learning_rate": 7.024937148654851e-06, "loss": 0.0372, "step": 483 }, { "epoch": 0.4, "grad_norm": 1.9354735612869263, "learning_rate": 7.012429908188523e-06, "loss": 0.0299, "step": 484 }, { "epoch": 0.40082644628099173, "grad_norm": 0.6434481739997864, "learning_rate": 6.999907623138296e-06, "loss": 0.024, "step": 485 }, { "epoch": 0.40165289256198344, "grad_norm": 0.2833828032016754, "learning_rate": 6.987370387118649e-06, "loss": 0.0389, "step": 486 }, { "epoch": 0.4024793388429752, "grad_norm": 0.3582015931606293, "learning_rate": 6.9748182938558225e-06, "loss": 0.0277, "step": 487 }, { "epoch": 0.4033057851239669, "grad_norm": 1.452950119972229, "learning_rate": 6.962251437187136e-06, "loss": 0.0389, "step": 488 }, { "epoch": 0.4041322314049587, "grad_norm": 0.47023990750312805, "learning_rate": 6.94966991106027e-06, "loss": 0.0217, "step": 489 }, { "epoch": 0.4049586776859504, "grad_norm": 0.49028366804122925, "learning_rate": 6.937073809532581e-06, "loss": 0.034, "step": 490 }, { "epoch": 0.40578512396694216, "grad_norm": 1.0381807088851929, "learning_rate": 6.924463226770376e-06, "loss": 0.0393, "step": 491 }, { "epoch": 0.4066115702479339, "grad_norm": 3.151425838470459, "learning_rate": 6.9118382570482316e-06, "loss": 0.3636, "step": 492 }, { "epoch": 0.40743801652892564, "grad_norm": 3.0906147956848145, "learning_rate": 6.899198994748274e-06, "loss": 0.3854, "step": 493 }, { "epoch": 0.40826446280991735, "grad_norm": 3.547203779220581, "learning_rate": 6.886545534359481e-06, "loss": 0.3912, "step": 494 }, { "epoch": 0.4090909090909091, "grad_norm": 2.5733325481414795, "learning_rate": 6.873877970476971e-06, "loss": 0.3503, "step": 495 }, { "epoch": 0.4099173553719008, "grad_norm": 2.8231985569000244, "learning_rate": 6.861196397801297e-06, "loss": 0.3479, "step": 496 }, { "epoch": 0.41074380165289254, "grad_norm": 1.7183728218078613, "learning_rate": 6.848500911137741e-06, "loss": 0.3072, "step": 497 }, { "epoch": 0.4115702479338843, "grad_norm": 4.216372489929199, "learning_rate": 6.835791605395606e-06, "loss": 0.1683, "step": 498 }, { "epoch": 0.412396694214876, "grad_norm": 3.251147985458374, "learning_rate": 6.823068575587496e-06, "loss": 0.1218, "step": 499 }, { "epoch": 0.4132231404958678, "grad_norm": 3.297546863555908, "learning_rate": 6.810331916828623e-06, "loss": 0.1202, "step": 500 }, { "epoch": 0.4140495867768595, "grad_norm": 1.731645107269287, "learning_rate": 6.797581724336081e-06, "loss": 0.2167, "step": 501 }, { "epoch": 0.41487603305785126, "grad_norm": 1.6075807809829712, "learning_rate": 6.784818093428144e-06, "loss": 0.2393, "step": 502 }, { "epoch": 0.41570247933884297, "grad_norm": 1.5941764116287231, "learning_rate": 6.772041119523545e-06, "loss": 0.2669, "step": 503 }, { "epoch": 0.41652892561983473, "grad_norm": 1.527315616607666, "learning_rate": 6.759250898140768e-06, "loss": 0.2266, "step": 504 }, { "epoch": 0.41735537190082644, "grad_norm": 0.7751933336257935, "learning_rate": 6.746447524897335e-06, "loss": 0.1128, "step": 505 }, { "epoch": 0.41818181818181815, "grad_norm": 1.885209321975708, "learning_rate": 6.733631095509088e-06, "loss": 0.0168, "step": 506 }, { "epoch": 0.4190082644628099, "grad_norm": 0.5803923606872559, "learning_rate": 6.720801705789475e-06, "loss": 0.0353, "step": 507 }, { "epoch": 0.41983471074380163, "grad_norm": 1.829307198524475, "learning_rate": 6.70795945164883e-06, "loss": 0.0259, "step": 508 }, { "epoch": 0.4206611570247934, "grad_norm": 0.3436581790447235, "learning_rate": 6.695104429093665e-06, "loss": 0.0191, "step": 509 }, { "epoch": 0.4214876033057851, "grad_norm": 0.5622700452804565, "learning_rate": 6.682236734225944e-06, "loss": 0.0169, "step": 510 }, { "epoch": 0.4223140495867769, "grad_norm": 1.0006561279296875, "learning_rate": 6.6693564632423626e-06, "loss": 0.0232, "step": 511 }, { "epoch": 0.4231404958677686, "grad_norm": 1.1930370330810547, "learning_rate": 6.65646371243364e-06, "loss": 0.0313, "step": 512 }, { "epoch": 0.42396694214876035, "grad_norm": 0.5112296938896179, "learning_rate": 6.643558578183787e-06, "loss": 0.0195, "step": 513 }, { "epoch": 0.42479338842975206, "grad_norm": 0.444097638130188, "learning_rate": 6.630641156969397e-06, "loss": 0.0252, "step": 514 }, { "epoch": 0.4256198347107438, "grad_norm": 0.6078004240989685, "learning_rate": 6.617711545358913e-06, "loss": 0.0214, "step": 515 }, { "epoch": 0.42644628099173554, "grad_norm": 1.4289065599441528, "learning_rate": 6.604769840011913e-06, "loss": 0.166, "step": 516 }, { "epoch": 0.42727272727272725, "grad_norm": 3.11472749710083, "learning_rate": 6.591816137678388e-06, "loss": 0.3878, "step": 517 }, { "epoch": 0.428099173553719, "grad_norm": 2.7481777667999268, "learning_rate": 6.578850535198015e-06, "loss": 0.3846, "step": 518 }, { "epoch": 0.4289256198347107, "grad_norm": 2.9360082149505615, "learning_rate": 6.565873129499431e-06, "loss": 0.3568, "step": 519 }, { "epoch": 0.4297520661157025, "grad_norm": 2.3579049110412598, "learning_rate": 6.552884017599517e-06, "loss": 0.3653, "step": 520 }, { "epoch": 0.4305785123966942, "grad_norm": 2.295041561126709, "learning_rate": 6.539883296602663e-06, "loss": 0.3499, "step": 521 }, { "epoch": 0.43140495867768597, "grad_norm": 2.4445390701293945, "learning_rate": 6.526871063700056e-06, "loss": 0.3592, "step": 522 }, { "epoch": 0.4322314049586777, "grad_norm": 3.2918050289154053, "learning_rate": 6.513847416168929e-06, "loss": 0.2361, "step": 523 }, { "epoch": 0.43305785123966944, "grad_norm": 4.195345401763916, "learning_rate": 6.500812451371862e-06, "loss": 0.1436, "step": 524 }, { "epoch": 0.43388429752066116, "grad_norm": 3.297032117843628, "learning_rate": 6.487766266756034e-06, "loss": 0.1245, "step": 525 }, { "epoch": 0.43471074380165287, "grad_norm": 2.270808696746826, "learning_rate": 6.474708959852504e-06, "loss": 0.1972, "step": 526 }, { "epoch": 0.43553719008264463, "grad_norm": 1.552821159362793, "learning_rate": 6.461640628275479e-06, "loss": 0.182, "step": 527 }, { "epoch": 0.43636363636363634, "grad_norm": 1.368065357208252, "learning_rate": 6.4485613697215835e-06, "loss": 0.1916, "step": 528 }, { "epoch": 0.4371900826446281, "grad_norm": 1.2759222984313965, "learning_rate": 6.435471281969133e-06, "loss": 0.1963, "step": 529 }, { "epoch": 0.4380165289256198, "grad_norm": 1.387843132019043, "learning_rate": 6.422370462877396e-06, "loss": 0.1878, "step": 530 }, { "epoch": 0.4388429752066116, "grad_norm": 1.299856185913086, "learning_rate": 6.409259010385871e-06, "loss": 0.2002, "step": 531 }, { "epoch": 0.4396694214876033, "grad_norm": 2.0802321434020996, "learning_rate": 6.396137022513545e-06, "loss": 0.094, "step": 532 }, { "epoch": 0.44049586776859506, "grad_norm": 1.1367005109786987, "learning_rate": 6.383004597358173e-06, "loss": 0.0304, "step": 533 }, { "epoch": 0.4413223140495868, "grad_norm": 2.08708119392395, "learning_rate": 6.369861833095531e-06, "loss": 0.0341, "step": 534 }, { "epoch": 0.44214876033057854, "grad_norm": 0.6207039952278137, "learning_rate": 6.3567088279786885e-06, "loss": 0.0213, "step": 535 }, { "epoch": 0.44297520661157025, "grad_norm": 1.192789077758789, "learning_rate": 6.343545680337278e-06, "loss": 0.0459, "step": 536 }, { "epoch": 0.44380165289256196, "grad_norm": 0.8067427277565002, "learning_rate": 6.330372488576754e-06, "loss": 0.0433, "step": 537 }, { "epoch": 0.4446280991735537, "grad_norm": 1.9640798568725586, "learning_rate": 6.317189351177657e-06, "loss": 0.0272, "step": 538 }, { "epoch": 0.44545454545454544, "grad_norm": 0.7341052889823914, "learning_rate": 6.303996366694882e-06, "loss": 0.0336, "step": 539 }, { "epoch": 0.4462809917355372, "grad_norm": 2.3869376182556152, "learning_rate": 6.29079363375694e-06, "loss": 0.0281, "step": 540 }, { "epoch": 0.4471074380165289, "grad_norm": 0.5138152837753296, "learning_rate": 6.277581251065217e-06, "loss": 0.0137, "step": 541 }, { "epoch": 0.4479338842975207, "grad_norm": 0.961467444896698, "learning_rate": 6.264359317393238e-06, "loss": 0.0315, "step": 542 }, { "epoch": 0.4487603305785124, "grad_norm": 3.061131000518799, "learning_rate": 6.251127931585933e-06, "loss": 0.326, "step": 543 }, { "epoch": 0.44958677685950416, "grad_norm": 2.2784407138824463, "learning_rate": 6.237887192558894e-06, "loss": 0.3668, "step": 544 }, { "epoch": 0.45041322314049587, "grad_norm": 3.0723907947540283, "learning_rate": 6.224637199297633e-06, "loss": 0.3496, "step": 545 }, { "epoch": 0.4512396694214876, "grad_norm": 2.5650062561035156, "learning_rate": 6.211378050856851e-06, "loss": 0.3412, "step": 546 }, { "epoch": 0.45206611570247934, "grad_norm": 2.559699058532715, "learning_rate": 6.198109846359682e-06, "loss": 0.3237, "step": 547 }, { "epoch": 0.45289256198347105, "grad_norm": 2.000291347503662, "learning_rate": 6.184832684996972e-06, "loss": 0.1759, "step": 548 }, { "epoch": 0.4537190082644628, "grad_norm": 3.068333625793457, "learning_rate": 6.171546666026522e-06, "loss": 0.0822, "step": 549 }, { "epoch": 0.45454545454545453, "grad_norm": 2.272804021835327, "learning_rate": 6.15825188877235e-06, "loss": 0.0864, "step": 550 }, { "epoch": 0.4553719008264463, "grad_norm": 1.6852322816848755, "learning_rate": 6.14494845262395e-06, "loss": 0.2012, "step": 551 }, { "epoch": 0.456198347107438, "grad_norm": 1.5493943691253662, "learning_rate": 6.13163645703555e-06, "loss": 0.1797, "step": 552 }, { "epoch": 0.4570247933884298, "grad_norm": 1.5561745166778564, "learning_rate": 6.118316001525368e-06, "loss": 0.2018, "step": 553 }, { "epoch": 0.4578512396694215, "grad_norm": 1.6809978485107422, "learning_rate": 6.104987185674863e-06, "loss": 0.2751, "step": 554 }, { "epoch": 0.45867768595041325, "grad_norm": 1.4814178943634033, "learning_rate": 6.091650109127994e-06, "loss": 0.2003, "step": 555 }, { "epoch": 0.45950413223140496, "grad_norm": 1.6107033491134644, "learning_rate": 6.078304871590485e-06, "loss": 0.084, "step": 556 }, { "epoch": 0.46033057851239667, "grad_norm": 2.6868271827697754, "learning_rate": 6.064951572829057e-06, "loss": 0.0216, "step": 557 }, { "epoch": 0.46115702479338844, "grad_norm": 1.9302111864089966, "learning_rate": 6.051590312670703e-06, "loss": 0.0299, "step": 558 }, { "epoch": 0.46198347107438015, "grad_norm": 1.8653727769851685, "learning_rate": 6.038221191001935e-06, "loss": 0.0292, "step": 559 }, { "epoch": 0.4628099173553719, "grad_norm": 3.6712772846221924, "learning_rate": 6.024844307768032e-06, "loss": 0.053, "step": 560 }, { "epoch": 0.4636363636363636, "grad_norm": 1.1558465957641602, "learning_rate": 6.011459762972299e-06, "loss": 0.0361, "step": 561 }, { "epoch": 0.4644628099173554, "grad_norm": 1.1140830516815186, "learning_rate": 5.998067656675318e-06, "loss": 0.0198, "step": 562 }, { "epoch": 0.4652892561983471, "grad_norm": 1.9024033546447754, "learning_rate": 5.984668088994199e-06, "loss": 0.0231, "step": 563 }, { "epoch": 0.46611570247933887, "grad_norm": 1.3747286796569824, "learning_rate": 5.9712611601018325e-06, "loss": 0.0303, "step": 564 }, { "epoch": 0.4669421487603306, "grad_norm": 0.42153114080429077, "learning_rate": 5.95784697022614e-06, "loss": 0.0126, "step": 565 }, { "epoch": 0.4677685950413223, "grad_norm": 0.48093897104263306, "learning_rate": 5.944425619649324e-06, "loss": 0.0097, "step": 566 }, { "epoch": 0.46859504132231405, "grad_norm": 0.18579694628715515, "learning_rate": 5.93099720870712e-06, "loss": 0.0073, "step": 567 }, { "epoch": 0.46942148760330576, "grad_norm": 1.9562228918075562, "learning_rate": 5.917561837788046e-06, "loss": 0.312, "step": 568 }, { "epoch": 0.47024793388429753, "grad_norm": 2.367879867553711, "learning_rate": 5.9041196073326515e-06, "loss": 0.3458, "step": 569 }, { "epoch": 0.47107438016528924, "grad_norm": 3.0242204666137695, "learning_rate": 5.8906706178327645e-06, "loss": 0.3189, "step": 570 }, { "epoch": 0.471900826446281, "grad_norm": 2.0471577644348145, "learning_rate": 5.877214969830746e-06, "loss": 0.3315, "step": 571 }, { "epoch": 0.4727272727272727, "grad_norm": 1.714192509651184, "learning_rate": 5.863752763918732e-06, "loss": 0.3171, "step": 572 }, { "epoch": 0.4735537190082645, "grad_norm": 1.4090819358825684, "learning_rate": 5.850284100737888e-06, "loss": 0.0729, "step": 573 }, { "epoch": 0.4743801652892562, "grad_norm": 2.7457051277160645, "learning_rate": 5.836809080977644e-06, "loss": 0.0727, "step": 574 }, { "epoch": 0.47520661157024796, "grad_norm": 3.2199480533599854, "learning_rate": 5.823327805374965e-06, "loss": 0.0987, "step": 575 }, { "epoch": 0.47603305785123967, "grad_norm": 1.385063648223877, "learning_rate": 5.809840374713571e-06, "loss": 0.1563, "step": 576 }, { "epoch": 0.4768595041322314, "grad_norm": 1.3922051191329956, "learning_rate": 5.7963468898232026e-06, "loss": 0.1555, "step": 577 }, { "epoch": 0.47768595041322315, "grad_norm": 1.4770236015319824, "learning_rate": 5.782847451578858e-06, "loss": 0.1544, "step": 578 }, { "epoch": 0.47851239669421486, "grad_norm": 1.353073239326477, "learning_rate": 5.769342160900043e-06, "loss": 0.1651, "step": 579 }, { "epoch": 0.4793388429752066, "grad_norm": 1.4431830644607544, "learning_rate": 5.755831118750016e-06, "loss": 0.1884, "step": 580 }, { "epoch": 0.48016528925619834, "grad_norm": 3.3073036670684814, "learning_rate": 5.742314426135029e-06, "loss": 0.0547, "step": 581 }, { "epoch": 0.4809917355371901, "grad_norm": 2.851544141769409, "learning_rate": 5.72879218410358e-06, "loss": 0.0537, "step": 582 }, { "epoch": 0.4818181818181818, "grad_norm": 4.026706695556641, "learning_rate": 5.715264493745652e-06, "loss": 0.0868, "step": 583 }, { "epoch": 0.4826446280991736, "grad_norm": 0.9649466276168823, "learning_rate": 5.701731456191958e-06, "loss": 0.0381, "step": 584 }, { "epoch": 0.4834710743801653, "grad_norm": 2.706048011779785, "learning_rate": 5.688193172613185e-06, "loss": 0.0601, "step": 585 }, { "epoch": 0.484297520661157, "grad_norm": 1.5482417345046997, "learning_rate": 5.6746497442192425e-06, "loss": 0.0287, "step": 586 }, { "epoch": 0.48512396694214877, "grad_norm": 2.6702229976654053, "learning_rate": 5.661101272258498e-06, "loss": 0.0711, "step": 587 }, { "epoch": 0.4859504132231405, "grad_norm": 0.5972803235054016, "learning_rate": 5.6475478580170214e-06, "loss": 0.0175, "step": 588 }, { "epoch": 0.48677685950413224, "grad_norm": 0.9942319989204407, "learning_rate": 5.633989602817837e-06, "loss": 0.0137, "step": 589 }, { "epoch": 0.48760330578512395, "grad_norm": 0.47811320424079895, "learning_rate": 5.620426608020156e-06, "loss": 0.0154, "step": 590 }, { "epoch": 0.4884297520661157, "grad_norm": 1.1594573259353638, "learning_rate": 5.606858975018621e-06, "loss": 0.0263, "step": 591 }, { "epoch": 0.48925619834710743, "grad_norm": 1.1246296167373657, "learning_rate": 5.593286805242549e-06, "loss": 0.1428, "step": 592 }, { "epoch": 0.4900826446280992, "grad_norm": 1.6759182214736938, "learning_rate": 5.5797102001551754e-06, "loss": 0.3093, "step": 593 }, { "epoch": 0.4909090909090909, "grad_norm": 1.9099022150039673, "learning_rate": 5.56612926125289e-06, "loss": 0.2813, "step": 594 }, { "epoch": 0.49173553719008267, "grad_norm": 2.161968469619751, "learning_rate": 5.552544090064487e-06, "loss": 0.2854, "step": 595 }, { "epoch": 0.4925619834710744, "grad_norm": 1.4985226392745972, "learning_rate": 5.538954788150395e-06, "loss": 0.3048, "step": 596 }, { "epoch": 0.4933884297520661, "grad_norm": 1.5315203666687012, "learning_rate": 5.525361457101923e-06, "loss": 0.3304, "step": 597 }, { "epoch": 0.49421487603305786, "grad_norm": 2.184929609298706, "learning_rate": 5.5117641985405055e-06, "loss": 0.1432, "step": 598 }, { "epoch": 0.49504132231404957, "grad_norm": 4.860492706298828, "learning_rate": 5.498163114116935e-06, "loss": 0.1237, "step": 599 }, { "epoch": 0.49586776859504134, "grad_norm": 2.90765380859375, "learning_rate": 5.484558305510609e-06, "loss": 0.0469, "step": 600 }, { "epoch": 0.49669421487603305, "grad_norm": 1.3841009140014648, "learning_rate": 5.47094987442876e-06, "loss": 0.1817, "step": 601 }, { "epoch": 0.4975206611570248, "grad_norm": 1.580209732055664, "learning_rate": 5.4573379226057086e-06, "loss": 0.1466, "step": 602 }, { "epoch": 0.4983471074380165, "grad_norm": 1.6098315715789795, "learning_rate": 5.4437225518020905e-06, "loss": 0.1735, "step": 603 }, { "epoch": 0.4991735537190083, "grad_norm": 1.4930258989334106, "learning_rate": 5.430103863804107e-06, "loss": 0.1803, "step": 604 }, { "epoch": 0.5, "grad_norm": 1.2915822267532349, "learning_rate": 5.416481960422748e-06, "loss": 0.1534, "step": 605 }, { "epoch": 0.5008264462809917, "grad_norm": 3.545429229736328, "learning_rate": 5.402856943493053e-06, "loss": 0.0449, "step": 606 }, { "epoch": 0.5016528925619834, "grad_norm": 3.1343140602111816, "learning_rate": 5.389228914873334e-06, "loss": 0.0363, "step": 607 }, { "epoch": 0.5024793388429752, "grad_norm": 3.4123377799987793, "learning_rate": 5.37559797644441e-06, "loss": 0.0515, "step": 608 }, { "epoch": 0.503305785123967, "grad_norm": 4.493556976318359, "learning_rate": 5.361964230108863e-06, "loss": 0.0548, "step": 609 }, { "epoch": 0.5041322314049587, "grad_norm": 3.2441487312316895, "learning_rate": 5.348327777790262e-06, "loss": 0.0565, "step": 610 }, { "epoch": 0.5049586776859504, "grad_norm": 2.693488597869873, "learning_rate": 5.334688721432409e-06, "loss": 0.0302, "step": 611 }, { "epoch": 0.5057851239669422, "grad_norm": 2.91070556640625, "learning_rate": 5.321047162998568e-06, "loss": 0.0402, "step": 612 }, { "epoch": 0.5066115702479339, "grad_norm": 0.9602301716804504, "learning_rate": 5.307403204470711e-06, "loss": 0.017, "step": 613 }, { "epoch": 0.5074380165289256, "grad_norm": 1.2631757259368896, "learning_rate": 5.293756947848755e-06, "loss": 0.016, "step": 614 }, { "epoch": 0.5082644628099173, "grad_norm": 0.46631762385368347, "learning_rate": 5.280108495149792e-06, "loss": 0.0139, "step": 615 }, { "epoch": 0.509090909090909, "grad_norm": 0.5036705136299133, "learning_rate": 5.266457948407336e-06, "loss": 0.0292, "step": 616 }, { "epoch": 0.5099173553719009, "grad_norm": 1.4803212881088257, "learning_rate": 5.252805409670554e-06, "loss": 0.18, "step": 617 }, { "epoch": 0.5107438016528926, "grad_norm": 2.6057372093200684, "learning_rate": 5.239150981003502e-06, "loss": 0.3133, "step": 618 }, { "epoch": 0.5115702479338843, "grad_norm": 1.715753436088562, "learning_rate": 5.2254947644843735e-06, "loss": 0.3183, "step": 619 }, { "epoch": 0.512396694214876, "grad_norm": 2.21403431892395, "learning_rate": 5.211836862204716e-06, "loss": 0.3027, "step": 620 }, { "epoch": 0.5132231404958678, "grad_norm": 2.1005899906158447, "learning_rate": 5.198177376268686e-06, "loss": 0.3099, "step": 621 }, { "epoch": 0.5140495867768595, "grad_norm": 2.234964370727539, "learning_rate": 5.18451640879228e-06, "loss": 0.2785, "step": 622 }, { "epoch": 0.5148760330578512, "grad_norm": 1.8259047269821167, "learning_rate": 5.1708540619025695e-06, "loss": 0.313, "step": 623 }, { "epoch": 0.515702479338843, "grad_norm": 4.017728805541992, "learning_rate": 5.157190437736935e-06, "loss": 0.1181, "step": 624 }, { "epoch": 0.5165289256198347, "grad_norm": 3.953747272491455, "learning_rate": 5.14352563844231e-06, "loss": 0.1302, "step": 625 }, { "epoch": 0.5173553719008265, "grad_norm": 1.2031114101409912, "learning_rate": 5.12985976617441e-06, "loss": 0.1742, "step": 626 }, { "epoch": 0.5181818181818182, "grad_norm": 1.241931676864624, "learning_rate": 5.1161929230969735e-06, "loss": 0.1661, "step": 627 }, { "epoch": 0.5190082644628099, "grad_norm": 1.359976053237915, "learning_rate": 5.1025252113809945e-06, "loss": 0.1765, "step": 628 }, { "epoch": 0.5198347107438016, "grad_norm": 1.1254280805587769, "learning_rate": 5.088856733203964e-06, "loss": 0.1451, "step": 629 }, { "epoch": 0.5206611570247934, "grad_norm": 1.0555247068405151, "learning_rate": 5.075187590749101e-06, "loss": 0.136, "step": 630 }, { "epoch": 0.5214876033057851, "grad_norm": 1.1446833610534668, "learning_rate": 5.061517886204592e-06, "loss": 0.1514, "step": 631 }, { "epoch": 0.5223140495867769, "grad_norm": 1.4794870615005493, "learning_rate": 5.047847721762821e-06, "loss": 0.0363, "step": 632 }, { "epoch": 0.5231404958677686, "grad_norm": 1.28078293800354, "learning_rate": 5.034177199619617e-06, "loss": 0.0114, "step": 633 }, { "epoch": 0.5239669421487604, "grad_norm": 2.1705374717712402, "learning_rate": 5.02050642197348e-06, "loss": 0.0521, "step": 634 }, { "epoch": 0.5247933884297521, "grad_norm": 0.7478830814361572, "learning_rate": 5.0068354910248165e-06, "loss": 0.0124, "step": 635 }, { "epoch": 0.5256198347107438, "grad_norm": 2.4068710803985596, "learning_rate": 4.993164508975184e-06, "loss": 0.0518, "step": 636 }, { "epoch": 0.5264462809917355, "grad_norm": 0.6064580082893372, "learning_rate": 4.979493578026523e-06, "loss": 0.0089, "step": 637 }, { "epoch": 0.5272727272727272, "grad_norm": 1.025275468826294, "learning_rate": 4.9658228003803835e-06, "loss": 0.0148, "step": 638 }, { "epoch": 0.528099173553719, "grad_norm": 1.3405190706253052, "learning_rate": 4.95215227823718e-06, "loss": 0.0366, "step": 639 }, { "epoch": 0.5289256198347108, "grad_norm": 0.8973997831344604, "learning_rate": 4.9384821137954106e-06, "loss": 0.019, "step": 640 }, { "epoch": 0.5297520661157025, "grad_norm": 6.026678085327148, "learning_rate": 4.924812409250899e-06, "loss": 0.1754, "step": 641 }, { "epoch": 0.5305785123966942, "grad_norm": 3.6006736755371094, "learning_rate": 4.911143266796038e-06, "loss": 0.3595, "step": 642 }, { "epoch": 0.531404958677686, "grad_norm": 1.8200002908706665, "learning_rate": 4.897474788619007e-06, "loss": 0.3225, "step": 643 }, { "epoch": 0.5322314049586777, "grad_norm": 2.401529312133789, "learning_rate": 4.883807076903029e-06, "loss": 0.3139, "step": 644 }, { "epoch": 0.5330578512396694, "grad_norm": 2.6860947608947754, "learning_rate": 4.870140233825592e-06, "loss": 0.2982, "step": 645 }, { "epoch": 0.5338842975206611, "grad_norm": 2.095231533050537, "learning_rate": 4.856474361557692e-06, "loss": 0.358, "step": 646 }, { "epoch": 0.5347107438016528, "grad_norm": 2.205946922302246, "learning_rate": 4.842809562263066e-06, "loss": 0.2445, "step": 647 }, { "epoch": 0.5355371900826447, "grad_norm": 3.7042648792266846, "learning_rate": 4.829145938097431e-06, "loss": 0.1261, "step": 648 }, { "epoch": 0.5363636363636364, "grad_norm": 3.2817203998565674, "learning_rate": 4.815483591207721e-06, "loss": 0.0743, "step": 649 }, { "epoch": 0.5371900826446281, "grad_norm": 3.1411526203155518, "learning_rate": 4.801822623731316e-06, "loss": 0.118, "step": 650 }, { "epoch": 0.5380165289256198, "grad_norm": 1.0231245756149292, "learning_rate": 4.788163137795286e-06, "loss": 0.1141, "step": 651 }, { "epoch": 0.5388429752066116, "grad_norm": 1.2480162382125854, "learning_rate": 4.774505235515628e-06, "loss": 0.1867, "step": 652 }, { "epoch": 0.5396694214876033, "grad_norm": 1.3538585901260376, "learning_rate": 4.760849018996499e-06, "loss": 0.1798, "step": 653 }, { "epoch": 0.540495867768595, "grad_norm": 1.2146517038345337, "learning_rate": 4.747194590329449e-06, "loss": 0.189, "step": 654 }, { "epoch": 0.5413223140495868, "grad_norm": 1.1301908493041992, "learning_rate": 4.733542051592665e-06, "loss": 0.1696, "step": 655 }, { "epoch": 0.5421487603305785, "grad_norm": 1.6396489143371582, "learning_rate": 4.719891504850209e-06, "loss": 0.1014, "step": 656 }, { "epoch": 0.5429752066115703, "grad_norm": 1.99111807346344, "learning_rate": 4.706243052151248e-06, "loss": 0.0498, "step": 657 }, { "epoch": 0.543801652892562, "grad_norm": 2.122771739959717, "learning_rate": 4.69259679552929e-06, "loss": 0.0399, "step": 658 }, { "epoch": 0.5446280991735537, "grad_norm": 1.1913613080978394, "learning_rate": 4.6789528370014335e-06, "loss": 0.0445, "step": 659 }, { "epoch": 0.5454545454545454, "grad_norm": 1.2134239673614502, "learning_rate": 4.665311278567593e-06, "loss": 0.0373, "step": 660 }, { "epoch": 0.5462809917355372, "grad_norm": 1.2265779972076416, "learning_rate": 4.651672222209738e-06, "loss": 0.0203, "step": 661 }, { "epoch": 0.547107438016529, "grad_norm": 0.5269374847412109, "learning_rate": 4.638035769891139e-06, "loss": 0.0216, "step": 662 }, { "epoch": 0.5479338842975207, "grad_norm": 1.136293888092041, "learning_rate": 4.624402023555592e-06, "loss": 0.0124, "step": 663 }, { "epoch": 0.5487603305785124, "grad_norm": 0.42652571201324463, "learning_rate": 4.6107710851266695e-06, "loss": 0.0102, "step": 664 }, { "epoch": 0.5495867768595041, "grad_norm": 0.3615831732749939, "learning_rate": 4.597143056506947e-06, "loss": 0.0024, "step": 665 }, { "epoch": 0.5504132231404959, "grad_norm": 0.703677237033844, "learning_rate": 4.583518039577253e-06, "loss": 0.0113, "step": 666 }, { "epoch": 0.5512396694214876, "grad_norm": 1.7550630569458008, "learning_rate": 4.5698961361958955e-06, "loss": 0.032, "step": 667 }, { "epoch": 0.5520661157024793, "grad_norm": 1.8069919347763062, "learning_rate": 4.556277448197909e-06, "loss": 0.181, "step": 668 }, { "epoch": 0.552892561983471, "grad_norm": 2.0002801418304443, "learning_rate": 4.542662077394292e-06, "loss": 0.3471, "step": 669 }, { "epoch": 0.5537190082644629, "grad_norm": 1.8980375528335571, "learning_rate": 4.529050125571241e-06, "loss": 0.3243, "step": 670 }, { "epoch": 0.5545454545454546, "grad_norm": 2.2224647998809814, "learning_rate": 4.5154416944893935e-06, "loss": 0.3145, "step": 671 }, { "epoch": 0.5553719008264463, "grad_norm": 2.437152624130249, "learning_rate": 4.5018368858830646e-06, "loss": 0.3099, "step": 672 }, { "epoch": 0.556198347107438, "grad_norm": 1.8314472436904907, "learning_rate": 4.488235801459495e-06, "loss": 0.2213, "step": 673 }, { "epoch": 0.5570247933884298, "grad_norm": 3.841614007949829, "learning_rate": 4.474638542898078e-06, "loss": 0.1219, "step": 674 }, { "epoch": 0.5578512396694215, "grad_norm": 3.001781463623047, "learning_rate": 4.461045211849605e-06, "loss": 0.0805, "step": 675 }, { "epoch": 0.5586776859504132, "grad_norm": 0.8312858939170837, "learning_rate": 4.447455909935513e-06, "loss": 0.1252, "step": 676 }, { "epoch": 0.5595041322314049, "grad_norm": 1.0251758098602295, "learning_rate": 4.4338707387471105e-06, "loss": 0.1715, "step": 677 }, { "epoch": 0.5603305785123966, "grad_norm": 0.9629795551300049, "learning_rate": 4.420289799844825e-06, "loss": 0.1367, "step": 678 }, { "epoch": 0.5611570247933885, "grad_norm": 1.0852874517440796, "learning_rate": 4.4067131947574515e-06, "loss": 0.1713, "step": 679 }, { "epoch": 0.5619834710743802, "grad_norm": 0.9580336213111877, "learning_rate": 4.393141024981381e-06, "loss": 0.1245, "step": 680 }, { "epoch": 0.5628099173553719, "grad_norm": 1.374263882637024, "learning_rate": 4.379573391979846e-06, "loss": 0.0813, "step": 681 }, { "epoch": 0.5636363636363636, "grad_norm": 1.5036835670471191, "learning_rate": 4.3660103971821635e-06, "loss": 0.0224, "step": 682 }, { "epoch": 0.5644628099173554, "grad_norm": 2.0704779624938965, "learning_rate": 4.352452141982979e-06, "loss": 0.0343, "step": 683 }, { "epoch": 0.5652892561983471, "grad_norm": 1.2086342573165894, "learning_rate": 4.338898727741505e-06, "loss": 0.0152, "step": 684 }, { "epoch": 0.5661157024793388, "grad_norm": 2.1616499423980713, "learning_rate": 4.3253502557807575e-06, "loss": 0.0417, "step": 685 }, { "epoch": 0.5669421487603306, "grad_norm": 1.2505360841751099, "learning_rate": 4.311806827386816e-06, "loss": 0.0314, "step": 686 }, { "epoch": 0.5677685950413223, "grad_norm": 0.4623047113418579, "learning_rate": 4.298268543808043e-06, "loss": 0.0254, "step": 687 }, { "epoch": 0.5685950413223141, "grad_norm": 1.0211182832717896, "learning_rate": 4.28473550625435e-06, "loss": 0.0271, "step": 688 }, { "epoch": 0.5694214876033058, "grad_norm": 0.7633079886436462, "learning_rate": 4.27120781589642e-06, "loss": 0.0095, "step": 689 }, { "epoch": 0.5702479338842975, "grad_norm": 0.45265504717826843, "learning_rate": 4.257685573864971e-06, "loss": 0.0121, "step": 690 }, { "epoch": 0.5710743801652892, "grad_norm": 1.9126603603363037, "learning_rate": 4.244168881249986e-06, "loss": 0.0217, "step": 691 }, { "epoch": 0.571900826446281, "grad_norm": 3.278047561645508, "learning_rate": 4.2306578390999576e-06, "loss": 0.1539, "step": 692 }, { "epoch": 0.5727272727272728, "grad_norm": 1.7494442462921143, "learning_rate": 4.217152548421143e-06, "loss": 0.3445, "step": 693 }, { "epoch": 0.5735537190082645, "grad_norm": 1.7223403453826904, "learning_rate": 4.203653110176798e-06, "loss": 0.2945, "step": 694 }, { "epoch": 0.5743801652892562, "grad_norm": 1.5911810398101807, "learning_rate": 4.190159625286428e-06, "loss": 0.254, "step": 695 }, { "epoch": 0.5752066115702479, "grad_norm": 1.535965919494629, "learning_rate": 4.176672194625036e-06, "loss": 0.3021, "step": 696 }, { "epoch": 0.5760330578512397, "grad_norm": 1.6443074941635132, "learning_rate": 4.163190919022357e-06, "loss": 0.2366, "step": 697 }, { "epoch": 0.5768595041322314, "grad_norm": 1.516901969909668, "learning_rate": 4.149715899262116e-06, "loss": 0.0365, "step": 698 }, { "epoch": 0.5776859504132231, "grad_norm": 2.6840264797210693, "learning_rate": 4.136247236081269e-06, "loss": 0.0598, "step": 699 }, { "epoch": 0.5785123966942148, "grad_norm": 3.295374631881714, "learning_rate": 4.122785030169256e-06, "loss": 0.0969, "step": 700 }, { "epoch": 0.5793388429752067, "grad_norm": 1.1777970790863037, "learning_rate": 4.109329382167237e-06, "loss": 0.1785, "step": 701 }, { "epoch": 0.5801652892561984, "grad_norm": 1.1650125980377197, "learning_rate": 4.095880392667349e-06, "loss": 0.2139, "step": 702 }, { "epoch": 0.5809917355371901, "grad_norm": 0.9443373084068298, "learning_rate": 4.082438162211955e-06, "loss": 0.1594, "step": 703 }, { "epoch": 0.5818181818181818, "grad_norm": 0.9858490824699402, "learning_rate": 4.069002791292882e-06, "loss": 0.137, "step": 704 }, { "epoch": 0.5826446280991735, "grad_norm": 1.3087631464004517, "learning_rate": 4.055574380350678e-06, "loss": 0.1357, "step": 705 }, { "epoch": 0.5834710743801653, "grad_norm": 1.2239716053009033, "learning_rate": 4.042153029773861e-06, "loss": 0.0234, "step": 706 }, { "epoch": 0.584297520661157, "grad_norm": 0.531774640083313, "learning_rate": 4.028738839898168e-06, "loss": 0.0145, "step": 707 }, { "epoch": 0.5851239669421487, "grad_norm": 0.7383906841278076, "learning_rate": 4.015331911005803e-06, "loss": 0.027, "step": 708 }, { "epoch": 0.5859504132231405, "grad_norm": 1.476829171180725, "learning_rate": 4.001932343324683e-06, "loss": 0.0265, "step": 709 }, { "epoch": 0.5867768595041323, "grad_norm": 1.3487377166748047, "learning_rate": 3.988540237027702e-06, "loss": 0.0147, "step": 710 }, { "epoch": 0.587603305785124, "grad_norm": 0.5895293354988098, "learning_rate": 3.97515569223197e-06, "loss": 0.0211, "step": 711 }, { "epoch": 0.5884297520661157, "grad_norm": 0.6942650079727173, "learning_rate": 3.961778808998066e-06, "loss": 0.0299, "step": 712 }, { "epoch": 0.5892561983471074, "grad_norm": 0.28293517231941223, "learning_rate": 3.948409687329298e-06, "loss": 0.0135, "step": 713 }, { "epoch": 0.5900826446280992, "grad_norm": 0.49668827652931213, "learning_rate": 3.935048427170944e-06, "loss": 0.0089, "step": 714 }, { "epoch": 0.5909090909090909, "grad_norm": 0.7324496507644653, "learning_rate": 3.921695128409517e-06, "loss": 0.0153, "step": 715 }, { "epoch": 0.5917355371900826, "grad_norm": 0.3670904338359833, "learning_rate": 3.908349890872005e-06, "loss": 0.0147, "step": 716 }, { "epoch": 0.5925619834710744, "grad_norm": 0.8715825080871582, "learning_rate": 3.895012814325139e-06, "loss": 0.0209, "step": 717 }, { "epoch": 0.5933884297520661, "grad_norm": 2.0958237648010254, "learning_rate": 3.8816839984746334e-06, "loss": 0.3306, "step": 718 }, { "epoch": 0.5942148760330579, "grad_norm": 1.6693692207336426, "learning_rate": 3.86836354296445e-06, "loss": 0.3009, "step": 719 }, { "epoch": 0.5950413223140496, "grad_norm": 2.8003673553466797, "learning_rate": 3.8550515473760515e-06, "loss": 0.327, "step": 720 }, { "epoch": 0.5958677685950413, "grad_norm": 2.277968406677246, "learning_rate": 3.841748111227652e-06, "loss": 0.2983, "step": 721 }, { "epoch": 0.596694214876033, "grad_norm": 1.5424673557281494, "learning_rate": 3.8284533339734804e-06, "loss": 0.2829, "step": 722 }, { "epoch": 0.5975206611570248, "grad_norm": 1.9213181734085083, "learning_rate": 3.815167315003029e-06, "loss": 0.2612, "step": 723 }, { "epoch": 0.5983471074380166, "grad_norm": 2.348574638366699, "learning_rate": 3.8018901536403198e-06, "loss": 0.0426, "step": 724 }, { "epoch": 0.5991735537190083, "grad_norm": 1.7470982074737549, "learning_rate": 3.788621949143152e-06, "loss": 0.0467, "step": 725 }, { "epoch": 0.6, "grad_norm": 0.8803451061248779, "learning_rate": 3.775362800702367e-06, "loss": 0.1494, "step": 726 }, { "epoch": 0.6008264462809917, "grad_norm": 0.9105450510978699, "learning_rate": 3.762112807441108e-06, "loss": 0.1478, "step": 727 }, { "epoch": 0.6016528925619835, "grad_norm": 0.8626505732536316, "learning_rate": 3.7488720684140684e-06, "loss": 0.1531, "step": 728 }, { "epoch": 0.6024793388429752, "grad_norm": 0.8685311675071716, "learning_rate": 3.735640682606764e-06, "loss": 0.1463, "step": 729 }, { "epoch": 0.6033057851239669, "grad_norm": 1.0221821069717407, "learning_rate": 3.7224187489347847e-06, "loss": 0.1823, "step": 730 }, { "epoch": 0.6041322314049586, "grad_norm": 1.0731297731399536, "learning_rate": 3.709206366243061e-06, "loss": 0.158, "step": 731 }, { "epoch": 0.6049586776859505, "grad_norm": 2.116424322128296, "learning_rate": 3.6960036333051184e-06, "loss": 0.1465, "step": 732 }, { "epoch": 0.6057851239669422, "grad_norm": 1.1477619409561157, "learning_rate": 3.682810648822343e-06, "loss": 0.01, "step": 733 }, { "epoch": 0.6066115702479339, "grad_norm": 0.518548846244812, "learning_rate": 3.669627511423247e-06, "loss": 0.0069, "step": 734 }, { "epoch": 0.6074380165289256, "grad_norm": 0.8379459381103516, "learning_rate": 3.6564543196627237e-06, "loss": 0.0213, "step": 735 }, { "epoch": 0.6082644628099173, "grad_norm": 1.508975625038147, "learning_rate": 3.6432911720213127e-06, "loss": 0.0225, "step": 736 }, { "epoch": 0.6090909090909091, "grad_norm": 1.7515640258789062, "learning_rate": 3.630138166904471e-06, "loss": 0.0278, "step": 737 }, { "epoch": 0.6099173553719008, "grad_norm": 0.838191032409668, "learning_rate": 3.6169954026418285e-06, "loss": 0.014, "step": 738 }, { "epoch": 0.6107438016528925, "grad_norm": 0.3030209243297577, "learning_rate": 3.6038629774864563e-06, "loss": 0.0106, "step": 739 }, { "epoch": 0.6115702479338843, "grad_norm": 0.4401758015155792, "learning_rate": 3.5907409896141308e-06, "loss": 0.0063, "step": 740 }, { "epoch": 0.6123966942148761, "grad_norm": 0.3650299906730652, "learning_rate": 3.5776295371226056e-06, "loss": 0.0159, "step": 741 }, { "epoch": 0.6132231404958678, "grad_norm": 1.193688988685608, "learning_rate": 3.56452871803087e-06, "loss": 0.0933, "step": 742 }, { "epoch": 0.6140495867768595, "grad_norm": 2.326871156692505, "learning_rate": 3.551438630278417e-06, "loss": 0.3112, "step": 743 }, { "epoch": 0.6148760330578512, "grad_norm": 5.446589946746826, "learning_rate": 3.5383593717245223e-06, "loss": 0.3338, "step": 744 }, { "epoch": 0.6157024793388429, "grad_norm": 2.3617842197418213, "learning_rate": 3.525291040147498e-06, "loss": 0.3336, "step": 745 }, { "epoch": 0.6165289256198347, "grad_norm": 1.975474238395691, "learning_rate": 3.512233733243967e-06, "loss": 0.2887, "step": 746 }, { "epoch": 0.6173553719008265, "grad_norm": 1.5796037912368774, "learning_rate": 3.49918754862814e-06, "loss": 0.3291, "step": 747 }, { "epoch": 0.6181818181818182, "grad_norm": 2.0289130210876465, "learning_rate": 3.486152583831072e-06, "loss": 0.192, "step": 748 }, { "epoch": 0.6190082644628099, "grad_norm": 2.0254485607147217, "learning_rate": 3.4731289362999473e-06, "loss": 0.056, "step": 749 }, { "epoch": 0.6198347107438017, "grad_norm": 1.9933934211730957, "learning_rate": 3.460116703397336e-06, "loss": 0.054, "step": 750 }, { "epoch": 0.6206611570247934, "grad_norm": 0.851510763168335, "learning_rate": 3.447115982400485e-06, "loss": 0.135, "step": 751 }, { "epoch": 0.6214876033057851, "grad_norm": 0.8434444665908813, "learning_rate": 3.4341268705005708e-06, "loss": 0.1234, "step": 752 }, { "epoch": 0.6223140495867768, "grad_norm": 0.9533182382583618, "learning_rate": 3.421149464801986e-06, "loss": 0.1712, "step": 753 }, { "epoch": 0.6231404958677685, "grad_norm": 0.8647515177726746, "learning_rate": 3.4081838623216124e-06, "loss": 0.1288, "step": 754 }, { "epoch": 0.6239669421487604, "grad_norm": 0.8543617129325867, "learning_rate": 3.3952301599880876e-06, "loss": 0.1472, "step": 755 }, { "epoch": 0.6247933884297521, "grad_norm": 1.66751229763031, "learning_rate": 3.3822884546410884e-06, "loss": 0.1636, "step": 756 }, { "epoch": 0.6256198347107438, "grad_norm": 3.0977776050567627, "learning_rate": 3.3693588430306035e-06, "loss": 0.0359, "step": 757 }, { "epoch": 0.6264462809917355, "grad_norm": 0.6407830119132996, "learning_rate": 3.356441421816214e-06, "loss": 0.0233, "step": 758 }, { "epoch": 0.6272727272727273, "grad_norm": 0.7153797149658203, "learning_rate": 3.3435362875663625e-06, "loss": 0.0211, "step": 759 }, { "epoch": 0.628099173553719, "grad_norm": 0.627882719039917, "learning_rate": 3.330643536757638e-06, "loss": 0.0287, "step": 760 }, { "epoch": 0.6289256198347107, "grad_norm": 1.0231915712356567, "learning_rate": 3.3177632657740575e-06, "loss": 0.0142, "step": 761 }, { "epoch": 0.6297520661157024, "grad_norm": 0.9797623157501221, "learning_rate": 3.3048955709063364e-06, "loss": 0.0101, "step": 762 }, { "epoch": 0.6305785123966943, "grad_norm": 0.7965518236160278, "learning_rate": 3.2920405483511702e-06, "loss": 0.0072, "step": 763 }, { "epoch": 0.631404958677686, "grad_norm": 0.5437694787979126, "learning_rate": 3.2791982942105265e-06, "loss": 0.0126, "step": 764 }, { "epoch": 0.6322314049586777, "grad_norm": 0.9789305329322815, "learning_rate": 3.266368904490914e-06, "loss": 0.0067, "step": 765 }, { "epoch": 0.6330578512396694, "grad_norm": 1.1776361465454102, "learning_rate": 3.253552475102668e-06, "loss": 0.0187, "step": 766 }, { "epoch": 0.6338842975206611, "grad_norm": 0.7138229608535767, "learning_rate": 3.240749101859234e-06, "loss": 0.0196, "step": 767 }, { "epoch": 0.6347107438016529, "grad_norm": 2.1212470531463623, "learning_rate": 3.227958880476457e-06, "loss": 0.2941, "step": 768 }, { "epoch": 0.6355371900826446, "grad_norm": 1.6883107423782349, "learning_rate": 3.215181906571858e-06, "loss": 0.3001, "step": 769 }, { "epoch": 0.6363636363636364, "grad_norm": 2.616964817047119, "learning_rate": 3.2024182756639188e-06, "loss": 0.3375, "step": 770 }, { "epoch": 0.6371900826446281, "grad_norm": 2.5359930992126465, "learning_rate": 3.189668083171379e-06, "loss": 0.2928, "step": 771 }, { "epoch": 0.6380165289256199, "grad_norm": 2.0412468910217285, "learning_rate": 3.1769314244125056e-06, "loss": 0.2874, "step": 772 }, { "epoch": 0.6388429752066116, "grad_norm": 3.327785015106201, "learning_rate": 3.1642083946043977e-06, "loss": 0.1906, "step": 773 }, { "epoch": 0.6396694214876033, "grad_norm": 0.8958473801612854, "learning_rate": 3.15149908886226e-06, "loss": 0.0149, "step": 774 }, { "epoch": 0.640495867768595, "grad_norm": 1.8769047260284424, "learning_rate": 3.1388036021987047e-06, "loss": 0.0437, "step": 775 }, { "epoch": 0.6413223140495867, "grad_norm": 0.7752872109413147, "learning_rate": 3.126122029523031e-06, "loss": 0.1335, "step": 776 }, { "epoch": 0.6421487603305785, "grad_norm": 0.7727296352386475, "learning_rate": 3.1134544656405198e-06, "loss": 0.13, "step": 777 }, { "epoch": 0.6429752066115703, "grad_norm": 0.8350527286529541, "learning_rate": 3.100801005251727e-06, "loss": 0.1258, "step": 778 }, { "epoch": 0.643801652892562, "grad_norm": 0.9546838402748108, "learning_rate": 3.0881617429517697e-06, "loss": 0.1615, "step": 779 }, { "epoch": 0.6446280991735537, "grad_norm": 0.9062439799308777, "learning_rate": 3.075536773229624e-06, "loss": 0.1642, "step": 780 }, { "epoch": 0.6454545454545455, "grad_norm": 1.0381230115890503, "learning_rate": 3.0629261904674206e-06, "loss": 0.1706, "step": 781 }, { "epoch": 0.6462809917355372, "grad_norm": 1.2149626016616821, "learning_rate": 3.0503300889397302e-06, "loss": 0.0749, "step": 782 }, { "epoch": 0.6471074380165289, "grad_norm": 1.1183955669403076, "learning_rate": 3.0377485628128657e-06, "loss": 0.0098, "step": 783 }, { "epoch": 0.6479338842975206, "grad_norm": 0.5233092904090881, "learning_rate": 3.025181706144178e-06, "loss": 0.0132, "step": 784 }, { "epoch": 0.6487603305785123, "grad_norm": 1.2450796365737915, "learning_rate": 3.012629612881354e-06, "loss": 0.0112, "step": 785 }, { "epoch": 0.6495867768595042, "grad_norm": 0.20728905498981476, "learning_rate": 3.000092376861705e-06, "loss": 0.0027, "step": 786 }, { "epoch": 0.6504132231404959, "grad_norm": 1.2542493343353271, "learning_rate": 2.987570091811479e-06, "loss": 0.0158, "step": 787 }, { "epoch": 0.6512396694214876, "grad_norm": 0.8259776830673218, "learning_rate": 2.97506285134515e-06, "loss": 0.0336, "step": 788 }, { "epoch": 0.6520661157024793, "grad_norm": 1.7150229215621948, "learning_rate": 2.9625707489647227e-06, "loss": 0.0198, "step": 789 }, { "epoch": 0.6528925619834711, "grad_norm": 0.2723279297351837, "learning_rate": 2.9500938780590276e-06, "loss": 0.019, "step": 790 }, { "epoch": 0.6537190082644628, "grad_norm": 0.4087146520614624, "learning_rate": 2.937632331903032e-06, "loss": 0.004, "step": 791 }, { "epoch": 0.6545454545454545, "grad_norm": 0.5747569799423218, "learning_rate": 2.92518620365714e-06, "loss": 0.0078, "step": 792 }, { "epoch": 0.6553719008264463, "grad_norm": 1.2564964294433594, "learning_rate": 2.9127555863664857e-06, "loss": 0.2254, "step": 793 }, { "epoch": 0.656198347107438, "grad_norm": 1.4814064502716064, "learning_rate": 2.900340572960253e-06, "loss": 0.2538, "step": 794 }, { "epoch": 0.6570247933884298, "grad_norm": 1.4104158878326416, "learning_rate": 2.887941256250972e-06, "loss": 0.2711, "step": 795 }, { "epoch": 0.6578512396694215, "grad_norm": 1.837869644165039, "learning_rate": 2.8755577289338267e-06, "loss": 0.2782, "step": 796 }, { "epoch": 0.6586776859504132, "grad_norm": 2.8386220932006836, "learning_rate": 2.863190083585962e-06, "loss": 0.2859, "step": 797 }, { "epoch": 0.6595041322314049, "grad_norm": 3.301816940307617, "learning_rate": 2.8508384126657906e-06, "loss": 0.111, "step": 798 }, { "epoch": 0.6603305785123967, "grad_norm": 4.864030838012695, "learning_rate": 2.838502808512309e-06, "loss": 0.126, "step": 799 }, { "epoch": 0.6611570247933884, "grad_norm": 1.8764886856079102, "learning_rate": 2.8261833633443914e-06, "loss": 0.049, "step": 800 }, { "epoch": 0.6619834710743802, "grad_norm": 0.9268789291381836, "learning_rate": 2.813880169260117e-06, "loss": 0.1589, "step": 801 }, { "epoch": 0.6628099173553719, "grad_norm": 1.0193241834640503, "learning_rate": 2.801593318236078e-06, "loss": 0.1732, "step": 802 }, { "epoch": 0.6636363636363637, "grad_norm": 0.9190545678138733, "learning_rate": 2.7893229021266776e-06, "loss": 0.1394, "step": 803 }, { "epoch": 0.6644628099173554, "grad_norm": 0.995844841003418, "learning_rate": 2.7770690126634643e-06, "loss": 0.1421, "step": 804 }, { "epoch": 0.6652892561983471, "grad_norm": 0.8262742757797241, "learning_rate": 2.764831741454432e-06, "loss": 0.0787, "step": 805 }, { "epoch": 0.6661157024793388, "grad_norm": 0.6985448002815247, "learning_rate": 2.7526111799833397e-06, "loss": 0.0165, "step": 806 }, { "epoch": 0.6669421487603305, "grad_norm": 0.6556599736213684, "learning_rate": 2.740407419609028e-06, "loss": 0.0217, "step": 807 }, { "epoch": 0.6677685950413224, "grad_norm": 1.64823317527771, "learning_rate": 2.7282205515647348e-06, "loss": 0.0196, "step": 808 }, { "epoch": 0.6685950413223141, "grad_norm": 2.291562795639038, "learning_rate": 2.7160506669574137e-06, "loss": 0.0332, "step": 809 }, { "epoch": 0.6694214876033058, "grad_norm": 3.0333375930786133, "learning_rate": 2.703897856767056e-06, "loss": 0.0383, "step": 810 }, { "epoch": 0.6702479338842975, "grad_norm": 0.9240926504135132, "learning_rate": 2.6917622118459975e-06, "loss": 0.0086, "step": 811 }, { "epoch": 0.6710743801652893, "grad_norm": 0.9838902950286865, "learning_rate": 2.6796438229182643e-06, "loss": 0.0105, "step": 812 }, { "epoch": 0.671900826446281, "grad_norm": 0.4214411973953247, "learning_rate": 2.66754278057887e-06, "loss": 0.0045, "step": 813 }, { "epoch": 0.6727272727272727, "grad_norm": 2.1211740970611572, "learning_rate": 2.655459175293146e-06, "loss": 0.0305, "step": 814 }, { "epoch": 0.6735537190082644, "grad_norm": 1.3328880071640015, "learning_rate": 2.6433930973960775e-06, "loss": 0.0122, "step": 815 }, { "epoch": 0.6743801652892562, "grad_norm": 1.5663409233093262, "learning_rate": 2.631344637091607e-06, "loss": 0.0109, "step": 816 }, { "epoch": 0.675206611570248, "grad_norm": 1.9309957027435303, "learning_rate": 2.6193138844519785e-06, "loss": 0.2505, "step": 817 }, { "epoch": 0.6760330578512397, "grad_norm": 1.5996431112289429, "learning_rate": 2.6073009294170514e-06, "loss": 0.2626, "step": 818 }, { "epoch": 0.6768595041322314, "grad_norm": 2.8478901386260986, "learning_rate": 2.5953058617936368e-06, "loss": 0.298, "step": 819 }, { "epoch": 0.6776859504132231, "grad_norm": 2.0270745754241943, "learning_rate": 2.58332877125482e-06, "loss": 0.2915, "step": 820 }, { "epoch": 0.6785123966942149, "grad_norm": 1.7036795616149902, "learning_rate": 2.5713697473392953e-06, "loss": 0.2774, "step": 821 }, { "epoch": 0.6793388429752066, "grad_norm": 1.6781381368637085, "learning_rate": 2.5594288794506917e-06, "loss": 0.1863, "step": 822 }, { "epoch": 0.6801652892561983, "grad_norm": 3.5772781372070312, "learning_rate": 2.5475062568569077e-06, "loss": 0.0304, "step": 823 }, { "epoch": 0.6809917355371901, "grad_norm": 3.3236935138702393, "learning_rate": 2.5356019686894457e-06, "loss": 0.0711, "step": 824 }, { "epoch": 0.6818181818181818, "grad_norm": 2.2396740913391113, "learning_rate": 2.523716103942734e-06, "loss": 0.0637, "step": 825 }, { "epoch": 0.6826446280991736, "grad_norm": 0.7092673182487488, "learning_rate": 2.511848751473485e-06, "loss": 0.1196, "step": 826 }, { "epoch": 0.6834710743801653, "grad_norm": 0.7840614914894104, "learning_rate": 2.5000000000000015e-06, "loss": 0.1372, "step": 827 }, { "epoch": 0.684297520661157, "grad_norm": 0.8343893885612488, "learning_rate": 2.488169938101536e-06, "loss": 0.1246, "step": 828 }, { "epoch": 0.6851239669421487, "grad_norm": 1.0356327295303345, "learning_rate": 2.476358654217627e-06, "loss": 0.1976, "step": 829 }, { "epoch": 0.6859504132231405, "grad_norm": 0.8545620441436768, "learning_rate": 2.4645662366474186e-06, "loss": 0.1451, "step": 830 }, { "epoch": 0.6867768595041323, "grad_norm": 1.6567367315292358, "learning_rate": 2.4527927735490213e-06, "loss": 0.132, "step": 831 }, { "epoch": 0.687603305785124, "grad_norm": 0.3666848838329315, "learning_rate": 2.4410383529388448e-06, "loss": 0.0204, "step": 832 }, { "epoch": 0.6884297520661157, "grad_norm": 0.686599850654602, "learning_rate": 2.429303062690938e-06, "loss": 0.0091, "step": 833 }, { "epoch": 0.6892561983471074, "grad_norm": 0.48144328594207764, "learning_rate": 2.417586990536339e-06, "loss": 0.0137, "step": 834 }, { "epoch": 0.6900826446280992, "grad_norm": 0.20945820212364197, "learning_rate": 2.405890224062406e-06, "loss": 0.0022, "step": 835 }, { "epoch": 0.6909090909090909, "grad_norm": 1.2613632678985596, "learning_rate": 2.3942128507121816e-06, "loss": 0.022, "step": 836 }, { "epoch": 0.6917355371900826, "grad_norm": 1.0795994997024536, "learning_rate": 2.3825549577837243e-06, "loss": 0.0352, "step": 837 }, { "epoch": 0.6925619834710743, "grad_norm": 0.9106585383415222, "learning_rate": 2.370916632429455e-06, "loss": 0.0107, "step": 838 }, { "epoch": 0.6933884297520662, "grad_norm": 0.4586517810821533, "learning_rate": 2.3592979616555194e-06, "loss": 0.0095, "step": 839 }, { "epoch": 0.6942148760330579, "grad_norm": 0.6390123963356018, "learning_rate": 2.347699032321127e-06, "loss": 0.0123, "step": 840 }, { "epoch": 0.6950413223140496, "grad_norm": 0.6808966994285583, "learning_rate": 2.336119931137897e-06, "loss": 0.0163, "step": 841 }, { "epoch": 0.6958677685950413, "grad_norm": 1.1223820447921753, "learning_rate": 2.324560744669224e-06, "loss": 0.0118, "step": 842 }, { "epoch": 0.6966942148760331, "grad_norm": 1.7861708402633667, "learning_rate": 2.31302155932962e-06, "loss": 0.2214, "step": 843 }, { "epoch": 0.6975206611570248, "grad_norm": 1.836301565170288, "learning_rate": 2.3015024613840742e-06, "loss": 0.2559, "step": 844 }, { "epoch": 0.6983471074380165, "grad_norm": 2.2409980297088623, "learning_rate": 2.2900035369474045e-06, "loss": 0.2709, "step": 845 }, { "epoch": 0.6991735537190082, "grad_norm": 1.363874912261963, "learning_rate": 2.2785248719836145e-06, "loss": 0.248, "step": 846 }, { "epoch": 0.7, "grad_norm": 1.4939771890640259, "learning_rate": 2.2670665523052534e-06, "loss": 0.2561, "step": 847 }, { "epoch": 0.7008264462809918, "grad_norm": 2.0174720287323, "learning_rate": 2.25562866357277e-06, "loss": 0.1054, "step": 848 }, { "epoch": 0.7016528925619835, "grad_norm": 3.05000638961792, "learning_rate": 2.244211291293877e-06, "loss": 0.0344, "step": 849 }, { "epoch": 0.7024793388429752, "grad_norm": 2.6590240001678467, "learning_rate": 2.2328145208229096e-06, "loss": 0.0729, "step": 850 }, { "epoch": 0.7033057851239669, "grad_norm": 0.8622211813926697, "learning_rate": 2.2214384373601843e-06, "loss": 0.1666, "step": 851 }, { "epoch": 0.7041322314049587, "grad_norm": 0.7983608245849609, "learning_rate": 2.210083125951366e-06, "loss": 0.1374, "step": 852 }, { "epoch": 0.7049586776859504, "grad_norm": 0.7725859880447388, "learning_rate": 2.1987486714868384e-06, "loss": 0.1202, "step": 853 }, { "epoch": 0.7057851239669422, "grad_norm": 0.8879849910736084, "learning_rate": 2.1874351587010505e-06, "loss": 0.1384, "step": 854 }, { "epoch": 0.7066115702479339, "grad_norm": 0.9821515083312988, "learning_rate": 2.1761426721719015e-06, "loss": 0.0418, "step": 855 }, { "epoch": 0.7074380165289256, "grad_norm": 0.5421770215034485, "learning_rate": 2.164871296320106e-06, "loss": 0.0135, "step": 856 }, { "epoch": 0.7082644628099174, "grad_norm": 0.7403706908226013, "learning_rate": 2.1536211154085473e-06, "loss": 0.015, "step": 857 }, { "epoch": 0.7090909090909091, "grad_norm": 0.5398378372192383, "learning_rate": 2.142392213541669e-06, "loss": 0.0092, "step": 858 }, { "epoch": 0.7099173553719008, "grad_norm": 0.1735723912715912, "learning_rate": 2.1311846746648325e-06, "loss": 0.0027, "step": 859 }, { "epoch": 0.7107438016528925, "grad_norm": 0.6800421476364136, "learning_rate": 2.119998582563692e-06, "loss": 0.0072, "step": 860 }, { "epoch": 0.7115702479338843, "grad_norm": 0.5147267580032349, "learning_rate": 2.108834020863573e-06, "loss": 0.008, "step": 861 }, { "epoch": 0.7123966942148761, "grad_norm": 1.2354320287704468, "learning_rate": 2.097691073028836e-06, "loss": 0.0126, "step": 862 }, { "epoch": 0.7132231404958678, "grad_norm": 0.2006523609161377, "learning_rate": 2.0865698223622693e-06, "loss": 0.0036, "step": 863 }, { "epoch": 0.7140495867768595, "grad_norm": 0.3145323097705841, "learning_rate": 2.075470352004453e-06, "loss": 0.0082, "step": 864 }, { "epoch": 0.7148760330578512, "grad_norm": 0.9217435717582703, "learning_rate": 2.064392744933135e-06, "loss": 0.0183, "step": 865 }, { "epoch": 0.715702479338843, "grad_norm": 1.0004950761795044, "learning_rate": 2.05333708396263e-06, "loss": 0.012, "step": 866 }, { "epoch": 0.7165289256198347, "grad_norm": 1.3667855262756348, "learning_rate": 2.042303451743174e-06, "loss": 0.1209, "step": 867 }, { "epoch": 0.7173553719008264, "grad_norm": 2.370497703552246, "learning_rate": 2.0312919307603286e-06, "loss": 0.2518, "step": 868 }, { "epoch": 0.7181818181818181, "grad_norm": 2.145073652267456, "learning_rate": 2.0203026033343525e-06, "loss": 0.2709, "step": 869 }, { "epoch": 0.71900826446281, "grad_norm": 1.861162543296814, "learning_rate": 2.009335551619589e-06, "loss": 0.271, "step": 870 }, { "epoch": 0.7198347107438017, "grad_norm": 1.8809741735458374, "learning_rate": 1.998390857603853e-06, "loss": 0.2814, "step": 871 }, { "epoch": 0.7206611570247934, "grad_norm": 1.8260799646377563, "learning_rate": 1.9874686031078156e-06, "loss": 0.2913, "step": 872 }, { "epoch": 0.7214876033057851, "grad_norm": 2.0237462520599365, "learning_rate": 1.976568869784396e-06, "loss": 0.1477, "step": 873 }, { "epoch": 0.7223140495867768, "grad_norm": 2.680821180343628, "learning_rate": 1.965691739118146e-06, "loss": 0.059, "step": 874 }, { "epoch": 0.7231404958677686, "grad_norm": 1.6376444101333618, "learning_rate": 1.9548372924246495e-06, "loss": 0.0202, "step": 875 }, { "epoch": 0.7239669421487603, "grad_norm": 0.8022472262382507, "learning_rate": 1.9440056108498974e-06, "loss": 0.1588, "step": 876 }, { "epoch": 0.724793388429752, "grad_norm": 0.8381442427635193, "learning_rate": 1.9331967753697077e-06, "loss": 0.141, "step": 877 }, { "epoch": 0.7256198347107438, "grad_norm": 0.7840932011604309, "learning_rate": 1.922410866789092e-06, "loss": 0.1124, "step": 878 }, { "epoch": 0.7264462809917356, "grad_norm": 0.9165108799934387, "learning_rate": 1.9116479657416687e-06, "loss": 0.1586, "step": 879 }, { "epoch": 0.7272727272727273, "grad_norm": 0.8586753606796265, "learning_rate": 1.9009081526890622e-06, "loss": 0.1463, "step": 880 }, { "epoch": 0.728099173553719, "grad_norm": 1.2581459283828735, "learning_rate": 1.8901915079202836e-06, "loss": 0.0756, "step": 881 }, { "epoch": 0.7289256198347107, "grad_norm": 0.4948238432407379, "learning_rate": 1.8794981115511478e-06, "loss": 0.0035, "step": 882 }, { "epoch": 0.7297520661157024, "grad_norm": 0.6490508913993835, "learning_rate": 1.8688280435236732e-06, "loss": 0.0134, "step": 883 }, { "epoch": 0.7305785123966942, "grad_norm": 0.5945568680763245, "learning_rate": 1.8581813836054697e-06, "loss": 0.005, "step": 884 }, { "epoch": 0.731404958677686, "grad_norm": 1.2948330640792847, "learning_rate": 1.8475582113891587e-06, "loss": 0.0122, "step": 885 }, { "epoch": 0.7322314049586777, "grad_norm": 1.1504799127578735, "learning_rate": 1.8369586062917693e-06, "loss": 0.0123, "step": 886 }, { "epoch": 0.7330578512396694, "grad_norm": 0.7296923995018005, "learning_rate": 1.826382647554148e-06, "loss": 0.0086, "step": 887 }, { "epoch": 0.7338842975206612, "grad_norm": 1.6546300649642944, "learning_rate": 1.8158304142403653e-06, "loss": 0.0222, "step": 888 }, { "epoch": 0.7347107438016529, "grad_norm": 2.178463935852051, "learning_rate": 1.8053019852371195e-06, "loss": 0.0289, "step": 889 }, { "epoch": 0.7355371900826446, "grad_norm": 0.14165276288986206, "learning_rate": 1.7947974392531615e-06, "loss": 0.0032, "step": 890 }, { "epoch": 0.7363636363636363, "grad_norm": 1.420249104499817, "learning_rate": 1.7843168548186895e-06, "loss": 0.0178, "step": 891 }, { "epoch": 0.7371900826446282, "grad_norm": 1.1662765741348267, "learning_rate": 1.7738603102847696e-06, "loss": 0.1101, "step": 892 }, { "epoch": 0.7380165289256199, "grad_norm": 2.345207452774048, "learning_rate": 1.7634278838227525e-06, "loss": 0.279, "step": 893 }, { "epoch": 0.7388429752066116, "grad_norm": 2.788140058517456, "learning_rate": 1.7530196534236842e-06, "loss": 0.2897, "step": 894 }, { "epoch": 0.7396694214876033, "grad_norm": 1.8566540479660034, "learning_rate": 1.7426356968977265e-06, "loss": 0.2754, "step": 895 }, { "epoch": 0.740495867768595, "grad_norm": 2.0167226791381836, "learning_rate": 1.7322760918735738e-06, "loss": 0.2636, "step": 896 }, { "epoch": 0.7413223140495868, "grad_norm": 1.5432149171829224, "learning_rate": 1.7219409157978706e-06, "loss": 0.236, "step": 897 }, { "epoch": 0.7421487603305785, "grad_norm": 2.1682021617889404, "learning_rate": 1.711630245934638e-06, "loss": 0.2504, "step": 898 }, { "epoch": 0.7429752066115702, "grad_norm": 3.0678889751434326, "learning_rate": 1.7013441593646895e-06, "loss": 0.0833, "step": 899 }, { "epoch": 0.743801652892562, "grad_norm": 1.4966950416564941, "learning_rate": 1.6910827329850614e-06, "loss": 0.0471, "step": 900 }, { "epoch": 0.7446280991735538, "grad_norm": 0.6166396737098694, "learning_rate": 1.6808460435084316e-06, "loss": 0.0792, "step": 901 }, { "epoch": 0.7454545454545455, "grad_norm": 0.9144138693809509, "learning_rate": 1.6706341674625538e-06, "loss": 0.1568, "step": 902 }, { "epoch": 0.7462809917355372, "grad_norm": 0.7173328995704651, "learning_rate": 1.6604471811896705e-06, "loss": 0.0997, "step": 903 }, { "epoch": 0.7471074380165289, "grad_norm": 0.8290011882781982, "learning_rate": 1.6502851608459668e-06, "loss": 0.1203, "step": 904 }, { "epoch": 0.7479338842975206, "grad_norm": 0.8501728773117065, "learning_rate": 1.640148182400975e-06, "loss": 0.1433, "step": 905 }, { "epoch": 0.7487603305785124, "grad_norm": 1.6242462396621704, "learning_rate": 1.630036321637022e-06, "loss": 0.0286, "step": 906 }, { "epoch": 0.7495867768595041, "grad_norm": 1.0156506299972534, "learning_rate": 1.6199496541486647e-06, "loss": 0.0133, "step": 907 }, { "epoch": 0.7504132231404959, "grad_norm": 0.5060174465179443, "learning_rate": 1.6098882553421101e-06, "loss": 0.0111, "step": 908 }, { "epoch": 0.7512396694214876, "grad_norm": 0.5839444398880005, "learning_rate": 1.5998522004346672e-06, "loss": 0.0251, "step": 909 }, { "epoch": 0.7520661157024794, "grad_norm": 0.8593085408210754, "learning_rate": 1.589841564454176e-06, "loss": 0.0094, "step": 910 }, { "epoch": 0.7528925619834711, "grad_norm": 0.6602495908737183, "learning_rate": 1.5798564222384493e-06, "loss": 0.0119, "step": 911 }, { "epoch": 0.7537190082644628, "grad_norm": 0.5076149702072144, "learning_rate": 1.5698968484347132e-06, "loss": 0.0066, "step": 912 }, { "epoch": 0.7545454545454545, "grad_norm": 0.5409338474273682, "learning_rate": 1.5599629174990482e-06, "loss": 0.0094, "step": 913 }, { "epoch": 0.7553719008264462, "grad_norm": 0.554561197757721, "learning_rate": 1.5500547036958336e-06, "loss": 0.0048, "step": 914 }, { "epoch": 0.756198347107438, "grad_norm": 0.26180991530418396, "learning_rate": 1.5401722810971926e-06, "loss": 0.0049, "step": 915 }, { "epoch": 0.7570247933884298, "grad_norm": 2.6749250888824463, "learning_rate": 1.5303157235824323e-06, "loss": 0.019, "step": 916 }, { "epoch": 0.7578512396694215, "grad_norm": 2.0448601245880127, "learning_rate": 1.5204851048375052e-06, "loss": 0.1908, "step": 917 }, { "epoch": 0.7586776859504132, "grad_norm": 2.299800157546997, "learning_rate": 1.510680498354447e-06, "loss": 0.2845, "step": 918 }, { "epoch": 0.759504132231405, "grad_norm": 1.8261854648590088, "learning_rate": 1.5009019774308249e-06, "loss": 0.2633, "step": 919 }, { "epoch": 0.7603305785123967, "grad_norm": 1.7616630792617798, "learning_rate": 1.4911496151692013e-06, "loss": 0.2646, "step": 920 }, { "epoch": 0.7611570247933884, "grad_norm": 1.765621542930603, "learning_rate": 1.4814234844765784e-06, "loss": 0.2744, "step": 921 }, { "epoch": 0.7619834710743801, "grad_norm": 1.6501365900039673, "learning_rate": 1.471723658063856e-06, "loss": 0.2514, "step": 922 }, { "epoch": 0.7628099173553718, "grad_norm": 2.1452829837799072, "learning_rate": 1.462050208445287e-06, "loss": 0.0825, "step": 923 }, { "epoch": 0.7636363636363637, "grad_norm": 1.7787621021270752, "learning_rate": 1.4524032079379369e-06, "loss": 0.0451, "step": 924 }, { "epoch": 0.7644628099173554, "grad_norm": 1.823784589767456, "learning_rate": 1.4427827286611412e-06, "loss": 0.035, "step": 925 }, { "epoch": 0.7652892561983471, "grad_norm": 0.8847120404243469, "learning_rate": 1.4331888425359697e-06, "loss": 0.1645, "step": 926 }, { "epoch": 0.7661157024793388, "grad_norm": 1.283545732498169, "learning_rate": 1.4236216212846787e-06, "loss": 0.185, "step": 927 }, { "epoch": 0.7669421487603306, "grad_norm": 0.8690438866615295, "learning_rate": 1.4140811364301931e-06, "loss": 0.157, "step": 928 }, { "epoch": 0.7677685950413223, "grad_norm": 0.7596165537834167, "learning_rate": 1.4045674592955561e-06, "loss": 0.1042, "step": 929 }, { "epoch": 0.768595041322314, "grad_norm": 0.80385422706604, "learning_rate": 1.3950806610033956e-06, "loss": 0.1306, "step": 930 }, { "epoch": 0.7694214876033058, "grad_norm": 1.0708730220794678, "learning_rate": 1.385620812475409e-06, "loss": 0.0881, "step": 931 }, { "epoch": 0.7702479338842976, "grad_norm": 0.5643999576568604, "learning_rate": 1.3761879844318116e-06, "loss": 0.0059, "step": 932 }, { "epoch": 0.7710743801652893, "grad_norm": 0.5080968141555786, "learning_rate": 1.3667822473908221e-06, "loss": 0.0099, "step": 933 }, { "epoch": 0.771900826446281, "grad_norm": 0.19685262441635132, "learning_rate": 1.3574036716681366e-06, "loss": 0.0019, "step": 934 }, { "epoch": 0.7727272727272727, "grad_norm": 0.4858970046043396, "learning_rate": 1.348052327376388e-06, "loss": 0.0092, "step": 935 }, { "epoch": 0.7735537190082644, "grad_norm": 1.647731065750122, "learning_rate": 1.3387282844246385e-06, "loss": 0.0213, "step": 936 }, { "epoch": 0.7743801652892562, "grad_norm": 1.358784794807434, "learning_rate": 1.3294316125178474e-06, "loss": 0.0074, "step": 937 }, { "epoch": 0.775206611570248, "grad_norm": 0.38342639803886414, "learning_rate": 1.3201623811563545e-06, "loss": 0.008, "step": 938 }, { "epoch": 0.7760330578512397, "grad_norm": 0.24300101399421692, "learning_rate": 1.3109206596353574e-06, "loss": 0.0039, "step": 939 }, { "epoch": 0.7768595041322314, "grad_norm": 0.7706601023674011, "learning_rate": 1.301706517044395e-06, "loss": 0.0249, "step": 940 }, { "epoch": 0.7776859504132232, "grad_norm": 1.2098647356033325, "learning_rate": 1.292520022266831e-06, "loss": 0.0131, "step": 941 }, { "epoch": 0.7785123966942149, "grad_norm": 0.957886815071106, "learning_rate": 1.2833612439793403e-06, "loss": 0.0317, "step": 942 }, { "epoch": 0.7793388429752066, "grad_norm": 1.9836186170578003, "learning_rate": 1.2742302506513894e-06, "loss": 0.2457, "step": 943 }, { "epoch": 0.7801652892561983, "grad_norm": 2.8069849014282227, "learning_rate": 1.2651271105447322e-06, "loss": 0.2876, "step": 944 }, { "epoch": 0.78099173553719, "grad_norm": 1.618880271911621, "learning_rate": 1.2560518917129017e-06, "loss": 0.2439, "step": 945 }, { "epoch": 0.7818181818181819, "grad_norm": 1.7697207927703857, "learning_rate": 1.247004662000686e-06, "loss": 0.2439, "step": 946 }, { "epoch": 0.7826446280991736, "grad_norm": 1.9872509241104126, "learning_rate": 1.2379854890436377e-06, "loss": 0.2743, "step": 947 }, { "epoch": 0.7834710743801653, "grad_norm": 1.743913173675537, "learning_rate": 1.2289944402675618e-06, "loss": 0.2494, "step": 948 }, { "epoch": 0.784297520661157, "grad_norm": 2.9703633785247803, "learning_rate": 1.2200315828880094e-06, "loss": 0.0574, "step": 949 }, { "epoch": 0.7851239669421488, "grad_norm": 0.9676649570465088, "learning_rate": 1.2110969839097798e-06, "loss": 0.018, "step": 950 }, { "epoch": 0.7859504132231405, "grad_norm": 0.8991837501525879, "learning_rate": 1.2021907101264147e-06, "loss": 0.1845, "step": 951 }, { "epoch": 0.7867768595041322, "grad_norm": 0.6820972561836243, "learning_rate": 1.1933128281197042e-06, "loss": 0.1181, "step": 952 }, { "epoch": 0.7876033057851239, "grad_norm": 0.9404390454292297, "learning_rate": 1.1844634042591858e-06, "loss": 0.1792, "step": 953 }, { "epoch": 0.7884297520661157, "grad_norm": 0.8390997648239136, "learning_rate": 1.175642504701644e-06, "loss": 0.1439, "step": 954 }, { "epoch": 0.7892561983471075, "grad_norm": 0.9683129191398621, "learning_rate": 1.166850195390628e-06, "loss": 0.1708, "step": 955 }, { "epoch": 0.7900826446280992, "grad_norm": 0.9276797771453857, "learning_rate": 1.158086542055949e-06, "loss": 0.1648, "step": 956 }, { "epoch": 0.7909090909090909, "grad_norm": 0.8429524302482605, "learning_rate": 1.1493516102131836e-06, "loss": 0.0208, "step": 957 }, { "epoch": 0.7917355371900826, "grad_norm": 0.1765168458223343, "learning_rate": 1.1406454651632042e-06, "loss": 0.0015, "step": 958 }, { "epoch": 0.7925619834710744, "grad_norm": 0.7258001565933228, "learning_rate": 1.1319681719916663e-06, "loss": 0.0114, "step": 959 }, { "epoch": 0.7933884297520661, "grad_norm": 0.8360604047775269, "learning_rate": 1.123319795568541e-06, "loss": 0.0189, "step": 960 }, { "epoch": 0.7942148760330578, "grad_norm": 0.9019877910614014, "learning_rate": 1.1147004005476192e-06, "loss": 0.0078, "step": 961 }, { "epoch": 0.7950413223140496, "grad_norm": 1.007905125617981, "learning_rate": 1.1061100513660332e-06, "loss": 0.0078, "step": 962 }, { "epoch": 0.7958677685950413, "grad_norm": 0.0849403589963913, "learning_rate": 1.0975488122437732e-06, "loss": 0.0008, "step": 963 }, { "epoch": 0.7966942148760331, "grad_norm": 1.677506923675537, "learning_rate": 1.089016747183208e-06, "loss": 0.03, "step": 964 }, { "epoch": 0.7975206611570248, "grad_norm": 0.5890437960624695, "learning_rate": 1.0805139199686049e-06, "loss": 0.0051, "step": 965 }, { "epoch": 0.7983471074380165, "grad_norm": 0.7736407518386841, "learning_rate": 1.072040394165655e-06, "loss": 0.012, "step": 966 }, { "epoch": 0.7991735537190082, "grad_norm": 1.1192368268966675, "learning_rate": 1.063596233120997e-06, "loss": 0.1202, "step": 967 }, { "epoch": 0.8, "grad_norm": 1.3015234470367432, "learning_rate": 1.0551814999617432e-06, "loss": 0.2413, "step": 968 }, { "epoch": 0.8008264462809918, "grad_norm": 1.6623808145523071, "learning_rate": 1.0467962575950097e-06, "loss": 0.2739, "step": 969 }, { "epoch": 0.8016528925619835, "grad_norm": 1.513471007347107, "learning_rate": 1.03844056870744e-06, "loss": 0.2316, "step": 970 }, { "epoch": 0.8024793388429752, "grad_norm": 4.34433126449585, "learning_rate": 1.0301144957647442e-06, "loss": 0.2644, "step": 971 }, { "epoch": 0.8033057851239669, "grad_norm": 1.4260059595108032, "learning_rate": 1.021818101011232e-06, "loss": 0.2076, "step": 972 }, { "epoch": 0.8041322314049587, "grad_norm": 2.9094693660736084, "learning_rate": 1.013551446469337e-06, "loss": 0.09, "step": 973 }, { "epoch": 0.8049586776859504, "grad_norm": 1.9255399703979492, "learning_rate": 1.005314593939164e-06, "loss": 0.0309, "step": 974 }, { "epoch": 0.8057851239669421, "grad_norm": 1.6190732717514038, "learning_rate": 9.97107604998022e-07, "loss": 0.0455, "step": 975 }, { "epoch": 0.8066115702479338, "grad_norm": 0.6468827724456787, "learning_rate": 9.889305409999656e-07, "loss": 0.0902, "step": 976 }, { "epoch": 0.8074380165289257, "grad_norm": 0.7833928465843201, "learning_rate": 9.807834630753366e-07, "loss": 0.1279, "step": 977 }, { "epoch": 0.8082644628099174, "grad_norm": 0.7632892727851868, "learning_rate": 9.726664321303008e-07, "loss": 0.1217, "step": 978 }, { "epoch": 0.8090909090909091, "grad_norm": 0.7852186560630798, "learning_rate": 9.64579508846405e-07, "loss": 0.1429, "step": 979 }, { "epoch": 0.8099173553719008, "grad_norm": 0.6835703253746033, "learning_rate": 9.565227536801136e-07, "loss": 0.0575, "step": 980 }, { "epoch": 0.8107438016528926, "grad_norm": 1.7434837818145752, "learning_rate": 9.484962268623549e-07, "loss": 0.0147, "step": 981 }, { "epoch": 0.8115702479338843, "grad_norm": 2.6885852813720703, "learning_rate": 9.40499988398082e-07, "loss": 0.0219, "step": 982 }, { "epoch": 0.812396694214876, "grad_norm": 0.2245260328054428, "learning_rate": 9.325340980658149e-07, "loss": 0.0041, "step": 983 }, { "epoch": 0.8132231404958677, "grad_norm": 0.39877408742904663, "learning_rate": 9.245986154171915e-07, "loss": 0.0042, "step": 984 }, { "epoch": 0.8140495867768595, "grad_norm": 0.32143980264663696, "learning_rate": 9.166935997765364e-07, "loss": 0.003, "step": 985 }, { "epoch": 0.8148760330578513, "grad_norm": 1.1524460315704346, "learning_rate": 9.088191102403992e-07, "loss": 0.0187, "step": 986 }, { "epoch": 0.815702479338843, "grad_norm": 1.9803694486618042, "learning_rate": 9.00975205677126e-07, "loss": 0.0281, "step": 987 }, { "epoch": 0.8165289256198347, "grad_norm": 0.14439859986305237, "learning_rate": 8.93161944726414e-07, "loss": 0.0033, "step": 988 }, { "epoch": 0.8173553719008264, "grad_norm": 0.32128700613975525, "learning_rate": 8.853793857988735e-07, "loss": 0.005, "step": 989 }, { "epoch": 0.8181818181818182, "grad_norm": 0.31499621272087097, "learning_rate": 8.776275870755924e-07, "loss": 0.0027, "step": 990 }, { "epoch": 0.8190082644628099, "grad_norm": 0.6206768155097961, "learning_rate": 8.699066065077005e-07, "loss": 0.0078, "step": 991 }, { "epoch": 0.8198347107438017, "grad_norm": 1.6296873092651367, "learning_rate": 8.622165018159356e-07, "loss": 0.04, "step": 992 }, { "epoch": 0.8206611570247934, "grad_norm": 1.5795947313308716, "learning_rate": 8.54557330490215e-07, "loss": 0.2485, "step": 993 }, { "epoch": 0.8214876033057851, "grad_norm": 1.4903229475021362, "learning_rate": 8.469291497891979e-07, "loss": 0.2361, "step": 994 }, { "epoch": 0.8223140495867769, "grad_norm": 2.2532012462615967, "learning_rate": 8.393320167398672e-07, "loss": 0.2507, "step": 995 }, { "epoch": 0.8231404958677686, "grad_norm": 1.4450434446334839, "learning_rate": 8.317659881371021e-07, "loss": 0.2469, "step": 996 }, { "epoch": 0.8239669421487603, "grad_norm": 1.5326659679412842, "learning_rate": 8.242311205432418e-07, "loss": 0.2538, "step": 997 }, { "epoch": 0.824793388429752, "grad_norm": 3.020674705505371, "learning_rate": 8.167274702876765e-07, "loss": 0.1389, "step": 998 }, { "epoch": 0.8256198347107438, "grad_norm": 1.6760151386260986, "learning_rate": 8.092550934664228e-07, "loss": 0.0222, "step": 999 }, { "epoch": 0.8264462809917356, "grad_norm": 1.6025710105895996, "learning_rate": 8.018140459416962e-07, "loss": 0.0443, "step": 1000 }, { "epoch": 0.8272727272727273, "grad_norm": 0.74948650598526, "learning_rate": 7.944043833415044e-07, "loss": 0.127, "step": 1001 }, { "epoch": 0.828099173553719, "grad_norm": 0.7373968362808228, "learning_rate": 7.870261610592256e-07, "loss": 0.1218, "step": 1002 }, { "epoch": 0.8289256198347107, "grad_norm": 0.8300755620002747, "learning_rate": 7.796794342531949e-07, "loss": 0.1385, "step": 1003 }, { "epoch": 0.8297520661157025, "grad_norm": 0.9344066977500916, "learning_rate": 7.723642578462948e-07, "loss": 0.1622, "step": 1004 }, { "epoch": 0.8305785123966942, "grad_norm": 0.7487844228744507, "learning_rate": 7.650806865255361e-07, "loss": 0.1309, "step": 1005 }, { "epoch": 0.8314049586776859, "grad_norm": 1.4011222124099731, "learning_rate": 7.57828774741664e-07, "loss": 0.0729, "step": 1006 }, { "epoch": 0.8322314049586776, "grad_norm": 1.5047969818115234, "learning_rate": 7.506085767087385e-07, "loss": 0.0214, "step": 1007 }, { "epoch": 0.8330578512396695, "grad_norm": 0.8907939791679382, "learning_rate": 7.434201464037288e-07, "loss": 0.0071, "step": 1008 }, { "epoch": 0.8338842975206612, "grad_norm": 0.5046177506446838, "learning_rate": 7.362635375661225e-07, "loss": 0.0095, "step": 1009 }, { "epoch": 0.8347107438016529, "grad_norm": 0.3181898295879364, "learning_rate": 7.291388036975073e-07, "loss": 0.003, "step": 1010 }, { "epoch": 0.8355371900826446, "grad_norm": 1.6783201694488525, "learning_rate": 7.220459980611838e-07, "loss": 0.0267, "step": 1011 }, { "epoch": 0.8363636363636363, "grad_norm": 1.0363799333572388, "learning_rate": 7.149851736817609e-07, "loss": 0.0146, "step": 1012 }, { "epoch": 0.8371900826446281, "grad_norm": 1.1079469919204712, "learning_rate": 7.079563833447617e-07, "loss": 0.0426, "step": 1013 }, { "epoch": 0.8380165289256198, "grad_norm": 0.05618565157055855, "learning_rate": 7.009596795962275e-07, "loss": 0.0007, "step": 1014 }, { "epoch": 0.8388429752066116, "grad_norm": 1.1225967407226562, "learning_rate": 6.939951147423269e-07, "loss": 0.0136, "step": 1015 }, { "epoch": 0.8396694214876033, "grad_norm": 1.6481060981750488, "learning_rate": 6.870627408489616e-07, "loss": 0.1562, "step": 1016 }, { "epoch": 0.8404958677685951, "grad_norm": 2.299081802368164, "learning_rate": 6.801626097413816e-07, "loss": 0.2741, "step": 1017 }, { "epoch": 0.8413223140495868, "grad_norm": 1.3912934064865112, "learning_rate": 6.732947730037936e-07, "loss": 0.2398, "step": 1018 }, { "epoch": 0.8421487603305785, "grad_norm": 2.0209543704986572, "learning_rate": 6.664592819789778e-07, "loss": 0.2426, "step": 1019 }, { "epoch": 0.8429752066115702, "grad_norm": 1.496512770652771, "learning_rate": 6.596561877679037e-07, "loss": 0.2415, "step": 1020 }, { "epoch": 0.843801652892562, "grad_norm": 1.5533783435821533, "learning_rate": 6.52885541229345e-07, "loss": 0.2283, "step": 1021 }, { "epoch": 0.8446280991735537, "grad_norm": 1.572188377380371, "learning_rate": 6.461473929795053e-07, "loss": 0.2244, "step": 1022 }, { "epoch": 0.8454545454545455, "grad_norm": 2.724888563156128, "learning_rate": 6.394417933916375e-07, "loss": 0.1038, "step": 1023 }, { "epoch": 0.8462809917355372, "grad_norm": 0.945579469203949, "learning_rate": 6.327687925956616e-07, "loss": 0.0157, "step": 1024 }, { "epoch": 0.8471074380165289, "grad_norm": 2.450042247772217, "learning_rate": 6.261284404777979e-07, "loss": 0.0571, "step": 1025 }, { "epoch": 0.8479338842975207, "grad_norm": 0.7468518614768982, "learning_rate": 6.1952078668019e-07, "loss": 0.1228, "step": 1026 }, { "epoch": 0.8487603305785124, "grad_norm": 0.7207930088043213, "learning_rate": 6.12945880600535e-07, "loss": 0.1161, "step": 1027 }, { "epoch": 0.8495867768595041, "grad_norm": 0.823848307132721, "learning_rate": 6.064037713917131e-07, "loss": 0.1232, "step": 1028 }, { "epoch": 0.8504132231404958, "grad_norm": 0.7894586324691772, "learning_rate": 5.998945079614199e-07, "loss": 0.1236, "step": 1029 }, { "epoch": 0.8512396694214877, "grad_norm": 0.7570236921310425, "learning_rate": 5.93418138971803e-07, "loss": 0.1066, "step": 1030 }, { "epoch": 0.8520661157024794, "grad_norm": 0.8137221932411194, "learning_rate": 5.869747128390963e-07, "loss": 0.0593, "step": 1031 }, { "epoch": 0.8528925619834711, "grad_norm": 0.5652878880500793, "learning_rate": 5.80564277733256e-07, "loss": 0.0083, "step": 1032 }, { "epoch": 0.8537190082644628, "grad_norm": 0.9958022236824036, "learning_rate": 5.741868815776081e-07, "loss": 0.0204, "step": 1033 }, { "epoch": 0.8545454545454545, "grad_norm": 0.49832838773727417, "learning_rate": 5.678425720484815e-07, "loss": 0.0112, "step": 1034 }, { "epoch": 0.8553719008264463, "grad_norm": 0.7005866169929504, "learning_rate": 5.615313965748531e-07, "loss": 0.0111, "step": 1035 }, { "epoch": 0.856198347107438, "grad_norm": 0.30058953166007996, "learning_rate": 5.552534023380024e-07, "loss": 0.0027, "step": 1036 }, { "epoch": 0.8570247933884297, "grad_norm": 1.8628147840499878, "learning_rate": 5.490086362711433e-07, "loss": 0.0089, "step": 1037 }, { "epoch": 0.8578512396694215, "grad_norm": 0.12764735519886017, "learning_rate": 5.427971450590868e-07, "loss": 0.002, "step": 1038 }, { "epoch": 0.8586776859504133, "grad_norm": 0.5221362113952637, "learning_rate": 5.366189751378858e-07, "loss": 0.005, "step": 1039 }, { "epoch": 0.859504132231405, "grad_norm": 0.3846019208431244, "learning_rate": 5.304741726944873e-07, "loss": 0.0044, "step": 1040 }, { "epoch": 0.8603305785123967, "grad_norm": 0.1011054664850235, "learning_rate": 5.243627836663906e-07, "loss": 0.0009, "step": 1041 }, { "epoch": 0.8611570247933884, "grad_norm": 2.067995309829712, "learning_rate": 5.18284853741301e-07, "loss": 0.2141, "step": 1042 }, { "epoch": 0.8619834710743801, "grad_norm": 1.9596076011657715, "learning_rate": 5.122404283567889e-07, "loss": 0.253, "step": 1043 }, { "epoch": 0.8628099173553719, "grad_norm": 2.1681344509124756, "learning_rate": 5.062295526999522e-07, "loss": 0.2268, "step": 1044 }, { "epoch": 0.8636363636363636, "grad_norm": 2.6632518768310547, "learning_rate": 5.002522717070751e-07, "loss": 0.2322, "step": 1045 }, { "epoch": 0.8644628099173554, "grad_norm": 2.1616790294647217, "learning_rate": 4.943086300632921e-07, "loss": 0.2325, "step": 1046 }, { "epoch": 0.8652892561983471, "grad_norm": 1.9508146047592163, "learning_rate": 4.88398672202261e-07, "loss": 0.2253, "step": 1047 }, { "epoch": 0.8661157024793389, "grad_norm": 1.3169227838516235, "learning_rate": 4.8252244230582e-07, "loss": 0.0584, "step": 1048 }, { "epoch": 0.8669421487603306, "grad_norm": 1.065989375114441, "learning_rate": 4.766799843036651e-07, "loss": 0.015, "step": 1049 }, { "epoch": 0.8677685950413223, "grad_norm": 2.5509748458862305, "learning_rate": 4.7087134187302095e-07, "loss": 0.0435, "step": 1050 }, { "epoch": 0.868595041322314, "grad_norm": 0.6893365383148193, "learning_rate": 4.6509655843830827e-07, "loss": 0.1141, "step": 1051 }, { "epoch": 0.8694214876033057, "grad_norm": 0.8257653713226318, "learning_rate": 4.5935567717082796e-07, "loss": 0.1358, "step": 1052 }, { "epoch": 0.8702479338842976, "grad_norm": 0.8547446131706238, "learning_rate": 4.536487409884327e-07, "loss": 0.137, "step": 1053 }, { "epoch": 0.8710743801652893, "grad_norm": 0.694800615310669, "learning_rate": 4.4797579255520585e-07, "loss": 0.1082, "step": 1054 }, { "epoch": 0.871900826446281, "grad_norm": 0.8044619560241699, "learning_rate": 4.423368742811468e-07, "loss": 0.1431, "step": 1055 }, { "epoch": 0.8727272727272727, "grad_norm": 0.7153838276863098, "learning_rate": 4.3673202832184956e-07, "loss": 0.071, "step": 1056 }, { "epoch": 0.8735537190082645, "grad_norm": 1.5677008628845215, "learning_rate": 4.311612965781903e-07, "loss": 0.0297, "step": 1057 }, { "epoch": 0.8743801652892562, "grad_norm": 0.2722497582435608, "learning_rate": 4.2562472069601236e-07, "loss": 0.0031, "step": 1058 }, { "epoch": 0.8752066115702479, "grad_norm": 0.06443261355161667, "learning_rate": 4.2012234206581346e-07, "loss": 0.0013, "step": 1059 }, { "epoch": 0.8760330578512396, "grad_norm": 0.1994827389717102, "learning_rate": 4.1465420182244476e-07, "loss": 0.0017, "step": 1060 }, { "epoch": 0.8768595041322315, "grad_norm": 0.4848335087299347, "learning_rate": 4.0922034084479146e-07, "loss": 0.0037, "step": 1061 }, { "epoch": 0.8776859504132232, "grad_norm": 0.6287811994552612, "learning_rate": 4.0382079975547383e-07, "loss": 0.0077, "step": 1062 }, { "epoch": 0.8785123966942149, "grad_norm": 0.4892734885215759, "learning_rate": 3.984556189205441e-07, "loss": 0.0053, "step": 1063 }, { "epoch": 0.8793388429752066, "grad_norm": 0.6679121255874634, "learning_rate": 3.9312483844918146e-07, "loss": 0.0065, "step": 1064 }, { "epoch": 0.8801652892561983, "grad_norm": 0.36687126755714417, "learning_rate": 3.87828498193395e-07, "loss": 0.0064, "step": 1065 }, { "epoch": 0.8809917355371901, "grad_norm": 0.9448103308677673, "learning_rate": 3.8256663774772383e-07, "loss": 0.0244, "step": 1066 }, { "epoch": 0.8818181818181818, "grad_norm": 0.7889144420623779, "learning_rate": 3.773392964489425e-07, "loss": 0.0392, "step": 1067 }, { "epoch": 0.8826446280991735, "grad_norm": 2.57269287109375, "learning_rate": 3.721465133757662e-07, "loss": 0.2697, "step": 1068 }, { "epoch": 0.8834710743801653, "grad_norm": 1.8215274810791016, "learning_rate": 3.669883273485575e-07, "loss": 0.2545, "step": 1069 }, { "epoch": 0.8842975206611571, "grad_norm": 1.8314193487167358, "learning_rate": 3.6186477692903955e-07, "loss": 0.2476, "step": 1070 }, { "epoch": 0.8851239669421488, "grad_norm": 2.515815019607544, "learning_rate": 3.5677590042000277e-07, "loss": 0.2235, "step": 1071 }, { "epoch": 0.8859504132231405, "grad_norm": 2.0202386379241943, "learning_rate": 3.5172173586502543e-07, "loss": 0.2506, "step": 1072 }, { "epoch": 0.8867768595041322, "grad_norm": 1.6547911167144775, "learning_rate": 3.46702321048179e-07, "loss": 0.1791, "step": 1073 }, { "epoch": 0.8876033057851239, "grad_norm": 2.1609323024749756, "learning_rate": 3.417176934937588e-07, "loss": 0.0519, "step": 1074 }, { "epoch": 0.8884297520661157, "grad_norm": 1.0010566711425781, "learning_rate": 3.3676789046599045e-07, "loss": 0.0121, "step": 1075 }, { "epoch": 0.8892561983471075, "grad_norm": 0.6641173362731934, "learning_rate": 3.318529489687605e-07, "loss": 0.121, "step": 1076 }, { "epoch": 0.8900826446280992, "grad_norm": 0.7665372490882874, "learning_rate": 3.2697290574533857e-07, "loss": 0.1216, "step": 1077 }, { "epoch": 0.8909090909090909, "grad_norm": 0.8700223565101624, "learning_rate": 3.2212779727809504e-07, "loss": 0.1393, "step": 1078 }, { "epoch": 0.8917355371900827, "grad_norm": 0.8250924944877625, "learning_rate": 3.173176597882388e-07, "loss": 0.1224, "step": 1079 }, { "epoch": 0.8925619834710744, "grad_norm": 0.8952280282974243, "learning_rate": 3.1254252923553994e-07, "loss": 0.0562, "step": 1080 }, { "epoch": 0.8933884297520661, "grad_norm": 0.15683647990226746, "learning_rate": 3.0780244131806193e-07, "loss": 0.0017, "step": 1081 }, { "epoch": 0.8942148760330578, "grad_norm": 0.30751723051071167, "learning_rate": 3.030974314718971e-07, "loss": 0.0047, "step": 1082 }, { "epoch": 0.8950413223140495, "grad_norm": 1.5253392457962036, "learning_rate": 2.9842753487089927e-07, "loss": 0.0208, "step": 1083 }, { "epoch": 0.8958677685950414, "grad_norm": 0.7621084451675415, "learning_rate": 2.937927864264206e-07, "loss": 0.0094, "step": 1084 }, { "epoch": 0.8966942148760331, "grad_norm": 1.3640185594558716, "learning_rate": 2.891932207870546e-07, "loss": 0.0441, "step": 1085 }, { "epoch": 0.8975206611570248, "grad_norm": 0.8421722650527954, "learning_rate": 2.8462887233836945e-07, "loss": 0.0141, "step": 1086 }, { "epoch": 0.8983471074380165, "grad_norm": 1.5583269596099854, "learning_rate": 2.800997752026596e-07, "loss": 0.0277, "step": 1087 }, { "epoch": 0.8991735537190083, "grad_norm": 0.26696208119392395, "learning_rate": 2.756059632386865e-07, "loss": 0.0022, "step": 1088 }, { "epoch": 0.9, "grad_norm": 0.37935540080070496, "learning_rate": 2.7114747004142237e-07, "loss": 0.0112, "step": 1089 }, { "epoch": 0.9008264462809917, "grad_norm": 0.48069116473197937, "learning_rate": 2.667243289418059e-07, "loss": 0.0044, "step": 1090 }, { "epoch": 0.9016528925619834, "grad_norm": 0.2301221340894699, "learning_rate": 2.6233657300648696e-07, "loss": 0.0032, "step": 1091 }, { "epoch": 0.9024793388429752, "grad_norm": 1.219067096710205, "learning_rate": 2.5798423503758385e-07, "loss": 0.0745, "step": 1092 }, { "epoch": 0.903305785123967, "grad_norm": 1.8919721841812134, "learning_rate": 2.5366734757243496e-07, "loss": 0.2512, "step": 1093 }, { "epoch": 0.9041322314049587, "grad_norm": 2.0167336463928223, "learning_rate": 2.4938594288335725e-07, "loss": 0.2505, "step": 1094 }, { "epoch": 0.9049586776859504, "grad_norm": 2.345390796661377, "learning_rate": 2.451400529774045e-07, "loss": 0.2476, "step": 1095 }, { "epoch": 0.9057851239669421, "grad_norm": 1.298659086227417, "learning_rate": 2.4092970959612885e-07, "loss": 0.2136, "step": 1096 }, { "epoch": 0.9066115702479339, "grad_norm": 3.467742919921875, "learning_rate": 2.3675494421533884e-07, "loss": 0.2128, "step": 1097 }, { "epoch": 0.9074380165289256, "grad_norm": 1.8462551832199097, "learning_rate": 2.3261578804487318e-07, "loss": 0.228, "step": 1098 }, { "epoch": 0.9082644628099174, "grad_norm": 2.1398022174835205, "learning_rate": 2.2851227202836002e-07, "loss": 0.0267, "step": 1099 }, { "epoch": 0.9090909090909091, "grad_norm": 1.4924956560134888, "learning_rate": 2.2444442684298572e-07, "loss": 0.0198, "step": 1100 }, { "epoch": 0.9099173553719008, "grad_norm": 0.5752552151679993, "learning_rate": 2.2041228289927108e-07, "loss": 0.0939, "step": 1101 }, { "epoch": 0.9107438016528926, "grad_norm": 0.7368069887161255, "learning_rate": 2.1641587034083756e-07, "loss": 0.1024, "step": 1102 }, { "epoch": 0.9115702479338843, "grad_norm": 0.7973672151565552, "learning_rate": 2.1245521904418643e-07, "loss": 0.1332, "step": 1103 }, { "epoch": 0.912396694214876, "grad_norm": 0.8172441720962524, "learning_rate": 2.0853035861847448e-07, "loss": 0.1282, "step": 1104 }, { "epoch": 0.9132231404958677, "grad_norm": 1.035966396331787, "learning_rate": 2.0464131840528978e-07, "loss": 0.152, "step": 1105 }, { "epoch": 0.9140495867768595, "grad_norm": 0.4986271262168884, "learning_rate": 2.0078812747843623e-07, "loss": 0.0042, "step": 1106 }, { "epoch": 0.9148760330578513, "grad_norm": 0.4449491500854492, "learning_rate": 1.9697081464371437e-07, "loss": 0.0032, "step": 1107 }, { "epoch": 0.915702479338843, "grad_norm": 1.5130363702774048, "learning_rate": 1.9318940843870594e-07, "loss": 0.0267, "step": 1108 }, { "epoch": 0.9165289256198347, "grad_norm": 0.3523405194282532, "learning_rate": 1.894439371325607e-07, "loss": 0.0044, "step": 1109 }, { "epoch": 0.9173553719008265, "grad_norm": 0.5672593116760254, "learning_rate": 1.8573442872578617e-07, "loss": 0.0059, "step": 1110 }, { "epoch": 0.9181818181818182, "grad_norm": 0.6381686925888062, "learning_rate": 1.8206091095003543e-07, "loss": 0.0057, "step": 1111 }, { "epoch": 0.9190082644628099, "grad_norm": 0.9101113677024841, "learning_rate": 1.7842341126790508e-07, "loss": 0.0104, "step": 1112 }, { "epoch": 0.9198347107438016, "grad_norm": 0.34019139409065247, "learning_rate": 1.7482195687272163e-07, "loss": 0.0035, "step": 1113 }, { "epoch": 0.9206611570247933, "grad_norm": 1.2434287071228027, "learning_rate": 1.7125657468834656e-07, "loss": 0.0246, "step": 1114 }, { "epoch": 0.9214876033057852, "grad_norm": 0.4532994329929352, "learning_rate": 1.6772729136897314e-07, "loss": 0.0095, "step": 1115 }, { "epoch": 0.9223140495867769, "grad_norm": 1.2381685972213745, "learning_rate": 1.6423413329892168e-07, "loss": 0.0225, "step": 1116 }, { "epoch": 0.9231404958677686, "grad_norm": 0.33696889877319336, "learning_rate": 1.6077712659244792e-07, "loss": 0.0024, "step": 1117 }, { "epoch": 0.9239669421487603, "grad_norm": 1.3697483539581299, "learning_rate": 1.573562970935466e-07, "loss": 0.1577, "step": 1118 }, { "epoch": 0.9247933884297521, "grad_norm": 1.9480425119400024, "learning_rate": 1.5397167037575823e-07, "loss": 0.2501, "step": 1119 }, { "epoch": 0.9256198347107438, "grad_norm": 1.6084264516830444, "learning_rate": 1.5062327174197645e-07, "loss": 0.239, "step": 1120 }, { "epoch": 0.9264462809917355, "grad_norm": 1.976704478263855, "learning_rate": 1.473111262242599e-07, "loss": 0.2445, "step": 1121 }, { "epoch": 0.9272727272727272, "grad_norm": 2.031085968017578, "learning_rate": 1.4403525858364576e-07, "loss": 0.218, "step": 1122 }, { "epoch": 0.928099173553719, "grad_norm": 1.7920631170272827, "learning_rate": 1.4079569330996412e-07, "loss": 0.1471, "step": 1123 }, { "epoch": 0.9289256198347108, "grad_norm": 1.3517217636108398, "learning_rate": 1.3759245462165282e-07, "loss": 0.0195, "step": 1124 }, { "epoch": 0.9297520661157025, "grad_norm": 2.0068581104278564, "learning_rate": 1.344255664655808e-07, "loss": 0.0391, "step": 1125 }, { "epoch": 0.9305785123966942, "grad_norm": 0.8138121962547302, "learning_rate": 1.3129505251686603e-07, "loss": 0.1505, "step": 1126 }, { "epoch": 0.9314049586776859, "grad_norm": 0.7338080406188965, "learning_rate": 1.2820093617869733e-07, "loss": 0.1178, "step": 1127 }, { "epoch": 0.9322314049586777, "grad_norm": 0.7904165983200073, "learning_rate": 1.25143240582164e-07, "loss": 0.1352, "step": 1128 }, { "epoch": 0.9330578512396694, "grad_norm": 0.8109901547431946, "learning_rate": 1.2212198858607694e-07, "loss": 0.1341, "step": 1129 }, { "epoch": 0.9338842975206612, "grad_norm": 0.9228838086128235, "learning_rate": 1.191372027768034e-07, "loss": 0.1339, "step": 1130 }, { "epoch": 0.9347107438016529, "grad_norm": 0.7603052854537964, "learning_rate": 1.1618890546809425e-07, "loss": 0.1033, "step": 1131 }, { "epoch": 0.9355371900826446, "grad_norm": 0.24581223726272583, "learning_rate": 1.1327711870091963e-07, "loss": 0.0024, "step": 1132 }, { "epoch": 0.9363636363636364, "grad_norm": 0.3206579387187958, "learning_rate": 1.1040186424330191e-07, "loss": 0.0037, "step": 1133 }, { "epoch": 0.9371900826446281, "grad_norm": 1.1099294424057007, "learning_rate": 1.0756316359015528e-07, "loss": 0.0281, "step": 1134 }, { "epoch": 0.9380165289256198, "grad_norm": 0.13626572489738464, "learning_rate": 1.0476103796312254e-07, "loss": 0.0023, "step": 1135 }, { "epoch": 0.9388429752066115, "grad_norm": 0.4995996057987213, "learning_rate": 1.0199550831041904e-07, "loss": 0.0095, "step": 1136 }, { "epoch": 0.9396694214876034, "grad_norm": 0.7871412634849548, "learning_rate": 9.926659530667294e-08, "loss": 0.0049, "step": 1137 }, { "epoch": 0.9404958677685951, "grad_norm": 2.2005467414855957, "learning_rate": 9.657431935277629e-08, "loss": 0.0149, "step": 1138 }, { "epoch": 0.9413223140495868, "grad_norm": 0.9672695398330688, "learning_rate": 9.391870057572527e-08, "loss": 0.0098, "step": 1139 }, { "epoch": 0.9421487603305785, "grad_norm": 0.46287235617637634, "learning_rate": 9.129975882847363e-08, "loss": 0.0023, "step": 1140 }, { "epoch": 0.9429752066115702, "grad_norm": 0.8012919425964355, "learning_rate": 8.871751368978554e-08, "loss": 0.0055, "step": 1141 }, { "epoch": 0.943801652892562, "grad_norm": 1.724612832069397, "learning_rate": 8.617198446408736e-08, "loss": 0.0535, "step": 1142 }, { "epoch": 0.9446280991735537, "grad_norm": 1.8171989917755127, "learning_rate": 8.366319018132229e-08, "loss": 0.2232, "step": 1143 }, { "epoch": 0.9454545454545454, "grad_norm": 2.0113537311553955, "learning_rate": 8.119114959680929e-08, "loss": 0.2322, "step": 1144 }, { "epoch": 0.9462809917355371, "grad_norm": 4.474810600280762, "learning_rate": 7.875588119110377e-08, "loss": 0.2435, "step": 1145 }, { "epoch": 0.947107438016529, "grad_norm": 2.493525266647339, "learning_rate": 7.635740316985885e-08, "loss": 0.2691, "step": 1146 }, { "epoch": 0.9479338842975207, "grad_norm": 1.6824287176132202, "learning_rate": 7.399573346368871e-08, "loss": 0.2223, "step": 1147 }, { "epoch": 0.9487603305785124, "grad_norm": 1.6271603107452393, "learning_rate": 7.167088972803326e-08, "loss": 0.1699, "step": 1148 }, { "epoch": 0.9495867768595041, "grad_norm": 1.3928841352462769, "learning_rate": 6.938288934303038e-08, "loss": 0.0138, "step": 1149 }, { "epoch": 0.9504132231404959, "grad_norm": 1.9528048038482666, "learning_rate": 6.713174941338163e-08, "loss": 0.0388, "step": 1150 }, { "epoch": 0.9512396694214876, "grad_norm": 0.7475579380989075, "learning_rate": 6.491748676822618e-08, "loss": 0.1071, "step": 1151 }, { "epoch": 0.9520661157024793, "grad_norm": 0.855401873588562, "learning_rate": 6.274011796101598e-08, "loss": 0.14, "step": 1152 }, { "epoch": 0.952892561983471, "grad_norm": 0.7454251646995544, "learning_rate": 6.05996592693886e-08, "loss": 0.1126, "step": 1153 }, { "epoch": 0.9537190082644628, "grad_norm": 0.8808317184448242, "learning_rate": 5.849612669505067e-08, "loss": 0.1207, "step": 1154 }, { "epoch": 0.9545454545454546, "grad_norm": 0.48413702845573425, "learning_rate": 5.642953596365408e-08, "loss": 0.052, "step": 1155 }, { "epoch": 0.9553719008264463, "grad_norm": 0.7997721433639526, "learning_rate": 5.439990252467886e-08, "loss": 0.0074, "step": 1156 }, { "epoch": 0.956198347107438, "grad_norm": 1.7531133890151978, "learning_rate": 5.2407241551320485e-08, "loss": 0.0149, "step": 1157 }, { "epoch": 0.9570247933884297, "grad_norm": 2.015205144882202, "learning_rate": 5.0451567940373316e-08, "loss": 0.023, "step": 1158 }, { "epoch": 0.9578512396694215, "grad_norm": 0.574540376663208, "learning_rate": 4.853289631212066e-08, "loss": 0.0048, "step": 1159 }, { "epoch": 0.9586776859504132, "grad_norm": 0.636974573135376, "learning_rate": 4.6651241010226e-08, "loss": 0.0141, "step": 1160 }, { "epoch": 0.959504132231405, "grad_norm": 0.5378000736236572, "learning_rate": 4.4806616101624176e-08, "loss": 0.0081, "step": 1161 }, { "epoch": 0.9603305785123967, "grad_norm": 0.7162144184112549, "learning_rate": 4.299903537641703e-08, "loss": 0.0133, "step": 1162 }, { "epoch": 0.9611570247933884, "grad_norm": 0.23031413555145264, "learning_rate": 4.122851234777181e-08, "loss": 0.0021, "step": 1163 }, { "epoch": 0.9619834710743802, "grad_norm": 1.0872267484664917, "learning_rate": 3.949506025181626e-08, "loss": 0.0097, "step": 1164 }, { "epoch": 0.9628099173553719, "grad_norm": 0.7706602215766907, "learning_rate": 3.779869204754427e-08, "loss": 0.0175, "step": 1165 }, { "epoch": 0.9636363636363636, "grad_norm": 0.4708734154701233, "learning_rate": 3.613942041671703e-08, "loss": 0.0054, "step": 1166 }, { "epoch": 0.9644628099173553, "grad_norm": 1.5092543363571167, "learning_rate": 3.451725776376647e-08, "loss": 0.232, "step": 1167 }, { "epoch": 0.9652892561983472, "grad_norm": 1.9864728450775146, "learning_rate": 3.2932216215704195e-08, "loss": 0.2257, "step": 1168 }, { "epoch": 0.9661157024793389, "grad_norm": 3.1599490642547607, "learning_rate": 3.138430762203215e-08, "loss": 0.2442, "step": 1169 }, { "epoch": 0.9669421487603306, "grad_norm": 1.5999311208724976, "learning_rate": 2.9873543554652106e-08, "loss": 0.2185, "step": 1170 }, { "epoch": 0.9677685950413223, "grad_norm": 1.9940649271011353, "learning_rate": 2.8399935307778516e-08, "loss": 0.2622, "step": 1171 }, { "epoch": 0.968595041322314, "grad_norm": 3.0313358306884766, "learning_rate": 2.6963493897856906e-08, "loss": 0.2309, "step": 1172 }, { "epoch": 0.9694214876033058, "grad_norm": 2.1844117641448975, "learning_rate": 2.5564230063478413e-08, "loss": 0.1205, "step": 1173 }, { "epoch": 0.9702479338842975, "grad_norm": 1.7357497215270996, "learning_rate": 2.420215426530259e-08, "loss": 0.0307, "step": 1174 }, { "epoch": 0.9710743801652892, "grad_norm": 1.7013660669326782, "learning_rate": 2.287727668597528e-08, "loss": 0.0221, "step": 1175 }, { "epoch": 0.971900826446281, "grad_norm": 0.6760327816009521, "learning_rate": 2.1589607230056432e-08, "loss": 0.1024, "step": 1176 }, { "epoch": 0.9727272727272728, "grad_norm": 0.7643543481826782, "learning_rate": 2.0339155523945164e-08, "loss": 0.128, "step": 1177 }, { "epoch": 0.9735537190082645, "grad_norm": 0.8929775357246399, "learning_rate": 1.912593091580428e-08, "loss": 0.1308, "step": 1178 }, { "epoch": 0.9743801652892562, "grad_norm": 0.7659059762954712, "learning_rate": 1.794994247549586e-08, "loss": 0.1352, "step": 1179 }, { "epoch": 0.9752066115702479, "grad_norm": 1.4182361364364624, "learning_rate": 1.681119899450856e-08, "loss": 0.0921, "step": 1180 }, { "epoch": 0.9760330578512396, "grad_norm": 1.379634976387024, "learning_rate": 1.5709708985895965e-08, "loss": 0.0155, "step": 1181 }, { "epoch": 0.9768595041322314, "grad_norm": 0.48459118604660034, "learning_rate": 1.4645480684210011e-08, "loss": 0.0034, "step": 1182 }, { "epoch": 0.9776859504132231, "grad_norm": 0.9793571829795837, "learning_rate": 1.3618522045439897e-08, "loss": 0.0076, "step": 1183 }, { "epoch": 0.9785123966942149, "grad_norm": 0.23963485658168793, "learning_rate": 1.2628840746954362e-08, "loss": 0.002, "step": 1184 }, { "epoch": 0.9793388429752066, "grad_norm": 0.8089652061462402, "learning_rate": 1.1676444187442848e-08, "loss": 0.0082, "step": 1185 }, { "epoch": 0.9801652892561984, "grad_norm": 0.12997634708881378, "learning_rate": 1.0761339486859424e-08, "loss": 0.0014, "step": 1186 }, { "epoch": 0.9809917355371901, "grad_norm": 1.119914174079895, "learning_rate": 9.883533486371721e-09, "loss": 0.014, "step": 1187 }, { "epoch": 0.9818181818181818, "grad_norm": 0.23493412137031555, "learning_rate": 9.0430327483082e-09, "loss": 0.0092, "step": 1188 }, { "epoch": 0.9826446280991735, "grad_norm": 1.9524502754211426, "learning_rate": 8.239843556108739e-09, "loss": 0.0103, "step": 1189 }, { "epoch": 0.9834710743801653, "grad_norm": 0.958412230014801, "learning_rate": 7.473971914280786e-09, "loss": 0.0131, "step": 1190 }, { "epoch": 0.984297520661157, "grad_norm": 0.4178364872932434, "learning_rate": 6.7454235483488395e-09, "loss": 0.0058, "step": 1191 }, { "epoch": 0.9851239669421488, "grad_norm": 1.409676194190979, "learning_rate": 6.054203904817812e-09, "loss": 0.0928, "step": 1192 }, { "epoch": 0.9859504132231405, "grad_norm": 1.602060317993164, "learning_rate": 5.400318151127515e-09, "loss": 0.2004, "step": 1193 }, { "epoch": 0.9867768595041322, "grad_norm": 1.7008346319198608, "learning_rate": 4.783771175617124e-09, "loss": 0.239, "step": 1194 }, { "epoch": 0.987603305785124, "grad_norm": 2.2031989097595215, "learning_rate": 4.204567587486885e-09, "loss": 0.2539, "step": 1195 }, { "epoch": 0.9884297520661157, "grad_norm": 2.037137508392334, "learning_rate": 3.6627117167642447e-09, "loss": 0.2378, "step": 1196 }, { "epoch": 0.9892561983471074, "grad_norm": 2.461138963699341, "learning_rate": 3.158207614272213e-09, "loss": 0.2525, "step": 1197 }, { "epoch": 0.9900826446280991, "grad_norm": 1.2552220821380615, "learning_rate": 2.6910590515966117e-09, "loss": 0.0538, "step": 1198 }, { "epoch": 0.990909090909091, "grad_norm": 6.865564346313477, "learning_rate": 2.2612695210616486e-09, "loss": 0.0893, "step": 1199 }, { "epoch": 0.9917355371900827, "grad_norm": 2.34413480758667, "learning_rate": 1.8688422357004963e-09, "loss": 0.0229, "step": 1200 }, { "epoch": 0.9925619834710744, "grad_norm": 0.7144143581390381, "learning_rate": 1.5137801292325338e-09, "loss": 0.1281, "step": 1201 }, { "epoch": 0.9933884297520661, "grad_norm": 0.8506456613540649, "learning_rate": 1.1960858560416954e-09, "loss": 0.1282, "step": 1202 }, { "epoch": 0.9942148760330578, "grad_norm": 1.2273684740066528, "learning_rate": 9.157617911570438e-10, "loss": 0.0568, "step": 1203 }, { "epoch": 0.9950413223140496, "grad_norm": 0.12330927699804306, "learning_rate": 6.728100302327844e-10, "loss": 0.0013, "step": 1204 }, { "epoch": 0.9958677685950413, "grad_norm": 1.1877310276031494, "learning_rate": 4.67232389535499e-10, "loss": 0.0118, "step": 1205 }, { "epoch": 0.996694214876033, "grad_norm": 0.7564953565597534, "learning_rate": 2.99030405928602e-10, "loss": 0.0049, "step": 1206 }, { "epoch": 0.9975206611570248, "grad_norm": 1.135886311531067, "learning_rate": 1.6820533686179308e-10, "loss": 0.0813, "step": 1207 }, { "epoch": 0.9983471074380166, "grad_norm": 2.0573935508728027, "learning_rate": 7.475816036051075e-11, "loss": 0.2733, "step": 1208 }, { "epoch": 0.9991735537190083, "grad_norm": 1.533027172088623, "learning_rate": 1.8689575020380825e-11, "loss": 0.2453, "step": 1209 }, { "epoch": 1.0, "grad_norm": 1.0230895280838013, "learning_rate": 0.0, "loss": 0.0737, "step": 1210 }, { "epoch": 1.0, "step": 1210, "total_flos": 56759944347648.0, "train_loss": 0.2560723489493878, "train_runtime": 6836.3212, "train_samples_per_second": 2.831, "train_steps_per_second": 0.177 } ], "logging_steps": 1.0, "max_steps": 1210, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 56759944347648.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }