{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1896, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004219409282700422, "grad_norm": 6.465786457061768, "learning_rate": 1.0526315789473685e-07, "loss": 2.199237823486328, "step": 2 }, { "epoch": 0.008438818565400843, "grad_norm": 6.138082981109619, "learning_rate": 3.1578947368421055e-07, "loss": 1.7785427570343018, "step": 4 }, { "epoch": 0.012658227848101266, "grad_norm": 1.5081427097320557, "learning_rate": 5.263157894736843e-07, "loss": 1.9374568462371826, "step": 6 }, { "epoch": 0.016877637130801686, "grad_norm": 2.888887882232666, "learning_rate": 7.368421052631579e-07, "loss": 1.9380292892456055, "step": 8 }, { "epoch": 0.02109704641350211, "grad_norm": 4.559475898742676, "learning_rate": 9.473684210526317e-07, "loss": 1.8323544263839722, "step": 10 }, { "epoch": 0.02531645569620253, "grad_norm": 1.0213398933410645, "learning_rate": 1.1578947368421053e-06, "loss": 1.29737389087677, "step": 12 }, { "epoch": 0.029535864978902954, "grad_norm": 2.1303820610046387, "learning_rate": 1.3684210526315791e-06, "loss": 1.6070220470428467, "step": 14 }, { "epoch": 0.03375527426160337, "grad_norm": 3.2898736000061035, "learning_rate": 1.5789473684210526e-06, "loss": 1.9115804433822632, "step": 16 }, { "epoch": 0.0379746835443038, "grad_norm": 0.9824860692024231, "learning_rate": 1.7894736842105265e-06, "loss": 1.6911016702651978, "step": 18 }, { "epoch": 0.04219409282700422, "grad_norm": 1.3768422603607178, "learning_rate": 2.0000000000000003e-06, "loss": 1.7770113945007324, "step": 20 }, { "epoch": 0.046413502109704644, "grad_norm": 1.0032649040222168, "learning_rate": 2.2105263157894738e-06, "loss": 1.4084525108337402, "step": 22 }, { "epoch": 0.05063291139240506, "grad_norm": 6.045759201049805, "learning_rate": 2.4210526315789477e-06, "loss": 1.5324207544326782, "step": 24 }, { "epoch": 0.05485232067510549, "grad_norm": 1.592543601989746, "learning_rate": 2.631578947368421e-06, "loss": 1.2799831628799438, "step": 26 }, { "epoch": 0.05907172995780591, "grad_norm": 1.5376907587051392, "learning_rate": 2.842105263157895e-06, "loss": 1.684704065322876, "step": 28 }, { "epoch": 0.06329113924050633, "grad_norm": 1.4627753496170044, "learning_rate": 3.052631578947369e-06, "loss": 1.276880145072937, "step": 30 }, { "epoch": 0.06751054852320675, "grad_norm": 2.527453899383545, "learning_rate": 3.2631578947368423e-06, "loss": 1.5167211294174194, "step": 32 }, { "epoch": 0.07172995780590717, "grad_norm": 6.948500156402588, "learning_rate": 3.473684210526316e-06, "loss": 0.9400781393051147, "step": 34 }, { "epoch": 0.0759493670886076, "grad_norm": 2.278308391571045, "learning_rate": 3.6842105263157896e-06, "loss": 1.5309321880340576, "step": 36 }, { "epoch": 0.08016877637130802, "grad_norm": 3.701179027557373, "learning_rate": 3.894736842105263e-06, "loss": 1.1039892435073853, "step": 38 }, { "epoch": 0.08438818565400844, "grad_norm": 1.0328092575073242, "learning_rate": 4.105263157894737e-06, "loss": 1.4938355684280396, "step": 40 }, { "epoch": 0.08860759493670886, "grad_norm": 2.642683506011963, "learning_rate": 4.315789473684211e-06, "loss": 1.0529941320419312, "step": 42 }, { "epoch": 0.09282700421940929, "grad_norm": 3.77479887008667, "learning_rate": 4.526315789473685e-06, "loss": 1.7686446905136108, "step": 44 }, { "epoch": 0.0970464135021097, "grad_norm": 3.5789642333984375, "learning_rate": 4.736842105263158e-06, "loss": 1.6447981595993042, "step": 46 }, { "epoch": 0.10126582278481013, "grad_norm": 0.9147924184799194, "learning_rate": 4.947368421052632e-06, "loss": 1.5085883140563965, "step": 48 }, { "epoch": 0.10548523206751055, "grad_norm": 55.66002655029297, "learning_rate": 5.157894736842106e-06, "loss": 0.7800276875495911, "step": 50 }, { "epoch": 0.10970464135021098, "grad_norm": 3.080514669418335, "learning_rate": 5.36842105263158e-06, "loss": 0.8507890701293945, "step": 52 }, { "epoch": 0.11392405063291139, "grad_norm": 1.7043066024780273, "learning_rate": 5.578947368421052e-06, "loss": 0.7773736715316772, "step": 54 }, { "epoch": 0.11814345991561181, "grad_norm": 0.8520327210426331, "learning_rate": 5.789473684210527e-06, "loss": 1.370112657546997, "step": 56 }, { "epoch": 0.12236286919831224, "grad_norm": 3.436246395111084, "learning_rate": 6e-06, "loss": 0.6616921424865723, "step": 58 }, { "epoch": 0.12658227848101267, "grad_norm": 1.310256004333496, "learning_rate": 6.2105263157894745e-06, "loss": 1.4200854301452637, "step": 60 }, { "epoch": 0.1308016877637131, "grad_norm": 1.1509495973587036, "learning_rate": 6.421052631578948e-06, "loss": 1.443635106086731, "step": 62 }, { "epoch": 0.1350210970464135, "grad_norm": 0.9931774735450745, "learning_rate": 6.631578947368421e-06, "loss": 1.0624401569366455, "step": 64 }, { "epoch": 0.13924050632911392, "grad_norm": 1.786999225616455, "learning_rate": 6.842105263157896e-06, "loss": 0.8246886134147644, "step": 66 }, { "epoch": 0.14345991561181434, "grad_norm": 1.4146567583084106, "learning_rate": 7.052631578947369e-06, "loss": 1.0782811641693115, "step": 68 }, { "epoch": 0.14767932489451477, "grad_norm": 4.062684059143066, "learning_rate": 7.263157894736843e-06, "loss": 0.9644668698310852, "step": 70 }, { "epoch": 0.1518987341772152, "grad_norm": 1.1023335456848145, "learning_rate": 7.473684210526316e-06, "loss": 1.2576028108596802, "step": 72 }, { "epoch": 0.15611814345991562, "grad_norm": 2.1730892658233643, "learning_rate": 7.68421052631579e-06, "loss": 1.0003982782363892, "step": 74 }, { "epoch": 0.16033755274261605, "grad_norm": 1.9199130535125732, "learning_rate": 7.894736842105265e-06, "loss": 0.8305221796035767, "step": 76 }, { "epoch": 0.16455696202531644, "grad_norm": 1.3110461235046387, "learning_rate": 8.105263157894736e-06, "loss": 1.3285223245620728, "step": 78 }, { "epoch": 0.16877637130801687, "grad_norm": 1.0852832794189453, "learning_rate": 8.315789473684212e-06, "loss": 1.3227169513702393, "step": 80 }, { "epoch": 0.1729957805907173, "grad_norm": 2.09266996383667, "learning_rate": 8.526315789473685e-06, "loss": 1.3691281080245972, "step": 82 }, { "epoch": 0.17721518987341772, "grad_norm": 3.0065836906433105, "learning_rate": 8.736842105263158e-06, "loss": 0.7072535157203674, "step": 84 }, { "epoch": 0.18143459915611815, "grad_norm": 2.310109853744507, "learning_rate": 8.947368421052632e-06, "loss": 1.108911395072937, "step": 86 }, { "epoch": 0.18565400843881857, "grad_norm": 1.5085989236831665, "learning_rate": 9.157894736842105e-06, "loss": 1.2826870679855347, "step": 88 }, { "epoch": 0.189873417721519, "grad_norm": 2.592907667160034, "learning_rate": 9.36842105263158e-06, "loss": 0.6292117238044739, "step": 90 }, { "epoch": 0.1940928270042194, "grad_norm": 1.7466903924942017, "learning_rate": 9.578947368421054e-06, "loss": 1.6944659948349, "step": 92 }, { "epoch": 0.19831223628691982, "grad_norm": 1.627853274345398, "learning_rate": 9.789473684210527e-06, "loss": 0.9387001991271973, "step": 94 }, { "epoch": 0.20253164556962025, "grad_norm": 1.2001192569732666, "learning_rate": 1e-05, "loss": 1.4122728109359741, "step": 96 }, { "epoch": 0.20675105485232068, "grad_norm": 0.6856104135513306, "learning_rate": 9.999972614896371e-06, "loss": 1.4657618999481201, "step": 98 }, { "epoch": 0.2109704641350211, "grad_norm": 11.178488731384277, "learning_rate": 9.999890459918794e-06, "loss": 1.2304973602294922, "step": 100 }, { "epoch": 0.21518987341772153, "grad_norm": 3.910228967666626, "learning_rate": 9.999753536067186e-06, "loss": 1.0468037128448486, "step": 102 }, { "epoch": 0.21940928270042195, "grad_norm": 2.711930990219116, "learning_rate": 9.999561845008071e-06, "loss": 0.986783504486084, "step": 104 }, { "epoch": 0.22362869198312235, "grad_norm": 21.524057388305664, "learning_rate": 9.999315389074552e-06, "loss": 0.9841020107269287, "step": 106 }, { "epoch": 0.22784810126582278, "grad_norm": 1.3347963094711304, "learning_rate": 9.999014171266281e-06, "loss": 0.9823999404907227, "step": 108 }, { "epoch": 0.2320675105485232, "grad_norm": 1.0721721649169922, "learning_rate": 9.99865819524943e-06, "loss": 1.0403262376785278, "step": 110 }, { "epoch": 0.23628691983122363, "grad_norm": 0.9829576015472412, "learning_rate": 9.998247465356636e-06, "loss": 1.3694502115249634, "step": 112 }, { "epoch": 0.24050632911392406, "grad_norm": 1.0071089267730713, "learning_rate": 9.997781986586959e-06, "loss": 1.2698887586593628, "step": 114 }, { "epoch": 0.24472573839662448, "grad_norm": 4.800805568695068, "learning_rate": 9.997261764605815e-06, "loss": 1.6063902378082275, "step": 116 }, { "epoch": 0.2489451476793249, "grad_norm": 1.2748767137527466, "learning_rate": 9.996686805744904e-06, "loss": 1.2578661441802979, "step": 118 }, { "epoch": 0.25316455696202533, "grad_norm": 0.5618524551391602, "learning_rate": 9.996057117002143e-06, "loss": 0.999391496181488, "step": 120 }, { "epoch": 0.25738396624472576, "grad_norm": 1.7549960613250732, "learning_rate": 9.995372706041573e-06, "loss": 1.2668333053588867, "step": 122 }, { "epoch": 0.2616033755274262, "grad_norm": 2.3584682941436768, "learning_rate": 9.994633581193267e-06, "loss": 1.2617768049240112, "step": 124 }, { "epoch": 0.26582278481012656, "grad_norm": 0.8955286741256714, "learning_rate": 9.993839751453232e-06, "loss": 1.3551467657089233, "step": 126 }, { "epoch": 0.270042194092827, "grad_norm": 5.981209754943848, "learning_rate": 9.992991226483287e-06, "loss": 0.8236246109008789, "step": 128 }, { "epoch": 0.2742616033755274, "grad_norm": 1.3256901502609253, "learning_rate": 9.992088016610973e-06, "loss": 1.1401005983352661, "step": 130 }, { "epoch": 0.27848101265822783, "grad_norm": 2.001391887664795, "learning_rate": 9.991130132829391e-06, "loss": 1.2099541425704956, "step": 132 }, { "epoch": 0.28270042194092826, "grad_norm": 3.312189817428589, "learning_rate": 9.990117586797098e-06, "loss": 0.6884139776229858, "step": 134 }, { "epoch": 0.2869198312236287, "grad_norm": 1.1149671077728271, "learning_rate": 9.989050390837953e-06, "loss": 0.8498684763908386, "step": 136 }, { "epoch": 0.2911392405063291, "grad_norm": 2.0233166217803955, "learning_rate": 9.987928557940963e-06, "loss": 1.3585927486419678, "step": 138 }, { "epoch": 0.29535864978902954, "grad_norm": 1.847275733947754, "learning_rate": 9.986752101760134e-06, "loss": 0.9446065425872803, "step": 140 }, { "epoch": 0.29957805907172996, "grad_norm": 1.6885318756103516, "learning_rate": 9.985521036614299e-06, "loss": 1.2848148345947266, "step": 142 }, { "epoch": 0.3037974683544304, "grad_norm": 2.0016934871673584, "learning_rate": 9.984235377486942e-06, "loss": 1.0829672813415527, "step": 144 }, { "epoch": 0.3080168776371308, "grad_norm": 1.3245930671691895, "learning_rate": 9.982895140026027e-06, "loss": 1.374953269958496, "step": 146 }, { "epoch": 0.31223628691983124, "grad_norm": 0.7807157039642334, "learning_rate": 9.981500340543795e-06, "loss": 1.363284945487976, "step": 148 }, { "epoch": 0.31645569620253167, "grad_norm": 1.3550828695297241, "learning_rate": 9.980050996016565e-06, "loss": 1.2079832553863525, "step": 150 }, { "epoch": 0.3206751054852321, "grad_norm": 1.3687413930892944, "learning_rate": 9.97854712408454e-06, "loss": 1.2671327590942383, "step": 152 }, { "epoch": 0.32489451476793246, "grad_norm": 0.667811393737793, "learning_rate": 9.97698874305158e-06, "loss": 1.4603054523468018, "step": 154 }, { "epoch": 0.3291139240506329, "grad_norm": 2.3403422832489014, "learning_rate": 9.97537587188499e-06, "loss": 1.242130160331726, "step": 156 }, { "epoch": 0.3333333333333333, "grad_norm": 0.9113782048225403, "learning_rate": 9.973708530215275e-06, "loss": 1.3086892366409302, "step": 158 }, { "epoch": 0.33755274261603374, "grad_norm": 0.7642857432365417, "learning_rate": 9.97198673833591e-06, "loss": 1.2843017578125, "step": 160 }, { "epoch": 0.34177215189873417, "grad_norm": 2.7208383083343506, "learning_rate": 9.970210517203099e-06, "loss": 0.8658415079116821, "step": 162 }, { "epoch": 0.3459915611814346, "grad_norm": 3.540055513381958, "learning_rate": 9.968379888435508e-06, "loss": 1.2179991006851196, "step": 164 }, { "epoch": 0.350210970464135, "grad_norm": 2.6345081329345703, "learning_rate": 9.966494874314004e-06, "loss": 0.8010786175727844, "step": 166 }, { "epoch": 0.35443037974683544, "grad_norm": 1.9970042705535889, "learning_rate": 9.964555497781395e-06, "loss": 1.2158904075622559, "step": 168 }, { "epoch": 0.35864978902953587, "grad_norm": 0.800459086894989, "learning_rate": 9.962561782442133e-06, "loss": 1.2994709014892578, "step": 170 }, { "epoch": 0.3628691983122363, "grad_norm": 0.83615642786026, "learning_rate": 9.960513752562044e-06, "loss": 1.191404104232788, "step": 172 }, { "epoch": 0.3670886075949367, "grad_norm": 0.9121875166893005, "learning_rate": 9.95841143306802e-06, "loss": 1.0079421997070312, "step": 174 }, { "epoch": 0.37130801687763715, "grad_norm": 1.0342307090759277, "learning_rate": 9.956254849547721e-06, "loss": 1.3034913539886475, "step": 176 }, { "epoch": 0.3755274261603376, "grad_norm": 0.7811413407325745, "learning_rate": 9.954044028249269e-06, "loss": 1.3008990287780762, "step": 178 }, { "epoch": 0.379746835443038, "grad_norm": 1.3971962928771973, "learning_rate": 9.95177899608091e-06, "loss": 0.9854909181594849, "step": 180 }, { "epoch": 0.38396624472573837, "grad_norm": 1.2044034004211426, "learning_rate": 9.949459780610714e-06, "loss": 1.2609633207321167, "step": 182 }, { "epoch": 0.3881856540084388, "grad_norm": 1.2054684162139893, "learning_rate": 9.94708641006621e-06, "loss": 1.2644842863082886, "step": 184 }, { "epoch": 0.3924050632911392, "grad_norm": 1.3307691812515259, "learning_rate": 9.94465891333407e-06, "loss": 0.5214270353317261, "step": 186 }, { "epoch": 0.39662447257383965, "grad_norm": 1.1408305168151855, "learning_rate": 9.942177319959733e-06, "loss": 0.9515210390090942, "step": 188 }, { "epoch": 0.4008438818565401, "grad_norm": 3.7265217304229736, "learning_rate": 9.939641660147067e-06, "loss": 1.0530356168746948, "step": 190 }, { "epoch": 0.4050632911392405, "grad_norm": 1.0529814958572388, "learning_rate": 9.937051964757982e-06, "loss": 1.279091238975525, "step": 192 }, { "epoch": 0.4092827004219409, "grad_norm": 0.9534339904785156, "learning_rate": 9.93440826531207e-06, "loss": 1.0599740743637085, "step": 194 }, { "epoch": 0.41350210970464135, "grad_norm": 0.83598393201828, "learning_rate": 9.93171059398621e-06, "loss": 1.2558493614196777, "step": 196 }, { "epoch": 0.4177215189873418, "grad_norm": 1.3215349912643433, "learning_rate": 9.928958983614187e-06, "loss": 1.0171372890472412, "step": 198 }, { "epoch": 0.4219409282700422, "grad_norm": 1.0270469188690186, "learning_rate": 9.926153467686282e-06, "loss": 1.1477622985839844, "step": 200 }, { "epoch": 0.42616033755274263, "grad_norm": 1.3883006572723389, "learning_rate": 9.92329408034887e-06, "loss": 1.1251156330108643, "step": 202 }, { "epoch": 0.43037974683544306, "grad_norm": 1.1333043575286865, "learning_rate": 9.920380856404002e-06, "loss": 0.9194478988647461, "step": 204 }, { "epoch": 0.4345991561181435, "grad_norm": 1.118269681930542, "learning_rate": 9.917413831308988e-06, "loss": 1.3536955118179321, "step": 206 }, { "epoch": 0.4388185654008439, "grad_norm": 2.772348403930664, "learning_rate": 9.914393041175954e-06, "loss": 0.7396001815795898, "step": 208 }, { "epoch": 0.4430379746835443, "grad_norm": 0.9644083380699158, "learning_rate": 9.911318522771414e-06, "loss": 1.259086012840271, "step": 210 }, { "epoch": 0.4472573839662447, "grad_norm": 2.7526473999023438, "learning_rate": 9.90819031351581e-06, "loss": 0.8133543729782104, "step": 212 }, { "epoch": 0.45147679324894513, "grad_norm": 0.8151541948318481, "learning_rate": 9.905008451483075e-06, "loss": 1.1889218091964722, "step": 214 }, { "epoch": 0.45569620253164556, "grad_norm": 0.921183168888092, "learning_rate": 9.901772975400147e-06, "loss": 1.2350777387619019, "step": 216 }, { "epoch": 0.459915611814346, "grad_norm": 1.7976837158203125, "learning_rate": 9.898483924646516e-06, "loss": 1.2836939096450806, "step": 218 }, { "epoch": 0.4641350210970464, "grad_norm": 1.6381433010101318, "learning_rate": 9.895141339253733e-06, "loss": 1.2279090881347656, "step": 220 }, { "epoch": 0.46835443037974683, "grad_norm": 2.8392746448516846, "learning_rate": 9.891745259904935e-06, "loss": 1.1983016729354858, "step": 222 }, { "epoch": 0.47257383966244726, "grad_norm": 2.3318963050842285, "learning_rate": 9.888295727934333e-06, "loss": 1.0209558010101318, "step": 224 }, { "epoch": 0.4767932489451477, "grad_norm": 1.2104547023773193, "learning_rate": 9.884792785326725e-06, "loss": 1.257072925567627, "step": 226 }, { "epoch": 0.4810126582278481, "grad_norm": 2.3684027194976807, "learning_rate": 9.881236474716976e-06, "loss": 0.7753751873970032, "step": 228 }, { "epoch": 0.48523206751054854, "grad_norm": 2.1228580474853516, "learning_rate": 9.877626839389501e-06, "loss": 0.9030119180679321, "step": 230 }, { "epoch": 0.48945147679324896, "grad_norm": 1.208469033241272, "learning_rate": 9.873963923277737e-06, "loss": 0.8896680474281311, "step": 232 }, { "epoch": 0.4936708860759494, "grad_norm": 1.147818684577942, "learning_rate": 9.870247770963616e-06, "loss": 1.2561113834381104, "step": 234 }, { "epoch": 0.4978902953586498, "grad_norm": 1.6988905668258667, "learning_rate": 9.866478427677009e-06, "loss": 1.3061769008636475, "step": 236 }, { "epoch": 0.5021097046413502, "grad_norm": 3.5365211963653564, "learning_rate": 9.862655939295184e-06, "loss": 0.9927146434783936, "step": 238 }, { "epoch": 0.5063291139240507, "grad_norm": 1.1306407451629639, "learning_rate": 9.858780352342252e-06, "loss": 0.504905104637146, "step": 240 }, { "epoch": 0.510548523206751, "grad_norm": 2.3302314281463623, "learning_rate": 9.854851713988588e-06, "loss": 1.4126393795013428, "step": 242 }, { "epoch": 0.5147679324894515, "grad_norm": 1.7707538604736328, "learning_rate": 9.850870072050268e-06, "loss": 0.865398108959198, "step": 244 }, { "epoch": 0.5189873417721519, "grad_norm": 1.1416205167770386, "learning_rate": 9.846835474988482e-06, "loss": 1.4666553735733032, "step": 246 }, { "epoch": 0.5232067510548524, "grad_norm": 0.8328902721405029, "learning_rate": 9.842747971908943e-06, "loss": 1.175310492515564, "step": 248 }, { "epoch": 0.5274261603375527, "grad_norm": 1.9283004999160767, "learning_rate": 9.838607612561295e-06, "loss": 1.291763424873352, "step": 250 }, { "epoch": 0.5316455696202531, "grad_norm": 1.902482032775879, "learning_rate": 9.834414447338503e-06, "loss": 1.1111410856246948, "step": 252 }, { "epoch": 0.5358649789029536, "grad_norm": 1.0006159543991089, "learning_rate": 9.830168527276238e-06, "loss": 1.2128857374191284, "step": 254 }, { "epoch": 0.540084388185654, "grad_norm": 1.026835560798645, "learning_rate": 9.825869904052261e-06, "loss": 1.1847703456878662, "step": 256 }, { "epoch": 0.5443037974683544, "grad_norm": 1.518582820892334, "learning_rate": 9.821518629985793e-06, "loss": 1.0248626470565796, "step": 258 }, { "epoch": 0.5485232067510548, "grad_norm": 1.5096015930175781, "learning_rate": 9.817114758036874e-06, "loss": 0.9648565053939819, "step": 260 }, { "epoch": 0.5527426160337553, "grad_norm": 1.910677433013916, "learning_rate": 9.81265834180572e-06, "loss": 1.256938099861145, "step": 262 }, { "epoch": 0.5569620253164557, "grad_norm": 1.0666650533676147, "learning_rate": 9.80814943553207e-06, "loss": 1.2715067863464355, "step": 264 }, { "epoch": 0.5611814345991561, "grad_norm": 0.9148522019386292, "learning_rate": 9.80358809409454e-06, "loss": 1.2238779067993164, "step": 266 }, { "epoch": 0.5654008438818565, "grad_norm": 2.0437240600585938, "learning_rate": 9.798974373009924e-06, "loss": 1.4990639686584473, "step": 268 }, { "epoch": 0.569620253164557, "grad_norm": 1.2008134126663208, "learning_rate": 9.794308328432554e-06, "loss": 1.0520625114440918, "step": 270 }, { "epoch": 0.5738396624472574, "grad_norm": 3.0810999870300293, "learning_rate": 9.789590017153587e-06, "loss": 1.310440182685852, "step": 272 }, { "epoch": 0.5780590717299579, "grad_norm": 1.1829187870025635, "learning_rate": 9.784819496600333e-06, "loss": 1.0964314937591553, "step": 274 }, { "epoch": 0.5822784810126582, "grad_norm": 1.9129283428192139, "learning_rate": 9.77999682483555e-06, "loss": 1.2469496726989746, "step": 276 }, { "epoch": 0.5864978902953587, "grad_norm": 2.8708689212799072, "learning_rate": 9.775122060556729e-06, "loss": 1.3884989023208618, "step": 278 }, { "epoch": 0.5907172995780591, "grad_norm": 1.0216045379638672, "learning_rate": 9.770195263095396e-06, "loss": 0.9563537240028381, "step": 280 }, { "epoch": 0.5949367088607594, "grad_norm": 1.04873788356781, "learning_rate": 9.765216492416375e-06, "loss": 1.314202070236206, "step": 282 }, { "epoch": 0.5991561181434599, "grad_norm": 1.0793180465698242, "learning_rate": 9.760185809117065e-06, "loss": 1.53078031539917, "step": 284 }, { "epoch": 0.6033755274261603, "grad_norm": 0.3450990319252014, "learning_rate": 9.755103274426709e-06, "loss": 1.119743824005127, "step": 286 }, { "epoch": 0.6075949367088608, "grad_norm": 0.927954375743866, "learning_rate": 9.74996895020563e-06, "loss": 1.2370059490203857, "step": 288 }, { "epoch": 0.6118143459915611, "grad_norm": 1.6949131488800049, "learning_rate": 9.744782898944496e-06, "loss": 0.8132422566413879, "step": 290 }, { "epoch": 0.6160337552742616, "grad_norm": 0.8690698742866516, "learning_rate": 9.739545183763554e-06, "loss": 0.6778867840766907, "step": 292 }, { "epoch": 0.620253164556962, "grad_norm": 1.065058946609497, "learning_rate": 9.734255868411857e-06, "loss": 1.217564344406128, "step": 294 }, { "epoch": 0.6244725738396625, "grad_norm": 1.3371275663375854, "learning_rate": 9.728915017266494e-06, "loss": 0.7072957158088684, "step": 296 }, { "epoch": 0.6286919831223629, "grad_norm": 11.500582695007324, "learning_rate": 9.723522695331806e-06, "loss": 0.6656824350357056, "step": 298 }, { "epoch": 0.6329113924050633, "grad_norm": 1.48736572265625, "learning_rate": 9.718078968238584e-06, "loss": 1.7741155624389648, "step": 300 }, { "epoch": 0.6371308016877637, "grad_norm": 0.9658617377281189, "learning_rate": 9.712583902243294e-06, "loss": 1.2526522874832153, "step": 302 }, { "epoch": 0.6413502109704642, "grad_norm": 4.880003929138184, "learning_rate": 9.707037564227244e-06, "loss": 0.8751387000083923, "step": 304 }, { "epoch": 0.6455696202531646, "grad_norm": 2.326631546020508, "learning_rate": 9.701440021695784e-06, "loss": 1.0059163570404053, "step": 306 }, { "epoch": 0.6497890295358649, "grad_norm": 0.7995657920837402, "learning_rate": 9.69579134277749e-06, "loss": 1.2537363767623901, "step": 308 }, { "epoch": 0.6540084388185654, "grad_norm": 1.0603656768798828, "learning_rate": 9.690091596223315e-06, "loss": 1.1936452388763428, "step": 310 }, { "epoch": 0.6582278481012658, "grad_norm": 1.9643880128860474, "learning_rate": 9.684340851405771e-06, "loss": 0.9918819665908813, "step": 312 }, { "epoch": 0.6624472573839663, "grad_norm": 0.8007776141166687, "learning_rate": 9.678539178318078e-06, "loss": 1.195359468460083, "step": 314 }, { "epoch": 0.6666666666666666, "grad_norm": 0.9312372207641602, "learning_rate": 9.672686647573312e-06, "loss": 1.09673273563385, "step": 316 }, { "epoch": 0.6708860759493671, "grad_norm": 0.9894766807556152, "learning_rate": 9.666783330403543e-06, "loss": 1.07291579246521, "step": 318 }, { "epoch": 0.6751054852320675, "grad_norm": 1.5419085025787354, "learning_rate": 9.660829298658972e-06, "loss": 1.0736496448516846, "step": 320 }, { "epoch": 0.679324894514768, "grad_norm": 1.2462348937988281, "learning_rate": 9.654824624807057e-06, "loss": 0.8691917657852173, "step": 322 }, { "epoch": 0.6835443037974683, "grad_norm": 0.902093231678009, "learning_rate": 9.648769381931627e-06, "loss": 0.8970058560371399, "step": 324 }, { "epoch": 0.6877637130801688, "grad_norm": 1.1327160596847534, "learning_rate": 9.642663643731993e-06, "loss": 0.8673514723777771, "step": 326 }, { "epoch": 0.6919831223628692, "grad_norm": 3.0607309341430664, "learning_rate": 9.636507484522054e-06, "loss": 0.856316328048706, "step": 328 }, { "epoch": 0.6962025316455697, "grad_norm": 2.566275119781494, "learning_rate": 9.630300979229393e-06, "loss": 1.5781216621398926, "step": 330 }, { "epoch": 0.70042194092827, "grad_norm": 1.6562979221343994, "learning_rate": 9.62404420339436e-06, "loss": 1.0775580406188965, "step": 332 }, { "epoch": 0.7046413502109705, "grad_norm": 0.8775741457939148, "learning_rate": 9.617737233169157e-06, "loss": 1.3338556289672852, "step": 334 }, { "epoch": 0.7088607594936709, "grad_norm": 1.404621958732605, "learning_rate": 9.611380145316913e-06, "loss": 1.248726487159729, "step": 336 }, { "epoch": 0.7130801687763713, "grad_norm": 1.2747576236724854, "learning_rate": 9.60497301721074e-06, "loss": 1.270586609840393, "step": 338 }, { "epoch": 0.7172995780590717, "grad_norm": 1.085620403289795, "learning_rate": 9.598515926832803e-06, "loss": 1.2445173263549805, "step": 340 }, { "epoch": 0.7215189873417721, "grad_norm": 1.1134731769561768, "learning_rate": 9.59200895277336e-06, "loss": 1.2411432266235352, "step": 342 }, { "epoch": 0.7257383966244726, "grad_norm": 10.576135635375977, "learning_rate": 9.58545217422982e-06, "loss": 1.064780354499817, "step": 344 }, { "epoch": 0.729957805907173, "grad_norm": 1.6926047801971436, "learning_rate": 9.578845671005764e-06, "loss": 0.8942855000495911, "step": 346 }, { "epoch": 0.7341772151898734, "grad_norm": 1.218462347984314, "learning_rate": 9.57218952350998e-06, "loss": 1.2353096008300781, "step": 348 }, { "epoch": 0.7383966244725738, "grad_norm": 2.767768144607544, "learning_rate": 9.565483812755484e-06, "loss": 1.1660033464431763, "step": 350 }, { "epoch": 0.7426160337552743, "grad_norm": 1.8932561874389648, "learning_rate": 9.558728620358539e-06, "loss": 1.0892016887664795, "step": 352 }, { "epoch": 0.7468354430379747, "grad_norm": 7.898970127105713, "learning_rate": 9.55192402853765e-06, "loss": 0.6569602489471436, "step": 354 }, { "epoch": 0.7510548523206751, "grad_norm": 3.425473928451538, "learning_rate": 9.545070120112574e-06, "loss": 1.0433964729309082, "step": 356 }, { "epoch": 0.7552742616033755, "grad_norm": 2.3788833618164062, "learning_rate": 9.538166978503311e-06, "loss": 1.0144389867782593, "step": 358 }, { "epoch": 0.759493670886076, "grad_norm": 0.9130741357803345, "learning_rate": 9.531214687729078e-06, "loss": 1.204459309577942, "step": 360 }, { "epoch": 0.7637130801687764, "grad_norm": 1.108164668083191, "learning_rate": 9.524213332407304e-06, "loss": 0.9747377634048462, "step": 362 }, { "epoch": 0.7679324894514767, "grad_norm": 1.5856913328170776, "learning_rate": 9.517162997752577e-06, "loss": 1.5746862888336182, "step": 364 }, { "epoch": 0.7721518987341772, "grad_norm": 2.186429500579834, "learning_rate": 9.510063769575636e-06, "loss": 0.7158275246620178, "step": 366 }, { "epoch": 0.7763713080168776, "grad_norm": 1.3378268480300903, "learning_rate": 9.5029157342823e-06, "loss": 1.1647388935089111, "step": 368 }, { "epoch": 0.7805907172995781, "grad_norm": 2.1393027305603027, "learning_rate": 9.49571897887243e-06, "loss": 1.4692306518554688, "step": 370 }, { "epoch": 0.7848101265822784, "grad_norm": 3.4950013160705566, "learning_rate": 9.488473590938865e-06, "loss": 0.9896475076675415, "step": 372 }, { "epoch": 0.7890295358649789, "grad_norm": 1.7229326963424683, "learning_rate": 9.481179658666365e-06, "loss": 1.038580298423767, "step": 374 }, { "epoch": 0.7932489451476793, "grad_norm": 1.5673446655273438, "learning_rate": 9.473837270830521e-06, "loss": 1.1549311876296997, "step": 376 }, { "epoch": 0.7974683544303798, "grad_norm": 0.4809153378009796, "learning_rate": 9.466446516796692e-06, "loss": 1.1178803443908691, "step": 378 }, { "epoch": 0.8016877637130801, "grad_norm": 0.9874527454376221, "learning_rate": 9.459007486518909e-06, "loss": 0.7096966505050659, "step": 380 }, { "epoch": 0.8059071729957806, "grad_norm": 1.9838331937789917, "learning_rate": 9.451520270538775e-06, "loss": 1.2621655464172363, "step": 382 }, { "epoch": 0.810126582278481, "grad_norm": 1.712768793106079, "learning_rate": 9.443984959984375e-06, "loss": 0.9930174946784973, "step": 384 }, { "epoch": 0.8143459915611815, "grad_norm": 1.079791784286499, "learning_rate": 9.436401646569154e-06, "loss": 1.23750901222229, "step": 386 }, { "epoch": 0.8185654008438819, "grad_norm": 1.103208065032959, "learning_rate": 9.428770422590817e-06, "loss": 0.938934862613678, "step": 388 }, { "epoch": 0.8227848101265823, "grad_norm": 0.9827385544776917, "learning_rate": 9.421091380930187e-06, "loss": 1.2091245651245117, "step": 390 }, { "epoch": 0.8270042194092827, "grad_norm": 1.9645754098892212, "learning_rate": 9.413364615050088e-06, "loss": 0.958865761756897, "step": 392 }, { "epoch": 0.8312236286919831, "grad_norm": 2.264772653579712, "learning_rate": 9.4055902189942e-06, "loss": 0.9200930595397949, "step": 394 }, { "epoch": 0.8354430379746836, "grad_norm": 1.021557331085205, "learning_rate": 9.397768287385923e-06, "loss": 1.2204573154449463, "step": 396 }, { "epoch": 0.8396624472573839, "grad_norm": 0.23912601172924042, "learning_rate": 9.389898915427213e-06, "loss": 1.0827133655548096, "step": 398 }, { "epoch": 0.8438818565400844, "grad_norm": 1.1516807079315186, "learning_rate": 9.381982198897434e-06, "loss": 0.9496260285377502, "step": 400 }, { "epoch": 0.8481012658227848, "grad_norm": 6.318907737731934, "learning_rate": 9.374018234152187e-06, "loss": 0.7158149480819702, "step": 402 }, { "epoch": 0.8523206751054853, "grad_norm": 2.1835873126983643, "learning_rate": 9.366007118122138e-06, "loss": 1.205085277557373, "step": 404 }, { "epoch": 0.8565400843881856, "grad_norm": 0.7345627546310425, "learning_rate": 9.35794894831184e-06, "loss": 0.936470627784729, "step": 406 }, { "epoch": 0.8607594936708861, "grad_norm": 1.0706825256347656, "learning_rate": 9.349843822798546e-06, "loss": 0.9720379114151001, "step": 408 }, { "epoch": 0.8649789029535865, "grad_norm": 1.026378870010376, "learning_rate": 9.341691840231008e-06, "loss": 1.223767876625061, "step": 410 }, { "epoch": 0.869198312236287, "grad_norm": 1.4687421321868896, "learning_rate": 9.333493099828292e-06, "loss": 0.854697585105896, "step": 412 }, { "epoch": 0.8734177215189873, "grad_norm": 1.7941433191299438, "learning_rate": 9.325247701378553e-06, "loss": 1.2082747220993042, "step": 414 }, { "epoch": 0.8776371308016878, "grad_norm": 1.1276103258132935, "learning_rate": 9.316955745237833e-06, "loss": 1.0644527673721313, "step": 416 }, { "epoch": 0.8818565400843882, "grad_norm": 2.0387966632843018, "learning_rate": 9.308617332328829e-06, "loss": 1.1607332229614258, "step": 418 }, { "epoch": 0.8860759493670886, "grad_norm": 2.268401861190796, "learning_rate": 9.300232564139681e-06, "loss": 0.9451881051063538, "step": 420 }, { "epoch": 0.890295358649789, "grad_norm": 1.1014145612716675, "learning_rate": 9.29180154272272e-06, "loss": 1.3351985216140747, "step": 422 }, { "epoch": 0.8945147679324894, "grad_norm": 3.3932483196258545, "learning_rate": 9.28332437069323e-06, "loss": 0.9659451246261597, "step": 424 }, { "epoch": 0.8987341772151899, "grad_norm": 0.8633236885070801, "learning_rate": 9.274801151228203e-06, "loss": 1.1778777837753296, "step": 426 }, { "epoch": 0.9029535864978903, "grad_norm": 0.9590879082679749, "learning_rate": 9.266231988065084e-06, "loss": 1.0409843921661377, "step": 428 }, { "epoch": 0.9071729957805907, "grad_norm": 5.541334629058838, "learning_rate": 9.257616985500508e-06, "loss": 1.0007435083389282, "step": 430 }, { "epoch": 0.9113924050632911, "grad_norm": 1.296730399131775, "learning_rate": 9.24895624838902e-06, "loss": 1.077131986618042, "step": 432 }, { "epoch": 0.9156118143459916, "grad_norm": 1.2288459539413452, "learning_rate": 9.240249882141818e-06, "loss": 1.2401601076126099, "step": 434 }, { "epoch": 0.919831223628692, "grad_norm": 4.885139465332031, "learning_rate": 9.23149799272545e-06, "loss": 0.8869986534118652, "step": 436 }, { "epoch": 0.9240506329113924, "grad_norm": 1.3291336297988892, "learning_rate": 9.222700686660537e-06, "loss": 1.194260597229004, "step": 438 }, { "epoch": 0.9282700421940928, "grad_norm": 0.9706813097000122, "learning_rate": 9.213858071020477e-06, "loss": 0.9821078777313232, "step": 440 }, { "epoch": 0.9324894514767933, "grad_norm": 4.1486053466796875, "learning_rate": 9.204970253430134e-06, "loss": 0.9321154356002808, "step": 442 }, { "epoch": 0.9367088607594937, "grad_norm": 2.189211845397949, "learning_rate": 9.19603734206453e-06, "loss": 1.0937957763671875, "step": 444 }, { "epoch": 0.9409282700421941, "grad_norm": 2.180600166320801, "learning_rate": 9.187059445647537e-06, "loss": 1.2937591075897217, "step": 446 }, { "epoch": 0.9451476793248945, "grad_norm": 1.4985079765319824, "learning_rate": 9.17803667345054e-06, "loss": 0.9991805553436279, "step": 448 }, { "epoch": 0.9493670886075949, "grad_norm": 11.288036346435547, "learning_rate": 9.16896913529112e-06, "loss": 0.9292160272598267, "step": 450 }, { "epoch": 0.9535864978902954, "grad_norm": 0.9068489670753479, "learning_rate": 9.159856941531707e-06, "loss": 1.286251425743103, "step": 452 }, { "epoch": 0.9578059071729957, "grad_norm": 1.380313754081726, "learning_rate": 9.150700203078245e-06, "loss": 0.9842349886894226, "step": 454 }, { "epoch": 0.9620253164556962, "grad_norm": 3.5392303466796875, "learning_rate": 9.141499031378836e-06, "loss": 1.139675498008728, "step": 456 }, { "epoch": 0.9662447257383966, "grad_norm": 2.057582378387451, "learning_rate": 9.132253538422389e-06, "loss": 0.8938308358192444, "step": 458 }, { "epoch": 0.9704641350210971, "grad_norm": 2.0617613792419434, "learning_rate": 9.12296383673725e-06, "loss": 0.6973727345466614, "step": 460 }, { "epoch": 0.9746835443037974, "grad_norm": 1.7789753675460815, "learning_rate": 9.113630039389835e-06, "loss": 0.8932716250419617, "step": 462 }, { "epoch": 0.9789029535864979, "grad_norm": 1.0312713384628296, "learning_rate": 9.104252259983264e-06, "loss": 1.161884069442749, "step": 464 }, { "epoch": 0.9831223628691983, "grad_norm": 1.9884393215179443, "learning_rate": 9.094830612655961e-06, "loss": 0.7291750311851501, "step": 466 }, { "epoch": 0.9873417721518988, "grad_norm": 1.363207221031189, "learning_rate": 9.085365212080279e-06, "loss": 1.306033730506897, "step": 468 }, { "epoch": 0.9915611814345991, "grad_norm": 3.05018949508667, "learning_rate": 9.075856173461094e-06, "loss": 0.8765395283699036, "step": 470 }, { "epoch": 0.9957805907172996, "grad_norm": 1.2941672801971436, "learning_rate": 9.06630361253441e-06, "loss": 1.2035664319992065, "step": 472 }, { "epoch": 1.0, "grad_norm": 0.9895281195640564, "learning_rate": 9.056707645565946e-06, "loss": 1.251152515411377, "step": 474 }, { "epoch": 1.0042194092827004, "grad_norm": 9.327601432800293, "learning_rate": 9.047068389349729e-06, "loss": 0.9515653252601624, "step": 476 }, { "epoch": 1.0084388185654007, "grad_norm": 1.014952301979065, "learning_rate": 9.037385961206654e-06, "loss": 1.0964629650115967, "step": 478 }, { "epoch": 1.0126582278481013, "grad_norm": 1.422553539276123, "learning_rate": 9.027660478983082e-06, "loss": 1.144622802734375, "step": 480 }, { "epoch": 1.0168776371308017, "grad_norm": 1.5049687623977661, "learning_rate": 9.01789206104938e-06, "loss": 0.8324063420295715, "step": 482 }, { "epoch": 1.021097046413502, "grad_norm": 1.828242540359497, "learning_rate": 9.008080826298504e-06, "loss": 1.0516753196716309, "step": 484 }, { "epoch": 1.0253164556962024, "grad_norm": 2.783456802368164, "learning_rate": 8.99822689414453e-06, "loss": 0.4855537414550781, "step": 486 }, { "epoch": 1.029535864978903, "grad_norm": 1.9455550909042358, "learning_rate": 8.988330384521218e-06, "loss": 0.9561428427696228, "step": 488 }, { "epoch": 1.0337552742616034, "grad_norm": 1.2932617664337158, "learning_rate": 8.978391417880539e-06, "loss": 0.7608006596565247, "step": 490 }, { "epoch": 1.0379746835443038, "grad_norm": 1.135732650756836, "learning_rate": 8.96841011519122e-06, "loss": 1.1182512044906616, "step": 492 }, { "epoch": 1.0421940928270041, "grad_norm": 2.1215767860412598, "learning_rate": 8.958386597937265e-06, "loss": 0.8226317763328552, "step": 494 }, { "epoch": 1.0464135021097047, "grad_norm": 2.2210495471954346, "learning_rate": 8.948320988116476e-06, "loss": 0.9199226498603821, "step": 496 }, { "epoch": 1.0506329113924051, "grad_norm": 0.9657720923423767, "learning_rate": 8.938213408238973e-06, "loss": 1.2488579750061035, "step": 498 }, { "epoch": 1.0548523206751055, "grad_norm": 1.3421814441680908, "learning_rate": 8.928063981325702e-06, "loss": 0.9965586066246033, "step": 500 }, { "epoch": 1.0590717299578059, "grad_norm": 1.1462544202804565, "learning_rate": 8.917872830906929e-06, "loss": 1.064499855041504, "step": 502 }, { "epoch": 1.0632911392405062, "grad_norm": 1.1126136779785156, "learning_rate": 8.907640081020748e-06, "loss": 1.2410351037979126, "step": 504 }, { "epoch": 1.0675105485232068, "grad_norm": 1.4900740385055542, "learning_rate": 8.897365856211569e-06, "loss": 0.7536718249320984, "step": 506 }, { "epoch": 1.0717299578059072, "grad_norm": 1.1911810636520386, "learning_rate": 8.887050281528595e-06, "loss": 1.0110081434249878, "step": 508 }, { "epoch": 1.0759493670886076, "grad_norm": 1.032368779182434, "learning_rate": 8.876693482524306e-06, "loss": 1.0914747714996338, "step": 510 }, { "epoch": 1.080168776371308, "grad_norm": 5.307929039001465, "learning_rate": 8.866295585252932e-06, "loss": 1.0044453144073486, "step": 512 }, { "epoch": 1.0843881856540085, "grad_norm": 1.4270268678665161, "learning_rate": 8.855856716268915e-06, "loss": 1.0741633176803589, "step": 514 }, { "epoch": 1.0886075949367089, "grad_norm": 0.7510942816734314, "learning_rate": 8.845377002625369e-06, "loss": 1.0632392168045044, "step": 516 }, { "epoch": 1.0928270042194093, "grad_norm": 2.129094123840332, "learning_rate": 8.834856571872536e-06, "loss": 0.9470487236976624, "step": 518 }, { "epoch": 1.0970464135021096, "grad_norm": 2.5391345024108887, "learning_rate": 8.824295552056231e-06, "loss": 0.8807843327522278, "step": 520 }, { "epoch": 1.1012658227848102, "grad_norm": 1.0601861476898193, "learning_rate": 8.81369407171629e-06, "loss": 0.8385681509971619, "step": 522 }, { "epoch": 1.1054852320675106, "grad_norm": 1.0985740423202515, "learning_rate": 8.803052259884993e-06, "loss": 1.0753412246704102, "step": 524 }, { "epoch": 1.109704641350211, "grad_norm": 5.063546180725098, "learning_rate": 8.792370246085504e-06, "loss": 0.8541594743728638, "step": 526 }, { "epoch": 1.1139240506329113, "grad_norm": 1.5629971027374268, "learning_rate": 8.781648160330295e-06, "loss": 1.2646830081939697, "step": 528 }, { "epoch": 1.1181434599156117, "grad_norm": 0.8296863436698914, "learning_rate": 8.770886133119553e-06, "loss": 1.2013119459152222, "step": 530 }, { "epoch": 1.1223628691983123, "grad_norm": 1.2659947872161865, "learning_rate": 8.760084295439606e-06, "loss": 0.6667452454566956, "step": 532 }, { "epoch": 1.1265822784810127, "grad_norm": 2.1373422145843506, "learning_rate": 8.749242778761317e-06, "loss": 0.8958901166915894, "step": 534 }, { "epoch": 1.130801687763713, "grad_norm": 0.8173815608024597, "learning_rate": 8.738361715038488e-06, "loss": 1.0577366352081299, "step": 536 }, { "epoch": 1.1350210970464134, "grad_norm": 0.8413187861442566, "learning_rate": 8.727441236706258e-06, "loss": 0.8066195845603943, "step": 538 }, { "epoch": 1.139240506329114, "grad_norm": 2.0623786449432373, "learning_rate": 8.716481476679482e-06, "loss": 0.7362573146820068, "step": 540 }, { "epoch": 1.1434599156118144, "grad_norm": 1.689022421836853, "learning_rate": 8.705482568351128e-06, "loss": 0.8258857131004333, "step": 542 }, { "epoch": 1.1476793248945147, "grad_norm": 1.3229973316192627, "learning_rate": 8.69444464559063e-06, "loss": 0.7806071639060974, "step": 544 }, { "epoch": 1.1518987341772151, "grad_norm": 3.623117446899414, "learning_rate": 8.683367842742285e-06, "loss": 1.0850385427474976, "step": 546 }, { "epoch": 1.1561181434599157, "grad_norm": 1.6875523328781128, "learning_rate": 8.6722522946236e-06, "loss": 1.1124842166900635, "step": 548 }, { "epoch": 1.160337552742616, "grad_norm": 2.32133150100708, "learning_rate": 8.661098136523663e-06, "loss": 0.8948966264724731, "step": 550 }, { "epoch": 1.1645569620253164, "grad_norm": 1.7540771961212158, "learning_rate": 8.649905504201478e-06, "loss": 1.3124022483825684, "step": 552 }, { "epoch": 1.1687763713080168, "grad_norm": 1.0661650896072388, "learning_rate": 8.638674533884338e-06, "loss": 1.1113786697387695, "step": 554 }, { "epoch": 1.1729957805907172, "grad_norm": 4.108656406402588, "learning_rate": 8.627405362266142e-06, "loss": 0.6394384503364563, "step": 556 }, { "epoch": 1.1772151898734178, "grad_norm": 1.596872329711914, "learning_rate": 8.616098126505755e-06, "loss": 0.9353201389312744, "step": 558 }, { "epoch": 1.1814345991561181, "grad_norm": 1.3951916694641113, "learning_rate": 8.604752964225315e-06, "loss": 0.6233245134353638, "step": 560 }, { "epoch": 1.1856540084388185, "grad_norm": 0.702913224697113, "learning_rate": 8.593370013508582e-06, "loss": 0.6408072710037231, "step": 562 }, { "epoch": 1.189873417721519, "grad_norm": 2.099499225616455, "learning_rate": 8.581949412899233e-06, "loss": 1.2306734323501587, "step": 564 }, { "epoch": 1.1940928270042195, "grad_norm": 1.1172051429748535, "learning_rate": 8.570491301399192e-06, "loss": 1.0443873405456543, "step": 566 }, { "epoch": 1.1983122362869199, "grad_norm": 1.7284196615219116, "learning_rate": 8.558995818466941e-06, "loss": 0.74605792760849, "step": 568 }, { "epoch": 1.2025316455696202, "grad_norm": 1.0657957792282104, "learning_rate": 8.547463104015805e-06, "loss": 1.0697757005691528, "step": 570 }, { "epoch": 1.2067510548523206, "grad_norm": 1.4374041557312012, "learning_rate": 8.535893298412262e-06, "loss": 1.0016920566558838, "step": 572 }, { "epoch": 1.2109704641350212, "grad_norm": 1.6338191032409668, "learning_rate": 8.524286542474239e-06, "loss": 1.1215568780899048, "step": 574 }, { "epoch": 1.2151898734177216, "grad_norm": 0.837556004524231, "learning_rate": 8.512642977469386e-06, "loss": 0.9005361199378967, "step": 576 }, { "epoch": 1.219409282700422, "grad_norm": 2.390796661376953, "learning_rate": 8.50096274511336e-06, "loss": 0.626017689704895, "step": 578 }, { "epoch": 1.2236286919831223, "grad_norm": 1.20292329788208, "learning_rate": 8.489245987568107e-06, "loss": 0.901731014251709, "step": 580 }, { "epoch": 1.2278481012658227, "grad_norm": 3.7085282802581787, "learning_rate": 8.477492847440124e-06, "loss": 0.8142147064208984, "step": 582 }, { "epoch": 1.2320675105485233, "grad_norm": 1.0192185640335083, "learning_rate": 8.465703467778728e-06, "loss": 0.7038715481758118, "step": 584 }, { "epoch": 1.2362869198312236, "grad_norm": 2.78006911277771, "learning_rate": 8.453877992074308e-06, "loss": 0.8698074221611023, "step": 586 }, { "epoch": 1.240506329113924, "grad_norm": 1.0351160764694214, "learning_rate": 8.442016564256594e-06, "loss": 0.7912866473197937, "step": 588 }, { "epoch": 1.2447257383966246, "grad_norm": 0.899462878704071, "learning_rate": 8.43011932869288e-06, "loss": 1.0758473873138428, "step": 590 }, { "epoch": 1.248945147679325, "grad_norm": 2.1590211391448975, "learning_rate": 8.418186430186298e-06, "loss": 0.5641391277313232, "step": 592 }, { "epoch": 1.2531645569620253, "grad_norm": 1.4241405725479126, "learning_rate": 8.406218013974023e-06, "loss": 0.8380205035209656, "step": 594 }, { "epoch": 1.2573839662447257, "grad_norm": 2.4764134883880615, "learning_rate": 8.394214225725537e-06, "loss": 0.7866545915603638, "step": 596 }, { "epoch": 1.261603375527426, "grad_norm": 3.0859792232513428, "learning_rate": 8.38217521154083e-06, "loss": 0.5584582686424255, "step": 598 }, { "epoch": 1.2658227848101267, "grad_norm": 0.9441730380058289, "learning_rate": 8.370101117948636e-06, "loss": 0.8391358256340027, "step": 600 }, { "epoch": 1.270042194092827, "grad_norm": 5.382818222045898, "learning_rate": 8.357992091904644e-06, "loss": 1.3513414859771729, "step": 602 }, { "epoch": 1.2742616033755274, "grad_norm": 0.8887715339660645, "learning_rate": 8.345848280789716e-06, "loss": 1.0456057786941528, "step": 604 }, { "epoch": 1.2784810126582278, "grad_norm": 2.219331741333008, "learning_rate": 8.333669832408086e-06, "loss": 0.82603919506073, "step": 606 }, { "epoch": 1.2827004219409281, "grad_norm": 0.9473860859870911, "learning_rate": 8.321456894985564e-06, "loss": 0.820503294467926, "step": 608 }, { "epoch": 1.2869198312236287, "grad_norm": 1.661283254623413, "learning_rate": 8.309209617167727e-06, "loss": 0.8039897084236145, "step": 610 }, { "epoch": 1.2911392405063291, "grad_norm": 4.051083564758301, "learning_rate": 8.29692814801812e-06, "loss": 0.5400303602218628, "step": 612 }, { "epoch": 1.2953586497890295, "grad_norm": 0.7381471395492554, "learning_rate": 8.284612637016435e-06, "loss": 0.6313523054122925, "step": 614 }, { "epoch": 1.29957805907173, "grad_norm": 0.9729277491569519, "learning_rate": 8.272263234056692e-06, "loss": 1.0223050117492676, "step": 616 }, { "epoch": 1.3037974683544304, "grad_norm": 0.7217312455177307, "learning_rate": 8.259880089445414e-06, "loss": 1.0454071760177612, "step": 618 }, { "epoch": 1.3080168776371308, "grad_norm": 0.9059873819351196, "learning_rate": 8.247463353899802e-06, "loss": 0.66311115026474, "step": 620 }, { "epoch": 1.3122362869198312, "grad_norm": 3.0761311054229736, "learning_rate": 8.235013178545896e-06, "loss": 0.7309844493865967, "step": 622 }, { "epoch": 1.3164556962025316, "grad_norm": 4.5476508140563965, "learning_rate": 8.222529714916733e-06, "loss": 0.8237135410308838, "step": 624 }, { "epoch": 1.3206751054852321, "grad_norm": 0.761461079120636, "learning_rate": 8.210013114950516e-06, "loss": 1.0684458017349243, "step": 626 }, { "epoch": 1.3248945147679325, "grad_norm": 2.118196725845337, "learning_rate": 8.197463530988747e-06, "loss": 1.4004764556884766, "step": 628 }, { "epoch": 1.3291139240506329, "grad_norm": 0.7632718682289124, "learning_rate": 8.18488111577439e-06, "loss": 0.8627358675003052, "step": 630 }, { "epoch": 1.3333333333333333, "grad_norm": 1.168583869934082, "learning_rate": 8.17226602244999e-06, "loss": 0.8860023617744446, "step": 632 }, { "epoch": 1.3375527426160336, "grad_norm": 0.3769671618938446, "learning_rate": 8.159618404555836e-06, "loss": 0.7583090662956238, "step": 634 }, { "epoch": 1.3417721518987342, "grad_norm": 1.960574984550476, "learning_rate": 8.146938416028071e-06, "loss": 0.6541010141372681, "step": 636 }, { "epoch": 1.3459915611814346, "grad_norm": 4.958837032318115, "learning_rate": 8.13422621119683e-06, "loss": 0.7914146184921265, "step": 638 }, { "epoch": 1.350210970464135, "grad_norm": 1.7161461114883423, "learning_rate": 8.121481944784356e-06, "loss": 1.2021106481552124, "step": 640 }, { "epoch": 1.3544303797468356, "grad_norm": 1.0110936164855957, "learning_rate": 8.108705771903118e-06, "loss": 0.7672172784805298, "step": 642 }, { "epoch": 1.358649789029536, "grad_norm": 0.7642340064048767, "learning_rate": 8.095897848053922e-06, "loss": 1.2129759788513184, "step": 644 }, { "epoch": 1.3628691983122363, "grad_norm": 0.8580188751220703, "learning_rate": 8.083058329124026e-06, "loss": 1.052816390991211, "step": 646 }, { "epoch": 1.3670886075949367, "grad_norm": 9.899145126342773, "learning_rate": 8.070187371385228e-06, "loss": 0.8623009920120239, "step": 648 }, { "epoch": 1.371308016877637, "grad_norm": 2.754798412322998, "learning_rate": 8.057285131491982e-06, "loss": 1.3044480085372925, "step": 650 }, { "epoch": 1.3755274261603376, "grad_norm": 0.8976891040802002, "learning_rate": 8.044351766479478e-06, "loss": 1.046906590461731, "step": 652 }, { "epoch": 1.379746835443038, "grad_norm": 0.6395276784896851, "learning_rate": 8.03138743376173e-06, "loss": 0.828856885433197, "step": 654 }, { "epoch": 1.3839662447257384, "grad_norm": 1.0773229598999023, "learning_rate": 8.018392291129672e-06, "loss": 1.1526814699172974, "step": 656 }, { "epoch": 1.3881856540084387, "grad_norm": 2.8421826362609863, "learning_rate": 8.005366496749228e-06, "loss": 0.6043949127197266, "step": 658 }, { "epoch": 1.3924050632911391, "grad_norm": 2.582421064376831, "learning_rate": 7.992310209159386e-06, "loss": 1.0708351135253906, "step": 660 }, { "epoch": 1.3966244725738397, "grad_norm": 10.88367748260498, "learning_rate": 7.979223587270276e-06, "loss": 0.7130739688873291, "step": 662 }, { "epoch": 1.40084388185654, "grad_norm": 1.1102014780044556, "learning_rate": 7.966106790361228e-06, "loss": 1.1376579999923706, "step": 664 }, { "epoch": 1.4050632911392404, "grad_norm": 1.0280653238296509, "learning_rate": 7.952959978078842e-06, "loss": 0.6759317517280579, "step": 666 }, { "epoch": 1.409282700421941, "grad_norm": 0.7805987596511841, "learning_rate": 7.939783310435036e-06, "loss": 1.026661992073059, "step": 668 }, { "epoch": 1.4135021097046414, "grad_norm": 0.7399758696556091, "learning_rate": 7.9265769478051e-06, "loss": 1.1155492067337036, "step": 670 }, { "epoch": 1.4177215189873418, "grad_norm": 1.8025891780853271, "learning_rate": 7.913341050925752e-06, "loss": 1.2646962404251099, "step": 672 }, { "epoch": 1.4219409282700421, "grad_norm": 1.6795815229415894, "learning_rate": 7.90007578089317e-06, "loss": 0.6441543102264404, "step": 674 }, { "epoch": 1.4261603375527425, "grad_norm": 1.4897671937942505, "learning_rate": 7.886781299161044e-06, "loss": 0.5868234038352966, "step": 676 }, { "epoch": 1.4303797468354431, "grad_norm": 2.602578639984131, "learning_rate": 7.873457767538598e-06, "loss": 0.9062780737876892, "step": 678 }, { "epoch": 1.4345991561181435, "grad_norm": 2.3317360877990723, "learning_rate": 7.860105348188632e-06, "loss": 1.0125105381011963, "step": 680 }, { "epoch": 1.4388185654008439, "grad_norm": 0.9133606553077698, "learning_rate": 7.84672420362554e-06, "loss": 0.7676307559013367, "step": 682 }, { "epoch": 1.4430379746835442, "grad_norm": 0.8514301776885986, "learning_rate": 7.83331449671333e-06, "loss": 1.0790849924087524, "step": 684 }, { "epoch": 1.4472573839662446, "grad_norm": 0.9023997187614441, "learning_rate": 7.819876390663661e-06, "loss": 0.7343665957450867, "step": 686 }, { "epoch": 1.4514767932489452, "grad_norm": 1.8860224485397339, "learning_rate": 7.806410049033829e-06, "loss": 0.8584230542182922, "step": 688 }, { "epoch": 1.4556962025316456, "grad_norm": 3.5990498065948486, "learning_rate": 7.792915635724796e-06, "loss": 0.9055770039558411, "step": 690 }, { "epoch": 1.459915611814346, "grad_norm": 1.6630886793136597, "learning_rate": 7.779393314979184e-06, "loss": 0.5961977243423462, "step": 692 }, { "epoch": 1.4641350210970465, "grad_norm": 1.3270388841629028, "learning_rate": 7.765843251379288e-06, "loss": 1.2194916009902954, "step": 694 }, { "epoch": 1.4683544303797469, "grad_norm": 1.065203070640564, "learning_rate": 7.752265609845061e-06, "loss": 0.5466008186340332, "step": 696 }, { "epoch": 1.4725738396624473, "grad_norm": 0.9837653040885925, "learning_rate": 7.738660555632112e-06, "loss": 1.1099483966827393, "step": 698 }, { "epoch": 1.4767932489451476, "grad_norm": 0.7686271667480469, "learning_rate": 7.72502825432969e-06, "loss": 1.1365954875946045, "step": 700 }, { "epoch": 1.481012658227848, "grad_norm": 1.989813208580017, "learning_rate": 7.711368871858685e-06, "loss": 0.9693925976753235, "step": 702 }, { "epoch": 1.4852320675105486, "grad_norm": 2.184723377227783, "learning_rate": 7.69768257446958e-06, "loss": 0.7514092326164246, "step": 704 }, { "epoch": 1.489451476793249, "grad_norm": 0.8448720574378967, "learning_rate": 7.683969528740454e-06, "loss": 1.0890294313430786, "step": 706 }, { "epoch": 1.4936708860759493, "grad_norm": 0.9302493333816528, "learning_rate": 7.670229901574946e-06, "loss": 1.0891846418380737, "step": 708 }, { "epoch": 1.49789029535865, "grad_norm": 0.6518703103065491, "learning_rate": 7.656463860200212e-06, "loss": 0.9403813481330872, "step": 710 }, { "epoch": 1.50210970464135, "grad_norm": 3.2188053131103516, "learning_rate": 7.642671572164907e-06, "loss": 0.4597378671169281, "step": 712 }, { "epoch": 1.5063291139240507, "grad_norm": 0.6529601216316223, "learning_rate": 7.628853205337138e-06, "loss": 1.0654302835464478, "step": 714 }, { "epoch": 1.510548523206751, "grad_norm": 0.8326946496963501, "learning_rate": 7.615008927902416e-06, "loss": 1.023169994354248, "step": 716 }, { "epoch": 1.5147679324894514, "grad_norm": 0.7532667517662048, "learning_rate": 7.601138908361621e-06, "loss": 1.0145213603973389, "step": 718 }, { "epoch": 1.518987341772152, "grad_norm": 1.9367239475250244, "learning_rate": 7.58724331552894e-06, "loss": 0.9516394734382629, "step": 720 }, { "epoch": 1.5232067510548524, "grad_norm": 1.505307912826538, "learning_rate": 7.573322318529818e-06, "loss": 1.067749261856079, "step": 722 }, { "epoch": 1.5274261603375527, "grad_norm": 0.936111569404602, "learning_rate": 7.559376086798894e-06, "loss": 1.1941784620285034, "step": 724 }, { "epoch": 1.5316455696202531, "grad_norm": 5.700168609619141, "learning_rate": 7.5454047900779495e-06, "loss": 0.5705253481864929, "step": 726 }, { "epoch": 1.5358649789029535, "grad_norm": 1.6554648876190186, "learning_rate": 7.531408598413832e-06, "loss": 0.3515922725200653, "step": 728 }, { "epoch": 1.540084388185654, "grad_norm": 1.2226029634475708, "learning_rate": 7.5173876821563905e-06, "loss": 0.8002812266349792, "step": 730 }, { "epoch": 1.5443037974683544, "grad_norm": 0.8525183796882629, "learning_rate": 7.503342211956398e-06, "loss": 0.9407591223716736, "step": 732 }, { "epoch": 1.5485232067510548, "grad_norm": 0.8929852843284607, "learning_rate": 7.4892723587634845e-06, "loss": 1.0790826082229614, "step": 734 }, { "epoch": 1.5527426160337554, "grad_norm": 0.8593856692314148, "learning_rate": 7.475178293824038e-06, "loss": 0.7785613536834717, "step": 736 }, { "epoch": 1.5569620253164556, "grad_norm": 1.3784115314483643, "learning_rate": 7.461060188679143e-06, "loss": 0.8724953532218933, "step": 738 }, { "epoch": 1.5611814345991561, "grad_norm": 1.11400306224823, "learning_rate": 7.446918215162474e-06, "loss": 1.0149387121200562, "step": 740 }, { "epoch": 1.5654008438818565, "grad_norm": 0.9480862617492676, "learning_rate": 7.432752545398215e-06, "loss": 0.6753342747688293, "step": 742 }, { "epoch": 1.5696202531645569, "grad_norm": 1.0038092136383057, "learning_rate": 7.418563351798959e-06, "loss": 0.5465993285179138, "step": 744 }, { "epoch": 1.5738396624472575, "grad_norm": 2.1697874069213867, "learning_rate": 7.40435080706361e-06, "loss": 0.609318733215332, "step": 746 }, { "epoch": 1.5780590717299579, "grad_norm": 3.692845582962036, "learning_rate": 7.390115084175283e-06, "loss": 0.6675580143928528, "step": 748 }, { "epoch": 1.5822784810126582, "grad_norm": 1.1590032577514648, "learning_rate": 7.375856356399201e-06, "loss": 1.0637143850326538, "step": 750 }, { "epoch": 1.5864978902953588, "grad_norm": 1.1369000673294067, "learning_rate": 7.36157479728058e-06, "loss": 0.6120810508728027, "step": 752 }, { "epoch": 1.590717299578059, "grad_norm": 0.7865007519721985, "learning_rate": 7.347270580642521e-06, "loss": 0.6230950355529785, "step": 754 }, { "epoch": 1.5949367088607596, "grad_norm": 1.102952003479004, "learning_rate": 7.332943880583892e-06, "loss": 0.5635507106781006, "step": 756 }, { "epoch": 1.59915611814346, "grad_norm": 0.9310120344161987, "learning_rate": 7.318594871477209e-06, "loss": 0.8760903477668762, "step": 758 }, { "epoch": 1.6033755274261603, "grad_norm": 0.9569773077964783, "learning_rate": 7.304223727966523e-06, "loss": 1.067618489265442, "step": 760 }, { "epoch": 1.6075949367088609, "grad_norm": 0.4024181067943573, "learning_rate": 7.289830624965275e-06, "loss": 0.6261290311813354, "step": 762 }, { "epoch": 1.611814345991561, "grad_norm": 0.7744966745376587, "learning_rate": 7.275415737654185e-06, "loss": 1.058768391609192, "step": 764 }, { "epoch": 1.6160337552742616, "grad_norm": 2.60288405418396, "learning_rate": 7.260979241479113e-06, "loss": 0.9792256951332092, "step": 766 }, { "epoch": 1.620253164556962, "grad_norm": 0.3700265884399414, "learning_rate": 7.246521312148924e-06, "loss": 0.8662976026535034, "step": 768 }, { "epoch": 1.6244725738396624, "grad_norm": 0.9629635214805603, "learning_rate": 7.232042125633345e-06, "loss": 1.0662864446640015, "step": 770 }, { "epoch": 1.628691983122363, "grad_norm": 1.305499792098999, "learning_rate": 7.217541858160834e-06, "loss": 1.1654834747314453, "step": 772 }, { "epoch": 1.6329113924050633, "grad_norm": 0.9148606657981873, "learning_rate": 7.203020686216422e-06, "loss": 1.0766959190368652, "step": 774 }, { "epoch": 1.6371308016877637, "grad_norm": 0.8112292885780334, "learning_rate": 7.188478786539579e-06, "loss": 1.0370523929595947, "step": 776 }, { "epoch": 1.6413502109704643, "grad_norm": 1.0768170356750488, "learning_rate": 7.173916336122049e-06, "loss": 0.8139550685882568, "step": 778 }, { "epoch": 1.6455696202531644, "grad_norm": 2.8071439266204834, "learning_rate": 7.159333512205703e-06, "loss": 0.3608042597770691, "step": 780 }, { "epoch": 1.649789029535865, "grad_norm": 2.5754024982452393, "learning_rate": 7.144730492280387e-06, "loss": 1.0327162742614746, "step": 782 }, { "epoch": 1.6540084388185654, "grad_norm": 4.566886901855469, "learning_rate": 7.1301074540817496e-06, "loss": 0.8067229390144348, "step": 784 }, { "epoch": 1.6582278481012658, "grad_norm": 1.7848758697509766, "learning_rate": 7.1154645755890875e-06, "loss": 1.070135235786438, "step": 786 }, { "epoch": 1.6624472573839664, "grad_norm": 2.845881462097168, "learning_rate": 7.1008020350231745e-06, "loss": 0.5474556088447571, "step": 788 }, { "epoch": 1.6666666666666665, "grad_norm": 0.7157531380653381, "learning_rate": 7.086120010844097e-06, "loss": 1.0604743957519531, "step": 790 }, { "epoch": 1.6708860759493671, "grad_norm": 3.6005265712738037, "learning_rate": 7.071418681749081e-06, "loss": 0.5055956840515137, "step": 792 }, { "epoch": 1.6751054852320675, "grad_norm": 0.2927176058292389, "learning_rate": 7.056698226670312e-06, "loss": 0.8437110185623169, "step": 794 }, { "epoch": 1.6793248945147679, "grad_norm": 20.34968376159668, "learning_rate": 7.041958824772761e-06, "loss": 1.075035572052002, "step": 796 }, { "epoch": 1.6835443037974684, "grad_norm": 1.290067434310913, "learning_rate": 7.027200655452007e-06, "loss": 0.8013339042663574, "step": 798 }, { "epoch": 1.6877637130801688, "grad_norm": 2.399333953857422, "learning_rate": 7.012423898332048e-06, "loss": 1.1806011199951172, "step": 800 }, { "epoch": 1.6919831223628692, "grad_norm": 1.8185135126113892, "learning_rate": 6.997628733263118e-06, "loss": 0.5866677165031433, "step": 802 }, { "epoch": 1.6962025316455698, "grad_norm": 1.0164341926574707, "learning_rate": 6.9828153403194945e-06, "loss": 1.1755256652832031, "step": 804 }, { "epoch": 1.70042194092827, "grad_norm": 0.7057609558105469, "learning_rate": 6.967983899797311e-06, "loss": 1.0253472328186035, "step": 806 }, { "epoch": 1.7046413502109705, "grad_norm": 5.4597039222717285, "learning_rate": 6.953134592212363e-06, "loss": 0.783820629119873, "step": 808 }, { "epoch": 1.7088607594936709, "grad_norm": 1.2312418222427368, "learning_rate": 6.938267598297906e-06, "loss": 0.8407894968986511, "step": 810 }, { "epoch": 1.7130801687763713, "grad_norm": 1.460578441619873, "learning_rate": 6.923383099002462e-06, "loss": 1.082040786743164, "step": 812 }, { "epoch": 1.7172995780590719, "grad_norm": 2.8771402835845947, "learning_rate": 6.9084812754876055e-06, "loss": 1.4422590732574463, "step": 814 }, { "epoch": 1.721518987341772, "grad_norm": 0.8137926459312439, "learning_rate": 6.893562309125778e-06, "loss": 1.11027193069458, "step": 816 }, { "epoch": 1.7257383966244726, "grad_norm": 1.688231110572815, "learning_rate": 6.8786263814980625e-06, "loss": 0.7849648594856262, "step": 818 }, { "epoch": 1.729957805907173, "grad_norm": 2.345541000366211, "learning_rate": 6.863673674391981e-06, "loss": 0.3530243933200836, "step": 820 }, { "epoch": 1.7341772151898733, "grad_norm": 2.868515968322754, "learning_rate": 6.848704369799282e-06, "loss": 0.5660111308097839, "step": 822 }, { "epoch": 1.738396624472574, "grad_norm": 1.6542320251464844, "learning_rate": 6.833718649913725e-06, "loss": 0.7747460007667542, "step": 824 }, { "epoch": 1.7426160337552743, "grad_norm": 1.011297345161438, "learning_rate": 6.8187166971288595e-06, "loss": 0.8842973113059998, "step": 826 }, { "epoch": 1.7468354430379747, "grad_norm": 7.091493606567383, "learning_rate": 6.803698694035812e-06, "loss": 0.8845611810684204, "step": 828 }, { "epoch": 1.7510548523206753, "grad_norm": 0.7830747365951538, "learning_rate": 6.788664823421061e-06, "loss": 1.0601418018341064, "step": 830 }, { "epoch": 1.7552742616033754, "grad_norm": 0.6343263387680054, "learning_rate": 6.773615268264205e-06, "loss": 1.0231902599334717, "step": 832 }, { "epoch": 1.759493670886076, "grad_norm": 0.995346188545227, "learning_rate": 6.75855021173575e-06, "loss": 0.8379502892494202, "step": 834 }, { "epoch": 1.7637130801687764, "grad_norm": 1.1212103366851807, "learning_rate": 6.74346983719486e-06, "loss": 1.0596427917480469, "step": 836 }, { "epoch": 1.7679324894514767, "grad_norm": 2.717280387878418, "learning_rate": 6.728374328187149e-06, "loss": 0.8759917616844177, "step": 838 }, { "epoch": 1.7721518987341773, "grad_norm": 2.1211788654327393, "learning_rate": 6.7132638684424286e-06, "loss": 0.7790533900260925, "step": 840 }, { "epoch": 1.7763713080168775, "grad_norm": 1.3415067195892334, "learning_rate": 6.698138641872478e-06, "loss": 0.8736241459846497, "step": 842 }, { "epoch": 1.780590717299578, "grad_norm": 0.47732099890708923, "learning_rate": 6.6829988325688066e-06, "loss": 0.38888755440711975, "step": 844 }, { "epoch": 1.7848101265822784, "grad_norm": 0.5851507782936096, "learning_rate": 6.667844624800414e-06, "loss": 0.6425119042396545, "step": 846 }, { "epoch": 1.7890295358649788, "grad_norm": 1.9702094793319702, "learning_rate": 6.652676203011545e-06, "loss": 0.5686200261116028, "step": 848 }, { "epoch": 1.7932489451476794, "grad_norm": 2.174381971359253, "learning_rate": 6.6374937518194445e-06, "loss": 0.7436455488204956, "step": 850 }, { "epoch": 1.7974683544303798, "grad_norm": 0.8795627355575562, "learning_rate": 6.622297456012114e-06, "loss": 1.0814870595932007, "step": 852 }, { "epoch": 1.8016877637130801, "grad_norm": 2.58670973777771, "learning_rate": 6.607087500546055e-06, "loss": 1.385353446006775, "step": 854 }, { "epoch": 1.8059071729957807, "grad_norm": 0.31646814942359924, "learning_rate": 6.591864070544029e-06, "loss": 0.8310590982437134, "step": 856 }, { "epoch": 1.810126582278481, "grad_norm": 2.06953763961792, "learning_rate": 6.57662735129279e-06, "loss": 1.0249300003051758, "step": 858 }, { "epoch": 1.8143459915611815, "grad_norm": 0.630493700504303, "learning_rate": 6.561377528240851e-06, "loss": 0.6101408004760742, "step": 860 }, { "epoch": 1.8185654008438819, "grad_norm": 1.0807077884674072, "learning_rate": 6.546114786996198e-06, "loss": 1.0944106578826904, "step": 862 }, { "epoch": 1.8227848101265822, "grad_norm": 0.6741223335266113, "learning_rate": 6.530839313324058e-06, "loss": 0.9731322526931763, "step": 864 }, { "epoch": 1.8270042194092828, "grad_norm": 1.1801656484603882, "learning_rate": 6.51555129314462e-06, "loss": 0.9303345084190369, "step": 866 }, { "epoch": 1.831223628691983, "grad_norm": 2.371090888977051, "learning_rate": 6.500250912530779e-06, "loss": 0.900037407875061, "step": 868 }, { "epoch": 1.8354430379746836, "grad_norm": 0.8631995320320129, "learning_rate": 6.4849383577058746e-06, "loss": 0.9859151244163513, "step": 870 }, { "epoch": 1.839662447257384, "grad_norm": 2.3207848072052, "learning_rate": 6.469613815041417e-06, "loss": 0.7240860462188721, "step": 872 }, { "epoch": 1.8438818565400843, "grad_norm": 1.054363489151001, "learning_rate": 6.454277471054824e-06, "loss": 0.9129312634468079, "step": 874 }, { "epoch": 1.8481012658227849, "grad_norm": 0.7508870959281921, "learning_rate": 6.438929512407148e-06, "loss": 1.0743602514266968, "step": 876 }, { "epoch": 1.8523206751054853, "grad_norm": 1.9282993078231812, "learning_rate": 6.423570125900807e-06, "loss": 0.6883825063705444, "step": 878 }, { "epoch": 1.8565400843881856, "grad_norm": 1.4551620483398438, "learning_rate": 6.408199498477307e-06, "loss": 0.7062540650367737, "step": 880 }, { "epoch": 1.8607594936708862, "grad_norm": 1.0817739963531494, "learning_rate": 6.392817817214972e-06, "loss": 0.836834192276001, "step": 882 }, { "epoch": 1.8649789029535864, "grad_norm": 1.155474305152893, "learning_rate": 6.377425269326659e-06, "loss": 0.6343708038330078, "step": 884 }, { "epoch": 1.869198312236287, "grad_norm": 2.2221062183380127, "learning_rate": 6.362022042157491e-06, "loss": 0.7365303635597229, "step": 886 }, { "epoch": 1.8734177215189873, "grad_norm": 1.0301685333251953, "learning_rate": 6.346608323182564e-06, "loss": 1.044546365737915, "step": 888 }, { "epoch": 1.8776371308016877, "grad_norm": 1.6433135271072388, "learning_rate": 6.331184300004677e-06, "loss": 0.4354269206523895, "step": 890 }, { "epoch": 1.8818565400843883, "grad_norm": 2.793412923812866, "learning_rate": 6.315750160352036e-06, "loss": 0.6559075117111206, "step": 892 }, { "epoch": 1.8860759493670884, "grad_norm": 0.6272038221359253, "learning_rate": 6.300306092075985e-06, "loss": 1.0311155319213867, "step": 894 }, { "epoch": 1.890295358649789, "grad_norm": 1.4633967876434326, "learning_rate": 6.284852283148705e-06, "loss": 1.2348912954330444, "step": 896 }, { "epoch": 1.8945147679324894, "grad_norm": 1.7175575494766235, "learning_rate": 6.269388921660931e-06, "loss": 0.7730060815811157, "step": 898 }, { "epoch": 1.8987341772151898, "grad_norm": 1.7055561542510986, "learning_rate": 6.2539161958196695e-06, "loss": 0.9323722720146179, "step": 900 }, { "epoch": 1.9029535864978904, "grad_norm": 2.442265748977661, "learning_rate": 6.238434293945895e-06, "loss": 1.1115236282348633, "step": 902 }, { "epoch": 1.9071729957805907, "grad_norm": 4.920662879943848, "learning_rate": 6.222943404472272e-06, "loss": 0.9061756730079651, "step": 904 }, { "epoch": 1.9113924050632911, "grad_norm": 0.6675768494606018, "learning_rate": 6.207443715940847e-06, "loss": 1.2283276319503784, "step": 906 }, { "epoch": 1.9156118143459917, "grad_norm": 2.168654680252075, "learning_rate": 6.191935417000771e-06, "loss": 0.46411430835723877, "step": 908 }, { "epoch": 1.9198312236286919, "grad_norm": 1.1325494050979614, "learning_rate": 6.176418696405981e-06, "loss": 1.032625675201416, "step": 910 }, { "epoch": 1.9240506329113924, "grad_norm": 3.4216084480285645, "learning_rate": 6.160893743012927e-06, "loss": 0.7713733315467834, "step": 912 }, { "epoch": 1.9282700421940928, "grad_norm": 0.8490431308746338, "learning_rate": 6.145360745778255e-06, "loss": 1.0290547609329224, "step": 914 }, { "epoch": 1.9324894514767932, "grad_norm": 4.315182685852051, "learning_rate": 6.129819893756516e-06, "loss": 0.7414301633834839, "step": 916 }, { "epoch": 1.9367088607594938, "grad_norm": 0.6664161682128906, "learning_rate": 6.1142713760978615e-06, "loss": 0.9903200268745422, "step": 918 }, { "epoch": 1.9409282700421941, "grad_norm": 1.0790371894836426, "learning_rate": 6.098715382045745e-06, "loss": 0.4343828558921814, "step": 920 }, { "epoch": 1.9451476793248945, "grad_norm": 0.7242168188095093, "learning_rate": 6.0831521009346135e-06, "loss": 1.0475226640701294, "step": 922 }, { "epoch": 1.9493670886075949, "grad_norm": 1.3203940391540527, "learning_rate": 6.067581722187609e-06, "loss": 1.0818966627120972, "step": 924 }, { "epoch": 1.9535864978902953, "grad_norm": 0.6348890066146851, "learning_rate": 6.0520044353142585e-06, "loss": 0.8304100036621094, "step": 926 }, { "epoch": 1.9578059071729959, "grad_norm": 0.9556230306625366, "learning_rate": 6.0364204299081665e-06, "loss": 0.7668738961219788, "step": 928 }, { "epoch": 1.9620253164556962, "grad_norm": 1.5916919708251953, "learning_rate": 6.0208298956447155e-06, "loss": 1.0781174898147583, "step": 930 }, { "epoch": 1.9662447257383966, "grad_norm": 3.0878689289093018, "learning_rate": 6.005233022278744e-06, "loss": 0.9163023233413696, "step": 932 }, { "epoch": 1.9704641350210972, "grad_norm": 0.5884475111961365, "learning_rate": 5.9896299996422546e-06, "loss": 1.1752666234970093, "step": 934 }, { "epoch": 1.9746835443037973, "grad_norm": 0.6786129474639893, "learning_rate": 5.974021017642084e-06, "loss": 1.0761367082595825, "step": 936 }, { "epoch": 1.978902953586498, "grad_norm": 1.0359677076339722, "learning_rate": 5.958406266257607e-06, "loss": 0.6669788360595703, "step": 938 }, { "epoch": 1.9831223628691983, "grad_norm": 0.7391291260719299, "learning_rate": 5.942785935538415e-06, "loss": 1.05643630027771, "step": 940 }, { "epoch": 1.9873417721518987, "grad_norm": 1.7905374765396118, "learning_rate": 5.927160215602009e-06, "loss": 0.8889905214309692, "step": 942 }, { "epoch": 1.9915611814345993, "grad_norm": 1.20616614818573, "learning_rate": 5.9115292966314855e-06, "loss": 0.7064967155456543, "step": 944 }, { "epoch": 1.9957805907172996, "grad_norm": 2.605886936187744, "learning_rate": 5.895893368873212e-06, "loss": 1.0327584743499756, "step": 946 }, { "epoch": 2.0, "grad_norm": 3.767585515975952, "learning_rate": 5.880252622634524e-06, "loss": 0.5525592565536499, "step": 948 }, { "epoch": 2.0042194092827006, "grad_norm": 1.9646209478378296, "learning_rate": 5.864607248281401e-06, "loss": 0.7654661536216736, "step": 950 }, { "epoch": 2.0084388185654007, "grad_norm": 2.279823064804077, "learning_rate": 5.848957436236156e-06, "loss": 0.44264787435531616, "step": 952 }, { "epoch": 2.0126582278481013, "grad_norm": 1.6513705253601074, "learning_rate": 5.833303376975109e-06, "loss": 0.7128357887268066, "step": 954 }, { "epoch": 2.0168776371308015, "grad_norm": 3.2315561771392822, "learning_rate": 5.8176452610262756e-06, "loss": 0.8415310382843018, "step": 956 }, { "epoch": 2.021097046413502, "grad_norm": 3.4165968894958496, "learning_rate": 5.8019832789670476e-06, "loss": 0.6201844811439514, "step": 958 }, { "epoch": 2.0253164556962027, "grad_norm": 9.56297779083252, "learning_rate": 5.7863176214218676e-06, "loss": 0.6868460178375244, "step": 960 }, { "epoch": 2.029535864978903, "grad_norm": 1.5671744346618652, "learning_rate": 5.770648479059918e-06, "loss": 0.9392538070678711, "step": 962 }, { "epoch": 2.0337552742616034, "grad_norm": 1.051895022392273, "learning_rate": 5.754976042592791e-06, "loss": 0.6610828638076782, "step": 964 }, { "epoch": 2.037974683544304, "grad_norm": 1.024628758430481, "learning_rate": 5.739300502772177e-06, "loss": 0.5569242238998413, "step": 966 }, { "epoch": 2.042194092827004, "grad_norm": 15.47443962097168, "learning_rate": 5.723622050387533e-06, "loss": 0.5953006148338318, "step": 968 }, { "epoch": 2.0464135021097047, "grad_norm": 0.8443486094474792, "learning_rate": 5.707940876263767e-06, "loss": 0.8928432464599609, "step": 970 }, { "epoch": 2.050632911392405, "grad_norm": 4.8549017906188965, "learning_rate": 5.6922571712589145e-06, "loss": 0.7484784126281738, "step": 972 }, { "epoch": 2.0548523206751055, "grad_norm": 0.8294370174407959, "learning_rate": 5.676571126261814e-06, "loss": 0.7304527759552002, "step": 974 }, { "epoch": 2.059071729957806, "grad_norm": 2.2054624557495117, "learning_rate": 5.660882932189783e-06, "loss": 0.5348646640777588, "step": 976 }, { "epoch": 2.0632911392405062, "grad_norm": 0.9927537441253662, "learning_rate": 5.6451927799863e-06, "loss": 0.5682324171066284, "step": 978 }, { "epoch": 2.067510548523207, "grad_norm": 0.6842828392982483, "learning_rate": 5.629500860618673e-06, "loss": 0.5526285171508789, "step": 980 }, { "epoch": 2.071729957805907, "grad_norm": 0.5549476742744446, "learning_rate": 5.613807365075716e-06, "loss": 0.8692628741264343, "step": 982 }, { "epoch": 2.0759493670886076, "grad_norm": 12.708823204040527, "learning_rate": 5.5981124843654335e-06, "loss": 0.8682882189750671, "step": 984 }, { "epoch": 2.080168776371308, "grad_norm": 1.0577720403671265, "learning_rate": 5.582416409512682e-06, "loss": 0.9204199314117432, "step": 986 }, { "epoch": 2.0843881856540083, "grad_norm": 1.049107313156128, "learning_rate": 5.566719331556858e-06, "loss": 0.9249716997146606, "step": 988 }, { "epoch": 2.088607594936709, "grad_norm": 1.5434415340423584, "learning_rate": 5.5510214415495635e-06, "loss": 0.43936803936958313, "step": 990 }, { "epoch": 2.0928270042194095, "grad_norm": 0.7453979253768921, "learning_rate": 5.535322930552283e-06, "loss": 0.4882759749889374, "step": 992 }, { "epoch": 2.0970464135021096, "grad_norm": 1.5207363367080688, "learning_rate": 5.519623989634065e-06, "loss": 1.0173232555389404, "step": 994 }, { "epoch": 2.1012658227848102, "grad_norm": 2.467822551727295, "learning_rate": 5.503924809869186e-06, "loss": 0.8716915845870972, "step": 996 }, { "epoch": 2.1054852320675104, "grad_norm": 0.31459274888038635, "learning_rate": 5.488225582334826e-06, "loss": 0.5366916060447693, "step": 998 }, { "epoch": 2.109704641350211, "grad_norm": 1.0145535469055176, "learning_rate": 5.472526498108756e-06, "loss": 1.0334587097167969, "step": 1000 }, { "epoch": 2.1139240506329116, "grad_norm": 1.3650320768356323, "learning_rate": 5.456827748266995e-06, "loss": 0.8567022085189819, "step": 1002 }, { "epoch": 2.1181434599156117, "grad_norm": 0.8111072182655334, "learning_rate": 5.441129523881496e-06, "loss": 0.8640495538711548, "step": 1004 }, { "epoch": 2.1223628691983123, "grad_norm": 0.5610778331756592, "learning_rate": 5.425432016017814e-06, "loss": 0.5426124334335327, "step": 1006 }, { "epoch": 2.1265822784810124, "grad_norm": 0.8662636876106262, "learning_rate": 5.409735415732784e-06, "loss": 0.6626504063606262, "step": 1008 }, { "epoch": 2.130801687763713, "grad_norm": 1.0036123991012573, "learning_rate": 5.394039914072198e-06, "loss": 0.602443277835846, "step": 1010 }, { "epoch": 2.1350210970464136, "grad_norm": 5.787118434906006, "learning_rate": 5.37834570206847e-06, "loss": 0.7818161249160767, "step": 1012 }, { "epoch": 2.1392405063291138, "grad_norm": 1.8635953664779663, "learning_rate": 5.362652970738321e-06, "loss": 1.0021519660949707, "step": 1014 }, { "epoch": 2.1434599156118144, "grad_norm": 1.0233852863311768, "learning_rate": 5.346961911080453e-06, "loss": 0.4967895448207855, "step": 1016 }, { "epoch": 2.147679324894515, "grad_norm": 0.7853139638900757, "learning_rate": 5.3312727140732175e-06, "loss": 0.7197954654693604, "step": 1018 }, { "epoch": 2.151898734177215, "grad_norm": 0.8818747997283936, "learning_rate": 5.315585570672298e-06, "loss": 0.6123325824737549, "step": 1020 }, { "epoch": 2.1561181434599157, "grad_norm": 1.8112258911132812, "learning_rate": 5.299900671808382e-06, "loss": 0.7056881785392761, "step": 1022 }, { "epoch": 2.160337552742616, "grad_norm": 18.123889923095703, "learning_rate": 5.284218208384839e-06, "loss": 0.7241491675376892, "step": 1024 }, { "epoch": 2.1645569620253164, "grad_norm": 0.9460628032684326, "learning_rate": 5.268538371275396e-06, "loss": 0.8828868865966797, "step": 1026 }, { "epoch": 2.168776371308017, "grad_norm": 1.4755462408065796, "learning_rate": 5.252861351321815e-06, "loss": 0.8952438235282898, "step": 1028 }, { "epoch": 2.172995780590717, "grad_norm": 1.3766902685165405, "learning_rate": 5.237187339331567e-06, "loss": 0.8603683710098267, "step": 1030 }, { "epoch": 2.1772151898734178, "grad_norm": 0.9352067112922668, "learning_rate": 5.2215165260755205e-06, "loss": 0.9045505523681641, "step": 1032 }, { "epoch": 2.181434599156118, "grad_norm": 1.3670021295547485, "learning_rate": 5.205849102285603e-06, "loss": 0.8514065146446228, "step": 1034 }, { "epoch": 2.1856540084388185, "grad_norm": 1.022005558013916, "learning_rate": 5.190185258652494e-06, "loss": 0.8968141674995422, "step": 1036 }, { "epoch": 2.189873417721519, "grad_norm": 1.3881776332855225, "learning_rate": 5.1745251858232935e-06, "loss": 0.8287613391876221, "step": 1038 }, { "epoch": 2.1940928270042193, "grad_norm": 0.9293564558029175, "learning_rate": 5.158869074399211e-06, "loss": 1.0347445011138916, "step": 1040 }, { "epoch": 2.19831223628692, "grad_norm": 3.9465243816375732, "learning_rate": 5.143217114933239e-06, "loss": 0.2707809507846832, "step": 1042 }, { "epoch": 2.2025316455696204, "grad_norm": 1.7887977361679077, "learning_rate": 5.127569497927837e-06, "loss": 0.9248485565185547, "step": 1044 }, { "epoch": 2.2067510548523206, "grad_norm": 3.2685720920562744, "learning_rate": 5.111926413832609e-06, "loss": 0.5480203032493591, "step": 1046 }, { "epoch": 2.210970464135021, "grad_norm": 0.8323540687561035, "learning_rate": 5.096288053041992e-06, "loss": 0.7119970321655273, "step": 1048 }, { "epoch": 2.2151898734177213, "grad_norm": 0.7563989758491516, "learning_rate": 5.080654605892931e-06, "loss": 0.9097958207130432, "step": 1050 }, { "epoch": 2.219409282700422, "grad_norm": 2.7414941787719727, "learning_rate": 5.065026262662572e-06, "loss": 0.7608872056007385, "step": 1052 }, { "epoch": 2.2236286919831225, "grad_norm": 1.799401879310608, "learning_rate": 5.049403213565932e-06, "loss": 0.7050530910491943, "step": 1054 }, { "epoch": 2.2278481012658227, "grad_norm": 1.2924493551254272, "learning_rate": 5.0337856487536e-06, "loss": 0.717831015586853, "step": 1056 }, { "epoch": 2.2320675105485233, "grad_norm": 3.7170071601867676, "learning_rate": 5.018173758309411e-06, "loss": 0.406954824924469, "step": 1058 }, { "epoch": 2.2362869198312234, "grad_norm": 0.7091597318649292, "learning_rate": 5.002567732248137e-06, "loss": 0.9544392824172974, "step": 1060 }, { "epoch": 2.240506329113924, "grad_norm": 0.5145078301429749, "learning_rate": 4.986967760513176e-06, "loss": 0.5994046330451965, "step": 1062 }, { "epoch": 2.2447257383966246, "grad_norm": 1.2531402111053467, "learning_rate": 4.971374032974233e-06, "loss": 0.432076632976532, "step": 1064 }, { "epoch": 2.2489451476793247, "grad_norm": 1.5886108875274658, "learning_rate": 4.9557867394250194e-06, "loss": 0.7569403648376465, "step": 1066 }, { "epoch": 2.2531645569620253, "grad_norm": 1.5607138872146606, "learning_rate": 4.940206069580932e-06, "loss": 1.0120244026184082, "step": 1068 }, { "epoch": 2.257383966244726, "grad_norm": 1.5534892082214355, "learning_rate": 4.924632213076754e-06, "loss": 0.9608168601989746, "step": 1070 }, { "epoch": 2.261603375527426, "grad_norm": 1.6631319522857666, "learning_rate": 4.9090653594643404e-06, "loss": 0.8874021768569946, "step": 1072 }, { "epoch": 2.2658227848101267, "grad_norm": 2.0827291011810303, "learning_rate": 4.893505698210313e-06, "loss": 1.1729992628097534, "step": 1074 }, { "epoch": 2.270042194092827, "grad_norm": 0.7913424968719482, "learning_rate": 4.877953418693755e-06, "loss": 0.8216667771339417, "step": 1076 }, { "epoch": 2.2742616033755274, "grad_norm": 2.5898029804229736, "learning_rate": 4.862408710203904e-06, "loss": 0.5997598767280579, "step": 1078 }, { "epoch": 2.278481012658228, "grad_norm": 1.503953456878662, "learning_rate": 4.8468717619378515e-06, "loss": 0.6715444326400757, "step": 1080 }, { "epoch": 2.282700421940928, "grad_norm": 2.866316795349121, "learning_rate": 4.831342762998233e-06, "loss": 0.3304208517074585, "step": 1082 }, { "epoch": 2.2869198312236287, "grad_norm": 1.4237805604934692, "learning_rate": 4.81582190239094e-06, "loss": 0.6000298857688904, "step": 1084 }, { "epoch": 2.291139240506329, "grad_norm": 2.4457147121429443, "learning_rate": 4.800309369022803e-06, "loss": 0.5227864384651184, "step": 1086 }, { "epoch": 2.2953586497890295, "grad_norm": 1.8989934921264648, "learning_rate": 4.784805351699306e-06, "loss": 0.5022572875022888, "step": 1088 }, { "epoch": 2.29957805907173, "grad_norm": 1.1429563760757446, "learning_rate": 4.769310039122278e-06, "loss": 0.4501606822013855, "step": 1090 }, { "epoch": 2.3037974683544302, "grad_norm": 1.7774832248687744, "learning_rate": 4.753823619887606e-06, "loss": 0.7520623803138733, "step": 1092 }, { "epoch": 2.308016877637131, "grad_norm": 0.8094785213470459, "learning_rate": 4.738346282482932e-06, "loss": 0.589955747127533, "step": 1094 }, { "epoch": 2.3122362869198314, "grad_norm": 1.6006946563720703, "learning_rate": 4.722878215285362e-06, "loss": 0.332165002822876, "step": 1096 }, { "epoch": 2.3164556962025316, "grad_norm": 2.6582677364349365, "learning_rate": 4.707419606559172e-06, "loss": 0.7813307046890259, "step": 1098 }, { "epoch": 2.320675105485232, "grad_norm": 0.9811158180236816, "learning_rate": 4.691970644453521e-06, "loss": 0.7614369988441467, "step": 1100 }, { "epoch": 2.3248945147679323, "grad_norm": 1.1281622648239136, "learning_rate": 4.676531517000152e-06, "loss": 0.8711140155792236, "step": 1102 }, { "epoch": 2.329113924050633, "grad_norm": 1.0006742477416992, "learning_rate": 4.661102412111113e-06, "loss": 1.09892737865448, "step": 1104 }, { "epoch": 2.3333333333333335, "grad_norm": 0.9522520899772644, "learning_rate": 4.645683517576465e-06, "loss": 0.7079843878746033, "step": 1106 }, { "epoch": 2.3375527426160336, "grad_norm": 3.4067864418029785, "learning_rate": 4.630275021061994e-06, "loss": 0.48118704557418823, "step": 1108 }, { "epoch": 2.3417721518987342, "grad_norm": 1.1255890130996704, "learning_rate": 4.614877110106936e-06, "loss": 0.8689737915992737, "step": 1110 }, { "epoch": 2.3459915611814344, "grad_norm": 0.9904977083206177, "learning_rate": 4.599489972121685e-06, "loss": 0.9105451703071594, "step": 1112 }, { "epoch": 2.350210970464135, "grad_norm": 0.7232893705368042, "learning_rate": 4.584113794385514e-06, "loss": 0.9162687063217163, "step": 1114 }, { "epoch": 2.3544303797468356, "grad_norm": 0.519036591053009, "learning_rate": 4.568748764044301e-06, "loss": 0.4805559813976288, "step": 1116 }, { "epoch": 2.3586497890295357, "grad_norm": 6.756855010986328, "learning_rate": 4.553395068108244e-06, "loss": 0.8094164133071899, "step": 1118 }, { "epoch": 2.3628691983122363, "grad_norm": 0.9828208088874817, "learning_rate": 4.538052893449589e-06, "loss": 0.5296162962913513, "step": 1120 }, { "epoch": 2.367088607594937, "grad_norm": 4.731954574584961, "learning_rate": 4.522722426800357e-06, "loss": 0.8078899383544922, "step": 1122 }, { "epoch": 2.371308016877637, "grad_norm": 0.6858487725257874, "learning_rate": 4.507403854750065e-06, "loss": 0.475280225276947, "step": 1124 }, { "epoch": 2.3755274261603376, "grad_norm": 2.410244941711426, "learning_rate": 4.492097363743461e-06, "loss": 0.6350052952766418, "step": 1126 }, { "epoch": 2.379746835443038, "grad_norm": 1.3143579959869385, "learning_rate": 4.476803140078253e-06, "loss": 0.8321637511253357, "step": 1128 }, { "epoch": 2.3839662447257384, "grad_norm": 3.1888086795806885, "learning_rate": 4.4615213699028426e-06, "loss": 0.3929082751274109, "step": 1130 }, { "epoch": 2.388185654008439, "grad_norm": 2.68168306350708, "learning_rate": 4.446252239214055e-06, "loss": 0.31692028045654297, "step": 1132 }, { "epoch": 2.392405063291139, "grad_norm": 1.4429116249084473, "learning_rate": 4.43099593385488e-06, "loss": 0.294213205575943, "step": 1134 }, { "epoch": 2.3966244725738397, "grad_norm": 3.231173276901245, "learning_rate": 4.4157526395122076e-06, "loss": 0.5183360576629639, "step": 1136 }, { "epoch": 2.40084388185654, "grad_norm": 0.8097783327102661, "learning_rate": 4.400522541714569e-06, "loss": 0.889994740486145, "step": 1138 }, { "epoch": 2.4050632911392404, "grad_norm": 3.5556163787841797, "learning_rate": 4.385305825829878e-06, "loss": 0.6985417008399963, "step": 1140 }, { "epoch": 2.409282700421941, "grad_norm": 2.427283763885498, "learning_rate": 4.370102677063176e-06, "loss": 0.22593039274215698, "step": 1142 }, { "epoch": 2.413502109704641, "grad_norm": 0.9665276408195496, "learning_rate": 4.354913280454376e-06, "loss": 0.6225028038024902, "step": 1144 }, { "epoch": 2.4177215189873418, "grad_norm": 0.776543140411377, "learning_rate": 4.339737820876011e-06, "loss": 0.8892446756362915, "step": 1146 }, { "epoch": 2.4219409282700424, "grad_norm": 1.4189026355743408, "learning_rate": 4.324576483030984e-06, "loss": 0.6498630046844482, "step": 1148 }, { "epoch": 2.4261603375527425, "grad_norm": 1.6917228698730469, "learning_rate": 4.309429451450323e-06, "loss": 0.9674113988876343, "step": 1150 }, { "epoch": 2.430379746835443, "grad_norm": 2.7559592723846436, "learning_rate": 4.294296910490927e-06, "loss": 0.5237405300140381, "step": 1152 }, { "epoch": 2.4345991561181437, "grad_norm": 0.759251594543457, "learning_rate": 4.279179044333334e-06, "loss": 1.038418173789978, "step": 1154 }, { "epoch": 2.438818565400844, "grad_norm": 0.7258760929107666, "learning_rate": 4.264076036979465e-06, "loss": 0.29808011651039124, "step": 1156 }, { "epoch": 2.4430379746835444, "grad_norm": 1.2960338592529297, "learning_rate": 4.2489880722503984e-06, "loss": 0.6186285018920898, "step": 1158 }, { "epoch": 2.4472573839662446, "grad_norm": 0.8735424280166626, "learning_rate": 4.233915333784125e-06, "loss": 0.953921914100647, "step": 1160 }, { "epoch": 2.451476793248945, "grad_norm": 1.6151870489120483, "learning_rate": 4.2188580050333125e-06, "loss": 0.5386602878570557, "step": 1162 }, { "epoch": 2.4556962025316453, "grad_norm": 1.0667333602905273, "learning_rate": 4.203816269263076e-06, "loss": 0.8307045698165894, "step": 1164 }, { "epoch": 2.459915611814346, "grad_norm": 0.7664170861244202, "learning_rate": 4.188790309548745e-06, "loss": 0.864146888256073, "step": 1166 }, { "epoch": 2.4641350210970465, "grad_norm": 0.42983004450798035, "learning_rate": 4.173780308773638e-06, "loss": 0.5185874700546265, "step": 1168 }, { "epoch": 2.4683544303797467, "grad_norm": 1.8288553953170776, "learning_rate": 4.158786449626832e-06, "loss": 0.847137451171875, "step": 1170 }, { "epoch": 2.4725738396624473, "grad_norm": 0.7871118187904358, "learning_rate": 4.1438089146009444e-06, "loss": 0.8581575751304626, "step": 1172 }, { "epoch": 2.476793248945148, "grad_norm": 0.8730447292327881, "learning_rate": 4.128847885989907e-06, "loss": 0.9124253988265991, "step": 1174 }, { "epoch": 2.481012658227848, "grad_norm": 1.2835520505905151, "learning_rate": 4.113903545886753e-06, "loss": 0.6599792838096619, "step": 1176 }, { "epoch": 2.4852320675105486, "grad_norm": 5.658310890197754, "learning_rate": 4.098976076181391e-06, "loss": 0.3625165522098541, "step": 1178 }, { "epoch": 2.489451476793249, "grad_norm": 15.800931930541992, "learning_rate": 4.084065658558404e-06, "loss": 0.6006633043289185, "step": 1180 }, { "epoch": 2.4936708860759493, "grad_norm": 1.3577805757522583, "learning_rate": 4.0691724744948255e-06, "loss": 0.6934759616851807, "step": 1182 }, { "epoch": 2.49789029535865, "grad_norm": 6.484335422515869, "learning_rate": 4.054296705257941e-06, "loss": 0.40067270398139954, "step": 1184 }, { "epoch": 2.50210970464135, "grad_norm": 0.6322926878929138, "learning_rate": 4.039438531903077e-06, "loss": 0.2836645245552063, "step": 1186 }, { "epoch": 2.5063291139240507, "grad_norm": 1.1335638761520386, "learning_rate": 4.024598135271394e-06, "loss": 0.6265759468078613, "step": 1188 }, { "epoch": 2.510548523206751, "grad_norm": 1.9667792320251465, "learning_rate": 4.009775695987694e-06, "loss": 0.838147759437561, "step": 1190 }, { "epoch": 2.5147679324894514, "grad_norm": 2.6841256618499756, "learning_rate": 3.994971394458214e-06, "loss": 0.3996051251888275, "step": 1192 }, { "epoch": 2.518987341772152, "grad_norm": 2.3056275844573975, "learning_rate": 3.980185410868436e-06, "loss": 1.167797565460205, "step": 1194 }, { "epoch": 2.523206751054852, "grad_norm": 0.9773274064064026, "learning_rate": 3.965417925180889e-06, "loss": 0.9167941212654114, "step": 1196 }, { "epoch": 2.5274261603375527, "grad_norm": 1.7874913215637207, "learning_rate": 3.950669117132961e-06, "loss": 0.8906291127204895, "step": 1198 }, { "epoch": 2.5316455696202533, "grad_norm": 1.4841127395629883, "learning_rate": 3.935939166234716e-06, "loss": 0.5971670150756836, "step": 1200 }, { "epoch": 2.5358649789029535, "grad_norm": 1.00154447555542, "learning_rate": 3.9212282517667e-06, "loss": 0.6971355676651001, "step": 1202 }, { "epoch": 2.540084388185654, "grad_norm": 1.9771873950958252, "learning_rate": 3.9065365527777645e-06, "loss": 0.6099141836166382, "step": 1204 }, { "epoch": 2.5443037974683547, "grad_norm": 1.1871707439422607, "learning_rate": 3.891864248082887e-06, "loss": 0.8208593726158142, "step": 1206 }, { "epoch": 2.548523206751055, "grad_norm": 7.188979625701904, "learning_rate": 3.877211516260996e-06, "loss": 0.6296668648719788, "step": 1208 }, { "epoch": 2.5527426160337554, "grad_norm": 0.9134591817855835, "learning_rate": 3.862578535652789e-06, "loss": 1.0518441200256348, "step": 1210 }, { "epoch": 2.5569620253164556, "grad_norm": 0.7472072243690491, "learning_rate": 3.847965484358577e-06, "loss": 0.9192833304405212, "step": 1212 }, { "epoch": 2.561181434599156, "grad_norm": 3.8333990573883057, "learning_rate": 3.833372540236103e-06, "loss": 0.23244482278823853, "step": 1214 }, { "epoch": 2.5654008438818563, "grad_norm": 1.4940085411071777, "learning_rate": 3.818799880898383e-06, "loss": 0.6407491564750671, "step": 1216 }, { "epoch": 2.569620253164557, "grad_norm": 0.9860958456993103, "learning_rate": 3.804247683711544e-06, "loss": 0.8455902934074402, "step": 1218 }, { "epoch": 2.5738396624472575, "grad_norm": 2.8924689292907715, "learning_rate": 3.789716125792665e-06, "loss": 0.5936464071273804, "step": 1220 }, { "epoch": 2.5780590717299576, "grad_norm": 2.5732288360595703, "learning_rate": 3.7752053840076207e-06, "loss": 0.715736448764801, "step": 1222 }, { "epoch": 2.5822784810126582, "grad_norm": 1.9856914281845093, "learning_rate": 3.7607156349689333e-06, "loss": 0.6130495667457581, "step": 1224 }, { "epoch": 2.586497890295359, "grad_norm": 5.838541507720947, "learning_rate": 3.7462470550336115e-06, "loss": 0.5375937223434448, "step": 1226 }, { "epoch": 2.590717299578059, "grad_norm": 0.8572865128517151, "learning_rate": 3.7317998203010188e-06, "loss": 0.7977232933044434, "step": 1228 }, { "epoch": 2.5949367088607596, "grad_norm": 0.9872308373451233, "learning_rate": 3.7173741066107184e-06, "loss": 0.8961679935455322, "step": 1230 }, { "epoch": 2.59915611814346, "grad_norm": 1.1416627168655396, "learning_rate": 3.7029700895403386e-06, "loss": 0.7586051821708679, "step": 1232 }, { "epoch": 2.6033755274261603, "grad_norm": 2.2268545627593994, "learning_rate": 3.6885879444034355e-06, "loss": 0.25110605359077454, "step": 1234 }, { "epoch": 2.607594936708861, "grad_norm": 1.4125570058822632, "learning_rate": 3.674227846247358e-06, "loss": 0.9204742312431335, "step": 1236 }, { "epoch": 2.611814345991561, "grad_norm": 2.517575979232788, "learning_rate": 3.659889969851118e-06, "loss": 1.1121842861175537, "step": 1238 }, { "epoch": 2.6160337552742616, "grad_norm": 1.053368330001831, "learning_rate": 3.6455744897232615e-06, "loss": 0.669468343257904, "step": 1240 }, { "epoch": 2.620253164556962, "grad_norm": 0.8371555209159851, "learning_rate": 3.631281580099749e-06, "loss": 0.9007189273834229, "step": 1242 }, { "epoch": 2.6244725738396624, "grad_norm": 2.657794713973999, "learning_rate": 3.6170114149418277e-06, "loss": 0.3218531906604767, "step": 1244 }, { "epoch": 2.628691983122363, "grad_norm": 0.6953291893005371, "learning_rate": 3.602764167933921e-06, "loss": 0.616287112236023, "step": 1246 }, { "epoch": 2.632911392405063, "grad_norm": 2.490736246109009, "learning_rate": 3.588540012481514e-06, "loss": 1.0413483381271362, "step": 1248 }, { "epoch": 2.6371308016877637, "grad_norm": 1.0899211168289185, "learning_rate": 3.574339121709035e-06, "loss": 0.8530718088150024, "step": 1250 }, { "epoch": 2.6413502109704643, "grad_norm": 1.2830111980438232, "learning_rate": 3.5601616684577587e-06, "loss": 0.8038271069526672, "step": 1252 }, { "epoch": 2.6455696202531644, "grad_norm": 1.318005919456482, "learning_rate": 3.546007825283697e-06, "loss": 0.3539282977581024, "step": 1254 }, { "epoch": 2.649789029535865, "grad_norm": 2.07309627532959, "learning_rate": 3.5318777644555024e-06, "loss": 0.3781224489212036, "step": 1256 }, { "epoch": 2.6540084388185656, "grad_norm": 1.1522823572158813, "learning_rate": 3.5177716579523602e-06, "loss": 0.7310733795166016, "step": 1258 }, { "epoch": 2.6582278481012658, "grad_norm": 1.0164247751235962, "learning_rate": 3.5036896774619135e-06, "loss": 0.8424127697944641, "step": 1260 }, { "epoch": 2.6624472573839664, "grad_norm": 1.0595896244049072, "learning_rate": 3.489631994378161e-06, "loss": 0.7590124011039734, "step": 1262 }, { "epoch": 2.6666666666666665, "grad_norm": 0.6736453771591187, "learning_rate": 3.47559877979937e-06, "loss": 0.4899386167526245, "step": 1264 }, { "epoch": 2.670886075949367, "grad_norm": 3.384662389755249, "learning_rate": 3.461590204526002e-06, "loss": 0.756107747554779, "step": 1266 }, { "epoch": 2.6751054852320673, "grad_norm": 1.117247462272644, "learning_rate": 3.4476064390586282e-06, "loss": 0.5926318168640137, "step": 1268 }, { "epoch": 2.679324894514768, "grad_norm": 0.8941352367401123, "learning_rate": 3.433647653595858e-06, "loss": 0.29376059770584106, "step": 1270 }, { "epoch": 2.6835443037974684, "grad_norm": 0.9455461502075195, "learning_rate": 3.4197140180322595e-06, "loss": 0.8394232392311096, "step": 1272 }, { "epoch": 2.6877637130801686, "grad_norm": 1.506241798400879, "learning_rate": 3.405805701956303e-06, "loss": 0.5689144730567932, "step": 1274 }, { "epoch": 2.691983122362869, "grad_norm": 1.9141788482666016, "learning_rate": 3.391922874648289e-06, "loss": 0.6709578037261963, "step": 1276 }, { "epoch": 2.6962025316455698, "grad_norm": 0.42958736419677734, "learning_rate": 3.3780657050782937e-06, "loss": 0.21942144632339478, "step": 1278 }, { "epoch": 2.70042194092827, "grad_norm": 4.082215309143066, "learning_rate": 3.364234361904101e-06, "loss": 0.7311381101608276, "step": 1280 }, { "epoch": 2.7046413502109705, "grad_norm": 0.871422290802002, "learning_rate": 3.350429013469164e-06, "loss": 0.8393055200576782, "step": 1282 }, { "epoch": 2.708860759493671, "grad_norm": 2.4200565814971924, "learning_rate": 3.336649827800551e-06, "loss": 0.4168017506599426, "step": 1284 }, { "epoch": 2.7130801687763713, "grad_norm": 1.16176438331604, "learning_rate": 3.3228969726068928e-06, "loss": 0.3925034701824188, "step": 1286 }, { "epoch": 2.717299578059072, "grad_norm": 0.554189920425415, "learning_rate": 3.3091706152763524e-06, "loss": 0.4354971945285797, "step": 1288 }, { "epoch": 2.721518987341772, "grad_norm": 0.29727903008461, "learning_rate": 3.295470922874583e-06, "loss": 0.7019829154014587, "step": 1290 }, { "epoch": 2.7257383966244726, "grad_norm": 1.5975490808486938, "learning_rate": 3.281798062142696e-06, "loss": 0.8629660606384277, "step": 1292 }, { "epoch": 2.7299578059071727, "grad_norm": 0.6528840065002441, "learning_rate": 3.2681521994952236e-06, "loss": 0.44343236088752747, "step": 1294 }, { "epoch": 2.7341772151898733, "grad_norm": 1.1418026685714722, "learning_rate": 3.2545335010181077e-06, "loss": 0.8660521507263184, "step": 1296 }, { "epoch": 2.738396624472574, "grad_norm": 1.0692051649093628, "learning_rate": 3.2409421324666674e-06, "loss": 0.912236213684082, "step": 1298 }, { "epoch": 2.742616033755274, "grad_norm": 0.6697847247123718, "learning_rate": 3.227378259263587e-06, "loss": 0.5473940372467041, "step": 1300 }, { "epoch": 2.7468354430379747, "grad_norm": 1.0614296197891235, "learning_rate": 3.213842046496896e-06, "loss": 0.967889130115509, "step": 1302 }, { "epoch": 2.7510548523206753, "grad_norm": 0.7884835600852966, "learning_rate": 3.200333658917969e-06, "loss": 0.5202937126159668, "step": 1304 }, { "epoch": 2.7552742616033754, "grad_norm": 1.617073655128479, "learning_rate": 3.1868532609395165e-06, "loss": 1.0390714406967163, "step": 1306 }, { "epoch": 2.759493670886076, "grad_norm": 1.1663974523544312, "learning_rate": 3.173401016633577e-06, "loss": 0.7771815061569214, "step": 1308 }, { "epoch": 2.7637130801687766, "grad_norm": 2.4878454208374023, "learning_rate": 3.159977089729532e-06, "loss": 0.7535280585289001, "step": 1310 }, { "epoch": 2.7679324894514767, "grad_norm": 1.4424842596054077, "learning_rate": 3.1465816436121055e-06, "loss": 0.8901900053024292, "step": 1312 }, { "epoch": 2.7721518987341773, "grad_norm": 1.9937193393707275, "learning_rate": 3.1332148413193796e-06, "loss": 0.9632768034934998, "step": 1314 }, { "epoch": 2.7763713080168775, "grad_norm": 1.2392187118530273, "learning_rate": 3.1198768455408023e-06, "loss": 0.5924683213233948, "step": 1316 }, { "epoch": 2.780590717299578, "grad_norm": 1.490188479423523, "learning_rate": 3.1065678186152186e-06, "loss": 0.4390377998352051, "step": 1318 }, { "epoch": 2.7848101265822782, "grad_norm": 0.849905252456665, "learning_rate": 3.093287922528886e-06, "loss": 0.8457968235015869, "step": 1320 }, { "epoch": 2.789029535864979, "grad_norm": 0.302488774061203, "learning_rate": 3.0800373189135096e-06, "loss": 0.5151106715202332, "step": 1322 }, { "epoch": 2.7932489451476794, "grad_norm": 1.754577398300171, "learning_rate": 3.0668161690442656e-06, "loss": 0.9207668304443359, "step": 1324 }, { "epoch": 2.7974683544303796, "grad_norm": 2.986112356185913, "learning_rate": 3.0536246338378466e-06, "loss": 0.7240561246871948, "step": 1326 }, { "epoch": 2.80168776371308, "grad_norm": 1.8140140771865845, "learning_rate": 3.040462873850503e-06, "loss": 0.6418823599815369, "step": 1328 }, { "epoch": 2.8059071729957807, "grad_norm": 0.9552450776100159, "learning_rate": 3.027331049276085e-06, "loss": 0.8471872806549072, "step": 1330 }, { "epoch": 2.810126582278481, "grad_norm": 0.7154285907745361, "learning_rate": 3.0142293199440907e-06, "loss": 0.692332923412323, "step": 1332 }, { "epoch": 2.8143459915611815, "grad_norm": 1.2054038047790527, "learning_rate": 3.001157845317727e-06, "loss": 0.524202823638916, "step": 1334 }, { "epoch": 2.818565400843882, "grad_norm": 0.2835144102573395, "learning_rate": 2.9881167844919683e-06, "loss": 0.6341201066970825, "step": 1336 }, { "epoch": 2.8227848101265822, "grad_norm": 1.1971274614334106, "learning_rate": 2.9751062961916146e-06, "loss": 0.6322475671768188, "step": 1338 }, { "epoch": 2.827004219409283, "grad_norm": 2.352694511413574, "learning_rate": 2.962126538769362e-06, "loss": 0.8327752351760864, "step": 1340 }, { "epoch": 2.831223628691983, "grad_norm": 1.024727463722229, "learning_rate": 2.949177670203883e-06, "loss": 0.8421899676322937, "step": 1342 }, { "epoch": 2.8354430379746836, "grad_norm": 2.226130485534668, "learning_rate": 2.9362598480978867e-06, "loss": 1.0524921417236328, "step": 1344 }, { "epoch": 2.8396624472573837, "grad_norm": 1.945210337638855, "learning_rate": 2.9233732296762173e-06, "loss": 0.6259896755218506, "step": 1346 }, { "epoch": 2.8438818565400843, "grad_norm": 0.8308857679367065, "learning_rate": 2.9105179717839353e-06, "loss": 0.5016956329345703, "step": 1348 }, { "epoch": 2.848101265822785, "grad_norm": 1.6660699844360352, "learning_rate": 2.897694230884405e-06, "loss": 0.9290784597396851, "step": 1350 }, { "epoch": 2.852320675105485, "grad_norm": 0.8582704663276672, "learning_rate": 2.88490216305739e-06, "loss": 0.5587412118911743, "step": 1352 }, { "epoch": 2.8565400843881856, "grad_norm": 1.8050309419631958, "learning_rate": 2.8721419239971582e-06, "loss": 0.601135790348053, "step": 1354 }, { "epoch": 2.8607594936708862, "grad_norm": 1.970723032951355, "learning_rate": 2.8594136690105867e-06, "loss": 0.5153637528419495, "step": 1356 }, { "epoch": 2.8649789029535864, "grad_norm": 1.3061662912368774, "learning_rate": 2.846717553015268e-06, "loss": 0.8993398547172546, "step": 1358 }, { "epoch": 2.869198312236287, "grad_norm": 0.9573718905448914, "learning_rate": 2.834053730537622e-06, "loss": 0.6737149357795715, "step": 1360 }, { "epoch": 2.8734177215189876, "grad_norm": 1.0735780000686646, "learning_rate": 2.821422355711024e-06, "loss": 0.5662659406661987, "step": 1362 }, { "epoch": 2.8776371308016877, "grad_norm": 1.5357694625854492, "learning_rate": 2.8088235822739253e-06, "loss": 0.8427922129631042, "step": 1364 }, { "epoch": 2.8818565400843883, "grad_norm": 1.1373776197433472, "learning_rate": 2.796257563567973e-06, "loss": 0.8800983428955078, "step": 1366 }, { "epoch": 2.8860759493670884, "grad_norm": 1.8824827671051025, "learning_rate": 2.7837244525361573e-06, "loss": 0.9415411949157715, "step": 1368 }, { "epoch": 2.890295358649789, "grad_norm": 2.000551223754883, "learning_rate": 2.771224401720942e-06, "loss": 0.887091338634491, "step": 1370 }, { "epoch": 2.894514767932489, "grad_norm": 2.074234962463379, "learning_rate": 2.7587575632624143e-06, "loss": 0.2655407190322876, "step": 1372 }, { "epoch": 2.8987341772151898, "grad_norm": 0.8872388005256653, "learning_rate": 2.7463240888964184e-06, "loss": 0.57696133852005, "step": 1374 }, { "epoch": 2.9029535864978904, "grad_norm": 1.0017720460891724, "learning_rate": 2.733924129952727e-06, "loss": 0.8804340958595276, "step": 1376 }, { "epoch": 2.9071729957805905, "grad_norm": 4.621462345123291, "learning_rate": 2.7215578373531905e-06, "loss": 0.6950758695602417, "step": 1378 }, { "epoch": 2.911392405063291, "grad_norm": 1.5469801425933838, "learning_rate": 2.709225361609901e-06, "loss": 0.9981220364570618, "step": 1380 }, { "epoch": 2.9156118143459917, "grad_norm": 2.7214841842651367, "learning_rate": 2.6969268528233545e-06, "loss": 0.43611621856689453, "step": 1382 }, { "epoch": 2.919831223628692, "grad_norm": 2.159730911254883, "learning_rate": 2.6846624606806372e-06, "loss": 0.6117579936981201, "step": 1384 }, { "epoch": 2.9240506329113924, "grad_norm": 0.6078017950057983, "learning_rate": 2.6724323344535953e-06, "loss": 0.5143052339553833, "step": 1386 }, { "epoch": 2.928270042194093, "grad_norm": 0.8536535501480103, "learning_rate": 2.6602366229970137e-06, "loss": 0.8916317224502563, "step": 1388 }, { "epoch": 2.932489451476793, "grad_norm": 0.8162920475006104, "learning_rate": 2.6480754747468153e-06, "loss": 0.8466449975967407, "step": 1390 }, { "epoch": 2.9367088607594938, "grad_norm": 0.6464320421218872, "learning_rate": 2.635949037718246e-06, "loss": 0.4764333665370941, "step": 1392 }, { "epoch": 2.9409282700421944, "grad_norm": 1.022177815437317, "learning_rate": 2.623857459504078e-06, "loss": 0.44133251905441284, "step": 1394 }, { "epoch": 2.9451476793248945, "grad_norm": 1.0162975788116455, "learning_rate": 2.6118008872728095e-06, "loss": 0.8427251577377319, "step": 1396 }, { "epoch": 2.9493670886075947, "grad_norm": 0.3307487964630127, "learning_rate": 2.5997794677668746e-06, "loss": 0.6520959734916687, "step": 1398 }, { "epoch": 2.9535864978902953, "grad_norm": 3.7802846431732178, "learning_rate": 2.587793347300861e-06, "loss": 0.832510232925415, "step": 1400 }, { "epoch": 2.957805907172996, "grad_norm": 2.1209182739257812, "learning_rate": 2.5758426717597257e-06, "loss": 0.5920344591140747, "step": 1402 }, { "epoch": 2.962025316455696, "grad_norm": 0.9574135541915894, "learning_rate": 2.563927586597017e-06, "loss": 0.8643596768379211, "step": 1404 }, { "epoch": 2.9662447257383966, "grad_norm": 2.102473497390747, "learning_rate": 2.552048236833109e-06, "loss": 0.788807213306427, "step": 1406 }, { "epoch": 2.970464135021097, "grad_norm": 2.4797873497009277, "learning_rate": 2.5402047670534375e-06, "loss": 0.44266387820243835, "step": 1408 }, { "epoch": 2.9746835443037973, "grad_norm": 1.5320416688919067, "learning_rate": 2.528397321406731e-06, "loss": 0.8683050274848938, "step": 1410 }, { "epoch": 2.978902953586498, "grad_norm": 0.7563115358352661, "learning_rate": 2.5166260436032686e-06, "loss": 0.9286722540855408, "step": 1412 }, { "epoch": 2.9831223628691985, "grad_norm": 1.4289554357528687, "learning_rate": 2.504891076913121e-06, "loss": 0.66124027967453, "step": 1414 }, { "epoch": 2.9873417721518987, "grad_norm": 0.8497927784919739, "learning_rate": 2.493192564164415e-06, "loss": 0.7980862855911255, "step": 1416 }, { "epoch": 2.9915611814345993, "grad_norm": 0.7365954518318176, "learning_rate": 2.4815306477415843e-06, "loss": 0.7196717858314514, "step": 1418 }, { "epoch": 2.9957805907173, "grad_norm": 3.072756290435791, "learning_rate": 2.469905469583648e-06, "loss": 0.8641300797462463, "step": 1420 }, { "epoch": 3.0, "grad_norm": 0.6757546067237854, "learning_rate": 2.4583171711824767e-06, "loss": 0.2503686845302582, "step": 1422 }, { "epoch": 3.0042194092827006, "grad_norm": 0.7034198641777039, "learning_rate": 2.4467658935810738e-06, "loss": 0.48008522391319275, "step": 1424 }, { "epoch": 3.0084388185654007, "grad_norm": 2.0994513034820557, "learning_rate": 2.43525177737185e-06, "loss": 0.42200714349746704, "step": 1426 }, { "epoch": 3.0126582278481013, "grad_norm": 1.5376875400543213, "learning_rate": 2.423774962694926e-06, "loss": 0.46593034267425537, "step": 1428 }, { "epoch": 3.0168776371308015, "grad_norm": 1.996058702468872, "learning_rate": 2.4123355892364162e-06, "loss": 0.2053375244140625, "step": 1430 }, { "epoch": 3.021097046413502, "grad_norm": 0.7631147503852844, "learning_rate": 2.4009337962267354e-06, "loss": 0.8324798941612244, "step": 1432 }, { "epoch": 3.0253164556962027, "grad_norm": 0.8996366262435913, "learning_rate": 2.3895697224388944e-06, "loss": 0.7130314111709595, "step": 1434 }, { "epoch": 3.029535864978903, "grad_norm": 1.1378889083862305, "learning_rate": 2.3782435061868237e-06, "loss": 0.8925870656967163, "step": 1436 }, { "epoch": 3.0337552742616034, "grad_norm": 1.352307677268982, "learning_rate": 2.366955285323682e-06, "loss": 0.43893763422966003, "step": 1438 }, { "epoch": 3.037974683544304, "grad_norm": 0.9720532298088074, "learning_rate": 2.3557051972401765e-06, "loss": 0.7230754494667053, "step": 1440 }, { "epoch": 3.042194092827004, "grad_norm": 0.5884406566619873, "learning_rate": 2.3444933788629005e-06, "loss": 0.5438792109489441, "step": 1442 }, { "epoch": 3.0464135021097047, "grad_norm": 0.9816262722015381, "learning_rate": 2.333319966652656e-06, "loss": 0.6565508842468262, "step": 1444 }, { "epoch": 3.050632911392405, "grad_norm": 0.9301005005836487, "learning_rate": 2.322185096602801e-06, "loss": 0.7488085031509399, "step": 1446 }, { "epoch": 3.0548523206751055, "grad_norm": 12.703023910522461, "learning_rate": 2.311088904237586e-06, "loss": 0.5115925669670105, "step": 1448 }, { "epoch": 3.059071729957806, "grad_norm": 3.3351986408233643, "learning_rate": 2.300031524610514e-06, "loss": 0.5711902976036072, "step": 1450 }, { "epoch": 3.0632911392405062, "grad_norm": 1.271050214767456, "learning_rate": 2.2890130923026903e-06, "loss": 0.8190644979476929, "step": 1452 }, { "epoch": 3.067510548523207, "grad_norm": 1.342450737953186, "learning_rate": 2.278033741421187e-06, "loss": 0.49537673592567444, "step": 1454 }, { "epoch": 3.071729957805907, "grad_norm": 1.6169253587722778, "learning_rate": 2.2670936055974075e-06, "loss": 0.382347047328949, "step": 1456 }, { "epoch": 3.0759493670886076, "grad_norm": 0.8829827904701233, "learning_rate": 2.256192817985465e-06, "loss": 0.4912588894367218, "step": 1458 }, { "epoch": 3.080168776371308, "grad_norm": 2.859389305114746, "learning_rate": 2.2453315112605604e-06, "loss": 0.4515080153942108, "step": 1460 }, { "epoch": 3.0843881856540083, "grad_norm": 0.805213212966919, "learning_rate": 2.2345098176173624e-06, "loss": 0.712715744972229, "step": 1462 }, { "epoch": 3.088607594936709, "grad_norm": 0.9044957160949707, "learning_rate": 2.2237278687684065e-06, "loss": 0.715802788734436, "step": 1464 }, { "epoch": 3.0928270042194095, "grad_norm": 0.9757974147796631, "learning_rate": 2.212985795942486e-06, "loss": 0.6326949000358582, "step": 1466 }, { "epoch": 3.0970464135021096, "grad_norm": 6.477185249328613, "learning_rate": 2.20228372988306e-06, "loss": 0.47976550459861755, "step": 1468 }, { "epoch": 3.1012658227848102, "grad_norm": 6.598858833312988, "learning_rate": 2.1916218008466524e-06, "loss": 0.06490237265825272, "step": 1470 }, { "epoch": 3.1054852320675104, "grad_norm": 2.848353385925293, "learning_rate": 2.18100013860128e-06, "loss": 0.7451671361923218, "step": 1472 }, { "epoch": 3.109704641350211, "grad_norm": 0.1323925107717514, "learning_rate": 2.170418872424863e-06, "loss": 0.41649919748306274, "step": 1474 }, { "epoch": 3.1139240506329116, "grad_norm": 1.0177364349365234, "learning_rate": 2.1598781311036563e-06, "loss": 0.767039954662323, "step": 1476 }, { "epoch": 3.1181434599156117, "grad_norm": 1.0474977493286133, "learning_rate": 2.149378042930676e-06, "loss": 0.835081160068512, "step": 1478 }, { "epoch": 3.1223628691983123, "grad_norm": 0.9528142809867859, "learning_rate": 2.138918735704148e-06, "loss": 0.6867841482162476, "step": 1480 }, { "epoch": 3.1265822784810124, "grad_norm": 1.8177701234817505, "learning_rate": 2.1285003367259445e-06, "loss": 0.7511188983917236, "step": 1482 }, { "epoch": 3.130801687763713, "grad_norm": 0.8467079401016235, "learning_rate": 2.1181229728000353e-06, "loss": 0.7508360743522644, "step": 1484 }, { "epoch": 3.1350210970464136, "grad_norm": 0.9410977959632874, "learning_rate": 2.1077867702309482e-06, "loss": 0.43571022152900696, "step": 1486 }, { "epoch": 3.1392405063291138, "grad_norm": 0.8319637775421143, "learning_rate": 2.0974918548222294e-06, "loss": 0.40240466594696045, "step": 1488 }, { "epoch": 3.1434599156118144, "grad_norm": 1.5343444347381592, "learning_rate": 2.0872383518749147e-06, "loss": 0.8346313834190369, "step": 1490 }, { "epoch": 3.147679324894515, "grad_norm": 2.50876522064209, "learning_rate": 2.077026386185996e-06, "loss": 0.5276301503181458, "step": 1492 }, { "epoch": 3.151898734177215, "grad_norm": 4.581535816192627, "learning_rate": 2.0668560820469152e-06, "loss": 0.5576310157775879, "step": 1494 }, { "epoch": 3.1561181434599157, "grad_norm": 1.7419183254241943, "learning_rate": 2.0567275632420412e-06, "loss": 0.5430642366409302, "step": 1496 }, { "epoch": 3.160337552742616, "grad_norm": 1.23338782787323, "learning_rate": 2.0466409530471702e-06, "loss": 0.37109193205833435, "step": 1498 }, { "epoch": 3.1645569620253164, "grad_norm": 1.194543480873108, "learning_rate": 2.0365963742280178e-06, "loss": 0.3984225392341614, "step": 1500 }, { "epoch": 3.168776371308017, "grad_norm": 1.2410297393798828, "learning_rate": 2.0265939490387325e-06, "loss": 0.753200352191925, "step": 1502 }, { "epoch": 3.172995780590717, "grad_norm": 1.0101797580718994, "learning_rate": 2.016633799220403e-06, "loss": 0.5517244338989258, "step": 1504 }, { "epoch": 3.1772151898734178, "grad_norm": 0.7676177024841309, "learning_rate": 2.00671604599958e-06, "loss": 0.7535607814788818, "step": 1506 }, { "epoch": 3.181434599156118, "grad_norm": 0.9343335628509521, "learning_rate": 1.9968408100867947e-06, "loss": 0.761473536491394, "step": 1508 }, { "epoch": 3.1856540084388185, "grad_norm": 8.236842155456543, "learning_rate": 1.9870082116750954e-06, "loss": 0.7786921262741089, "step": 1510 }, { "epoch": 3.189873417721519, "grad_norm": 1.3662457466125488, "learning_rate": 1.9772183704385846e-06, "loss": 0.16808030009269714, "step": 1512 }, { "epoch": 3.1940928270042193, "grad_norm": 0.9107233881950378, "learning_rate": 1.967471405530956e-06, "loss": 0.6586081385612488, "step": 1514 }, { "epoch": 3.19831223628692, "grad_norm": 0.3760078251361847, "learning_rate": 1.957767435584053e-06, "loss": 0.4365515112876892, "step": 1516 }, { "epoch": 3.2025316455696204, "grad_norm": 0.9538941979408264, "learning_rate": 1.948106578706419e-06, "loss": 0.8228858709335327, "step": 1518 }, { "epoch": 3.2067510548523206, "grad_norm": 1.5654665231704712, "learning_rate": 1.938488952481863e-06, "loss": 0.6656263470649719, "step": 1520 }, { "epoch": 3.210970464135021, "grad_norm": 2.4456095695495605, "learning_rate": 1.928914673968021e-06, "loss": 0.22482064366340637, "step": 1522 }, { "epoch": 3.2151898734177213, "grad_norm": 1.5158286094665527, "learning_rate": 1.9193838596949454e-06, "loss": 0.5232290029525757, "step": 1524 }, { "epoch": 3.219409282700422, "grad_norm": 1.7476248741149902, "learning_rate": 1.9098966256636724e-06, "loss": 0.6611694097518921, "step": 1526 }, { "epoch": 3.2236286919831225, "grad_norm": 0.34821638464927673, "learning_rate": 1.9004530873448218e-06, "loss": 0.2679532766342163, "step": 1528 }, { "epoch": 3.2278481012658227, "grad_norm": 3.054241895675659, "learning_rate": 1.8910533596771788e-06, "loss": 0.5168284177780151, "step": 1530 }, { "epoch": 3.2320675105485233, "grad_norm": 0.26659509539604187, "learning_rate": 1.8816975570663077e-06, "loss": 0.0904851034283638, "step": 1532 }, { "epoch": 3.2362869198312234, "grad_norm": 2.452047824859619, "learning_rate": 1.8723857933831535e-06, "loss": 0.7081596851348877, "step": 1534 }, { "epoch": 3.240506329113924, "grad_norm": 0.9422764182090759, "learning_rate": 1.8631181819626542e-06, "loss": 0.6472712755203247, "step": 1536 }, { "epoch": 3.2447257383966246, "grad_norm": 0.8585634231567383, "learning_rate": 1.8538948356023647e-06, "loss": 0.5950202345848083, "step": 1538 }, { "epoch": 3.2489451476793247, "grad_norm": 3.480011463165283, "learning_rate": 1.8447158665610842e-06, "loss": 0.5550104379653931, "step": 1540 }, { "epoch": 3.2531645569620253, "grad_norm": 4.935113906860352, "learning_rate": 1.8355813865574884e-06, "loss": 0.5158566832542419, "step": 1542 }, { "epoch": 3.257383966244726, "grad_norm": 4.212364196777344, "learning_rate": 1.8264915067687666e-06, "loss": 0.5667371153831482, "step": 1544 }, { "epoch": 3.261603375527426, "grad_norm": 1.6413614749908447, "learning_rate": 1.8174463378292762e-06, "loss": 0.42425766587257385, "step": 1546 }, { "epoch": 3.2658227848101267, "grad_norm": 0.9698576331138611, "learning_rate": 1.808445989829189e-06, "loss": 0.6741539239883423, "step": 1548 }, { "epoch": 3.270042194092827, "grad_norm": 2.9141268730163574, "learning_rate": 1.7994905723131567e-06, "loss": 0.22690419852733612, "step": 1550 }, { "epoch": 3.2742616033755274, "grad_norm": 0.9573975205421448, "learning_rate": 1.7905801942789711e-06, "loss": 0.1521233469247818, "step": 1552 }, { "epoch": 3.278481012658228, "grad_norm": 1.928755521774292, "learning_rate": 1.781714964176245e-06, "loss": 0.36475875973701477, "step": 1554 }, { "epoch": 3.282700421940928, "grad_norm": 0.9502660632133484, "learning_rate": 1.7728949899050879e-06, "loss": 0.6794001460075378, "step": 1556 }, { "epoch": 3.2869198312236287, "grad_norm": 0.21531406044960022, "learning_rate": 1.7641203788147913e-06, "loss": 0.4672155976295471, "step": 1558 }, { "epoch": 3.291139240506329, "grad_norm": 1.0818421840667725, "learning_rate": 1.7553912377025251e-06, "loss": 0.4196876585483551, "step": 1560 }, { "epoch": 3.2953586497890295, "grad_norm": 1.9371572732925415, "learning_rate": 1.7467076728120416e-06, "loss": 0.43262502551078796, "step": 1562 }, { "epoch": 3.29957805907173, "grad_norm": 1.8827433586120605, "learning_rate": 1.7380697898323707e-06, "loss": 0.6897112727165222, "step": 1564 }, { "epoch": 3.3037974683544302, "grad_norm": 2.5251636505126953, "learning_rate": 1.7294776938965443e-06, "loss": 0.5110076069831848, "step": 1566 }, { "epoch": 3.308016877637131, "grad_norm": 0.5228278636932373, "learning_rate": 1.7209314895803132e-06, "loss": 0.34877893328666687, "step": 1568 }, { "epoch": 3.3122362869198314, "grad_norm": 2.872612953186035, "learning_rate": 1.7124312809008736e-06, "loss": 0.2827436029911041, "step": 1570 }, { "epoch": 3.3164556962025316, "grad_norm": 1.213196873664856, "learning_rate": 1.703977171315599e-06, "loss": 0.4463627338409424, "step": 1572 }, { "epoch": 3.320675105485232, "grad_norm": 1.4449701309204102, "learning_rate": 1.6955692637207883e-06, "loss": 0.8240289092063904, "step": 1574 }, { "epoch": 3.3248945147679323, "grad_norm": 1.1643035411834717, "learning_rate": 1.6872076604504053e-06, "loss": 0.5528379082679749, "step": 1576 }, { "epoch": 3.329113924050633, "grad_norm": 1.1459054946899414, "learning_rate": 1.6788924632748383e-06, "loss": 0.7021325826644897, "step": 1578 }, { "epoch": 3.3333333333333335, "grad_norm": 1.096561074256897, "learning_rate": 1.6706237733996578e-06, "loss": 0.42998167872428894, "step": 1580 }, { "epoch": 3.3375527426160336, "grad_norm": 0.9841512441635132, "learning_rate": 1.6624016914643882e-06, "loss": 0.37765806913375854, "step": 1582 }, { "epoch": 3.3417721518987342, "grad_norm": 2.4759042263031006, "learning_rate": 1.6542263175412827e-06, "loss": 0.6210746169090271, "step": 1584 }, { "epoch": 3.3459915611814344, "grad_norm": 3.4111969470977783, "learning_rate": 1.6460977511340993e-06, "loss": 0.497697651386261, "step": 1586 }, { "epoch": 3.350210970464135, "grad_norm": 0.9993033409118652, "learning_rate": 1.638016091176899e-06, "loss": 0.2598119080066681, "step": 1588 }, { "epoch": 3.3544303797468356, "grad_norm": 1.674139380455017, "learning_rate": 1.6299814360328353e-06, "loss": 0.698246955871582, "step": 1590 }, { "epoch": 3.3586497890295357, "grad_norm": 1.6265552043914795, "learning_rate": 1.6219938834929594e-06, "loss": 0.6517130136489868, "step": 1592 }, { "epoch": 3.3628691983122363, "grad_norm": 0.30047714710235596, "learning_rate": 1.6140535307750272e-06, "loss": 0.4073562026023865, "step": 1594 }, { "epoch": 3.367088607594937, "grad_norm": 2.1237504482269287, "learning_rate": 1.6061604745223194e-06, "loss": 0.26270949840545654, "step": 1596 }, { "epoch": 3.371308016877637, "grad_norm": 0.3136138916015625, "learning_rate": 1.598314810802466e-06, "loss": 0.32933512330055237, "step": 1598 }, { "epoch": 3.3755274261603376, "grad_norm": 6.139480113983154, "learning_rate": 1.5905166351062723e-06, "loss": 0.4753924608230591, "step": 1600 }, { "epoch": 3.379746835443038, "grad_norm": 0.9504700899124146, "learning_rate": 1.5827660423465601e-06, "loss": 0.40094509720802307, "step": 1602 }, { "epoch": 3.3839662447257384, "grad_norm": 0.3125917613506317, "learning_rate": 1.5750631268570112e-06, "loss": 0.3668811619281769, "step": 1604 }, { "epoch": 3.388185654008439, "grad_norm": 1.0951470136642456, "learning_rate": 1.5674079823910226e-06, "loss": 0.801574170589447, "step": 1606 }, { "epoch": 3.392405063291139, "grad_norm": 1.1177030801773071, "learning_rate": 1.5598007021205608e-06, "loss": 0.412584513425827, "step": 1608 }, { "epoch": 3.3966244725738397, "grad_norm": 0.919816792011261, "learning_rate": 1.552241378635027e-06, "loss": 0.38608789443969727, "step": 1610 }, { "epoch": 3.40084388185654, "grad_norm": 0.8037455677986145, "learning_rate": 1.5447301039401378e-06, "loss": 0.6610428690910339, "step": 1612 }, { "epoch": 3.4050632911392404, "grad_norm": 0.6057993173599243, "learning_rate": 1.5372669694567975e-06, "loss": 0.19705288112163544, "step": 1614 }, { "epoch": 3.409282700421941, "grad_norm": 1.795708179473877, "learning_rate": 1.5298520660199884e-06, "loss": 0.5120692253112793, "step": 1616 }, { "epoch": 3.413502109704641, "grad_norm": 0.8644084930419922, "learning_rate": 1.5224854838776655e-06, "loss": 0.7795750498771667, "step": 1618 }, { "epoch": 3.4177215189873418, "grad_norm": 0.835720419883728, "learning_rate": 1.5151673126896582e-06, "loss": 0.7784020900726318, "step": 1620 }, { "epoch": 3.4219409282700424, "grad_norm": 1.0033234357833862, "learning_rate": 1.5078976415265792e-06, "loss": 0.39296573400497437, "step": 1622 }, { "epoch": 3.4261603375527425, "grad_norm": 2.746508836746216, "learning_rate": 1.5006765588687364e-06, "loss": 0.18016311526298523, "step": 1624 }, { "epoch": 3.430379746835443, "grad_norm": 2.4568941593170166, "learning_rate": 1.4935041526050642e-06, "loss": 0.19380182027816772, "step": 1626 }, { "epoch": 3.4345991561181437, "grad_norm": 1.0824241638183594, "learning_rate": 1.4863805100320446e-06, "loss": 0.7001661062240601, "step": 1628 }, { "epoch": 3.438818565400844, "grad_norm": 1.1608247756958008, "learning_rate": 1.4793057178526535e-06, "loss": 0.2364884465932846, "step": 1630 }, { "epoch": 3.4430379746835444, "grad_norm": 1.1154956817626953, "learning_rate": 1.4722798621752955e-06, "loss": 0.8514795899391174, "step": 1632 }, { "epoch": 3.4472573839662446, "grad_norm": 0.26867973804473877, "learning_rate": 1.4653030285127655e-06, "loss": 0.4324265122413635, "step": 1634 }, { "epoch": 3.451476793248945, "grad_norm": 2.6347060203552246, "learning_rate": 1.458375301781204e-06, "loss": 0.6815493702888489, "step": 1636 }, { "epoch": 3.4556962025316453, "grad_norm": 5.761023044586182, "learning_rate": 1.4514967662990595e-06, "loss": 0.8933783769607544, "step": 1638 }, { "epoch": 3.459915611814346, "grad_norm": 2.1877338886260986, "learning_rate": 1.4446675057860693e-06, "loss": 0.7585189938545227, "step": 1640 }, { "epoch": 3.4641350210970465, "grad_norm": 1.3892275094985962, "learning_rate": 1.4378876033622362e-06, "loss": 0.7087560892105103, "step": 1642 }, { "epoch": 3.4683544303797467, "grad_norm": 0.4493592381477356, "learning_rate": 1.4311571415468201e-06, "loss": 0.17352484166622162, "step": 1644 }, { "epoch": 3.4725738396624473, "grad_norm": 0.9975357055664062, "learning_rate": 1.4244762022573269e-06, "loss": 0.552936315536499, "step": 1646 }, { "epoch": 3.476793248945148, "grad_norm": 1.205847978591919, "learning_rate": 1.4178448668085198e-06, "loss": 0.7463341355323792, "step": 1648 }, { "epoch": 3.481012658227848, "grad_norm": 1.143504023551941, "learning_rate": 1.4112632159114253e-06, "loss": 0.33594828844070435, "step": 1650 }, { "epoch": 3.4852320675105486, "grad_norm": 1.0623492002487183, "learning_rate": 1.4047313296723512e-06, "loss": 0.5425666570663452, "step": 1652 }, { "epoch": 3.489451476793249, "grad_norm": 0.23641593754291534, "learning_rate": 1.3982492875919098e-06, "loss": 0.378449946641922, "step": 1654 }, { "epoch": 3.4936708860759493, "grad_norm": 0.6653390526771545, "learning_rate": 1.3918171685640555e-06, "loss": 0.4959578514099121, "step": 1656 }, { "epoch": 3.49789029535865, "grad_norm": 2.064697027206421, "learning_rate": 1.3854350508751193e-06, "loss": 0.5861192345619202, "step": 1658 }, { "epoch": 3.50210970464135, "grad_norm": 0.9278109669685364, "learning_rate": 1.379103012202859e-06, "loss": 0.6913314461708069, "step": 1660 }, { "epoch": 3.5063291139240507, "grad_norm": 3.567821979522705, "learning_rate": 1.3728211296155116e-06, "loss": 0.7072320580482483, "step": 1662 }, { "epoch": 3.510548523206751, "grad_norm": 3.988811492919922, "learning_rate": 1.3665894795708585e-06, "loss": 0.30893296003341675, "step": 1664 }, { "epoch": 3.5147679324894514, "grad_norm": 1.6869466304779053, "learning_rate": 1.3604081379152916e-06, "loss": 0.7611141204833984, "step": 1666 }, { "epoch": 3.518987341772152, "grad_norm": 2.7361690998077393, "learning_rate": 1.3542771798828917e-06, "loss": 0.4133511185646057, "step": 1668 }, { "epoch": 3.523206751054852, "grad_norm": 0.824147641658783, "learning_rate": 1.3481966800945118e-06, "loss": 0.72611403465271, "step": 1670 }, { "epoch": 3.5274261603375527, "grad_norm": 2.7410728931427, "learning_rate": 1.342166712556871e-06, "loss": 0.19016826152801514, "step": 1672 }, { "epoch": 3.5316455696202533, "grad_norm": 1.1030796766281128, "learning_rate": 1.3361873506616527e-06, "loss": 0.4317885935306549, "step": 1674 }, { "epoch": 3.5358649789029535, "grad_norm": 6.5921406745910645, "learning_rate": 1.330258667184609e-06, "loss": 0.531998872756958, "step": 1676 }, { "epoch": 3.540084388185654, "grad_norm": 3.1609206199645996, "learning_rate": 1.3243807342846784e-06, "loss": 0.4869120717048645, "step": 1678 }, { "epoch": 3.5443037974683547, "grad_norm": 1.309848666191101, "learning_rate": 1.3185536235031075e-06, "loss": 0.7829226851463318, "step": 1680 }, { "epoch": 3.548523206751055, "grad_norm": 0.9369983077049255, "learning_rate": 1.3127774057625764e-06, "loss": 0.557019054889679, "step": 1682 }, { "epoch": 3.5527426160337554, "grad_norm": 2.0268139839172363, "learning_rate": 1.307052151366339e-06, "loss": 0.7136536836624146, "step": 1684 }, { "epoch": 3.5569620253164556, "grad_norm": 2.2542266845703125, "learning_rate": 1.3013779299973665e-06, "loss": 0.15833915770053864, "step": 1686 }, { "epoch": 3.561181434599156, "grad_norm": 0.3605692684650421, "learning_rate": 1.2957548107174997e-06, "loss": 0.36434122920036316, "step": 1688 }, { "epoch": 3.5654008438818563, "grad_norm": 1.3760899305343628, "learning_rate": 1.2901828619666053e-06, "loss": 0.7427794933319092, "step": 1690 }, { "epoch": 3.569620253164557, "grad_norm": 3.3748419284820557, "learning_rate": 1.2846621515617488e-06, "loss": 0.1066126599907875, "step": 1692 }, { "epoch": 3.5738396624472575, "grad_norm": 0.24079623818397522, "learning_rate": 1.2791927466963641e-06, "loss": 0.5616010427474976, "step": 1694 }, { "epoch": 3.5780590717299576, "grad_norm": 2.4317874908447266, "learning_rate": 1.2737747139394373e-06, "loss": 0.16680264472961426, "step": 1696 }, { "epoch": 3.5822784810126582, "grad_norm": 2.811868190765381, "learning_rate": 1.2684081192346964e-06, "loss": 0.4473068416118622, "step": 1698 }, { "epoch": 3.586497890295359, "grad_norm": 0.8403407335281372, "learning_rate": 1.263093027899809e-06, "loss": 0.4710557162761688, "step": 1700 }, { "epoch": 3.590717299578059, "grad_norm": 1.3591110706329346, "learning_rate": 1.257829504625587e-06, "loss": 0.3712272644042969, "step": 1702 }, { "epoch": 3.5949367088607596, "grad_norm": 1.0779433250427246, "learning_rate": 1.2526176134752009e-06, "loss": 0.6357992887496948, "step": 1704 }, { "epoch": 3.59915611814346, "grad_norm": 1.0337231159210205, "learning_rate": 1.2474574178833945e-06, "loss": 0.42933955788612366, "step": 1706 }, { "epoch": 3.6033755274261603, "grad_norm": 1.9262011051177979, "learning_rate": 1.2423489806557212e-06, "loss": 0.4344020485877991, "step": 1708 }, { "epoch": 3.607594936708861, "grad_norm": 0.4806056022644043, "learning_rate": 1.2372923639677734e-06, "loss": 0.36270609498023987, "step": 1710 }, { "epoch": 3.611814345991561, "grad_norm": 0.9081553816795349, "learning_rate": 1.2322876293644264e-06, "loss": 0.6728399395942688, "step": 1712 }, { "epoch": 3.6160337552742616, "grad_norm": 3.634809732437134, "learning_rate": 1.227334837759092e-06, "loss": 0.7867997884750366, "step": 1714 }, { "epoch": 3.620253164556962, "grad_norm": 1.037297248840332, "learning_rate": 1.2224340494329754e-06, "loss": 0.4691082537174225, "step": 1716 }, { "epoch": 3.6244725738396624, "grad_norm": 1.400949239730835, "learning_rate": 1.217585324034343e-06, "loss": 0.30403026938438416, "step": 1718 }, { "epoch": 3.628691983122363, "grad_norm": 4.410190582275391, "learning_rate": 1.212788720577791e-06, "loss": 0.14185987412929535, "step": 1720 }, { "epoch": 3.632911392405063, "grad_norm": 1.215036392211914, "learning_rate": 1.2080442974435357e-06, "loss": 0.6829768419265747, "step": 1722 }, { "epoch": 3.6371308016877637, "grad_norm": 3.4625253677368164, "learning_rate": 1.2033521123766964e-06, "loss": 0.2671421766281128, "step": 1724 }, { "epoch": 3.6413502109704643, "grad_norm": 5.7889885902404785, "learning_rate": 1.1987122224865958e-06, "loss": 0.19312286376953125, "step": 1726 }, { "epoch": 3.6455696202531644, "grad_norm": 1.6845052242279053, "learning_rate": 1.1941246842460608e-06, "loss": 0.6866393685340881, "step": 1728 }, { "epoch": 3.649789029535865, "grad_norm": 2.1908621788024902, "learning_rate": 1.1895895534907422e-06, "loss": 0.1419493705034256, "step": 1730 }, { "epoch": 3.6540084388185656, "grad_norm": 2.3620223999023438, "learning_rate": 1.1851068854184285e-06, "loss": 0.781204342842102, "step": 1732 }, { "epoch": 3.6582278481012658, "grad_norm": 2.979437828063965, "learning_rate": 1.1806767345883786e-06, "loss": 0.1693078726530075, "step": 1734 }, { "epoch": 3.6624472573839664, "grad_norm": 0.948310911655426, "learning_rate": 1.1762991549206526e-06, "loss": 0.20168332755565643, "step": 1736 }, { "epoch": 3.6666666666666665, "grad_norm": 1.4314289093017578, "learning_rate": 1.1719741996954616e-06, "loss": 0.492892324924469, "step": 1738 }, { "epoch": 3.670886075949367, "grad_norm": 1.343795657157898, "learning_rate": 1.1677019215525157e-06, "loss": 0.184087336063385, "step": 1740 }, { "epoch": 3.6751054852320673, "grad_norm": 0.8561673760414124, "learning_rate": 1.1634823724903831e-06, "loss": 0.8875271081924438, "step": 1742 }, { "epoch": 3.679324894514768, "grad_norm": 0.8399161100387573, "learning_rate": 1.1593156038658585e-06, "loss": 0.4086609482765198, "step": 1744 }, { "epoch": 3.6835443037974684, "grad_norm": 1.2690807580947876, "learning_rate": 1.155201666393338e-06, "loss": 0.4635493755340576, "step": 1746 }, { "epoch": 3.6877637130801686, "grad_norm": 1.5574302673339844, "learning_rate": 1.1511406101442017e-06, "loss": 0.8151191473007202, "step": 1748 }, { "epoch": 3.691983122362869, "grad_norm": 1.122839093208313, "learning_rate": 1.1471324845462025e-06, "loss": 0.6579084992408752, "step": 1750 }, { "epoch": 3.6962025316455698, "grad_norm": 1.312188744544983, "learning_rate": 1.1431773383828677e-06, "loss": 0.690669596195221, "step": 1752 }, { "epoch": 3.70042194092827, "grad_norm": 1.1095813512802124, "learning_rate": 1.139275219792902e-06, "loss": 0.832473635673523, "step": 1754 }, { "epoch": 3.7046413502109705, "grad_norm": 1.8412452936172485, "learning_rate": 1.1354261762696058e-06, "loss": 0.5572829246520996, "step": 1756 }, { "epoch": 3.708860759493671, "grad_norm": 1.6649295091629028, "learning_rate": 1.131630254660291e-06, "loss": 0.5332546234130859, "step": 1758 }, { "epoch": 3.7130801687763713, "grad_norm": 3.771629571914673, "learning_rate": 1.1278875011657168e-06, "loss": 0.5314247608184814, "step": 1760 }, { "epoch": 3.717299578059072, "grad_norm": 2.1248600482940674, "learning_rate": 1.1241979613395246e-06, "loss": 0.10494165867567062, "step": 1762 }, { "epoch": 3.721518987341772, "grad_norm": 9.594347953796387, "learning_rate": 1.120561680087682e-06, "loss": 0.27785858511924744, "step": 1764 }, { "epoch": 3.7257383966244726, "grad_norm": 0.9054338932037354, "learning_rate": 1.1169787016679412e-06, "loss": 0.6860408782958984, "step": 1766 }, { "epoch": 3.7299578059071727, "grad_norm": 1.7399121522903442, "learning_rate": 1.1134490696892955e-06, "loss": 0.3859502971172333, "step": 1768 }, { "epoch": 3.7341772151898733, "grad_norm": 1.3602585792541504, "learning_rate": 1.1099728271114502e-06, "loss": 0.42375150322914124, "step": 1770 }, { "epoch": 3.738396624472574, "grad_norm": 0.8375009894371033, "learning_rate": 1.1065500162442996e-06, "loss": 0.6297698020935059, "step": 1772 }, { "epoch": 3.742616033755274, "grad_norm": 0.7627524137496948, "learning_rate": 1.1031806787474133e-06, "loss": 0.14215049147605896, "step": 1774 }, { "epoch": 3.7468354430379747, "grad_norm": 0.16473160684108734, "learning_rate": 1.0998648556295273e-06, "loss": 0.41220539808273315, "step": 1776 }, { "epoch": 3.7510548523206753, "grad_norm": 1.6988688707351685, "learning_rate": 1.0966025872480462e-06, "loss": 0.7022276520729065, "step": 1778 }, { "epoch": 3.7552742616033754, "grad_norm": 1.3168625831604004, "learning_rate": 1.0933939133085506e-06, "loss": 0.6889693737030029, "step": 1780 }, { "epoch": 3.759493670886076, "grad_norm": 1.546899437904358, "learning_rate": 1.090238872864316e-06, "loss": 0.5887824296951294, "step": 1782 }, { "epoch": 3.7637130801687766, "grad_norm": 1.0409128665924072, "learning_rate": 1.0871375043158357e-06, "loss": 0.6705577373504639, "step": 1784 }, { "epoch": 3.7679324894514767, "grad_norm": 1.1737289428710938, "learning_rate": 1.084089845410352e-06, "loss": 0.7254518270492554, "step": 1786 }, { "epoch": 3.7721518987341773, "grad_norm": 6.093574523925781, "learning_rate": 1.081095933241402e-06, "loss": 0.13085541129112244, "step": 1788 }, { "epoch": 3.7763713080168775, "grad_norm": 1.51913583278656, "learning_rate": 1.078155804248362e-06, "loss": 0.343511700630188, "step": 1790 }, { "epoch": 3.780590717299578, "grad_norm": 1.4337199926376343, "learning_rate": 1.0752694942160019e-06, "loss": 0.7373083829879761, "step": 1792 }, { "epoch": 3.7848101265822782, "grad_norm": 2.5105719566345215, "learning_rate": 1.0724370382740567e-06, "loss": 0.5225054621696472, "step": 1794 }, { "epoch": 3.789029535864979, "grad_norm": 1.3649709224700928, "learning_rate": 1.0696584708967913e-06, "loss": 0.6087401509284973, "step": 1796 }, { "epoch": 3.7932489451476794, "grad_norm": 3.092470407485962, "learning_rate": 1.0669338259025872e-06, "loss": 0.6996036171913147, "step": 1798 }, { "epoch": 3.7974683544303796, "grad_norm": 0.9999194145202637, "learning_rate": 1.0642631364535258e-06, "loss": 0.7401312589645386, "step": 1800 }, { "epoch": 3.80168776371308, "grad_norm": 1.338626503944397, "learning_rate": 1.0616464350549887e-06, "loss": 0.692215621471405, "step": 1802 }, { "epoch": 3.8059071729957807, "grad_norm": 0.8229432106018066, "learning_rate": 1.0590837535552602e-06, "loss": 0.35592326521873474, "step": 1804 }, { "epoch": 3.810126582278481, "grad_norm": 5.760233402252197, "learning_rate": 1.0565751231451391e-06, "loss": 0.08561700582504272, "step": 1806 }, { "epoch": 3.8143459915611815, "grad_norm": 3.0829389095306396, "learning_rate": 1.05412057435756e-06, "loss": 0.6724193096160889, "step": 1808 }, { "epoch": 3.818565400843882, "grad_norm": 0.8098561763763428, "learning_rate": 1.0517201370672234e-06, "loss": 0.6981774568557739, "step": 1810 }, { "epoch": 3.8227848101265822, "grad_norm": 1.4649556875228882, "learning_rate": 1.0493738404902271e-06, "loss": 0.2824139893054962, "step": 1812 }, { "epoch": 3.827004219409283, "grad_norm": 1.0864131450653076, "learning_rate": 1.0470817131837167e-06, "loss": 0.7339631915092468, "step": 1814 }, { "epoch": 3.831223628691983, "grad_norm": 1.9783216714859009, "learning_rate": 1.0448437830455336e-06, "loss": 0.7125032544136047, "step": 1816 }, { "epoch": 3.8354430379746836, "grad_norm": 2.4752309322357178, "learning_rate": 1.042660077313877e-06, "loss": 0.6021037697792053, "step": 1818 }, { "epoch": 3.8396624472573837, "grad_norm": 2.3754894733428955, "learning_rate": 1.0405306225669729e-06, "loss": 0.42927706241607666, "step": 1820 }, { "epoch": 3.8438818565400843, "grad_norm": 1.2844568490982056, "learning_rate": 1.0384554447227493e-06, "loss": 0.6535811424255371, "step": 1822 }, { "epoch": 3.848101265822785, "grad_norm": 1.143534541130066, "learning_rate": 1.0364345690385225e-06, "loss": 0.5529283881187439, "step": 1824 }, { "epoch": 3.852320675105485, "grad_norm": 1.6517040729522705, "learning_rate": 1.0344680201106878e-06, "loss": 0.6606560945510864, "step": 1826 }, { "epoch": 3.8565400843881856, "grad_norm": 1.1957817077636719, "learning_rate": 1.0325558218744205e-06, "loss": 0.6097090840339661, "step": 1828 }, { "epoch": 3.8607594936708862, "grad_norm": 0.6652842164039612, "learning_rate": 1.0306979976033873e-06, "loss": 0.6680082082748413, "step": 1830 }, { "epoch": 3.8649789029535864, "grad_norm": 1.5998671054840088, "learning_rate": 1.0288945699094583e-06, "loss": 0.08007294684648514, "step": 1832 }, { "epoch": 3.869198312236287, "grad_norm": 1.9613630771636963, "learning_rate": 1.0271455607424356e-06, "loss": 0.4352293312549591, "step": 1834 }, { "epoch": 3.8734177215189876, "grad_norm": 1.3804049491882324, "learning_rate": 1.0254509913897852e-06, "loss": 0.4666420817375183, "step": 1836 }, { "epoch": 3.8776371308016877, "grad_norm": 3.938565492630005, "learning_rate": 1.0238108824763768e-06, "loss": 0.39950013160705566, "step": 1838 }, { "epoch": 3.8818565400843883, "grad_norm": 1.9116551876068115, "learning_rate": 1.022225253964233e-06, "loss": 0.6780977249145508, "step": 1840 }, { "epoch": 3.8860759493670884, "grad_norm": 1.1439679861068726, "learning_rate": 1.0206941251522885e-06, "loss": 0.5495419502258301, "step": 1842 }, { "epoch": 3.890295358649789, "grad_norm": 0.3519618511199951, "learning_rate": 1.0192175146761524e-06, "loss": 0.4044393002986908, "step": 1844 }, { "epoch": 3.894514767932489, "grad_norm": 1.1921393871307373, "learning_rate": 1.0177954405078835e-06, "loss": 0.680756151676178, "step": 1846 }, { "epoch": 3.8987341772151898, "grad_norm": 2.43611478805542, "learning_rate": 1.0164279199557686e-06, "loss": 0.29115813970565796, "step": 1848 }, { "epoch": 3.9029535864978904, "grad_norm": 0.9541180729866028, "learning_rate": 1.0151149696641168e-06, "loss": 0.707886278629303, "step": 1850 }, { "epoch": 3.9071729957805905, "grad_norm": 1.1355844736099243, "learning_rate": 1.0138566056130515e-06, "loss": 0.704441487789154, "step": 1852 }, { "epoch": 3.911392405063291, "grad_norm": 0.9665595889091492, "learning_rate": 1.0126528431183195e-06, "loss": 0.6503458023071289, "step": 1854 }, { "epoch": 3.9156118143459917, "grad_norm": 4.960097312927246, "learning_rate": 1.0115036968311033e-06, "loss": 0.6068054437637329, "step": 1856 }, { "epoch": 3.919831223628692, "grad_norm": 1.0344171524047852, "learning_rate": 1.0104091807378438e-06, "loss": 0.6732302904129028, "step": 1858 }, { "epoch": 3.9240506329113924, "grad_norm": 1.231258511543274, "learning_rate": 1.0093693081600666e-06, "loss": 0.7045161724090576, "step": 1860 }, { "epoch": 3.928270042194093, "grad_norm": 0.8634406924247742, "learning_rate": 1.008384091754226e-06, "loss": 0.39907118678092957, "step": 1862 }, { "epoch": 3.932489451476793, "grad_norm": 1.5422383546829224, "learning_rate": 1.007453543511545e-06, "loss": 0.3921220600605011, "step": 1864 }, { "epoch": 3.9367088607594938, "grad_norm": 4.6426286697387695, "learning_rate": 1.006577674757873e-06, "loss": 0.8266934156417847, "step": 1866 }, { "epoch": 3.9409282700421944, "grad_norm": 0.939873993396759, "learning_rate": 1.0057564961535454e-06, "loss": 0.6563214659690857, "step": 1868 }, { "epoch": 3.9451476793248945, "grad_norm": 1.617569923400879, "learning_rate": 1.0049900176932567e-06, "loss": 0.41478830575942993, "step": 1870 }, { "epoch": 3.9493670886075947, "grad_norm": 2.5628774166107178, "learning_rate": 1.0042782487059369e-06, "loss": 0.35407257080078125, "step": 1872 }, { "epoch": 3.9535864978902953, "grad_norm": 3.1225600242614746, "learning_rate": 1.0036211978546373e-06, "loss": 0.18025706708431244, "step": 1874 }, { "epoch": 3.957805907172996, "grad_norm": 14.55397891998291, "learning_rate": 1.0030188731364275e-06, "loss": 0.48766762018203735, "step": 1876 }, { "epoch": 3.962025316455696, "grad_norm": 1.701096773147583, "learning_rate": 1.0024712818822967e-06, "loss": 0.5640935897827148, "step": 1878 }, { "epoch": 3.9662447257383966, "grad_norm": 1.1950315237045288, "learning_rate": 1.001978430757064e-06, "loss": 0.39117005467414856, "step": 1880 }, { "epoch": 3.970464135021097, "grad_norm": 1.0402491092681885, "learning_rate": 1.0015403257592978e-06, "loss": 0.6083173751831055, "step": 1882 }, { "epoch": 3.9746835443037973, "grad_norm": 1.166829228401184, "learning_rate": 1.0011569722212425e-06, "loss": 0.11440423876047134, "step": 1884 }, { "epoch": 3.978902953586498, "grad_norm": 2.3907763957977295, "learning_rate": 1.000828374808755e-06, "loss": 0.6026467084884644, "step": 1886 }, { "epoch": 3.9831223628691985, "grad_norm": 1.612939476966858, "learning_rate": 1.000554537521245e-06, "loss": 0.47693824768066406, "step": 1888 }, { "epoch": 3.9873417721518987, "grad_norm": 2.3837125301361084, "learning_rate": 1.0003354636916303e-06, "loss": 0.6994826793670654, "step": 1890 }, { "epoch": 3.9915611814345993, "grad_norm": 1.6159396171569824, "learning_rate": 1.0001711559862924e-06, "loss": 0.36422663927078247, "step": 1892 }, { "epoch": 3.9957805907173, "grad_norm": 2.879718065261841, "learning_rate": 1.0000616164050463e-06, "loss": 0.6771517395973206, "step": 1894 }, { "epoch": 4.0, "grad_norm": 1.0333420038223267, "learning_rate": 1.0000068462811152e-06, "loss": 0.5582597851753235, "step": 1896 }, { "epoch": 4.0, "step": 1896, "total_flos": 3.5948540672197263e+18, "train_loss": 0.8186590513253765, "train_runtime": 9356.5778, "train_samples_per_second": 6.079, "train_steps_per_second": 0.203 } ], "logging_steps": 2, "max_steps": 1896, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 99999, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.5948540672197263e+18, "train_batch_size": 3, "trial_name": null, "trial_params": null }