{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.994876571960876, "eval_steps": 500, "global_step": 6438, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004657661853749418, "grad_norm": 2.3019327809756027, "learning_rate": 3.8819875776397516e-07, "loss": 0.8392, "step": 5 }, { "epoch": 0.009315323707498836, "grad_norm": 2.213377640018512, "learning_rate": 7.763975155279503e-07, "loss": 0.8345, "step": 10 }, { "epoch": 0.013972985561248253, "grad_norm": 1.938448121700729, "learning_rate": 1.1645962732919254e-06, "loss": 0.8232, "step": 15 }, { "epoch": 0.018630647414997672, "grad_norm": 1.4174158770374174, "learning_rate": 1.5527950310559006e-06, "loss": 0.8181, "step": 20 }, { "epoch": 0.02328830926874709, "grad_norm": 1.2985051245036479, "learning_rate": 1.940993788819876e-06, "loss": 0.7929, "step": 25 }, { "epoch": 0.027945971122496506, "grad_norm": 0.7411315693283763, "learning_rate": 2.329192546583851e-06, "loss": 0.7857, "step": 30 }, { "epoch": 0.032603632976245925, "grad_norm": 0.6956299736096847, "learning_rate": 2.7173913043478263e-06, "loss": 0.77, "step": 35 }, { "epoch": 0.037261294829995344, "grad_norm": 0.5087907626429498, "learning_rate": 3.1055900621118013e-06, "loss": 0.7555, "step": 40 }, { "epoch": 0.04191895668374476, "grad_norm": 0.5162321192122032, "learning_rate": 3.4937888198757763e-06, "loss": 0.7084, "step": 45 }, { "epoch": 0.04657661853749418, "grad_norm": 0.5210165292785406, "learning_rate": 3.881987577639752e-06, "loss": 0.7105, "step": 50 }, { "epoch": 0.05123428039124359, "grad_norm": 0.3681578442807255, "learning_rate": 4.270186335403727e-06, "loss": 0.6925, "step": 55 }, { "epoch": 0.05589194224499301, "grad_norm": 0.3493851793168087, "learning_rate": 4.658385093167702e-06, "loss": 0.6864, "step": 60 }, { "epoch": 0.06054960409874243, "grad_norm": 0.33352129992367174, "learning_rate": 5.046583850931677e-06, "loss": 0.6761, "step": 65 }, { "epoch": 0.06520726595249185, "grad_norm": 0.3133310695756018, "learning_rate": 5.4347826086956525e-06, "loss": 0.6499, "step": 70 }, { "epoch": 0.06986492780624126, "grad_norm": 0.30368569873447704, "learning_rate": 5.8229813664596275e-06, "loss": 0.6506, "step": 75 }, { "epoch": 0.07452258965999069, "grad_norm": 0.3578590618471248, "learning_rate": 6.2111801242236025e-06, "loss": 0.6638, "step": 80 }, { "epoch": 0.0791802515137401, "grad_norm": 0.2975725510627923, "learning_rate": 6.5993788819875775e-06, "loss": 0.6367, "step": 85 }, { "epoch": 0.08383791336748952, "grad_norm": 0.3276714508421403, "learning_rate": 6.9875776397515525e-06, "loss": 0.6428, "step": 90 }, { "epoch": 0.08849557522123894, "grad_norm": 0.31592187428483076, "learning_rate": 7.375776397515528e-06, "loss": 0.6501, "step": 95 }, { "epoch": 0.09315323707498836, "grad_norm": 0.33605781865180967, "learning_rate": 7.763975155279503e-06, "loss": 0.6365, "step": 100 }, { "epoch": 0.09781089892873777, "grad_norm": 0.3123669418062645, "learning_rate": 8.15217391304348e-06, "loss": 0.6411, "step": 105 }, { "epoch": 0.10246856078248719, "grad_norm": 0.3182910388435519, "learning_rate": 8.540372670807453e-06, "loss": 0.625, "step": 110 }, { "epoch": 0.10712622263623661, "grad_norm": 0.30730998581150065, "learning_rate": 8.92857142857143e-06, "loss": 0.6246, "step": 115 }, { "epoch": 0.11178388448998602, "grad_norm": 0.32097965731601447, "learning_rate": 9.316770186335403e-06, "loss": 0.6375, "step": 120 }, { "epoch": 0.11644154634373545, "grad_norm": 0.3252410734808718, "learning_rate": 9.70496894409938e-06, "loss": 0.6119, "step": 125 }, { "epoch": 0.12109920819748486, "grad_norm": 0.32133167619890884, "learning_rate": 1.0093167701863353e-05, "loss": 0.6157, "step": 130 }, { "epoch": 0.1257568700512343, "grad_norm": 0.3527562637095088, "learning_rate": 1.048136645962733e-05, "loss": 0.6239, "step": 135 }, { "epoch": 0.1304145319049837, "grad_norm": 0.34538857270658335, "learning_rate": 1.0869565217391305e-05, "loss": 0.6153, "step": 140 }, { "epoch": 0.1350721937587331, "grad_norm": 0.35520393785158333, "learning_rate": 1.1257763975155281e-05, "loss": 0.6276, "step": 145 }, { "epoch": 0.13972985561248252, "grad_norm": 0.32779931366160103, "learning_rate": 1.1645962732919255e-05, "loss": 0.6189, "step": 150 }, { "epoch": 0.14438751746623196, "grad_norm": 0.3506567531998013, "learning_rate": 1.2034161490683231e-05, "loss": 0.5974, "step": 155 }, { "epoch": 0.14904517931998137, "grad_norm": 0.44095887699322106, "learning_rate": 1.2422360248447205e-05, "loss": 0.605, "step": 160 }, { "epoch": 0.1537028411737308, "grad_norm": 0.34515748430777565, "learning_rate": 1.2810559006211181e-05, "loss": 0.6063, "step": 165 }, { "epoch": 0.1583605030274802, "grad_norm": 0.3703511121105675, "learning_rate": 1.3198757763975155e-05, "loss": 0.6034, "step": 170 }, { "epoch": 0.1630181648812296, "grad_norm": 0.3801541735761265, "learning_rate": 1.3586956521739131e-05, "loss": 0.6162, "step": 175 }, { "epoch": 0.16767582673497905, "grad_norm": 0.38335348125990687, "learning_rate": 1.3975155279503105e-05, "loss": 0.6094, "step": 180 }, { "epoch": 0.17233348858872846, "grad_norm": 0.33889480785461495, "learning_rate": 1.4363354037267083e-05, "loss": 0.6063, "step": 185 }, { "epoch": 0.17699115044247787, "grad_norm": 0.34026964020284706, "learning_rate": 1.4751552795031057e-05, "loss": 0.5997, "step": 190 }, { "epoch": 0.18164881229622729, "grad_norm": 0.38360615235771023, "learning_rate": 1.5139751552795031e-05, "loss": 0.6054, "step": 195 }, { "epoch": 0.18630647414997673, "grad_norm": 0.3673594707968111, "learning_rate": 1.5527950310559007e-05, "loss": 0.5736, "step": 200 }, { "epoch": 0.19096413600372614, "grad_norm": 0.4215764775548937, "learning_rate": 1.5916149068322984e-05, "loss": 0.5991, "step": 205 }, { "epoch": 0.19562179785747555, "grad_norm": 0.35716858104216526, "learning_rate": 1.630434782608696e-05, "loss": 0.5873, "step": 210 }, { "epoch": 0.20027945971122496, "grad_norm": 0.39376705863848954, "learning_rate": 1.6692546583850933e-05, "loss": 0.5994, "step": 215 }, { "epoch": 0.20493712156497437, "grad_norm": 0.3462654305819616, "learning_rate": 1.7080745341614907e-05, "loss": 0.5933, "step": 220 }, { "epoch": 0.2095947834187238, "grad_norm": 0.3573326879725803, "learning_rate": 1.7468944099378884e-05, "loss": 0.5969, "step": 225 }, { "epoch": 0.21425244527247322, "grad_norm": 0.363187653666975, "learning_rate": 1.785714285714286e-05, "loss": 0.5946, "step": 230 }, { "epoch": 0.21891010712622264, "grad_norm": 0.35619313386667184, "learning_rate": 1.8245341614906833e-05, "loss": 0.5887, "step": 235 }, { "epoch": 0.22356776897997205, "grad_norm": 0.41620107457751127, "learning_rate": 1.8633540372670807e-05, "loss": 0.5876, "step": 240 }, { "epoch": 0.22822543083372146, "grad_norm": 0.3259480454084811, "learning_rate": 1.9021739130434784e-05, "loss": 0.5753, "step": 245 }, { "epoch": 0.2328830926874709, "grad_norm": 0.3538447269557447, "learning_rate": 1.940993788819876e-05, "loss": 0.572, "step": 250 }, { "epoch": 0.2375407545412203, "grad_norm": 0.3552600320695115, "learning_rate": 1.9798136645962733e-05, "loss": 0.5845, "step": 255 }, { "epoch": 0.24219841639496972, "grad_norm": 0.3744422077805896, "learning_rate": 2.0186335403726707e-05, "loss": 0.5903, "step": 260 }, { "epoch": 0.24685607824871914, "grad_norm": 0.3834654650083814, "learning_rate": 2.0574534161490684e-05, "loss": 0.5816, "step": 265 }, { "epoch": 0.2515137401024686, "grad_norm": 0.372590583801973, "learning_rate": 2.096273291925466e-05, "loss": 0.5689, "step": 270 }, { "epoch": 0.25617140195621796, "grad_norm": 0.4034248924667653, "learning_rate": 2.1350931677018636e-05, "loss": 0.5888, "step": 275 }, { "epoch": 0.2608290638099674, "grad_norm": 0.3840702221152365, "learning_rate": 2.173913043478261e-05, "loss": 0.5756, "step": 280 }, { "epoch": 0.26548672566371684, "grad_norm": 0.3998609430141785, "learning_rate": 2.2127329192546584e-05, "loss": 0.5727, "step": 285 }, { "epoch": 0.2701443875174662, "grad_norm": 0.3747341118173786, "learning_rate": 2.2515527950310562e-05, "loss": 0.5709, "step": 290 }, { "epoch": 0.27480204937121566, "grad_norm": 0.36453338746878033, "learning_rate": 2.2903726708074536e-05, "loss": 0.5634, "step": 295 }, { "epoch": 0.27945971122496505, "grad_norm": 0.3924429598865349, "learning_rate": 2.329192546583851e-05, "loss": 0.5758, "step": 300 }, { "epoch": 0.2841173730787145, "grad_norm": 0.3988718061633333, "learning_rate": 2.3680124223602484e-05, "loss": 0.5842, "step": 305 }, { "epoch": 0.2887750349324639, "grad_norm": 0.3447171086328858, "learning_rate": 2.4068322981366462e-05, "loss": 0.5786, "step": 310 }, { "epoch": 0.2934326967862133, "grad_norm": 0.4213428981911342, "learning_rate": 2.4456521739130436e-05, "loss": 0.5652, "step": 315 }, { "epoch": 0.29809035863996275, "grad_norm": 0.4108509535575422, "learning_rate": 2.484472049689441e-05, "loss": 0.575, "step": 320 }, { "epoch": 0.30274802049371213, "grad_norm": 0.3817928360474198, "learning_rate": 2.5232919254658388e-05, "loss": 0.5774, "step": 325 }, { "epoch": 0.3074056823474616, "grad_norm": 0.3968947295283744, "learning_rate": 2.5621118012422362e-05, "loss": 0.5759, "step": 330 }, { "epoch": 0.312063344201211, "grad_norm": 0.390007886083059, "learning_rate": 2.6009316770186336e-05, "loss": 0.5559, "step": 335 }, { "epoch": 0.3167210060549604, "grad_norm": 0.40698973096999513, "learning_rate": 2.639751552795031e-05, "loss": 0.5715, "step": 340 }, { "epoch": 0.32137866790870984, "grad_norm": 0.42006314669230893, "learning_rate": 2.6785714285714288e-05, "loss": 0.5589, "step": 345 }, { "epoch": 0.3260363297624592, "grad_norm": 0.40917182872900076, "learning_rate": 2.7173913043478262e-05, "loss": 0.5624, "step": 350 }, { "epoch": 0.33069399161620866, "grad_norm": 0.4353608052419867, "learning_rate": 2.7562111801242236e-05, "loss": 0.5585, "step": 355 }, { "epoch": 0.3353516534699581, "grad_norm": 0.35259436320364285, "learning_rate": 2.795031055900621e-05, "loss": 0.5702, "step": 360 }, { "epoch": 0.3400093153237075, "grad_norm": 0.3786466745629636, "learning_rate": 2.833850931677019e-05, "loss": 0.5698, "step": 365 }, { "epoch": 0.3446669771774569, "grad_norm": 0.4302871538538141, "learning_rate": 2.8726708074534165e-05, "loss": 0.581, "step": 370 }, { "epoch": 0.3493246390312063, "grad_norm": 0.4281769198833719, "learning_rate": 2.911490683229814e-05, "loss": 0.5736, "step": 375 }, { "epoch": 0.35398230088495575, "grad_norm": 0.4286640932651176, "learning_rate": 2.9503105590062114e-05, "loss": 0.5589, "step": 380 }, { "epoch": 0.3586399627387052, "grad_norm": 0.3472119563345766, "learning_rate": 2.9891304347826088e-05, "loss": 0.5519, "step": 385 }, { "epoch": 0.36329762459245457, "grad_norm": 0.43689086462268834, "learning_rate": 3.0279503105590062e-05, "loss": 0.559, "step": 390 }, { "epoch": 0.367955286446204, "grad_norm": 0.3561411341022254, "learning_rate": 3.066770186335404e-05, "loss": 0.5514, "step": 395 }, { "epoch": 0.37261294829995345, "grad_norm": 0.4098863517432012, "learning_rate": 3.1055900621118014e-05, "loss": 0.5482, "step": 400 }, { "epoch": 0.37727061015370283, "grad_norm": 0.40087866654617516, "learning_rate": 3.1444099378881995e-05, "loss": 0.5528, "step": 405 }, { "epoch": 0.3819282720074523, "grad_norm": 0.4193289443930705, "learning_rate": 3.183229813664597e-05, "loss": 0.5593, "step": 410 }, { "epoch": 0.38658593386120166, "grad_norm": 0.4098712703222279, "learning_rate": 3.222049689440994e-05, "loss": 0.5598, "step": 415 }, { "epoch": 0.3912435957149511, "grad_norm": 0.354010365263074, "learning_rate": 3.260869565217392e-05, "loss": 0.5473, "step": 420 }, { "epoch": 0.39590125756870054, "grad_norm": 0.3938475208870259, "learning_rate": 3.299689440993789e-05, "loss": 0.5664, "step": 425 }, { "epoch": 0.4005589194224499, "grad_norm": 0.4450748659361935, "learning_rate": 3.3385093167701865e-05, "loss": 0.5593, "step": 430 }, { "epoch": 0.40521658127619936, "grad_norm": 0.4369412101411175, "learning_rate": 3.377329192546584e-05, "loss": 0.5613, "step": 435 }, { "epoch": 0.40987424312994875, "grad_norm": 0.4321131945940359, "learning_rate": 3.4161490683229814e-05, "loss": 0.5732, "step": 440 }, { "epoch": 0.4145319049836982, "grad_norm": 0.38384248969287893, "learning_rate": 3.4549689440993795e-05, "loss": 0.5461, "step": 445 }, { "epoch": 0.4191895668374476, "grad_norm": 0.4088211173201318, "learning_rate": 3.493788819875777e-05, "loss": 0.5511, "step": 450 }, { "epoch": 0.423847228691197, "grad_norm": 0.46046590946956345, "learning_rate": 3.532608695652174e-05, "loss": 0.5724, "step": 455 }, { "epoch": 0.42850489054494645, "grad_norm": 0.3814425183208477, "learning_rate": 3.571428571428572e-05, "loss": 0.5505, "step": 460 }, { "epoch": 0.43316255239869583, "grad_norm": 0.43769887054072637, "learning_rate": 3.610248447204969e-05, "loss": 0.5608, "step": 465 }, { "epoch": 0.43782021425244527, "grad_norm": 0.38209982946067284, "learning_rate": 3.6490683229813665e-05, "loss": 0.5516, "step": 470 }, { "epoch": 0.4424778761061947, "grad_norm": 0.40982299061690375, "learning_rate": 3.687888198757764e-05, "loss": 0.5619, "step": 475 }, { "epoch": 0.4471355379599441, "grad_norm": 0.390466195989608, "learning_rate": 3.7267080745341614e-05, "loss": 0.5458, "step": 480 }, { "epoch": 0.45179319981369354, "grad_norm": 0.44259240049879167, "learning_rate": 3.765527950310559e-05, "loss": 0.5491, "step": 485 }, { "epoch": 0.4564508616674429, "grad_norm": 0.4310248778920179, "learning_rate": 3.804347826086957e-05, "loss": 0.5542, "step": 490 }, { "epoch": 0.46110852352119236, "grad_norm": 0.4125289896821679, "learning_rate": 3.843167701863354e-05, "loss": 0.5439, "step": 495 }, { "epoch": 0.4657661853749418, "grad_norm": 0.4293338177041983, "learning_rate": 3.881987577639752e-05, "loss": 0.5525, "step": 500 }, { "epoch": 0.4704238472286912, "grad_norm": 0.3674703165767253, "learning_rate": 3.920807453416149e-05, "loss": 0.5452, "step": 505 }, { "epoch": 0.4750815090824406, "grad_norm": 0.449390613703762, "learning_rate": 3.9596273291925465e-05, "loss": 0.5412, "step": 510 }, { "epoch": 0.47973917093619, "grad_norm": 0.4217736031082808, "learning_rate": 3.998447204968944e-05, "loss": 0.5549, "step": 515 }, { "epoch": 0.48439683278993945, "grad_norm": 0.4754511610880146, "learning_rate": 4.0372670807453414e-05, "loss": 0.5497, "step": 520 }, { "epoch": 0.4890544946436889, "grad_norm": 0.4367161255822699, "learning_rate": 4.076086956521739e-05, "loss": 0.5615, "step": 525 }, { "epoch": 0.49371215649743827, "grad_norm": 0.4811669231980709, "learning_rate": 4.114906832298137e-05, "loss": 0.5446, "step": 530 }, { "epoch": 0.4983698183511877, "grad_norm": 0.4810252906811935, "learning_rate": 4.153726708074534e-05, "loss": 0.5511, "step": 535 }, { "epoch": 0.5030274802049371, "grad_norm": 0.4066794680716447, "learning_rate": 4.192546583850932e-05, "loss": 0.5551, "step": 540 }, { "epoch": 0.5076851420586865, "grad_norm": 0.402782406511805, "learning_rate": 4.23136645962733e-05, "loss": 0.5432, "step": 545 }, { "epoch": 0.5123428039124359, "grad_norm": 0.4568647474773819, "learning_rate": 4.270186335403727e-05, "loss": 0.5606, "step": 550 }, { "epoch": 0.5170004657661854, "grad_norm": 0.4766904626572621, "learning_rate": 4.3090062111801246e-05, "loss": 0.5466, "step": 555 }, { "epoch": 0.5216581276199348, "grad_norm": 0.41489132116700206, "learning_rate": 4.347826086956522e-05, "loss": 0.5519, "step": 560 }, { "epoch": 0.5263157894736842, "grad_norm": 0.5015387935295137, "learning_rate": 4.3866459627329195e-05, "loss": 0.5495, "step": 565 }, { "epoch": 0.5309734513274337, "grad_norm": 0.4117235113215161, "learning_rate": 4.425465838509317e-05, "loss": 0.5488, "step": 570 }, { "epoch": 0.5356311131811831, "grad_norm": 0.3609129750510567, "learning_rate": 4.464285714285715e-05, "loss": 0.5453, "step": 575 }, { "epoch": 0.5402887750349324, "grad_norm": 0.3831882369717561, "learning_rate": 4.5031055900621124e-05, "loss": 0.5456, "step": 580 }, { "epoch": 0.5449464368886818, "grad_norm": 0.37316337627447, "learning_rate": 4.54192546583851e-05, "loss": 0.5404, "step": 585 }, { "epoch": 0.5496040987424313, "grad_norm": 0.3706323022342129, "learning_rate": 4.580745341614907e-05, "loss": 0.5597, "step": 590 }, { "epoch": 0.5542617605961807, "grad_norm": 0.35957671806000513, "learning_rate": 4.6195652173913046e-05, "loss": 0.5488, "step": 595 }, { "epoch": 0.5589194224499301, "grad_norm": 0.3803703659322469, "learning_rate": 4.658385093167702e-05, "loss": 0.5554, "step": 600 }, { "epoch": 0.5635770843036796, "grad_norm": 0.37256551042988023, "learning_rate": 4.6972049689440995e-05, "loss": 0.5253, "step": 605 }, { "epoch": 0.568234746157429, "grad_norm": 0.4221546520996378, "learning_rate": 4.736024844720497e-05, "loss": 0.5479, "step": 610 }, { "epoch": 0.5728924080111784, "grad_norm": 0.39067305639094996, "learning_rate": 4.774844720496895e-05, "loss": 0.5389, "step": 615 }, { "epoch": 0.5775500698649279, "grad_norm": 0.4063023455045797, "learning_rate": 4.8136645962732924e-05, "loss": 0.5423, "step": 620 }, { "epoch": 0.5822077317186772, "grad_norm": 0.41472334204512, "learning_rate": 4.85248447204969e-05, "loss": 0.5544, "step": 625 }, { "epoch": 0.5868653935724266, "grad_norm": 0.39565462429940207, "learning_rate": 4.891304347826087e-05, "loss": 0.5387, "step": 630 }, { "epoch": 0.5915230554261761, "grad_norm": 0.3644199440011395, "learning_rate": 4.9301242236024846e-05, "loss": 0.5379, "step": 635 }, { "epoch": 0.5961807172799255, "grad_norm": 0.40249401565839343, "learning_rate": 4.968944099378882e-05, "loss": 0.5447, "step": 640 }, { "epoch": 0.6008383791336749, "grad_norm": 0.5010546666411587, "learning_rate": 4.999137038315499e-05, "loss": 0.5456, "step": 645 }, { "epoch": 0.6054960409874243, "grad_norm": 0.41555835770423566, "learning_rate": 4.994822229892993e-05, "loss": 0.5409, "step": 650 }, { "epoch": 0.6101537028411738, "grad_norm": 0.4542471038040309, "learning_rate": 4.9905074214704875e-05, "loss": 0.5473, "step": 655 }, { "epoch": 0.6148113646949231, "grad_norm": 0.3920053153066082, "learning_rate": 4.986192613047981e-05, "loss": 0.5501, "step": 660 }, { "epoch": 0.6194690265486725, "grad_norm": 0.3777008933946134, "learning_rate": 4.9818778046254746e-05, "loss": 0.5435, "step": 665 }, { "epoch": 0.624126688402422, "grad_norm": 0.43378127221557466, "learning_rate": 4.977562996202969e-05, "loss": 0.5467, "step": 670 }, { "epoch": 0.6287843502561714, "grad_norm": 0.3659136139237235, "learning_rate": 4.9732481877804624e-05, "loss": 0.5356, "step": 675 }, { "epoch": 0.6334420121099208, "grad_norm": 0.3649255574178679, "learning_rate": 4.968933379357957e-05, "loss": 0.5405, "step": 680 }, { "epoch": 0.6380996739636703, "grad_norm": 0.40414131536865466, "learning_rate": 4.964618570935451e-05, "loss": 0.5547, "step": 685 }, { "epoch": 0.6427573358174197, "grad_norm": 0.4080493697071801, "learning_rate": 4.9603037625129445e-05, "loss": 0.5414, "step": 690 }, { "epoch": 0.6474149976711691, "grad_norm": 0.3279309802425546, "learning_rate": 4.955988954090439e-05, "loss": 0.5411, "step": 695 }, { "epoch": 0.6520726595249184, "grad_norm": 0.39432782457184934, "learning_rate": 4.951674145667933e-05, "loss": 0.5375, "step": 700 }, { "epoch": 0.6567303213786679, "grad_norm": 0.3793684730030065, "learning_rate": 4.9473593372454266e-05, "loss": 0.5337, "step": 705 }, { "epoch": 0.6613879832324173, "grad_norm": 0.40364573399461023, "learning_rate": 4.94304452882292e-05, "loss": 0.5467, "step": 710 }, { "epoch": 0.6660456450861667, "grad_norm": 0.4278045269782971, "learning_rate": 4.9387297204004144e-05, "loss": 0.541, "step": 715 }, { "epoch": 0.6707033069399162, "grad_norm": 0.37917807432493683, "learning_rate": 4.934414911977908e-05, "loss": 0.5295, "step": 720 }, { "epoch": 0.6753609687936656, "grad_norm": 0.3517382924406672, "learning_rate": 4.930100103555402e-05, "loss": 0.5345, "step": 725 }, { "epoch": 0.680018630647415, "grad_norm": 0.3691724849836069, "learning_rate": 4.9257852951328965e-05, "loss": 0.5433, "step": 730 }, { "epoch": 0.6846762925011645, "grad_norm": 0.3774463553551797, "learning_rate": 4.921470486710391e-05, "loss": 0.5303, "step": 735 }, { "epoch": 0.6893339543549138, "grad_norm": 0.3444405228975367, "learning_rate": 4.917155678287884e-05, "loss": 0.5372, "step": 740 }, { "epoch": 0.6939916162086632, "grad_norm": 0.409850694989795, "learning_rate": 4.9128408698653785e-05, "loss": 0.5327, "step": 745 }, { "epoch": 0.6986492780624126, "grad_norm": 0.38403187408188155, "learning_rate": 4.908526061442872e-05, "loss": 0.5366, "step": 750 }, { "epoch": 0.7033069399161621, "grad_norm": 0.35649232222227883, "learning_rate": 4.904211253020366e-05, "loss": 0.5257, "step": 755 }, { "epoch": 0.7079646017699115, "grad_norm": 0.30980653360294913, "learning_rate": 4.89989644459786e-05, "loss": 0.5282, "step": 760 }, { "epoch": 0.7126222636236609, "grad_norm": 0.34011715176249335, "learning_rate": 4.895581636175354e-05, "loss": 0.54, "step": 765 }, { "epoch": 0.7172799254774104, "grad_norm": 0.4233695677463251, "learning_rate": 4.891266827752848e-05, "loss": 0.5387, "step": 770 }, { "epoch": 0.7219375873311598, "grad_norm": 0.4140086288437692, "learning_rate": 4.886952019330342e-05, "loss": 0.525, "step": 775 }, { "epoch": 0.7265952491849091, "grad_norm": 0.34068328418934496, "learning_rate": 4.882637210907836e-05, "loss": 0.5439, "step": 780 }, { "epoch": 0.7312529110386586, "grad_norm": 0.3240612426420949, "learning_rate": 4.87832240248533e-05, "loss": 0.5369, "step": 785 }, { "epoch": 0.735910572892408, "grad_norm": 0.3917193996260291, "learning_rate": 4.874007594062824e-05, "loss": 0.5279, "step": 790 }, { "epoch": 0.7405682347461574, "grad_norm": 0.36031341636954306, "learning_rate": 4.8696927856403176e-05, "loss": 0.5349, "step": 795 }, { "epoch": 0.7452258965999069, "grad_norm": 0.3215250598752723, "learning_rate": 4.865377977217811e-05, "loss": 0.5309, "step": 800 }, { "epoch": 0.7498835584536563, "grad_norm": 0.3635147064054966, "learning_rate": 4.8610631687953055e-05, "loss": 0.5478, "step": 805 }, { "epoch": 0.7545412203074057, "grad_norm": 0.35052754976371886, "learning_rate": 4.8567483603728e-05, "loss": 0.5304, "step": 810 }, { "epoch": 0.759198882161155, "grad_norm": 0.34643395359554885, "learning_rate": 4.852433551950293e-05, "loss": 0.5342, "step": 815 }, { "epoch": 0.7638565440149045, "grad_norm": 0.30085265220400775, "learning_rate": 4.8481187435277875e-05, "loss": 0.5341, "step": 820 }, { "epoch": 0.7685142058686539, "grad_norm": 0.34285432131613336, "learning_rate": 4.843803935105282e-05, "loss": 0.5194, "step": 825 }, { "epoch": 0.7731718677224033, "grad_norm": 0.3508942566369898, "learning_rate": 4.839489126682776e-05, "loss": 0.5285, "step": 830 }, { "epoch": 0.7778295295761528, "grad_norm": 0.3478656279332421, "learning_rate": 4.8351743182602696e-05, "loss": 0.5363, "step": 835 }, { "epoch": 0.7824871914299022, "grad_norm": 0.38291627498228514, "learning_rate": 4.830859509837763e-05, "loss": 0.5196, "step": 840 }, { "epoch": 0.7871448532836516, "grad_norm": 0.3222374661978585, "learning_rate": 4.8265447014152574e-05, "loss": 0.5265, "step": 845 }, { "epoch": 0.7918025151374011, "grad_norm": 0.35627225208143615, "learning_rate": 4.822229892992751e-05, "loss": 0.529, "step": 850 }, { "epoch": 0.7964601769911505, "grad_norm": 0.3279912697315041, "learning_rate": 4.817915084570245e-05, "loss": 0.5186, "step": 855 }, { "epoch": 0.8011178388448998, "grad_norm": 0.30956440224112497, "learning_rate": 4.8136002761477395e-05, "loss": 0.5236, "step": 860 }, { "epoch": 0.8057755006986492, "grad_norm": 0.336307530077032, "learning_rate": 4.809285467725233e-05, "loss": 0.5254, "step": 865 }, { "epoch": 0.8104331625523987, "grad_norm": 0.33254883757445347, "learning_rate": 4.804970659302727e-05, "loss": 0.518, "step": 870 }, { "epoch": 0.8150908244061481, "grad_norm": 0.377527821349766, "learning_rate": 4.8006558508802216e-05, "loss": 0.5319, "step": 875 }, { "epoch": 0.8197484862598975, "grad_norm": 0.30166412860585307, "learning_rate": 4.796341042457715e-05, "loss": 0.5107, "step": 880 }, { "epoch": 0.824406148113647, "grad_norm": 0.34941996287915006, "learning_rate": 4.792026234035209e-05, "loss": 0.5311, "step": 885 }, { "epoch": 0.8290638099673964, "grad_norm": 0.3372371522822523, "learning_rate": 4.787711425612703e-05, "loss": 0.5289, "step": 890 }, { "epoch": 0.8337214718211458, "grad_norm": 0.27848184163657946, "learning_rate": 4.7833966171901966e-05, "loss": 0.5293, "step": 895 }, { "epoch": 0.8383791336748952, "grad_norm": 0.29098378273358105, "learning_rate": 4.779081808767691e-05, "loss": 0.5227, "step": 900 }, { "epoch": 0.8430367955286446, "grad_norm": 0.32419352391747996, "learning_rate": 4.774767000345185e-05, "loss": 0.5271, "step": 905 }, { "epoch": 0.847694457382394, "grad_norm": 0.29545635962331085, "learning_rate": 4.770452191922679e-05, "loss": 0.535, "step": 910 }, { "epoch": 0.8523521192361434, "grad_norm": 0.3466450476582371, "learning_rate": 4.766137383500173e-05, "loss": 0.5235, "step": 915 }, { "epoch": 0.8570097810898929, "grad_norm": 0.33112434590899054, "learning_rate": 4.761822575077667e-05, "loss": 0.5335, "step": 920 }, { "epoch": 0.8616674429436423, "grad_norm": 0.32926898274319316, "learning_rate": 4.757507766655161e-05, "loss": 0.5262, "step": 925 }, { "epoch": 0.8663251047973917, "grad_norm": 0.30701888433235225, "learning_rate": 4.753192958232654e-05, "loss": 0.5286, "step": 930 }, { "epoch": 0.8709827666511412, "grad_norm": 0.2887728728137387, "learning_rate": 4.7488781498101485e-05, "loss": 0.5139, "step": 935 }, { "epoch": 0.8756404285048905, "grad_norm": 0.2863916983613684, "learning_rate": 4.744563341387643e-05, "loss": 0.5122, "step": 940 }, { "epoch": 0.8802980903586399, "grad_norm": 0.3202090595337484, "learning_rate": 4.7402485329651363e-05, "loss": 0.5189, "step": 945 }, { "epoch": 0.8849557522123894, "grad_norm": 0.3104151086222973, "learning_rate": 4.7359337245426306e-05, "loss": 0.5058, "step": 950 }, { "epoch": 0.8896134140661388, "grad_norm": 0.2775313905979402, "learning_rate": 4.731618916120125e-05, "loss": 0.5222, "step": 955 }, { "epoch": 0.8942710759198882, "grad_norm": 0.3164082262603208, "learning_rate": 4.7273041076976184e-05, "loss": 0.5285, "step": 960 }, { "epoch": 0.8989287377736377, "grad_norm": 0.32179226815996614, "learning_rate": 4.722989299275113e-05, "loss": 0.522, "step": 965 }, { "epoch": 0.9035863996273871, "grad_norm": 0.33249905859473566, "learning_rate": 4.718674490852606e-05, "loss": 0.5255, "step": 970 }, { "epoch": 0.9082440614811365, "grad_norm": 0.3278910699357039, "learning_rate": 4.7143596824301e-05, "loss": 0.5196, "step": 975 }, { "epoch": 0.9129017233348858, "grad_norm": 0.32734834503767285, "learning_rate": 4.710044874007594e-05, "loss": 0.5224, "step": 980 }, { "epoch": 0.9175593851886353, "grad_norm": 0.31685076836771814, "learning_rate": 4.705730065585088e-05, "loss": 0.5281, "step": 985 }, { "epoch": 0.9222170470423847, "grad_norm": 0.31015842507995484, "learning_rate": 4.7014152571625826e-05, "loss": 0.4956, "step": 990 }, { "epoch": 0.9268747088961341, "grad_norm": 0.31456008669522556, "learning_rate": 4.697100448740076e-05, "loss": 0.5138, "step": 995 }, { "epoch": 0.9315323707498836, "grad_norm": 0.32558826075647235, "learning_rate": 4.6927856403175704e-05, "loss": 0.5178, "step": 1000 }, { "epoch": 0.936190032603633, "grad_norm": 0.3200916523159601, "learning_rate": 4.6884708318950646e-05, "loss": 0.5289, "step": 1005 }, { "epoch": 0.9408476944573824, "grad_norm": 0.3238116143973664, "learning_rate": 4.684156023472558e-05, "loss": 0.5158, "step": 1010 }, { "epoch": 0.9455053563111319, "grad_norm": 0.3040347022225117, "learning_rate": 4.679841215050052e-05, "loss": 0.5185, "step": 1015 }, { "epoch": 0.9501630181648812, "grad_norm": 0.29781029866309666, "learning_rate": 4.675526406627546e-05, "loss": 0.5281, "step": 1020 }, { "epoch": 0.9548206800186306, "grad_norm": 0.3747848744327474, "learning_rate": 4.6712115982050396e-05, "loss": 0.5187, "step": 1025 }, { "epoch": 0.95947834187238, "grad_norm": 0.3239749753313598, "learning_rate": 4.666896789782534e-05, "loss": 0.5096, "step": 1030 }, { "epoch": 0.9641360037261295, "grad_norm": 0.29492771555109554, "learning_rate": 4.662581981360028e-05, "loss": 0.5137, "step": 1035 }, { "epoch": 0.9687936655798789, "grad_norm": 0.38614613600395553, "learning_rate": 4.658267172937522e-05, "loss": 0.5114, "step": 1040 }, { "epoch": 0.9734513274336283, "grad_norm": 0.3049069360151345, "learning_rate": 4.653952364515016e-05, "loss": 0.5138, "step": 1045 }, { "epoch": 0.9781089892873778, "grad_norm": 0.27262230431147544, "learning_rate": 4.64963755609251e-05, "loss": 0.5127, "step": 1050 }, { "epoch": 0.9827666511411272, "grad_norm": 0.304788030747315, "learning_rate": 4.645322747670004e-05, "loss": 0.5152, "step": 1055 }, { "epoch": 0.9874243129948765, "grad_norm": 0.2915164782447978, "learning_rate": 4.641007939247497e-05, "loss": 0.518, "step": 1060 }, { "epoch": 0.992081974848626, "grad_norm": 0.3042077493609863, "learning_rate": 4.6366931308249916e-05, "loss": 0.5159, "step": 1065 }, { "epoch": 0.9967396367023754, "grad_norm": 0.30993274643234153, "learning_rate": 4.632378322402486e-05, "loss": 0.5057, "step": 1070 }, { "epoch": 1.00093153237075, "grad_norm": 0.4632921785448845, "learning_rate": 4.6280635139799794e-05, "loss": 0.5248, "step": 1075 }, { "epoch": 1.0055891942244992, "grad_norm": 0.32912869412074214, "learning_rate": 4.6237487055574736e-05, "loss": 0.4875, "step": 1080 }, { "epoch": 1.0102468560782487, "grad_norm": 0.2919883060335107, "learning_rate": 4.619433897134968e-05, "loss": 0.4721, "step": 1085 }, { "epoch": 1.0149045179319982, "grad_norm": 0.3614415335939762, "learning_rate": 4.6151190887124615e-05, "loss": 0.4927, "step": 1090 }, { "epoch": 1.0195621797857475, "grad_norm": 0.3532510485861133, "learning_rate": 4.610804280289955e-05, "loss": 0.4884, "step": 1095 }, { "epoch": 1.024219841639497, "grad_norm": 0.35165281921734176, "learning_rate": 4.606489471867449e-05, "loss": 0.4908, "step": 1100 }, { "epoch": 1.0288775034932465, "grad_norm": 0.3799256112905046, "learning_rate": 4.602174663444943e-05, "loss": 0.4883, "step": 1105 }, { "epoch": 1.0335351653469957, "grad_norm": 0.3153281108251351, "learning_rate": 4.597859855022437e-05, "loss": 0.485, "step": 1110 }, { "epoch": 1.0381928272007452, "grad_norm": 0.33845770374279704, "learning_rate": 4.5935450465999314e-05, "loss": 0.4769, "step": 1115 }, { "epoch": 1.0428504890544947, "grad_norm": 0.3372423601537124, "learning_rate": 4.589230238177425e-05, "loss": 0.4875, "step": 1120 }, { "epoch": 1.047508150908244, "grad_norm": 0.3019385666252077, "learning_rate": 4.584915429754919e-05, "loss": 0.4935, "step": 1125 }, { "epoch": 1.0521658127619935, "grad_norm": 0.3323566719657497, "learning_rate": 4.5806006213324134e-05, "loss": 0.4802, "step": 1130 }, { "epoch": 1.056823474615743, "grad_norm": 0.2916867154047276, "learning_rate": 4.576285812909907e-05, "loss": 0.4868, "step": 1135 }, { "epoch": 1.0614811364694923, "grad_norm": 0.31237281271760353, "learning_rate": 4.5719710044874006e-05, "loss": 0.4877, "step": 1140 }, { "epoch": 1.0661387983232418, "grad_norm": 0.36387566760214146, "learning_rate": 4.567656196064895e-05, "loss": 0.487, "step": 1145 }, { "epoch": 1.0707964601769913, "grad_norm": 0.31981723577657195, "learning_rate": 4.563341387642389e-05, "loss": 0.4857, "step": 1150 }, { "epoch": 1.0754541220307405, "grad_norm": 0.334912264348049, "learning_rate": 4.5590265792198827e-05, "loss": 0.4883, "step": 1155 }, { "epoch": 1.08011178388449, "grad_norm": 0.3490053750136755, "learning_rate": 4.554711770797377e-05, "loss": 0.4959, "step": 1160 }, { "epoch": 1.0847694457382393, "grad_norm": 0.2889374292851012, "learning_rate": 4.550396962374871e-05, "loss": 0.4911, "step": 1165 }, { "epoch": 1.0894271075919888, "grad_norm": 0.29588178159788314, "learning_rate": 4.546082153952365e-05, "loss": 0.4894, "step": 1170 }, { "epoch": 1.0940847694457383, "grad_norm": 0.297453818800464, "learning_rate": 4.541767345529859e-05, "loss": 0.4912, "step": 1175 }, { "epoch": 1.0987424312994876, "grad_norm": 0.3479721250121237, "learning_rate": 4.5374525371073526e-05, "loss": 0.4828, "step": 1180 }, { "epoch": 1.103400093153237, "grad_norm": 0.3062707990612977, "learning_rate": 4.533137728684846e-05, "loss": 0.4805, "step": 1185 }, { "epoch": 1.1080577550069866, "grad_norm": 0.3039107853990957, "learning_rate": 4.5288229202623404e-05, "loss": 0.4624, "step": 1190 }, { "epoch": 1.1127154168607358, "grad_norm": 0.3113022694317826, "learning_rate": 4.5245081118398346e-05, "loss": 0.4745, "step": 1195 }, { "epoch": 1.1173730787144853, "grad_norm": 0.29219964657069414, "learning_rate": 4.520193303417328e-05, "loss": 0.4818, "step": 1200 }, { "epoch": 1.1220307405682348, "grad_norm": 0.3392341176685231, "learning_rate": 4.5158784949948224e-05, "loss": 0.4942, "step": 1205 }, { "epoch": 1.126688402421984, "grad_norm": 0.33008101295602316, "learning_rate": 4.511563686572317e-05, "loss": 0.4888, "step": 1210 }, { "epoch": 1.1313460642757336, "grad_norm": 0.34245861963236385, "learning_rate": 4.50724887814981e-05, "loss": 0.4833, "step": 1215 }, { "epoch": 1.136003726129483, "grad_norm": 0.3421395395062613, "learning_rate": 4.5029340697273045e-05, "loss": 0.491, "step": 1220 }, { "epoch": 1.1406613879832324, "grad_norm": 0.33123859609667766, "learning_rate": 4.498619261304798e-05, "loss": 0.4813, "step": 1225 }, { "epoch": 1.1453190498369819, "grad_norm": 0.359519078533143, "learning_rate": 4.4943044528822923e-05, "loss": 0.4804, "step": 1230 }, { "epoch": 1.1499767116907313, "grad_norm": 0.3345159204769192, "learning_rate": 4.489989644459786e-05, "loss": 0.4856, "step": 1235 }, { "epoch": 1.1546343735444806, "grad_norm": 0.3088588280620258, "learning_rate": 4.48567483603728e-05, "loss": 0.4938, "step": 1240 }, { "epoch": 1.1592920353982301, "grad_norm": 0.2966023397027488, "learning_rate": 4.4813600276147744e-05, "loss": 0.4892, "step": 1245 }, { "epoch": 1.1639496972519794, "grad_norm": 0.3301716866826791, "learning_rate": 4.477045219192268e-05, "loss": 0.4994, "step": 1250 }, { "epoch": 1.1686073591057289, "grad_norm": 0.300666661687487, "learning_rate": 4.472730410769762e-05, "loss": 0.4857, "step": 1255 }, { "epoch": 1.1732650209594784, "grad_norm": 0.28175269019647703, "learning_rate": 4.4684156023472565e-05, "loss": 0.4942, "step": 1260 }, { "epoch": 1.1779226828132279, "grad_norm": 0.31234252298252274, "learning_rate": 4.46410079392475e-05, "loss": 0.4802, "step": 1265 }, { "epoch": 1.1825803446669771, "grad_norm": 0.2889673407909235, "learning_rate": 4.4597859855022436e-05, "loss": 0.473, "step": 1270 }, { "epoch": 1.1872380065207266, "grad_norm": 0.32907625488950515, "learning_rate": 4.455471177079738e-05, "loss": 0.48, "step": 1275 }, { "epoch": 1.191895668374476, "grad_norm": 0.3872547580880964, "learning_rate": 4.4511563686572315e-05, "loss": 0.4892, "step": 1280 }, { "epoch": 1.1965533302282254, "grad_norm": 0.3424296149155122, "learning_rate": 4.446841560234726e-05, "loss": 0.4907, "step": 1285 }, { "epoch": 1.201210992081975, "grad_norm": 0.31770618961382174, "learning_rate": 4.44252675181222e-05, "loss": 0.478, "step": 1290 }, { "epoch": 1.2058686539357242, "grad_norm": 0.32981744342937497, "learning_rate": 4.4382119433897135e-05, "loss": 0.4838, "step": 1295 }, { "epoch": 1.2105263157894737, "grad_norm": 0.3240560265185589, "learning_rate": 4.433897134967208e-05, "loss": 0.4787, "step": 1300 }, { "epoch": 1.2151839776432232, "grad_norm": 0.29157966807929886, "learning_rate": 4.429582326544702e-05, "loss": 0.4899, "step": 1305 }, { "epoch": 1.2198416394969724, "grad_norm": 0.29966248704229675, "learning_rate": 4.4252675181221956e-05, "loss": 0.4934, "step": 1310 }, { "epoch": 1.224499301350722, "grad_norm": 0.29209527914560146, "learning_rate": 4.420952709699689e-05, "loss": 0.4828, "step": 1315 }, { "epoch": 1.2291569632044714, "grad_norm": 0.28847978994151485, "learning_rate": 4.4166379012771834e-05, "loss": 0.4939, "step": 1320 }, { "epoch": 1.2338146250582207, "grad_norm": 0.2869276195242927, "learning_rate": 4.412323092854678e-05, "loss": 0.479, "step": 1325 }, { "epoch": 1.2384722869119702, "grad_norm": 0.29129753146127935, "learning_rate": 4.408008284432171e-05, "loss": 0.4913, "step": 1330 }, { "epoch": 1.2431299487657197, "grad_norm": 0.3157239258230541, "learning_rate": 4.4036934760096655e-05, "loss": 0.4842, "step": 1335 }, { "epoch": 1.247787610619469, "grad_norm": 0.3430043059100621, "learning_rate": 4.39937866758716e-05, "loss": 0.482, "step": 1340 }, { "epoch": 1.2524452724732185, "grad_norm": 0.29108394447322516, "learning_rate": 4.395063859164653e-05, "loss": 0.4723, "step": 1345 }, { "epoch": 1.257102934326968, "grad_norm": 0.30471066067981095, "learning_rate": 4.3907490507421476e-05, "loss": 0.4829, "step": 1350 }, { "epoch": 1.2617605961807172, "grad_norm": 0.352227839186927, "learning_rate": 4.386434242319641e-05, "loss": 0.4753, "step": 1355 }, { "epoch": 1.2664182580344667, "grad_norm": 0.2933568982073623, "learning_rate": 4.382119433897135e-05, "loss": 0.4688, "step": 1360 }, { "epoch": 1.271075919888216, "grad_norm": 0.29078495379443625, "learning_rate": 4.377804625474629e-05, "loss": 0.4867, "step": 1365 }, { "epoch": 1.2757335817419655, "grad_norm": 0.326200148442532, "learning_rate": 4.373489817052123e-05, "loss": 0.4829, "step": 1370 }, { "epoch": 1.280391243595715, "grad_norm": 0.2914299363887864, "learning_rate": 4.369175008629617e-05, "loss": 0.482, "step": 1375 }, { "epoch": 1.2850489054494645, "grad_norm": 0.2711007051503921, "learning_rate": 4.364860200207111e-05, "loss": 0.4821, "step": 1380 }, { "epoch": 1.2897065673032138, "grad_norm": 0.28308537381937476, "learning_rate": 4.360545391784605e-05, "loss": 0.4825, "step": 1385 }, { "epoch": 1.2943642291569633, "grad_norm": 0.3164763233653568, "learning_rate": 4.356230583362099e-05, "loss": 0.491, "step": 1390 }, { "epoch": 1.2990218910107125, "grad_norm": 0.30450607097390087, "learning_rate": 4.351915774939593e-05, "loss": 0.475, "step": 1395 }, { "epoch": 1.303679552864462, "grad_norm": 0.2939389706827691, "learning_rate": 4.347600966517087e-05, "loss": 0.4894, "step": 1400 }, { "epoch": 1.3083372147182115, "grad_norm": 0.2790352452124077, "learning_rate": 4.343286158094581e-05, "loss": 0.4782, "step": 1405 }, { "epoch": 1.312994876571961, "grad_norm": 0.28768130457131963, "learning_rate": 4.3389713496720745e-05, "loss": 0.4749, "step": 1410 }, { "epoch": 1.3176525384257103, "grad_norm": 0.2767762112338014, "learning_rate": 4.334656541249569e-05, "loss": 0.4961, "step": 1415 }, { "epoch": 1.3223102002794598, "grad_norm": 0.3001306312130908, "learning_rate": 4.330341732827063e-05, "loss": 0.4843, "step": 1420 }, { "epoch": 1.326967862133209, "grad_norm": 0.2721487179105162, "learning_rate": 4.3260269244045566e-05, "loss": 0.4778, "step": 1425 }, { "epoch": 1.3316255239869585, "grad_norm": 0.3349004234823024, "learning_rate": 4.321712115982051e-05, "loss": 0.4768, "step": 1430 }, { "epoch": 1.336283185840708, "grad_norm": 0.28726920143958445, "learning_rate": 4.317397307559545e-05, "loss": 0.4815, "step": 1435 }, { "epoch": 1.3409408476944573, "grad_norm": 0.28309608323757895, "learning_rate": 4.3130824991370387e-05, "loss": 0.4844, "step": 1440 }, { "epoch": 1.3455985095482068, "grad_norm": 0.3114004757061075, "learning_rate": 4.308767690714532e-05, "loss": 0.4934, "step": 1445 }, { "epoch": 1.350256171401956, "grad_norm": 0.33091791915795965, "learning_rate": 4.3044528822920265e-05, "loss": 0.4795, "step": 1450 }, { "epoch": 1.3549138332557056, "grad_norm": 0.30056666367000356, "learning_rate": 4.30013807386952e-05, "loss": 0.4902, "step": 1455 }, { "epoch": 1.359571495109455, "grad_norm": 0.27716216697913887, "learning_rate": 4.295823265447014e-05, "loss": 0.4706, "step": 1460 }, { "epoch": 1.3642291569632046, "grad_norm": 0.27713551972252015, "learning_rate": 4.2915084570245085e-05, "loss": 0.4788, "step": 1465 }, { "epoch": 1.3688868188169538, "grad_norm": 0.29923102325192574, "learning_rate": 4.287193648602002e-05, "loss": 0.4829, "step": 1470 }, { "epoch": 1.3735444806707033, "grad_norm": 0.338944380371894, "learning_rate": 4.2828788401794964e-05, "loss": 0.4748, "step": 1475 }, { "epoch": 1.3782021425244526, "grad_norm": 0.3030666115554409, "learning_rate": 4.27856403175699e-05, "loss": 0.4751, "step": 1480 }, { "epoch": 1.382859804378202, "grad_norm": 0.2930060181395125, "learning_rate": 4.274249223334484e-05, "loss": 0.4818, "step": 1485 }, { "epoch": 1.3875174662319516, "grad_norm": 0.3306900511088145, "learning_rate": 4.269934414911978e-05, "loss": 0.486, "step": 1490 }, { "epoch": 1.392175128085701, "grad_norm": 0.2819482209237745, "learning_rate": 4.265619606489472e-05, "loss": 0.4866, "step": 1495 }, { "epoch": 1.3968327899394504, "grad_norm": 0.2722046364147041, "learning_rate": 4.261304798066966e-05, "loss": 0.4729, "step": 1500 }, { "epoch": 1.4014904517931999, "grad_norm": 0.3160858342454398, "learning_rate": 4.25698998964446e-05, "loss": 0.4783, "step": 1505 }, { "epoch": 1.4061481136469491, "grad_norm": 0.3097314519773002, "learning_rate": 4.252675181221954e-05, "loss": 0.4775, "step": 1510 }, { "epoch": 1.4108057755006986, "grad_norm": 0.27198353698009836, "learning_rate": 4.248360372799448e-05, "loss": 0.4897, "step": 1515 }, { "epoch": 1.4154634373544481, "grad_norm": 0.3391629336482396, "learning_rate": 4.244045564376942e-05, "loss": 0.4774, "step": 1520 }, { "epoch": 1.4201210992081974, "grad_norm": 0.3007396520295025, "learning_rate": 4.2397307559544355e-05, "loss": 0.4777, "step": 1525 }, { "epoch": 1.424778761061947, "grad_norm": 0.2984587001230894, "learning_rate": 4.23541594753193e-05, "loss": 0.4704, "step": 1530 }, { "epoch": 1.4294364229156964, "grad_norm": 0.286923614396669, "learning_rate": 4.231101139109423e-05, "loss": 0.486, "step": 1535 }, { "epoch": 1.4340940847694457, "grad_norm": 0.2803651033209193, "learning_rate": 4.2267863306869176e-05, "loss": 0.4758, "step": 1540 }, { "epoch": 1.4387517466231952, "grad_norm": 0.2855980702998801, "learning_rate": 4.222471522264412e-05, "loss": 0.4775, "step": 1545 }, { "epoch": 1.4434094084769447, "grad_norm": 0.3127203259037703, "learning_rate": 4.2181567138419054e-05, "loss": 0.472, "step": 1550 }, { "epoch": 1.448067070330694, "grad_norm": 0.2625555748412213, "learning_rate": 4.2138419054193996e-05, "loss": 0.4679, "step": 1555 }, { "epoch": 1.4527247321844434, "grad_norm": 0.26511749665855916, "learning_rate": 4.209527096996894e-05, "loss": 0.476, "step": 1560 }, { "epoch": 1.4573823940381927, "grad_norm": 0.2986509617670059, "learning_rate": 4.2052122885743875e-05, "loss": 0.4859, "step": 1565 }, { "epoch": 1.4620400558919422, "grad_norm": 0.2855892793458747, "learning_rate": 4.200897480151881e-05, "loss": 0.5018, "step": 1570 }, { "epoch": 1.4666977177456917, "grad_norm": 0.293253371927899, "learning_rate": 4.196582671729375e-05, "loss": 0.4796, "step": 1575 }, { "epoch": 1.4713553795994412, "grad_norm": 0.2826309796827852, "learning_rate": 4.1922678633068695e-05, "loss": 0.4678, "step": 1580 }, { "epoch": 1.4760130414531905, "grad_norm": 0.2785576198036202, "learning_rate": 4.187953054884363e-05, "loss": 0.4771, "step": 1585 }, { "epoch": 1.48067070330694, "grad_norm": 0.30168732783175745, "learning_rate": 4.1836382464618573e-05, "loss": 0.4775, "step": 1590 }, { "epoch": 1.4853283651606892, "grad_norm": 0.2888190465717287, "learning_rate": 4.1793234380393516e-05, "loss": 0.4728, "step": 1595 }, { "epoch": 1.4899860270144387, "grad_norm": 0.28524305336894035, "learning_rate": 4.175008629616845e-05, "loss": 0.4811, "step": 1600 }, { "epoch": 1.4946436888681882, "grad_norm": 0.2840817267674215, "learning_rate": 4.1706938211943394e-05, "loss": 0.4717, "step": 1605 }, { "epoch": 1.4993013507219377, "grad_norm": 0.28061432719129525, "learning_rate": 4.166379012771833e-05, "loss": 0.478, "step": 1610 }, { "epoch": 1.503959012575687, "grad_norm": 0.28993729872378593, "learning_rate": 4.1620642043493266e-05, "loss": 0.4794, "step": 1615 }, { "epoch": 1.5086166744294365, "grad_norm": 0.3103483727047431, "learning_rate": 4.157749395926821e-05, "loss": 0.4767, "step": 1620 }, { "epoch": 1.5132743362831858, "grad_norm": 0.2717067901334242, "learning_rate": 4.153434587504315e-05, "loss": 0.483, "step": 1625 }, { "epoch": 1.5179319981369352, "grad_norm": 0.26950448814209005, "learning_rate": 4.1491197790818086e-05, "loss": 0.4792, "step": 1630 }, { "epoch": 1.5225896599906847, "grad_norm": 0.29012301269593405, "learning_rate": 4.144804970659303e-05, "loss": 0.4912, "step": 1635 }, { "epoch": 1.5272473218444342, "grad_norm": 0.2964771656223394, "learning_rate": 4.140490162236797e-05, "loss": 0.4835, "step": 1640 }, { "epoch": 1.5319049836981835, "grad_norm": 0.28188380235315447, "learning_rate": 4.1361753538142914e-05, "loss": 0.4893, "step": 1645 }, { "epoch": 1.5365626455519328, "grad_norm": 0.2793390290497567, "learning_rate": 4.131860545391785e-05, "loss": 0.4714, "step": 1650 }, { "epoch": 1.5412203074056823, "grad_norm": 0.32520731304464173, "learning_rate": 4.1275457369692785e-05, "loss": 0.4696, "step": 1655 }, { "epoch": 1.5458779692594318, "grad_norm": 0.28493777023118516, "learning_rate": 4.123230928546773e-05, "loss": 0.4681, "step": 1660 }, { "epoch": 1.5505356311131813, "grad_norm": 0.31165496114762914, "learning_rate": 4.1189161201242664e-05, "loss": 0.4824, "step": 1665 }, { "epoch": 1.5551932929669308, "grad_norm": 0.3183640415651854, "learning_rate": 4.1146013117017606e-05, "loss": 0.4762, "step": 1670 }, { "epoch": 1.55985095482068, "grad_norm": 0.27003966447848793, "learning_rate": 4.110286503279255e-05, "loss": 0.4734, "step": 1675 }, { "epoch": 1.5645086166744293, "grad_norm": 0.29022926801947263, "learning_rate": 4.1059716948567484e-05, "loss": 0.482, "step": 1680 }, { "epoch": 1.5691662785281788, "grad_norm": 0.3100363021620269, "learning_rate": 4.101656886434243e-05, "loss": 0.4711, "step": 1685 }, { "epoch": 1.5738239403819283, "grad_norm": 0.3014273300764397, "learning_rate": 4.097342078011737e-05, "loss": 0.4782, "step": 1690 }, { "epoch": 1.5784816022356778, "grad_norm": 0.25818287760473824, "learning_rate": 4.0930272695892305e-05, "loss": 0.4755, "step": 1695 }, { "epoch": 1.583139264089427, "grad_norm": 0.28016753599602673, "learning_rate": 4.088712461166724e-05, "loss": 0.4808, "step": 1700 }, { "epoch": 1.5877969259431766, "grad_norm": 0.27362006614298395, "learning_rate": 4.084397652744218e-05, "loss": 0.4742, "step": 1705 }, { "epoch": 1.5924545877969258, "grad_norm": 0.29106008462525784, "learning_rate": 4.080082844321712e-05, "loss": 0.4795, "step": 1710 }, { "epoch": 1.5971122496506753, "grad_norm": 0.293896792588217, "learning_rate": 4.075768035899206e-05, "loss": 0.4874, "step": 1715 }, { "epoch": 1.6017699115044248, "grad_norm": 0.2813231425489303, "learning_rate": 4.0714532274767004e-05, "loss": 0.4704, "step": 1720 }, { "epoch": 1.6064275733581743, "grad_norm": 0.2878983478156043, "learning_rate": 4.0671384190541946e-05, "loss": 0.4737, "step": 1725 }, { "epoch": 1.6110852352119236, "grad_norm": 0.2822461682447495, "learning_rate": 4.062823610631688e-05, "loss": 0.4876, "step": 1730 }, { "epoch": 1.6157428970656729, "grad_norm": 0.29711563225212795, "learning_rate": 4.0585088022091825e-05, "loss": 0.484, "step": 1735 }, { "epoch": 1.6204005589194224, "grad_norm": 0.28134833194408376, "learning_rate": 4.054193993786676e-05, "loss": 0.4639, "step": 1740 }, { "epoch": 1.6250582207731719, "grad_norm": 0.26927341786795544, "learning_rate": 4.0498791853641696e-05, "loss": 0.5001, "step": 1745 }, { "epoch": 1.6297158826269214, "grad_norm": 0.2655069262105719, "learning_rate": 4.045564376941664e-05, "loss": 0.4706, "step": 1750 }, { "epoch": 1.6343735444806708, "grad_norm": 0.2685194810205972, "learning_rate": 4.041249568519158e-05, "loss": 0.4884, "step": 1755 }, { "epoch": 1.6390312063344201, "grad_norm": 0.2773220126527348, "learning_rate": 4.036934760096652e-05, "loss": 0.4671, "step": 1760 }, { "epoch": 1.6436888681881694, "grad_norm": 0.280172412215713, "learning_rate": 4.032619951674146e-05, "loss": 0.4739, "step": 1765 }, { "epoch": 1.648346530041919, "grad_norm": 0.28981799850171003, "learning_rate": 4.02830514325164e-05, "loss": 0.4676, "step": 1770 }, { "epoch": 1.6530041918956684, "grad_norm": 0.2693809746473411, "learning_rate": 4.023990334829134e-05, "loss": 0.485, "step": 1775 }, { "epoch": 1.6576618537494179, "grad_norm": 0.2764797001266346, "learning_rate": 4.019675526406628e-05, "loss": 0.4692, "step": 1780 }, { "epoch": 1.6623195156031674, "grad_norm": 0.2934880983965738, "learning_rate": 4.0153607179841216e-05, "loss": 0.4803, "step": 1785 }, { "epoch": 1.6669771774569166, "grad_norm": 0.26486250114979143, "learning_rate": 4.011045909561615e-05, "loss": 0.4708, "step": 1790 }, { "epoch": 1.671634839310666, "grad_norm": 0.2883170760677119, "learning_rate": 4.0067311011391094e-05, "loss": 0.468, "step": 1795 }, { "epoch": 1.6762925011644154, "grad_norm": 0.26886056072539066, "learning_rate": 4.0024162927166037e-05, "loss": 0.4676, "step": 1800 }, { "epoch": 1.680950163018165, "grad_norm": 0.23953674554184504, "learning_rate": 3.998101484294098e-05, "loss": 0.4746, "step": 1805 }, { "epoch": 1.6856078248719144, "grad_norm": 0.2653550975091167, "learning_rate": 3.9937866758715915e-05, "loss": 0.4729, "step": 1810 }, { "epoch": 1.6902654867256637, "grad_norm": 0.2804730855492134, "learning_rate": 3.989471867449086e-05, "loss": 0.4745, "step": 1815 }, { "epoch": 1.6949231485794132, "grad_norm": 0.2672890269409446, "learning_rate": 3.98515705902658e-05, "loss": 0.4577, "step": 1820 }, { "epoch": 1.6995808104331624, "grad_norm": 0.29201514888862934, "learning_rate": 3.9808422506040736e-05, "loss": 0.4637, "step": 1825 }, { "epoch": 1.704238472286912, "grad_norm": 0.29900458474130365, "learning_rate": 3.976527442181567e-05, "loss": 0.4662, "step": 1830 }, { "epoch": 1.7088961341406614, "grad_norm": 0.2633432180510318, "learning_rate": 3.9722126337590614e-05, "loss": 0.4758, "step": 1835 }, { "epoch": 1.713553795994411, "grad_norm": 0.2819716773445563, "learning_rate": 3.967897825336555e-05, "loss": 0.4717, "step": 1840 }, { "epoch": 1.7182114578481602, "grad_norm": 0.29835832294832193, "learning_rate": 3.963583016914049e-05, "loss": 0.4734, "step": 1845 }, { "epoch": 1.7228691197019095, "grad_norm": 0.27742797497073457, "learning_rate": 3.9592682084915434e-05, "loss": 0.4851, "step": 1850 }, { "epoch": 1.727526781555659, "grad_norm": 0.28631747383811534, "learning_rate": 3.954953400069037e-05, "loss": 0.4624, "step": 1855 }, { "epoch": 1.7321844434094085, "grad_norm": 0.2698043984577089, "learning_rate": 3.950638591646531e-05, "loss": 0.4932, "step": 1860 }, { "epoch": 1.736842105263158, "grad_norm": 0.28220061906724964, "learning_rate": 3.9463237832240255e-05, "loss": 0.4682, "step": 1865 }, { "epoch": 1.7414997671169075, "grad_norm": 0.25410530954556343, "learning_rate": 3.942008974801519e-05, "loss": 0.4763, "step": 1870 }, { "epoch": 1.7461574289706567, "grad_norm": 0.26971827300849793, "learning_rate": 3.937694166379013e-05, "loss": 0.4921, "step": 1875 }, { "epoch": 1.750815090824406, "grad_norm": 0.2764590187624231, "learning_rate": 3.933379357956507e-05, "loss": 0.4814, "step": 1880 }, { "epoch": 1.7554727526781555, "grad_norm": 0.32425453917862546, "learning_rate": 3.9290645495340005e-05, "loss": 0.4831, "step": 1885 }, { "epoch": 1.760130414531905, "grad_norm": 0.27070971454464965, "learning_rate": 3.924749741111495e-05, "loss": 0.4771, "step": 1890 }, { "epoch": 1.7647880763856545, "grad_norm": 0.30482510776810723, "learning_rate": 3.920434932688989e-05, "loss": 0.4887, "step": 1895 }, { "epoch": 1.7694457382394038, "grad_norm": 0.25714752199699287, "learning_rate": 3.916120124266483e-05, "loss": 0.4771, "step": 1900 }, { "epoch": 1.7741034000931533, "grad_norm": 0.2950990923750265, "learning_rate": 3.911805315843977e-05, "loss": 0.4761, "step": 1905 }, { "epoch": 1.7787610619469025, "grad_norm": 0.29230401361574815, "learning_rate": 3.9074905074214704e-05, "loss": 0.4672, "step": 1910 }, { "epoch": 1.783418723800652, "grad_norm": 0.2684460766706467, "learning_rate": 3.9031756989989646e-05, "loss": 0.4589, "step": 1915 }, { "epoch": 1.7880763856544015, "grad_norm": 0.30958796366672636, "learning_rate": 3.898860890576458e-05, "loss": 0.4685, "step": 1920 }, { "epoch": 1.792734047508151, "grad_norm": 0.2771778238669022, "learning_rate": 3.8945460821539525e-05, "loss": 0.4755, "step": 1925 }, { "epoch": 1.7973917093619003, "grad_norm": 0.2631689602628431, "learning_rate": 3.890231273731447e-05, "loss": 0.4686, "step": 1930 }, { "epoch": 1.8020493712156498, "grad_norm": 0.25854910119197666, "learning_rate": 3.88591646530894e-05, "loss": 0.4619, "step": 1935 }, { "epoch": 1.806707033069399, "grad_norm": 0.26763724255196647, "learning_rate": 3.8816016568864345e-05, "loss": 0.4649, "step": 1940 }, { "epoch": 1.8113646949231486, "grad_norm": 0.2575169577985457, "learning_rate": 3.877286848463929e-05, "loss": 0.478, "step": 1945 }, { "epoch": 1.816022356776898, "grad_norm": 0.26569533301995135, "learning_rate": 3.8729720400414224e-05, "loss": 0.468, "step": 1950 }, { "epoch": 1.8206800186306475, "grad_norm": 0.2557935376542548, "learning_rate": 3.868657231618916e-05, "loss": 0.4704, "step": 1955 }, { "epoch": 1.8253376804843968, "grad_norm": 0.2548045868186804, "learning_rate": 3.86434242319641e-05, "loss": 0.4727, "step": 1960 }, { "epoch": 1.829995342338146, "grad_norm": 0.2778105867176685, "learning_rate": 3.860027614773904e-05, "loss": 0.4751, "step": 1965 }, { "epoch": 1.8346530041918956, "grad_norm": 0.28173241188506193, "learning_rate": 3.855712806351398e-05, "loss": 0.471, "step": 1970 }, { "epoch": 1.839310666045645, "grad_norm": 0.29705890432093524, "learning_rate": 3.851397997928892e-05, "loss": 0.4768, "step": 1975 }, { "epoch": 1.8439683278993946, "grad_norm": 0.2745031878305927, "learning_rate": 3.8470831895063865e-05, "loss": 0.4686, "step": 1980 }, { "epoch": 1.848625989753144, "grad_norm": 0.30643088637918886, "learning_rate": 3.84276838108388e-05, "loss": 0.4855, "step": 1985 }, { "epoch": 1.8532836516068933, "grad_norm": 0.2791281292475335, "learning_rate": 3.838453572661374e-05, "loss": 0.4763, "step": 1990 }, { "epoch": 1.8579413134606426, "grad_norm": 0.25189125443363714, "learning_rate": 3.834138764238868e-05, "loss": 0.4593, "step": 1995 }, { "epoch": 1.8625989753143921, "grad_norm": 0.2624794212526965, "learning_rate": 3.8298239558163615e-05, "loss": 0.4726, "step": 2000 }, { "epoch": 1.8672566371681416, "grad_norm": 0.268869119427028, "learning_rate": 3.825509147393856e-05, "loss": 0.4828, "step": 2005 }, { "epoch": 1.871914299021891, "grad_norm": 0.25345592833906166, "learning_rate": 3.82119433897135e-05, "loss": 0.4645, "step": 2010 }, { "epoch": 1.8765719608756404, "grad_norm": 0.2508497293453585, "learning_rate": 3.8168795305488435e-05, "loss": 0.4848, "step": 2015 }, { "epoch": 1.8812296227293899, "grad_norm": 0.25906478992834975, "learning_rate": 3.812564722126338e-05, "loss": 0.4658, "step": 2020 }, { "epoch": 1.8858872845831391, "grad_norm": 0.2756232774321132, "learning_rate": 3.808249913703832e-05, "loss": 0.4728, "step": 2025 }, { "epoch": 1.8905449464368886, "grad_norm": 0.2672035827470766, "learning_rate": 3.8039351052813256e-05, "loss": 0.4681, "step": 2030 }, { "epoch": 1.8952026082906381, "grad_norm": 0.25183326606986073, "learning_rate": 3.79962029685882e-05, "loss": 0.4651, "step": 2035 }, { "epoch": 1.8998602701443876, "grad_norm": 0.2744865010082688, "learning_rate": 3.7953054884363134e-05, "loss": 0.4782, "step": 2040 }, { "epoch": 1.904517931998137, "grad_norm": 0.24541300807455738, "learning_rate": 3.790990680013807e-05, "loss": 0.4835, "step": 2045 }, { "epoch": 1.9091755938518864, "grad_norm": 0.28628962176634354, "learning_rate": 3.786675871591301e-05, "loss": 0.4705, "step": 2050 }, { "epoch": 1.9138332557056357, "grad_norm": 0.2534647303445009, "learning_rate": 3.7823610631687955e-05, "loss": 0.4705, "step": 2055 }, { "epoch": 1.9184909175593852, "grad_norm": 0.27512016922683297, "learning_rate": 3.77804625474629e-05, "loss": 0.4652, "step": 2060 }, { "epoch": 1.9231485794131347, "grad_norm": 0.25959172822434223, "learning_rate": 3.773731446323783e-05, "loss": 0.4697, "step": 2065 }, { "epoch": 1.9278062412668842, "grad_norm": 0.28372147487964944, "learning_rate": 3.7694166379012776e-05, "loss": 0.4726, "step": 2070 }, { "epoch": 1.9324639031206334, "grad_norm": 0.27142055843860996, "learning_rate": 3.765101829478772e-05, "loss": 0.4704, "step": 2075 }, { "epoch": 1.9371215649743827, "grad_norm": 0.2712064942986188, "learning_rate": 3.7607870210562654e-05, "loss": 0.4618, "step": 2080 }, { "epoch": 1.9417792268281322, "grad_norm": 0.2626331764580097, "learning_rate": 3.756472212633759e-05, "loss": 0.4776, "step": 2085 }, { "epoch": 1.9464368886818817, "grad_norm": 0.24698578857562906, "learning_rate": 3.752157404211253e-05, "loss": 0.4541, "step": 2090 }, { "epoch": 1.9510945505356312, "grad_norm": 0.2640709472656743, "learning_rate": 3.747842595788747e-05, "loss": 0.4669, "step": 2095 }, { "epoch": 1.9557522123893807, "grad_norm": 0.318779639998938, "learning_rate": 3.743527787366241e-05, "loss": 0.4657, "step": 2100 }, { "epoch": 1.96040987424313, "grad_norm": 0.27957149731441905, "learning_rate": 3.739212978943735e-05, "loss": 0.4764, "step": 2105 }, { "epoch": 1.9650675360968792, "grad_norm": 0.2621687905162846, "learning_rate": 3.734898170521229e-05, "loss": 0.4584, "step": 2110 }, { "epoch": 1.9697251979506287, "grad_norm": 0.2753004729634785, "learning_rate": 3.730583362098723e-05, "loss": 0.4709, "step": 2115 }, { "epoch": 1.9743828598043782, "grad_norm": 0.2495586129653223, "learning_rate": 3.7262685536762174e-05, "loss": 0.4743, "step": 2120 }, { "epoch": 1.9790405216581277, "grad_norm": 0.2732351941720727, "learning_rate": 3.721953745253711e-05, "loss": 0.4635, "step": 2125 }, { "epoch": 1.983698183511877, "grad_norm": 0.2542355999652173, "learning_rate": 3.7176389368312045e-05, "loss": 0.4673, "step": 2130 }, { "epoch": 1.9883558453656265, "grad_norm": 0.25866761256242665, "learning_rate": 3.713324128408699e-05, "loss": 0.4743, "step": 2135 }, { "epoch": 1.9930135072193758, "grad_norm": 0.2549880250088915, "learning_rate": 3.709009319986193e-05, "loss": 0.473, "step": 2140 }, { "epoch": 1.9976711690731253, "grad_norm": 0.2695206822580522, "learning_rate": 3.7046945115636866e-05, "loss": 0.4729, "step": 2145 }, { "epoch": 2.0018630647415, "grad_norm": 0.2952067062504725, "learning_rate": 3.700379703141181e-05, "loss": 0.4646, "step": 2150 }, { "epoch": 2.0065207265952494, "grad_norm": 0.2959251559851445, "learning_rate": 3.696064894718675e-05, "loss": 0.4331, "step": 2155 }, { "epoch": 2.0111783884489984, "grad_norm": 0.2964702408813218, "learning_rate": 3.6917500862961687e-05, "loss": 0.4254, "step": 2160 }, { "epoch": 2.015836050302748, "grad_norm": 0.2992601350758417, "learning_rate": 3.687435277873663e-05, "loss": 0.4313, "step": 2165 }, { "epoch": 2.0204937121564974, "grad_norm": 0.2712482239143513, "learning_rate": 3.6831204694511565e-05, "loss": 0.4174, "step": 2170 }, { "epoch": 2.025151374010247, "grad_norm": 0.28354012145517715, "learning_rate": 3.67880566102865e-05, "loss": 0.44, "step": 2175 }, { "epoch": 2.0298090358639964, "grad_norm": 0.28207716456353477, "learning_rate": 3.674490852606144e-05, "loss": 0.4257, "step": 2180 }, { "epoch": 2.034466697717746, "grad_norm": 0.3286377981360172, "learning_rate": 3.6701760441836386e-05, "loss": 0.4362, "step": 2185 }, { "epoch": 2.039124359571495, "grad_norm": 0.2921247948044917, "learning_rate": 3.665861235761132e-05, "loss": 0.4317, "step": 2190 }, { "epoch": 2.0437820214252445, "grad_norm": 0.2887724781092165, "learning_rate": 3.6615464273386264e-05, "loss": 0.4304, "step": 2195 }, { "epoch": 2.048439683278994, "grad_norm": 0.28068327695888107, "learning_rate": 3.6572316189161206e-05, "loss": 0.4279, "step": 2200 }, { "epoch": 2.0530973451327434, "grad_norm": 0.27457813090517463, "learning_rate": 3.652916810493614e-05, "loss": 0.4355, "step": 2205 }, { "epoch": 2.057755006986493, "grad_norm": 0.2544486844892888, "learning_rate": 3.6486020020711085e-05, "loss": 0.4199, "step": 2210 }, { "epoch": 2.062412668840242, "grad_norm": 0.3335841121295516, "learning_rate": 3.644287193648602e-05, "loss": 0.4291, "step": 2215 }, { "epoch": 2.0670703306939915, "grad_norm": 0.27586572192688225, "learning_rate": 3.639972385226096e-05, "loss": 0.4319, "step": 2220 }, { "epoch": 2.071727992547741, "grad_norm": 0.25396050689096766, "learning_rate": 3.63565757680359e-05, "loss": 0.4287, "step": 2225 }, { "epoch": 2.0763856544014905, "grad_norm": 0.2639162589412496, "learning_rate": 3.631342768381084e-05, "loss": 0.4304, "step": 2230 }, { "epoch": 2.08104331625524, "grad_norm": 0.24951306673217283, "learning_rate": 3.6270279599585783e-05, "loss": 0.4239, "step": 2235 }, { "epoch": 2.0857009781089895, "grad_norm": 0.2515835097779391, "learning_rate": 3.622713151536072e-05, "loss": 0.435, "step": 2240 }, { "epoch": 2.0903586399627385, "grad_norm": 0.2583301850368636, "learning_rate": 3.618398343113566e-05, "loss": 0.4348, "step": 2245 }, { "epoch": 2.095016301816488, "grad_norm": 0.26545910661458344, "learning_rate": 3.6140835346910604e-05, "loss": 0.4268, "step": 2250 }, { "epoch": 2.0996739636702375, "grad_norm": 0.2718875580761793, "learning_rate": 3.609768726268554e-05, "loss": 0.4392, "step": 2255 }, { "epoch": 2.104331625523987, "grad_norm": 0.29442016691756145, "learning_rate": 3.6054539178460476e-05, "loss": 0.4251, "step": 2260 }, { "epoch": 2.1089892873777365, "grad_norm": 0.2625290585208749, "learning_rate": 3.601139109423542e-05, "loss": 0.4415, "step": 2265 }, { "epoch": 2.113646949231486, "grad_norm": 0.25773607261067005, "learning_rate": 3.5968243010010354e-05, "loss": 0.4293, "step": 2270 }, { "epoch": 2.118304611085235, "grad_norm": 0.2815717375075622, "learning_rate": 3.5925094925785296e-05, "loss": 0.4308, "step": 2275 }, { "epoch": 2.1229622729389845, "grad_norm": 0.26509972611907234, "learning_rate": 3.588194684156024e-05, "loss": 0.4303, "step": 2280 }, { "epoch": 2.127619934792734, "grad_norm": 0.2679741832446721, "learning_rate": 3.5838798757335175e-05, "loss": 0.4354, "step": 2285 }, { "epoch": 2.1322775966464835, "grad_norm": 0.2822562838462212, "learning_rate": 3.579565067311012e-05, "loss": 0.4332, "step": 2290 }, { "epoch": 2.136935258500233, "grad_norm": 0.27916042745813696, "learning_rate": 3.575250258888505e-05, "loss": 0.4419, "step": 2295 }, { "epoch": 2.1415929203539825, "grad_norm": 0.2633516130609347, "learning_rate": 3.5709354504659995e-05, "loss": 0.4425, "step": 2300 }, { "epoch": 2.1462505822077316, "grad_norm": 0.25451963961380186, "learning_rate": 3.566620642043493e-05, "loss": 0.4328, "step": 2305 }, { "epoch": 2.150908244061481, "grad_norm": 0.2615036843246581, "learning_rate": 3.5623058336209874e-05, "loss": 0.4168, "step": 2310 }, { "epoch": 2.1555659059152306, "grad_norm": 0.2762195965299843, "learning_rate": 3.5579910251984816e-05, "loss": 0.4241, "step": 2315 }, { "epoch": 2.16022356776898, "grad_norm": 0.27349956394712477, "learning_rate": 3.553676216775975e-05, "loss": 0.4265, "step": 2320 }, { "epoch": 2.1648812296227296, "grad_norm": 0.260821542030323, "learning_rate": 3.5493614083534694e-05, "loss": 0.4367, "step": 2325 }, { "epoch": 2.1695388914764786, "grad_norm": 0.26345035661134975, "learning_rate": 3.545046599930964e-05, "loss": 0.4392, "step": 2330 }, { "epoch": 2.174196553330228, "grad_norm": 0.2567292844000678, "learning_rate": 3.540731791508457e-05, "loss": 0.4232, "step": 2335 }, { "epoch": 2.1788542151839776, "grad_norm": 0.2643316404113489, "learning_rate": 3.536416983085951e-05, "loss": 0.4355, "step": 2340 }, { "epoch": 2.183511877037727, "grad_norm": 0.26076719295894946, "learning_rate": 3.532102174663445e-05, "loss": 0.4356, "step": 2345 }, { "epoch": 2.1881695388914766, "grad_norm": 0.28309366456316865, "learning_rate": 3.5277873662409386e-05, "loss": 0.4336, "step": 2350 }, { "epoch": 2.192827200745226, "grad_norm": 0.26367127268387425, "learning_rate": 3.523472557818433e-05, "loss": 0.4267, "step": 2355 }, { "epoch": 2.197484862598975, "grad_norm": 0.2610536840278961, "learning_rate": 3.519157749395927e-05, "loss": 0.4369, "step": 2360 }, { "epoch": 2.2021425244527246, "grad_norm": 0.2656399574271333, "learning_rate": 3.514842940973421e-05, "loss": 0.4335, "step": 2365 }, { "epoch": 2.206800186306474, "grad_norm": 0.2674019710957106, "learning_rate": 3.510528132550915e-05, "loss": 0.4378, "step": 2370 }, { "epoch": 2.2114578481602236, "grad_norm": 0.2847425846316516, "learning_rate": 3.506213324128409e-05, "loss": 0.4386, "step": 2375 }, { "epoch": 2.216115510013973, "grad_norm": 0.3029827106465256, "learning_rate": 3.501898515705903e-05, "loss": 0.4298, "step": 2380 }, { "epoch": 2.2207731718677226, "grad_norm": 0.2552519813434588, "learning_rate": 3.4975837072833964e-05, "loss": 0.4455, "step": 2385 }, { "epoch": 2.2254308337214717, "grad_norm": 0.23996443205177895, "learning_rate": 3.4932688988608906e-05, "loss": 0.4336, "step": 2390 }, { "epoch": 2.230088495575221, "grad_norm": 0.2537208048279137, "learning_rate": 3.488954090438385e-05, "loss": 0.4328, "step": 2395 }, { "epoch": 2.2347461574289706, "grad_norm": 0.27320098855250385, "learning_rate": 3.4846392820158784e-05, "loss": 0.4237, "step": 2400 }, { "epoch": 2.23940381928272, "grad_norm": 0.26102386450135995, "learning_rate": 3.480324473593373e-05, "loss": 0.4341, "step": 2405 }, { "epoch": 2.2440614811364696, "grad_norm": 0.2674347368977834, "learning_rate": 3.476009665170867e-05, "loss": 0.4331, "step": 2410 }, { "epoch": 2.248719142990219, "grad_norm": 0.268454431269816, "learning_rate": 3.4716948567483605e-05, "loss": 0.4292, "step": 2415 }, { "epoch": 2.253376804843968, "grad_norm": 0.26413421293039197, "learning_rate": 3.467380048325855e-05, "loss": 0.4169, "step": 2420 }, { "epoch": 2.2580344666977177, "grad_norm": 0.2783374741111239, "learning_rate": 3.463065239903348e-05, "loss": 0.4425, "step": 2425 }, { "epoch": 2.262692128551467, "grad_norm": 0.25257799016651605, "learning_rate": 3.458750431480842e-05, "loss": 0.4245, "step": 2430 }, { "epoch": 2.2673497904052167, "grad_norm": 0.2547696235601633, "learning_rate": 3.454435623058336e-05, "loss": 0.4336, "step": 2435 }, { "epoch": 2.272007452258966, "grad_norm": 0.2812470098078865, "learning_rate": 3.4501208146358304e-05, "loss": 0.4317, "step": 2440 }, { "epoch": 2.276665114112715, "grad_norm": 0.260924349702531, "learning_rate": 3.445806006213324e-05, "loss": 0.4301, "step": 2445 }, { "epoch": 2.2813227759664647, "grad_norm": 0.261580133602531, "learning_rate": 3.441491197790818e-05, "loss": 0.4303, "step": 2450 }, { "epoch": 2.285980437820214, "grad_norm": 0.28823094443648856, "learning_rate": 3.4371763893683125e-05, "loss": 0.4256, "step": 2455 }, { "epoch": 2.2906380996739637, "grad_norm": 0.2729954632292237, "learning_rate": 3.432861580945806e-05, "loss": 0.4224, "step": 2460 }, { "epoch": 2.295295761527713, "grad_norm": 0.26242077383593465, "learning_rate": 3.4285467725233e-05, "loss": 0.445, "step": 2465 }, { "epoch": 2.2999534233814627, "grad_norm": 0.28102983626021105, "learning_rate": 3.424231964100794e-05, "loss": 0.4352, "step": 2470 }, { "epoch": 2.3046110852352117, "grad_norm": 0.2564621840620987, "learning_rate": 3.419917155678288e-05, "loss": 0.4381, "step": 2475 }, { "epoch": 2.3092687470889612, "grad_norm": 0.2714942464902215, "learning_rate": 3.415602347255782e-05, "loss": 0.4308, "step": 2480 }, { "epoch": 2.3139264089427107, "grad_norm": 0.252628052467502, "learning_rate": 3.411287538833276e-05, "loss": 0.4433, "step": 2485 }, { "epoch": 2.3185840707964602, "grad_norm": 0.2520702622820183, "learning_rate": 3.40697273041077e-05, "loss": 0.4421, "step": 2490 }, { "epoch": 2.3232417326502097, "grad_norm": 0.26221642237477627, "learning_rate": 3.402657921988264e-05, "loss": 0.4321, "step": 2495 }, { "epoch": 2.3278993945039588, "grad_norm": 0.25979879682236756, "learning_rate": 3.398343113565758e-05, "loss": 0.4193, "step": 2500 }, { "epoch": 2.3325570563577083, "grad_norm": 0.2742819503490753, "learning_rate": 3.394028305143252e-05, "loss": 0.4306, "step": 2505 }, { "epoch": 2.3372147182114578, "grad_norm": 0.26716487556728397, "learning_rate": 3.389713496720746e-05, "loss": 0.4318, "step": 2510 }, { "epoch": 2.3418723800652073, "grad_norm": 0.26792191627546563, "learning_rate": 3.3853986882982394e-05, "loss": 0.433, "step": 2515 }, { "epoch": 2.3465300419189568, "grad_norm": 0.26545159005363334, "learning_rate": 3.381083879875734e-05, "loss": 0.4373, "step": 2520 }, { "epoch": 2.3511877037727063, "grad_norm": 0.2567660274307837, "learning_rate": 3.376769071453227e-05, "loss": 0.4341, "step": 2525 }, { "epoch": 2.3558453656264557, "grad_norm": 0.2576816392869728, "learning_rate": 3.3724542630307215e-05, "loss": 0.4336, "step": 2530 }, { "epoch": 2.360503027480205, "grad_norm": 0.25821071489227754, "learning_rate": 3.368139454608216e-05, "loss": 0.4215, "step": 2535 }, { "epoch": 2.3651606893339543, "grad_norm": 0.24312873519624179, "learning_rate": 3.363824646185709e-05, "loss": 0.4196, "step": 2540 }, { "epoch": 2.369818351187704, "grad_norm": 0.25282341243806994, "learning_rate": 3.3595098377632036e-05, "loss": 0.4351, "step": 2545 }, { "epoch": 2.3744760130414533, "grad_norm": 0.2553405908937004, "learning_rate": 3.355195029340698e-05, "loss": 0.4362, "step": 2550 }, { "epoch": 2.3791336748952028, "grad_norm": 0.2783032812907951, "learning_rate": 3.3508802209181914e-05, "loss": 0.4272, "step": 2555 }, { "epoch": 2.383791336748952, "grad_norm": 0.27377898947618523, "learning_rate": 3.346565412495685e-05, "loss": 0.4304, "step": 2560 }, { "epoch": 2.3884489986027013, "grad_norm": 0.2599072027076737, "learning_rate": 3.342250604073179e-05, "loss": 0.4331, "step": 2565 }, { "epoch": 2.393106660456451, "grad_norm": 0.260210869176159, "learning_rate": 3.3379357956506735e-05, "loss": 0.4317, "step": 2570 }, { "epoch": 2.3977643223102003, "grad_norm": 0.25196239094164763, "learning_rate": 3.333620987228167e-05, "loss": 0.4339, "step": 2575 }, { "epoch": 2.40242198416395, "grad_norm": 0.272862526082632, "learning_rate": 3.329306178805661e-05, "loss": 0.4241, "step": 2580 }, { "epoch": 2.4070796460176993, "grad_norm": 0.2612253412903384, "learning_rate": 3.3249913703831555e-05, "loss": 0.4256, "step": 2585 }, { "epoch": 2.4117373078714484, "grad_norm": 0.24373562659219036, "learning_rate": 3.320676561960649e-05, "loss": 0.4197, "step": 2590 }, { "epoch": 2.416394969725198, "grad_norm": 0.2794181137276651, "learning_rate": 3.3163617535381434e-05, "loss": 0.4398, "step": 2595 }, { "epoch": 2.4210526315789473, "grad_norm": 0.2745111242599339, "learning_rate": 3.312046945115637e-05, "loss": 0.4356, "step": 2600 }, { "epoch": 2.425710293432697, "grad_norm": 0.2723181786572597, "learning_rate": 3.3077321366931305e-05, "loss": 0.4262, "step": 2605 }, { "epoch": 2.4303679552864463, "grad_norm": 0.26855188029822885, "learning_rate": 3.303417328270625e-05, "loss": 0.4221, "step": 2610 }, { "epoch": 2.4350256171401954, "grad_norm": 0.2856930979359255, "learning_rate": 3.299102519848119e-05, "loss": 0.4253, "step": 2615 }, { "epoch": 2.439683278993945, "grad_norm": 0.2635953132443748, "learning_rate": 3.2947877114256126e-05, "loss": 0.4309, "step": 2620 }, { "epoch": 2.4443409408476944, "grad_norm": 0.256354507220247, "learning_rate": 3.290472903003107e-05, "loss": 0.4289, "step": 2625 }, { "epoch": 2.448998602701444, "grad_norm": 0.2566956971855695, "learning_rate": 3.286158094580601e-05, "loss": 0.423, "step": 2630 }, { "epoch": 2.4536562645551934, "grad_norm": 0.25000086044773284, "learning_rate": 3.281843286158095e-05, "loss": 0.4355, "step": 2635 }, { "epoch": 2.458313926408943, "grad_norm": 0.25724206722314436, "learning_rate": 3.277528477735589e-05, "loss": 0.4345, "step": 2640 }, { "epoch": 2.4629715882626924, "grad_norm": 0.2810879090653776, "learning_rate": 3.2732136693130825e-05, "loss": 0.4343, "step": 2645 }, { "epoch": 2.4676292501164414, "grad_norm": 0.24224797738734555, "learning_rate": 3.268898860890577e-05, "loss": 0.4266, "step": 2650 }, { "epoch": 2.472286911970191, "grad_norm": 0.28725952527387194, "learning_rate": 3.26458405246807e-05, "loss": 0.434, "step": 2655 }, { "epoch": 2.4769445738239404, "grad_norm": 0.2921016853541725, "learning_rate": 3.2602692440455645e-05, "loss": 0.4266, "step": 2660 }, { "epoch": 2.48160223567769, "grad_norm": 0.28722137220004484, "learning_rate": 3.255954435623059e-05, "loss": 0.4269, "step": 2665 }, { "epoch": 2.4862598975314394, "grad_norm": 0.263128959610319, "learning_rate": 3.2516396272005524e-05, "loss": 0.4337, "step": 2670 }, { "epoch": 2.4909175593851884, "grad_norm": 0.2850874080622611, "learning_rate": 3.2473248187780466e-05, "loss": 0.4247, "step": 2675 }, { "epoch": 2.495575221238938, "grad_norm": 0.2623979507634575, "learning_rate": 3.243010010355541e-05, "loss": 0.4265, "step": 2680 }, { "epoch": 2.5002328830926874, "grad_norm": 0.27921048485721145, "learning_rate": 3.2386952019330344e-05, "loss": 0.4311, "step": 2685 }, { "epoch": 2.504890544946437, "grad_norm": 0.26376677686883115, "learning_rate": 3.234380393510528e-05, "loss": 0.4169, "step": 2690 }, { "epoch": 2.5095482068001864, "grad_norm": 0.25234117142761325, "learning_rate": 3.230065585088022e-05, "loss": 0.429, "step": 2695 }, { "epoch": 2.514205868653936, "grad_norm": 0.2573830694278526, "learning_rate": 3.225750776665516e-05, "loss": 0.4238, "step": 2700 }, { "epoch": 2.5188635305076854, "grad_norm": 0.29323973710237644, "learning_rate": 3.22143596824301e-05, "loss": 0.4359, "step": 2705 }, { "epoch": 2.5235211923614345, "grad_norm": 0.3053919111708649, "learning_rate": 3.217121159820504e-05, "loss": 0.4273, "step": 2710 }, { "epoch": 2.528178854215184, "grad_norm": 0.2662391605124705, "learning_rate": 3.2128063513979986e-05, "loss": 0.4363, "step": 2715 }, { "epoch": 2.5328365160689335, "grad_norm": 0.2526338549129562, "learning_rate": 3.208491542975492e-05, "loss": 0.4468, "step": 2720 }, { "epoch": 2.537494177922683, "grad_norm": 0.24953941859083192, "learning_rate": 3.204176734552986e-05, "loss": 0.4296, "step": 2725 }, { "epoch": 2.542151839776432, "grad_norm": 0.2542094082130189, "learning_rate": 3.19986192613048e-05, "loss": 0.44, "step": 2730 }, { "epoch": 2.5468095016301815, "grad_norm": 0.26419301761320413, "learning_rate": 3.1955471177079735e-05, "loss": 0.4272, "step": 2735 }, { "epoch": 2.551467163483931, "grad_norm": 0.2654085350913693, "learning_rate": 3.191232309285468e-05, "loss": 0.4264, "step": 2740 }, { "epoch": 2.5561248253376805, "grad_norm": 0.25187495275149485, "learning_rate": 3.186917500862962e-05, "loss": 0.4256, "step": 2745 }, { "epoch": 2.56078248719143, "grad_norm": 0.2584526695806898, "learning_rate": 3.1826026924404556e-05, "loss": 0.4249, "step": 2750 }, { "epoch": 2.5654401490451795, "grad_norm": 0.25513814042866473, "learning_rate": 3.17828788401795e-05, "loss": 0.4208, "step": 2755 }, { "epoch": 2.570097810898929, "grad_norm": 0.2561720187996727, "learning_rate": 3.173973075595444e-05, "loss": 0.4331, "step": 2760 }, { "epoch": 2.574755472752678, "grad_norm": 0.24811043853849127, "learning_rate": 3.169658267172938e-05, "loss": 0.425, "step": 2765 }, { "epoch": 2.5794131346064275, "grad_norm": 0.26663061983010483, "learning_rate": 3.165343458750431e-05, "loss": 0.4271, "step": 2770 }, { "epoch": 2.584070796460177, "grad_norm": 0.24209119651760802, "learning_rate": 3.1610286503279255e-05, "loss": 0.4251, "step": 2775 }, { "epoch": 2.5887284583139265, "grad_norm": 0.25885866674625785, "learning_rate": 3.156713841905419e-05, "loss": 0.4324, "step": 2780 }, { "epoch": 2.5933861201676756, "grad_norm": 0.2527836803727701, "learning_rate": 3.152399033482913e-05, "loss": 0.4373, "step": 2785 }, { "epoch": 2.598043782021425, "grad_norm": 0.25014165858774184, "learning_rate": 3.1480842250604076e-05, "loss": 0.4381, "step": 2790 }, { "epoch": 2.6027014438751745, "grad_norm": 0.2691979070172152, "learning_rate": 3.143769416637902e-05, "loss": 0.4277, "step": 2795 }, { "epoch": 2.607359105728924, "grad_norm": 0.26539543099068236, "learning_rate": 3.1394546082153954e-05, "loss": 0.4286, "step": 2800 }, { "epoch": 2.6120167675826735, "grad_norm": 0.25024958666323965, "learning_rate": 3.13513979979289e-05, "loss": 0.4249, "step": 2805 }, { "epoch": 2.616674429436423, "grad_norm": 0.2645924840749571, "learning_rate": 3.130824991370383e-05, "loss": 0.4319, "step": 2810 }, { "epoch": 2.6213320912901725, "grad_norm": 0.24013734060096562, "learning_rate": 3.126510182947877e-05, "loss": 0.4246, "step": 2815 }, { "epoch": 2.625989753143922, "grad_norm": 0.2587662202003454, "learning_rate": 3.122195374525371e-05, "loss": 0.4363, "step": 2820 }, { "epoch": 2.630647414997671, "grad_norm": 0.2510766768465769, "learning_rate": 3.117880566102865e-05, "loss": 0.4365, "step": 2825 }, { "epoch": 2.6353050768514206, "grad_norm": 0.3012629250888138, "learning_rate": 3.113565757680359e-05, "loss": 0.4257, "step": 2830 }, { "epoch": 2.63996273870517, "grad_norm": 0.2858048883768053, "learning_rate": 3.109250949257853e-05, "loss": 0.4373, "step": 2835 }, { "epoch": 2.6446204005589196, "grad_norm": 0.2512121482382347, "learning_rate": 3.1049361408353474e-05, "loss": 0.4404, "step": 2840 }, { "epoch": 2.6492780624126686, "grad_norm": 0.26830404894529586, "learning_rate": 3.100621332412841e-05, "loss": 0.4346, "step": 2845 }, { "epoch": 2.653935724266418, "grad_norm": 0.2526518954982327, "learning_rate": 3.096306523990335e-05, "loss": 0.4357, "step": 2850 }, { "epoch": 2.6585933861201676, "grad_norm": 0.2345891892426849, "learning_rate": 3.091991715567829e-05, "loss": 0.4285, "step": 2855 }, { "epoch": 2.663251047973917, "grad_norm": 0.2620877648611118, "learning_rate": 3.0876769071453223e-05, "loss": 0.4352, "step": 2860 }, { "epoch": 2.6679087098276666, "grad_norm": 0.25516423925557496, "learning_rate": 3.0833620987228166e-05, "loss": 0.4342, "step": 2865 }, { "epoch": 2.672566371681416, "grad_norm": 0.27280945337956203, "learning_rate": 3.079047290300311e-05, "loss": 0.4258, "step": 2870 }, { "epoch": 2.6772240335351656, "grad_norm": 0.24714870131758138, "learning_rate": 3.074732481877805e-05, "loss": 0.4306, "step": 2875 }, { "epoch": 2.6818816953889146, "grad_norm": 0.2441578274584815, "learning_rate": 3.070417673455299e-05, "loss": 0.4232, "step": 2880 }, { "epoch": 2.686539357242664, "grad_norm": 0.2636144372890178, "learning_rate": 3.066102865032793e-05, "loss": 0.4408, "step": 2885 }, { "epoch": 2.6911970190964136, "grad_norm": 0.2544019775519927, "learning_rate": 3.061788056610287e-05, "loss": 0.4265, "step": 2890 }, { "epoch": 2.695854680950163, "grad_norm": 0.2921716775871019, "learning_rate": 3.057473248187781e-05, "loss": 0.4336, "step": 2895 }, { "epoch": 2.700512342803912, "grad_norm": 0.2489164544160931, "learning_rate": 3.053158439765274e-05, "loss": 0.4288, "step": 2900 }, { "epoch": 2.7051700046576617, "grad_norm": 0.24352017346282376, "learning_rate": 3.048843631342769e-05, "loss": 0.4229, "step": 2905 }, { "epoch": 2.709827666511411, "grad_norm": 0.2604807387643326, "learning_rate": 3.0445288229202625e-05, "loss": 0.4264, "step": 2910 }, { "epoch": 2.7144853283651607, "grad_norm": 0.26046537195623654, "learning_rate": 3.0402140144977564e-05, "loss": 0.4362, "step": 2915 }, { "epoch": 2.71914299021891, "grad_norm": 0.25554985498189525, "learning_rate": 3.0358992060752506e-05, "loss": 0.4268, "step": 2920 }, { "epoch": 2.7238006520726596, "grad_norm": 0.25287478911638683, "learning_rate": 3.0315843976527442e-05, "loss": 0.4402, "step": 2925 }, { "epoch": 2.728458313926409, "grad_norm": 0.23770234642998606, "learning_rate": 3.027269589230238e-05, "loss": 0.439, "step": 2930 }, { "epoch": 2.7331159757801586, "grad_norm": 0.24119306770336316, "learning_rate": 3.0229547808077324e-05, "loss": 0.4272, "step": 2935 }, { "epoch": 2.7377736376339077, "grad_norm": 0.2517641620498618, "learning_rate": 3.018639972385226e-05, "loss": 0.4275, "step": 2940 }, { "epoch": 2.742431299487657, "grad_norm": 0.25468761922213756, "learning_rate": 3.0143251639627202e-05, "loss": 0.4365, "step": 2945 }, { "epoch": 2.7470889613414067, "grad_norm": 0.27014798245613814, "learning_rate": 3.010010355540214e-05, "loss": 0.4277, "step": 2950 }, { "epoch": 2.751746623195156, "grad_norm": 0.2738329846778614, "learning_rate": 3.0056955471177077e-05, "loss": 0.425, "step": 2955 }, { "epoch": 2.7564042850489052, "grad_norm": 0.2615697522909756, "learning_rate": 3.001380738695202e-05, "loss": 0.4306, "step": 2960 }, { "epoch": 2.7610619469026547, "grad_norm": 0.2616747841853829, "learning_rate": 2.9970659302726962e-05, "loss": 0.4296, "step": 2965 }, { "epoch": 2.765719608756404, "grad_norm": 0.2780172592243042, "learning_rate": 2.99275112185019e-05, "loss": 0.4311, "step": 2970 }, { "epoch": 2.7703772706101537, "grad_norm": 0.25828687459886684, "learning_rate": 2.9884363134276837e-05, "loss": 0.4238, "step": 2975 }, { "epoch": 2.775034932463903, "grad_norm": 0.2587975925905609, "learning_rate": 2.984121505005178e-05, "loss": 0.425, "step": 2980 }, { "epoch": 2.7796925943176527, "grad_norm": 0.2745949765324412, "learning_rate": 2.979806696582672e-05, "loss": 0.4354, "step": 2985 }, { "epoch": 2.784350256171402, "grad_norm": 0.2413980752981667, "learning_rate": 2.9754918881601657e-05, "loss": 0.4278, "step": 2990 }, { "epoch": 2.7890079180251512, "grad_norm": 0.2550452204371712, "learning_rate": 2.9711770797376596e-05, "loss": 0.4253, "step": 2995 }, { "epoch": 2.7936655798789007, "grad_norm": 0.26211376186850915, "learning_rate": 2.966862271315154e-05, "loss": 0.4372, "step": 3000 }, { "epoch": 2.7983232417326502, "grad_norm": 0.234740078489774, "learning_rate": 2.9625474628926475e-05, "loss": 0.4231, "step": 3005 }, { "epoch": 2.8029809035863997, "grad_norm": 0.24595561670192548, "learning_rate": 2.9582326544701417e-05, "loss": 0.4388, "step": 3010 }, { "epoch": 2.807638565440149, "grad_norm": 0.25096281166381534, "learning_rate": 2.9539178460476356e-05, "loss": 0.4156, "step": 3015 }, { "epoch": 2.8122962272938983, "grad_norm": 0.25633255338774125, "learning_rate": 2.9496030376251292e-05, "loss": 0.4332, "step": 3020 }, { "epoch": 2.8169538891476478, "grad_norm": 0.2593321484988308, "learning_rate": 2.9452882292026235e-05, "loss": 0.4298, "step": 3025 }, { "epoch": 2.8216115510013973, "grad_norm": 0.25982501766827676, "learning_rate": 2.9409734207801177e-05, "loss": 0.4302, "step": 3030 }, { "epoch": 2.8262692128551468, "grad_norm": 0.2685093685632085, "learning_rate": 2.9366586123576113e-05, "loss": 0.4327, "step": 3035 }, { "epoch": 2.8309268747088963, "grad_norm": 0.2706984385371921, "learning_rate": 2.9323438039351052e-05, "loss": 0.4417, "step": 3040 }, { "epoch": 2.8355845365626458, "grad_norm": 0.23478222223240322, "learning_rate": 2.9280289955125994e-05, "loss": 0.4283, "step": 3045 }, { "epoch": 2.840242198416395, "grad_norm": 0.25161201150892354, "learning_rate": 2.9237141870900937e-05, "loss": 0.4331, "step": 3050 }, { "epoch": 2.8448998602701443, "grad_norm": 0.267503025278117, "learning_rate": 2.9193993786675873e-05, "loss": 0.4354, "step": 3055 }, { "epoch": 2.849557522123894, "grad_norm": 0.25753801698486606, "learning_rate": 2.9150845702450812e-05, "loss": 0.4366, "step": 3060 }, { "epoch": 2.8542151839776433, "grad_norm": 0.2600382024905236, "learning_rate": 2.9107697618225754e-05, "loss": 0.4307, "step": 3065 }, { "epoch": 2.858872845831393, "grad_norm": 0.2472748253347587, "learning_rate": 2.906454953400069e-05, "loss": 0.4208, "step": 3070 }, { "epoch": 2.863530507685142, "grad_norm": 0.25817323530945246, "learning_rate": 2.9021401449775632e-05, "loss": 0.4315, "step": 3075 }, { "epoch": 2.8681881695388913, "grad_norm": 0.2484467256888752, "learning_rate": 2.897825336555057e-05, "loss": 0.4203, "step": 3080 }, { "epoch": 2.872845831392641, "grad_norm": 0.24016575511510896, "learning_rate": 2.8935105281325507e-05, "loss": 0.4318, "step": 3085 }, { "epoch": 2.8775034932463903, "grad_norm": 0.24816329257695519, "learning_rate": 2.889195719710045e-05, "loss": 0.4368, "step": 3090 }, { "epoch": 2.88216115510014, "grad_norm": 0.2626027030727546, "learning_rate": 2.8848809112875392e-05, "loss": 0.4229, "step": 3095 }, { "epoch": 2.8868188169538893, "grad_norm": 0.2499976816509292, "learning_rate": 2.8805661028650328e-05, "loss": 0.4307, "step": 3100 }, { "epoch": 2.891476478807639, "grad_norm": 0.24794945856706246, "learning_rate": 2.8762512944425267e-05, "loss": 0.4366, "step": 3105 }, { "epoch": 2.896134140661388, "grad_norm": 0.2475191944997728, "learning_rate": 2.871936486020021e-05, "loss": 0.4241, "step": 3110 }, { "epoch": 2.9007918025151374, "grad_norm": 0.25722789909799715, "learning_rate": 2.8676216775975145e-05, "loss": 0.4197, "step": 3115 }, { "epoch": 2.905449464368887, "grad_norm": 0.26074399102308204, "learning_rate": 2.8633068691750088e-05, "loss": 0.4286, "step": 3120 }, { "epoch": 2.9101071262226363, "grad_norm": 0.2421933959585582, "learning_rate": 2.8589920607525027e-05, "loss": 0.4349, "step": 3125 }, { "epoch": 2.9147647880763854, "grad_norm": 0.23293995856070393, "learning_rate": 2.854677252329997e-05, "loss": 0.4168, "step": 3130 }, { "epoch": 2.919422449930135, "grad_norm": 0.25539969196653156, "learning_rate": 2.8503624439074905e-05, "loss": 0.4226, "step": 3135 }, { "epoch": 2.9240801117838844, "grad_norm": 0.23291903261083885, "learning_rate": 2.8460476354849848e-05, "loss": 0.4358, "step": 3140 }, { "epoch": 2.928737773637634, "grad_norm": 0.2410617869811893, "learning_rate": 2.8417328270624787e-05, "loss": 0.4385, "step": 3145 }, { "epoch": 2.9333954354913834, "grad_norm": 0.25751473595376734, "learning_rate": 2.8374180186399723e-05, "loss": 0.4356, "step": 3150 }, { "epoch": 2.938053097345133, "grad_norm": 0.2935306468715078, "learning_rate": 2.8331032102174665e-05, "loss": 0.4198, "step": 3155 }, { "epoch": 2.9427107591988824, "grad_norm": 0.2533808215991353, "learning_rate": 2.8287884017949608e-05, "loss": 0.4324, "step": 3160 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2387442330943504, "learning_rate": 2.8244735933724543e-05, "loss": 0.4327, "step": 3165 }, { "epoch": 2.952026082906381, "grad_norm": 0.2380208417237493, "learning_rate": 2.8201587849499482e-05, "loss": 0.4294, "step": 3170 }, { "epoch": 2.9566837447601304, "grad_norm": 0.24087912113306323, "learning_rate": 2.8158439765274425e-05, "loss": 0.4342, "step": 3175 }, { "epoch": 2.96134140661388, "grad_norm": 0.2514392283052296, "learning_rate": 2.811529168104936e-05, "loss": 0.4254, "step": 3180 }, { "epoch": 2.9659990684676294, "grad_norm": 0.26464801124401477, "learning_rate": 2.8072143596824303e-05, "loss": 0.4305, "step": 3185 }, { "epoch": 2.9706567303213784, "grad_norm": 0.24219760482258892, "learning_rate": 2.8028995512599242e-05, "loss": 0.4194, "step": 3190 }, { "epoch": 2.975314392175128, "grad_norm": 0.25508215324035977, "learning_rate": 2.7985847428374178e-05, "loss": 0.4364, "step": 3195 }, { "epoch": 2.9799720540288774, "grad_norm": 0.2557778421552533, "learning_rate": 2.794269934414912e-05, "loss": 0.4338, "step": 3200 }, { "epoch": 2.984629715882627, "grad_norm": 0.26074836029614396, "learning_rate": 2.7899551259924063e-05, "loss": 0.4402, "step": 3205 }, { "epoch": 2.9892873777363764, "grad_norm": 0.24786721104566684, "learning_rate": 2.7856403175699002e-05, "loss": 0.4128, "step": 3210 }, { "epoch": 2.993945039590126, "grad_norm": 0.23741365663032332, "learning_rate": 2.7813255091473938e-05, "loss": 0.4138, "step": 3215 }, { "epoch": 2.9986027014438754, "grad_norm": 0.2536866892954683, "learning_rate": 2.777010700724888e-05, "loss": 0.4338, "step": 3220 }, { "epoch": 3.0027945971122496, "grad_norm": 0.2850426396287805, "learning_rate": 2.7726958923023823e-05, "loss": 0.3965, "step": 3225 }, { "epoch": 3.007452258965999, "grad_norm": 0.3029671500755888, "learning_rate": 2.768381083879876e-05, "loss": 0.3818, "step": 3230 }, { "epoch": 3.0121099208197486, "grad_norm": 0.2620239643057931, "learning_rate": 2.7640662754573698e-05, "loss": 0.3866, "step": 3235 }, { "epoch": 3.016767582673498, "grad_norm": 0.261858169998403, "learning_rate": 2.759751467034864e-05, "loss": 0.3753, "step": 3240 }, { "epoch": 3.021425244527247, "grad_norm": 0.26318970273700987, "learning_rate": 2.7554366586123576e-05, "loss": 0.3852, "step": 3245 }, { "epoch": 3.0260829063809966, "grad_norm": 0.25295694011942804, "learning_rate": 2.751121850189852e-05, "loss": 0.3868, "step": 3250 }, { "epoch": 3.030740568234746, "grad_norm": 0.2575910449412991, "learning_rate": 2.7468070417673457e-05, "loss": 0.3885, "step": 3255 }, { "epoch": 3.0353982300884956, "grad_norm": 0.2568550074590964, "learning_rate": 2.7424922333448393e-05, "loss": 0.3893, "step": 3260 }, { "epoch": 3.040055891942245, "grad_norm": 0.2804582844844359, "learning_rate": 2.7381774249223336e-05, "loss": 0.3917, "step": 3265 }, { "epoch": 3.0447135537959946, "grad_norm": 0.27843743097731594, "learning_rate": 2.7338626164998278e-05, "loss": 0.3801, "step": 3270 }, { "epoch": 3.0493712156497437, "grad_norm": 0.255962500269876, "learning_rate": 2.7295478080773214e-05, "loss": 0.3859, "step": 3275 }, { "epoch": 3.054028877503493, "grad_norm": 0.25305462648666593, "learning_rate": 2.7252329996548153e-05, "loss": 0.3796, "step": 3280 }, { "epoch": 3.0586865393572427, "grad_norm": 0.2698990291377143, "learning_rate": 2.7209181912323096e-05, "loss": 0.3978, "step": 3285 }, { "epoch": 3.063344201210992, "grad_norm": 0.26847519400149733, "learning_rate": 2.7166033828098038e-05, "loss": 0.3839, "step": 3290 }, { "epoch": 3.0680018630647417, "grad_norm": 0.25655165832155463, "learning_rate": 2.7122885743872974e-05, "loss": 0.3888, "step": 3295 }, { "epoch": 3.0726595249184907, "grad_norm": 0.2656256849713492, "learning_rate": 2.7079737659647913e-05, "loss": 0.3813, "step": 3300 }, { "epoch": 3.07731718677224, "grad_norm": 0.26706787964729345, "learning_rate": 2.7036589575422855e-05, "loss": 0.379, "step": 3305 }, { "epoch": 3.0819748486259897, "grad_norm": 0.262938944863919, "learning_rate": 2.699344149119779e-05, "loss": 0.3837, "step": 3310 }, { "epoch": 3.086632510479739, "grad_norm": 0.24623376098845876, "learning_rate": 2.6950293406972734e-05, "loss": 0.3806, "step": 3315 }, { "epoch": 3.0912901723334887, "grad_norm": 0.2465075578715643, "learning_rate": 2.6907145322747673e-05, "loss": 0.3744, "step": 3320 }, { "epoch": 3.095947834187238, "grad_norm": 0.24853994481057223, "learning_rate": 2.686399723852261e-05, "loss": 0.3925, "step": 3325 }, { "epoch": 3.1006054960409872, "grad_norm": 0.2702015767429184, "learning_rate": 2.682084915429755e-05, "loss": 0.3861, "step": 3330 }, { "epoch": 3.1052631578947367, "grad_norm": 0.28638131368057346, "learning_rate": 2.677770107007249e-05, "loss": 0.3813, "step": 3335 }, { "epoch": 3.109920819748486, "grad_norm": 0.26700269706754914, "learning_rate": 2.673455298584743e-05, "loss": 0.3794, "step": 3340 }, { "epoch": 3.1145784816022357, "grad_norm": 0.2656263235869519, "learning_rate": 2.6691404901622368e-05, "loss": 0.3862, "step": 3345 }, { "epoch": 3.119236143455985, "grad_norm": 0.27023267868765766, "learning_rate": 2.664825681739731e-05, "loss": 0.4005, "step": 3350 }, { "epoch": 3.1238938053097347, "grad_norm": 0.2471096010321038, "learning_rate": 2.6605108733172247e-05, "loss": 0.3865, "step": 3355 }, { "epoch": 3.1285514671634838, "grad_norm": 0.28322504731765796, "learning_rate": 2.6561960648947186e-05, "loss": 0.3858, "step": 3360 }, { "epoch": 3.1332091290172333, "grad_norm": 0.26176114979929954, "learning_rate": 2.6518812564722128e-05, "loss": 0.3925, "step": 3365 }, { "epoch": 3.1378667908709827, "grad_norm": 0.24761004035973244, "learning_rate": 2.647566448049707e-05, "loss": 0.3878, "step": 3370 }, { "epoch": 3.1425244527247322, "grad_norm": 0.25855644758327995, "learning_rate": 2.6432516396272006e-05, "loss": 0.3873, "step": 3375 }, { "epoch": 3.1471821145784817, "grad_norm": 0.23795343594172358, "learning_rate": 2.6389368312046945e-05, "loss": 0.3858, "step": 3380 }, { "epoch": 3.1518397764322312, "grad_norm": 0.24758092557409284, "learning_rate": 2.6346220227821888e-05, "loss": 0.3844, "step": 3385 }, { "epoch": 3.1564974382859803, "grad_norm": 0.25912228808757465, "learning_rate": 2.6303072143596824e-05, "loss": 0.39, "step": 3390 }, { "epoch": 3.16115510013973, "grad_norm": 0.2504846983115132, "learning_rate": 2.6259924059371766e-05, "loss": 0.3805, "step": 3395 }, { "epoch": 3.1658127619934793, "grad_norm": 0.2648802072379492, "learning_rate": 2.6216775975146705e-05, "loss": 0.3896, "step": 3400 }, { "epoch": 3.1704704238472288, "grad_norm": 0.2522254944799055, "learning_rate": 2.617362789092164e-05, "loss": 0.3925, "step": 3405 }, { "epoch": 3.1751280857009783, "grad_norm": 0.27212922354414304, "learning_rate": 2.6130479806696584e-05, "loss": 0.3981, "step": 3410 }, { "epoch": 3.1797857475547273, "grad_norm": 0.26122638974618656, "learning_rate": 2.6087331722471526e-05, "loss": 0.383, "step": 3415 }, { "epoch": 3.184443409408477, "grad_norm": 0.2868408852177913, "learning_rate": 2.6044183638246462e-05, "loss": 0.3976, "step": 3420 }, { "epoch": 3.1891010712622263, "grad_norm": 0.26690811636849704, "learning_rate": 2.60010355540214e-05, "loss": 0.3866, "step": 3425 }, { "epoch": 3.193758733115976, "grad_norm": 0.27046300814732926, "learning_rate": 2.5957887469796343e-05, "loss": 0.3992, "step": 3430 }, { "epoch": 3.1984163949697253, "grad_norm": 0.26670636988151436, "learning_rate": 2.591473938557128e-05, "loss": 0.3959, "step": 3435 }, { "epoch": 3.203074056823475, "grad_norm": 0.27760414588312937, "learning_rate": 2.587159130134622e-05, "loss": 0.3927, "step": 3440 }, { "epoch": 3.207731718677224, "grad_norm": 0.2759978737605295, "learning_rate": 2.582844321712116e-05, "loss": 0.3806, "step": 3445 }, { "epoch": 3.2123893805309733, "grad_norm": 0.2559078708749848, "learning_rate": 2.5785295132896096e-05, "loss": 0.389, "step": 3450 }, { "epoch": 3.217047042384723, "grad_norm": 0.2719562663392501, "learning_rate": 2.574214704867104e-05, "loss": 0.3929, "step": 3455 }, { "epoch": 3.2217047042384723, "grad_norm": 0.27377329451882454, "learning_rate": 2.569899896444598e-05, "loss": 0.3908, "step": 3460 }, { "epoch": 3.226362366092222, "grad_norm": 0.2656753150911727, "learning_rate": 2.565585088022092e-05, "loss": 0.3862, "step": 3465 }, { "epoch": 3.2310200279459713, "grad_norm": 0.2575945083497491, "learning_rate": 2.5612702795995856e-05, "loss": 0.3928, "step": 3470 }, { "epoch": 3.2356776897997204, "grad_norm": 0.26658523635601905, "learning_rate": 2.55695547117708e-05, "loss": 0.3857, "step": 3475 }, { "epoch": 3.24033535165347, "grad_norm": 0.24615064865653052, "learning_rate": 2.552640662754574e-05, "loss": 0.3913, "step": 3480 }, { "epoch": 3.2449930135072194, "grad_norm": 0.2549986080619571, "learning_rate": 2.5483258543320677e-05, "loss": 0.4009, "step": 3485 }, { "epoch": 3.249650675360969, "grad_norm": 0.27396948956495615, "learning_rate": 2.5440110459095616e-05, "loss": 0.4043, "step": 3490 }, { "epoch": 3.2543083372147183, "grad_norm": 0.2696818524601873, "learning_rate": 2.539696237487056e-05, "loss": 0.402, "step": 3495 }, { "epoch": 3.258965999068468, "grad_norm": 0.27558712104733646, "learning_rate": 2.5353814290645494e-05, "loss": 0.4002, "step": 3500 }, { "epoch": 3.263623660922217, "grad_norm": 0.24631587826142518, "learning_rate": 2.5310666206420437e-05, "loss": 0.403, "step": 3505 }, { "epoch": 3.2682813227759664, "grad_norm": 0.2600931259787659, "learning_rate": 2.5267518122195376e-05, "loss": 0.4024, "step": 3510 }, { "epoch": 3.272938984629716, "grad_norm": 0.2662929244792879, "learning_rate": 2.5224370037970312e-05, "loss": 0.3957, "step": 3515 }, { "epoch": 3.2775966464834654, "grad_norm": 0.2546912550062893, "learning_rate": 2.5181221953745254e-05, "loss": 0.3937, "step": 3520 }, { "epoch": 3.282254308337215, "grad_norm": 0.2844412888231005, "learning_rate": 2.5138073869520197e-05, "loss": 0.4092, "step": 3525 }, { "epoch": 3.286911970190964, "grad_norm": 0.24913765812797214, "learning_rate": 2.5094925785295132e-05, "loss": 0.3836, "step": 3530 }, { "epoch": 3.2915696320447134, "grad_norm": 0.25901378015758547, "learning_rate": 2.505177770107007e-05, "loss": 0.3823, "step": 3535 }, { "epoch": 3.296227293898463, "grad_norm": 0.26699752111045466, "learning_rate": 2.5008629616845014e-05, "loss": 0.3863, "step": 3540 }, { "epoch": 3.3008849557522124, "grad_norm": 0.2551485219499295, "learning_rate": 2.4965481532619953e-05, "loss": 0.3954, "step": 3545 }, { "epoch": 3.305542617605962, "grad_norm": 0.25436510840724635, "learning_rate": 2.4922333448394892e-05, "loss": 0.3889, "step": 3550 }, { "epoch": 3.3102002794597114, "grad_norm": 0.27132034931800814, "learning_rate": 2.487918536416983e-05, "loss": 0.3807, "step": 3555 }, { "epoch": 3.3148579413134605, "grad_norm": 0.2570286437391233, "learning_rate": 2.483603727994477e-05, "loss": 0.3908, "step": 3560 }, { "epoch": 3.31951560316721, "grad_norm": 0.2865463918576976, "learning_rate": 2.4792889195719713e-05, "loss": 0.3912, "step": 3565 }, { "epoch": 3.3241732650209594, "grad_norm": 0.2691275079149316, "learning_rate": 2.4749741111494652e-05, "loss": 0.3865, "step": 3570 }, { "epoch": 3.328830926874709, "grad_norm": 0.3056593465681156, "learning_rate": 2.4706593027269588e-05, "loss": 0.3982, "step": 3575 }, { "epoch": 3.3334885887284584, "grad_norm": 0.27363696073911653, "learning_rate": 2.466344494304453e-05, "loss": 0.3931, "step": 3580 }, { "epoch": 3.3381462505822075, "grad_norm": 0.27465668380758373, "learning_rate": 2.462029685881947e-05, "loss": 0.3957, "step": 3585 }, { "epoch": 3.342803912435957, "grad_norm": 0.26137957176793936, "learning_rate": 2.457714877459441e-05, "loss": 0.3877, "step": 3590 }, { "epoch": 3.3474615742897065, "grad_norm": 0.25548315606716654, "learning_rate": 2.4534000690369348e-05, "loss": 0.3867, "step": 3595 }, { "epoch": 3.352119236143456, "grad_norm": 0.2758170214985089, "learning_rate": 2.4490852606144287e-05, "loss": 0.388, "step": 3600 }, { "epoch": 3.3567768979972055, "grad_norm": 0.2670053184496206, "learning_rate": 2.444770452191923e-05, "loss": 0.3797, "step": 3605 }, { "epoch": 3.361434559850955, "grad_norm": 0.24909958084102465, "learning_rate": 2.440455643769417e-05, "loss": 0.3908, "step": 3610 }, { "epoch": 3.3660922217047045, "grad_norm": 0.27068048595447425, "learning_rate": 2.4361408353469108e-05, "loss": 0.387, "step": 3615 }, { "epoch": 3.3707498835584535, "grad_norm": 0.24352527826474507, "learning_rate": 2.4318260269244047e-05, "loss": 0.388, "step": 3620 }, { "epoch": 3.375407545412203, "grad_norm": 0.2519548028233095, "learning_rate": 2.4275112185018986e-05, "loss": 0.397, "step": 3625 }, { "epoch": 3.3800652072659525, "grad_norm": 0.27142523648971983, "learning_rate": 2.4231964100793925e-05, "loss": 0.39, "step": 3630 }, { "epoch": 3.384722869119702, "grad_norm": 0.2432948271205881, "learning_rate": 2.4188816016568867e-05, "loss": 0.4005, "step": 3635 }, { "epoch": 3.3893805309734515, "grad_norm": 0.2479793845698093, "learning_rate": 2.4145667932343803e-05, "loss": 0.3773, "step": 3640 }, { "epoch": 3.3940381928272005, "grad_norm": 0.2596053646448, "learning_rate": 2.4102519848118746e-05, "loss": 0.393, "step": 3645 }, { "epoch": 3.39869585468095, "grad_norm": 0.24002381843625598, "learning_rate": 2.4059371763893685e-05, "loss": 0.383, "step": 3650 }, { "epoch": 3.4033535165346995, "grad_norm": 0.25334616181521774, "learning_rate": 2.4016223679668624e-05, "loss": 0.3999, "step": 3655 }, { "epoch": 3.408011178388449, "grad_norm": 0.2588954253115573, "learning_rate": 2.3973075595443563e-05, "loss": 0.3845, "step": 3660 }, { "epoch": 3.4126688402421985, "grad_norm": 0.2573902613839303, "learning_rate": 2.3929927511218502e-05, "loss": 0.385, "step": 3665 }, { "epoch": 3.417326502095948, "grad_norm": 0.2578597664718883, "learning_rate": 2.388677942699344e-05, "loss": 0.4, "step": 3670 }, { "epoch": 3.421984163949697, "grad_norm": 0.25994921289075856, "learning_rate": 2.3843631342768384e-05, "loss": 0.3871, "step": 3675 }, { "epoch": 3.4266418258034466, "grad_norm": 0.2559593209747011, "learning_rate": 2.3800483258543323e-05, "loss": 0.3792, "step": 3680 }, { "epoch": 3.431299487657196, "grad_norm": 0.2572197743564571, "learning_rate": 2.3757335174318262e-05, "loss": 0.3949, "step": 3685 }, { "epoch": 3.4359571495109456, "grad_norm": 0.2660142459311976, "learning_rate": 2.37141870900932e-05, "loss": 0.3862, "step": 3690 }, { "epoch": 3.440614811364695, "grad_norm": 0.28887966840704243, "learning_rate": 2.367103900586814e-05, "loss": 0.3896, "step": 3695 }, { "epoch": 3.445272473218444, "grad_norm": 0.2564794754358609, "learning_rate": 2.3627890921643083e-05, "loss": 0.3976, "step": 3700 }, { "epoch": 3.4499301350721936, "grad_norm": 0.2577705090187694, "learning_rate": 2.358474283741802e-05, "loss": 0.3998, "step": 3705 }, { "epoch": 3.454587796925943, "grad_norm": 0.2674455807765323, "learning_rate": 2.3541594753192957e-05, "loss": 0.3951, "step": 3710 }, { "epoch": 3.4592454587796926, "grad_norm": 0.2585556155609789, "learning_rate": 2.34984466689679e-05, "loss": 0.3846, "step": 3715 }, { "epoch": 3.463903120633442, "grad_norm": 0.26962358138653486, "learning_rate": 2.345529858474284e-05, "loss": 0.3884, "step": 3720 }, { "epoch": 3.4685607824871916, "grad_norm": 0.2648664682136359, "learning_rate": 2.3412150500517778e-05, "loss": 0.398, "step": 3725 }, { "epoch": 3.473218444340941, "grad_norm": 0.25648233746672777, "learning_rate": 2.3369002416292717e-05, "loss": 0.3935, "step": 3730 }, { "epoch": 3.47787610619469, "grad_norm": 0.24932165713084561, "learning_rate": 2.3325854332067656e-05, "loss": 0.3971, "step": 3735 }, { "epoch": 3.4825337680484396, "grad_norm": 0.26222640082720006, "learning_rate": 2.32827062478426e-05, "loss": 0.3875, "step": 3740 }, { "epoch": 3.487191429902189, "grad_norm": 0.24941076877169988, "learning_rate": 2.3239558163617538e-05, "loss": 0.3923, "step": 3745 }, { "epoch": 3.4918490917559386, "grad_norm": 0.26335788367214463, "learning_rate": 2.3196410079392474e-05, "loss": 0.3968, "step": 3750 }, { "epoch": 3.496506753609688, "grad_norm": 0.25045257367936463, "learning_rate": 2.3153261995167416e-05, "loss": 0.393, "step": 3755 }, { "epoch": 3.501164415463437, "grad_norm": 0.2732756024737759, "learning_rate": 2.3110113910942355e-05, "loss": 0.3906, "step": 3760 }, { "epoch": 3.5058220773171866, "grad_norm": 0.2634237847638818, "learning_rate": 2.3066965826717294e-05, "loss": 0.3836, "step": 3765 }, { "epoch": 3.510479739170936, "grad_norm": 0.27710985052241993, "learning_rate": 2.3023817742492234e-05, "loss": 0.3969, "step": 3770 }, { "epoch": 3.5151374010246856, "grad_norm": 0.23978318024726392, "learning_rate": 2.2980669658267173e-05, "loss": 0.3856, "step": 3775 }, { "epoch": 3.519795062878435, "grad_norm": 0.24325823478512942, "learning_rate": 2.2937521574042115e-05, "loss": 0.375, "step": 3780 }, { "epoch": 3.5244527247321846, "grad_norm": 0.2575769211804813, "learning_rate": 2.2894373489817054e-05, "loss": 0.3955, "step": 3785 }, { "epoch": 3.529110386585934, "grad_norm": 0.24893572682038842, "learning_rate": 2.285122540559199e-05, "loss": 0.389, "step": 3790 }, { "epoch": 3.533768048439683, "grad_norm": 0.2692260516805509, "learning_rate": 2.2808077321366933e-05, "loss": 0.3856, "step": 3795 }, { "epoch": 3.5384257102934327, "grad_norm": 0.24374782497732958, "learning_rate": 2.276492923714187e-05, "loss": 0.3985, "step": 3800 }, { "epoch": 3.543083372147182, "grad_norm": 0.2560735447436802, "learning_rate": 2.2721781152916814e-05, "loss": 0.4045, "step": 3805 }, { "epoch": 3.5477410340009317, "grad_norm": 0.2539388113725351, "learning_rate": 2.267863306869175e-05, "loss": 0.397, "step": 3810 }, { "epoch": 3.5523986958546807, "grad_norm": 0.2392510071720218, "learning_rate": 2.263548498446669e-05, "loss": 0.3953, "step": 3815 }, { "epoch": 3.55705635770843, "grad_norm": 0.25099690929470503, "learning_rate": 2.259233690024163e-05, "loss": 0.3861, "step": 3820 }, { "epoch": 3.5617140195621797, "grad_norm": 0.25789019280464376, "learning_rate": 2.254918881601657e-05, "loss": 0.401, "step": 3825 }, { "epoch": 3.566371681415929, "grad_norm": 0.2494228818292851, "learning_rate": 2.250604073179151e-05, "loss": 0.394, "step": 3830 }, { "epoch": 3.5710293432696787, "grad_norm": 0.23868009264109472, "learning_rate": 2.246289264756645e-05, "loss": 0.3977, "step": 3835 }, { "epoch": 3.575687005123428, "grad_norm": 0.25099787753121583, "learning_rate": 2.2419744563341388e-05, "loss": 0.3909, "step": 3840 }, { "epoch": 3.5803446669771777, "grad_norm": 0.25007381719660315, "learning_rate": 2.237659647911633e-05, "loss": 0.3856, "step": 3845 }, { "epoch": 3.5850023288309267, "grad_norm": 0.2511976351350397, "learning_rate": 2.233344839489127e-05, "loss": 0.3918, "step": 3850 }, { "epoch": 3.5896599906846762, "grad_norm": 0.2516701392987979, "learning_rate": 2.2290300310666205e-05, "loss": 0.4011, "step": 3855 }, { "epoch": 3.5943176525384257, "grad_norm": 0.2519931092649134, "learning_rate": 2.2247152226441148e-05, "loss": 0.3928, "step": 3860 }, { "epoch": 3.598975314392175, "grad_norm": 0.2733375851735107, "learning_rate": 2.2204004142216087e-05, "loss": 0.399, "step": 3865 }, { "epoch": 3.6036329762459243, "grad_norm": 0.24413513064949421, "learning_rate": 2.2160856057991026e-05, "loss": 0.394, "step": 3870 }, { "epoch": 3.6082906380996738, "grad_norm": 0.26264035661118207, "learning_rate": 2.2117707973765965e-05, "loss": 0.3939, "step": 3875 }, { "epoch": 3.6129482999534233, "grad_norm": 0.25286563512081883, "learning_rate": 2.2074559889540904e-05, "loss": 0.3965, "step": 3880 }, { "epoch": 3.6176059618071728, "grad_norm": 0.25021435845115786, "learning_rate": 2.2031411805315847e-05, "loss": 0.3903, "step": 3885 }, { "epoch": 3.6222636236609222, "grad_norm": 0.23906170104577193, "learning_rate": 2.1988263721090786e-05, "loss": 0.3906, "step": 3890 }, { "epoch": 3.6269212855146717, "grad_norm": 0.25713146172155743, "learning_rate": 2.1945115636865725e-05, "loss": 0.394, "step": 3895 }, { "epoch": 3.6315789473684212, "grad_norm": 0.24800699927444764, "learning_rate": 2.1901967552640664e-05, "loss": 0.3801, "step": 3900 }, { "epoch": 3.6362366092221707, "grad_norm": 0.24782122047655403, "learning_rate": 2.1858819468415603e-05, "loss": 0.4009, "step": 3905 }, { "epoch": 3.64089427107592, "grad_norm": 0.2597691135897313, "learning_rate": 2.1815671384190542e-05, "loss": 0.3908, "step": 3910 }, { "epoch": 3.6455519329296693, "grad_norm": 0.24337001249729273, "learning_rate": 2.1772523299965485e-05, "loss": 0.3958, "step": 3915 }, { "epoch": 3.6502095947834188, "grad_norm": 0.23934462265348078, "learning_rate": 2.172937521574042e-05, "loss": 0.3851, "step": 3920 }, { "epoch": 3.6548672566371683, "grad_norm": 0.23907248790044563, "learning_rate": 2.1686227131515363e-05, "loss": 0.3732, "step": 3925 }, { "epoch": 3.6595249184909173, "grad_norm": 0.24011701610129518, "learning_rate": 2.1643079047290302e-05, "loss": 0.3918, "step": 3930 }, { "epoch": 3.664182580344667, "grad_norm": 0.25611912623170535, "learning_rate": 2.159993096306524e-05, "loss": 0.3903, "step": 3935 }, { "epoch": 3.6688402421984163, "grad_norm": 0.2497213213702731, "learning_rate": 2.155678287884018e-05, "loss": 0.3926, "step": 3940 }, { "epoch": 3.673497904052166, "grad_norm": 0.24612399124179193, "learning_rate": 2.151363479461512e-05, "loss": 0.3896, "step": 3945 }, { "epoch": 3.6781555659059153, "grad_norm": 0.25298920948804704, "learning_rate": 2.147048671039006e-05, "loss": 0.3824, "step": 3950 }, { "epoch": 3.682813227759665, "grad_norm": 0.228204207433831, "learning_rate": 2.1427338626165e-05, "loss": 0.396, "step": 3955 }, { "epoch": 3.6874708896134143, "grad_norm": 0.26293116399183375, "learning_rate": 2.1384190541939937e-05, "loss": 0.3979, "step": 3960 }, { "epoch": 3.6921285514671633, "grad_norm": 0.25362659390052195, "learning_rate": 2.134104245771488e-05, "loss": 0.3907, "step": 3965 }, { "epoch": 3.696786213320913, "grad_norm": 0.24096853968582052, "learning_rate": 2.129789437348982e-05, "loss": 0.3998, "step": 3970 }, { "epoch": 3.7014438751746623, "grad_norm": 0.24635715529101504, "learning_rate": 2.1254746289264758e-05, "loss": 0.3801, "step": 3975 }, { "epoch": 3.706101537028412, "grad_norm": 0.2709393810967093, "learning_rate": 2.1211598205039697e-05, "loss": 0.3865, "step": 3980 }, { "epoch": 3.710759198882161, "grad_norm": 0.2416679809516335, "learning_rate": 2.1168450120814636e-05, "loss": 0.4059, "step": 3985 }, { "epoch": 3.7154168607359104, "grad_norm": 0.26083343223894645, "learning_rate": 2.1125302036589575e-05, "loss": 0.3925, "step": 3990 }, { "epoch": 3.72007452258966, "grad_norm": 0.24250045728162495, "learning_rate": 2.1082153952364517e-05, "loss": 0.3869, "step": 3995 }, { "epoch": 3.7247321844434094, "grad_norm": 0.2507095996898488, "learning_rate": 2.1039005868139457e-05, "loss": 0.3911, "step": 4000 }, { "epoch": 3.729389846297159, "grad_norm": 0.25179011811639973, "learning_rate": 2.0995857783914392e-05, "loss": 0.391, "step": 4005 }, { "epoch": 3.7340475081509084, "grad_norm": 0.2661142776116369, "learning_rate": 2.0952709699689335e-05, "loss": 0.3984, "step": 4010 }, { "epoch": 3.738705170004658, "grad_norm": 0.2398723130501074, "learning_rate": 2.0909561615464274e-05, "loss": 0.3835, "step": 4015 }, { "epoch": 3.7433628318584073, "grad_norm": 0.24507680623594794, "learning_rate": 2.0866413531239216e-05, "loss": 0.399, "step": 4020 }, { "epoch": 3.7480204937121564, "grad_norm": 0.2594359976919824, "learning_rate": 2.0823265447014152e-05, "loss": 0.3957, "step": 4025 }, { "epoch": 3.752678155565906, "grad_norm": 0.23183088650511982, "learning_rate": 2.078011736278909e-05, "loss": 0.3917, "step": 4030 }, { "epoch": 3.7573358174196554, "grad_norm": 0.2375548571237375, "learning_rate": 2.0736969278564034e-05, "loss": 0.3887, "step": 4035 }, { "epoch": 3.761993479273405, "grad_norm": 0.2434371548999832, "learning_rate": 2.0693821194338973e-05, "loss": 0.3868, "step": 4040 }, { "epoch": 3.766651141127154, "grad_norm": 0.2391945484130995, "learning_rate": 2.0650673110113912e-05, "loss": 0.4035, "step": 4045 }, { "epoch": 3.7713088029809034, "grad_norm": 0.2442126668364074, "learning_rate": 2.060752502588885e-05, "loss": 0.3977, "step": 4050 }, { "epoch": 3.775966464834653, "grad_norm": 0.23454693492435408, "learning_rate": 2.056437694166379e-05, "loss": 0.4013, "step": 4055 }, { "epoch": 3.7806241266884024, "grad_norm": 0.24702684533608035, "learning_rate": 2.0521228857438733e-05, "loss": 0.3901, "step": 4060 }, { "epoch": 3.785281788542152, "grad_norm": 0.25458690894528274, "learning_rate": 2.0478080773213672e-05, "loss": 0.3854, "step": 4065 }, { "epoch": 3.7899394503959014, "grad_norm": 0.2535427901318289, "learning_rate": 2.0434932688988608e-05, "loss": 0.3907, "step": 4070 }, { "epoch": 3.794597112249651, "grad_norm": 0.2542059979123618, "learning_rate": 2.039178460476355e-05, "loss": 0.3877, "step": 4075 }, { "epoch": 3.7992547741034, "grad_norm": 0.27915415228368606, "learning_rate": 2.034863652053849e-05, "loss": 0.3935, "step": 4080 }, { "epoch": 3.8039124359571495, "grad_norm": 0.2568790523892513, "learning_rate": 2.0305488436313428e-05, "loss": 0.3929, "step": 4085 }, { "epoch": 3.808570097810899, "grad_norm": 0.23991931335641786, "learning_rate": 2.0262340352088367e-05, "loss": 0.3913, "step": 4090 }, { "epoch": 3.8132277596646484, "grad_norm": 0.2558317225941586, "learning_rate": 2.0219192267863306e-05, "loss": 0.3855, "step": 4095 }, { "epoch": 3.8178854215183975, "grad_norm": 0.2624711994377453, "learning_rate": 2.017604418363825e-05, "loss": 0.3883, "step": 4100 }, { "epoch": 3.822543083372147, "grad_norm": 0.24603650558542686, "learning_rate": 2.0132896099413188e-05, "loss": 0.3867, "step": 4105 }, { "epoch": 3.8272007452258965, "grad_norm": 0.2501268977501799, "learning_rate": 2.0089748015188127e-05, "loss": 0.3891, "step": 4110 }, { "epoch": 3.831858407079646, "grad_norm": 0.25434103394053753, "learning_rate": 2.0046599930963066e-05, "loss": 0.3975, "step": 4115 }, { "epoch": 3.8365160689333955, "grad_norm": 0.24358624012374833, "learning_rate": 2.0003451846738005e-05, "loss": 0.3844, "step": 4120 }, { "epoch": 3.841173730787145, "grad_norm": 0.25839161234542657, "learning_rate": 1.9960303762512945e-05, "loss": 0.3958, "step": 4125 }, { "epoch": 3.8458313926408945, "grad_norm": 0.2398977503928776, "learning_rate": 1.9917155678287887e-05, "loss": 0.3988, "step": 4130 }, { "epoch": 3.850489054494644, "grad_norm": 0.25169753993214783, "learning_rate": 1.9874007594062823e-05, "loss": 0.3967, "step": 4135 }, { "epoch": 3.855146716348393, "grad_norm": 0.24646088128457036, "learning_rate": 1.9830859509837765e-05, "loss": 0.3942, "step": 4140 }, { "epoch": 3.8598043782021425, "grad_norm": 0.24585181185139302, "learning_rate": 1.9787711425612704e-05, "loss": 0.3971, "step": 4145 }, { "epoch": 3.864462040055892, "grad_norm": 0.2486685841150682, "learning_rate": 1.9744563341387643e-05, "loss": 0.3851, "step": 4150 }, { "epoch": 3.8691197019096415, "grad_norm": 0.23739537933574464, "learning_rate": 1.9701415257162583e-05, "loss": 0.3888, "step": 4155 }, { "epoch": 3.8737773637633905, "grad_norm": 0.2566318308440151, "learning_rate": 1.9658267172937522e-05, "loss": 0.4082, "step": 4160 }, { "epoch": 3.87843502561714, "grad_norm": 0.2592406592560921, "learning_rate": 1.961511908871246e-05, "loss": 0.3992, "step": 4165 }, { "epoch": 3.8830926874708895, "grad_norm": 0.25138732776779676, "learning_rate": 1.9571971004487403e-05, "loss": 0.389, "step": 4170 }, { "epoch": 3.887750349324639, "grad_norm": 0.2595679156104136, "learning_rate": 1.952882292026234e-05, "loss": 0.3979, "step": 4175 }, { "epoch": 3.8924080111783885, "grad_norm": 0.24443748796007034, "learning_rate": 1.948567483603728e-05, "loss": 0.3924, "step": 4180 }, { "epoch": 3.897065673032138, "grad_norm": 0.2389230492173908, "learning_rate": 1.944252675181222e-05, "loss": 0.3942, "step": 4185 }, { "epoch": 3.9017233348858875, "grad_norm": 0.2462673012936362, "learning_rate": 1.939937866758716e-05, "loss": 0.3923, "step": 4190 }, { "epoch": 3.9063809967396366, "grad_norm": 0.24007785175311064, "learning_rate": 1.93562305833621e-05, "loss": 0.3841, "step": 4195 }, { "epoch": 3.911038658593386, "grad_norm": 0.24022637241458067, "learning_rate": 1.9313082499137038e-05, "loss": 0.3878, "step": 4200 }, { "epoch": 3.9156963204471356, "grad_norm": 0.2405043603509575, "learning_rate": 1.9269934414911977e-05, "loss": 0.3933, "step": 4205 }, { "epoch": 3.920353982300885, "grad_norm": 0.23878423226357479, "learning_rate": 1.922678633068692e-05, "loss": 0.3877, "step": 4210 }, { "epoch": 3.925011644154634, "grad_norm": 0.2390080404451324, "learning_rate": 1.918363824646186e-05, "loss": 0.3858, "step": 4215 }, { "epoch": 3.9296693060083836, "grad_norm": 0.24164349748111402, "learning_rate": 1.9140490162236798e-05, "loss": 0.3895, "step": 4220 }, { "epoch": 3.934326967862133, "grad_norm": 0.24609235154863504, "learning_rate": 1.9097342078011737e-05, "loss": 0.3865, "step": 4225 }, { "epoch": 3.9389846297158826, "grad_norm": 0.24358167523632618, "learning_rate": 1.9054193993786676e-05, "loss": 0.3907, "step": 4230 }, { "epoch": 3.943642291569632, "grad_norm": 0.26400085073242524, "learning_rate": 1.901104590956162e-05, "loss": 0.3893, "step": 4235 }, { "epoch": 3.9482999534233816, "grad_norm": 0.2468456611523116, "learning_rate": 1.8967897825336554e-05, "loss": 0.3862, "step": 4240 }, { "epoch": 3.952957615277131, "grad_norm": 0.24305237212689243, "learning_rate": 1.8924749741111493e-05, "loss": 0.3868, "step": 4245 }, { "epoch": 3.9576152771308806, "grad_norm": 0.24687285492561709, "learning_rate": 1.8881601656886436e-05, "loss": 0.3913, "step": 4250 }, { "epoch": 3.9622729389846296, "grad_norm": 0.2533717063044844, "learning_rate": 1.8838453572661375e-05, "loss": 0.392, "step": 4255 }, { "epoch": 3.966930600838379, "grad_norm": 0.24378065616500003, "learning_rate": 1.8795305488436314e-05, "loss": 0.3978, "step": 4260 }, { "epoch": 3.9715882626921286, "grad_norm": 0.2505014305549489, "learning_rate": 1.8752157404211253e-05, "loss": 0.3984, "step": 4265 }, { "epoch": 3.976245924545878, "grad_norm": 0.24312369695300431, "learning_rate": 1.8709009319986192e-05, "loss": 0.3925, "step": 4270 }, { "epoch": 3.980903586399627, "grad_norm": 0.24666614099565512, "learning_rate": 1.8665861235761135e-05, "loss": 0.3994, "step": 4275 }, { "epoch": 3.9855612482533767, "grad_norm": 0.24652448794147927, "learning_rate": 1.8622713151536074e-05, "loss": 0.3961, "step": 4280 }, { "epoch": 3.990218910107126, "grad_norm": 0.24350346656335373, "learning_rate": 1.857956506731101e-05, "loss": 0.3858, "step": 4285 }, { "epoch": 3.9948765719608756, "grad_norm": 0.24285952012834353, "learning_rate": 1.8536416983085952e-05, "loss": 0.3922, "step": 4290 }, { "epoch": 3.999534233814625, "grad_norm": 0.23947089080901657, "learning_rate": 1.849326889886089e-05, "loss": 0.3944, "step": 4295 }, { "epoch": 4.003726129483, "grad_norm": 0.25247465162580635, "learning_rate": 1.8450120814635834e-05, "loss": 0.3541, "step": 4300 }, { "epoch": 4.008383791336749, "grad_norm": 0.2686612441337043, "learning_rate": 1.840697273041077e-05, "loss": 0.3454, "step": 4305 }, { "epoch": 4.013041453190499, "grad_norm": 0.25833833733633355, "learning_rate": 1.836382464618571e-05, "loss": 0.3494, "step": 4310 }, { "epoch": 4.017699115044247, "grad_norm": 0.2530472954136736, "learning_rate": 1.832067656196065e-05, "loss": 0.3434, "step": 4315 }, { "epoch": 4.022356776897997, "grad_norm": 0.2584327937397181, "learning_rate": 1.827752847773559e-05, "loss": 0.3468, "step": 4320 }, { "epoch": 4.027014438751746, "grad_norm": 0.26433887412492874, "learning_rate": 1.823438039351053e-05, "loss": 0.337, "step": 4325 }, { "epoch": 4.031672100605496, "grad_norm": 0.2639294539895767, "learning_rate": 1.819123230928547e-05, "loss": 0.3481, "step": 4330 }, { "epoch": 4.036329762459245, "grad_norm": 0.25741091401200683, "learning_rate": 1.8148084225060408e-05, "loss": 0.3505, "step": 4335 }, { "epoch": 4.040987424312995, "grad_norm": 0.26104366209611046, "learning_rate": 1.810493614083535e-05, "loss": 0.3496, "step": 4340 }, { "epoch": 4.045645086166744, "grad_norm": 0.25587901247344313, "learning_rate": 1.806178805661029e-05, "loss": 0.3459, "step": 4345 }, { "epoch": 4.050302748020494, "grad_norm": 0.25326753115597384, "learning_rate": 1.8018639972385225e-05, "loss": 0.3507, "step": 4350 }, { "epoch": 4.054960409874243, "grad_norm": 0.26336224553591, "learning_rate": 1.7975491888160167e-05, "loss": 0.3568, "step": 4355 }, { "epoch": 4.059618071727993, "grad_norm": 0.2709433556907873, "learning_rate": 1.7932343803935107e-05, "loss": 0.3584, "step": 4360 }, { "epoch": 4.064275733581742, "grad_norm": 0.25277760815101297, "learning_rate": 1.7889195719710046e-05, "loss": 0.3526, "step": 4365 }, { "epoch": 4.068933395435492, "grad_norm": 0.24950624952231276, "learning_rate": 1.7846047635484985e-05, "loss": 0.3534, "step": 4370 }, { "epoch": 4.07359105728924, "grad_norm": 0.2676557834747737, "learning_rate": 1.7802899551259924e-05, "loss": 0.3488, "step": 4375 }, { "epoch": 4.07824871914299, "grad_norm": 0.2627159956676244, "learning_rate": 1.7759751467034866e-05, "loss": 0.3478, "step": 4380 }, { "epoch": 4.082906380996739, "grad_norm": 0.258819108920642, "learning_rate": 1.7716603382809806e-05, "loss": 0.347, "step": 4385 }, { "epoch": 4.087564042850489, "grad_norm": 0.2593145754821633, "learning_rate": 1.767345529858474e-05, "loss": 0.3548, "step": 4390 }, { "epoch": 4.092221704704238, "grad_norm": 0.25195295600009215, "learning_rate": 1.7630307214359684e-05, "loss": 0.3509, "step": 4395 }, { "epoch": 4.096879366557988, "grad_norm": 0.26460242787211713, "learning_rate": 1.7587159130134623e-05, "loss": 0.3511, "step": 4400 }, { "epoch": 4.101537028411737, "grad_norm": 0.24719167615605106, "learning_rate": 1.7544011045909562e-05, "loss": 0.3514, "step": 4405 }, { "epoch": 4.106194690265487, "grad_norm": 0.25998667977808193, "learning_rate": 1.75008629616845e-05, "loss": 0.3537, "step": 4410 }, { "epoch": 4.110852352119236, "grad_norm": 0.252067931083926, "learning_rate": 1.745771487745944e-05, "loss": 0.3489, "step": 4415 }, { "epoch": 4.115510013972986, "grad_norm": 0.265889880056648, "learning_rate": 1.7414566793234383e-05, "loss": 0.3596, "step": 4420 }, { "epoch": 4.120167675826735, "grad_norm": 0.26940967632624896, "learning_rate": 1.7371418709009322e-05, "loss": 0.3535, "step": 4425 }, { "epoch": 4.124825337680484, "grad_norm": 0.2614314372730659, "learning_rate": 1.732827062478426e-05, "loss": 0.3583, "step": 4430 }, { "epoch": 4.1294829995342335, "grad_norm": 0.26461220568751925, "learning_rate": 1.72851225405592e-05, "loss": 0.3435, "step": 4435 }, { "epoch": 4.134140661387983, "grad_norm": 0.2582995004785811, "learning_rate": 1.724197445633414e-05, "loss": 0.3526, "step": 4440 }, { "epoch": 4.1387983232417325, "grad_norm": 0.2640821711491604, "learning_rate": 1.7198826372109078e-05, "loss": 0.3538, "step": 4445 }, { "epoch": 4.143455985095482, "grad_norm": 0.254541638012217, "learning_rate": 1.715567828788402e-05, "loss": 0.354, "step": 4450 }, { "epoch": 4.1481136469492315, "grad_norm": 0.27356217660978976, "learning_rate": 1.7112530203658957e-05, "loss": 0.3527, "step": 4455 }, { "epoch": 4.152771308802981, "grad_norm": 0.2738194921005561, "learning_rate": 1.70693821194339e-05, "loss": 0.3509, "step": 4460 }, { "epoch": 4.1574289706567304, "grad_norm": 0.26607082885921474, "learning_rate": 1.7026234035208838e-05, "loss": 0.3609, "step": 4465 }, { "epoch": 4.16208663251048, "grad_norm": 0.2567386716021225, "learning_rate": 1.6983085950983777e-05, "loss": 0.3615, "step": 4470 }, { "epoch": 4.166744294364229, "grad_norm": 0.2641036616870359, "learning_rate": 1.6939937866758716e-05, "loss": 0.3511, "step": 4475 }, { "epoch": 4.171401956217979, "grad_norm": 0.256513995994292, "learning_rate": 1.6896789782533655e-05, "loss": 0.3508, "step": 4480 }, { "epoch": 4.1760596180717275, "grad_norm": 0.24518462711920755, "learning_rate": 1.6853641698308595e-05, "loss": 0.3404, "step": 4485 }, { "epoch": 4.180717279925477, "grad_norm": 0.24074939426589254, "learning_rate": 1.6810493614083537e-05, "loss": 0.3467, "step": 4490 }, { "epoch": 4.1853749417792265, "grad_norm": 0.25680149290650184, "learning_rate": 1.6767345529858476e-05, "loss": 0.3555, "step": 4495 }, { "epoch": 4.190032603632976, "grad_norm": 0.26524681560333696, "learning_rate": 1.6724197445633415e-05, "loss": 0.3595, "step": 4500 }, { "epoch": 4.1946902654867255, "grad_norm": 0.269124083593698, "learning_rate": 1.6681049361408354e-05, "loss": 0.3473, "step": 4505 }, { "epoch": 4.199347927340475, "grad_norm": 0.2504448969685379, "learning_rate": 1.6637901277183294e-05, "loss": 0.3565, "step": 4510 }, { "epoch": 4.2040055891942245, "grad_norm": 0.2654922293107417, "learning_rate": 1.6594753192958236e-05, "loss": 0.3525, "step": 4515 }, { "epoch": 4.208663251047974, "grad_norm": 0.2651106600342314, "learning_rate": 1.6551605108733172e-05, "loss": 0.3531, "step": 4520 }, { "epoch": 4.2133209129017235, "grad_norm": 0.2455363231070034, "learning_rate": 1.650845702450811e-05, "loss": 0.3499, "step": 4525 }, { "epoch": 4.217978574755473, "grad_norm": 0.27460043240083193, "learning_rate": 1.6465308940283053e-05, "loss": 0.3515, "step": 4530 }, { "epoch": 4.2226362366092225, "grad_norm": 0.2510910197059824, "learning_rate": 1.6422160856057992e-05, "loss": 0.3516, "step": 4535 }, { "epoch": 4.227293898462972, "grad_norm": 0.2605605016945513, "learning_rate": 1.637901277183293e-05, "loss": 0.3561, "step": 4540 }, { "epoch": 4.231951560316721, "grad_norm": 0.25674169277643916, "learning_rate": 1.633586468760787e-05, "loss": 0.3558, "step": 4545 }, { "epoch": 4.23660922217047, "grad_norm": 0.2608602400046302, "learning_rate": 1.629271660338281e-05, "loss": 0.3528, "step": 4550 }, { "epoch": 4.24126688402422, "grad_norm": 0.27603325770015286, "learning_rate": 1.6249568519157752e-05, "loss": 0.3579, "step": 4555 }, { "epoch": 4.245924545877969, "grad_norm": 0.2735081269610808, "learning_rate": 1.620642043493269e-05, "loss": 0.3617, "step": 4560 }, { "epoch": 4.250582207731719, "grad_norm": 0.2713320052389058, "learning_rate": 1.6163272350707627e-05, "loss": 0.3529, "step": 4565 }, { "epoch": 4.255239869585468, "grad_norm": 0.258793554139262, "learning_rate": 1.612012426648257e-05, "loss": 0.3622, "step": 4570 }, { "epoch": 4.259897531439218, "grad_norm": 0.27089472605529064, "learning_rate": 1.607697618225751e-05, "loss": 0.3605, "step": 4575 }, { "epoch": 4.264555193292967, "grad_norm": 0.2543344453160982, "learning_rate": 1.6033828098032448e-05, "loss": 0.3586, "step": 4580 }, { "epoch": 4.269212855146717, "grad_norm": 0.24436434548125638, "learning_rate": 1.5990680013807387e-05, "loss": 0.3555, "step": 4585 }, { "epoch": 4.273870517000466, "grad_norm": 0.28388750580698824, "learning_rate": 1.5947531929582326e-05, "loss": 0.3525, "step": 4590 }, { "epoch": 4.2785281788542155, "grad_norm": 0.2772708324432262, "learning_rate": 1.590438384535727e-05, "loss": 0.3574, "step": 4595 }, { "epoch": 4.283185840707965, "grad_norm": 0.25250238740576053, "learning_rate": 1.5861235761132208e-05, "loss": 0.3588, "step": 4600 }, { "epoch": 4.287843502561714, "grad_norm": 0.2655978152340446, "learning_rate": 1.5818087676907143e-05, "loss": 0.3629, "step": 4605 }, { "epoch": 4.292501164415463, "grad_norm": 0.27854527730887996, "learning_rate": 1.5774939592682086e-05, "loss": 0.3535, "step": 4610 }, { "epoch": 4.297158826269213, "grad_norm": 0.2601541920449813, "learning_rate": 1.5731791508457025e-05, "loss": 0.3539, "step": 4615 }, { "epoch": 4.301816488122962, "grad_norm": 0.26532185220911, "learning_rate": 1.5688643424231964e-05, "loss": 0.3508, "step": 4620 }, { "epoch": 4.306474149976712, "grad_norm": 0.25779141040470965, "learning_rate": 1.5645495340006903e-05, "loss": 0.3554, "step": 4625 }, { "epoch": 4.311131811830461, "grad_norm": 0.2527293548794855, "learning_rate": 1.5602347255781842e-05, "loss": 0.3583, "step": 4630 }, { "epoch": 4.315789473684211, "grad_norm": 0.2665694111614692, "learning_rate": 1.5559199171556785e-05, "loss": 0.3532, "step": 4635 }, { "epoch": 4.32044713553796, "grad_norm": 0.2521039352343892, "learning_rate": 1.5516051087331724e-05, "loss": 0.3536, "step": 4640 }, { "epoch": 4.32510479739171, "grad_norm": 0.2599182818073454, "learning_rate": 1.5472903003106663e-05, "loss": 0.3511, "step": 4645 }, { "epoch": 4.329762459245459, "grad_norm": 0.2514861541121452, "learning_rate": 1.5429754918881602e-05, "loss": 0.3533, "step": 4650 }, { "epoch": 4.334420121099209, "grad_norm": 0.2512750184887021, "learning_rate": 1.538660683465654e-05, "loss": 0.3528, "step": 4655 }, { "epoch": 4.339077782952957, "grad_norm": 0.2538464643494344, "learning_rate": 1.534345875043148e-05, "loss": 0.3564, "step": 4660 }, { "epoch": 4.343735444806707, "grad_norm": 0.256262668529666, "learning_rate": 1.5300310666206423e-05, "loss": 0.3625, "step": 4665 }, { "epoch": 4.348393106660456, "grad_norm": 0.2577773873772109, "learning_rate": 1.525716258198136e-05, "loss": 0.3579, "step": 4670 }, { "epoch": 4.353050768514206, "grad_norm": 0.25946520670259987, "learning_rate": 1.5214014497756301e-05, "loss": 0.3481, "step": 4675 }, { "epoch": 4.357708430367955, "grad_norm": 0.2719197995662212, "learning_rate": 1.517086641353124e-05, "loss": 0.361, "step": 4680 }, { "epoch": 4.362366092221705, "grad_norm": 0.25262445717065574, "learning_rate": 1.5127718329306178e-05, "loss": 0.3507, "step": 4685 }, { "epoch": 4.367023754075454, "grad_norm": 0.2547222483331524, "learning_rate": 1.508457024508112e-05, "loss": 0.3555, "step": 4690 }, { "epoch": 4.371681415929204, "grad_norm": 0.2552232021583807, "learning_rate": 1.5041422160856058e-05, "loss": 0.3517, "step": 4695 }, { "epoch": 4.376339077782953, "grad_norm": 0.2588734453093337, "learning_rate": 1.4998274076630997e-05, "loss": 0.3632, "step": 4700 }, { "epoch": 4.380996739636703, "grad_norm": 0.2488284426344132, "learning_rate": 1.4955125992405938e-05, "loss": 0.3533, "step": 4705 }, { "epoch": 4.385654401490452, "grad_norm": 0.2547316587490947, "learning_rate": 1.4911977908180877e-05, "loss": 0.3632, "step": 4710 }, { "epoch": 4.390312063344201, "grad_norm": 0.2604304922804846, "learning_rate": 1.4868829823955818e-05, "loss": 0.3472, "step": 4715 }, { "epoch": 4.39496972519795, "grad_norm": 0.25841224561666964, "learning_rate": 1.4825681739730757e-05, "loss": 0.3507, "step": 4720 }, { "epoch": 4.3996273870517, "grad_norm": 0.2600235675255718, "learning_rate": 1.4782533655505696e-05, "loss": 0.3457, "step": 4725 }, { "epoch": 4.404285048905449, "grad_norm": 0.25803086318978696, "learning_rate": 1.4739385571280637e-05, "loss": 0.3618, "step": 4730 }, { "epoch": 4.408942710759199, "grad_norm": 0.25121837083236226, "learning_rate": 1.4696237487055576e-05, "loss": 0.3611, "step": 4735 }, { "epoch": 4.413600372612948, "grad_norm": 0.258157759041617, "learning_rate": 1.4653089402830513e-05, "loss": 0.3439, "step": 4740 }, { "epoch": 4.418258034466698, "grad_norm": 0.26358469996201345, "learning_rate": 1.4609941318605456e-05, "loss": 0.3559, "step": 4745 }, { "epoch": 4.422915696320447, "grad_norm": 0.2595175799371224, "learning_rate": 1.4566793234380393e-05, "loss": 0.3506, "step": 4750 }, { "epoch": 4.427573358174197, "grad_norm": 0.2675806891530391, "learning_rate": 1.4523645150155336e-05, "loss": 0.3651, "step": 4755 }, { "epoch": 4.432231020027946, "grad_norm": 0.26785770546503535, "learning_rate": 1.4480497065930273e-05, "loss": 0.355, "step": 4760 }, { "epoch": 4.436888681881696, "grad_norm": 0.24158928609208005, "learning_rate": 1.4437348981705212e-05, "loss": 0.3557, "step": 4765 }, { "epoch": 4.441546343735445, "grad_norm": 0.25279892386131353, "learning_rate": 1.4394200897480153e-05, "loss": 0.3468, "step": 4770 }, { "epoch": 4.446204005589194, "grad_norm": 0.2552169709561882, "learning_rate": 1.4351052813255092e-05, "loss": 0.3547, "step": 4775 }, { "epoch": 4.450861667442943, "grad_norm": 0.2640576794042077, "learning_rate": 1.4307904729030031e-05, "loss": 0.3575, "step": 4780 }, { "epoch": 4.455519329296693, "grad_norm": 0.2518334768773973, "learning_rate": 1.4264756644804972e-05, "loss": 0.3619, "step": 4785 }, { "epoch": 4.460176991150442, "grad_norm": 0.24876157668659526, "learning_rate": 1.4221608560579911e-05, "loss": 0.353, "step": 4790 }, { "epoch": 4.464834653004192, "grad_norm": 0.2642225377678936, "learning_rate": 1.4178460476354852e-05, "loss": 0.3558, "step": 4795 }, { "epoch": 4.469492314857941, "grad_norm": 0.25275944881331464, "learning_rate": 1.4135312392129791e-05, "loss": 0.36, "step": 4800 }, { "epoch": 4.474149976711691, "grad_norm": 0.2504912272692354, "learning_rate": 1.4092164307904728e-05, "loss": 0.3574, "step": 4805 }, { "epoch": 4.47880763856544, "grad_norm": 0.2679559663995821, "learning_rate": 1.404901622367967e-05, "loss": 0.354, "step": 4810 }, { "epoch": 4.48346530041919, "grad_norm": 0.2660628921042456, "learning_rate": 1.4005868139454608e-05, "loss": 0.3491, "step": 4815 }, { "epoch": 4.488122962272939, "grad_norm": 0.2563230482193863, "learning_rate": 1.3962720055229547e-05, "loss": 0.3606, "step": 4820 }, { "epoch": 4.492780624126689, "grad_norm": 0.25683586857920354, "learning_rate": 1.3919571971004488e-05, "loss": 0.3578, "step": 4825 }, { "epoch": 4.497438285980438, "grad_norm": 0.25605634033432917, "learning_rate": 1.3876423886779427e-05, "loss": 0.3627, "step": 4830 }, { "epoch": 4.502095947834187, "grad_norm": 0.2630584652316749, "learning_rate": 1.3833275802554368e-05, "loss": 0.3566, "step": 4835 }, { "epoch": 4.506753609687936, "grad_norm": 0.25166781860903803, "learning_rate": 1.3790127718329307e-05, "loss": 0.3583, "step": 4840 }, { "epoch": 4.511411271541686, "grad_norm": 0.25578210843033916, "learning_rate": 1.3746979634104246e-05, "loss": 0.355, "step": 4845 }, { "epoch": 4.516068933395435, "grad_norm": 0.25081436095598236, "learning_rate": 1.3703831549879187e-05, "loss": 0.3487, "step": 4850 }, { "epoch": 4.520726595249185, "grad_norm": 0.2482724172881988, "learning_rate": 1.3660683465654126e-05, "loss": 0.3566, "step": 4855 }, { "epoch": 4.525384257102934, "grad_norm": 0.25162447109785135, "learning_rate": 1.3617535381429064e-05, "loss": 0.3501, "step": 4860 }, { "epoch": 4.530041918956684, "grad_norm": 0.24188134173374082, "learning_rate": 1.3574387297204006e-05, "loss": 0.3562, "step": 4865 }, { "epoch": 4.534699580810433, "grad_norm": 0.24515784321889664, "learning_rate": 1.3531239212978944e-05, "loss": 0.3579, "step": 4870 }, { "epoch": 4.539357242664183, "grad_norm": 0.24154302892971688, "learning_rate": 1.3488091128753886e-05, "loss": 0.359, "step": 4875 }, { "epoch": 4.544014904517932, "grad_norm": 0.25616623132601496, "learning_rate": 1.3444943044528824e-05, "loss": 0.3589, "step": 4880 }, { "epoch": 4.548672566371682, "grad_norm": 0.2397743427934741, "learning_rate": 1.3401794960303763e-05, "loss": 0.3573, "step": 4885 }, { "epoch": 4.55333022822543, "grad_norm": 0.2531113010243328, "learning_rate": 1.3358646876078703e-05, "loss": 0.3543, "step": 4890 }, { "epoch": 4.55798789007918, "grad_norm": 0.24625831780490043, "learning_rate": 1.3315498791853643e-05, "loss": 0.3518, "step": 4895 }, { "epoch": 4.562645551932929, "grad_norm": 0.2558554076735099, "learning_rate": 1.327235070762858e-05, "loss": 0.3468, "step": 4900 }, { "epoch": 4.567303213786679, "grad_norm": 0.25332265275347166, "learning_rate": 1.3229202623403522e-05, "loss": 0.3579, "step": 4905 }, { "epoch": 4.571960875640428, "grad_norm": 0.2530795126014753, "learning_rate": 1.318605453917846e-05, "loss": 0.3543, "step": 4910 }, { "epoch": 4.576618537494178, "grad_norm": 0.24636048480334669, "learning_rate": 1.3142906454953402e-05, "loss": 0.3506, "step": 4915 }, { "epoch": 4.581276199347927, "grad_norm": 0.2499973927207776, "learning_rate": 1.309975837072834e-05, "loss": 0.3518, "step": 4920 }, { "epoch": 4.585933861201677, "grad_norm": 0.24963705446429768, "learning_rate": 1.3056610286503279e-05, "loss": 0.3586, "step": 4925 }, { "epoch": 4.590591523055426, "grad_norm": 0.2566977710543526, "learning_rate": 1.301346220227822e-05, "loss": 0.3509, "step": 4930 }, { "epoch": 4.595249184909176, "grad_norm": 0.2403355430645342, "learning_rate": 1.2970314118053159e-05, "loss": 0.3597, "step": 4935 }, { "epoch": 4.599906846762925, "grad_norm": 0.24141709166732558, "learning_rate": 1.2927166033828098e-05, "loss": 0.3508, "step": 4940 }, { "epoch": 4.604564508616674, "grad_norm": 0.25158631487592803, "learning_rate": 1.2884017949603039e-05, "loss": 0.3658, "step": 4945 }, { "epoch": 4.6092221704704235, "grad_norm": 0.26086378431260904, "learning_rate": 1.2840869865377978e-05, "loss": 0.3515, "step": 4950 }, { "epoch": 4.613879832324173, "grad_norm": 0.2484994218902223, "learning_rate": 1.2797721781152919e-05, "loss": 0.3594, "step": 4955 }, { "epoch": 4.6185374941779225, "grad_norm": 0.2428066328271051, "learning_rate": 1.2754573696927858e-05, "loss": 0.3505, "step": 4960 }, { "epoch": 4.623195156031672, "grad_norm": 0.2584058706156403, "learning_rate": 1.2711425612702795e-05, "loss": 0.3625, "step": 4965 }, { "epoch": 4.6278528178854215, "grad_norm": 0.24651408268565203, "learning_rate": 1.2668277528477738e-05, "loss": 0.3615, "step": 4970 }, { "epoch": 4.632510479739171, "grad_norm": 0.24634168558750194, "learning_rate": 1.2625129444252675e-05, "loss": 0.3471, "step": 4975 }, { "epoch": 4.6371681415929205, "grad_norm": 0.2571829043586315, "learning_rate": 1.2581981360027614e-05, "loss": 0.3493, "step": 4980 }, { "epoch": 4.64182580344667, "grad_norm": 0.2564258892044161, "learning_rate": 1.2538833275802555e-05, "loss": 0.3647, "step": 4985 }, { "epoch": 4.6464834653004194, "grad_norm": 0.24872022239075656, "learning_rate": 1.2495685191577494e-05, "loss": 0.3497, "step": 4990 }, { "epoch": 4.651141127154169, "grad_norm": 0.257311480026475, "learning_rate": 1.2452537107352433e-05, "loss": 0.3573, "step": 4995 }, { "epoch": 4.6557987890079175, "grad_norm": 0.254225816412534, "learning_rate": 1.2409389023127374e-05, "loss": 0.3579, "step": 5000 }, { "epoch": 4.660456450861668, "grad_norm": 0.26685568129755044, "learning_rate": 1.2366240938902313e-05, "loss": 0.357, "step": 5005 }, { "epoch": 4.6651141127154165, "grad_norm": 0.25186887503190153, "learning_rate": 1.2323092854677252e-05, "loss": 0.3614, "step": 5010 }, { "epoch": 4.669771774569166, "grad_norm": 0.25190527999130236, "learning_rate": 1.2279944770452193e-05, "loss": 0.3558, "step": 5015 }, { "epoch": 4.6744294364229155, "grad_norm": 0.2504444719462384, "learning_rate": 1.2236796686227132e-05, "loss": 0.3562, "step": 5020 }, { "epoch": 4.679087098276665, "grad_norm": 0.2477500841925964, "learning_rate": 1.2193648602002073e-05, "loss": 0.3576, "step": 5025 }, { "epoch": 4.6837447601304145, "grad_norm": 0.2535409159627147, "learning_rate": 1.215050051777701e-05, "loss": 0.3537, "step": 5030 }, { "epoch": 4.688402421984164, "grad_norm": 0.24618143662368114, "learning_rate": 1.2107352433551951e-05, "loss": 0.3547, "step": 5035 }, { "epoch": 4.6930600838379135, "grad_norm": 0.25239845060994737, "learning_rate": 1.206420434932689e-05, "loss": 0.3529, "step": 5040 }, { "epoch": 4.697717745691663, "grad_norm": 0.2570197551849746, "learning_rate": 1.202105626510183e-05, "loss": 0.349, "step": 5045 }, { "epoch": 4.7023754075454125, "grad_norm": 0.2503684995219595, "learning_rate": 1.1977908180876769e-05, "loss": 0.3511, "step": 5050 }, { "epoch": 4.707033069399162, "grad_norm": 0.24738699005472128, "learning_rate": 1.193476009665171e-05, "loss": 0.3519, "step": 5055 }, { "epoch": 4.7116907312529115, "grad_norm": 0.24966649125673582, "learning_rate": 1.1891612012426649e-05, "loss": 0.3527, "step": 5060 }, { "epoch": 4.71634839310666, "grad_norm": 0.24893618167215475, "learning_rate": 1.1848463928201588e-05, "loss": 0.3486, "step": 5065 }, { "epoch": 4.72100605496041, "grad_norm": 0.2417144457872443, "learning_rate": 1.1805315843976528e-05, "loss": 0.3523, "step": 5070 }, { "epoch": 4.725663716814159, "grad_norm": 0.2484890517729988, "learning_rate": 1.1762167759751468e-05, "loss": 0.3585, "step": 5075 }, { "epoch": 4.730321378667909, "grad_norm": 0.2586963699493771, "learning_rate": 1.1719019675526408e-05, "loss": 0.3585, "step": 5080 }, { "epoch": 4.734979040521658, "grad_norm": 0.2457386489819265, "learning_rate": 1.1675871591301346e-05, "loss": 0.3495, "step": 5085 }, { "epoch": 4.739636702375408, "grad_norm": 0.24137995163219128, "learning_rate": 1.1632723507076287e-05, "loss": 0.3547, "step": 5090 }, { "epoch": 4.744294364229157, "grad_norm": 0.2461505268941351, "learning_rate": 1.1589575422851226e-05, "loss": 0.3482, "step": 5095 }, { "epoch": 4.748952026082907, "grad_norm": 0.2489729548487017, "learning_rate": 1.1546427338626167e-05, "loss": 0.3572, "step": 5100 }, { "epoch": 4.753609687936656, "grad_norm": 0.26760737854325534, "learning_rate": 1.1503279254401104e-05, "loss": 0.3586, "step": 5105 }, { "epoch": 4.7582673497904056, "grad_norm": 0.25249512099620824, "learning_rate": 1.1460131170176045e-05, "loss": 0.3569, "step": 5110 }, { "epoch": 4.762925011644155, "grad_norm": 0.2668638310964985, "learning_rate": 1.1416983085950984e-05, "loss": 0.3538, "step": 5115 }, { "epoch": 4.767582673497904, "grad_norm": 0.24872922370228842, "learning_rate": 1.1373835001725925e-05, "loss": 0.3485, "step": 5120 }, { "epoch": 4.772240335351653, "grad_norm": 0.2610564442043746, "learning_rate": 1.1330686917500862e-05, "loss": 0.3556, "step": 5125 }, { "epoch": 4.776897997205403, "grad_norm": 0.2583163245317877, "learning_rate": 1.1287538833275803e-05, "loss": 0.3576, "step": 5130 }, { "epoch": 4.781555659059152, "grad_norm": 0.2601358076764965, "learning_rate": 1.1244390749050742e-05, "loss": 0.3681, "step": 5135 }, { "epoch": 4.786213320912902, "grad_norm": 0.25848242335804494, "learning_rate": 1.1201242664825683e-05, "loss": 0.3487, "step": 5140 }, { "epoch": 4.790870982766651, "grad_norm": 0.25059920689561765, "learning_rate": 1.1158094580600622e-05, "loss": 0.3554, "step": 5145 }, { "epoch": 4.795528644620401, "grad_norm": 0.251788050386831, "learning_rate": 1.1114946496375561e-05, "loss": 0.3408, "step": 5150 }, { "epoch": 4.80018630647415, "grad_norm": 0.2460690472182616, "learning_rate": 1.1071798412150502e-05, "loss": 0.347, "step": 5155 }, { "epoch": 4.8048439683279, "grad_norm": 0.25986725890170786, "learning_rate": 1.1028650327925441e-05, "loss": 0.3482, "step": 5160 }, { "epoch": 4.809501630181649, "grad_norm": 0.23970137586090656, "learning_rate": 1.098550224370038e-05, "loss": 0.3592, "step": 5165 }, { "epoch": 4.814159292035399, "grad_norm": 0.25183140326470865, "learning_rate": 1.094235415947532e-05, "loss": 0.3599, "step": 5170 }, { "epoch": 4.818816953889147, "grad_norm": 0.2571748546149219, "learning_rate": 1.089920607525026e-05, "loss": 0.3639, "step": 5175 }, { "epoch": 4.823474615742897, "grad_norm": 0.25460194554045285, "learning_rate": 1.0856057991025199e-05, "loss": 0.3512, "step": 5180 }, { "epoch": 4.828132277596646, "grad_norm": 0.25161487020378837, "learning_rate": 1.0812909906800138e-05, "loss": 0.351, "step": 5185 }, { "epoch": 4.832789939450396, "grad_norm": 0.26426340562746536, "learning_rate": 1.0769761822575077e-05, "loss": 0.3649, "step": 5190 }, { "epoch": 4.837447601304145, "grad_norm": 0.24804886711010168, "learning_rate": 1.0726613738350018e-05, "loss": 0.3541, "step": 5195 }, { "epoch": 4.842105263157895, "grad_norm": 0.24018651790174347, "learning_rate": 1.0683465654124957e-05, "loss": 0.3484, "step": 5200 }, { "epoch": 4.846762925011644, "grad_norm": 0.24643097067990474, "learning_rate": 1.0640317569899896e-05, "loss": 0.3598, "step": 5205 }, { "epoch": 4.851420586865394, "grad_norm": 0.2485949494566269, "learning_rate": 1.0597169485674835e-05, "loss": 0.3642, "step": 5210 }, { "epoch": 4.856078248719143, "grad_norm": 0.2515952015729273, "learning_rate": 1.0554021401449776e-05, "loss": 0.3563, "step": 5215 }, { "epoch": 4.860735910572893, "grad_norm": 0.24778792054840915, "learning_rate": 1.0510873317224715e-05, "loss": 0.3573, "step": 5220 }, { "epoch": 4.865393572426642, "grad_norm": 0.24744283938507503, "learning_rate": 1.0467725232999655e-05, "loss": 0.3489, "step": 5225 }, { "epoch": 4.870051234280391, "grad_norm": 0.25352419463692855, "learning_rate": 1.0424577148774595e-05, "loss": 0.3554, "step": 5230 }, { "epoch": 4.874708896134141, "grad_norm": 0.2574779480432367, "learning_rate": 1.0381429064549534e-05, "loss": 0.3616, "step": 5235 }, { "epoch": 4.87936655798789, "grad_norm": 0.2518009621412077, "learning_rate": 1.0338280980324475e-05, "loss": 0.3534, "step": 5240 }, { "epoch": 4.884024219841639, "grad_norm": 0.2527311775982243, "learning_rate": 1.0295132896099413e-05, "loss": 0.3669, "step": 5245 }, { "epoch": 4.888681881695389, "grad_norm": 0.27007244654397233, "learning_rate": 1.0251984811874353e-05, "loss": 0.364, "step": 5250 }, { "epoch": 4.893339543549138, "grad_norm": 0.2451827022215433, "learning_rate": 1.0208836727649293e-05, "loss": 0.3556, "step": 5255 }, { "epoch": 4.897997205402888, "grad_norm": 0.2544177671117187, "learning_rate": 1.0165688643424233e-05, "loss": 0.3483, "step": 5260 }, { "epoch": 4.902654867256637, "grad_norm": 0.24697796134380745, "learning_rate": 1.012254055919917e-05, "loss": 0.3675, "step": 5265 }, { "epoch": 4.907312529110387, "grad_norm": 0.2504481827884134, "learning_rate": 1.0079392474974112e-05, "loss": 0.3584, "step": 5270 }, { "epoch": 4.911970190964136, "grad_norm": 0.2593249833605583, "learning_rate": 1.003624439074905e-05, "loss": 0.356, "step": 5275 }, { "epoch": 4.916627852817886, "grad_norm": 0.24908537342241302, "learning_rate": 9.993096306523992e-06, "loss": 0.3576, "step": 5280 }, { "epoch": 4.921285514671635, "grad_norm": 0.24873807772717937, "learning_rate": 9.94994822229893e-06, "loss": 0.3533, "step": 5285 }, { "epoch": 4.925943176525385, "grad_norm": 0.2541406320769065, "learning_rate": 9.90680013807387e-06, "loss": 0.3617, "step": 5290 }, { "epoch": 4.930600838379133, "grad_norm": 0.2478894946081179, "learning_rate": 9.86365205384881e-06, "loss": 0.3511, "step": 5295 }, { "epoch": 4.935258500232883, "grad_norm": 0.24332517410865012, "learning_rate": 9.82050396962375e-06, "loss": 0.3553, "step": 5300 }, { "epoch": 4.939916162086632, "grad_norm": 0.2550232582028649, "learning_rate": 9.777355885398689e-06, "loss": 0.3593, "step": 5305 }, { "epoch": 4.944573823940382, "grad_norm": 0.2450904089870607, "learning_rate": 9.734207801173628e-06, "loss": 0.3542, "step": 5310 }, { "epoch": 4.949231485794131, "grad_norm": 0.25231508949434067, "learning_rate": 9.691059716948569e-06, "loss": 0.3466, "step": 5315 }, { "epoch": 4.953889147647881, "grad_norm": 0.2587907498538464, "learning_rate": 9.647911632723508e-06, "loss": 0.3548, "step": 5320 }, { "epoch": 4.95854680950163, "grad_norm": 0.25522917803705397, "learning_rate": 9.604763548498447e-06, "loss": 0.3586, "step": 5325 }, { "epoch": 4.96320447135538, "grad_norm": 0.25368543940903576, "learning_rate": 9.561615464273386e-06, "loss": 0.3587, "step": 5330 }, { "epoch": 4.967862133209129, "grad_norm": 0.25189465295915614, "learning_rate": 9.518467380048327e-06, "loss": 0.3452, "step": 5335 }, { "epoch": 4.972519795062879, "grad_norm": 0.24895971595256566, "learning_rate": 9.475319295823266e-06, "loss": 0.3566, "step": 5340 }, { "epoch": 4.977177456916628, "grad_norm": 0.24930356979273882, "learning_rate": 9.432171211598205e-06, "loss": 0.3505, "step": 5345 }, { "epoch": 4.981835118770377, "grad_norm": 0.2552853622739202, "learning_rate": 9.389023127373144e-06, "loss": 0.3449, "step": 5350 }, { "epoch": 4.986492780624126, "grad_norm": 0.2455794618388901, "learning_rate": 9.345875043148085e-06, "loss": 0.3561, "step": 5355 }, { "epoch": 4.991150442477876, "grad_norm": 0.2465848834342473, "learning_rate": 9.302726958923024e-06, "loss": 0.3416, "step": 5360 }, { "epoch": 4.995808104331625, "grad_norm": 0.2480075751479837, "learning_rate": 9.259578874697963e-06, "loss": 0.3577, "step": 5365 }, { "epoch": 5.0, "grad_norm": 0.2509438814897534, "learning_rate": 9.216430790472904e-06, "loss": 0.3449, "step": 5370 }, { "epoch": 5.0046576618537495, "grad_norm": 0.27328838696375196, "learning_rate": 9.173282706247843e-06, "loss": 0.3274, "step": 5375 }, { "epoch": 5.009315323707499, "grad_norm": 0.2851461930364874, "learning_rate": 9.130134622022784e-06, "loss": 0.3269, "step": 5380 }, { "epoch": 5.0139729855612485, "grad_norm": 0.2672151201433304, "learning_rate": 9.086986537797721e-06, "loss": 0.3225, "step": 5385 }, { "epoch": 5.018630647414998, "grad_norm": 0.26482398526077866, "learning_rate": 9.043838453572662e-06, "loss": 0.333, "step": 5390 }, { "epoch": 5.0232883092687475, "grad_norm": 0.2609465972582804, "learning_rate": 9.000690369347601e-06, "loss": 0.3184, "step": 5395 }, { "epoch": 5.027945971122496, "grad_norm": 0.26630009189305526, "learning_rate": 8.957542285122542e-06, "loss": 0.3158, "step": 5400 }, { "epoch": 5.032603632976246, "grad_norm": 0.25006712199076125, "learning_rate": 8.91439420089748e-06, "loss": 0.3186, "step": 5405 }, { "epoch": 5.037261294829995, "grad_norm": 0.2535596823448538, "learning_rate": 8.87124611667242e-06, "loss": 0.3201, "step": 5410 }, { "epoch": 5.041918956683745, "grad_norm": 0.28628175814542733, "learning_rate": 8.82809803244736e-06, "loss": 0.3199, "step": 5415 }, { "epoch": 5.046576618537494, "grad_norm": 0.26578575371746, "learning_rate": 8.7849499482223e-06, "loss": 0.3126, "step": 5420 }, { "epoch": 5.051234280391244, "grad_norm": 0.2521905357122807, "learning_rate": 8.741801863997238e-06, "loss": 0.3201, "step": 5425 }, { "epoch": 5.055891942244993, "grad_norm": 0.26362304119911245, "learning_rate": 8.698653779772179e-06, "loss": 0.3266, "step": 5430 }, { "epoch": 5.0605496040987425, "grad_norm": 0.26067591473180557, "learning_rate": 8.655505695547118e-06, "loss": 0.3083, "step": 5435 }, { "epoch": 5.065207265952492, "grad_norm": 0.25709325318601545, "learning_rate": 8.612357611322058e-06, "loss": 0.3121, "step": 5440 }, { "epoch": 5.0698649278062415, "grad_norm": 0.24772623494553947, "learning_rate": 8.569209527096998e-06, "loss": 0.3154, "step": 5445 }, { "epoch": 5.074522589659991, "grad_norm": 0.24130343566594567, "learning_rate": 8.526061442871937e-06, "loss": 0.3291, "step": 5450 }, { "epoch": 5.0791802515137405, "grad_norm": 0.2731637023041765, "learning_rate": 8.482913358646877e-06, "loss": 0.3282, "step": 5455 }, { "epoch": 5.083837913367489, "grad_norm": 0.24538494720544413, "learning_rate": 8.439765274421817e-06, "loss": 0.3081, "step": 5460 }, { "epoch": 5.088495575221239, "grad_norm": 0.26408208075755085, "learning_rate": 8.396617190196756e-06, "loss": 0.3217, "step": 5465 }, { "epoch": 5.093153237074988, "grad_norm": 0.261764102043343, "learning_rate": 8.353469105971695e-06, "loss": 0.3265, "step": 5470 }, { "epoch": 5.097810898928738, "grad_norm": 0.25605501004925385, "learning_rate": 8.310321021746636e-06, "loss": 0.3258, "step": 5475 }, { "epoch": 5.102468560782487, "grad_norm": 0.2648393196988148, "learning_rate": 8.267172937521575e-06, "loss": 0.3323, "step": 5480 }, { "epoch": 5.107126222636237, "grad_norm": 0.26647330467691877, "learning_rate": 8.224024853296514e-06, "loss": 0.3215, "step": 5485 }, { "epoch": 5.111783884489986, "grad_norm": 0.2533926730189367, "learning_rate": 8.180876769071453e-06, "loss": 0.3176, "step": 5490 }, { "epoch": 5.116441546343736, "grad_norm": 0.2678508386798619, "learning_rate": 8.137728684846394e-06, "loss": 0.3312, "step": 5495 }, { "epoch": 5.121099208197485, "grad_norm": 0.25963015886579505, "learning_rate": 8.094580600621333e-06, "loss": 0.3242, "step": 5500 }, { "epoch": 5.125756870051235, "grad_norm": 0.2524480702302166, "learning_rate": 8.051432516396272e-06, "loss": 0.3231, "step": 5505 }, { "epoch": 5.130414531904984, "grad_norm": 0.25844182652541203, "learning_rate": 8.008284432171211e-06, "loss": 0.3319, "step": 5510 }, { "epoch": 5.135072193758733, "grad_norm": 0.2548980044670304, "learning_rate": 7.965136347946152e-06, "loss": 0.315, "step": 5515 }, { "epoch": 5.139729855612482, "grad_norm": 0.2566724762167897, "learning_rate": 7.921988263721091e-06, "loss": 0.3281, "step": 5520 }, { "epoch": 5.144387517466232, "grad_norm": 0.2541318651525467, "learning_rate": 7.87884017949603e-06, "loss": 0.3226, "step": 5525 }, { "epoch": 5.149045179319981, "grad_norm": 0.25827133849557715, "learning_rate": 7.835692095270971e-06, "loss": 0.3191, "step": 5530 }, { "epoch": 5.153702841173731, "grad_norm": 0.2556317452621972, "learning_rate": 7.79254401104591e-06, "loss": 0.3242, "step": 5535 }, { "epoch": 5.15836050302748, "grad_norm": 0.26731311103947986, "learning_rate": 7.749395926820851e-06, "loss": 0.3211, "step": 5540 }, { "epoch": 5.16301816488123, "grad_norm": 0.2597403712001897, "learning_rate": 7.706247842595788e-06, "loss": 0.3208, "step": 5545 }, { "epoch": 5.167675826734979, "grad_norm": 0.2643618829585676, "learning_rate": 7.663099758370729e-06, "loss": 0.3265, "step": 5550 }, { "epoch": 5.172333488588729, "grad_norm": 0.2578625190541001, "learning_rate": 7.619951674145669e-06, "loss": 0.3251, "step": 5555 }, { "epoch": 5.176991150442478, "grad_norm": 0.2576023219960571, "learning_rate": 7.576803589920608e-06, "loss": 0.3376, "step": 5560 }, { "epoch": 5.181648812296228, "grad_norm": 0.2578382636227229, "learning_rate": 7.533655505695547e-06, "loss": 0.3214, "step": 5565 }, { "epoch": 5.186306474149977, "grad_norm": 0.25273428784745017, "learning_rate": 7.490507421470487e-06, "loss": 0.3217, "step": 5570 }, { "epoch": 5.190964136003726, "grad_norm": 0.24211111515375283, "learning_rate": 7.447359337245427e-06, "loss": 0.3237, "step": 5575 }, { "epoch": 5.195621797857475, "grad_norm": 0.2565782995469832, "learning_rate": 7.4042112530203655e-06, "loss": 0.318, "step": 5580 }, { "epoch": 5.200279459711225, "grad_norm": 0.25505850187923607, "learning_rate": 7.361063168795305e-06, "loss": 0.3225, "step": 5585 }, { "epoch": 5.204937121564974, "grad_norm": 0.26855214005637623, "learning_rate": 7.317915084570245e-06, "loss": 0.3253, "step": 5590 }, { "epoch": 5.209594783418724, "grad_norm": 0.25892750717240975, "learning_rate": 7.274767000345185e-06, "loss": 0.3245, "step": 5595 }, { "epoch": 5.214252445272473, "grad_norm": 0.2577227990453449, "learning_rate": 7.231618916120124e-06, "loss": 0.3285, "step": 5600 }, { "epoch": 5.218910107126223, "grad_norm": 0.25763027485825307, "learning_rate": 7.1884708318950636e-06, "loss": 0.3286, "step": 5605 }, { "epoch": 5.223567768979972, "grad_norm": 0.25927933258439384, "learning_rate": 7.1453227476700035e-06, "loss": 0.3304, "step": 5610 }, { "epoch": 5.228225430833722, "grad_norm": 0.2681726984641857, "learning_rate": 7.1021746634449435e-06, "loss": 0.3194, "step": 5615 }, { "epoch": 5.232883092687471, "grad_norm": 0.26142061707890185, "learning_rate": 7.059026579219883e-06, "loss": 0.3224, "step": 5620 }, { "epoch": 5.237540754541221, "grad_norm": 0.2564286092815123, "learning_rate": 7.0158784949948226e-06, "loss": 0.3131, "step": 5625 }, { "epoch": 5.242198416394969, "grad_norm": 0.25292776938814693, "learning_rate": 6.9727304107697625e-06, "loss": 0.3197, "step": 5630 }, { "epoch": 5.246856078248719, "grad_norm": 0.26464109233691396, "learning_rate": 6.9295823265447025e-06, "loss": 0.3261, "step": 5635 }, { "epoch": 5.251513740102468, "grad_norm": 0.25404563768394817, "learning_rate": 6.886434242319641e-06, "loss": 0.317, "step": 5640 }, { "epoch": 5.256171401956218, "grad_norm": 0.24580165731885362, "learning_rate": 6.843286158094581e-06, "loss": 0.3216, "step": 5645 }, { "epoch": 5.260829063809967, "grad_norm": 0.26281318046934754, "learning_rate": 6.800138073869521e-06, "loss": 0.3225, "step": 5650 }, { "epoch": 5.265486725663717, "grad_norm": 0.254080177754658, "learning_rate": 6.756989989644461e-06, "loss": 0.32, "step": 5655 }, { "epoch": 5.270144387517466, "grad_norm": 0.25508928327378216, "learning_rate": 6.713841905419399e-06, "loss": 0.3191, "step": 5660 }, { "epoch": 5.274802049371216, "grad_norm": 0.25315017360426073, "learning_rate": 6.670693821194339e-06, "loss": 0.3252, "step": 5665 }, { "epoch": 5.279459711224965, "grad_norm": 0.25749671377916616, "learning_rate": 6.627545736969279e-06, "loss": 0.32, "step": 5670 }, { "epoch": 5.284117373078715, "grad_norm": 0.2511806049153446, "learning_rate": 6.584397652744219e-06, "loss": 0.3159, "step": 5675 }, { "epoch": 5.288775034932464, "grad_norm": 0.26598065774818425, "learning_rate": 6.541249568519157e-06, "loss": 0.3305, "step": 5680 }, { "epoch": 5.293432696786214, "grad_norm": 0.25154524982644555, "learning_rate": 6.498101484294097e-06, "loss": 0.3242, "step": 5685 }, { "epoch": 5.298090358639962, "grad_norm": 0.25331719863914787, "learning_rate": 6.454953400069037e-06, "loss": 0.3242, "step": 5690 }, { "epoch": 5.302748020493712, "grad_norm": 0.2512360038332603, "learning_rate": 6.411805315843977e-06, "loss": 0.3237, "step": 5695 }, { "epoch": 5.307405682347461, "grad_norm": 0.2513718759735994, "learning_rate": 6.368657231618916e-06, "loss": 0.3194, "step": 5700 }, { "epoch": 5.312063344201211, "grad_norm": 0.2494378325365335, "learning_rate": 6.325509147393856e-06, "loss": 0.3194, "step": 5705 }, { "epoch": 5.31672100605496, "grad_norm": 0.25732404242754436, "learning_rate": 6.282361063168796e-06, "loss": 0.3248, "step": 5710 }, { "epoch": 5.32137866790871, "grad_norm": 0.254977001031559, "learning_rate": 6.239212978943735e-06, "loss": 0.3244, "step": 5715 }, { "epoch": 5.326036329762459, "grad_norm": 0.2643880591045418, "learning_rate": 6.196064894718675e-06, "loss": 0.3234, "step": 5720 }, { "epoch": 5.330693991616209, "grad_norm": 0.26735910085429626, "learning_rate": 6.152916810493614e-06, "loss": 0.326, "step": 5725 }, { "epoch": 5.335351653469958, "grad_norm": 0.2596830708881661, "learning_rate": 6.109768726268554e-06, "loss": 0.3263, "step": 5730 }, { "epoch": 5.340009315323708, "grad_norm": 0.2532350111497506, "learning_rate": 6.066620642043493e-06, "loss": 0.3248, "step": 5735 }, { "epoch": 5.344666977177457, "grad_norm": 0.2584742169144322, "learning_rate": 6.023472557818433e-06, "loss": 0.3262, "step": 5740 }, { "epoch": 5.349324639031206, "grad_norm": 0.2743456221964328, "learning_rate": 5.980324473593372e-06, "loss": 0.3209, "step": 5745 }, { "epoch": 5.353982300884955, "grad_norm": 0.2554149304817499, "learning_rate": 5.937176389368312e-06, "loss": 0.3198, "step": 5750 }, { "epoch": 5.358639962738705, "grad_norm": 0.25858908225532734, "learning_rate": 5.894028305143251e-06, "loss": 0.3203, "step": 5755 }, { "epoch": 5.363297624592454, "grad_norm": 0.2570214386900507, "learning_rate": 5.850880220918191e-06, "loss": 0.322, "step": 5760 }, { "epoch": 5.367955286446204, "grad_norm": 0.2568328829375655, "learning_rate": 5.807732136693131e-06, "loss": 0.32, "step": 5765 }, { "epoch": 5.372612948299953, "grad_norm": 0.2706974645417809, "learning_rate": 5.76458405246807e-06, "loss": 0.3245, "step": 5770 }, { "epoch": 5.377270610153703, "grad_norm": 0.2534737178789615, "learning_rate": 5.72143596824301e-06, "loss": 0.322, "step": 5775 }, { "epoch": 5.381928272007452, "grad_norm": 0.2723546093448459, "learning_rate": 5.67828788401795e-06, "loss": 0.3213, "step": 5780 }, { "epoch": 5.386585933861202, "grad_norm": 0.266021938189842, "learning_rate": 5.6351397997928894e-06, "loss": 0.3229, "step": 5785 }, { "epoch": 5.391243595714951, "grad_norm": 0.25568795714908576, "learning_rate": 5.591991715567829e-06, "loss": 0.3322, "step": 5790 }, { "epoch": 5.395901257568701, "grad_norm": 0.24606934110311102, "learning_rate": 5.5488436313427685e-06, "loss": 0.3289, "step": 5795 }, { "epoch": 5.4005589194224495, "grad_norm": 0.2586084557153241, "learning_rate": 5.5056955471177085e-06, "loss": 0.3214, "step": 5800 }, { "epoch": 5.405216581276199, "grad_norm": 0.2612973907754063, "learning_rate": 5.462547462892648e-06, "loss": 0.3387, "step": 5805 }, { "epoch": 5.4098742431299485, "grad_norm": 0.2540142266959533, "learning_rate": 5.4193993786675876e-06, "loss": 0.3198, "step": 5810 }, { "epoch": 5.414531904983698, "grad_norm": 0.24904352551676412, "learning_rate": 5.376251294442527e-06, "loss": 0.3195, "step": 5815 }, { "epoch": 5.4191895668374475, "grad_norm": 0.24739383052008818, "learning_rate": 5.333103210217467e-06, "loss": 0.3202, "step": 5820 }, { "epoch": 5.423847228691197, "grad_norm": 0.2586367709307302, "learning_rate": 5.289955125992406e-06, "loss": 0.3236, "step": 5825 }, { "epoch": 5.4285048905449464, "grad_norm": 0.26324932478774654, "learning_rate": 5.246807041767346e-06, "loss": 0.32, "step": 5830 }, { "epoch": 5.433162552398696, "grad_norm": 0.252384815450562, "learning_rate": 5.203658957542285e-06, "loss": 0.3219, "step": 5835 }, { "epoch": 5.437820214252445, "grad_norm": 0.25385649854632747, "learning_rate": 5.160510873317225e-06, "loss": 0.3341, "step": 5840 }, { "epoch": 5.442477876106195, "grad_norm": 0.25596847034123377, "learning_rate": 5.117362789092165e-06, "loss": 0.3192, "step": 5845 }, { "epoch": 5.447135537959944, "grad_norm": 0.2678454579408059, "learning_rate": 5.074214704867105e-06, "loss": 0.3277, "step": 5850 }, { "epoch": 5.451793199813694, "grad_norm": 0.258936071500233, "learning_rate": 5.031066620642044e-06, "loss": 0.3252, "step": 5855 }, { "epoch": 5.4564508616674425, "grad_norm": 0.24933337003989026, "learning_rate": 4.987918536416984e-06, "loss": 0.3246, "step": 5860 }, { "epoch": 5.461108523521192, "grad_norm": 0.26089157292078463, "learning_rate": 4.944770452191923e-06, "loss": 0.3349, "step": 5865 }, { "epoch": 5.4657661853749415, "grad_norm": 0.2574249916298197, "learning_rate": 4.901622367966863e-06, "loss": 0.3232, "step": 5870 }, { "epoch": 5.470423847228691, "grad_norm": 0.2719559819104923, "learning_rate": 4.858474283741802e-06, "loss": 0.3085, "step": 5875 }, { "epoch": 5.4750815090824405, "grad_norm": 0.2543768403111794, "learning_rate": 4.815326199516742e-06, "loss": 0.3214, "step": 5880 }, { "epoch": 5.47973917093619, "grad_norm": 0.25746176319209374, "learning_rate": 4.772178115291681e-06, "loss": 0.3222, "step": 5885 }, { "epoch": 5.4843968327899395, "grad_norm": 0.2522169180797675, "learning_rate": 4.729030031066621e-06, "loss": 0.3273, "step": 5890 }, { "epoch": 5.489054494643689, "grad_norm": 0.2511333982527805, "learning_rate": 4.68588194684156e-06, "loss": 0.3288, "step": 5895 }, { "epoch": 5.4937121564974385, "grad_norm": 0.24906124802776006, "learning_rate": 4.6427338626165e-06, "loss": 0.3207, "step": 5900 }, { "epoch": 5.498369818351188, "grad_norm": 0.25964491043069493, "learning_rate": 4.599585778391439e-06, "loss": 0.3342, "step": 5905 }, { "epoch": 5.5030274802049375, "grad_norm": 0.25487554306656507, "learning_rate": 4.556437694166379e-06, "loss": 0.3167, "step": 5910 }, { "epoch": 5.507685142058687, "grad_norm": 0.25993668940432557, "learning_rate": 4.513289609941319e-06, "loss": 0.3228, "step": 5915 }, { "epoch": 5.512342803912436, "grad_norm": 0.2548266988785691, "learning_rate": 4.470141525716258e-06, "loss": 0.3186, "step": 5920 }, { "epoch": 5.517000465766185, "grad_norm": 0.24225094115037232, "learning_rate": 4.426993441491198e-06, "loss": 0.3257, "step": 5925 }, { "epoch": 5.521658127619935, "grad_norm": 0.2518370501745694, "learning_rate": 4.383845357266138e-06, "loss": 0.3209, "step": 5930 }, { "epoch": 5.526315789473684, "grad_norm": 0.24854312187556646, "learning_rate": 4.340697273041077e-06, "loss": 0.3214, "step": 5935 }, { "epoch": 5.530973451327434, "grad_norm": 0.2569548920944948, "learning_rate": 4.297549188816017e-06, "loss": 0.3218, "step": 5940 }, { "epoch": 5.535631113181183, "grad_norm": 0.25160177488553725, "learning_rate": 4.254401104590956e-06, "loss": 0.3244, "step": 5945 }, { "epoch": 5.5402887750349326, "grad_norm": 0.25778940613492785, "learning_rate": 4.211253020365896e-06, "loss": 0.3341, "step": 5950 }, { "epoch": 5.544946436888682, "grad_norm": 0.25874828455021986, "learning_rate": 4.168104936140835e-06, "loss": 0.3113, "step": 5955 }, { "epoch": 5.5496040987424315, "grad_norm": 0.25671640690286507, "learning_rate": 4.124956851915775e-06, "loss": 0.323, "step": 5960 }, { "epoch": 5.554261760596181, "grad_norm": 0.2533776783033336, "learning_rate": 4.0818087676907145e-06, "loss": 0.3218, "step": 5965 }, { "epoch": 5.5589194224499305, "grad_norm": 0.25823009927307755, "learning_rate": 4.0386606834656544e-06, "loss": 0.3187, "step": 5970 }, { "epoch": 5.563577084303679, "grad_norm": 0.24992267594760914, "learning_rate": 3.9955125992405935e-06, "loss": 0.325, "step": 5975 }, { "epoch": 5.568234746157429, "grad_norm": 0.2533060476463673, "learning_rate": 3.9523645150155335e-06, "loss": 0.3247, "step": 5980 }, { "epoch": 5.572892408011178, "grad_norm": 0.25989530227570995, "learning_rate": 3.909216430790473e-06, "loss": 0.3225, "step": 5985 }, { "epoch": 5.577550069864928, "grad_norm": 0.2556285947142826, "learning_rate": 3.8660683465654126e-06, "loss": 0.3197, "step": 5990 }, { "epoch": 5.582207731718677, "grad_norm": 0.26374425070682833, "learning_rate": 3.8229202623403525e-06, "loss": 0.3196, "step": 5995 }, { "epoch": 5.586865393572427, "grad_norm": 0.26744750793190947, "learning_rate": 3.779772178115292e-06, "loss": 0.33, "step": 6000 }, { "epoch": 5.591523055426176, "grad_norm": 0.25499924385082806, "learning_rate": 3.736624093890231e-06, "loss": 0.3278, "step": 6005 }, { "epoch": 5.596180717279926, "grad_norm": 0.2548948920520942, "learning_rate": 3.693476009665171e-06, "loss": 0.324, "step": 6010 }, { "epoch": 5.600838379133675, "grad_norm": 0.25563462056321246, "learning_rate": 3.6503279254401107e-06, "loss": 0.328, "step": 6015 }, { "epoch": 5.605496040987425, "grad_norm": 0.2500475535088693, "learning_rate": 3.6071798412150506e-06, "loss": 0.3203, "step": 6020 }, { "epoch": 5.610153702841174, "grad_norm": 0.26361997853802444, "learning_rate": 3.5640317569899898e-06, "loss": 0.3168, "step": 6025 }, { "epoch": 5.614811364694923, "grad_norm": 0.2686833548557954, "learning_rate": 3.5208836727649297e-06, "loss": 0.3213, "step": 6030 }, { "epoch": 5.619469026548672, "grad_norm": 0.2493073683687577, "learning_rate": 3.477735588539869e-06, "loss": 0.3174, "step": 6035 }, { "epoch": 5.624126688402422, "grad_norm": 0.2631834541802001, "learning_rate": 3.434587504314809e-06, "loss": 0.3191, "step": 6040 }, { "epoch": 5.628784350256171, "grad_norm": 0.2520653494934578, "learning_rate": 3.3914394200897483e-06, "loss": 0.3235, "step": 6045 }, { "epoch": 5.633442012109921, "grad_norm": 0.25963512074360573, "learning_rate": 3.348291335864688e-06, "loss": 0.3316, "step": 6050 }, { "epoch": 5.63809967396367, "grad_norm": 0.2433513754654855, "learning_rate": 3.3051432516396274e-06, "loss": 0.3201, "step": 6055 }, { "epoch": 5.64275733581742, "grad_norm": 0.254021534835333, "learning_rate": 3.2619951674145674e-06, "loss": 0.3224, "step": 6060 }, { "epoch": 5.647414997671169, "grad_norm": 0.2407148180765517, "learning_rate": 3.2188470831895065e-06, "loss": 0.3193, "step": 6065 }, { "epoch": 5.652072659524919, "grad_norm": 0.24764440272411284, "learning_rate": 3.1756989989644464e-06, "loss": 0.3219, "step": 6070 }, { "epoch": 5.656730321378668, "grad_norm": 0.24775075749099854, "learning_rate": 3.1325509147393856e-06, "loss": 0.3255, "step": 6075 }, { "epoch": 5.661387983232418, "grad_norm": 0.2497585798329685, "learning_rate": 3.089402830514325e-06, "loss": 0.3254, "step": 6080 }, { "epoch": 5.666045645086166, "grad_norm": 0.25603593863758956, "learning_rate": 3.046254746289265e-06, "loss": 0.3286, "step": 6085 }, { "epoch": 5.670703306939917, "grad_norm": 0.2500703197548113, "learning_rate": 3.0031066620642046e-06, "loss": 0.3156, "step": 6090 }, { "epoch": 5.675360968793665, "grad_norm": 0.2534741609791622, "learning_rate": 2.959958577839144e-06, "loss": 0.3163, "step": 6095 }, { "epoch": 5.680018630647415, "grad_norm": 0.24344540392178865, "learning_rate": 2.9168104936140837e-06, "loss": 0.3228, "step": 6100 }, { "epoch": 5.684676292501164, "grad_norm": 0.2570653584234335, "learning_rate": 2.873662409389023e-06, "loss": 0.3273, "step": 6105 }, { "epoch": 5.689333954354914, "grad_norm": 0.2587023698794426, "learning_rate": 2.8305143251639627e-06, "loss": 0.3229, "step": 6110 }, { "epoch": 5.693991616208663, "grad_norm": 0.25716556286991227, "learning_rate": 2.7873662409389023e-06, "loss": 0.3186, "step": 6115 }, { "epoch": 5.698649278062413, "grad_norm": 0.2528863183534424, "learning_rate": 2.7442181567138422e-06, "loss": 0.3273, "step": 6120 }, { "epoch": 5.703306939916162, "grad_norm": 0.26738185869339237, "learning_rate": 2.7010700724887818e-06, "loss": 0.3265, "step": 6125 }, { "epoch": 5.707964601769912, "grad_norm": 0.23807891261882724, "learning_rate": 2.6579219882637213e-06, "loss": 0.3186, "step": 6130 }, { "epoch": 5.712622263623661, "grad_norm": 0.2490587817487366, "learning_rate": 2.614773904038661e-06, "loss": 0.3236, "step": 6135 }, { "epoch": 5.717279925477411, "grad_norm": 0.2534837885598515, "learning_rate": 2.5716258198136004e-06, "loss": 0.3255, "step": 6140 }, { "epoch": 5.72193758733116, "grad_norm": 0.25238661721398836, "learning_rate": 2.52847773558854e-06, "loss": 0.3189, "step": 6145 }, { "epoch": 5.726595249184909, "grad_norm": 0.2485077488258087, "learning_rate": 2.4853296513634795e-06, "loss": 0.3252, "step": 6150 }, { "epoch": 5.731252911038658, "grad_norm": 0.25259224198610286, "learning_rate": 2.442181567138419e-06, "loss": 0.3302, "step": 6155 }, { "epoch": 5.735910572892408, "grad_norm": 0.25126253648080377, "learning_rate": 2.399033482913359e-06, "loss": 0.3277, "step": 6160 }, { "epoch": 5.740568234746157, "grad_norm": 0.2512732897506285, "learning_rate": 2.3558853986882985e-06, "loss": 0.3294, "step": 6165 }, { "epoch": 5.745225896599907, "grad_norm": 0.25100727025125136, "learning_rate": 2.312737314463238e-06, "loss": 0.3164, "step": 6170 }, { "epoch": 5.749883558453656, "grad_norm": 0.25079782757648933, "learning_rate": 2.2695892302381776e-06, "loss": 0.3255, "step": 6175 }, { "epoch": 5.754541220307406, "grad_norm": 0.24557830223207125, "learning_rate": 2.226441146013117e-06, "loss": 0.3238, "step": 6180 }, { "epoch": 5.759198882161155, "grad_norm": 0.2586555113809283, "learning_rate": 2.1832930617880566e-06, "loss": 0.3223, "step": 6185 }, { "epoch": 5.763856544014905, "grad_norm": 0.24481810786064626, "learning_rate": 2.140144977562996e-06, "loss": 0.3182, "step": 6190 }, { "epoch": 5.768514205868654, "grad_norm": 0.24983904667968027, "learning_rate": 2.096996893337936e-06, "loss": 0.3291, "step": 6195 }, { "epoch": 5.773171867722404, "grad_norm": 0.25089229357761356, "learning_rate": 2.0538488091128757e-06, "loss": 0.3264, "step": 6200 }, { "epoch": 5.777829529576152, "grad_norm": 0.2556272143043493, "learning_rate": 2.010700724887815e-06, "loss": 0.3299, "step": 6205 }, { "epoch": 5.782487191429902, "grad_norm": 0.23707866912481357, "learning_rate": 1.9675526406627547e-06, "loss": 0.3198, "step": 6210 }, { "epoch": 5.787144853283651, "grad_norm": 0.24423511484705163, "learning_rate": 1.9244045564376943e-06, "loss": 0.3193, "step": 6215 }, { "epoch": 5.791802515137401, "grad_norm": 0.250975187675256, "learning_rate": 1.8812564722126338e-06, "loss": 0.3194, "step": 6220 }, { "epoch": 5.79646017699115, "grad_norm": 0.2464292640422164, "learning_rate": 1.8381083879875736e-06, "loss": 0.3245, "step": 6225 }, { "epoch": 5.8011178388449, "grad_norm": 0.25162685105147736, "learning_rate": 1.794960303762513e-06, "loss": 0.3327, "step": 6230 }, { "epoch": 5.805775500698649, "grad_norm": 0.2520139786523937, "learning_rate": 1.7518122195374526e-06, "loss": 0.3277, "step": 6235 }, { "epoch": 5.810433162552399, "grad_norm": 0.25082558064757243, "learning_rate": 1.7086641353123924e-06, "loss": 0.3232, "step": 6240 }, { "epoch": 5.815090824406148, "grad_norm": 0.25030417982750025, "learning_rate": 1.665516051087332e-06, "loss": 0.3222, "step": 6245 }, { "epoch": 5.819748486259898, "grad_norm": 0.2581002815450062, "learning_rate": 1.6223679668622715e-06, "loss": 0.3244, "step": 6250 }, { "epoch": 5.824406148113647, "grad_norm": 0.24935831106499434, "learning_rate": 1.579219882637211e-06, "loss": 0.3334, "step": 6255 }, { "epoch": 5.829063809967396, "grad_norm": 0.2516956028203003, "learning_rate": 1.5360717984121505e-06, "loss": 0.3179, "step": 6260 }, { "epoch": 5.833721471821145, "grad_norm": 0.2579353739304209, "learning_rate": 1.49292371418709e-06, "loss": 0.3231, "step": 6265 }, { "epoch": 5.838379133674895, "grad_norm": 0.25057480730505377, "learning_rate": 1.4497756299620296e-06, "loss": 0.3318, "step": 6270 }, { "epoch": 5.843036795528644, "grad_norm": 0.24904486899389905, "learning_rate": 1.4066275457369694e-06, "loss": 0.3243, "step": 6275 }, { "epoch": 5.847694457382394, "grad_norm": 0.24586186859532755, "learning_rate": 1.363479461511909e-06, "loss": 0.3233, "step": 6280 }, { "epoch": 5.852352119236143, "grad_norm": 0.24396316926899028, "learning_rate": 1.3203313772868484e-06, "loss": 0.325, "step": 6285 }, { "epoch": 5.857009781089893, "grad_norm": 0.24891542518010956, "learning_rate": 1.277183293061788e-06, "loss": 0.3185, "step": 6290 }, { "epoch": 5.861667442943642, "grad_norm": 0.2372062842337855, "learning_rate": 1.2340352088367277e-06, "loss": 0.3176, "step": 6295 }, { "epoch": 5.866325104797392, "grad_norm": 0.2433505328239024, "learning_rate": 1.1908871246116673e-06, "loss": 0.3202, "step": 6300 }, { "epoch": 5.870982766651141, "grad_norm": 0.2502370157287282, "learning_rate": 1.1477390403866068e-06, "loss": 0.3137, "step": 6305 }, { "epoch": 5.875640428504891, "grad_norm": 0.24856638485803317, "learning_rate": 1.1045909561615463e-06, "loss": 0.3286, "step": 6310 }, { "epoch": 5.8802980903586395, "grad_norm": 0.24649977530213535, "learning_rate": 1.061442871936486e-06, "loss": 0.3113, "step": 6315 }, { "epoch": 5.88495575221239, "grad_norm": 0.2418744786513444, "learning_rate": 1.0182947877114256e-06, "loss": 0.3202, "step": 6320 }, { "epoch": 5.8896134140661385, "grad_norm": 0.2500585067180137, "learning_rate": 9.751467034863652e-07, "loss": 0.3208, "step": 6325 }, { "epoch": 5.894271075919888, "grad_norm": 0.25375009975067697, "learning_rate": 9.319986192613048e-07, "loss": 0.3308, "step": 6330 }, { "epoch": 5.8989287377736375, "grad_norm": 0.2499109776272833, "learning_rate": 8.888505350362444e-07, "loss": 0.3175, "step": 6335 }, { "epoch": 5.903586399627387, "grad_norm": 0.24947063456117938, "learning_rate": 8.45702450811184e-07, "loss": 0.3167, "step": 6340 }, { "epoch": 5.9082440614811365, "grad_norm": 0.24848980570377643, "learning_rate": 8.025543665861236e-07, "loss": 0.3117, "step": 6345 }, { "epoch": 5.912901723334886, "grad_norm": 0.24686013962856782, "learning_rate": 7.594062823610632e-07, "loss": 0.3225, "step": 6350 }, { "epoch": 5.9175593851886354, "grad_norm": 0.24882083021419651, "learning_rate": 7.162581981360028e-07, "loss": 0.3225, "step": 6355 }, { "epoch": 5.922217047042385, "grad_norm": 0.2456811775279622, "learning_rate": 6.731101139109423e-07, "loss": 0.3143, "step": 6360 }, { "epoch": 5.926874708896134, "grad_norm": 0.2491248488571996, "learning_rate": 6.29962029685882e-07, "loss": 0.3284, "step": 6365 }, { "epoch": 5.931532370749884, "grad_norm": 0.24437502124137397, "learning_rate": 5.868139454608215e-07, "loss": 0.3135, "step": 6370 }, { "epoch": 5.936190032603633, "grad_norm": 0.2491106983696512, "learning_rate": 5.436658612357612e-07, "loss": 0.3329, "step": 6375 }, { "epoch": 5.940847694457382, "grad_norm": 0.2501021996400697, "learning_rate": 5.005177770107007e-07, "loss": 0.3212, "step": 6380 }, { "epoch": 5.9455053563111315, "grad_norm": 0.2500357597141651, "learning_rate": 4.5736969278564034e-07, "loss": 0.3247, "step": 6385 }, { "epoch": 5.950163018164881, "grad_norm": 0.2514734720666558, "learning_rate": 4.142216085605799e-07, "loss": 0.3327, "step": 6390 }, { "epoch": 5.9548206800186305, "grad_norm": 0.2506683114938206, "learning_rate": 3.710735243355195e-07, "loss": 0.3279, "step": 6395 }, { "epoch": 5.95947834187238, "grad_norm": 0.24503482218362424, "learning_rate": 3.279254401104591e-07, "loss": 0.3252, "step": 6400 }, { "epoch": 5.9641360037261295, "grad_norm": 0.24310088967585244, "learning_rate": 2.847773558853987e-07, "loss": 0.3193, "step": 6405 }, { "epoch": 5.968793665579879, "grad_norm": 0.24764148511346176, "learning_rate": 2.416292716603383e-07, "loss": 0.3217, "step": 6410 }, { "epoch": 5.9734513274336285, "grad_norm": 0.23830671386976018, "learning_rate": 1.984811874352779e-07, "loss": 0.3105, "step": 6415 }, { "epoch": 5.978108989287378, "grad_norm": 0.24758534081825365, "learning_rate": 1.5533310321021747e-07, "loss": 0.3142, "step": 6420 }, { "epoch": 5.9827666511411275, "grad_norm": 0.2434213917493329, "learning_rate": 1.1218501898515707e-07, "loss": 0.3219, "step": 6425 }, { "epoch": 5.987424312994877, "grad_norm": 0.24840065368329303, "learning_rate": 6.903693476009665e-08, "loss": 0.3292, "step": 6430 }, { "epoch": 5.992081974848626, "grad_norm": 0.24223025598148082, "learning_rate": 2.5888850535036245e-08, "loss": 0.3246, "step": 6435 }, { "epoch": 5.994876571960876, "step": 6438, "total_flos": 2925479637680128.0, "train_loss": 0.42425346351366083, "train_runtime": 29144.7491, "train_samples_per_second": 3.535, "train_steps_per_second": 0.221 } ], "logging_steps": 5, "max_steps": 6438, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2925479637680128.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }