{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1004, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00796812749003984, "grad_norm": 0.8687085509300232, "learning_rate": 3.921568627450981e-07, "loss": 2.0886306762695312, "step": 2 }, { "epoch": 0.01593625498007968, "grad_norm": 0.8256942629814148, "learning_rate": 1.1764705882352942e-06, "loss": 2.0069615840911865, "step": 4 }, { "epoch": 0.02390438247011952, "grad_norm": 7.175477027893066, "learning_rate": 1.96078431372549e-06, "loss": 2.1241238117218018, "step": 6 }, { "epoch": 0.03187250996015936, "grad_norm": 0.5740149617195129, "learning_rate": 2.7450980392156867e-06, "loss": 1.8192579746246338, "step": 8 }, { "epoch": 0.0398406374501992, "grad_norm": 0.9182372093200684, "learning_rate": 3.529411764705883e-06, "loss": 1.282393455505371, "step": 10 }, { "epoch": 0.04780876494023904, "grad_norm": 0.5668178796768188, "learning_rate": 4.313725490196079e-06, "loss": 1.586937665939331, "step": 12 }, { "epoch": 0.055776892430278883, "grad_norm": 0.509973406791687, "learning_rate": 5.098039215686274e-06, "loss": 1.6420693397521973, "step": 14 }, { "epoch": 0.06374501992031872, "grad_norm": 8.057994842529297, "learning_rate": 5.882352941176471e-06, "loss": 1.7643235921859741, "step": 16 }, { "epoch": 0.07171314741035857, "grad_norm": 10.05883502960205, "learning_rate": 6.666666666666667e-06, "loss": 1.5502036809921265, "step": 18 }, { "epoch": 0.0796812749003984, "grad_norm": 0.6553092002868652, "learning_rate": 7.450980392156863e-06, "loss": 1.4846529960632324, "step": 20 }, { "epoch": 0.08764940239043825, "grad_norm": 0.5488642454147339, "learning_rate": 8.23529411764706e-06, "loss": 1.144375205039978, "step": 22 }, { "epoch": 0.09561752988047809, "grad_norm": 0.6479690670967102, "learning_rate": 9.019607843137256e-06, "loss": 1.2942190170288086, "step": 24 }, { "epoch": 0.10358565737051793, "grad_norm": 0.27360522747039795, "learning_rate": 9.803921568627451e-06, "loss": 1.4014755487442017, "step": 26 }, { "epoch": 0.11155378486055777, "grad_norm": 0.4664228558540344, "learning_rate": 1.0588235294117648e-05, "loss": 1.6535426378250122, "step": 28 }, { "epoch": 0.11952191235059761, "grad_norm": 0.8422274589538574, "learning_rate": 1.1372549019607844e-05, "loss": 1.3123046159744263, "step": 30 }, { "epoch": 0.12749003984063745, "grad_norm": 0.6282227635383606, "learning_rate": 1.215686274509804e-05, "loss": 1.153808832168579, "step": 32 }, { "epoch": 0.13545816733067728, "grad_norm": 1.4378248453140259, "learning_rate": 1.2941176470588238e-05, "loss": 1.2372275590896606, "step": 34 }, { "epoch": 0.14342629482071714, "grad_norm": 0.4517601728439331, "learning_rate": 1.3725490196078432e-05, "loss": 1.3791842460632324, "step": 36 }, { "epoch": 0.15139442231075698, "grad_norm": 0.9697667360305786, "learning_rate": 1.4509803921568629e-05, "loss": 1.1730167865753174, "step": 38 }, { "epoch": 0.1593625498007968, "grad_norm": 0.3961893916130066, "learning_rate": 1.5294117647058822e-05, "loss": 1.292687177658081, "step": 40 }, { "epoch": 0.16733067729083664, "grad_norm": 1.2038718461990356, "learning_rate": 1.607843137254902e-05, "loss": 0.8232792615890503, "step": 42 }, { "epoch": 0.1752988047808765, "grad_norm": 0.4270932078361511, "learning_rate": 1.686274509803922e-05, "loss": 0.9939359426498413, "step": 44 }, { "epoch": 0.18326693227091634, "grad_norm": 0.7167245149612427, "learning_rate": 1.7647058823529414e-05, "loss": 0.9492533802986145, "step": 46 }, { "epoch": 0.19123505976095617, "grad_norm": 0.45268625020980835, "learning_rate": 1.843137254901961e-05, "loss": 1.1746896505355835, "step": 48 }, { "epoch": 0.199203187250996, "grad_norm": 0.41129186749458313, "learning_rate": 1.9215686274509807e-05, "loss": 1.3339111804962158, "step": 50 }, { "epoch": 0.20717131474103587, "grad_norm": 0.4729901850223541, "learning_rate": 2e-05, "loss": 1.2871543169021606, "step": 52 }, { "epoch": 0.2151394422310757, "grad_norm": 1.602961778640747, "learning_rate": 1.9999804392782173e-05, "loss": 1.207393765449524, "step": 54 }, { "epoch": 0.22310756972111553, "grad_norm": 0.46118712425231934, "learning_rate": 1.9999217579631398e-05, "loss": 1.5350557565689087, "step": 56 }, { "epoch": 0.23107569721115537, "grad_norm": 0.8428758382797241, "learning_rate": 1.9998239586055426e-05, "loss": 1.3389298915863037, "step": 58 }, { "epoch": 0.23904382470119523, "grad_norm": 0.30435454845428467, "learning_rate": 1.999687045456595e-05, "loss": 0.7883101105690002, "step": 60 }, { "epoch": 0.24701195219123506, "grad_norm": 0.37775376439094543, "learning_rate": 1.9995110244676744e-05, "loss": 1.3454675674438477, "step": 62 }, { "epoch": 0.2549800796812749, "grad_norm": 0.5100111365318298, "learning_rate": 1.999295903290109e-05, "loss": 1.1524405479431152, "step": 64 }, { "epoch": 0.26294820717131473, "grad_norm": 0.3763675093650818, "learning_rate": 1.999041691274844e-05, "loss": 1.2753775119781494, "step": 66 }, { "epoch": 0.27091633466135456, "grad_norm": 2.065988063812256, "learning_rate": 1.998748399472037e-05, "loss": 1.1413958072662354, "step": 68 }, { "epoch": 0.2788844621513944, "grad_norm": 0.4919253885746002, "learning_rate": 1.9984160406305745e-05, "loss": 1.6083652973175049, "step": 70 }, { "epoch": 0.2868525896414343, "grad_norm": 0.816326916217804, "learning_rate": 1.9980446291975217e-05, "loss": 0.9345599412918091, "step": 72 }, { "epoch": 0.2948207171314741, "grad_norm": 0.6255055665969849, "learning_rate": 1.99763418131749e-05, "loss": 1.1615979671478271, "step": 74 }, { "epoch": 0.30278884462151395, "grad_norm": 0.5406404733657837, "learning_rate": 1.9971847148319392e-05, "loss": 1.4970171451568604, "step": 76 }, { "epoch": 0.3107569721115538, "grad_norm": 1.2664341926574707, "learning_rate": 1.9966962492784006e-05, "loss": 1.1129828691482544, "step": 78 }, { "epoch": 0.3187250996015936, "grad_norm": 0.3932921290397644, "learning_rate": 1.996168805889627e-05, "loss": 0.9678430557250977, "step": 80 }, { "epoch": 0.32669322709163345, "grad_norm": 0.7051851153373718, "learning_rate": 1.99560240759267e-05, "loss": 1.42896568775177, "step": 82 }, { "epoch": 0.3346613545816733, "grad_norm": 0.461885541677475, "learning_rate": 1.9949970790078847e-05, "loss": 0.9989966154098511, "step": 84 }, { "epoch": 0.3426294820717131, "grad_norm": 0.3382815718650818, "learning_rate": 1.9943528464478573e-05, "loss": 1.3530247211456299, "step": 86 }, { "epoch": 0.350597609561753, "grad_norm": 0.6359050869941711, "learning_rate": 1.993669737916263e-05, "loss": 1.0272246599197388, "step": 88 }, { "epoch": 0.35856573705179284, "grad_norm": 0.4157576560974121, "learning_rate": 1.9929477831066485e-05, "loss": 1.3488913774490356, "step": 90 }, { "epoch": 0.3665338645418327, "grad_norm": 0.5085843205451965, "learning_rate": 1.992187013401141e-05, "loss": 1.1709015369415283, "step": 92 }, { "epoch": 0.3745019920318725, "grad_norm": 0.3481963872909546, "learning_rate": 1.9913874618690837e-05, "loss": 1.2576426267623901, "step": 94 }, { "epoch": 0.38247011952191234, "grad_norm": 0.5730408430099487, "learning_rate": 1.9905491632655996e-05, "loss": 1.142296314239502, "step": 96 }, { "epoch": 0.3904382470119522, "grad_norm": 0.34298205375671387, "learning_rate": 1.989672154030078e-05, "loss": 1.2693374156951904, "step": 98 }, { "epoch": 0.398406374501992, "grad_norm": 0.34943079948425293, "learning_rate": 1.988756472284595e-05, "loss": 0.903995931148529, "step": 100 }, { "epoch": 0.4063745019920319, "grad_norm": 0.3412981927394867, "learning_rate": 1.9878021578322518e-05, "loss": 1.2715134620666504, "step": 102 }, { "epoch": 0.41434262948207173, "grad_norm": 0.29975271224975586, "learning_rate": 1.9868092521554478e-05, "loss": 1.042019248008728, "step": 104 }, { "epoch": 0.42231075697211157, "grad_norm": 2.0418882369995117, "learning_rate": 1.9857777984140746e-05, "loss": 0.7882804870605469, "step": 106 }, { "epoch": 0.4302788844621514, "grad_norm": 0.5299073457717896, "learning_rate": 1.9847078414436438e-05, "loss": 1.0833579301834106, "step": 108 }, { "epoch": 0.43824701195219123, "grad_norm": 0.335245817899704, "learning_rate": 1.983599427753334e-05, "loss": 1.2959026098251343, "step": 110 }, { "epoch": 0.44621513944223107, "grad_norm": 0.5007705688476562, "learning_rate": 1.9824526055239712e-05, "loss": 0.92479407787323, "step": 112 }, { "epoch": 0.4541832669322709, "grad_norm": 0.5642781257629395, "learning_rate": 1.981267424605935e-05, "loss": 1.1809154748916626, "step": 114 }, { "epoch": 0.46215139442231074, "grad_norm": 0.32401934266090393, "learning_rate": 1.98004393651699e-05, "loss": 1.2920209169387817, "step": 116 }, { "epoch": 0.4701195219123506, "grad_norm": 0.31211525201797485, "learning_rate": 1.9787821944400477e-05, "loss": 1.3557462692260742, "step": 118 }, { "epoch": 0.47808764940239046, "grad_norm": 0.34074831008911133, "learning_rate": 1.9774822532208537e-05, "loss": 1.2343910932540894, "step": 120 }, { "epoch": 0.4860557768924303, "grad_norm": 0.4543141722679138, "learning_rate": 1.9761441693656052e-05, "loss": 1.018692970275879, "step": 122 }, { "epoch": 0.4940239043824701, "grad_norm": 0.7025930881500244, "learning_rate": 1.974768001038493e-05, "loss": 1.0649566650390625, "step": 124 }, { "epoch": 0.50199203187251, "grad_norm": 0.3762131333351135, "learning_rate": 1.973353808059175e-05, "loss": 0.9526509642601013, "step": 126 }, { "epoch": 0.5099601593625498, "grad_norm": 0.33326825499534607, "learning_rate": 1.9719016519001738e-05, "loss": 1.2880756855010986, "step": 128 }, { "epoch": 0.5179282868525896, "grad_norm": 0.2846304774284363, "learning_rate": 1.9704115956842066e-05, "loss": 0.9497164487838745, "step": 130 }, { "epoch": 0.5258964143426295, "grad_norm": 0.4433225095272064, "learning_rate": 1.9688837041814396e-05, "loss": 0.9790914058685303, "step": 132 }, { "epoch": 0.5338645418326693, "grad_norm": 0.4545140564441681, "learning_rate": 1.967318043806675e-05, "loss": 0.9353604316711426, "step": 134 }, { "epoch": 0.5418326693227091, "grad_norm": 0.3878089189529419, "learning_rate": 1.965714682616461e-05, "loss": 1.3441240787506104, "step": 136 }, { "epoch": 0.549800796812749, "grad_norm": 2.243861436843872, "learning_rate": 1.9640736903061363e-05, "loss": 0.9743496775627136, "step": 138 }, { "epoch": 0.5577689243027888, "grad_norm": 0.9255803227424622, "learning_rate": 1.9623951382067983e-05, "loss": 1.113278865814209, "step": 140 }, { "epoch": 0.5657370517928287, "grad_norm": 0.2995326519012451, "learning_rate": 1.960679099282204e-05, "loss": 1.0455888509750366, "step": 142 }, { "epoch": 0.5737051792828686, "grad_norm": 0.29048699140548706, "learning_rate": 1.9589256481255984e-05, "loss": 1.2361657619476318, "step": 144 }, { "epoch": 0.5816733067729084, "grad_norm": 0.45288383960723877, "learning_rate": 1.9571348609564697e-05, "loss": 1.191515326499939, "step": 146 }, { "epoch": 0.5896414342629482, "grad_norm": 0.4257696270942688, "learning_rate": 1.9553068156172404e-05, "loss": 1.0653226375579834, "step": 148 }, { "epoch": 0.5976095617529881, "grad_norm": 0.8186884522438049, "learning_rate": 1.9534415915698793e-05, "loss": 0.9824154376983643, "step": 150 }, { "epoch": 0.6055776892430279, "grad_norm": 0.33720093965530396, "learning_rate": 1.9515392698924504e-05, "loss": 0.9725387096405029, "step": 152 }, { "epoch": 0.6135458167330677, "grad_norm": 0.9997106194496155, "learning_rate": 1.949599933275587e-05, "loss": 1.1494280099868774, "step": 154 }, { "epoch": 0.6215139442231076, "grad_norm": 1.5014402866363525, "learning_rate": 1.9476236660188982e-05, "loss": 1.0726919174194336, "step": 156 }, { "epoch": 0.6294820717131474, "grad_norm": 0.7345775365829468, "learning_rate": 1.9456105540273035e-05, "loss": 1.194985270500183, "step": 158 }, { "epoch": 0.6374501992031872, "grad_norm": 0.3693063259124756, "learning_rate": 1.9435606848073003e-05, "loss": 1.0574865341186523, "step": 160 }, { "epoch": 0.6454183266932271, "grad_norm": 0.16802608966827393, "learning_rate": 1.9414741474631586e-05, "loss": 0.7915345430374146, "step": 162 }, { "epoch": 0.6533864541832669, "grad_norm": 0.24361276626586914, "learning_rate": 1.939351032693048e-05, "loss": 1.1572449207305908, "step": 164 }, { "epoch": 0.6613545816733067, "grad_norm": 0.2987329065799713, "learning_rate": 1.9371914327850958e-05, "loss": 0.880090057849884, "step": 166 }, { "epoch": 0.6693227091633466, "grad_norm": 0.757393479347229, "learning_rate": 1.934995441613376e-05, "loss": 1.2498260736465454, "step": 168 }, { "epoch": 0.6772908366533864, "grad_norm": 1.6156872510910034, "learning_rate": 1.9327631546338263e-05, "loss": 1.065740704536438, "step": 170 }, { "epoch": 0.6852589641434262, "grad_norm": 0.285990446805954, "learning_rate": 1.9304946688801014e-05, "loss": 0.9508867859840393, "step": 172 }, { "epoch": 0.6932270916334662, "grad_norm": 0.2722166180610657, "learning_rate": 1.9281900829593544e-05, "loss": 1.246326208114624, "step": 174 }, { "epoch": 0.701195219123506, "grad_norm": 0.6919268369674683, "learning_rate": 1.9258494970479494e-05, "loss": 0.8008362054824829, "step": 176 }, { "epoch": 0.7091633466135459, "grad_norm": 0.7445635795593262, "learning_rate": 1.923473012887109e-05, "loss": 0.9828277826309204, "step": 178 }, { "epoch": 0.7171314741035857, "grad_norm": 0.55351722240448, "learning_rate": 1.9210607337784885e-05, "loss": 1.158448576927185, "step": 180 }, { "epoch": 0.7250996015936255, "grad_norm": 0.13257816433906555, "learning_rate": 1.9186127645796902e-05, "loss": 0.5361558198928833, "step": 182 }, { "epoch": 0.7330677290836654, "grad_norm": 0.24445906281471252, "learning_rate": 1.916129211699701e-05, "loss": 1.3766955137252808, "step": 184 }, { "epoch": 0.7410358565737052, "grad_norm": 0.4627974033355713, "learning_rate": 1.91361018309427e-05, "loss": 1.304077386856079, "step": 186 }, { "epoch": 0.749003984063745, "grad_norm": 0.26658743619918823, "learning_rate": 1.911055788261214e-05, "loss": 1.151049256324768, "step": 188 }, { "epoch": 0.7569721115537849, "grad_norm": 0.3607999086380005, "learning_rate": 1.9084661382356592e-05, "loss": 0.9221289157867432, "step": 190 }, { "epoch": 0.7649402390438247, "grad_norm": 1.0667331218719482, "learning_rate": 1.9058413455852142e-05, "loss": 1.2540066242218018, "step": 192 }, { "epoch": 0.7729083665338645, "grad_norm": 0.35192084312438965, "learning_rate": 1.9031815244050752e-05, "loss": 0.9460887908935547, "step": 194 }, { "epoch": 0.7808764940239044, "grad_norm": 0.39151957631111145, "learning_rate": 1.9004867903130694e-05, "loss": 0.6812059283256531, "step": 196 }, { "epoch": 0.7888446215139442, "grad_norm": 0.4794232249259949, "learning_rate": 1.897757260444628e-05, "loss": 0.7969710826873779, "step": 198 }, { "epoch": 0.796812749003984, "grad_norm": 0.4055477976799011, "learning_rate": 1.8949930534476938e-05, "loss": 1.0776989459991455, "step": 200 }, { "epoch": 0.8047808764940239, "grad_norm": 0.13282935321331024, "learning_rate": 1.892194289477565e-05, "loss": 1.0324515104293823, "step": 202 }, { "epoch": 0.8127490039840638, "grad_norm": 0.31035351753234863, "learning_rate": 1.8893610901916707e-05, "loss": 1.5635279417037964, "step": 204 }, { "epoch": 0.8207171314741036, "grad_norm": 0.34337109327316284, "learning_rate": 1.886493578744284e-05, "loss": 1.242823600769043, "step": 206 }, { "epoch": 0.8286852589641435, "grad_norm": 0.1983502358198166, "learning_rate": 1.8835918797811693e-05, "loss": 0.6256985068321228, "step": 208 }, { "epoch": 0.8366533864541833, "grad_norm": 0.34944215416908264, "learning_rate": 1.880656119434162e-05, "loss": 1.284050464630127, "step": 210 }, { "epoch": 0.8446215139442231, "grad_norm": 0.22934027016162872, "learning_rate": 1.8776864253156875e-05, "loss": 1.2318283319473267, "step": 212 }, { "epoch": 0.852589641434263, "grad_norm": 0.2371150404214859, "learning_rate": 1.874682926513213e-05, "loss": 0.9791166186332703, "step": 214 }, { "epoch": 0.8605577689243028, "grad_norm": 1.4798812866210938, "learning_rate": 1.871645753583638e-05, "loss": 1.452410340309143, "step": 216 }, { "epoch": 0.8685258964143426, "grad_norm": 0.7958971858024597, "learning_rate": 1.8685750385476166e-05, "loss": 0.916776716709137, "step": 218 }, { "epoch": 0.8764940239043825, "grad_norm": 1.7680853605270386, "learning_rate": 1.8654709148838218e-05, "loss": 1.2467654943466187, "step": 220 }, { "epoch": 0.8844621513944223, "grad_norm": 0.6561282873153687, "learning_rate": 1.8623335175231402e-05, "loss": 1.5111079216003418, "step": 222 }, { "epoch": 0.8924302788844621, "grad_norm": 1.2204989194869995, "learning_rate": 1.85916298284281e-05, "loss": 0.7252726554870605, "step": 224 }, { "epoch": 0.900398406374502, "grad_norm": 0.29036325216293335, "learning_rate": 1.8559594486604905e-05, "loss": 1.0382778644561768, "step": 226 }, { "epoch": 0.9083665338645418, "grad_norm": 0.6182889938354492, "learning_rate": 1.8527230542282724e-05, "loss": 1.1135358810424805, "step": 228 }, { "epoch": 0.9163346613545816, "grad_norm": 0.3456054925918579, "learning_rate": 1.849453940226625e-05, "loss": 1.1879663467407227, "step": 230 }, { "epoch": 0.9243027888446215, "grad_norm": 0.5696732401847839, "learning_rate": 1.8461522487582803e-05, "loss": 1.3329076766967773, "step": 232 }, { "epoch": 0.9322709163346613, "grad_norm": 0.38616132736206055, "learning_rate": 1.8428181233420565e-05, "loss": 0.8451637029647827, "step": 234 }, { "epoch": 0.9402390438247012, "grad_norm": 0.25511351227760315, "learning_rate": 1.8394517089066197e-05, "loss": 0.8644623756408691, "step": 236 }, { "epoch": 0.9482071713147411, "grad_norm": 0.2771114408969879, "learning_rate": 1.8360531517841832e-05, "loss": 0.5260741114616394, "step": 238 }, { "epoch": 0.9561752988047809, "grad_norm": 1.012864589691162, "learning_rate": 1.8326225997041482e-05, "loss": 0.9196873903274536, "step": 240 }, { "epoch": 0.9641434262948207, "grad_norm": 0.35297006368637085, "learning_rate": 1.8291602017866806e-05, "loss": 1.1390161514282227, "step": 242 }, { "epoch": 0.9721115537848606, "grad_norm": 0.30612561106681824, "learning_rate": 1.8256661085362308e-05, "loss": 1.2218761444091797, "step": 244 }, { "epoch": 0.9800796812749004, "grad_norm": 0.6584000587463379, "learning_rate": 1.8221404718349888e-05, "loss": 0.9740089774131775, "step": 246 }, { "epoch": 0.9880478087649402, "grad_norm": 0.4018401801586151, "learning_rate": 1.8185834449362855e-05, "loss": 1.025275468826294, "step": 248 }, { "epoch": 0.9960159362549801, "grad_norm": 1.4323194026947021, "learning_rate": 1.8149951824579283e-05, "loss": 1.0199095010757446, "step": 250 }, { "epoch": 1.00398406374502, "grad_norm": 0.341948926448822, "learning_rate": 1.8113758403754823e-05, "loss": 0.9343042373657227, "step": 252 }, { "epoch": 1.0119521912350598, "grad_norm": 0.38058942556381226, "learning_rate": 1.8077255760154883e-05, "loss": 0.7046458721160889, "step": 254 }, { "epoch": 1.0199203187250996, "grad_norm": 0.5085623860359192, "learning_rate": 1.8040445480486254e-05, "loss": 1.0890356302261353, "step": 256 }, { "epoch": 1.0278884462151394, "grad_norm": 0.4822426438331604, "learning_rate": 1.8003329164828133e-05, "loss": 1.0524687767028809, "step": 258 }, { "epoch": 1.0358565737051793, "grad_norm": 0.38201844692230225, "learning_rate": 1.7965908426562582e-05, "loss": 0.9374608993530273, "step": 260 }, { "epoch": 1.043824701195219, "grad_norm": 0.4644787311553955, "learning_rate": 1.7928184892304366e-05, "loss": 0.9212496876716614, "step": 262 }, { "epoch": 1.051792828685259, "grad_norm": 0.721108078956604, "learning_rate": 1.789016020183029e-05, "loss": 1.007407546043396, "step": 264 }, { "epoch": 1.0597609561752988, "grad_norm": 0.7453786730766296, "learning_rate": 1.7851836008007883e-05, "loss": 0.75822514295578, "step": 266 }, { "epoch": 1.0677290836653386, "grad_norm": 1.0901387929916382, "learning_rate": 1.781321397672358e-05, "loss": 0.8778277039527893, "step": 268 }, { "epoch": 1.0756972111553784, "grad_norm": 0.289546400308609, "learning_rate": 1.777429578681029e-05, "loss": 0.5031875371932983, "step": 270 }, { "epoch": 1.0836653386454183, "grad_norm": 0.48452669382095337, "learning_rate": 1.7735083129974423e-05, "loss": 1.1954156160354614, "step": 272 }, { "epoch": 1.091633466135458, "grad_norm": 0.5753158330917358, "learning_rate": 1.769557771072236e-05, "loss": 0.6099209189414978, "step": 274 }, { "epoch": 1.099601593625498, "grad_norm": 0.4469282329082489, "learning_rate": 1.7655781246286345e-05, "loss": 0.8086526989936829, "step": 276 }, { "epoch": 1.1075697211155378, "grad_norm": 0.8727370500564575, "learning_rate": 1.761569546654988e-05, "loss": 0.7694612741470337, "step": 278 }, { "epoch": 1.1155378486055776, "grad_norm": 0.4654983580112457, "learning_rate": 1.7575322113972472e-05, "loss": 0.9192116260528564, "step": 280 }, { "epoch": 1.1235059760956174, "grad_norm": 0.31477856636047363, "learning_rate": 1.753466294351395e-05, "loss": 1.049499750137329, "step": 282 }, { "epoch": 1.1314741035856573, "grad_norm": 0.4698004126548767, "learning_rate": 1.7493719722558135e-05, "loss": 1.1166934967041016, "step": 284 }, { "epoch": 1.139442231075697, "grad_norm": 0.20743758976459503, "learning_rate": 1.7452494230836034e-05, "loss": 0.3405384123325348, "step": 286 }, { "epoch": 1.1474103585657371, "grad_norm": 0.21572747826576233, "learning_rate": 1.741098826034848e-05, "loss": 0.6110213994979858, "step": 288 }, { "epoch": 1.155378486055777, "grad_norm": 0.9294064044952393, "learning_rate": 1.7369203615288227e-05, "loss": 0.86930912733078, "step": 290 }, { "epoch": 1.1633466135458168, "grad_norm": 0.9067952036857605, "learning_rate": 1.7327142111961537e-05, "loss": 0.7051547169685364, "step": 292 }, { "epoch": 1.1713147410358566, "grad_norm": 0.3776642382144928, "learning_rate": 1.7284805578709218e-05, "loss": 1.1381611824035645, "step": 294 }, { "epoch": 1.1792828685258965, "grad_norm": 0.20979639887809753, "learning_rate": 1.724219585582716e-05, "loss": 1.2165122032165527, "step": 296 }, { "epoch": 1.1872509960159363, "grad_norm": 0.3244563043117523, "learning_rate": 1.7199314795486325e-05, "loss": 1.2280006408691406, "step": 298 }, { "epoch": 1.1952191235059761, "grad_norm": 0.7252885699272156, "learning_rate": 1.7156164261652247e-05, "loss": 0.6707150340080261, "step": 300 }, { "epoch": 1.203187250996016, "grad_norm": 0.3757059574127197, "learning_rate": 1.711274613000401e-05, "loss": 0.8710638880729675, "step": 302 }, { "epoch": 1.2111553784860558, "grad_norm": 0.30097636580467224, "learning_rate": 1.7069062287852717e-05, "loss": 0.5094844102859497, "step": 304 }, { "epoch": 1.2191235059760956, "grad_norm": 0.48242101073265076, "learning_rate": 1.702511463405943e-05, "loss": 1.133294701576233, "step": 306 }, { "epoch": 1.2270916334661355, "grad_norm": 0.7108588814735413, "learning_rate": 1.698090507895266e-05, "loss": 0.9296752214431763, "step": 308 }, { "epoch": 1.2350597609561753, "grad_norm": 0.41015177965164185, "learning_rate": 1.693643554424532e-05, "loss": 1.068943738937378, "step": 310 }, { "epoch": 1.2430278884462151, "grad_norm": 0.34054386615753174, "learning_rate": 1.6891707962951173e-05, "loss": 1.0081392526626587, "step": 312 }, { "epoch": 1.250996015936255, "grad_norm": 2.2303950786590576, "learning_rate": 1.684672427930083e-05, "loss": 0.8653253316879272, "step": 314 }, { "epoch": 1.2589641434262948, "grad_norm": 0.3943715989589691, "learning_rate": 1.680148644865722e-05, "loss": 0.7365275621414185, "step": 316 }, { "epoch": 1.2669322709163346, "grad_norm": 0.33673974871635437, "learning_rate": 1.6755996437430622e-05, "loss": 0.6356416344642639, "step": 318 }, { "epoch": 1.2749003984063745, "grad_norm": 0.9208086729049683, "learning_rate": 1.6710256222993137e-05, "loss": 0.5271879434585571, "step": 320 }, { "epoch": 1.2828685258964143, "grad_norm": 0.45602428913116455, "learning_rate": 1.6664267793592797e-05, "loss": 0.9226617217063904, "step": 322 }, { "epoch": 1.2908366533864541, "grad_norm": 0.5400494337081909, "learning_rate": 1.661803314826709e-05, "loss": 0.8759934902191162, "step": 324 }, { "epoch": 1.298804780876494, "grad_norm": 1.4296598434448242, "learning_rate": 1.65715542967561e-05, "loss": 1.1430692672729492, "step": 326 }, { "epoch": 1.3067729083665338, "grad_norm": 0.3259183168411255, "learning_rate": 1.652483325941511e-05, "loss": 0.7194448709487915, "step": 328 }, { "epoch": 1.3147410358565736, "grad_norm": 0.40675562620162964, "learning_rate": 1.647787206712683e-05, "loss": 0.7846541404724121, "step": 330 }, { "epoch": 1.3227091633466135, "grad_norm": 0.5686507821083069, "learning_rate": 1.6430672761213065e-05, "loss": 0.8795408010482788, "step": 332 }, { "epoch": 1.3306772908366533, "grad_norm": 0.5391749739646912, "learning_rate": 1.6383237393346025e-05, "loss": 0.5901771187782288, "step": 334 }, { "epoch": 1.3386454183266931, "grad_norm": 1.5842124223709106, "learning_rate": 1.633556802545911e-05, "loss": 0.8455764651298523, "step": 336 }, { "epoch": 1.3466135458167332, "grad_norm": 0.6567497253417969, "learning_rate": 1.628766672965731e-05, "loss": 1.0685632228851318, "step": 338 }, { "epoch": 1.354581673306773, "grad_norm": 0.28743740916252136, "learning_rate": 1.6239535588127107e-05, "loss": 1.0498569011688232, "step": 340 }, { "epoch": 1.3625498007968129, "grad_norm": 0.24235428869724274, "learning_rate": 1.6191176693046e-05, "loss": 1.1290383338928223, "step": 342 }, { "epoch": 1.3705179282868527, "grad_norm": 0.27160707116127014, "learning_rate": 1.6142592146491517e-05, "loss": 1.0615555047988892, "step": 344 }, { "epoch": 1.3784860557768925, "grad_norm": 0.5951285362243652, "learning_rate": 1.6093784060349876e-05, "loss": 0.6895939111709595, "step": 346 }, { "epoch": 1.3864541832669324, "grad_norm": 0.267936646938324, "learning_rate": 1.6044754556224178e-05, "loss": 1.1047388315200806, "step": 348 }, { "epoch": 1.3944223107569722, "grad_norm": 0.2702598571777344, "learning_rate": 1.5995505765342176e-05, "loss": 0.6365596055984497, "step": 350 }, { "epoch": 1.402390438247012, "grad_norm": 0.3268156051635742, "learning_rate": 1.594603982846364e-05, "loss": 1.1005016565322876, "step": 352 }, { "epoch": 1.4103585657370519, "grad_norm": 0.49795475602149963, "learning_rate": 1.5896358895787304e-05, "loss": 1.080939769744873, "step": 354 }, { "epoch": 1.4183266932270917, "grad_norm": 0.6326602101325989, "learning_rate": 1.5846465126857386e-05, "loss": 0.8446483612060547, "step": 356 }, { "epoch": 1.4262948207171315, "grad_norm": 0.3423049747943878, "learning_rate": 1.579636069046975e-05, "loss": 1.112828016281128, "step": 358 }, { "epoch": 1.4342629482071714, "grad_norm": 0.331617534160614, "learning_rate": 1.5746047764577586e-05, "loss": 0.556983470916748, "step": 360 }, { "epoch": 1.4422310756972112, "grad_norm": 0.7952442169189453, "learning_rate": 1.5695528536196774e-05, "loss": 0.7050241827964783, "step": 362 }, { "epoch": 1.450199203187251, "grad_norm": 0.49163997173309326, "learning_rate": 1.564480520131081e-05, "loss": 1.011673927307129, "step": 364 }, { "epoch": 1.4581673306772909, "grad_norm": 0.5051209330558777, "learning_rate": 1.559387996477534e-05, "loss": 1.0447050333023071, "step": 366 }, { "epoch": 1.4661354581673307, "grad_norm": 0.4506257474422455, "learning_rate": 1.5542755040222325e-05, "loss": 0.5882746577262878, "step": 368 }, { "epoch": 1.4741035856573705, "grad_norm": 0.3848789930343628, "learning_rate": 1.5491432649963823e-05, "loss": 0.6615412831306458, "step": 370 }, { "epoch": 1.4820717131474104, "grad_norm": 1.171698808670044, "learning_rate": 1.543991502489538e-05, "loss": 1.2864530086517334, "step": 372 }, { "epoch": 1.4900398406374502, "grad_norm": 0.4419739544391632, "learning_rate": 1.5388204404399073e-05, "loss": 1.0378817319869995, "step": 374 }, { "epoch": 1.49800796812749, "grad_norm": 0.23308596014976501, "learning_rate": 1.533630303624614e-05, "loss": 1.0560197830200195, "step": 376 }, { "epoch": 1.5059760956175299, "grad_norm": 0.8023196458816528, "learning_rate": 1.5284213176499302e-05, "loss": 0.8570104241371155, "step": 378 }, { "epoch": 1.5139442231075697, "grad_norm": 0.3250346779823303, "learning_rate": 1.5231937089414675e-05, "loss": 1.092508316040039, "step": 380 }, { "epoch": 1.5219123505976095, "grad_norm": 0.25869283080101013, "learning_rate": 1.517947704734337e-05, "loss": 0.6813873648643494, "step": 382 }, { "epoch": 1.5298804780876494, "grad_norm": 0.28996741771698, "learning_rate": 1.5126835330632677e-05, "loss": 0.6645854115486145, "step": 384 }, { "epoch": 1.5378486055776892, "grad_norm": 1.5717236995697021, "learning_rate": 1.5074014227526997e-05, "loss": 0.9236294031143188, "step": 386 }, { "epoch": 1.545816733067729, "grad_norm": 0.32109910249710083, "learning_rate": 1.502101603406833e-05, "loss": 1.0823489427566528, "step": 388 }, { "epoch": 1.5537848605577689, "grad_norm": 0.7276486158370972, "learning_rate": 1.4967843053996494e-05, "loss": 0.5451988577842712, "step": 390 }, { "epoch": 1.5617529880478087, "grad_norm": 0.3085494041442871, "learning_rate": 1.4914497598648973e-05, "loss": 0.5751717686653137, "step": 392 }, { "epoch": 1.5697211155378485, "grad_norm": 1.1126803159713745, "learning_rate": 1.4860981986860464e-05, "loss": 1.058145523071289, "step": 394 }, { "epoch": 1.5776892430278884, "grad_norm": 0.6459108591079712, "learning_rate": 1.4807298544862054e-05, "loss": 0.9958094358444214, "step": 396 }, { "epoch": 1.5856573705179282, "grad_norm": 0.20127789676189423, "learning_rate": 1.4753449606180137e-05, "loss": 1.0852116346359253, "step": 398 }, { "epoch": 1.593625498007968, "grad_norm": 0.3237609565258026, "learning_rate": 1.4699437511534947e-05, "loss": 0.6027621030807495, "step": 400 }, { "epoch": 1.6015936254980079, "grad_norm": 0.4658999443054199, "learning_rate": 1.4645264608738832e-05, "loss": 1.0461393594741821, "step": 402 }, { "epoch": 1.6095617529880477, "grad_norm": 0.22849686443805695, "learning_rate": 1.4590933252594193e-05, "loss": 1.1783668994903564, "step": 404 }, { "epoch": 1.6175298804780875, "grad_norm": 0.464072585105896, "learning_rate": 1.4536445804791125e-05, "loss": 0.699569582939148, "step": 406 }, { "epoch": 1.6254980079681274, "grad_norm": 0.18738897144794464, "learning_rate": 1.4481804633804746e-05, "loss": 0.5158436894416809, "step": 408 }, { "epoch": 1.6334661354581672, "grad_norm": 0.4792879521846771, "learning_rate": 1.4427012114792269e-05, "loss": 0.7027358412742615, "step": 410 }, { "epoch": 1.641434262948207, "grad_norm": 0.2847132980823517, "learning_rate": 1.4372070629489744e-05, "loss": 0.4589526355266571, "step": 412 }, { "epoch": 1.6494023904382469, "grad_norm": 0.16233396530151367, "learning_rate": 1.4316982566108515e-05, "loss": 0.7499012351036072, "step": 414 }, { "epoch": 1.6573705179282867, "grad_norm": 0.34753382205963135, "learning_rate": 1.4261750319231432e-05, "loss": 0.7557674050331116, "step": 416 }, { "epoch": 1.6653386454183265, "grad_norm": 0.5319584608078003, "learning_rate": 1.4206376289708752e-05, "loss": 0.8566523194313049, "step": 418 }, { "epoch": 1.6733067729083664, "grad_norm": 0.291802316904068, "learning_rate": 1.4150862884553776e-05, "loss": 1.1130759716033936, "step": 420 }, { "epoch": 1.6812749003984062, "grad_norm": 0.19954712688922882, "learning_rate": 1.4095212516838216e-05, "loss": 0.9514334201812744, "step": 422 }, { "epoch": 1.6892430278884463, "grad_norm": 0.3112265467643738, "learning_rate": 1.4039427605587326e-05, "loss": 0.5233280062675476, "step": 424 }, { "epoch": 1.697211155378486, "grad_norm": 0.20384936034679413, "learning_rate": 1.398351057567472e-05, "loss": 1.1268967390060425, "step": 426 }, { "epoch": 1.705179282868526, "grad_norm": 0.21102385222911835, "learning_rate": 1.392746385771699e-05, "loss": 1.063062071800232, "step": 428 }, { "epoch": 1.7131474103585658, "grad_norm": 0.3036285936832428, "learning_rate": 1.3871289887968034e-05, "loss": 0.6780144572257996, "step": 430 }, { "epoch": 1.7211155378486056, "grad_norm": 0.7043957114219666, "learning_rate": 1.3814991108213173e-05, "loss": 0.8546534776687622, "step": 432 }, { "epoch": 1.7290836653386454, "grad_norm": 0.360525518655777, "learning_rate": 1.3758569965663011e-05, "loss": 0.6243395805358887, "step": 434 }, { "epoch": 1.7370517928286853, "grad_norm": 0.8308858871459961, "learning_rate": 1.370202891284703e-05, "loss": 0.43398115038871765, "step": 436 }, { "epoch": 1.745019920318725, "grad_norm": 0.3703770935535431, "learning_rate": 1.3645370407507017e-05, "loss": 0.738655149936676, "step": 438 }, { "epoch": 1.752988047808765, "grad_norm": 2.820668935775757, "learning_rate": 1.3588596912490222e-05, "loss": 0.7261440753936768, "step": 440 }, { "epoch": 1.7609561752988048, "grad_norm": 0.43590405583381653, "learning_rate": 1.3531710895642288e-05, "loss": 1.3262492418289185, "step": 442 }, { "epoch": 1.7689243027888446, "grad_norm": 0.34120041131973267, "learning_rate": 1.3474714829699987e-05, "loss": 0.7070552706718445, "step": 444 }, { "epoch": 1.7768924302788844, "grad_norm": 0.18316373229026794, "learning_rate": 1.341761119218374e-05, "loss": 1.004502773284912, "step": 446 }, { "epoch": 1.7848605577689243, "grad_norm": 0.3774756193161011, "learning_rate": 1.3360402465289916e-05, "loss": 1.0533740520477295, "step": 448 }, { "epoch": 1.792828685258964, "grad_norm": 0.21326151490211487, "learning_rate": 1.3303091135782942e-05, "loss": 0.8273346424102783, "step": 450 }, { "epoch": 1.800796812749004, "grad_norm": 0.2267659306526184, "learning_rate": 1.3245679694887192e-05, "loss": 0.42468857765197754, "step": 452 }, { "epoch": 1.8087649402390438, "grad_norm": 0.5060834288597107, "learning_rate": 1.318817063817872e-05, "loss": 0.8974787592887878, "step": 454 }, { "epoch": 1.8167330677290838, "grad_norm": 0.48161670565605164, "learning_rate": 1.3130566465476773e-05, "loss": 0.6163372993469238, "step": 456 }, { "epoch": 1.8247011952191237, "grad_norm": 0.2777350842952728, "learning_rate": 1.307286968073511e-05, "loss": 0.9941050410270691, "step": 458 }, { "epoch": 1.8326693227091635, "grad_norm": 0.488695353269577, "learning_rate": 1.3015082791933182e-05, "loss": 0.7475647926330566, "step": 460 }, { "epoch": 1.8406374501992033, "grad_norm": 0.24865223467350006, "learning_rate": 1.295720831096712e-05, "loss": 0.8023468255996704, "step": 462 }, { "epoch": 1.8486055776892432, "grad_norm": 0.17197415232658386, "learning_rate": 1.2899248753540518e-05, "loss": 0.1325809210538864, "step": 464 }, { "epoch": 1.856573705179283, "grad_norm": 1.5523875951766968, "learning_rate": 1.2841206639055108e-05, "loss": 1.1007118225097656, "step": 466 }, { "epoch": 1.8645418326693228, "grad_norm": 0.5094614624977112, "learning_rate": 1.2783084490501229e-05, "loss": 0.514072060585022, "step": 468 }, { "epoch": 1.8725099601593627, "grad_norm": 0.35147467255592346, "learning_rate": 1.2724884834348163e-05, "loss": 1.0952625274658203, "step": 470 }, { "epoch": 1.8804780876494025, "grad_norm": 0.36751729249954224, "learning_rate": 1.266661020043432e-05, "loss": 0.9377644658088684, "step": 472 }, { "epoch": 1.8884462151394423, "grad_norm": 0.4373418092727661, "learning_rate": 1.2608263121857244e-05, "loss": 0.9737136960029602, "step": 474 }, { "epoch": 1.8964143426294822, "grad_norm": 0.19097857177257538, "learning_rate": 1.254984613486355e-05, "loss": 0.9451252222061157, "step": 476 }, { "epoch": 1.904382470119522, "grad_norm": 0.42185327410697937, "learning_rate": 1.2491361778738631e-05, "loss": 0.7926995158195496, "step": 478 }, { "epoch": 1.9123505976095618, "grad_norm": 0.5808318257331848, "learning_rate": 1.243281259569631e-05, "loss": 0.5798477530479431, "step": 480 }, { "epoch": 1.9203187250996017, "grad_norm": 0.5500463247299194, "learning_rate": 1.2374201130768325e-05, "loss": 0.7669761180877686, "step": 482 }, { "epoch": 1.9282868525896415, "grad_norm": 0.21460963785648346, "learning_rate": 1.2315529931693682e-05, "loss": 1.054688811302185, "step": 484 }, { "epoch": 1.9362549800796813, "grad_norm": 0.2985857129096985, "learning_rate": 1.2256801548807948e-05, "loss": 0.9884510040283203, "step": 486 }, { "epoch": 1.9442231075697212, "grad_norm": 0.22740538418293, "learning_rate": 1.2198018534932367e-05, "loss": 1.0773851871490479, "step": 488 }, { "epoch": 1.952191235059761, "grad_norm": 0.1833743005990982, "learning_rate": 1.2139183445262892e-05, "loss": 1.0440764427185059, "step": 490 }, { "epoch": 1.9601593625498008, "grad_norm": 0.26161497831344604, "learning_rate": 1.2080298837259124e-05, "loss": 0.7149063348770142, "step": 492 }, { "epoch": 1.9681274900398407, "grad_norm": 2.253765821456909, "learning_rate": 1.2021367270533138e-05, "loss": 0.7989740967750549, "step": 494 }, { "epoch": 1.9760956175298805, "grad_norm": 0.28019073605537415, "learning_rate": 1.1962391306738226e-05, "loss": 1.0134761333465576, "step": 496 }, { "epoch": 1.9840637450199203, "grad_norm": 0.6458740234375, "learning_rate": 1.190337350945754e-05, "loss": 0.823985755443573, "step": 498 }, { "epoch": 1.9920318725099602, "grad_norm": 0.298125684261322, "learning_rate": 1.1844316444092667e-05, "loss": 1.132564902305603, "step": 500 }, { "epoch": 2.0, "grad_norm": 0.3069063127040863, "learning_rate": 1.1785222677752105e-05, "loss": 0.6213638782501221, "step": 502 }, { "epoch": 2.00796812749004, "grad_norm": 0.2165108621120453, "learning_rate": 1.1726094779139685e-05, "loss": 0.5043126344680786, "step": 504 }, { "epoch": 2.0159362549800797, "grad_norm": 0.4651063084602356, "learning_rate": 1.1666935318442905e-05, "loss": 0.44121354818344116, "step": 506 }, { "epoch": 2.0239043824701195, "grad_norm": 0.08969016373157501, "learning_rate": 1.1607746867221208e-05, "loss": 0.4672836661338806, "step": 508 }, { "epoch": 2.0318725099601593, "grad_norm": 0.38188546895980835, "learning_rate": 1.1548531998294217e-05, "loss": 0.7249612808227539, "step": 510 }, { "epoch": 2.039840637450199, "grad_norm": 0.2776472866535187, "learning_rate": 1.148929328562987e-05, "loss": 0.6245005130767822, "step": 512 }, { "epoch": 2.047808764940239, "grad_norm": 0.6827823519706726, "learning_rate": 1.1430033304232569e-05, "loss": 0.3463484048843384, "step": 514 }, { "epoch": 2.055776892430279, "grad_norm": 0.4058661162853241, "learning_rate": 1.137075463003122e-05, "loss": 0.7836011052131653, "step": 516 }, { "epoch": 2.0637450199203187, "grad_norm": 12.217242240905762, "learning_rate": 1.1311459839767278e-05, "loss": 0.4506489038467407, "step": 518 }, { "epoch": 2.0717131474103585, "grad_norm": 3.7635204792022705, "learning_rate": 1.1252151510882731e-05, "loss": 0.6491232514381409, "step": 520 }, { "epoch": 2.0796812749003983, "grad_norm": 0.39710062742233276, "learning_rate": 1.1192832221408068e-05, "loss": 0.8215765953063965, "step": 522 }, { "epoch": 2.087649402390438, "grad_norm": 0.4940469563007355, "learning_rate": 1.1133504549850218e-05, "loss": 0.7698899507522583, "step": 524 }, { "epoch": 2.095617529880478, "grad_norm": 0.536239504814148, "learning_rate": 1.1074171075080469e-05, "loss": 0.36201098561286926, "step": 526 }, { "epoch": 2.103585657370518, "grad_norm": 0.8106605410575867, "learning_rate": 1.1014834376222351e-05, "loss": 0.5792776942253113, "step": 528 }, { "epoch": 2.1115537848605577, "grad_norm": 0.15770025551319122, "learning_rate": 1.0955497032539557e-05, "loss": 0.44848746061325073, "step": 530 }, { "epoch": 2.1195219123505975, "grad_norm": 0.24326692521572113, "learning_rate": 1.0896161623323795e-05, "loss": 0.1985977292060852, "step": 532 }, { "epoch": 2.1274900398406373, "grad_norm": 1.5041277408599854, "learning_rate": 1.0836830727782692e-05, "loss": 0.612493634223938, "step": 534 }, { "epoch": 2.135458167330677, "grad_norm": 1.0610326528549194, "learning_rate": 1.0777506924927667e-05, "loss": 0.6036497950553894, "step": 536 }, { "epoch": 2.143426294820717, "grad_norm": 0.6076405644416809, "learning_rate": 1.0718192793461849e-05, "loss": 0.6230844855308533, "step": 538 }, { "epoch": 2.151394422310757, "grad_norm": 0.36088430881500244, "learning_rate": 1.065889091166795e-05, "loss": 0.7613107562065125, "step": 540 }, { "epoch": 2.1593625498007967, "grad_norm": 0.3054327964782715, "learning_rate": 1.059960385729621e-05, "loss": 0.6941779851913452, "step": 542 }, { "epoch": 2.1673306772908365, "grad_norm": 0.24954797327518463, "learning_rate": 1.0540334207452363e-05, "loss": 0.47066619992256165, "step": 544 }, { "epoch": 2.1752988047808763, "grad_norm": 0.2986539900302887, "learning_rate": 1.0481084538485589e-05, "loss": 0.5359241366386414, "step": 546 }, { "epoch": 2.183266932270916, "grad_norm": 0.3956416845321655, "learning_rate": 1.0421857425876524e-05, "loss": 0.7813495397567749, "step": 548 }, { "epoch": 2.191235059760956, "grad_norm": 0.3207624852657318, "learning_rate": 1.0362655444125334e-05, "loss": 0.8096965551376343, "step": 550 }, { "epoch": 2.199203187250996, "grad_norm": 0.4274860620498657, "learning_rate": 1.0303481166639784e-05, "loss": 0.509590208530426, "step": 552 }, { "epoch": 2.2071713147410357, "grad_norm": 0.5321890711784363, "learning_rate": 1.0244337165623378e-05, "loss": 0.453169047832489, "step": 554 }, { "epoch": 2.2151394422310755, "grad_norm": 0.5689948797225952, "learning_rate": 1.0185226011963563e-05, "loss": 0.6031365990638733, "step": 556 }, { "epoch": 2.2231075697211153, "grad_norm": 2.9450175762176514, "learning_rate": 1.0126150275119958e-05, "loss": 0.8096473813056946, "step": 558 }, { "epoch": 2.231075697211155, "grad_norm": 0.4231691062450409, "learning_rate": 1.0067112523012686e-05, "loss": 0.7732781767845154, "step": 560 }, { "epoch": 2.239043824701195, "grad_norm": 0.31910139322280884, "learning_rate": 1.0008115321910729e-05, "loss": 0.8720684051513672, "step": 562 }, { "epoch": 2.247011952191235, "grad_norm": 6.204998016357422, "learning_rate": 9.949161236320388e-06, "loss": 0.5987430214881897, "step": 564 }, { "epoch": 2.2549800796812747, "grad_norm": 0.29381808638572693, "learning_rate": 9.890252828873816e-06, "loss": 0.4853253960609436, "step": 566 }, { "epoch": 2.2629482071713145, "grad_norm": 0.2391190379858017, "learning_rate": 9.831392660217608e-06, "loss": 0.6356629729270935, "step": 568 }, { "epoch": 2.2709163346613543, "grad_norm": 0.35715413093566895, "learning_rate": 9.772583288901502e-06, "loss": 0.7994184494018555, "step": 570 }, { "epoch": 2.278884462151394, "grad_norm": 0.8083705306053162, "learning_rate": 9.713827271267169e-06, "loss": 0.5638254284858704, "step": 572 }, { "epoch": 2.2868525896414345, "grad_norm": 0.25096696615219116, "learning_rate": 9.655127161337088e-06, "loss": 0.5889987349510193, "step": 574 }, { "epoch": 2.2948207171314743, "grad_norm": 0.2611815333366394, "learning_rate": 9.59648551070351e-06, "loss": 0.2555178701877594, "step": 576 }, { "epoch": 2.302788844621514, "grad_norm": 0.5718734264373779, "learning_rate": 9.53790486841759e-06, "loss": 0.5340811014175415, "step": 578 }, { "epoch": 2.310756972111554, "grad_norm": 0.3825013339519501, "learning_rate": 9.479387780878531e-06, "loss": 0.5315930247306824, "step": 580 }, { "epoch": 2.318725099601594, "grad_norm": 0.685142457485199, "learning_rate": 9.42093679172294e-06, "loss": 0.4931807219982147, "step": 582 }, { "epoch": 2.3266932270916336, "grad_norm": 0.657268762588501, "learning_rate": 9.362554441714216e-06, "loss": 0.624793529510498, "step": 584 }, { "epoch": 2.3346613545816735, "grad_norm": 0.36978161334991455, "learning_rate": 9.304243268632165e-06, "loss": 0.5345178842544556, "step": 586 }, { "epoch": 2.3426294820717133, "grad_norm": 0.6148081421852112, "learning_rate": 9.246005807162632e-06, "loss": 0.6727567911148071, "step": 588 }, { "epoch": 2.350597609561753, "grad_norm": 0.299528568983078, "learning_rate": 9.187844588787354e-06, "loss": 0.7979969382286072, "step": 590 }, { "epoch": 2.358565737051793, "grad_norm": 0.37552663683891296, "learning_rate": 9.12976214167391e-06, "loss": 0.8545841574668884, "step": 592 }, { "epoch": 2.366533864541833, "grad_norm": 0.31660106778144836, "learning_rate": 9.071760990565832e-06, "loss": 0.5427640676498413, "step": 594 }, { "epoch": 2.3745019920318726, "grad_norm": 0.2705290913581848, "learning_rate": 9.013843656672854e-06, "loss": 0.7104488015174866, "step": 596 }, { "epoch": 2.3824701195219125, "grad_norm": 0.27716466784477234, "learning_rate": 8.956012657561314e-06, "loss": 0.5637896060943604, "step": 598 }, { "epoch": 2.3904382470119523, "grad_norm": 2.9362845420837402, "learning_rate": 8.89827050704474e-06, "loss": 0.6183806657791138, "step": 600 }, { "epoch": 2.398406374501992, "grad_norm": 0.2689732313156128, "learning_rate": 8.840619715074553e-06, "loss": 0.7946896553039551, "step": 602 }, { "epoch": 2.406374501992032, "grad_norm": 0.23491685092449188, "learning_rate": 8.78306278763098e-06, "loss": 0.4485781192779541, "step": 604 }, { "epoch": 2.414342629482072, "grad_norm": 0.9759865999221802, "learning_rate": 8.725602226614121e-06, "loss": 0.2319762110710144, "step": 606 }, { "epoch": 2.4223107569721116, "grad_norm": 0.15988869965076447, "learning_rate": 8.668240529735192e-06, "loss": 0.3493569493293762, "step": 608 }, { "epoch": 2.4302788844621515, "grad_norm": 0.17206406593322754, "learning_rate": 8.610980190407958e-06, "loss": 0.6467002630233765, "step": 610 }, { "epoch": 2.4382470119521913, "grad_norm": 0.25553181767463684, "learning_rate": 8.55382369764034e-06, "loss": 0.583063006401062, "step": 612 }, { "epoch": 2.446215139442231, "grad_norm": 0.3950878381729126, "learning_rate": 8.496773535926242e-06, "loss": 0.46504709124565125, "step": 614 }, { "epoch": 2.454183266932271, "grad_norm": 0.26962918043136597, "learning_rate": 8.439832185137529e-06, "loss": 0.6895124912261963, "step": 616 }, { "epoch": 2.462151394422311, "grad_norm": 0.41879427433013916, "learning_rate": 8.383002120416241e-06, "loss": 0.5566327571868896, "step": 618 }, { "epoch": 2.4701195219123506, "grad_norm": 1.4798431396484375, "learning_rate": 8.326285812067023e-06, "loss": 0.6534566879272461, "step": 620 }, { "epoch": 2.4780876494023905, "grad_norm": 0.307312548160553, "learning_rate": 8.269685725449708e-06, "loss": 0.6504800915718079, "step": 622 }, { "epoch": 2.4860557768924303, "grad_norm": 0.5427370071411133, "learning_rate": 8.213204320872176e-06, "loss": 0.6383635997772217, "step": 624 }, { "epoch": 2.49402390438247, "grad_norm": 0.26320162415504456, "learning_rate": 8.156844053483412e-06, "loss": 0.4011181890964508, "step": 626 }, { "epoch": 2.50199203187251, "grad_norm": 0.37865692377090454, "learning_rate": 8.100607373166773e-06, "loss": 0.7987120151519775, "step": 628 }, { "epoch": 2.50996015936255, "grad_norm": 0.4195093512535095, "learning_rate": 8.044496724433493e-06, "loss": 0.2998882532119751, "step": 630 }, { "epoch": 2.5179282868525896, "grad_norm": 0.9238357543945312, "learning_rate": 7.988514546316437e-06, "loss": 0.34079158306121826, "step": 632 }, { "epoch": 2.5258964143426295, "grad_norm": 0.27209165692329407, "learning_rate": 7.932663272264079e-06, "loss": 0.8152284622192383, "step": 634 }, { "epoch": 2.5338645418326693, "grad_norm": 0.3044971227645874, "learning_rate": 7.87694533003471e-06, "loss": 0.7516045570373535, "step": 636 }, { "epoch": 2.541832669322709, "grad_norm": 0.5729214549064636, "learning_rate": 7.82136314159092e-06, "loss": 0.8303281664848328, "step": 638 }, { "epoch": 2.549800796812749, "grad_norm": 0.19276340305805206, "learning_rate": 7.765919122994319e-06, "loss": 0.29311320185661316, "step": 640 }, { "epoch": 2.557768924302789, "grad_norm": 0.4937683045864105, "learning_rate": 7.710615684300518e-06, "loss": 0.7855862379074097, "step": 642 }, { "epoch": 2.5657370517928286, "grad_norm": 0.2187207043170929, "learning_rate": 7.655455229454354e-06, "loss": 0.7239468097686768, "step": 644 }, { "epoch": 2.5737051792828685, "grad_norm": 1.5033259391784668, "learning_rate": 7.6004401561854e-06, "loss": 0.5276362299919128, "step": 646 }, { "epoch": 2.5816733067729083, "grad_norm": 0.33054134249687195, "learning_rate": 7.545572855903756e-06, "loss": 0.7969309687614441, "step": 648 }, { "epoch": 2.589641434262948, "grad_norm": 0.3152036666870117, "learning_rate": 7.490855713596081e-06, "loss": 0.6026449203491211, "step": 650 }, { "epoch": 2.597609561752988, "grad_norm": 0.33109569549560547, "learning_rate": 7.4362911077219155e-06, "loss": 0.5262701511383057, "step": 652 }, { "epoch": 2.605577689243028, "grad_norm": 0.29034096002578735, "learning_rate": 7.381881410110326e-06, "loss": 0.6021281480789185, "step": 654 }, { "epoch": 2.6135458167330676, "grad_norm": 0.25865310430526733, "learning_rate": 7.327628985856765e-06, "loss": 0.25670185685157776, "step": 656 }, { "epoch": 2.6215139442231075, "grad_norm": 0.39587166905403137, "learning_rate": 7.2735361932202965e-06, "loss": 0.47300997376441956, "step": 658 }, { "epoch": 2.6294820717131473, "grad_norm": 0.32333165407180786, "learning_rate": 7.219605383521067e-06, "loss": 0.6984432935714722, "step": 660 }, { "epoch": 2.637450199203187, "grad_norm": 0.8259761929512024, "learning_rate": 7.165838901038107e-06, "loss": 0.5749056935310364, "step": 662 }, { "epoch": 2.645418326693227, "grad_norm": 1.1761703491210938, "learning_rate": 7.112239082907433e-06, "loss": 0.452744722366333, "step": 664 }, { "epoch": 2.653386454183267, "grad_norm": 0.3080389201641083, "learning_rate": 7.058808259020442e-06, "loss": 0.7340803146362305, "step": 666 }, { "epoch": 2.6613545816733066, "grad_norm": 0.13718551397323608, "learning_rate": 7.005548751922642e-06, "loss": 0.5631315112113953, "step": 668 }, { "epoch": 2.6693227091633465, "grad_norm": 0.48113957047462463, "learning_rate": 6.952462876712707e-06, "loss": 0.5454351305961609, "step": 670 }, { "epoch": 2.6772908366533863, "grad_norm": 0.10773833841085434, "learning_rate": 6.899552940941829e-06, "loss": 0.27837103605270386, "step": 672 }, { "epoch": 2.685258964143426, "grad_norm": 0.22576193511486053, "learning_rate": 6.846821244513411e-06, "loss": 0.8114858865737915, "step": 674 }, { "epoch": 2.6932270916334664, "grad_norm": 0.784417450428009, "learning_rate": 6.794270079583101e-06, "loss": 0.5748249292373657, "step": 676 }, { "epoch": 2.7011952191235062, "grad_norm": 0.3679204285144806, "learning_rate": 6.741901730459166e-06, "loss": 0.4891148507595062, "step": 678 }, { "epoch": 2.709163346613546, "grad_norm": 0.29442018270492554, "learning_rate": 6.68971847350317e-06, "loss": 0.8089858293533325, "step": 680 }, { "epoch": 2.717131474103586, "grad_norm": 0.22440965473651886, "learning_rate": 6.6377225770310514e-06, "loss": 0.8312827348709106, "step": 682 }, { "epoch": 2.7250996015936257, "grad_norm": 0.8225514888763428, "learning_rate": 6.585916301214519e-06, "loss": 0.5896182656288147, "step": 684 }, { "epoch": 2.7330677290836656, "grad_norm": 3.1597442626953125, "learning_rate": 6.534301897982774e-06, "loss": 0.3686487376689911, "step": 686 }, { "epoch": 2.7410358565737054, "grad_norm": 0.24462340772151947, "learning_rate": 6.482881610924674e-06, "loss": 0.8054239749908447, "step": 688 }, { "epoch": 2.7490039840637452, "grad_norm": 1.4142591953277588, "learning_rate": 6.43165767519117e-06, "loss": 0.4302287697792053, "step": 690 }, { "epoch": 2.756972111553785, "grad_norm": 0.3220599293708801, "learning_rate": 6.380632317398168e-06, "loss": 0.9143630862236023, "step": 692 }, { "epoch": 2.764940239043825, "grad_norm": 0.6856467723846436, "learning_rate": 6.3298077555297245e-06, "loss": 0.6507794857025146, "step": 694 }, { "epoch": 2.7729083665338647, "grad_norm": 0.4382452070713043, "learning_rate": 6.279186198841647e-06, "loss": 0.3969390094280243, "step": 696 }, { "epoch": 2.7808764940239046, "grad_norm": 0.2783852219581604, "learning_rate": 6.228769847765468e-06, "loss": 0.626663327217102, "step": 698 }, { "epoch": 2.7888446215139444, "grad_norm": 0.2537877857685089, "learning_rate": 6.178560893812774e-06, "loss": 0.8403069376945496, "step": 700 }, { "epoch": 2.7968127490039842, "grad_norm": 0.1850716918706894, "learning_rate": 6.1285615194799695e-06, "loss": 0.48170754313468933, "step": 702 }, { "epoch": 2.804780876494024, "grad_norm": 0.4740298390388489, "learning_rate": 6.0787738981533825e-06, "loss": 0.8492451906204224, "step": 704 }, { "epoch": 2.812749003984064, "grad_norm": 0.20938153564929962, "learning_rate": 6.0292001940148174e-06, "loss": 0.7743903398513794, "step": 706 }, { "epoch": 2.8207171314741037, "grad_norm": 0.3462710380554199, "learning_rate": 5.979842561947455e-06, "loss": 0.8912703990936279, "step": 708 }, { "epoch": 2.8286852589641436, "grad_norm": 0.2809637188911438, "learning_rate": 5.9307031474422074e-06, "loss": 0.43541547656059265, "step": 710 }, { "epoch": 2.8366533864541834, "grad_norm": 0.20937590301036835, "learning_rate": 5.88178408650445e-06, "loss": 0.9104054570198059, "step": 712 }, { "epoch": 2.8446215139442232, "grad_norm": 0.2386903315782547, "learning_rate": 5.833087505561148e-06, "loss": 0.5239242315292358, "step": 714 }, { "epoch": 2.852589641434263, "grad_norm": 0.3977036476135254, "learning_rate": 5.784615521368468e-06, "loss": 0.7960683107376099, "step": 716 }, { "epoch": 2.860557768924303, "grad_norm": 0.9357836842536926, "learning_rate": 5.736370240919735e-06, "loss": 0.5691960453987122, "step": 718 }, { "epoch": 2.8685258964143427, "grad_norm": 0.204420268535614, "learning_rate": 5.688353761353862e-06, "loss": 0.49336379766464233, "step": 720 }, { "epoch": 2.8764940239043826, "grad_norm": 0.2908172607421875, "learning_rate": 5.640568169864173e-06, "loss": 0.4811123311519623, "step": 722 }, { "epoch": 2.8844621513944224, "grad_norm": 0.5298336148262024, "learning_rate": 5.5930155436076875e-06, "loss": 0.565929114818573, "step": 724 }, { "epoch": 2.8924302788844622, "grad_norm": 0.1939915418624878, "learning_rate": 5.5456979496148385e-06, "loss": 0.7743662595748901, "step": 726 }, { "epoch": 2.900398406374502, "grad_norm": 0.2288486510515213, "learning_rate": 5.498617444699603e-06, "loss": 0.46328917145729065, "step": 728 }, { "epoch": 2.908366533864542, "grad_norm": 0.35470640659332275, "learning_rate": 5.451776075370114e-06, "loss": 0.7746002674102783, "step": 730 }, { "epoch": 2.9163346613545817, "grad_norm": 0.39310505986213684, "learning_rate": 5.405175877739684e-06, "loss": 0.22616282105445862, "step": 732 }, { "epoch": 2.9243027888446216, "grad_norm": 0.27109962701797485, "learning_rate": 5.3588188774383235e-06, "loss": 0.8417502641677856, "step": 734 }, { "epoch": 2.9322709163346614, "grad_norm": 1.1222072839736938, "learning_rate": 5.3127070895246604e-06, "loss": 0.3744705617427826, "step": 736 }, { "epoch": 2.9402390438247012, "grad_norm": 0.9205291867256165, "learning_rate": 5.266842518398369e-06, "loss": 0.5713416934013367, "step": 738 }, { "epoch": 2.948207171314741, "grad_norm": 0.26441994309425354, "learning_rate": 5.2212271577130495e-06, "loss": 0.848888635635376, "step": 740 }, { "epoch": 2.956175298804781, "grad_norm": 0.9064684510231018, "learning_rate": 5.1758629902895375e-06, "loss": 0.25246933102607727, "step": 742 }, { "epoch": 2.9641434262948207, "grad_norm": 0.6127145886421204, "learning_rate": 5.1307519880297385e-06, "loss": 0.6468943953514099, "step": 744 }, { "epoch": 2.9721115537848606, "grad_norm": 0.4546615779399872, "learning_rate": 5.085896111830908e-06, "loss": 0.6896576881408691, "step": 746 }, { "epoch": 2.9800796812749004, "grad_norm": 0.5989493727684021, "learning_rate": 5.041297311500417e-06, "loss": 0.3880175054073334, "step": 748 }, { "epoch": 2.9880478087649402, "grad_norm": 0.24675695598125458, "learning_rate": 4.996957525670984e-06, "loss": 0.12411849945783615, "step": 750 }, { "epoch": 2.99601593625498, "grad_norm": 0.26221850514411926, "learning_rate": 4.952878681716416e-06, "loss": 0.7962881922721863, "step": 752 }, { "epoch": 3.00398406374502, "grad_norm": 0.34225115180015564, "learning_rate": 4.9090626956678355e-06, "loss": 0.3844722807407379, "step": 754 }, { "epoch": 3.0119521912350598, "grad_norm": 0.3443976640701294, "learning_rate": 4.865511472130379e-06, "loss": 0.35608866810798645, "step": 756 }, { "epoch": 3.0199203187250996, "grad_norm": 0.2815234661102295, "learning_rate": 4.822226904200422e-06, "loss": 0.17388103902339935, "step": 758 }, { "epoch": 3.0278884462151394, "grad_norm": 0.29143962264060974, "learning_rate": 4.779210873383273e-06, "loss": 0.3388209342956543, "step": 760 }, { "epoch": 3.0358565737051793, "grad_norm": 1.1175932884216309, "learning_rate": 4.7364652495114e-06, "loss": 0.3835744559764862, "step": 762 }, { "epoch": 3.043824701195219, "grad_norm": 0.3416759967803955, "learning_rate": 4.693991890663152e-06, "loss": 0.5161765813827515, "step": 764 }, { "epoch": 3.051792828685259, "grad_norm": 0.2444799840450287, "learning_rate": 4.651792643081986e-06, "loss": 0.17736996710300446, "step": 766 }, { "epoch": 3.0597609561752988, "grad_norm": 0.28991037607192993, "learning_rate": 4.609869341096217e-06, "loss": 0.37515631318092346, "step": 768 }, { "epoch": 3.0677290836653386, "grad_norm": 0.32158225774765015, "learning_rate": 4.568223807039282e-06, "loss": 0.3763376772403717, "step": 770 }, { "epoch": 3.0756972111553784, "grad_norm": 0.34686094522476196, "learning_rate": 4.52685785117052e-06, "loss": 0.5709128975868225, "step": 772 }, { "epoch": 3.0836653386454183, "grad_norm": 0.7250041961669922, "learning_rate": 4.485773271596503e-06, "loss": 0.5019816160202026, "step": 774 }, { "epoch": 3.091633466135458, "grad_norm": 0.054395563900470734, "learning_rate": 4.444971854192848e-06, "loss": 0.3104590177536011, "step": 776 }, { "epoch": 3.099601593625498, "grad_norm": 0.2409711331129074, "learning_rate": 4.404455372526615e-06, "loss": 0.33854958415031433, "step": 778 }, { "epoch": 3.1075697211155378, "grad_norm": 0.2990105450153351, "learning_rate": 4.3642255877791876e-06, "loss": 0.5261071920394897, "step": 780 }, { "epoch": 3.1155378486055776, "grad_norm": 0.09115161001682281, "learning_rate": 4.324284248669742e-06, "loss": 0.11824757605791092, "step": 782 }, { "epoch": 3.1235059760956174, "grad_norm": 0.2456287443637848, "learning_rate": 4.2846330913792136e-06, "loss": 0.6229012608528137, "step": 784 }, { "epoch": 3.1314741035856573, "grad_norm": 0.4126826524734497, "learning_rate": 4.245273839474835e-06, "loss": 0.41413745284080505, "step": 786 }, { "epoch": 3.139442231075697, "grad_norm": 0.7544516324996948, "learning_rate": 4.20620820383523e-06, "loss": 0.3049668073654175, "step": 788 }, { "epoch": 3.147410358565737, "grad_norm": 0.1292313188314438, "learning_rate": 4.167437882576009e-06, "loss": 0.2927045524120331, "step": 790 }, { "epoch": 3.1553784860557768, "grad_norm": 0.5389977693557739, "learning_rate": 4.128964560975993e-06, "loss": 0.38354364037513733, "step": 792 }, { "epoch": 3.1633466135458166, "grad_norm": 0.05460236594080925, "learning_rate": 4.090789911403938e-06, "loss": 0.1887034922838211, "step": 794 }, { "epoch": 3.1713147410358564, "grad_norm": 0.4996011257171631, "learning_rate": 4.0529155932458444e-06, "loss": 0.33719515800476074, "step": 796 }, { "epoch": 3.1792828685258963, "grad_norm": 0.3487769365310669, "learning_rate": 4.015343252832824e-06, "loss": 0.3880740702152252, "step": 798 }, { "epoch": 3.187250996015936, "grad_norm": 0.3392852544784546, "learning_rate": 3.978074523369533e-06, "loss": 0.4826694428920746, "step": 800 }, { "epoch": 3.195219123505976, "grad_norm": 0.20547737181186676, "learning_rate": 3.941111024863193e-06, "loss": 0.38525742292404175, "step": 802 }, { "epoch": 3.2031872509960158, "grad_norm": 0.3879428207874298, "learning_rate": 3.90445436405316e-06, "loss": 0.25935789942741394, "step": 804 }, { "epoch": 3.2111553784860556, "grad_norm": 0.6928282976150513, "learning_rate": 3.86810613434109e-06, "loss": 0.4072348177433014, "step": 806 }, { "epoch": 3.2191235059760954, "grad_norm": 0.4690568745136261, "learning_rate": 3.832067915721661e-06, "loss": 0.0453445203602314, "step": 808 }, { "epoch": 3.2270916334661353, "grad_norm": 0.24398498237133026, "learning_rate": 3.7963412747139204e-06, "loss": 0.3684697151184082, "step": 810 }, { "epoch": 3.235059760956175, "grad_norm": 0.45747777819633484, "learning_rate": 3.7609277642931642e-06, "loss": 0.27333521842956543, "step": 812 }, { "epoch": 3.243027888446215, "grad_norm": 0.2253321260213852, "learning_rate": 3.725828923823447e-06, "loss": 0.45263350009918213, "step": 814 }, { "epoch": 3.2509960159362548, "grad_norm": 0.40673020482063293, "learning_rate": 3.6910462789906697e-06, "loss": 0.0962015688419342, "step": 816 }, { "epoch": 3.2589641434262946, "grad_norm": 0.4036368429660797, "learning_rate": 3.6565813417362476e-06, "loss": 0.5429524779319763, "step": 818 }, { "epoch": 3.2669322709163344, "grad_norm": 0.5956811904907227, "learning_rate": 3.622435610191398e-06, "loss": 0.20509321987628937, "step": 820 }, { "epoch": 3.2749003984063743, "grad_norm": 1.8914116621017456, "learning_rate": 3.5886105686120267e-06, "loss": 0.20021887123584747, "step": 822 }, { "epoch": 3.2828685258964145, "grad_norm": 0.8176438212394714, "learning_rate": 3.5551076873141875e-06, "loss": 0.3322441577911377, "step": 824 }, { "epoch": 3.2908366533864544, "grad_norm": 0.24719004333019257, "learning_rate": 3.5219284226101992e-06, "loss": 0.521284818649292, "step": 826 }, { "epoch": 3.298804780876494, "grad_norm": 0.4595783054828644, "learning_rate": 3.4890742167453134e-06, "loss": 0.660916268825531, "step": 828 }, { "epoch": 3.306772908366534, "grad_norm": 0.32658329606056213, "learning_rate": 3.4565464978350447e-06, "loss": 0.4208177924156189, "step": 830 }, { "epoch": 3.314741035856574, "grad_norm": 0.2831469178199768, "learning_rate": 3.4243466798030813e-06, "loss": 0.23003339767456055, "step": 832 }, { "epoch": 3.3227091633466137, "grad_norm": 1.099875569343567, "learning_rate": 3.3924761623198276e-06, "loss": 0.17236332595348358, "step": 834 }, { "epoch": 3.3306772908366535, "grad_norm": 0.6602292060852051, "learning_rate": 3.360936330741563e-06, "loss": 0.33426642417907715, "step": 836 }, { "epoch": 3.3386454183266934, "grad_norm": 0.5026458501815796, "learning_rate": 3.329728556050219e-06, "loss": 0.41616302728652954, "step": 838 }, { "epoch": 3.346613545816733, "grad_norm": 3.4541831016540527, "learning_rate": 3.2988541947937948e-06, "loss": 0.07192525267601013, "step": 840 }, { "epoch": 3.354581673306773, "grad_norm": 0.48100268840789795, "learning_rate": 3.2683145890273803e-06, "loss": 0.2855004668235779, "step": 842 }, { "epoch": 3.362549800796813, "grad_norm": 0.5678504705429077, "learning_rate": 3.2381110662548244e-06, "loss": 0.43228018283843994, "step": 844 }, { "epoch": 3.3705179282868527, "grad_norm": 0.24944768846035004, "learning_rate": 3.208244939371029e-06, "loss": 0.5930905342102051, "step": 846 }, { "epoch": 3.3784860557768925, "grad_norm": 0.2541601359844208, "learning_rate": 3.178717506604878e-06, "loss": 0.5573995113372803, "step": 848 }, { "epoch": 3.3864541832669324, "grad_norm": 0.4352867901325226, "learning_rate": 3.1495300514628137e-06, "loss": 0.4143456220626831, "step": 850 }, { "epoch": 3.394422310756972, "grad_norm": 0.27721530199050903, "learning_rate": 3.120683842673029e-06, "loss": 0.5134739875793457, "step": 852 }, { "epoch": 3.402390438247012, "grad_norm": 0.2205602526664734, "learning_rate": 3.092180134130341e-06, "loss": 0.3087632358074188, "step": 854 }, { "epoch": 3.410358565737052, "grad_norm": 0.3095087707042694, "learning_rate": 3.064020164841661e-06, "loss": 0.46302488446235657, "step": 856 }, { "epoch": 3.4183266932270917, "grad_norm": 0.3580918312072754, "learning_rate": 3.03620515887216e-06, "loss": 0.4601234793663025, "step": 858 }, { "epoch": 3.4262948207171315, "grad_norm": 0.4854097366333008, "learning_rate": 3.0087363252920392e-06, "loss": 0.5634459257125854, "step": 860 }, { "epoch": 3.4342629482071714, "grad_norm": 0.24722632765769958, "learning_rate": 2.9816148581239945e-06, "loss": 0.3312654495239258, "step": 862 }, { "epoch": 3.442231075697211, "grad_norm": 0.8358548283576965, "learning_rate": 2.954841936291304e-06, "loss": 0.23872403800487518, "step": 864 }, { "epoch": 3.450199203187251, "grad_norm": 0.3561617136001587, "learning_rate": 2.9284187235665706e-06, "loss": 0.4579213261604309, "step": 866 }, { "epoch": 3.458167330677291, "grad_norm": 0.2745280861854553, "learning_rate": 2.902346368521161e-06, "loss": 0.38387465476989746, "step": 868 }, { "epoch": 3.4661354581673307, "grad_norm": 0.33510804176330566, "learning_rate": 2.8766260044752596e-06, "loss": 0.3727482557296753, "step": 870 }, { "epoch": 3.4741035856573705, "grad_norm": 0.05946040898561478, "learning_rate": 2.851258749448613e-06, "loss": 0.336728572845459, "step": 872 }, { "epoch": 3.4820717131474104, "grad_norm": 0.08459708839654922, "learning_rate": 2.8262457061119275e-06, "loss": 0.31364670395851135, "step": 874 }, { "epoch": 3.49003984063745, "grad_norm": 0.24611854553222656, "learning_rate": 2.801587961738936e-06, "loss": 0.26714128255844116, "step": 876 }, { "epoch": 3.49800796812749, "grad_norm": 0.3433525860309601, "learning_rate": 2.7772865881591487e-06, "loss": 0.3233880400657654, "step": 878 }, { "epoch": 3.50597609561753, "grad_norm": 0.077357217669487, "learning_rate": 2.7533426417112463e-06, "loss": 0.1428777575492859, "step": 880 }, { "epoch": 3.5139442231075697, "grad_norm": 0.23806530237197876, "learning_rate": 2.729757163197175e-06, "loss": 0.1798655092716217, "step": 882 }, { "epoch": 3.5219123505976095, "grad_norm": 0.41716670989990234, "learning_rate": 2.706531177836896e-06, "loss": 0.04974370449781418, "step": 884 }, { "epoch": 3.5298804780876494, "grad_norm": 0.7920284271240234, "learning_rate": 2.683665695223827e-06, "loss": 0.46149638295173645, "step": 886 }, { "epoch": 3.537848605577689, "grad_norm": 0.3813696801662445, "learning_rate": 2.661161709280954e-06, "loss": 0.47457778453826904, "step": 888 }, { "epoch": 3.545816733067729, "grad_norm": 0.4823150932788849, "learning_rate": 2.6390201982176284e-06, "loss": 0.2846560478210449, "step": 890 }, { "epoch": 3.553784860557769, "grad_norm": 1.2098549604415894, "learning_rate": 2.617242124487048e-06, "loss": 0.3184957206249237, "step": 892 }, { "epoch": 3.5617529880478087, "grad_norm": 0.2593185305595398, "learning_rate": 2.595828434744411e-06, "loss": 0.7096160650253296, "step": 894 }, { "epoch": 3.5697211155378485, "grad_norm": 0.10369162261486053, "learning_rate": 2.574780059805779e-06, "loss": 0.10589734464883804, "step": 896 }, { "epoch": 3.5776892430278884, "grad_norm": 0.26918283104896545, "learning_rate": 2.5540979146076145e-06, "loss": 0.2939029335975647, "step": 898 }, { "epoch": 3.585657370517928, "grad_norm": 0.2926011383533478, "learning_rate": 2.5337828981669966e-06, "loss": 0.09356319904327393, "step": 900 }, { "epoch": 3.593625498007968, "grad_norm": 1.341439962387085, "learning_rate": 2.513835893542561e-06, "loss": 0.09488323330879211, "step": 902 }, { "epoch": 3.601593625498008, "grad_norm": 0.47240838408470154, "learning_rate": 2.494257767796101e-06, "loss": 0.3548218905925751, "step": 904 }, { "epoch": 3.6095617529880477, "grad_norm": 0.49076366424560547, "learning_rate": 2.475049371954888e-06, "loss": 0.2988426685333252, "step": 906 }, { "epoch": 3.6175298804780875, "grad_norm": 0.2681836783885956, "learning_rate": 2.4562115409746662e-06, "loss": 0.5401598215103149, "step": 908 }, { "epoch": 3.6254980079681274, "grad_norm": 0.406819611787796, "learning_rate": 2.4377450937033753e-06, "loss": 0.4441235661506653, "step": 910 }, { "epoch": 3.633466135458167, "grad_norm": 0.05496419966220856, "learning_rate": 2.419650832845541e-06, "loss": 0.019690319895744324, "step": 912 }, { "epoch": 3.641434262948207, "grad_norm": 0.29483741521835327, "learning_rate": 2.40192954492739e-06, "loss": 0.4060436189174652, "step": 914 }, { "epoch": 3.649402390438247, "grad_norm": 0.4651680290699005, "learning_rate": 2.3845820002626623e-06, "loss": 0.4076462984085083, "step": 916 }, { "epoch": 3.6573705179282867, "grad_norm": 2.9567272663116455, "learning_rate": 2.3676089529191234e-06, "loss": 0.047276318073272705, "step": 918 }, { "epoch": 3.6653386454183265, "grad_norm": 0.32289329171180725, "learning_rate": 2.3510111406857915e-06, "loss": 0.5000100135803223, "step": 920 }, { "epoch": 3.6733067729083664, "grad_norm": 0.23058217763900757, "learning_rate": 2.3347892850408575e-06, "loss": 0.06835205107927322, "step": 922 }, { "epoch": 3.681274900398406, "grad_norm": 1.3678746223449707, "learning_rate": 2.3189440911203328e-06, "loss": 0.35598766803741455, "step": 924 }, { "epoch": 3.6892430278884465, "grad_norm": 0.30284255743026733, "learning_rate": 2.3034762476873973e-06, "loss": 0.13118457794189453, "step": 926 }, { "epoch": 3.6972111553784863, "grad_norm": 0.8098158836364746, "learning_rate": 2.2883864271024524e-06, "loss": 0.29144927859306335, "step": 928 }, { "epoch": 3.705179282868526, "grad_norm": 0.131113201379776, "learning_rate": 2.273675285293905e-06, "loss": 0.4039907455444336, "step": 930 }, { "epoch": 3.713147410358566, "grad_norm": 0.34469276666641235, "learning_rate": 2.2593434617296474e-06, "loss": 0.5197895765304565, "step": 932 }, { "epoch": 3.721115537848606, "grad_norm": 0.2677764296531677, "learning_rate": 2.2453915793892665e-06, "loss": 0.23381216824054718, "step": 934 }, { "epoch": 3.7290836653386457, "grad_norm": 0.4345526099205017, "learning_rate": 2.231820244736958e-06, "loss": 0.4805620014667511, "step": 936 }, { "epoch": 3.7370517928286855, "grad_norm": 0.4274682402610779, "learning_rate": 2.2186300476951693e-06, "loss": 0.1564408391714096, "step": 938 }, { "epoch": 3.7450199203187253, "grad_norm": 1.1103200912475586, "learning_rate": 2.2058215616189578e-06, "loss": 0.47250640392303467, "step": 940 }, { "epoch": 3.752988047808765, "grad_norm": 0.2901248037815094, "learning_rate": 2.1933953432710588e-06, "loss": 0.25581350922584534, "step": 942 }, { "epoch": 3.760956175298805, "grad_norm": 0.2037886381149292, "learning_rate": 2.181351932797695e-06, "loss": 0.3167116641998291, "step": 944 }, { "epoch": 3.768924302788845, "grad_norm": 0.36940625309944153, "learning_rate": 2.169691853705094e-06, "loss": 0.6154989004135132, "step": 946 }, { "epoch": 3.7768924302788847, "grad_norm": 0.3643878102302551, "learning_rate": 2.1584156128367303e-06, "loss": 0.3078484535217285, "step": 948 }, { "epoch": 3.7848605577689245, "grad_norm": 0.4483620822429657, "learning_rate": 2.147523700351291e-06, "loss": 0.5290223956108093, "step": 950 }, { "epoch": 3.7928286852589643, "grad_norm": 0.5038286447525024, "learning_rate": 2.137016589701375e-06, "loss": 0.5246944427490234, "step": 952 }, { "epoch": 3.800796812749004, "grad_norm": 0.3047266900539398, "learning_rate": 2.126894737612914e-06, "loss": 0.29258349537849426, "step": 954 }, { "epoch": 3.808764940239044, "grad_norm": 0.3544226884841919, "learning_rate": 2.117158584065313e-06, "loss": 0.3819803297519684, "step": 956 }, { "epoch": 3.816733067729084, "grad_norm": 0.9558009505271912, "learning_rate": 2.107808552272329e-06, "loss": 0.25099891424179077, "step": 958 }, { "epoch": 3.8247011952191237, "grad_norm": 0.3349020779132843, "learning_rate": 2.0988450486636745e-06, "loss": 0.17486253380775452, "step": 960 }, { "epoch": 3.8326693227091635, "grad_norm": 0.13526098430156708, "learning_rate": 2.090268462867351e-06, "loss": 0.31952333450317383, "step": 962 }, { "epoch": 3.8406374501992033, "grad_norm": 0.412202388048172, "learning_rate": 2.0820791676927093e-06, "loss": 0.6047512292861938, "step": 964 }, { "epoch": 3.848605577689243, "grad_norm": 0.3296831250190735, "learning_rate": 2.0742775191142496e-06, "loss": 0.16787327826023102, "step": 966 }, { "epoch": 3.856573705179283, "grad_norm": 0.28071603178977966, "learning_rate": 2.066863856256143e-06, "loss": 0.3841116726398468, "step": 968 }, { "epoch": 3.864541832669323, "grad_norm": 0.29851338267326355, "learning_rate": 2.0598385013774933e-06, "loss": 0.346584677696228, "step": 970 }, { "epoch": 3.8725099601593627, "grad_norm": 0.03955311328172684, "learning_rate": 2.053201759858327e-06, "loss": 0.2920938730239868, "step": 972 }, { "epoch": 3.8804780876494025, "grad_norm": 0.051783155649900436, "learning_rate": 2.0469539201863224e-06, "loss": 0.2272939682006836, "step": 974 }, { "epoch": 3.8884462151394423, "grad_norm": 0.3298843204975128, "learning_rate": 2.0410952539442624e-06, "loss": 0.5179523229598999, "step": 976 }, { "epoch": 3.896414342629482, "grad_norm": 0.28545433282852173, "learning_rate": 2.0356260157982393e-06, "loss": 0.27209949493408203, "step": 978 }, { "epoch": 3.904382470119522, "grad_norm": 1.0891438722610474, "learning_rate": 2.030546443486575e-06, "loss": 0.24100713431835175, "step": 980 }, { "epoch": 3.912350597609562, "grad_norm": 0.6865116357803345, "learning_rate": 2.0258567578094947e-06, "loss": 0.18800026178359985, "step": 982 }, { "epoch": 3.9203187250996017, "grad_norm": 0.24787557125091553, "learning_rate": 2.0215571626195242e-06, "loss": 0.5200425982475281, "step": 984 }, { "epoch": 3.9282868525896415, "grad_norm": 0.6841551065444946, "learning_rate": 2.0176478448126306e-06, "loss": 0.1371404379606247, "step": 986 }, { "epoch": 3.9362549800796813, "grad_norm": 1.6476190090179443, "learning_rate": 2.014128974320099e-06, "loss": 0.41096165776252747, "step": 988 }, { "epoch": 3.944223107569721, "grad_norm": 0.20494024455547333, "learning_rate": 2.011000704101143e-06, "loss": 0.30098965764045715, "step": 990 }, { "epoch": 3.952191235059761, "grad_norm": 0.48796623945236206, "learning_rate": 2.00826317013626e-06, "loss": 0.5071312785148621, "step": 992 }, { "epoch": 3.960159362549801, "grad_norm": 0.33370301127433777, "learning_rate": 2.0059164914213175e-06, "loss": 0.13360963761806488, "step": 994 }, { "epoch": 3.9681274900398407, "grad_norm": 0.24733327329158783, "learning_rate": 2.00396076996238e-06, "loss": 0.41967302560806274, "step": 996 }, { "epoch": 3.9760956175298805, "grad_norm": 0.22083163261413574, "learning_rate": 2.0023960907712782e-06, "loss": 0.3552241027355194, "step": 998 }, { "epoch": 3.9840637450199203, "grad_norm": 0.4792640805244446, "learning_rate": 2.0012225218619097e-06, "loss": 0.2334318608045578, "step": 1000 }, { "epoch": 3.99203187250996, "grad_norm": 0.2573681175708771, "learning_rate": 2.0004401142472857e-06, "loss": 0.5154892802238464, "step": 1002 }, { "epoch": 4.0, "grad_norm": 0.1436181664466858, "learning_rate": 2.000048901937313e-06, "loss": 0.12288407981395721, "step": 1004 }, { "epoch": 4.0, "step": 1004, "total_flos": 4.038502240003031e+18, "train_loss": 0.7417308912200637, "train_runtime": 11316.072, "train_samples_per_second": 5.323, "train_steps_per_second": 0.089 } ], "logging_steps": 2, "max_steps": 1004, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 99999, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4.038502240003031e+18, "train_batch_size": 3, "trial_name": null, "trial_params": null }